3098 lines
587 KiB
Plaintext
3098 lines
587 KiB
Plaintext
[2026-04-16 10:31:52,083] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:135] baseline 0.000GB ()
|
||
[2026-04-16 10:31:52,086] [INFO] [axolotl.cli.config.load_cfg:341] [PID:135] config:
|
||
{
|
||
"activation_offloading": false,
|
||
"axolotl_config_path": "./config.yaml",
|
||
"base_model": "Qwen/Qwen2.5-7B",
|
||
"base_model_config": "Qwen/Qwen2.5-7B",
|
||
"batch_size": 16,
|
||
"bf16": true,
|
||
"capabilities": {
|
||
"bf16": true,
|
||
"compute_capability": "sm_80",
|
||
"fp8": false,
|
||
"n_gpu": 1,
|
||
"n_node": 1,
|
||
"tf32": true
|
||
},
|
||
"context_parallel_size": 1,
|
||
"dataloader_num_workers": 1,
|
||
"dataloader_pin_memory": true,
|
||
"dataloader_prefetch_factor": 256,
|
||
"dataset_num_proc": 96,
|
||
"dataset_prepared_path": "./prepared_data",
|
||
"datasets": [
|
||
{
|
||
"path": "Bossssss/medqa-dpo-idk",
|
||
"split": "train",
|
||
"type": "passthrough"
|
||
}
|
||
],
|
||
"ddp": false,
|
||
"device": "cuda:0",
|
||
"dion_rank_fraction": 1.0,
|
||
"dion_rank_multiple_of": 1,
|
||
"eaft_alpha": 1.0,
|
||
"eaft_k": 20,
|
||
"env_capabilities": {
|
||
"torch_version": "2.9.1"
|
||
},
|
||
"eval_batch_size": 2,
|
||
"eval_causal_lm_metrics": [
|
||
"sacrebleu",
|
||
"comet",
|
||
"ter",
|
||
"chrf"
|
||
],
|
||
"eval_max_new_tokens": 128,
|
||
"eval_steps": 100,
|
||
"eval_strategy": "steps",
|
||
"eval_table_size": 0,
|
||
"experimental_skip_move_to_device": true,
|
||
"flash_attention": true,
|
||
"fp16": false,
|
||
"generate_samples": false,
|
||
"generation_do_sample": true,
|
||
"generation_max_new_tokens": 50,
|
||
"generation_prompt_ratio": 0.5,
|
||
"generation_temperature": 0.7,
|
||
"gradient_accumulation_steps": 8,
|
||
"gradient_checkpointing": true,
|
||
"greater_is_better": false,
|
||
"include_tkps": true,
|
||
"is_falcon_derived_model": false,
|
||
"is_llama_derived_model": false,
|
||
"is_mistral_derived_model": false,
|
||
"layer_offloading": false,
|
||
"learning_rate": 5e-05,
|
||
"lisa_layers_attribute": "model.layers",
|
||
"load_best_model_at_end": true,
|
||
"load_in_4bit": false,
|
||
"load_in_8bit": false,
|
||
"local_rank": 0,
|
||
"logging_steps": 10,
|
||
"lora_dropout": 0.0,
|
||
"loraplus_lr_embedding": 1e-06,
|
||
"lr_scheduler": "cosine",
|
||
"max_grad_norm": 1.0,
|
||
"mean_resizing_embeddings": false,
|
||
"merge_method": "memory_efficient",
|
||
"metric_for_best_model": "eval_loss",
|
||
"micro_batch_size": 2,
|
||
"model_config_type": "qwen2",
|
||
"num_epochs": 3.0,
|
||
"num_generation_samples": 3,
|
||
"optimizer": "adamw_bnb_8bit",
|
||
"otel_metrics_host": "localhost",
|
||
"otel_metrics_port": 8000,
|
||
"output_dir": "kikiyaa/qwen-dpo-finetuned-ver2",
|
||
"pretrain_multipack_attn": true,
|
||
"profiler_steps_start": 0,
|
||
"qlora_sharded_model_loading": false,
|
||
"quantize_moe_experts": false,
|
||
"ray_num_workers": 1,
|
||
"resources_per_worker": {
|
||
"GPU": 1
|
||
},
|
||
"rl": "dpo",
|
||
"rl_beta": 0.1,
|
||
"sample_packing": false,
|
||
"sample_packing_bin_size": 200,
|
||
"sample_packing_group_size": 100000,
|
||
"save_only_model": false,
|
||
"save_safetensors": true,
|
||
"save_steps": 100,
|
||
"save_total_limit": 3,
|
||
"seed": 42,
|
||
"sequence_len": 2048,
|
||
"shuffle_before_merging_datasets": false,
|
||
"shuffle_merged_datasets": true,
|
||
"skip_prepare_dataset": false,
|
||
"streaming_multipack_buffer_size": 10000,
|
||
"strict": false,
|
||
"tensor_parallel_size": 1,
|
||
"tf32": true,
|
||
"tiled_mlp_use_original_mlp": true,
|
||
"tokenizer_config": "Qwen/Qwen2.5-7B",
|
||
"tokenizer_save_jinja_files": true,
|
||
"tokenizer_type": "AutoTokenizer",
|
||
"torch_dtype": "torch.bfloat16",
|
||
"train_on_inputs": false,
|
||
"trl": {
|
||
"async_prefetch": false,
|
||
"log_completions": false,
|
||
"mask_truncated_completions": false,
|
||
"ref_model_mixup_alpha": 0.9,
|
||
"ref_model_sync_steps": 64,
|
||
"replay_buffer_size": 0,
|
||
"replay_recompute_logps": true,
|
||
"reroll_max_groups": 1,
|
||
"reroll_start_fraction": 1.0,
|
||
"reward_num_workers": 1,
|
||
"scale_rewards": true,
|
||
"skip_zero_advantage_batches": true,
|
||
"sync_ref_model": false,
|
||
"use_data_producer": false,
|
||
"use_vllm": false,
|
||
"vllm_lora_sync": false,
|
||
"vllm_server_host": "0.0.0.0",
|
||
"vllm_server_port": 8000
|
||
},
|
||
"type_of_model": "AutoModelForCausalLM",
|
||
"use_otel_metrics": false,
|
||
"use_ray": false,
|
||
"val_set_size": 0.05,
|
||
"vllm": {
|
||
"device": "auto",
|
||
"dtype": "auto",
|
||
"gpu_memory_utilization": 0.9,
|
||
"host": "0.0.0.0",
|
||
"port": 8000
|
||
},
|
||
"warmup_ratio": 0.1,
|
||
"weight_decay": 0.01,
|
||
"world_size": 1
|
||
}
|
||
[2026-04-16 10:31:57,826] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:135] EOS: 151643 / <|endoftext|>
|
||
[2026-04-16 10:31:57,826] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:135] BOS: None / None
|
||
[2026-04-16 10:31:57,826] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:135] PAD: 151643 / <|endoftext|>
|
||
[2026-04-16 10:31:57,826] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:135] UNK: None / None
|
||
[2026-04-16 10:31:57,831] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:135] Loading prepared dataset from disk at prepared_data/b845853b1ffa0f92dd415602f19f08af...
|
||
[2026-04-16 10:31:57,902] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:135] loading tokenizer... Qwen/Qwen2.5-7B
|
||
[2026-04-16 10:31:59,556] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:135] EOS: 151643 / <|endoftext|>
|
||
[2026-04-16 10:31:59,556] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:135] BOS: None / None
|
||
[2026-04-16 10:31:59,556] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:135] PAD: 151643 / <|endoftext|>
|
||
[2026-04-16 10:31:59,556] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:135] UNK: None / None
|
||
[2026-04-16 10:31:59,556] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:135] Loading model
|
||
[2026-04-16 10:31:59,777] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:75] [PID:135] Patched OptimState8bit for torch.compile compatibility
|
||
[2026-04-16 10:31:59,778] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:122] [PID:135] Patched OptimState4bit for torch.compile compatibility
|
||
[2026-04-16 10:31:59,778] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:154] [PID:135] Patched OptimStateFp8 for torch.compile compatibility
|
||
[2026-04-16 10:31:59,795] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:135] Patched Trainer.evaluation_loop with nanmean loss calculation
|
||
[2026-04-16 10:31:59,798] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:135] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
|
||
[2026-04-16 10:32:00,017] [INFO] [axolotl.loaders.patch_manager._apply_trl_trainer_utils_patches:852] [PID:135] Patched trl.trainer.utils with Triton selective_log_softmax and entropy_from_logits
|
||
|
||
Fetching 4 files: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Fetching 4 files: 25%|██▌ | 1/4 [02:20<07:01, 140.64s/it]
|
||
Fetching 4 files: 75%|███████▌ | 3/4 [02:22<00:37, 37.05s/it]
|
||
Fetching 4 files: 100%|██████████| 4/4 [02:22<00:00, 35.56s/it]
|
||
|
||
Loading weights: 0%| | 0/339 [00:00<?, ?it/s]
|
||
Loading weights: 100%|██████████| 339/339 [00:00<00:00, 5017.02it/s]
|
||
[2026-04-16 10:34:26,588] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:135] Converting modules to torch.bfloat16
|
||
[2026-04-16 10:34:27,756] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:135] Memory usage after model load 0.000GB ()
|
||
[2026-04-16 10:34:28,584] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:75] [PID:135] Patched OptimState8bit for torch.compile compatibility
|
||
[2026-04-16 10:34:28,584] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:122] [PID:135] Patched OptimState4bit for torch.compile compatibility
|
||
[2026-04-16 10:34:28,584] [DEBUG] [axolotl.monkeypatch.torchao_optim.patch_torchao_optim_state_8bit:154] [PID:135] Patched OptimStateFp8 for torch.compile compatibility
|
||
[2026-04-16 10:34:28,584] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:51] [PID:135] Trainer.evaluation_loop already patched
|
||
[2026-04-16 10:34:28,584] [INFO] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:110] [PID:135] Trainer._maybe_log_save_evaluate already patched
|
||
[2026-04-16 10:34:28,584] [INFO] [axolotl.loaders.patch_manager._apply_trl_trainer_utils_patches:852] [PID:135] Patched trl.trainer.utils with Triton selective_log_softmax and entropy_from_logits
|
||
|
||
Loading weights: 0%| | 0/339 [00:00<?, ?it/s]
|
||
Loading weights: 100%|██████████| 339/339 [00:00<00:00, 4331.59it/s]
|
||
[2026-04-16 10:34:30,928] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:135] Converting modules to torch.bfloat16
|
||
[2026-04-16 10:34:32,130] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:135] Memory usage after model load 0.000GB ()
|
||
|
||
Adding EOS to train dataset (num_proc=96): 0%| | 0/5399 [00:00<?, ? examples/s]
|
||
Adding EOS to train dataset (num_proc=96): 1%| | 57/5399 [00:06<09:40, 9.20 examples/s]
|
||
Adding EOS to train dataset (num_proc=96): 5%|▌ | 285/5399 [00:06<01:24, 60.34 examples/s]
|
||
Adding EOS to train dataset (num_proc=96): 18%|█▊ | 969/5399 [00:06<00:16, 271.57 examples/s]
|
||
Adding EOS to train dataset (num_proc=96): 76%|███████▌ | 4111/5399 [00:06<00:00, 1596.87 examples/s]
|
||
Adding EOS to train dataset (num_proc=96): 100%|██████████| 5399/5399 [00:07<00:00, 700.21 examples/s]
|
||
|
||
Tokenizing train dataset (num_proc=96): 0%| | 0/5399 [00:00<?, ? examples/s][2026-04-16 10:34:51,717] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:672] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:51,764] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:672] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:51,764] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:672] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:51,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:672] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:51,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:672] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 1%| | 27/5399 [00:08<27:02, 3.31 examples/s][2026-04-16 10:34:52,858] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:673] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:52,859] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:673] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:52,899] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:673] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:52,899] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:673] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 2%|▏ | 85/5399 [00:09<07:52, 11.24 examples/s][2026-04-16 10:34:52,923] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:673] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,960] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,960] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,964] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,970] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,970] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:53,978] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:54,007] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:54,007] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 3%|▎ | 139/5399 [00:10<04:47, 18.29 examples/s][2026-04-16 10:34:54,014] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:54,014] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:54,032] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:54,032] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:674] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,060] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,061] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,065] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,108] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,108] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 4%|▎ | 198/5399 [00:11<03:22, 25.71 examples/s][2026-04-16 10:34:55,126] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:55,126] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:675] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,206] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,206] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,208] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,208] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,241] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,241] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 5%|▍ | 254/5399 [00:12<02:44, 31.37 examples/s][2026-04-16 10:34:56,254] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:56,254] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:676] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,314] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,314] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,316] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,316] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 6%|▌ | 311/5399 [00:13<02:19, 36.35 examples/s][2026-04-16 10:34:57,356] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,357] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,376] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:57,377] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:677] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,407] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,407] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,412] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,412] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 7%|▋ | 367/5399 [00:14<02:05, 39.95 examples/s][2026-04-16 10:34:58,479] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:58,500] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:678] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:59,541] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:679] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:59,541] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:679] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:59,568] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:679] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:34:59,568] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:679] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 8%|▊ | 425/5399 [00:15<01:54, 43.41 examples/s][2026-04-16 10:34:59,584] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:679] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,615] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,615] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,627] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,627] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,631] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,648] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,648] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,652] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,672] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,672] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 9%|▉ | 481/5399 [00:17<01:48, 45.46 examples/s][2026-04-16 10:35:00,703] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,703] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,714] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:00,714] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:680] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,765] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,766] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,775] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,775] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,797] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,797] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 10%|▉ | 538/5399 [00:18<01:43, 46.82 examples/s][2026-04-16 10:35:01,822] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,822] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,837] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,843] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:01,843] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:681] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,864] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,878] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,894] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,894] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,905] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,905] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 11%|█ | 598/5399 [00:19<01:38, 48.97 examples/s][2026-04-16 10:35:02,947] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,948] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,951] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:02,951] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:682] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:03,960] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:03,962] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:03,982] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:03,982] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,000] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,000] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,006] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,006] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,008] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,009] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 12%|█▏ | 654/5399 [00:20<01:35, 49.61 examples/s][2026-04-16 10:35:04,028] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:04,028] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:683] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,066] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,066] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,092] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,092] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,094] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:05,094] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:684] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 13%|█▎ | 711/5399 [00:21<01:33, 50.22 examples/s][2026-04-16 10:35:06,168] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,168] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,172] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,175] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,175] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,207] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,207] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,215] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,215] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 14%|█▍ | 767/5399 [00:22<01:32, 50.28 examples/s][2026-04-16 10:35:06,244] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:06,244] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:685] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,269] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,270] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,271] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,272] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,294] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,294] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,303] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 15%|█▌ | 825/5399 [00:23<01:29, 51.13 examples/s][2026-04-16 10:35:07,324] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:07,324] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:686] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,359] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,360] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,374] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,374] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,384] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,384] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,386] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,386] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,392] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,393] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,415] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,415] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,417] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,417] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 16%|█▋ | 880/5399 [00:24<01:29, 50.74 examples/s][2026-04-16 10:35:08,424] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,424] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:08,445] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:687] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,490] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,490] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,492] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,499] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,499] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 17%|█▋ | 937/5399 [00:25<01:27, 50.97 examples/s][2026-04-16 10:35:09,536] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,536] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:09,553] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:688] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,590] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,591] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,593] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,594] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 18%|█▊ | 994/5399 [00:27<01:25, 51.23 examples/s][2026-04-16 10:35:10,644] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,644] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,657] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:10,657] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:689] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,635] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,673] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,673] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 19%|█▉ | 1052/5399 [00:28<01:23, 52.30 examples/s][2026-04-16 10:35:11,697] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,697] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,710] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:11,710] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:690] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:12,809] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:12,810] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 21%|██ | 1109/5399 [00:29<01:23, 51.61 examples/s][2026-04-16 10:35:12,823] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:12,823] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:12,849] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:12,849] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:691] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,876] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,876] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,879] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,879] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,904] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,904] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,906] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,906] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:13,922] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:692] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 22%|██▏ | 1167/5399 [00:30<01:21, 51.87 examples/s][2026-04-16 10:35:15,019] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:693] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 23%|██▎ | 1221/5399 [00:31<01:21, 51.00 examples/s][2026-04-16 10:35:15,069] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:693] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,040] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,040] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,074] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,078] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,078] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 24%|██▍ | 1283/5399 [00:32<01:17, 53.29 examples/s][2026-04-16 10:35:16,111] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:16,111] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:694] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:17,180] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:17,180] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 25%|██▍ | 1338/5399 [00:33<01:18, 51.83 examples/s][2026-04-16 10:35:17,217] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:17,217] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:17,246] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:17,246] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:695] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,262] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,262] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,284] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,284] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,294] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 26%|██▌ | 1392/5399 [00:34<01:18, 51.01 examples/s][2026-04-16 10:35:18,320] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,333] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:18,333] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:696] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,354] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,369] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,369] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 27%|██▋ | 1449/5399 [00:35<01:16, 51.38 examples/s][2026-04-16 10:35:19,412] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,418] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,418] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:19,420] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:697] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,436] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,436] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,440] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,440] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,457] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,461] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,467] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,467] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,488] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,488] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,493] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:20,493] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 28%|██▊ | 1504/5399 [00:36<01:16, 51.10 examples/s][2026-04-16 10:35:20,515] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:698] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,536] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,539] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,539] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,573] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,573] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,582] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,582] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 29%|██▉ | 1563/5399 [00:37<01:13, 51.99 examples/s][2026-04-16 10:35:21,592] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,592] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,603] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,603] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,610] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:21,610] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:699] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,636] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,658] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,658] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,680] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,680] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 30%|██▉ | 1617/5399 [00:39<01:14, 51.09 examples/s][2026-04-16 10:35:22,691] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,691] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,693] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,693] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,717] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:22,717] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:700] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,757] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,758] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,766] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 31%|███ | 1673/5399 [00:40<01:12, 51.34 examples/s][2026-04-16 10:35:23,770] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,770] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,774] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,774] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:23,785] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:701] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,843] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,867] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 32%|███▏ | 1728/5399 [00:41<01:12, 50.65 examples/s][2026-04-16 10:35:24,892] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,892] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,904] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,904] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,913] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:24,913] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:702] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:25,977] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:25,977] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:25,996] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:25,996] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,005] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,006] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,016] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,016] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,017] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,017] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,021] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,021] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 33%|███▎ | 1785/5399 [00:42<01:11, 50.29 examples/s][2026-04-16 10:35:26,041] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,041] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,058] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:26,058] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:703] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,090] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,096] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,096] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,097] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,097] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,105] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,105] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,107] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,107] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 34%|███▍ | 1841/5399 [00:43<01:10, 50.45 examples/s][2026-04-16 10:35:27,143] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,151] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,151] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,153] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:27,153] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:704] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:28,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:705] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:28,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:705] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:28,219] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:705] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:28,219] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:705] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 35%|███▌ | 1897/5399 [00:44<01:09, 50.67 examples/s][2026-04-16 10:35:28,254] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:705] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,236] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,236] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,279] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,279] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,283] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,283] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 36%|███▌ | 1953/5399 [00:45<01:07, 51.31 examples/s][2026-04-16 10:35:29,310] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,310] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,323] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,323] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,326] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:29,326] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:706] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,337] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,337] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,385] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,385] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 37%|███▋ | 2009/5399 [00:46<01:06, 51.28 examples/s][2026-04-16 10:35:30,397] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,398] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,412] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:30,412] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:707] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,463] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,495] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,495] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,496] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,506] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,506] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 38%|███▊ | 2066/5399 [00:47<01:05, 51.07 examples/s][2026-04-16 10:35:31,539] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:31,540] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:708] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,575] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,576] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,590] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,590] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,595] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,595] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,606] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,606] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,609] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,609] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,611] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,611] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,616] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,617] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 39%|███▉ | 2120/5399 [00:49<01:05, 50.21 examples/s][2026-04-16 10:35:32,662] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,662] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,670] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:32,670] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:709] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:33,675] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:710] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:33,675] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:710] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:33,728] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:710] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:33,728] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:710] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 40%|████ | 2176/5399 [00:50<01:03, 50.47 examples/s][2026-04-16 10:35:34,819] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,819] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,829] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,829] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,830] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,830] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,832] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,833] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,839] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,839] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,851] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:34,851] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:711] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 41%|████▏ | 2230/5399 [00:51<01:04, 49.45 examples/s][2026-04-16 10:35:35,901] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,901] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,906] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,906] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,917] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,917] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,937] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,937] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 42%|████▏ | 2289/5399 [00:52<01:00, 51.06 examples/s][2026-04-16 10:35:35,945] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,945] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,949] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,949] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,955] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,955] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,963] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,963] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,968] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,968] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,978] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:35,978] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:712] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,009] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,010] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,016] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,016] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,027] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,028] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,055] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:37,055] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:713] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 43%|████▎ | 2347/5399 [00:53<00:59, 51.27 examples/s][2026-04-16 10:35:38,106] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,106] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,115] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,115] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,117] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,117] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,143] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,143] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,155] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,155] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 44%|████▍ | 2400/5399 [00:54<00:59, 50.49 examples/s][2026-04-16 10:35:38,164] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,164] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,165] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,166] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:38,171] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:714] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:39,250] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:715] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 45%|████▌ | 2455/5399 [00:55<00:58, 50.45 examples/s][2026-04-16 10:35:39,250] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:715] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:39,255] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:715] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:39,285] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:715] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:39,285] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:715] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 47%|████▋ | 2513/5399 [00:56<00:56, 51.34 examples/s][2026-04-16 10:35:40,342] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:716] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:40,342] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:716] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,395] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,395] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,422] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,422] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,424] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,424] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,445] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,445] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,446] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,446] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 48%|████▊ | 2568/5399 [00:57<00:55, 50.68 examples/s][2026-04-16 10:35:41,468] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,481] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:41,481] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:717] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,443] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,464] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,479] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 49%|████▊ | 2626/5399 [00:58<00:53, 52.08 examples/s][2026-04-16 10:35:42,508] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,508] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,532] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:42,532] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:718] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,598] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,598] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,604] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,604] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,606] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,606] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,620] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,620] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,645] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 50%|████▉ | 2678/5399 [01:00<00:54, 49.98 examples/s][2026-04-16 10:35:43,674] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,674] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,691] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:43,691] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:719] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,700] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,700] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,733] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,733] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,752] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,753] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 51%|█████ | 2734/5399 [01:01<00:53, 50.14 examples/s][2026-04-16 10:35:44,761] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,778] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,778] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,785] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,785] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,794] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,794] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,798] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:44,798] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:720] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,809] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,809] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,822] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,831] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,831] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,833] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,833] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,837] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,838] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,851] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,851] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 52%|█████▏ | 2790/5399 [01:02<00:51, 50.18 examples/s][2026-04-16 10:35:45,881] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,881] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,883] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,896] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:45,896] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:721] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:46,950] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:722] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:46,951] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:722] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 53%|█████▎ | 2848/5399 [01:03<00:50, 50.31 examples/s][2026-04-16 10:35:48,111] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,111] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,141] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 54%|█████▍ | 2904/5399 [01:04<00:49, 50.09 examples/s][2026-04-16 10:35:48,153] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,153] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,158] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,158] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:48,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:723] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:49,186] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:49,186] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 55%|█████▍ | 2961/5399 [01:05<00:48, 50.65 examples/s][2026-04-16 10:35:49,264] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:49,264] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:49,266] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:49,266] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:724] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,293] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,293] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,299] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,299] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,308] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,329] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 56%|█████▌ | 3016/5399 [01:06<00:47, 50.33 examples/s][2026-04-16 10:35:50,347] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,347] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,357] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:50,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:725] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,395] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,395] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,400] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,400] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,405] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,405] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,419] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,419] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,444] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,444] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,446] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,448] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,448] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 57%|█████▋ | 3072/5399 [01:07<00:46, 50.48 examples/s][2026-04-16 10:35:51,459] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,459] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,461] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,461] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,484] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:51,484] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:726] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,484] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,484] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,487] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,487] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,498] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,498] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,531] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,532] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,535] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,535] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 58%|█████▊ | 3129/5399 [01:08<00:44, 50.88 examples/s][2026-04-16 10:35:52,557] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,557] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,564] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,564] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,581] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:52,581] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:727] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,584] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,585] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,609] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,609] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,627] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,632] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,633] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,634] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,634] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,640] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:53,640] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:728] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 59%|█████▉ | 3186/5399 [01:10<00:43, 51.20 examples/s][2026-04-16 10:35:54,659] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:54,659] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:54,696] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:54,696] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:54,714] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:54,714] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 60%|██████ | 3241/5399 [01:11<00:42, 51.28 examples/s][2026-04-16 10:35:54,733] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:729] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,765] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,765] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,787] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,787] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,796] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,796] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,802] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,819] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:55,823] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:730] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 61%|██████ | 3297/5399 [01:12<00:41, 50.82 examples/s][2026-04-16 10:35:56,930] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 62%|██████▏ | 3352/5399 [01:13<00:40, 50.73 examples/s][2026-04-16 10:35:56,937] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:56,937] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:56,942] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:56,943] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:56,947] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:56,947] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:731] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:57,980] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:57,998] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:57,998] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:58,008] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:58,008] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 63%|██████▎ | 3409/5399 [01:14<00:38, 51.21 examples/s][2026-04-16 10:35:58,028] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:58,028] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:732] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,050] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,050] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,053] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,053] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,064] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,064] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,070] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,081] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,099] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,099] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 64%|██████▍ | 3465/5399 [01:15<00:37, 51.34 examples/s][2026-04-16 10:35:59,104] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,113] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,113] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,126] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,137] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:35:59,137] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:733] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,158] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,161] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,199] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 65%|██████▌ | 3519/5399 [01:16<00:37, 50.70 examples/s][2026-04-16 10:36:00,207] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,207] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,209] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,209] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,216] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,216] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,235] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:00,235] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:734] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:01,286] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:735] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:01,292] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:735] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:01,307] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:735] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:01,307] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:735] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 66%|██████▋ | 3578/5399 [01:17<00:35, 51.04 examples/s][2026-04-16 10:36:01,342] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:735] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:02,416] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:02,416] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 67%|██████▋ | 3632/5399 [01:18<00:35, 50.49 examples/s][2026-04-16 10:36:02,453] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:02,453] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:02,479] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:02,479] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:736] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,492] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,492] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,504] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,504] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,519] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,519] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,521] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,521] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 68%|██████▊ | 3688/5399 [01:19<00:33, 50.62 examples/s][2026-04-16 10:36:03,545] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:03,545] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:737] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,610] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,611] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,625] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,625] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,631] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,631] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,633] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,645] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,645] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,663] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,663] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 69%|██████▉ | 3743/5399 [01:21<00:33, 49.98 examples/s][2026-04-16 10:36:04,693] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,693] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,701] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:04,701] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:738] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,716] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,716] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,724] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,724] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,743] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,743] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,745] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,745] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,762] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:05,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 70%|███████ | 3801/5399 [01:22<00:31, 50.73 examples/s][2026-04-16 10:36:05,786] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:739] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,794] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,794] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,802] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,802] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,830] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,830] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,836] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,836] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,843] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 71%|███████▏ | 3856/5399 [01:23<00:30, 50.77 examples/s][2026-04-16 10:36:06,862] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,862] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,868] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,868] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,873] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,876] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,889] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:06,889] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:740] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,907] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,907] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,946] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,970] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,970] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 72%|███████▏ | 3913/5399 [01:24<00:29, 50.80 examples/s][2026-04-16 10:36:07,976] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,976] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,989] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,989] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,994] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,994] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,998] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:07,998] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:741] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,015] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,015] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,030] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,030] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,049] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,049] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,060] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 73%|███████▎ | 3968/5399 [01:25<00:28, 50.64 examples/s][2026-04-16 10:36:09,098] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:09,098] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:742] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,119] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,119] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,132] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,132] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 75%|███████▍ | 4026/5399 [01:26<00:26, 51.33 examples/s][2026-04-16 10:36:10,165] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,165] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,178] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,179] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,179] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,187] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,187] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,200] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:10,200] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:743] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:11,266] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:744] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:11,268] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:744] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 76%|███████▌ | 4082/5399 [01:27<00:25, 51.13 examples/s][2026-04-16 10:36:12,309] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:12,309] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 77%|███████▋ | 4135/5399 [01:28<00:25, 50.35 examples/s][2026-04-16 10:36:12,369] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:12,369] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:12,376] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:12,376] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:745] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,470] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,471] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,513] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,513] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 78%|███████▊ | 4192/5399 [01:29<00:24, 49.97 examples/s][2026-04-16 10:36:13,527] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,527] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,537] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:13,537] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:746] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,586] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,586] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,592] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,592] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,611] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,611] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,620] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,620] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 79%|███████▊ | 4249/5399 [01:31<00:22, 50.57 examples/s][2026-04-16 10:36:14,630] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,630] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,637] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,637] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:14,646] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:747] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,680] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,681] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,702] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,703] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,727] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,727] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,730] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,739] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,739] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 80%|███████▉ | 4304/5399 [01:32<00:21, 50.14 examples/s][2026-04-16 10:36:15,745] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,745] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:15,758] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:748] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 81%|████████ | 4359/5399 [01:33<00:20, 50.19 examples/s][2026-04-16 10:36:16,840] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:749] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:16,872] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:749] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:16,872] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:749] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 82%|████████▏ | 4417/5399 [01:34<00:19, 50.31 examples/s][2026-04-16 10:36:17,988] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:750] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:17,988] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:750] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:17,992] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:750] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:17,992] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:750] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,049] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,050] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,056] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,056] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,062] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,062] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,067] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,067] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:19,081] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:751] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 83%|████████▎ | 4474/5399 [01:35<00:18, 50.76 examples/s][2026-04-16 10:36:20,130] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,131] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,145] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,145] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,160] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,160] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,164] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,171] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:20,172] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:752] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 84%|████████▍ | 4529/5399 [01:36<00:17, 50.51 examples/s][2026-04-16 10:36:21,206] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,207] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,215] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,215] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,229] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,248] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,248] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,253] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:21,253] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 85%|████████▍ | 4585/5399 [01:37<00:16, 50.72 examples/s][2026-04-16 10:36:21,288] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:753] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,350] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,351] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,355] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,355] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,357] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,357] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,368] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,374] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,374] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 86%|████████▌ | 4642/5399 [01:38<00:14, 50.66 examples/s][2026-04-16 10:36:22,407] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,407] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,414] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:22,437] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:754] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:23,492] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:755] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:23,495] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:755] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:23,496] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:755] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 87%|████████▋ | 4698/5399 [01:39<00:13, 50.54 examples/s][2026-04-16 10:36:23,527] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:755] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:23,544] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:755] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,541] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,542] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,550] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,550] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,570] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,570] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,572] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,572] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 88%|████████▊ | 4748/5399 [01:40<00:13, 49.28 examples/s][2026-04-16 10:36:24,600] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,600] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,612] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,613] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,616] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,616] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,619] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,620] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,622] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,622] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,633] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,633] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:24,644] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:756] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,698] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,698] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,729] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,729] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 89%|████████▉ | 4808/5399 [01:42<00:11, 50.28 examples/s][2026-04-16 10:36:25,746] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,746] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:25,775] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:757] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,729] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,730] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,768] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,771] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,771] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 90%|█████████ | 4868/5399 [01:43<00:10, 52.20 examples/s][2026-04-16 10:36:26,802] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,802] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,813] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:26,813] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:758] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:27,915] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:759] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:27,915] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:759] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 91%|█████████ | 4920/5399 [01:44<00:09, 50.26 examples/s][2026-04-16 10:36:27,936] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:759] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:27,936] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:759] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:27,941] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:759] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:28,977] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:28,993] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:28,993] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,002] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,002] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,004] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,022] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 92%|█████████▏| 4976/5399 [01:45<00:08, 50.51 examples/s][2026-04-16 10:36:29,045] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,057] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:29,057] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:760] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,075] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,075] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,097] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,097] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,099] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,099] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,109] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,109] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 93%|█████████▎| 5034/5399 [01:46<00:07, 51.15 examples/s][2026-04-16 10:36:30,134] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:30,134] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:761] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,176] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,176] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,183] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,184] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,190] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,190] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,202] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,202] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,204] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,204] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,221] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,221] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 94%|█████████▍| 5088/5399 [01:47<00:06, 50.55 examples/s][2026-04-16 10:36:31,240] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,240] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,259] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:31,259] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:762] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 95%|█████████▍| 5119/5399 [01:47<00:04, 60.22 examples/s][2026-04-16 10:36:32,265] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:763] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:32,265] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:763] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:32,267] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:763] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 95%|█████████▌| 5148/5399 [01:48<00:04, 50.26 examples/s][2026-04-16 10:36:32,278] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:763] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:32,279] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:763] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,350] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,376] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,376] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,380] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,380] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,388] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,394] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:33,394] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:764] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 96%|█████████▋| 5201/5399 [01:49<00:04, 48.69 examples/s][2026-04-16 10:36:34,463] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,464] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,467] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,474] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,474] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 97%|█████████▋| 5257/5399 [01:50<00:02, 49.54 examples/s][2026-04-16 10:36:34,521] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,521] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,537] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:34,537] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:765] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,582] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,582] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,590] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,590] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,596] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,596] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,614] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,614] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,616] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,616] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,621] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,621] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,643] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 98%|█████████▊| 5312/5399 [01:52<00:01, 49.35 examples/s][2026-04-16 10:36:35,643] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,653] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,653] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,657] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,657] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,669] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:35,669] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:766] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,697] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,698] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,722] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,726] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,726] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,729] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 99%|█████████▉| 5367/5399 [01:53<00:00, 49.65 examples/s][2026-04-16 10:36:36,759] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:36,773] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:767] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing train dataset (num_proc=96): 100%|██████████| 5399/5399 [01:54<00:00, 47.24 examples/s]
|
||
|
||
Adding EOS to eval dataset (num_proc=96): 0%| | 0/285 [00:00<?, ? examples/s]
|
||
Adding EOS to eval dataset (num_proc=96): 1%| | 3/285 [00:06<10:22, 2.21s/ examples]
|
||
Adding EOS to eval dataset (num_proc=96): 15%|█▍ | 42/285 [00:06<00:28, 8.68 examples/s]
|
||
Adding EOS to eval dataset (num_proc=96): 79%|███████▉ | 225/285 [00:06<00:00, 61.99 examples/s]
|
||
Adding EOS to eval dataset (num_proc=96): 100%|██████████| 285/285 [00:08<00:00, 34.68 examples/s]
|
||
|
||
Tokenizing eval dataset (num_proc=96): 0%| | 0/285 [00:00<?, ? examples/s][2026-04-16 10:36:55,837] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1460] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:36:55,837] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1460] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 1%| | 3/285 [00:08<12:53, 2.74s/ examples][2026-04-16 10:36:56,938] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1461] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 2%|▏ | 6/285 [00:09<06:16, 1.35s/ examples]
|
||
Tokenizing eval dataset (num_proc=96): 3%|▎ | 9/285 [00:10<04:08, 1.11 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 4%|▍ | 12/285 [00:11<03:08, 1.45 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 5%|▌ | 15/285 [00:12<02:35, 1.74 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 6%|▋ | 18/285 [00:14<02:24, 1.85 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 7%|▋ | 21/285 [00:15<02:07, 2.07 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 8%|▊ | 24/285 [00:16<01:56, 2.23 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 9%|▉ | 27/285 [00:17<01:49, 2.36 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 11%|█ | 30/285 [00:18<01:42, 2.49 examples/s][2026-04-16 10:37:07,172] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1470] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 12%|█▏ | 33/285 [00:19<01:38, 2.56 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 13%|█▎ | 36/285 [00:20<01:36, 2.59 examples/s][2026-04-16 10:37:09,405] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1472] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:09,405] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1472] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 14%|█▎ | 39/285 [00:21<01:33, 2.63 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 15%|█▍ | 42/285 [00:22<01:31, 2.66 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 16%|█▌ | 45/285 [00:23<01:29, 2.68 examples/s][2026-04-16 10:37:12,701] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1475] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:12,701] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1475] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 17%|█▋ | 48/285 [00:25<01:27, 2.69 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 18%|█▊ | 51/285 [00:26<01:26, 2.71 examples/s][2026-04-16 10:37:14,905] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1477] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 19%|█▉ | 54/285 [00:27<01:25, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 20%|██ | 57/285 [00:28<01:24, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 21%|██ | 60/285 [00:29<01:22, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 22%|██▏ | 63/285 [00:30<01:22, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 23%|██▎ | 66/285 [00:31<01:20, 2.73 examples/s][2026-04-16 10:37:20,446] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1482] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:20,446] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1482] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 24%|██▍ | 69/285 [00:32<01:19, 2.70 examples/s][2026-04-16 10:37:21,529] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1483] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 25%|██▌ | 72/285 [00:33<01:18, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 26%|██▋ | 75/285 [00:35<01:17, 2.71 examples/s][2026-04-16 10:37:23,734] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1485] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 27%|██▋ | 78/285 [00:36<01:16, 2.72 examples/s][2026-04-16 10:37:24,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1486] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:24,841] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1486] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 28%|██▊ | 81/285 [00:37<01:14, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 29%|██▉ | 84/285 [00:38<01:14, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 31%|███ | 87/285 [00:39<01:12, 2.72 examples/s][2026-04-16 10:37:28,151] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1489] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:28,151] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1489] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 32%|███▏ | 90/285 [00:40<01:11, 2.72 examples/s][2026-04-16 10:37:29,245] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1490] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 33%|███▎ | 93/285 [00:41<01:10, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 34%|███▎ | 96/285 [00:42<01:09, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 35%|███▍ | 99/285 [00:43<01:08, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 36%|███▌ | 102/285 [00:44<01:07, 2.72 examples/s][2026-04-16 10:37:33,636] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1494] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:33,636] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1494] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 37%|███▋ | 105/285 [00:46<01:05, 2.74 examples/s][2026-04-16 10:37:34,757] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1495] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:34,757] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1495] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 38%|███▊ | 108/285 [00:47<01:05, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 39%|███▉ | 111/285 [00:48<01:04, 2.72 examples/s][2026-04-16 10:37:36,969] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1497] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:36,969] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1497] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 40%|████ | 114/285 [00:49<01:03, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 41%|████ | 117/285 [00:50<01:01, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 42%|████▏ | 120/285 [00:51<01:00, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 43%|████▎ | 123/285 [00:52<00:59, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 44%|████▍ | 126/285 [00:53<00:58, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 45%|████▌ | 129/285 [00:54<00:57, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 46%|████▋ | 132/285 [00:56<00:56, 2.71 examples/s][2026-04-16 10:37:44,694] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1504] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:44,694] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1504] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 47%|████▋ | 135/285 [00:57<00:55, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 48%|████▊ | 138/285 [00:58<00:54, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 49%|████▉ | 141/285 [00:59<00:53, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 51%|█████ | 144/285 [01:00<00:52, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 52%|█████▏ | 147/285 [01:01<00:50, 2.72 examples/s][2026-04-16 10:37:50,233] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1509] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:50,233] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1509] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 53%|█████▎ | 150/285 [01:02<00:49, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 54%|█████▎ | 153/285 [01:03<00:48, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 55%|█████▍ | 156/285 [01:04<00:47, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 56%|█████▌ | 159/285 [01:05<00:46, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 57%|█████▋ | 162/285 [01:07<00:45, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 58%|█████▊ | 165/285 [01:08<00:44, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 59%|█████▉ | 168/285 [01:09<00:43, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 60%|██████ | 171/285 [01:10<00:42, 2.71 examples/s][2026-04-16 10:37:59,092] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1517] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:59,092] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1517] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:59,098] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1517] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:37:59,099] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1517] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 61%|██████ | 174/285 [01:11<00:41, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 62%|██████▏ | 177/285 [01:12<00:40, 2.70 examples/s][2026-04-16 10:38:01,343] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1519] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:01,343] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1519] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 63%|██████▎ | 180/285 [01:13<00:39, 2.69 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 64%|██████▍ | 183/285 [01:14<00:37, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 65%|██████▌ | 186/285 [01:15<00:36, 2.69 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 66%|██████▋ | 189/285 [01:17<00:35, 2.69 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 67%|██████▋ | 192/285 [01:18<00:34, 2.70 examples/s][2026-04-16 10:38:06,869] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1524] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:06,870] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1524] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 68%|██████▊ | 195/285 [01:19<00:33, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 69%|██████▉ | 198/285 [01:20<00:32, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 71%|███████ | 201/285 [01:21<00:30, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 72%|███████▏ | 204/285 [01:22<00:29, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 73%|███████▎ | 207/285 [01:23<00:28, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 74%|███████▎ | 210/285 [01:24<00:27, 2.72 examples/s][2026-04-16 10:38:13,504] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1530] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:13,505] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1530] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 75%|███████▍ | 213/285 [01:25<00:26, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 76%|███████▌ | 216/285 [01:27<00:25, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 77%|███████▋ | 219/285 [01:28<00:24, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 78%|███████▊ | 222/285 [01:29<00:23, 2.72 examples/s][2026-04-16 10:38:17,888] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1534] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:17,889] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1534] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 79%|███████▉ | 225/285 [01:30<00:21, 2.73 examples/s][2026-04-16 10:38:19,014] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1535] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:19,014] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1535] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 80%|████████ | 228/285 [01:31<00:20, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 81%|████████ | 231/285 [01:32<00:19, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 82%|████████▏ | 234/285 [01:33<00:18, 2.74 examples/s][2026-04-16 10:38:22,308] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1538] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:22,308] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1538] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 83%|████████▎ | 237/285 [01:34<00:17, 2.73 examples/s][2026-04-16 10:38:23,406] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1539] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:23,407] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1539] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 84%|████████▍ | 240/285 [01:35<00:16, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 85%|████████▌ | 243/285 [01:36<00:15, 2.73 examples/s][2026-04-16 10:38:25,598] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1541] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:25,598] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1541] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 86%|████████▋ | 246/285 [01:37<00:14, 2.74 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 87%|████████▋ | 249/285 [01:39<00:13, 2.73 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 88%|████████▊ | 252/285 [01:40<00:12, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 89%|████████▉ | 255/285 [01:41<00:11, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 91%|█████████ | 258/285 [01:42<00:09, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 92%|█████████▏| 261/285 [01:43<00:08, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 93%|█████████▎| 264/285 [01:44<00:07, 2.71 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 94%|█████████▎| 267/285 [01:45<00:06, 2.72 examples/s][2026-04-16 10:38:34,430] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1549] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:34,431] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1549] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 95%|█████████▍| 270/285 [01:46<00:05, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 96%|█████████▌| 273/285 [01:47<00:04, 2.71 examples/s][2026-04-16 10:38:36,648] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1551] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:36,649] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1551] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:36,654] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:929] [PID:1551] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+chosen. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
[2026-04-16 10:38:36,654] [WARNING] [trl.trainer.dpo_trainer.tokenize_fn:935] [PID:1551] [RANK 0] Mismatch between tokenized prompt and the start of tokenized prompt+rejected. This may be due to unexpected tokenizer behavior, whitespace issues, or special token handling. Verify that the tokenizer is processing text consistently.
|
||
|
||
Tokenizing eval dataset (num_proc=96): 97%|█████████▋| 276/285 [01:49<00:03, 2.70 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 98%|█████████▊| 279/285 [01:50<00:02, 2.72 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 99%|█████████▊| 281/285 [01:51<00:01, 2.45 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 99%|█████████▉| 283/285 [01:52<00:00, 2.26 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 100%|██████████| 285/285 [01:53<00:00, 2.13 examples/s]
|
||
Tokenizing eval dataset (num_proc=96): 100%|██████████| 285/285 [01:54<00:00, 2.49 examples/s]
|
||
[2026-04-16 10:38:46,976] [INFO] [axolotl.train.save_initial_configs:452] [PID:135] Pre-saving tokenizer to kikiyaa/qwen-dpo-finetuned-ver2...
|
||
[2026-04-16 10:38:47,137] [INFO] [axolotl.train.save_initial_configs:457] [PID:135] Pre-saving model config to kikiyaa/qwen-dpo-finetuned-ver2...
|
||
[2026-04-16 10:38:47,145] [INFO] [axolotl.train.execute_training:226] [PID:135] Starting trainer...
|
||
|
||
0%| | 0/1013 [00:00<?, ?it/s]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:20, 6.77it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:28, 4.88it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:30, 4.55it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:33, 4.14it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:32, 4.22it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:30, 4.47it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:32, 4.19it/s][A
|
||
|
||
6%|▋ | 9/143 [00:01<00:29, 4.47it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:30, 4.34it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:30, 4.36it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:32, 4.07it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:32, 3.98it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:34, 3.76it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:34, 3.76it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:30, 4.10it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:03<00:28, 4.39it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:27, 4.47it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:31, 3.98it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:32, 3.76it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:31, 3.85it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:31, 3.80it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:30, 3.88it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:05<00:31, 3.81it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:29, 3.98it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:28, 4.15it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:31, 3.69it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:06<00:32, 3.57it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:31, 3.59it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:32, 3.52it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:07<00:31, 3.57it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:07<00:29, 3.78it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:27, 4.01it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 4.04it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:08<00:27, 3.91it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:08<00:26, 4.11it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:25, 4.13it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:25, 4.11it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:09<00:27, 3.84it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:09<00:25, 4.04it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:25, 4.06it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:26, 3.81it/s][A
|
||
|
||
30%|███ | 43/143 [00:10<00:26, 3.74it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:25, 3.82it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:24, 3.99it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:11<00:30, 3.20it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:11<00:29, 3.28it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:27, 3.47it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:26, 3.52it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:12<00:26, 3.57it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:25, 3.60it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:24, 3.72it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.90it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:13<00:24, 3.64it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:23, 3.75it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.94it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:14<00:21, 3.98it/s][A
|
||
|
||
41%|████ | 58/143 [00:14<00:19, 4.28it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:14<00:19, 4.38it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.15it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:18, 4.40it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:15<00:21, 3.74it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:21, 3.76it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:22, 3.54it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:16<00:21, 3.55it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:23, 3.24it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.42it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:17<00:21, 3.52it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:17<00:23, 3.18it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:20, 3.51it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:18<00:20, 3.56it/s][A
|
||
|
||
50%|█████ | 72/143 [00:18<00:19, 3.59it/s][A
|
||
|
||
51%|█████ | 73/143 [00:18<00:19, 3.54it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:19, 3.53it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:19<00:19, 3.47it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:19<00:18, 3.61it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:17, 3.75it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:15, 4.07it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:20<00:15, 4.08it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:20<00:18, 3.49it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.84it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:21<00:17, 3.50it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:21<00:17, 3.38it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.39it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:22<00:16, 3.57it/s][A
|
||
|
||
60%|██████ | 86/143 [00:22<00:13, 4.13it/s][A
|
||
|
||
61%|██████ | 87/143 [00:22<00:13, 4.23it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:22<00:13, 4.08it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:13, 3.93it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:23<00:13, 3.96it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:23<00:12, 4.26it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:23<00:12, 4.11it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 4.10it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:24<00:12, 3.80it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:24<00:14, 3.40it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:12, 3.63it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:25<00:11, 3.99it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:25<00:10, 4.12it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:25<00:11, 3.90it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:11, 3.63it/s][A
|
||
|
||
71%|███████ | 101/143 [00:26<00:10, 3.88it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:26<00:10, 3.82it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:26<00:10, 3.65it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:09, 3.90it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:27<00:09, 3.82it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:27<00:09, 3.77it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:27<00:09, 3.94it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:28<00:08, 4.08it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:28<00:08, 4.08it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:28<00:07, 4.18it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:28<00:08, 3.79it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:29<00:07, 3.94it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:29<00:08, 3.44it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:29<00:08, 3.61it/s][A
|
||
|
||
80%|████████ | 115/143 [00:30<00:07, 3.60it/s][A
|
||
|
||
81%|████████ | 116/143 [00:30<00:07, 3.80it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:30<00:07, 3.64it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:30<00:06, 3.99it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:30<00:05, 4.28it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:31<00:05, 4.06it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:31<00:05, 3.87it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:31<00:04, 4.32it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:31<00:04, 4.04it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:32<00:04, 4.14it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:32<00:03, 4.58it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:32<00:03, 4.53it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:32<00:03, 4.18it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:33<00:03, 3.95it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:33<00:03, 4.07it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:33<00:03, 4.21it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:33<00:02, 4.32it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:34<00:02, 4.24it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:34<00:02, 3.69it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:34<00:02, 3.67it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:34<00:02, 3.54it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:35<00:01, 3.75it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:35<00:01, 3.59it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:35<00:01, 3.58it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:36<00:01, 3.71it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:36<00:00, 4.05it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:36<00:00, 3.96it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:36<00:00, 3.85it/s][A
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.83it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '0.6931', 'eval_runtime': '39.08', 'eval_samples_per_second': '7.293', 'eval_steps_per_second': '3.659', 'eval_entropy': '1.729', 'eval_num_tokens': '0', 'eval_logits/chosen': '0.8636', 'eval_logits/rejected': '-0.6579', 'eval_mean_token_accuracy': '0.4934', 'eval_rewards/chosen': '0', 'eval_rewards/rejected': '0', 'eval_rewards/accuracies': '0', 'eval_rewards/margins': '0', 'eval_logps/chosen': '-111.2', 'eval_logps/rejected': '-175', 'epoch': 0}
|
||
|
||
0%| | 0/1013 [00:39<?, ?it/s]
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.83it/s][A
|
||
|
||
[A
|
||
0%| | 1/1013 [00:47<13:22:13, 47.56s/it]
|
||
|
||
{'loss': '0.6931', 'grad_norm': '83.5', 'learning_rate': '0', 'entropy': '1.75', 'num_tokens': '1.017e+04', 'logits/chosen': '1.082', 'logits/rejected': '-0.5941', 'mean_token_accuracy': '0.5048', 'rewards/chosen': '0', 'rewards/rejected': '0', 'rewards/accuracies': '0', 'rewards/margins': '0', 'logps/chosen': '-110.6', 'logps/rejected': '-182.5', 'epoch': '0.002963'}
|
||
|
||
0%| | 1/1013 [00:47<13:22:13, 47.56s/it]
|
||
0%| | 2/1013 [00:54<6:35:36, 23.48s/it]
|
||
0%| | 3/1013 [01:01<4:28:53, 15.97s/it]
|
||
0%| | 4/1013 [01:08<3:31:38, 12.59s/it]
|
||
0%| | 5/1013 [01:14<2:53:31, 10.33s/it]
|
||
1%| | 6/1013 [01:22<2:34:58, 9.23s/it]
|
||
1%| | 7/1013 [01:28<2:20:10, 8.36s/it]
|
||
1%| | 8/1013 [01:35<2:12:30, 7.91s/it]
|
||
1%| | 9/1013 [01:42<2:06:06, 7.54s/it]
|
||
1%| | 10/1013 [01:49<2:02:38, 7.34s/it]
|
||
|
||
{'loss': '0.5316', 'grad_norm': '29.88', 'learning_rate': '4.455e-06', 'entropy': '1.73', 'num_tokens': '8.912e+04', 'logits/chosen': '0.8213', 'logits/rejected': '-0.6694', 'mean_token_accuracy': '0.5101', 'rewards/chosen': '0.3062', 'rewards/rejected': '-0.1129', 'rewards/accuracies': '0.8125', 'rewards/margins': '0.4191', 'logps/chosen': '-100.8', 'logps/rejected': '-171.8', 'epoch': '0.02963'}
|
||
|
||
1%| | 10/1013 [01:49<2:02:38, 7.34s/it]
|
||
1%| | 11/1013 [01:56<2:02:58, 7.36s/it]
|
||
1%| | 12/1013 [02:03<1:59:21, 7.15s/it]
|
||
1%|▏ | 13/1013 [02:10<2:00:35, 7.24s/it]
|
||
1%|▏ | 14/1013 [02:17<1:58:43, 7.13s/it]
|
||
1%|▏ | 15/1013 [02:25<2:00:13, 7.23s/it]
|
||
2%|▏ | 16/1013 [02:32<2:01:38, 7.32s/it]
|
||
2%|▏ | 17/1013 [02:39<2:00:19, 7.25s/it]
|
||
2%|▏ | 18/1013 [02:46<1:59:47, 7.22s/it]
|
||
2%|▏ | 19/1013 [02:53<1:59:24, 7.21s/it]
|
||
2%|▏ | 20/1013 [03:01<2:00:00, 7.25s/it]
|
||
|
||
{'loss': '0.03662', 'grad_norm': '0.07471', 'learning_rate': '9.406e-06', 'entropy': '1.585', 'num_tokens': '1.828e+05', 'logits/chosen': '1.218', 'logits/rejected': '-0.8403', 'mean_token_accuracy': '0.5997', 'rewards/chosen': '2.911', 'rewards/rejected': '-2.458', 'rewards/accuracies': '1', 'rewards/margins': '5.369', 'logps/chosen': '-77.17', 'logps/rejected': '-196.3', 'epoch': '0.05926'}
|
||
|
||
2%|▏ | 20/1013 [03:01<2:00:00, 7.25s/it]
|
||
2%|▏ | 21/1013 [03:08<1:57:36, 7.11s/it]
|
||
2%|▏ | 22/1013 [03:15<1:57:37, 7.12s/it]
|
||
2%|▏ | 23/1013 [03:22<1:58:26, 7.18s/it]
|
||
2%|▏ | 24/1013 [03:29<1:56:28, 7.07s/it]
|
||
2%|▏ | 25/1013 [03:36<1:57:33, 7.14s/it]
|
||
3%|▎ | 26/1013 [03:43<1:56:58, 7.11s/it]
|
||
3%|▎ | 27/1013 [03:51<1:58:01, 7.18s/it]
|
||
3%|▎ | 28/1013 [03:58<1:57:11, 7.14s/it]
|
||
3%|▎ | 29/1013 [04:05<1:57:01, 7.14s/it]
|
||
3%|▎ | 30/1013 [04:12<1:55:47, 7.07s/it]
|
||
|
||
{'loss': '6.737e-05', 'grad_norm': '0.01929', 'learning_rate': '1.436e-05', 'entropy': '1.412', 'num_tokens': '2.748e+05', 'logits/chosen': '2.265', 'logits/rejected': '-1.035', 'mean_token_accuracy': '0.6582', 'rewards/chosen': '4.463', 'rewards/rejected': '-8.481', 'rewards/accuracies': '1', 'rewards/margins': '12.94', 'logps/chosen': '-64.55', 'logps/rejected': '-259.6', 'epoch': '0.08889'}
|
||
|
||
3%|▎ | 30/1013 [04:12<1:55:47, 7.07s/it]
|
||
3%|▎ | 31/1013 [04:19<1:56:04, 7.09s/it]
|
||
3%|▎ | 32/1013 [04:26<1:54:09, 6.98s/it]
|
||
3%|▎ | 33/1013 [04:33<1:54:16, 7.00s/it]
|
||
3%|▎ | 34/1013 [04:40<1:56:21, 7.13s/it]
|
||
3%|▎ | 35/1013 [04:47<1:55:57, 7.11s/it]
|
||
4%|▎ | 36/1013 [04:54<1:54:24, 7.03s/it]
|
||
4%|▎ | 37/1013 [05:01<1:52:27, 6.91s/it]
|
||
4%|▍ | 38/1013 [05:08<1:55:24, 7.10s/it]
|
||
4%|▍ | 39/1013 [05:15<1:54:45, 7.07s/it]
|
||
4%|▍ | 40/1013 [05:22<1:55:25, 7.12s/it]
|
||
|
||
{'loss': '3.113e-06', 'grad_norm': '0.0004864', 'learning_rate': '1.931e-05', 'entropy': '1.356', 'num_tokens': '3.673e+05', 'logits/chosen': '2.337', 'logits/rejected': '-1.143', 'mean_token_accuracy': '0.667', 'rewards/chosen': '4.367', 'rewards/rejected': '-11.72', 'rewards/accuracies': '1', 'rewards/margins': '16.09', 'logps/chosen': '-61.83', 'logps/rejected': '-295.9', 'epoch': '0.1185'}
|
||
|
||
4%|▍ | 40/1013 [05:22<1:55:25, 7.12s/it]
|
||
4%|▍ | 41/1013 [05:30<1:56:39, 7.20s/it]
|
||
4%|▍ | 42/1013 [05:37<1:56:43, 7.21s/it]
|
||
4%|▍ | 43/1013 [05:44<1:53:57, 7.05s/it]
|
||
4%|▍ | 44/1013 [05:51<1:54:20, 7.08s/it]
|
||
4%|▍ | 45/1013 [05:58<1:56:37, 7.23s/it]
|
||
5%|▍ | 46/1013 [06:06<1:58:31, 7.35s/it]
|
||
5%|▍ | 47/1013 [06:13<1:56:24, 7.23s/it]
|
||
5%|▍ | 48/1013 [06:20<1:57:02, 7.28s/it]
|
||
5%|▍ | 49/1013 [06:28<1:58:27, 7.37s/it]
|
||
5%|▍ | 50/1013 [06:35<1:55:07, 7.17s/it]
|
||
|
||
{'loss': '7.578e-06', 'grad_norm': '0.0001202', 'learning_rate': '2.426e-05', 'entropy': '1.32', 'num_tokens': '4.615e+05', 'logits/chosen': '2.315', 'logits/rejected': '-1.057', 'mean_token_accuracy': '0.6602', 'rewards/chosen': '4.112', 'rewards/rejected': '-12.43', 'rewards/accuracies': '1', 'rewards/margins': '16.55', 'logps/chosen': '-63.68', 'logps/rejected': '-302.8', 'epoch': '0.1481'}
|
||
|
||
5%|▍ | 50/1013 [06:35<1:55:07, 7.17s/it]
|
||
5%|▌ | 51/1013 [06:42<1:55:56, 7.23s/it]
|
||
5%|▌ | 52/1013 [06:50<1:58:47, 7.42s/it]
|
||
5%|▌ | 53/1013 [06:57<1:55:39, 7.23s/it]
|
||
5%|▌ | 54/1013 [07:04<1:56:24, 7.28s/it]
|
||
5%|▌ | 55/1013 [07:11<1:56:34, 7.30s/it]
|
||
6%|▌ | 56/1013 [07:19<1:55:38, 7.25s/it]
|
||
6%|▌ | 57/1013 [07:26<1:54:14, 7.17s/it]
|
||
6%|▌ | 58/1013 [07:33<1:54:28, 7.19s/it]
|
||
6%|▌ | 59/1013 [07:40<1:54:08, 7.18s/it]
|
||
6%|▌ | 60/1013 [07:47<1:53:30, 7.15s/it]
|
||
|
||
{'loss': '2.057e-06', 'grad_norm': '0.0003872', 'learning_rate': '2.921e-05', 'entropy': '1.327', 'num_tokens': '5.552e+05', 'logits/chosen': '2.262', 'logits/rejected': '-1.086', 'mean_token_accuracy': '0.6665', 'rewards/chosen': '4.521', 'rewards/rejected': '-12.74', 'rewards/accuracies': '1', 'rewards/margins': '17.26', 'logps/chosen': '-63.42', 'logps/rejected': '-304.6', 'epoch': '0.1778'}
|
||
|
||
6%|▌ | 60/1013 [07:47<1:53:30, 7.15s/it]
|
||
6%|▌ | 61/1013 [07:54<1:53:42, 7.17s/it]
|
||
6%|▌ | 62/1013 [08:01<1:51:50, 7.06s/it]
|
||
6%|▌ | 63/1013 [08:08<1:52:22, 7.10s/it]
|
||
6%|▋ | 64/1013 [08:15<1:51:52, 7.07s/it]
|
||
6%|▋ | 65/1013 [08:22<1:51:50, 7.08s/it]
|
||
7%|▋ | 66/1013 [08:29<1:50:27, 7.00s/it]
|
||
7%|▋ | 67/1013 [08:36<1:49:35, 6.95s/it]
|
||
7%|▋ | 68/1013 [08:43<1:49:25, 6.95s/it]
|
||
7%|▋ | 69/1013 [08:50<1:50:50, 7.04s/it]
|
||
7%|▋ | 70/1013 [08:58<1:52:31, 7.16s/it]
|
||
|
||
{'loss': '2.663e-05', 'grad_norm': '1.061e-05', 'learning_rate': '3.416e-05', 'entropy': '1.311', 'num_tokens': '6.462e+05', 'logits/chosen': '2.317', 'logits/rejected': '-1.146', 'mean_token_accuracy': '0.6684', 'rewards/chosen': '4.37', 'rewards/rejected': '-12.66', 'rewards/accuracies': '1', 'rewards/margins': '17.03', 'logps/chosen': '-62.94', 'logps/rejected': '-301.5', 'epoch': '0.2074'}
|
||
|
||
7%|▋ | 70/1013 [08:58<1:52:31, 7.16s/it]
|
||
7%|▋ | 71/1013 [09:05<1:51:31, 7.10s/it]
|
||
7%|▋ | 72/1013 [09:12<1:51:15, 7.09s/it]
|
||
7%|▋ | 73/1013 [09:19<1:52:22, 7.17s/it]
|
||
7%|▋ | 74/1013 [09:27<1:54:54, 7.34s/it]
|
||
7%|▋ | 75/1013 [09:35<1:57:27, 7.51s/it]
|
||
8%|▊ | 76/1013 [09:42<1:54:29, 7.33s/it]
|
||
8%|▊ | 77/1013 [09:49<1:53:50, 7.30s/it]
|
||
8%|▊ | 78/1013 [09:55<1:49:59, 7.06s/it]
|
||
8%|▊ | 79/1013 [10:02<1:49:07, 7.01s/it]
|
||
8%|▊ | 80/1013 [10:09<1:50:23, 7.10s/it]
|
||
|
||
{'loss': '2.219e-07', 'grad_norm': '8.464e-06', 'learning_rate': '3.911e-05', 'entropy': '1.318', 'num_tokens': '7.414e+05', 'logits/chosen': '2.253', 'logits/rejected': '-1.145', 'mean_token_accuracy': '0.6683', 'rewards/chosen': '4.62', 'rewards/rejected': '-13.44', 'rewards/accuracies': '1', 'rewards/margins': '18.06', 'logps/chosen': '-64.7', 'logps/rejected': '-313.3', 'epoch': '0.237'}
|
||
|
||
8%|▊ | 80/1013 [10:09<1:50:23, 7.10s/it]
|
||
8%|▊ | 81/1013 [10:16<1:49:54, 7.08s/it]
|
||
8%|▊ | 82/1013 [10:24<1:52:45, 7.27s/it]
|
||
8%|▊ | 83/1013 [10:31<1:52:43, 7.27s/it]
|
||
8%|▊ | 84/1013 [10:39<1:51:43, 7.22s/it]
|
||
8%|▊ | 85/1013 [10:46<1:52:19, 7.26s/it]
|
||
8%|▊ | 86/1013 [10:53<1:50:38, 7.16s/it]
|
||
9%|▊ | 87/1013 [10:59<1:46:54, 6.93s/it]
|
||
9%|▊ | 88/1013 [11:06<1:47:04, 6.95s/it]
|
||
9%|▉ | 89/1013 [11:14<1:50:18, 7.16s/it]
|
||
9%|▉ | 90/1013 [11:21<1:48:12, 7.03s/it]
|
||
|
||
{'loss': '6.854e-06', 'grad_norm': '0.0001421', 'learning_rate': '4.406e-05', 'entropy': '1.307', 'num_tokens': '8.335e+05', 'logits/chosen': '2.265', 'logits/rejected': '-1.145', 'mean_token_accuracy': '0.6589', 'rewards/chosen': '4.537', 'rewards/rejected': '-13.27', 'rewards/accuracies': '1', 'rewards/margins': '17.81', 'logps/chosen': '-62.47', 'logps/rejected': '-309.7', 'epoch': '0.2667'}
|
||
|
||
9%|▉ | 90/1013 [11:21<1:48:12, 7.03s/it]
|
||
9%|▉ | 91/1013 [11:27<1:46:42, 6.94s/it]
|
||
9%|▉ | 92/1013 [11:34<1:47:22, 6.99s/it]
|
||
9%|▉ | 93/1013 [11:42<1:47:54, 7.04s/it]
|
||
9%|▉ | 94/1013 [11:49<1:47:45, 7.04s/it]
|
||
9%|▉ | 95/1013 [11:56<1:49:26, 7.15s/it]
|
||
9%|▉ | 96/1013 [12:03<1:48:32, 7.10s/it]
|
||
10%|▉ | 97/1013 [12:10<1:47:33, 7.05s/it]
|
||
10%|▉ | 98/1013 [12:17<1:48:51, 7.14s/it]
|
||
10%|▉ | 99/1013 [12:24<1:47:02, 7.03s/it]
|
||
10%|▉ | 100/1013 [12:31<1:48:22, 7.12s/it]
|
||
|
||
{'loss': '2e-06', 'grad_norm': '0.0001278', 'learning_rate': '4.901e-05', 'entropy': '1.304', 'num_tokens': '9.253e+05', 'logits/chosen': '2.328', 'logits/rejected': '-1.059', 'mean_token_accuracy': '0.6724', 'rewards/chosen': '4.472', 'rewards/rejected': '-13.28', 'rewards/accuracies': '1', 'rewards/margins': '17.75', 'logps/chosen': '-57.69', 'logps/rejected': '-307.1', 'epoch': '0.2963'}
|
||
|
||
10%|▉ | 100/1013 [12:31<1:48:22, 7.12s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.25it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.64it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:31, 4.37it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.98it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.09it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.32it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.05it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.30it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.23it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.94it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:33, 3.86it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.65it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:34, 3.66it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:31, 3.99it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.27it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:28, 4.35it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.86it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.66it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.74it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:32, 3.68it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:31, 3.76it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.71it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.86it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:28, 4.04it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.59it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.48it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.50it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:07<00:32, 3.48it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.67it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.89it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 3.92it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:08<00:28, 3.81it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:26, 4.01it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 4.01it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:27, 3.74it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.94it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:25, 3.95it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.71it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.65it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.74it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.90it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.13it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:29, 3.21it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:27, 3.40it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.45it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.50it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.52it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.63it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.80it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.56it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:23, 3.67it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.85it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:14<00:22, 3.88it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.17it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.28it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.05it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:19, 4.28it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.64it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:21, 3.65it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:22, 3.46it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.45it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.16it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.36it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.45it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.11it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.43it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:18<00:20, 3.47it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.50it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.44it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.40it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:18, 3.54it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:17, 3.67it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:16, 3.98it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.99it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.42it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.76it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:21<00:17, 3.43it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.32it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.33it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:22<00:16, 3.51it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 4.05it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.13it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 4.00it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:14, 3.85it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.89it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.18it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 4.03it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 4.03it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.72it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.34it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.58it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:25<00:11, 3.93it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 4.04it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.84it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:12, 3.56it/s][A
|
||
|
||
71%|███████ | 101/143 [00:26<00:11, 3.80it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:10, 3.75it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.58it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:10, 3.82it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.73it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.68it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.86it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:28<00:08, 3.99it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 4.00it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.09it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.72it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:29<00:07, 3.88it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.37it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.54it/s][A
|
||
|
||
80%|████████ | 115/143 [00:30<00:07, 3.54it/s][A
|
||
|
||
81%|████████ | 116/143 [00:30<00:07, 3.75it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.58it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.91it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:31<00:05, 4.20it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:31<00:05, 3.98it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.79it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:04, 4.24it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:32<00:05, 3.96it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:32<00:04, 4.05it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.47it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:33<00:03, 4.41it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:33<00:03, 4.11it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:33<00:03, 3.89it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 3.99it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:34<00:03, 4.13it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:34<00:02, 4.25it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:34<00:02, 4.17it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.62it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:35<00:02, 3.58it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:35<00:02, 3.47it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.68it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:36<00:01, 3.54it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:36<00:01, 3.52it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:36<00:01, 3.65it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.97it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:37<00:00, 3.89it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:37<00:00, 3.78it/s][A
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.71it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '3.521e-05', 'eval_runtime': '38.32', 'eval_samples_per_second': '7.437', 'eval_steps_per_second': '3.731', 'eval_entropy': '1.309', 'eval_num_tokens': '9.253e+05', 'eval_logits/chosen': '2.256', 'eval_logits/rejected': '-1.138', 'eval_mean_token_accuracy': '0.6629', 'eval_rewards/chosen': '4.51', 'eval_rewards/rejected': '-13.52', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '18.03', 'eval_logps/chosen': '-66.05', 'eval_logps/rejected': '-310.3', 'epoch': '0.2963'}
|
||
|
||
10%|▉ | 100/1013 [13:10<1:48:22, 7.12s/it]
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.71it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:38<00:00, 38.01s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:38<00:00, 38.01s/it]
|
||
|
||
10%|▉ | 101/1013 [14:36<10:45:32, 42.47s/it]
|
||
10%|█ | 102/1013 [14:43<8:03:48, 31.86s/it]
|
||
10%|█ | 103/1013 [14:51<6:10:40, 24.44s/it]
|
||
10%|█ | 104/1013 [14:58<4:51:34, 19.25s/it]
|
||
10%|█ | 105/1013 [15:05<3:56:32, 15.63s/it]
|
||
10%|█ | 106/1013 [15:12<3:17:14, 13.05s/it]
|
||
11%|█ | 107/1013 [15:20<2:53:34, 11.49s/it]
|
||
11%|█ | 108/1013 [15:27<2:35:55, 10.34s/it]
|
||
11%|█ | 109/1013 [15:34<2:20:35, 9.33s/it]
|
||
11%|█ | 110/1013 [15:41<2:08:10, 8.52s/it]
|
||
|
||
{'loss': '3.422e-06', 'grad_norm': '0.0008125', 'learning_rate': '4.999e-05', 'entropy': '1.285', 'num_tokens': '1.016e+06', 'logits/chosen': '2.34', 'logits/rejected': '-1.114', 'mean_token_accuracy': '0.6787', 'rewards/chosen': '4.463', 'rewards/rejected': '-13.3', 'rewards/accuracies': '1', 'rewards/margins': '17.77', 'logps/chosen': '-61.88', 'logps/rejected': '-304.7', 'epoch': '0.3259'}
|
||
|
||
11%|█ | 110/1013 [15:41<2:08:10, 8.52s/it]
|
||
11%|█ | 111/1013 [15:49<2:03:52, 8.24s/it]
|
||
11%|█ | 112/1013 [15:55<1:56:17, 7.74s/it]
|
||
11%|█ | 113/1013 [16:02<1:53:28, 7.57s/it]
|
||
11%|█▏ | 114/1013 [16:09<1:50:31, 7.38s/it]
|
||
11%|█▏ | 115/1013 [16:16<1:49:07, 7.29s/it]
|
||
11%|█▏ | 116/1013 [16:23<1:47:25, 7.19s/it]
|
||
12%|█▏ | 117/1013 [16:30<1:46:04, 7.10s/it]
|
||
12%|█▏ | 118/1013 [16:37<1:46:22, 7.13s/it]
|
||
12%|█▏ | 119/1013 [16:44<1:45:18, 7.07s/it]
|
||
12%|█▏ | 120/1013 [16:51<1:44:43, 7.04s/it]
|
||
|
||
{'loss': '1.316e-06', 'grad_norm': '0.000102', 'learning_rate': '4.995e-05', 'entropy': '1.284', 'num_tokens': '1.106e+06', 'logits/chosen': '2.345', 'logits/rejected': '-1.094', 'mean_token_accuracy': '0.671', 'rewards/chosen': '4.635', 'rewards/rejected': '-13.68', 'rewards/accuracies': '1', 'rewards/margins': '18.31', 'logps/chosen': '-61.62', 'logps/rejected': '-307.1', 'epoch': '0.3556'}
|
||
|
||
12%|█▏ | 120/1013 [16:51<1:44:43, 7.04s/it]
|
||
12%|█▏ | 121/1013 [16:58<1:44:44, 7.05s/it]
|
||
12%|█▏ | 122/1013 [17:06<1:46:34, 7.18s/it]
|
||
12%|█▏ | 123/1013 [17:13<1:47:04, 7.22s/it]
|
||
12%|█▏ | 124/1013 [17:20<1:43:36, 6.99s/it]
|
||
12%|█▏ | 125/1013 [17:27<1:45:26, 7.12s/it]
|
||
12%|█▏ | 126/1013 [17:34<1:45:34, 7.14s/it]
|
||
13%|█▎ | 127/1013 [17:42<1:47:55, 7.31s/it]
|
||
13%|█▎ | 128/1013 [17:49<1:47:40, 7.30s/it]
|
||
13%|█▎ | 129/1013 [17:57<1:49:32, 7.43s/it]
|
||
13%|█▎ | 130/1013 [18:04<1:49:11, 7.42s/it]
|
||
|
||
{'loss': '2.281e-06', 'grad_norm': '0.0009766', 'learning_rate': '4.988e-05', 'entropy': '1.296', 'num_tokens': '1.198e+06', 'logits/chosen': '2.33', 'logits/rejected': '-1.083', 'mean_token_accuracy': '0.664', 'rewards/chosen': '4.473', 'rewards/rejected': '-13.82', 'rewards/accuracies': '1', 'rewards/margins': '18.29', 'logps/chosen': '-60.91', 'logps/rejected': '-320.1', 'epoch': '0.3852'}
|
||
|
||
13%|█▎ | 130/1013 [18:04<1:49:11, 7.42s/it]
|
||
13%|█▎ | 131/1013 [18:11<1:47:26, 7.31s/it]
|
||
13%|█▎ | 132/1013 [18:19<1:46:44, 7.27s/it]
|
||
13%|█▎ | 133/1013 [18:26<1:46:27, 7.26s/it]
|
||
13%|█▎ | 134/1013 [18:33<1:44:36, 7.14s/it]
|
||
13%|█▎ | 135/1013 [18:39<1:42:41, 7.02s/it]
|
||
13%|█▎ | 136/1013 [18:47<1:43:17, 7.07s/it]
|
||
14%|█▎ | 137/1013 [18:53<1:42:11, 7.00s/it]
|
||
14%|█▎ | 138/1013 [19:01<1:45:04, 7.21s/it]
|
||
14%|█▎ | 139/1013 [19:09<1:46:32, 7.31s/it]
|
||
14%|█▍ | 140/1013 [19:16<1:46:17, 7.31s/it]
|
||
|
||
{'loss': '1.216e-06', 'grad_norm': '0.00116', 'learning_rate': '4.979e-05', 'entropy': '1.274', 'num_tokens': '1.289e+06', 'logits/chosen': '2.311', 'logits/rejected': '-1.121', 'mean_token_accuracy': '0.675', 'rewards/chosen': '4.255', 'rewards/rejected': '-13.96', 'rewards/accuracies': '1', 'rewards/margins': '18.21', 'logps/chosen': '-58.56', 'logps/rejected': '-314.1', 'epoch': '0.4148'}
|
||
|
||
14%|█▍ | 140/1013 [19:16<1:46:17, 7.31s/it]
|
||
14%|█▍ | 141/1013 [19:23<1:44:41, 7.20s/it]
|
||
14%|█▍ | 142/1013 [19:30<1:44:59, 7.23s/it]
|
||
14%|█▍ | 143/1013 [19:37<1:43:49, 7.16s/it]
|
||
14%|█▍ | 144/1013 [19:45<1:44:02, 7.18s/it]
|
||
14%|█▍ | 145/1013 [19:52<1:43:59, 7.19s/it]
|
||
14%|█▍ | 146/1013 [19:59<1:43:07, 7.14s/it]
|
||
15%|█▍ | 147/1013 [20:06<1:41:35, 7.04s/it]
|
||
15%|█▍ | 148/1013 [20:13<1:43:35, 7.19s/it]
|
||
15%|█▍ | 149/1013 [20:21<1:45:27, 7.32s/it]
|
||
15%|█▍ | 150/1013 [20:28<1:43:39, 7.21s/it]
|
||
|
||
{'loss': '4.051e-07', 'grad_norm': '0.0001659', 'learning_rate': '4.966e-05', 'entropy': '1.285', 'num_tokens': '1.38e+06', 'logits/chosen': '2.333', 'logits/rejected': '-1.181', 'mean_token_accuracy': '0.6699', 'rewards/chosen': '4.356', 'rewards/rejected': '-14.17', 'rewards/accuracies': '1', 'rewards/margins': '18.53', 'logps/chosen': '-60.03', 'logps/rejected': '-315.8', 'epoch': '0.4444'}
|
||
|
||
15%|█▍ | 150/1013 [20:28<1:43:39, 7.21s/it]
|
||
15%|█▍ | 151/1013 [20:34<1:41:44, 7.08s/it]
|
||
15%|█▌ | 152/1013 [20:42<1:44:01, 7.25s/it]
|
||
15%|█▌ | 153/1013 [20:49<1:44:08, 7.27s/it]
|
||
15%|█▌ | 154/1013 [20:57<1:44:48, 7.32s/it]
|
||
15%|█▌ | 155/1013 [21:04<1:42:22, 7.16s/it]
|
||
15%|█▌ | 156/1013 [21:11<1:43:08, 7.22s/it]
|
||
15%|█▌ | 157/1013 [21:18<1:44:10, 7.30s/it]
|
||
16%|█▌ | 158/1013 [21:26<1:44:14, 7.31s/it]
|
||
16%|█▌ | 159/1013 [21:33<1:42:34, 7.21s/it]
|
||
16%|█▌ | 160/1013 [21:40<1:42:35, 7.22s/it]
|
||
|
||
{'loss': '2.103e-07', 'grad_norm': '1.013e-05', 'learning_rate': '4.95e-05', 'entropy': '1.301', 'num_tokens': '1.474e+06', 'logits/chosen': '2.325', 'logits/rejected': '-1.09', 'mean_token_accuracy': '0.668', 'rewards/chosen': '4.37', 'rewards/rejected': '-14.26', 'rewards/accuracies': '1', 'rewards/margins': '18.63', 'logps/chosen': '-62.87', 'logps/rejected': '-325.7', 'epoch': '0.4741'}
|
||
|
||
16%|█▌ | 160/1013 [21:40<1:42:35, 7.22s/it]
|
||
16%|█▌ | 161/1013 [21:47<1:42:33, 7.22s/it]
|
||
16%|█▌ | 162/1013 [21:55<1:46:32, 7.51s/it]
|
||
16%|█▌ | 163/1013 [22:02<1:43:39, 7.32s/it]
|
||
16%|█▌ | 164/1013 [22:09<1:42:13, 7.22s/it]
|
||
16%|█▋ | 165/1013 [22:17<1:42:37, 7.26s/it]
|
||
16%|█▋ | 166/1013 [22:24<1:41:17, 7.18s/it]
|
||
16%|█▋ | 167/1013 [22:30<1:39:31, 7.06s/it]
|
||
17%|█▋ | 168/1013 [22:38<1:41:37, 7.22s/it]
|
||
17%|█▋ | 169/1013 [22:45<1:41:00, 7.18s/it]
|
||
17%|█▋ | 170/1013 [22:52<1:40:15, 7.14s/it]
|
||
|
||
{'loss': '5.846e-07', 'grad_norm': '0.0001707', 'learning_rate': '4.932e-05', 'entropy': '1.293', 'num_tokens': '1.567e+06', 'logits/chosen': '2.199', 'logits/rejected': '-1.131', 'mean_token_accuracy': '0.6591', 'rewards/chosen': '4.248', 'rewards/rejected': '-13.77', 'rewards/accuracies': '1', 'rewards/margins': '18.02', 'logps/chosen': '-66.82', 'logps/rejected': '-313', 'epoch': '0.5037'}
|
||
|
||
17%|█▋ | 170/1013 [22:52<1:40:15, 7.14s/it]
|
||
17%|█▋ | 171/1013 [22:59<1:39:43, 7.11s/it]
|
||
17%|█▋ | 172/1013 [23:06<1:39:07, 7.07s/it]
|
||
17%|█▋ | 173/1013 [23:14<1:40:44, 7.20s/it]
|
||
17%|█▋ | 174/1013 [23:20<1:38:52, 7.07s/it]
|
||
17%|█▋ | 175/1013 [23:28<1:39:51, 7.15s/it]
|
||
17%|█▋ | 176/1013 [23:35<1:38:41, 7.07s/it]
|
||
17%|█▋ | 177/1013 [23:42<1:38:58, 7.10s/it]
|
||
18%|█▊ | 178/1013 [23:50<1:41:14, 7.27s/it]
|
||
18%|█▊ | 179/1013 [23:57<1:40:31, 7.23s/it]
|
||
18%|█▊ | 180/1013 [24:04<1:41:05, 7.28s/it]
|
||
|
||
{'loss': '4.462e-07', 'grad_norm': '1.162e-05', 'learning_rate': '4.91e-05', 'entropy': '1.291', 'num_tokens': '1.659e+06', 'logits/chosen': '2.257', 'logits/rejected': '-1.186', 'mean_token_accuracy': '0.6724', 'rewards/chosen': '4.278', 'rewards/rejected': '-14.01', 'rewards/accuracies': '1', 'rewards/margins': '18.28', 'logps/chosen': '-60.77', 'logps/rejected': '-319.7', 'epoch': '0.5333'}
|
||
|
||
18%|█▊ | 180/1013 [24:04<1:41:05, 7.28s/it]
|
||
18%|█▊ | 181/1013 [24:11<1:40:15, 7.23s/it]
|
||
18%|█▊ | 182/1013 [24:18<1:37:47, 7.06s/it]
|
||
18%|█▊ | 183/1013 [24:25<1:39:14, 7.17s/it]
|
||
18%|█▊ | 184/1013 [24:33<1:40:01, 7.24s/it]
|
||
18%|█▊ | 185/1013 [24:39<1:37:14, 7.05s/it]
|
||
18%|█▊ | 186/1013 [24:46<1:37:33, 7.08s/it]
|
||
18%|█▊ | 187/1013 [24:53<1:36:39, 7.02s/it]
|
||
19%|█▊ | 188/1013 [25:00<1:35:15, 6.93s/it]
|
||
19%|█▊ | 189/1013 [25:08<1:39:11, 7.22s/it]
|
||
19%|█▉ | 190/1013 [25:15<1:38:43, 7.20s/it]
|
||
|
||
{'loss': '5.486e-07', 'grad_norm': '6.485e-05', 'learning_rate': '4.886e-05', 'entropy': '1.302', 'num_tokens': '1.75e+06', 'logits/chosen': '2.302', 'logits/rejected': '-1.049', 'mean_token_accuracy': '0.6693', 'rewards/chosen': '4.455', 'rewards/rejected': '-13.99', 'rewards/accuracies': '1', 'rewards/margins': '18.44', 'logps/chosen': '-61.81', 'logps/rejected': '-315.3', 'epoch': '0.563'}
|
||
|
||
19%|█▉ | 190/1013 [25:15<1:38:43, 7.20s/it]
|
||
19%|█▉ | 191/1013 [25:22<1:38:35, 7.20s/it]
|
||
19%|█▉ | 192/1013 [25:29<1:38:10, 7.18s/it]
|
||
19%|█▉ | 193/1013 [25:37<1:38:46, 7.23s/it]
|
||
19%|█▉ | 194/1013 [25:44<1:39:48, 7.31s/it]
|
||
19%|█▉ | 195/1013 [25:51<1:36:33, 7.08s/it]
|
||
19%|█▉ | 196/1013 [25:58<1:37:29, 7.16s/it]
|
||
19%|█▉ | 197/1013 [26:05<1:38:00, 7.21s/it]
|
||
20%|█▉ | 198/1013 [26:12<1:36:06, 7.08s/it]
|
||
20%|█▉ | 199/1013 [26:19<1:34:54, 7.00s/it]
|
||
20%|█▉ | 200/1013 [26:26<1:34:20, 6.96s/it]
|
||
|
||
{'loss': '5.882e-06', 'grad_norm': '0.008789', 'learning_rate': '4.859e-05', 'entropy': '1.301', 'num_tokens': '1.841e+06', 'logits/chosen': '2.215', 'logits/rejected': '-1.123', 'mean_token_accuracy': '0.6559', 'rewards/chosen': '4.423', 'rewards/rejected': '-14.15', 'rewards/accuracies': '1', 'rewards/margins': '18.57', 'logps/chosen': '-66.62', 'logps/rejected': '-316.4', 'epoch': '0.5926'}
|
||
|
||
20%|█▉ | 200/1013 [26:26<1:34:20, 6.96s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.19it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.61it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:31, 4.34it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.97it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.07it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.31it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.05it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.31it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.23it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.94it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:33, 3.87it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.65it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:34, 3.67it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:31, 3.97it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.24it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:28, 4.33it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.86it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.65it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.73it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:32, 3.69it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:31, 3.77it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.71it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.87it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:28, 4.04it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.59it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.48it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.49it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.46it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.66it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.89it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 3.93it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:08<00:28, 3.80it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.98it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:27, 3.73it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.92it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:25, 3.94it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.71it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.64it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.73it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.89it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.12it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:29, 3.20it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:27, 3.40it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.43it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.48it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.51it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.62it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.80it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.54it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.66it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.84it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:14<00:22, 3.87it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.15it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.26it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.03it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:19, 4.28it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.64it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:21, 3.66it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:22, 3.45it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.45it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.16it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.36it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.44it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.11it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.42it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:18<00:20, 3.46it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.49it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.45it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.44it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.39it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:18, 3.53it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.65it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:16, 3.96it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.98it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.41it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.75it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:17, 3.40it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.29it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.31it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:22<00:16, 3.48it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 4.02it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.10it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 3.96it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:14, 3.84it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.88it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.17it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 4.01it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 4.01it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.71it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.32it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.57it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:25<00:11, 3.90it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 4.02it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.82it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:12, 3.54it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.79it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.72it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.55it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:10, 3.80it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.73it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.68it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.84it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:28<00:08, 3.98it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.98it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.09it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.70it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:29<00:08, 3.85it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.36it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.53it/s][A
|
||
|
||
80%|████████ | 115/143 [00:30<00:07, 3.53it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.74it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.57it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.91it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:31<00:05, 4.19it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.97it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.78it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:04, 4.22it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:32<00:05, 3.95it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.06it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.48it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:33<00:03, 4.42it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:33<00:03, 4.09it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:03, 3.88it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 4.00it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:34<00:03, 4.12it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:34<00:02, 4.23it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:34<00:02, 4.15it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.62it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:35<00:02, 3.59it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:35<00:02, 3.46it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.67it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:36<00:01, 3.53it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:36<00:01, 3.51it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:36<00:01, 3.63it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.96it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:37<00:00, 3.88it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:37<00:00, 3.77it/s][A
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.83it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '1.247e-05', 'eval_runtime': '38.39', 'eval_samples_per_second': '7.424', 'eval_steps_per_second': '3.725', 'eval_entropy': '1.294', 'eval_num_tokens': '1.841e+06', 'eval_logits/chosen': '2.251', 'eval_logits/rejected': '-1.153', 'eval_mean_token_accuracy': '0.6633', 'eval_rewards/chosen': '4.431', 'eval_rewards/rejected': '-14.31', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '18.74', 'eval_logps/chosen': '-66.84', 'eval_logps/rejected': '-318.1', 'epoch': '0.5926'}
|
||
|
||
20%|█▉ | 200/1013 [27:04<1:34:20, 6.96s/it]
|
||
|
||
100%|██████████| 143/143 [00:37<00:00, 3.83it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:41<00:00, 41.14s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:41<00:00, 41.14s/it]
|
||
|
||
20%|█▉ | 201/1013 [28:34<9:48:05, 43.46s/it]
|
||
20%|█▉ | 202/1013 [28:41<7:18:26, 32.44s/it]
|
||
20%|██ | 203/1013 [28:48<5:35:32, 24.85s/it]
|
||
20%|██ | 204/1013 [28:55<4:22:40, 19.48s/it]
|
||
20%|██ | 205/1013 [29:03<3:34:25, 15.92s/it]
|
||
20%|██ | 206/1013 [29:10<2:59:46, 13.37s/it]
|
||
20%|██ | 207/1013 [29:18<2:37:01, 11.69s/it]
|
||
21%|██ | 208/1013 [29:26<2:19:53, 10.43s/it]
|
||
21%|██ | 209/1013 [29:32<2:05:31, 9.37s/it]
|
||
21%|██ | 210/1013 [29:39<1:55:43, 8.65s/it]
|
||
|
||
{'loss': '2.41e-07', 'grad_norm': '5.126e-05', 'learning_rate': '4.829e-05', 'entropy': '1.294', 'num_tokens': '1.936e+06', 'logits/chosen': '2.345', 'logits/rejected': '-1.186', 'mean_token_accuracy': '0.6671', 'rewards/chosen': '4.46', 'rewards/rejected': '-14.67', 'rewards/accuracies': '1', 'rewards/margins': '19.13', 'logps/chosen': '-64.12', 'logps/rejected': '-325.7', 'epoch': '0.6222'}
|
||
|
||
21%|██ | 210/1013 [29:39<1:55:43, 8.65s/it]
|
||
21%|██ | 211/1013 [29:47<1:52:25, 8.41s/it]
|
||
21%|██ | 212/1013 [29:54<1:46:06, 7.95s/it]
|
||
21%|██ | 213/1013 [30:02<1:44:51, 7.86s/it]
|
||
21%|██ | 214/1013 [30:09<1:40:43, 7.56s/it]
|
||
21%|██ | 215/1013 [30:16<1:38:47, 7.43s/it]
|
||
21%|██▏ | 216/1013 [30:23<1:37:23, 7.33s/it]
|
||
21%|██▏ | 217/1013 [30:31<1:39:10, 7.48s/it]
|
||
22%|██▏ | 218/1013 [30:38<1:36:36, 7.29s/it]
|
||
22%|██▏ | 219/1013 [30:45<1:35:30, 7.22s/it]
|
||
22%|██▏ | 220/1013 [30:52<1:35:25, 7.22s/it]
|
||
|
||
{'loss': '3.415e-07', 'grad_norm': '4.768e-05', 'learning_rate': '4.796e-05', 'entropy': '1.255', 'num_tokens': '2.029e+06', 'logits/chosen': '2.309', 'logits/rejected': '-1.075', 'mean_token_accuracy': '0.6794', 'rewards/chosen': '4.353', 'rewards/rejected': '-14.4', 'rewards/accuracies': '1', 'rewards/margins': '18.75', 'logps/chosen': '-58.98', 'logps/rejected': '-315.6', 'epoch': '0.6519'}
|
||
|
||
22%|██▏ | 220/1013 [30:52<1:35:25, 7.22s/it]
|
||
22%|██▏ | 221/1013 [30:59<1:35:57, 7.27s/it]
|
||
22%|██▏ | 222/1013 [31:06<1:34:17, 7.15s/it]
|
||
22%|██▏ | 223/1013 [31:14<1:35:41, 7.27s/it]
|
||
22%|██▏ | 224/1013 [31:21<1:36:20, 7.33s/it]
|
||
22%|██▏ | 225/1013 [31:29<1:36:55, 7.38s/it]
|
||
22%|██▏ | 226/1013 [31:36<1:37:17, 7.42s/it]
|
||
22%|██▏ | 227/1013 [31:43<1:36:31, 7.37s/it]
|
||
23%|██▎ | 228/1013 [31:50<1:35:16, 7.28s/it]
|
||
23%|██▎ | 229/1013 [31:58<1:34:07, 7.20s/it]
|
||
23%|██▎ | 230/1013 [32:04<1:33:01, 7.13s/it]
|
||
|
||
{'loss': '1.383e-06', 'grad_norm': '2.789e-05', 'learning_rate': '4.761e-05', 'entropy': '1.275', 'num_tokens': '2.123e+06', 'logits/chosen': '2.263', 'logits/rejected': '-1.075', 'mean_token_accuracy': '0.666', 'rewards/chosen': '4.317', 'rewards/rejected': '-14.6', 'rewards/accuracies': '1', 'rewards/margins': '18.91', 'logps/chosen': '-64.98', 'logps/rejected': '-320.6', 'epoch': '0.6815'}
|
||
|
||
23%|██▎ | 230/1013 [32:04<1:33:01, 7.13s/it]
|
||
23%|██▎ | 231/1013 [32:12<1:33:07, 7.15s/it]
|
||
23%|██▎ | 232/1013 [32:19<1:32:21, 7.10s/it]
|
||
23%|██▎ | 233/1013 [32:26<1:31:35, 7.04s/it]
|
||
23%|██▎ | 234/1013 [32:33<1:31:42, 7.06s/it]
|
||
23%|██▎ | 235/1013 [32:39<1:30:23, 6.97s/it]
|
||
23%|██▎ | 236/1013 [32:46<1:29:54, 6.94s/it]
|
||
23%|██▎ | 237/1013 [32:53<1:30:33, 7.00s/it]
|
||
23%|██▎ | 238/1013 [33:01<1:31:13, 7.06s/it]
|
||
24%|██▎ | 239/1013 [33:08<1:32:23, 7.16s/it]
|
||
24%|██▎ | 240/1013 [33:15<1:32:25, 7.17s/it]
|
||
|
||
{'loss': '1.857e-07', 'grad_norm': '2.789e-05', 'learning_rate': '4.723e-05', 'entropy': '1.289', 'num_tokens': '2.212e+06', 'logits/chosen': '2.338', 'logits/rejected': '-1.152', 'mean_token_accuracy': '0.6677', 'rewards/chosen': '4.302', 'rewards/rejected': '-14.91', 'rewards/accuracies': '1', 'rewards/margins': '19.21', 'logps/chosen': '-62.95', 'logps/rejected': '-325.2', 'epoch': '0.7111'}
|
||
|
||
24%|██▎ | 240/1013 [33:15<1:32:25, 7.17s/it]
|
||
24%|██▍ | 241/1013 [33:23<1:33:45, 7.29s/it]
|
||
24%|██▍ | 242/1013 [33:30<1:33:45, 7.30s/it]
|
||
24%|██▍ | 243/1013 [33:38<1:34:22, 7.35s/it]
|
||
24%|██▍ | 244/1013 [33:45<1:36:12, 7.51s/it]
|
||
24%|██▍ | 245/1013 [33:53<1:35:40, 7.48s/it]
|
||
24%|██▍ | 246/1013 [34:00<1:34:26, 7.39s/it]
|
||
24%|██▍ | 247/1013 [34:08<1:35:52, 7.51s/it]
|
||
24%|██▍ | 248/1013 [34:15<1:35:14, 7.47s/it]
|
||
25%|██▍ | 249/1013 [34:23<1:34:28, 7.42s/it]
|
||
25%|██▍ | 250/1013 [34:29<1:32:15, 7.25s/it]
|
||
|
||
{'loss': '4.805e-07', 'grad_norm': '1.365e-05', 'learning_rate': '4.682e-05', 'entropy': '1.298', 'num_tokens': '2.308e+06', 'logits/chosen': '2.357', 'logits/rejected': '-1.215', 'mean_token_accuracy': '0.6871', 'rewards/chosen': '4.415', 'rewards/rejected': '-14.85', 'rewards/accuracies': '1', 'rewards/margins': '19.26', 'logps/chosen': '-61.08', 'logps/rejected': '-327.5', 'epoch': '0.7407'}
|
||
|
||
25%|██▍ | 250/1013 [34:29<1:32:15, 7.25s/it]
|
||
25%|██▍ | 251/1013 [34:37<1:31:40, 7.22s/it]
|
||
25%|██▍ | 252/1013 [34:45<1:34:55, 7.48s/it]
|
||
25%|██▍ | 253/1013 [34:53<1:38:19, 7.76s/it]
|
||
25%|██▌ | 254/1013 [35:00<1:36:15, 7.61s/it]
|
||
25%|██▌ | 255/1013 [35:07<1:33:54, 7.43s/it]
|
||
25%|██▌ | 256/1013 [35:15<1:34:48, 7.51s/it]
|
||
25%|██▌ | 257/1013 [35:22<1:32:54, 7.37s/it]
|
||
25%|██▌ | 258/1013 [35:29<1:32:47, 7.37s/it]
|
||
26%|██▌ | 259/1013 [35:37<1:32:20, 7.35s/it]
|
||
26%|██▌ | 260/1013 [35:44<1:30:35, 7.22s/it]
|
||
|
||
{'loss': '1.567e-07', 'grad_norm': '0.0001364', 'learning_rate': '4.639e-05', 'entropy': '1.29', 'num_tokens': '2.404e+06', 'logits/chosen': '2.268', 'logits/rejected': '-1.113', 'mean_token_accuracy': '0.6552', 'rewards/chosen': '4.321', 'rewards/rejected': '-14.58', 'rewards/accuracies': '1', 'rewards/margins': '18.9', 'logps/chosen': '-67.26', 'logps/rejected': '-321.5', 'epoch': '0.7704'}
|
||
|
||
26%|██▌ | 260/1013 [35:44<1:30:35, 7.22s/it]
|
||
26%|██▌ | 261/1013 [35:51<1:31:17, 7.28s/it]
|
||
26%|██▌ | 262/1013 [35:58<1:30:22, 7.22s/it]
|
||
26%|██▌ | 263/1013 [36:05<1:28:16, 7.06s/it]
|
||
26%|██▌ | 264/1013 [36:11<1:26:36, 6.94s/it]
|
||
26%|██▌ | 265/1013 [36:19<1:27:26, 7.01s/it]
|
||
26%|██▋ | 266/1013 [36:25<1:26:26, 6.94s/it]
|
||
26%|██▋ | 267/1013 [36:32<1:25:58, 6.91s/it]
|
||
26%|██▋ | 268/1013 [36:40<1:26:58, 7.00s/it]
|
||
27%|██▋ | 269/1013 [36:47<1:26:55, 7.01s/it]
|
||
27%|██▋ | 270/1013 [36:54<1:28:38, 7.16s/it]
|
||
|
||
{'loss': '3.22e-07', 'grad_norm': '2.599e-05', 'learning_rate': '4.593e-05', 'entropy': '1.291', 'num_tokens': '2.494e+06', 'logits/chosen': '2.338', 'logits/rejected': '-1.181', 'mean_token_accuracy': '0.671', 'rewards/chosen': '4.552', 'rewards/rejected': '-14.61', 'rewards/accuracies': '1', 'rewards/margins': '19.16', 'logps/chosen': '-61.25', 'logps/rejected': '-321.8', 'epoch': '0.8'}
|
||
|
||
27%|██▋ | 270/1013 [36:54<1:28:38, 7.16s/it]
|
||
27%|██▋ | 271/1013 [37:01<1:28:06, 7.13s/it]
|
||
27%|██▋ | 272/1013 [37:09<1:30:18, 7.31s/it]
|
||
27%|██▋ | 273/1013 [37:16<1:30:48, 7.36s/it]
|
||
27%|██▋ | 274/1013 [37:23<1:28:57, 7.22s/it]
|
||
27%|██▋ | 275/1013 [37:30<1:27:54, 7.15s/it]
|
||
27%|██▋ | 276/1013 [37:37<1:26:49, 7.07s/it]
|
||
27%|██▋ | 277/1013 [37:44<1:27:31, 7.13s/it]
|
||
27%|██▋ | 278/1013 [37:51<1:26:38, 7.07s/it]
|
||
28%|██▊ | 279/1013 [37:58<1:25:30, 6.99s/it]
|
||
28%|██▊ | 280/1013 [38:06<1:27:12, 7.14s/it]
|
||
|
||
{'loss': '1.684e-07', 'grad_norm': '1.073e-05', 'learning_rate': '4.545e-05', 'entropy': '1.297', 'num_tokens': '2.584e+06', 'logits/chosen': '2.262', 'logits/rejected': '-1.199', 'mean_token_accuracy': '0.6727', 'rewards/chosen': '4.606', 'rewards/rejected': '-14.74', 'rewards/accuracies': '1', 'rewards/margins': '19.35', 'logps/chosen': '-62.55', 'logps/rejected': '-328.4', 'epoch': '0.8296'}
|
||
|
||
28%|██▊ | 280/1013 [38:06<1:27:12, 7.14s/it]
|
||
28%|██▊ | 281/1013 [38:12<1:25:09, 6.98s/it]
|
||
28%|██▊ | 282/1013 [38:20<1:26:29, 7.10s/it]
|
||
28%|██▊ | 283/1013 [38:27<1:26:22, 7.10s/it]
|
||
28%|██▊ | 284/1013 [38:34<1:26:36, 7.13s/it]
|
||
28%|██▊ | 285/1013 [38:41<1:26:54, 7.16s/it]
|
||
28%|██▊ | 286/1013 [38:48<1:25:21, 7.05s/it]
|
||
28%|██▊ | 287/1013 [38:55<1:26:01, 7.11s/it]
|
||
28%|██▊ | 288/1013 [39:02<1:25:45, 7.10s/it]
|
||
29%|██▊ | 289/1013 [39:09<1:25:45, 7.11s/it]
|
||
29%|██▊ | 290/1013 [39:16<1:24:51, 7.04s/it]
|
||
|
||
{'loss': '1.092e-07', 'grad_norm': '1.472e-05', 'learning_rate': '4.494e-05', 'entropy': '1.271', 'num_tokens': '2.673e+06', 'logits/chosen': '2.304', 'logits/rejected': '-1.16', 'mean_token_accuracy': '0.6695', 'rewards/chosen': '4.521', 'rewards/rejected': '-14.96', 'rewards/accuracies': '1', 'rewards/margins': '19.48', 'logps/chosen': '-64.2', 'logps/rejected': '-321.6', 'epoch': '0.8593'}
|
||
|
||
29%|██▊ | 290/1013 [39:16<1:24:51, 7.04s/it]
|
||
29%|██▊ | 291/1013 [39:23<1:24:50, 7.05s/it]
|
||
29%|██▉ | 292/1013 [39:30<1:24:39, 7.04s/it]
|
||
29%|██▉ | 293/1013 [39:38<1:25:47, 7.15s/it]
|
||
29%|██▉ | 294/1013 [39:45<1:25:02, 7.10s/it]
|
||
29%|██▉ | 295/1013 [39:52<1:24:54, 7.10s/it]
|
||
29%|██▉ | 296/1013 [39:59<1:26:42, 7.26s/it]
|
||
29%|██▉ | 297/1013 [40:07<1:28:02, 7.38s/it]
|
||
29%|██▉ | 298/1013 [40:15<1:28:56, 7.46s/it]
|
||
30%|██▉ | 299/1013 [40:21<1:26:19, 7.25s/it]
|
||
30%|██▉ | 300/1013 [40:29<1:26:07, 7.25s/it]
|
||
|
||
{'loss': '9.59e-07', 'grad_norm': '8.047e-06', 'learning_rate': '4.441e-05', 'entropy': '1.259', 'num_tokens': '2.765e+06', 'logits/chosen': '2.245', 'logits/rejected': '-1.205', 'mean_token_accuracy': '0.6734', 'rewards/chosen': '4.453', 'rewards/rejected': '-14.7', 'rewards/accuracies': '1', 'rewards/margins': '19.16', 'logps/chosen': '-63.22', 'logps/rejected': '-316.8', 'epoch': '0.8889'}
|
||
|
||
30%|██▉ | 300/1013 [40:29<1:26:07, 7.25s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.29it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.64it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:31, 4.36it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.98it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.08it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.31it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.04it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.31it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.22it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.93it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:33, 3.86it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.65it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.65it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:31, 3.98it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.26it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:28, 4.34it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.85it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.65it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.73it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:32, 3.68it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:31, 3.75it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.71it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.86it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 4.02it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.57it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.47it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.49it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.42it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.46it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.67it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.89it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 3.92it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.81it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:26, 4.01it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 4.02it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:27, 3.73it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.93it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:25, 3.94it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.71it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.65it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.74it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.89it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.12it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.20it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:27, 3.40it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.43it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.48it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.52it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.64it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.81it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.56it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:23, 3.67it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.85it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:14<00:22, 3.89it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.15it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.26it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.03it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:19, 4.29it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.64it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:21, 3.65it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:22, 3.46it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.45it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.16it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.35it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.44it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.11it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.42it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:18<00:20, 3.47it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.49it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.45it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.39it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:18, 3.53it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.66it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:16, 3.97it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.98it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.41it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.75it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:17, 3.42it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.31it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.34it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:22<00:16, 3.49it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 4.03it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.12it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 3.98it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:14, 3.84it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.87it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.17it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 4.01it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 4.00it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.72it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.33it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.56it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:25<00:11, 3.91it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 4.02it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.81it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:12, 3.55it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.79it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:10, 3.73it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.56it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:10, 3.81it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.73it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.68it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.84it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:28<00:08, 3.98it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.97it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.07it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.71it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:29<00:08, 3.86it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.36it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.54it/s][A
|
||
|
||
80%|████████ | 115/143 [00:30<00:07, 3.53it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.73it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.57it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.91it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:31<00:05, 4.20it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.98it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.79it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:04, 4.23it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:32<00:05, 3.95it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.06it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.49it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:33<00:03, 4.43it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:33<00:03, 4.10it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:33<00:03, 3.87it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 4.00it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:34<00:03, 4.13it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:34<00:02, 4.24it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:34<00:02, 4.16it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.62it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:35<00:02, 3.59it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:35<00:02, 3.46it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.68it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:36<00:01, 3.52it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:36<00:01, 3.51it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:36<00:01, 3.63it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.96it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:37<00:00, 3.87it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:37<00:00, 3.76it/s][A
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.68it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '9.115e-06', 'eval_runtime': '38.41', 'eval_samples_per_second': '7.42', 'eval_steps_per_second': '3.723', 'eval_entropy': '1.286', 'eval_num_tokens': '2.765e+06', 'eval_logits/chosen': '2.245', 'eval_logits/rejected': '-1.158', 'eval_mean_token_accuracy': '0.6628', 'eval_rewards/chosen': '4.364', 'eval_rewards/rejected': '-14.81', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.17', 'eval_logps/chosen': '-67.52', 'eval_logps/rejected': '-323.2', 'epoch': '0.8889'}
|
||
|
||
30%|██▉ | 300/1013 [41:07<1:26:07, 7.25s/it]
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.68it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:41<00:00, 41.39s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:41<00:00, 41.39s/it]
|
||
|
||
30%|██▉ | 301/1013 [42:35<8:29:41, 42.95s/it]
|
||
30%|██▉ | 302/1013 [42:43<6:25:23, 32.52s/it]
|
||
30%|██▉ | 303/1013 [42:52<4:59:06, 25.28s/it]
|
||
30%|███ | 304/1013 [43:00<3:58:18, 20.17s/it]
|
||
30%|███ | 305/1013 [43:08<3:15:13, 16.54s/it]
|
||
30%|███ | 306/1013 [43:16<2:46:04, 14.09s/it]
|
||
30%|███ | 307/1013 [43:25<2:25:15, 12.34s/it]
|
||
30%|███ | 308/1013 [43:33<2:10:10, 11.08s/it]
|
||
31%|███ | 309/1013 [43:40<1:57:36, 10.02s/it]
|
||
31%|███ | 310/1013 [43:49<1:52:15, 9.58s/it]
|
||
|
||
{'loss': '2.076e-07', 'grad_norm': '4.315e-05', 'learning_rate': '4.385e-05', 'entropy': '1.277', 'num_tokens': '2.86e+06', 'logits/chosen': '2.296', 'logits/rejected': '-1.201', 'mean_token_accuracy': '0.6736', 'rewards/chosen': '4.336', 'rewards/rejected': '-15.02', 'rewards/accuracies': '1', 'rewards/margins': '19.35', 'logps/chosen': '-62.47', 'logps/rejected': '-329.2', 'epoch': '0.9185'}
|
||
|
||
31%|███ | 310/1013 [43:49<1:52:15, 9.58s/it]
|
||
31%|███ | 311/1013 [43:57<1:47:15, 9.17s/it]
|
||
31%|███ | 312/1013 [44:05<1:42:14, 8.75s/it]
|
||
31%|███ | 313/1013 [44:13<1:39:31, 8.53s/it]
|
||
31%|███ | 314/1013 [44:21<1:37:02, 8.33s/it]
|
||
31%|███ | 315/1013 [44:29<1:36:50, 8.32s/it]
|
||
31%|███ | 316/1013 [44:37<1:36:08, 8.28s/it]
|
||
31%|███▏ | 317/1013 [44:45<1:35:36, 8.24s/it]
|
||
31%|███▏ | 318/1013 [44:53<1:34:46, 8.18s/it]
|
||
31%|███▏ | 319/1013 [45:02<1:34:46, 8.19s/it]
|
||
32%|███▏ | 320/1013 [45:10<1:34:41, 8.20s/it]
|
||
|
||
{'loss': '8.637e-08', 'grad_norm': '2.265e-05', 'learning_rate': '4.328e-05', 'entropy': '1.267', 'num_tokens': '2.951e+06', 'logits/chosen': '2.301', 'logits/rejected': '-1.161', 'mean_token_accuracy': '0.6695', 'rewards/chosen': '4.261', 'rewards/rejected': '-15.03', 'rewards/accuracies': '1', 'rewards/margins': '19.29', 'logps/chosen': '-60.54', 'logps/rejected': '-325.3', 'epoch': '0.9481'}
|
||
|
||
32%|███▏ | 320/1013 [45:10<1:34:41, 8.20s/it]
|
||
32%|███▏ | 321/1013 [45:18<1:34:39, 8.21s/it]
|
||
32%|███▏ | 322/1013 [45:26<1:35:21, 8.28s/it]
|
||
32%|███▏ | 323/1013 [45:35<1:35:01, 8.26s/it]
|
||
32%|███▏ | 324/1013 [45:43<1:34:37, 8.24s/it]
|
||
32%|███▏ | 325/1013 [45:51<1:34:05, 8.21s/it]
|
||
32%|███▏ | 326/1013 [45:59<1:34:18, 8.24s/it]
|
||
32%|███▏ | 327/1013 [46:08<1:34:21, 8.25s/it]
|
||
32%|███▏ | 328/1013 [46:16<1:33:12, 8.16s/it]
|
||
32%|███▏ | 329/1013 [46:23<1:31:15, 8.01s/it]
|
||
33%|███▎ | 330/1013 [46:31<1:31:38, 8.05s/it]
|
||
|
||
{'loss': '1.65e-06', 'grad_norm': '3.144e-06', 'learning_rate': '4.268e-05', 'entropy': '1.28', 'num_tokens': '3.046e+06', 'logits/chosen': '2.304', 'logits/rejected': '-1.125', 'mean_token_accuracy': '0.6599', 'rewards/chosen': '4.304', 'rewards/rejected': '-14.87', 'rewards/accuracies': '1', 'rewards/margins': '19.17', 'logps/chosen': '-65.51', 'logps/rejected': '-327.7', 'epoch': '0.9778'}
|
||
|
||
33%|███▎ | 330/1013 [46:31<1:31:38, 8.05s/it]
|
||
33%|███▎ | 331/1013 [46:39<1:31:17, 8.03s/it]
|
||
33%|███▎ | 332/1013 [46:48<1:33:09, 8.21s/it]
|
||
33%|███▎ | 333/1013 [46:56<1:32:57, 8.20s/it]
|
||
33%|███▎ | 334/1013 [47:04<1:32:05, 8.14s/it]
|
||
33%|███▎ | 335/1013 [47:12<1:31:20, 8.08s/it]
|
||
33%|███▎ | 336/1013 [47:20<1:31:16, 8.09s/it]
|
||
33%|███▎ | 337/1013 [47:28<1:28:52, 7.89s/it]
|
||
33%|███▎ | 338/1013 [47:32<1:15:35, 6.72s/it]
|
||
33%|███▎ | 339/1013 [47:39<1:18:17, 6.97s/it]
|
||
34%|███▎ | 340/1013 [47:46<1:18:58, 7.04s/it]
|
||
|
||
{'loss': '3.58e-07', 'grad_norm': '5.794e-05', 'learning_rate': '4.206e-05', 'entropy': '1.286', 'num_tokens': '3.131e+06', 'logits/chosen': '2.319', 'logits/rejected': '-1.215', 'mean_token_accuracy': '0.6625', 'rewards/chosen': '4.281', 'rewards/rejected': '-15.31', 'rewards/accuracies': '1', 'rewards/margins': '19.59', 'logps/chosen': '-67.07', 'logps/rejected': '-330.4', 'epoch': '1.006'}
|
||
|
||
34%|███▎ | 340/1013 [47:46<1:18:58, 7.04s/it]
|
||
34%|███▎ | 341/1013 [47:54<1:20:43, 7.21s/it]
|
||
34%|███▍ | 342/1013 [48:02<1:22:11, 7.35s/it]
|
||
34%|███▍ | 343/1013 [48:09<1:23:00, 7.43s/it]
|
||
34%|███▍ | 344/1013 [48:17<1:22:46, 7.42s/it]
|
||
34%|███▍ | 345/1013 [48:24<1:22:19, 7.39s/it]
|
||
34%|███▍ | 346/1013 [48:31<1:22:20, 7.41s/it]
|
||
34%|███▍ | 347/1013 [48:39<1:23:31, 7.53s/it]
|
||
34%|███▍ | 348/1013 [48:47<1:25:25, 7.71s/it]
|
||
34%|███▍ | 349/1013 [48:55<1:24:59, 7.68s/it]
|
||
35%|███▍ | 350/1013 [49:03<1:25:20, 7.72s/it]
|
||
|
||
{'loss': '1.532e-07', 'grad_norm': '6.008e-05', 'learning_rate': '4.142e-05', 'entropy': '1.282', 'num_tokens': '3.225e+06', 'logits/chosen': '2.34', 'logits/rejected': '-1.147', 'mean_token_accuracy': '0.6736', 'rewards/chosen': '4.493', 'rewards/rejected': '-15.33', 'rewards/accuracies': '1', 'rewards/margins': '19.83', 'logps/chosen': '-60.32', 'logps/rejected': '-335.2', 'epoch': '1.036'}
|
||
|
||
35%|███▍ | 350/1013 [49:03<1:25:20, 7.72s/it]
|
||
35%|███▍ | 351/1013 [49:11<1:25:48, 7.78s/it]
|
||
35%|███▍ | 352/1013 [49:19<1:26:26, 7.85s/it]
|
||
35%|███▍ | 353/1013 [49:27<1:29:24, 8.13s/it]
|
||
35%|███▍ | 354/1013 [49:35<1:26:59, 7.92s/it]
|
||
35%|███▌ | 355/1013 [49:43<1:27:40, 7.99s/it]
|
||
35%|███▌ | 356/1013 [49:52<1:29:16, 8.15s/it]
|
||
35%|███▌ | 357/1013 [50:00<1:29:09, 8.15s/it]
|
||
35%|███▌ | 358/1013 [50:08<1:28:49, 8.14s/it]
|
||
35%|███▌ | 359/1013 [50:16<1:29:01, 8.17s/it]
|
||
36%|███▌ | 360/1013 [50:24<1:29:02, 8.18s/it]
|
||
|
||
{'loss': '4.122e-07', 'grad_norm': '0.0001926', 'learning_rate': '4.076e-05', 'entropy': '1.273', 'num_tokens': '3.319e+06', 'logits/chosen': '2.3', 'logits/rejected': '-1.202', 'mean_token_accuracy': '0.6744', 'rewards/chosen': '4.402', 'rewards/rejected': '-15.23', 'rewards/accuracies': '1', 'rewards/margins': '19.63', 'logps/chosen': '-60.59', 'logps/rejected': '-329.2', 'epoch': '1.065'}
|
||
|
||
36%|███▌ | 360/1013 [50:24<1:29:02, 8.18s/it]
|
||
36%|███▌ | 361/1013 [50:32<1:27:12, 8.03s/it]
|
||
36%|███▌ | 362/1013 [50:40<1:26:54, 8.01s/it]
|
||
36%|███▌ | 363/1013 [50:48<1:28:31, 8.17s/it]
|
||
36%|███▌ | 364/1013 [50:57<1:28:39, 8.20s/it]
|
||
36%|███▌ | 365/1013 [51:05<1:27:21, 8.09s/it]
|
||
36%|███▌ | 366/1013 [51:13<1:27:11, 8.09s/it]
|
||
36%|███▌ | 367/1013 [51:20<1:25:46, 7.97s/it]
|
||
36%|███▋ | 368/1013 [51:28<1:24:52, 7.90s/it]
|
||
36%|███▋ | 369/1013 [51:36<1:23:22, 7.77s/it]
|
||
37%|███▋ | 370/1013 [51:43<1:23:12, 7.76s/it]
|
||
|
||
{'loss': '1.151e-06', 'grad_norm': '0.0005913', 'learning_rate': '4.008e-05', 'entropy': '1.277', 'num_tokens': '3.411e+06', 'logits/chosen': '2.288', 'logits/rejected': '-1.155', 'mean_token_accuracy': '0.6719', 'rewards/chosen': '4.197', 'rewards/rejected': '-14.81', 'rewards/accuracies': '1', 'rewards/margins': '19.01', 'logps/chosen': '-63.77', 'logps/rejected': '-319', 'epoch': '1.095'}
|
||
|
||
37%|███▋ | 370/1013 [51:43<1:23:12, 7.76s/it]
|
||
37%|███▋ | 371/1013 [51:51<1:23:42, 7.82s/it]
|
||
37%|███▋ | 372/1013 [51:59<1:24:05, 7.87s/it]
|
||
37%|███▋ | 373/1013 [52:08<1:25:21, 8.00s/it]
|
||
37%|███▋ | 374/1013 [52:16<1:25:33, 8.03s/it]
|
||
37%|███▋ | 375/1013 [52:23<1:23:34, 7.86s/it]
|
||
37%|███▋ | 376/1013 [52:31<1:23:39, 7.88s/it]
|
||
37%|███▋ | 377/1013 [52:38<1:21:50, 7.72s/it]
|
||
37%|███▋ | 378/1013 [52:46<1:22:47, 7.82s/it]
|
||
37%|███▋ | 379/1013 [52:54<1:20:47, 7.65s/it]
|
||
38%|███▊ | 380/1013 [53:01<1:20:08, 7.60s/it]
|
||
|
||
{'loss': '1.237e-07', 'grad_norm': '0.0002241', 'learning_rate': '3.939e-05', 'entropy': '1.295', 'num_tokens': '3.504e+06', 'logits/chosen': '2.294', 'logits/rejected': '-1.169', 'mean_token_accuracy': '0.6641', 'rewards/chosen': '4.359', 'rewards/rejected': '-15.51', 'rewards/accuracies': '1', 'rewards/margins': '19.87', 'logps/chosen': '-64.16', 'logps/rejected': '-339.4', 'epoch': '1.124'}
|
||
|
||
38%|███▊ | 380/1013 [53:01<1:20:08, 7.60s/it]
|
||
38%|███▊ | 381/1013 [53:09<1:20:27, 7.64s/it]
|
||
38%|███▊ | 382/1013 [53:17<1:22:21, 7.83s/it]
|
||
38%|███▊ | 383/1013 [53:25<1:21:11, 7.73s/it]
|
||
38%|███▊ | 384/1013 [53:32<1:19:35, 7.59s/it]
|
||
38%|███▊ | 385/1013 [53:40<1:20:34, 7.70s/it]
|
||
38%|███▊ | 386/1013 [53:47<1:19:51, 7.64s/it]
|
||
38%|███▊ | 387/1013 [53:55<1:19:57, 7.66s/it]
|
||
38%|███▊ | 388/1013 [54:03<1:20:37, 7.74s/it]
|
||
38%|███▊ | 389/1013 [54:10<1:16:56, 7.40s/it]
|
||
38%|███▊ | 390/1013 [54:17<1:16:25, 7.36s/it]
|
||
|
||
{'loss': '1.195e-07', 'grad_norm': '3.695e-06', 'learning_rate': '3.867e-05', 'entropy': '1.293', 'num_tokens': '3.594e+06', 'logits/chosen': '2.177', 'logits/rejected': '-1.088', 'mean_token_accuracy': '0.657', 'rewards/chosen': '4.462', 'rewards/rejected': '-15.24', 'rewards/accuracies': '1', 'rewards/margins': '19.7', 'logps/chosen': '-69.47', 'logps/rejected': '-327.7', 'epoch': '1.154'}
|
||
|
||
38%|███▊ | 390/1013 [54:17<1:16:25, 7.36s/it]
|
||
39%|███▊ | 391/1013 [54:24<1:16:30, 7.38s/it]
|
||
39%|███▊ | 392/1013 [54:32<1:16:02, 7.35s/it]
|
||
39%|███▉ | 393/1013 [54:39<1:14:53, 7.25s/it]
|
||
39%|███▉ | 394/1013 [54:46<1:14:02, 7.18s/it]
|
||
39%|███▉ | 395/1013 [54:53<1:14:00, 7.19s/it]
|
||
39%|███▉ | 396/1013 [55:00<1:14:01, 7.20s/it]
|
||
39%|███▉ | 397/1013 [55:08<1:15:21, 7.34s/it]
|
||
39%|███▉ | 398/1013 [55:15<1:15:46, 7.39s/it]
|
||
39%|███▉ | 399/1013 [55:23<1:15:39, 7.39s/it]
|
||
39%|███▉ | 400/1013 [55:30<1:14:30, 7.29s/it]
|
||
|
||
{'loss': '7.844e-08', 'grad_norm': '8.941e-06', 'learning_rate': '3.794e-05', 'entropy': '1.255', 'num_tokens': '3.683e+06', 'logits/chosen': '2.283', 'logits/rejected': '-1.142', 'mean_token_accuracy': '0.6629', 'rewards/chosen': '4.419', 'rewards/rejected': '-15.36', 'rewards/accuracies': '1', 'rewards/margins': '19.78', 'logps/chosen': '-64.67', 'logps/rejected': '-324.4', 'epoch': '1.184'}
|
||
|
||
39%|███▉ | 400/1013 [55:30<1:14:30, 7.29s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.30it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.64it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:31, 4.38it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.98it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.08it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.30it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.03it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.29it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.21it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.92it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:33, 3.84it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.63it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.64it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.97it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.24it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:28, 4.32it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.83it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.64it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.72it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.66it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.74it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.70it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.85it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 4.01it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.56it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.46it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.48it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.41it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.45it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.65it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.87it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 3.90it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.79it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:26, 3.98it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.97it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:27, 3.73it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.92it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:25, 3.94it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.70it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.63it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.72it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.88it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.12it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.19it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:28, 3.39it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.42it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.46it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.49it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.61it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.79it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.52it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.64it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.82it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.85it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.13it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.23it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.00it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:19, 4.25it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:22, 3.63it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:23, 3.42it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.42it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.15it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.33it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.43it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.10it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.40it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.49it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.45it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.38it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.52it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.65it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:16, 3.95it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.96it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.40it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.73it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:17, 3.40it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.30it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.31it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:22<00:16, 3.47it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 4.00it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.09it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 3.96it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:14, 3.83it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.86it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.14it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 3.99it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 3.99it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.70it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.32it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.55it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.90it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 4.01it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.80it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:12, 3.54it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.79it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:10, 3.73it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.55it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:10, 3.80it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.71it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.66it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.82it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:28<00:08, 3.97it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.96it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.06it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.68it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.83it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.34it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.51it/s][A
|
||
|
||
80%|████████ | 115/143 [00:30<00:07, 3.52it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.71it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.55it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.89it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:31<00:05, 4.17it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.96it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.78it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:04, 4.21it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:32<00:05, 3.94it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.03it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.45it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:33<00:03, 4.39it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:33<00:03, 4.07it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:03, 3.85it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 3.98it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:34<00:03, 4.10it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:34<00:02, 4.21it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.14it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.61it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:35<00:02, 3.58it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.45it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.66it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:36<00:01, 3.52it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:36<00:01, 3.50it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.62it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.94it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:37<00:00, 3.85it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:37<00:00, 3.75it/s][A
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.66it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '7.358e-06', 'eval_runtime': '38.58', 'eval_samples_per_second': '7.387', 'eval_steps_per_second': '3.706', 'eval_entropy': '1.281', 'eval_num_tokens': '3.683e+06', 'eval_logits/chosen': '2.247', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6629', 'eval_rewards/chosen': '4.324', 'eval_rewards/rejected': '-15.1', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.42', 'eval_logps/chosen': '-67.91', 'eval_logps/rejected': '-326', 'epoch': '1.184'}
|
||
|
||
39%|███▉ | 400/1013 [56:08<1:14:30, 7.29s/it]
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.66it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.18s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.18s/it]
|
||
|
||
40%|███▉ | 401/1013 [57:27<6:51:04, 40.30s/it]
|
||
40%|███▉ | 402/1013 [57:34<5:09:43, 30.41s/it]
|
||
40%|███▉ | 403/1013 [57:41<3:57:34, 23.37s/it]
|
||
40%|███▉ | 404/1013 [57:49<3:09:06, 18.63s/it]
|
||
40%|███▉ | 405/1013 [57:56<2:35:22, 15.33s/it]
|
||
40%|████ | 406/1013 [58:04<2:09:51, 12.84s/it]
|
||
40%|████ | 407/1013 [58:11<1:52:29, 11.14s/it]
|
||
40%|████ | 408/1013 [58:18<1:42:00, 10.12s/it]
|
||
40%|████ | 409/1013 [58:26<1:33:45, 9.31s/it]
|
||
40%|████ | 410/1013 [58:34<1:29:21, 8.89s/it]
|
||
|
||
{'loss': '1.582e-07', 'grad_norm': '6.05e-06', 'learning_rate': '3.72e-05', 'entropy': '1.279', 'num_tokens': '3.776e+06', 'logits/chosen': '2.235', 'logits/rejected': '-1.204', 'mean_token_accuracy': '0.6723', 'rewards/chosen': '4.321', 'rewards/rejected': '-15.27', 'rewards/accuracies': '1', 'rewards/margins': '19.59', 'logps/chosen': '-61.86', 'logps/rejected': '-331.4', 'epoch': '1.213'}
|
||
|
||
40%|████ | 410/1013 [58:34<1:29:21, 8.89s/it]
|
||
41%|████ | 411/1013 [58:41<1:24:26, 8.42s/it]
|
||
41%|████ | 412/1013 [58:48<1:19:57, 7.98s/it]
|
||
41%|████ | 413/1013 [58:56<1:19:37, 7.96s/it]
|
||
41%|████ | 414/1013 [59:03<1:17:34, 7.77s/it]
|
||
41%|████ | 415/1013 [59:11<1:16:10, 7.64s/it]
|
||
41%|████ | 416/1013 [59:18<1:14:15, 7.46s/it]
|
||
41%|████ | 417/1013 [59:25<1:13:48, 7.43s/it]
|
||
41%|████▏ | 418/1013 [59:32<1:13:28, 7.41s/it]
|
||
41%|████▏ | 419/1013 [59:40<1:14:32, 7.53s/it]
|
||
41%|████▏ | 420/1013 [59:48<1:14:50, 7.57s/it]
|
||
|
||
{'loss': '9.945e-08', 'grad_norm': '2.787e-06', 'learning_rate': '3.644e-05', 'entropy': '1.282', 'num_tokens': '3.869e+06', 'logits/chosen': '2.271', 'logits/rejected': '-1.192', 'mean_token_accuracy': '0.6634', 'rewards/chosen': '4.3', 'rewards/rejected': '-15.3', 'rewards/accuracies': '1', 'rewards/margins': '19.6', 'logps/chosen': '-64.48', 'logps/rejected': '-332.1', 'epoch': '1.243'}
|
||
|
||
41%|████▏ | 420/1013 [59:48<1:14:50, 7.57s/it]
|
||
42%|████▏ | 421/1013 [59:56<1:14:57, 7.60s/it]
|
||
42%|████▏ | 422/1013 [1:00:03<1:14:09, 7.53s/it]
|
||
42%|████▏ | 423/1013 [1:00:10<1:13:50, 7.51s/it]
|
||
42%|████▏ | 424/1013 [1:00:18<1:12:54, 7.43s/it]
|
||
42%|████▏ | 425/1013 [1:00:25<1:12:37, 7.41s/it]
|
||
42%|████▏ | 426/1013 [1:00:32<1:12:16, 7.39s/it]
|
||
42%|████▏ | 427/1013 [1:00:40<1:14:01, 7.58s/it]
|
||
42%|████▏ | 428/1013 [1:00:48<1:13:27, 7.53s/it]
|
||
42%|████▏ | 429/1013 [1:00:55<1:11:59, 7.40s/it]
|
||
42%|████▏ | 430/1013 [1:01:02<1:12:26, 7.45s/it]
|
||
|
||
{'loss': '2.405e-07', 'grad_norm': '6.294e-05', 'learning_rate': '3.567e-05', 'entropy': '1.276', 'num_tokens': '3.962e+06', 'logits/chosen': '2.305', 'logits/rejected': '-1.136', 'mean_token_accuracy': '0.6751', 'rewards/chosen': '4.183', 'rewards/rejected': '-15.29', 'rewards/accuracies': '1', 'rewards/margins': '19.47', 'logps/chosen': '-64.89', 'logps/rejected': '-334', 'epoch': '1.273'}
|
||
|
||
42%|████▏ | 430/1013 [1:01:02<1:12:26, 7.45s/it]
|
||
43%|████▎ | 431/1013 [1:01:10<1:11:33, 7.38s/it]
|
||
43%|████▎ | 432/1013 [1:01:17<1:10:30, 7.28s/it]
|
||
43%|████▎ | 433/1013 [1:01:25<1:12:08, 7.46s/it]
|
||
43%|████▎ | 434/1013 [1:01:32<1:12:10, 7.48s/it]
|
||
43%|████▎ | 435/1013 [1:01:39<1:10:50, 7.35s/it]
|
||
43%|████▎ | 436/1013 [1:01:46<1:10:23, 7.32s/it]
|
||
43%|████▎ | 437/1013 [1:01:54<1:10:39, 7.36s/it]
|
||
43%|████▎ | 438/1013 [1:02:01<1:09:46, 7.28s/it]
|
||
43%|████▎ | 439/1013 [1:02:08<1:10:19, 7.35s/it]
|
||
43%|████▎ | 440/1013 [1:02:16<1:09:22, 7.27s/it]
|
||
|
||
{'loss': '2.914e-07', 'grad_norm': '0.0001268', 'learning_rate': '3.488e-05', 'entropy': '1.28', 'num_tokens': '4.051e+06', 'logits/chosen': '2.346', 'logits/rejected': '-1.232', 'mean_token_accuracy': '0.6791', 'rewards/chosen': '4.32', 'rewards/rejected': '-15.07', 'rewards/accuracies': '1', 'rewards/margins': '19.39', 'logps/chosen': '-58.36', 'logps/rejected': '-320.9', 'epoch': '1.302'}
|
||
|
||
43%|████▎ | 440/1013 [1:02:16<1:09:22, 7.27s/it]
|
||
44%|████▎ | 441/1013 [1:02:23<1:10:26, 7.39s/it]
|
||
44%|████▎ | 442/1013 [1:02:31<1:11:32, 7.52s/it]
|
||
44%|████▎ | 443/1013 [1:02:39<1:12:06, 7.59s/it]
|
||
44%|████▍ | 444/1013 [1:02:46<1:10:32, 7.44s/it]
|
||
44%|████▍ | 445/1013 [1:02:53<1:10:41, 7.47s/it]
|
||
44%|████▍ | 446/1013 [1:03:01<1:11:50, 7.60s/it]
|
||
44%|████▍ | 447/1013 [1:03:09<1:11:34, 7.59s/it]
|
||
44%|████▍ | 448/1013 [1:03:16<1:10:30, 7.49s/it]
|
||
44%|████▍ | 449/1013 [1:03:23<1:08:23, 7.28s/it]
|
||
44%|████▍ | 450/1013 [1:03:30<1:09:09, 7.37s/it]
|
||
|
||
{'loss': '1.31e-07', 'grad_norm': '3.934e-05', 'learning_rate': '3.409e-05', 'entropy': '1.261', 'num_tokens': '4.145e+06', 'logits/chosen': '2.359', 'logits/rejected': '-1.181', 'mean_token_accuracy': '0.6829', 'rewards/chosen': '4.355', 'rewards/rejected': '-15.14', 'rewards/accuracies': '1', 'rewards/margins': '19.49', 'logps/chosen': '-57.82', 'logps/rejected': '-327.4', 'epoch': '1.332'}
|
||
|
||
44%|████▍ | 450/1013 [1:03:30<1:09:09, 7.37s/it]
|
||
45%|████▍ | 451/1013 [1:03:38<1:08:28, 7.31s/it]
|
||
45%|████▍ | 452/1013 [1:03:45<1:08:56, 7.37s/it]
|
||
45%|████▍ | 453/1013 [1:03:52<1:08:43, 7.36s/it]
|
||
45%|████▍ | 454/1013 [1:04:00<1:07:44, 7.27s/it]
|
||
45%|████▍ | 455/1013 [1:04:07<1:07:55, 7.30s/it]
|
||
45%|████▌ | 456/1013 [1:04:14<1:06:01, 7.11s/it]
|
||
45%|████▌ | 457/1013 [1:04:21<1:06:39, 7.19s/it]
|
||
45%|████▌ | 458/1013 [1:04:28<1:06:49, 7.22s/it]
|
||
45%|████▌ | 459/1013 [1:04:36<1:06:46, 7.23s/it]
|
||
45%|████▌ | 460/1013 [1:04:43<1:08:33, 7.44s/it]
|
||
|
||
{'loss': '1.477e-07', 'grad_norm': '7.153e-06', 'learning_rate': '3.328e-05', 'entropy': '1.272', 'num_tokens': '4.236e+06', 'logits/chosen': '2.284', 'logits/rejected': '-1.066', 'mean_token_accuracy': '0.6687', 'rewards/chosen': '4.341', 'rewards/rejected': '-14.95', 'rewards/accuracies': '1', 'rewards/margins': '19.29', 'logps/chosen': '-65.58', 'logps/rejected': '-324.4', 'epoch': '1.361'}
|
||
|
||
45%|████▌ | 460/1013 [1:04:43<1:08:33, 7.44s/it]
|
||
46%|████▌ | 461/1013 [1:04:51<1:08:13, 7.41s/it]
|
||
46%|████▌ | 462/1013 [1:04:59<1:08:53, 7.50s/it]
|
||
46%|████▌ | 463/1013 [1:05:06<1:08:37, 7.49s/it]
|
||
46%|████▌ | 464/1013 [1:05:14<1:09:10, 7.56s/it]
|
||
46%|████▌ | 465/1013 [1:05:21<1:07:53, 7.43s/it]
|
||
46%|████▌ | 466/1013 [1:05:29<1:09:14, 7.59s/it]
|
||
46%|████▌ | 467/1013 [1:05:36<1:07:32, 7.42s/it]
|
||
46%|████▌ | 468/1013 [1:05:43<1:07:53, 7.47s/it]
|
||
46%|████▋ | 469/1013 [1:05:50<1:06:05, 7.29s/it]
|
||
46%|████▋ | 470/1013 [1:05:58<1:06:45, 7.38s/it]
|
||
|
||
{'loss': '2.972e-07', 'grad_norm': '0.0001192', 'learning_rate': '3.246e-05', 'entropy': '1.287', 'num_tokens': '4.328e+06', 'logits/chosen': '2.265', 'logits/rejected': '-1.102', 'mean_token_accuracy': '0.6702', 'rewards/chosen': '4.188', 'rewards/rejected': '-15.2', 'rewards/accuracies': '1', 'rewards/margins': '19.39', 'logps/chosen': '-63.99', 'logps/rejected': '-333', 'epoch': '1.391'}
|
||
|
||
46%|████▋ | 470/1013 [1:05:58<1:06:45, 7.38s/it]
|
||
46%|████▋ | 471/1013 [1:06:05<1:06:34, 7.37s/it]
|
||
47%|████▋ | 472/1013 [1:06:13<1:06:16, 7.35s/it]
|
||
47%|████▋ | 473/1013 [1:06:19<1:05:00, 7.22s/it]
|
||
47%|████▋ | 474/1013 [1:06:27<1:05:05, 7.25s/it]
|
||
47%|████▋ | 475/1013 [1:06:34<1:04:39, 7.21s/it]
|
||
47%|████▋ | 476/1013 [1:06:41<1:05:01, 7.27s/it]
|
||
47%|████▋ | 477/1013 [1:06:49<1:07:13, 7.53s/it]
|
||
47%|████▋ | 478/1013 [1:06:57<1:06:35, 7.47s/it]
|
||
47%|████▋ | 479/1013 [1:07:04<1:06:26, 7.47s/it]
|
||
47%|████▋ | 480/1013 [1:07:11<1:05:08, 7.33s/it]
|
||
|
||
{'loss': '2.586e-07', 'grad_norm': '9.871e-05', 'learning_rate': '3.164e-05', 'entropy': '1.294', 'num_tokens': '4.42e+06', 'logits/chosen': '2.307', 'logits/rejected': '-1.166', 'mean_token_accuracy': '0.6737', 'rewards/chosen': '4.177', 'rewards/rejected': '-15.15', 'rewards/accuracies': '1', 'rewards/margins': '19.33', 'logps/chosen': '-61.82', 'logps/rejected': '-332.9', 'epoch': '1.421'}
|
||
|
||
47%|████▋ | 480/1013 [1:07:11<1:05:08, 7.33s/it]
|
||
47%|████▋ | 481/1013 [1:07:18<1:03:48, 7.20s/it]
|
||
48%|████▊ | 482/1013 [1:07:26<1:04:17, 7.27s/it]
|
||
48%|████▊ | 483/1013 [1:07:33<1:04:27, 7.30s/it]
|
||
48%|████▊ | 484/1013 [1:07:40<1:04:53, 7.36s/it]
|
||
48%|████▊ | 485/1013 [1:07:47<1:03:22, 7.20s/it]
|
||
48%|████▊ | 486/1013 [1:07:54<1:02:24, 7.11s/it]
|
||
48%|████▊ | 487/1013 [1:08:02<1:05:15, 7.44s/it]
|
||
48%|████▊ | 488/1013 [1:08:10<1:06:08, 7.56s/it]
|
||
48%|████▊ | 489/1013 [1:08:18<1:07:12, 7.70s/it]
|
||
48%|████▊ | 490/1013 [1:08:25<1:05:35, 7.52s/it]
|
||
|
||
{'loss': '8.574e-08', 'grad_norm': '6.771e-05', 'learning_rate': '3.08e-05', 'entropy': '1.276', 'num_tokens': '4.511e+06', 'logits/chosen': '2.339', 'logits/rejected': '-1.179', 'mean_token_accuracy': '0.677', 'rewards/chosen': '4.381', 'rewards/rejected': '-15.2', 'rewards/accuracies': '1', 'rewards/margins': '19.58', 'logps/chosen': '-58.54', 'logps/rejected': '-332.7', 'epoch': '1.45'}
|
||
|
||
48%|████▊ | 490/1013 [1:08:25<1:05:35, 7.52s/it]
|
||
48%|████▊ | 491/1013 [1:08:33<1:05:51, 7.57s/it]
|
||
49%|████▊ | 492/1013 [1:08:41<1:06:45, 7.69s/it]
|
||
49%|████▊ | 493/1013 [1:08:49<1:06:43, 7.70s/it]
|
||
49%|████▉ | 494/1013 [1:08:56<1:05:03, 7.52s/it]
|
||
49%|████▉ | 495/1013 [1:09:03<1:04:33, 7.48s/it]
|
||
49%|████▉ | 496/1013 [1:09:11<1:04:47, 7.52s/it]
|
||
49%|████▉ | 497/1013 [1:09:19<1:06:23, 7.72s/it]
|
||
49%|████▉ | 498/1013 [1:09:26<1:04:56, 7.57s/it]
|
||
49%|████▉ | 499/1013 [1:09:33<1:03:49, 7.45s/it]
|
||
49%|████▉ | 500/1013 [1:09:41<1:03:06, 7.38s/it]
|
||
|
||
{'loss': '3.208e-07', 'grad_norm': '8.047e-06', 'learning_rate': '2.996e-05', 'entropy': '1.259', 'num_tokens': '4.605e+06', 'logits/chosen': '2.251', 'logits/rejected': '-1.136', 'mean_token_accuracy': '0.6653', 'rewards/chosen': '4.144', 'rewards/rejected': '-15.39', 'rewards/accuracies': '1', 'rewards/margins': '19.53', 'logps/chosen': '-66', 'logps/rejected': '-332.1', 'epoch': '1.48'}
|
||
|
||
49%|████▉ | 500/1013 [1:09:41<1:03:06, 7.38s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.24it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.62it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.33it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.95it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.06it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.30it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.03it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.29it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:31, 4.17it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.21it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.92it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:33, 3.84it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.63it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.64it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.95it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.23it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.31it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.82it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.63it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.71it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.66it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.75it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.69it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.84it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 4.00it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.56it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.46it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.48it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.40it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.44it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.66it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.87it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:27, 3.91it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.79it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:26, 3.99it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 4.00it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.98it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.71it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.90it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:26, 3.91it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.68it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.62it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.71it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.86it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.10it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.18it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:28, 3.38it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.41it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.46it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.48it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.60it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:13<00:23, 3.77it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.53it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.64it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.81it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.84it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.11it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.23it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.00it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:15<00:19, 4.25it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:22, 3.63it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:23, 3.42it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.42it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.14it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.33it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.43it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.10it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.41it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.48it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.44it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.42it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.37it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.51it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.63it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:20<00:16, 3.93it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.94it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.39it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.72it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:17, 3.40it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.29it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.31it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:16, 3.48it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 4.00it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.08it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 3.95it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:23<00:14, 3.81it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.84it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.13it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 3.97it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:24<00:12, 3.98it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.69it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.31it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.54it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.87it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 3.99it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.79it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:26<00:12, 3.53it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.71it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.54it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:27<00:10, 3.78it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.70it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.66it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.81it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.96it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.95it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.06it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.68it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.84it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.34it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.50it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.68it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.54it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.87it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:31<00:05, 4.16it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.93it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.76it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:05, 4.19it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:32<00:05, 3.92it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.02it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.45it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:33<00:03, 4.39it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:33<00:03, 4.08it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:03, 3.85it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 3.96it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:34<00:03, 4.09it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:34<00:02, 4.20it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.12it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.60it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:35<00:02, 3.57it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.45it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.65it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:36<00:01, 3.51it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:36<00:01, 3.49it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.62it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.93it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:37<00:00, 3.84it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:37<00:00, 3.74it/s][A
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.65it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '7.327e-06', 'eval_runtime': '38.66', 'eval_samples_per_second': '7.371', 'eval_steps_per_second': '3.699', 'eval_entropy': '1.281', 'eval_num_tokens': '4.605e+06', 'eval_logits/chosen': '2.245', 'eval_logits/rejected': '-1.16', 'eval_mean_token_accuracy': '0.6633', 'eval_rewards/chosen': '4.323', 'eval_rewards/rejected': '-15.11', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.44', 'eval_logps/chosen': '-67.92', 'eval_logps/rejected': '-326.2', 'epoch': '1.48'}
|
||
|
||
49%|████▉ | 500/1013 [1:10:19<1:03:06, 7.38s/it]
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.65it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.58s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.58s/it]
|
||
|
||
49%|████▉ | 501/1013 [1:11:43<5:57:21, 41.88s/it]
|
||
50%|████▉ | 502/1013 [1:11:50<4:28:21, 31.51s/it]
|
||
50%|████▉ | 503/1013 [1:11:58<3:26:58, 24.35s/it]
|
||
50%|████▉ | 504/1013 [1:12:05<2:41:52, 19.08s/it]
|
||
50%|████▉ | 505/1013 [1:12:13<2:13:01, 15.71s/it]
|
||
50%|████▉ | 506/1013 [1:12:20<1:51:26, 13.19s/it]
|
||
50%|█████ | 507/1013 [1:12:27<1:34:44, 11.23s/it]
|
||
50%|█████ | 508/1013 [1:12:34<1:25:16, 10.13s/it]
|
||
50%|█████ | 509/1013 [1:12:42<1:18:29, 9.34s/it]
|
||
50%|█████ | 510/1013 [1:12:49<1:13:29, 8.77s/it]
|
||
|
||
{'loss': '1.007e-07', 'grad_norm': '0.0001259', 'learning_rate': '2.911e-05', 'entropy': '1.262', 'num_tokens': '4.695e+06', 'logits/chosen': '2.294', 'logits/rejected': '-1.094', 'mean_token_accuracy': '0.666', 'rewards/chosen': '4.359', 'rewards/rejected': '-15.34', 'rewards/accuracies': '1', 'rewards/margins': '19.7', 'logps/chosen': '-64.26', 'logps/rejected': '-325.9', 'epoch': '1.51'}
|
||
|
||
50%|█████ | 510/1013 [1:12:49<1:13:29, 8.77s/it]
|
||
50%|█████ | 511/1013 [1:12:56<1:09:29, 8.31s/it]
|
||
51%|█████ | 512/1013 [1:13:03<1:06:43, 7.99s/it]
|
||
51%|█████ | 513/1013 [1:13:11<1:04:39, 7.76s/it]
|
||
51%|█████ | 514/1013 [1:13:18<1:04:28, 7.75s/it]
|
||
51%|█████ | 515/1013 [1:13:26<1:03:31, 7.65s/it]
|
||
51%|█████ | 516/1013 [1:13:33<1:03:11, 7.63s/it]
|
||
51%|█████ | 517/1013 [1:13:41<1:02:39, 7.58s/it]
|
||
51%|█████ | 518/1013 [1:13:48<1:02:10, 7.54s/it]
|
||
51%|█████ | 519/1013 [1:13:56<1:01:13, 7.44s/it]
|
||
51%|█████▏ | 520/1013 [1:14:03<1:00:03, 7.31s/it]
|
||
|
||
{'loss': '1.422e-07', 'grad_norm': '8.821e-05', 'learning_rate': '2.826e-05', 'entropy': '1.271', 'num_tokens': '4.789e+06', 'logits/chosen': '2.228', 'logits/rejected': '-1.113', 'mean_token_accuracy': '0.6668', 'rewards/chosen': '4.314', 'rewards/rejected': '-14.96', 'rewards/accuracies': '1', 'rewards/margins': '19.27', 'logps/chosen': '-69.59', 'logps/rejected': '-321.3', 'epoch': '1.539'}
|
||
|
||
51%|█████▏ | 520/1013 [1:14:03<1:00:03, 7.31s/it]
|
||
51%|█████▏ | 521/1013 [1:14:10<1:00:37, 7.39s/it]
|
||
52%|█████▏ | 522/1013 [1:14:17<1:00:16, 7.37s/it]
|
||
52%|█████▏ | 523/1013 [1:14:26<1:02:22, 7.64s/it]
|
||
52%|█████▏ | 524/1013 [1:14:33<1:00:26, 7.42s/it]
|
||
52%|█████▏ | 525/1013 [1:14:39<58:40, 7.21s/it]
|
||
52%|█████▏ | 526/1013 [1:14:46<58:13, 7.17s/it]
|
||
52%|█████▏ | 527/1013 [1:14:54<57:53, 7.15s/it]
|
||
52%|█████▏ | 528/1013 [1:15:01<57:37, 7.13s/it]
|
||
52%|█████▏ | 529/1013 [1:15:08<58:48, 7.29s/it]
|
||
52%|█████▏ | 530/1013 [1:15:15<57:39, 7.16s/it]
|
||
|
||
{'loss': '1.384e-07', 'grad_norm': '0.000246', 'learning_rate': '2.741e-05', 'entropy': '1.277', 'num_tokens': '4.878e+06', 'logits/chosen': '2.317', 'logits/rejected': '-1.221', 'mean_token_accuracy': '0.6752', 'rewards/chosen': '4.162', 'rewards/rejected': '-14.95', 'rewards/accuracies': '1', 'rewards/margins': '19.11', 'logps/chosen': '-58.48', 'logps/rejected': '-321.2', 'epoch': '1.569'}
|
||
|
||
52%|█████▏ | 530/1013 [1:15:15<57:39, 7.16s/it]
|
||
52%|█████▏ | 531/1013 [1:15:23<58:02, 7.23s/it]
|
||
53%|█████▎ | 532/1013 [1:15:30<57:50, 7.21s/it]
|
||
53%|█████▎ | 533/1013 [1:15:37<56:52, 7.11s/it]
|
||
53%|█████▎ | 534/1013 [1:15:44<57:32, 7.21s/it]
|
||
53%|█████▎ | 535/1013 [1:15:52<59:28, 7.47s/it]
|
||
53%|█████▎ | 536/1013 [1:16:00<1:00:23, 7.60s/it]
|
||
53%|█████▎ | 537/1013 [1:16:07<1:00:03, 7.57s/it]
|
||
53%|█████▎ | 538/1013 [1:16:15<59:18, 7.49s/it]
|
||
53%|█████▎ | 539/1013 [1:16:22<58:15, 7.38s/it]
|
||
53%|█████▎ | 540/1013 [1:16:29<58:14, 7.39s/it]
|
||
|
||
{'loss': '1.751e-07', 'grad_norm': '3.844e-06', 'learning_rate': '2.655e-05', 'entropy': '1.262', 'num_tokens': '4.97e+06', 'logits/chosen': '2.263', 'logits/rejected': '-1.121', 'mean_token_accuracy': '0.6701', 'rewards/chosen': '4.282', 'rewards/rejected': '-15.32', 'rewards/accuracies': '1', 'rewards/margins': '19.61', 'logps/chosen': '-64.28', 'logps/rejected': '-328.7', 'epoch': '1.599'}
|
||
|
||
53%|█████▎ | 540/1013 [1:16:29<58:14, 7.39s/it]
|
||
53%|█████▎ | 541/1013 [1:16:37<59:09, 7.52s/it]
|
||
54%|█████▎ | 542/1013 [1:16:45<59:04, 7.53s/it]
|
||
54%|█████▎ | 543/1013 [1:16:52<59:00, 7.53s/it]
|
||
54%|█████▎ | 544/1013 [1:17:00<58:55, 7.54s/it]
|
||
54%|█████▍ | 545/1013 [1:17:08<59:33, 7.63s/it]
|
||
54%|█████▍ | 546/1013 [1:17:15<58:33, 7.52s/it]
|
||
54%|█████▍ | 547/1013 [1:17:22<58:16, 7.50s/it]
|
||
54%|█████▍ | 548/1013 [1:17:30<58:38, 7.57s/it]
|
||
54%|█████▍ | 549/1013 [1:17:38<58:21, 7.55s/it]
|
||
54%|█████▍ | 550/1013 [1:17:45<57:31, 7.45s/it]
|
||
|
||
{'loss': '1.952e-07', 'grad_norm': '1.49e-05', 'learning_rate': '2.569e-05', 'entropy': '1.266', 'num_tokens': '5.065e+06', 'logits/chosen': '2.304', 'logits/rejected': '-1.12', 'mean_token_accuracy': '0.6727', 'rewards/chosen': '4.242', 'rewards/rejected': '-15.33', 'rewards/accuracies': '1', 'rewards/margins': '19.57', 'logps/chosen': '-63.53', 'logps/rejected': '-332.4', 'epoch': '1.628'}
|
||
|
||
54%|█████▍ | 550/1013 [1:17:45<57:31, 7.45s/it]
|
||
54%|█████▍ | 551/1013 [1:17:52<57:47, 7.51s/it]
|
||
54%|█████▍ | 552/1013 [1:18:00<58:09, 7.57s/it]
|
||
55%|█████▍ | 553/1013 [1:18:07<57:14, 7.47s/it]
|
||
55%|█████▍ | 554/1013 [1:18:15<57:06, 7.47s/it]
|
||
55%|█████▍ | 555/1013 [1:18:22<55:36, 7.29s/it]
|
||
55%|█████▍ | 556/1013 [1:18:29<54:59, 7.22s/it]
|
||
55%|█████▍ | 557/1013 [1:18:36<55:04, 7.25s/it]
|
||
55%|█████▌ | 558/1013 [1:18:44<55:41, 7.34s/it]
|
||
55%|█████▌ | 559/1013 [1:18:51<54:49, 7.25s/it]
|
||
55%|█████▌ | 560/1013 [1:18:58<54:38, 7.24s/it]
|
||
|
||
{'loss': '1.471e-07', 'grad_norm': '3.934e-06', 'learning_rate': '2.483e-05', 'entropy': '1.272', 'num_tokens': '5.155e+06', 'logits/chosen': '2.315', 'logits/rejected': '-1.231', 'mean_token_accuracy': '0.6736', 'rewards/chosen': '4.429', 'rewards/rejected': '-15.17', 'rewards/accuracies': '1', 'rewards/margins': '19.6', 'logps/chosen': '-60.61', 'logps/rejected': '-325.5', 'epoch': '1.658'}
|
||
|
||
55%|█████▌ | 560/1013 [1:18:58<54:38, 7.24s/it]
|
||
55%|█████▌ | 561/1013 [1:19:05<54:26, 7.23s/it]
|
||
55%|█████▌ | 562/1013 [1:19:13<55:21, 7.36s/it]
|
||
56%|█████▌ | 563/1013 [1:19:20<54:56, 7.32s/it]
|
||
56%|█████▌ | 564/1013 [1:19:28<55:34, 7.43s/it]
|
||
56%|█████▌ | 565/1013 [1:19:35<55:20, 7.41s/it]
|
||
56%|█████▌ | 566/1013 [1:19:43<55:52, 7.50s/it]
|
||
56%|█████▌ | 567/1013 [1:19:50<55:11, 7.42s/it]
|
||
56%|█████▌ | 568/1013 [1:19:57<55:06, 7.43s/it]
|
||
56%|█████▌ | 569/1013 [1:20:05<54:26, 7.36s/it]
|
||
56%|█████▋ | 570/1013 [1:20:12<53:29, 7.25s/it]
|
||
|
||
{'loss': '1.805e-07', 'grad_norm': '0.0003395', 'learning_rate': '2.397e-05', 'entropy': '1.281', 'num_tokens': '5.248e+06', 'logits/chosen': '2.255', 'logits/rejected': '-1.159', 'mean_token_accuracy': '0.6601', 'rewards/chosen': '4.413', 'rewards/rejected': '-15.06', 'rewards/accuracies': '1', 'rewards/margins': '19.47', 'logps/chosen': '-64.34', 'logps/rejected': '-327.6', 'epoch': '1.687'}
|
||
|
||
56%|█████▋ | 570/1013 [1:20:12<53:29, 7.25s/it]
|
||
56%|█████▋ | 571/1013 [1:20:19<53:33, 7.27s/it]
|
||
56%|█████▋ | 572/1013 [1:20:26<54:03, 7.36s/it]
|
||
57%|█████▋ | 573/1013 [1:20:34<54:30, 7.43s/it]
|
||
57%|█████▋ | 574/1013 [1:20:42<54:48, 7.49s/it]
|
||
57%|█████▋ | 575/1013 [1:20:49<53:46, 7.37s/it]
|
||
57%|█████▋ | 576/1013 [1:20:56<53:03, 7.29s/it]
|
||
57%|█████▋ | 577/1013 [1:21:04<53:48, 7.40s/it]
|
||
57%|█████▋ | 578/1013 [1:21:11<53:56, 7.44s/it]
|
||
57%|█████▋ | 579/1013 [1:21:19<54:21, 7.52s/it]
|
||
57%|█████▋ | 580/1013 [1:21:26<53:01, 7.35s/it]
|
||
|
||
{'loss': '2.299e-07', 'grad_norm': '0.0001183', 'learning_rate': '2.311e-05', 'entropy': '1.269', 'num_tokens': '5.341e+06', 'logits/chosen': '2.278', 'logits/rejected': '-1.179', 'mean_token_accuracy': '0.667', 'rewards/chosen': '4.299', 'rewards/rejected': '-15.06', 'rewards/accuracies': '1', 'rewards/margins': '19.36', 'logps/chosen': '-66.66', 'logps/rejected': '-323.9', 'epoch': '1.717'}
|
||
|
||
57%|█████▋ | 580/1013 [1:21:26<53:01, 7.35s/it]
|
||
57%|█████▋ | 581/1013 [1:21:33<52:57, 7.36s/it]
|
||
57%|█████▋ | 582/1013 [1:21:40<52:03, 7.25s/it]
|
||
58%|█████▊ | 583/1013 [1:21:48<53:24, 7.45s/it]
|
||
58%|█████▊ | 584/1013 [1:21:56<54:23, 7.61s/it]
|
||
58%|█████▊ | 585/1013 [1:22:03<53:40, 7.52s/it]
|
||
58%|█████▊ | 586/1013 [1:22:11<52:51, 7.43s/it]
|
||
58%|█████▊ | 587/1013 [1:22:18<52:27, 7.39s/it]
|
||
58%|█████▊ | 588/1013 [1:22:25<52:29, 7.41s/it]
|
||
58%|█████▊ | 589/1013 [1:22:33<52:15, 7.40s/it]
|
||
58%|█████▊ | 590/1013 [1:22:40<51:33, 7.31s/it]
|
||
|
||
{'loss': '5.122e-07', 'grad_norm': '9.894e-06', 'learning_rate': '2.225e-05', 'entropy': '1.303', 'num_tokens': '5.433e+06', 'logits/chosen': '2.242', 'logits/rejected': '-1.124', 'mean_token_accuracy': '0.658', 'rewards/chosen': '4.279', 'rewards/rejected': '-14.9', 'rewards/accuracies': '1', 'rewards/margins': '19.18', 'logps/chosen': '-66.86', 'logps/rejected': '-326.8', 'epoch': '1.747'}
|
||
|
||
58%|█████▊ | 590/1013 [1:22:40<51:33, 7.31s/it]
|
||
58%|█████▊ | 591/1013 [1:22:47<51:09, 7.27s/it]
|
||
58%|█████▊ | 592/1013 [1:22:55<52:36, 7.50s/it]
|
||
59%|█████▊ | 593/1013 [1:23:02<51:59, 7.43s/it]
|
||
59%|█████▊ | 594/1013 [1:23:10<51:59, 7.45s/it]
|
||
59%|█████▊ | 595/1013 [1:23:17<52:26, 7.53s/it]
|
||
59%|█████▉ | 596/1013 [1:23:25<52:53, 7.61s/it]
|
||
59%|█████▉ | 597/1013 [1:23:33<52:30, 7.57s/it]
|
||
59%|█████▉ | 598/1013 [1:23:40<52:26, 7.58s/it]
|
||
59%|█████▉ | 599/1013 [1:23:48<52:11, 7.56s/it]
|
||
59%|█████▉ | 600/1013 [1:23:55<51:42, 7.51s/it]
|
||
|
||
{'loss': '5.188e-07', 'grad_norm': '1.812e-05', 'learning_rate': '2.14e-05', 'entropy': '1.251', 'num_tokens': '5.528e+06', 'logits/chosen': '2.429', 'logits/rejected': '-1.098', 'mean_token_accuracy': '0.6845', 'rewards/chosen': '4.607', 'rewards/rejected': '-15.17', 'rewards/accuracies': '1', 'rewards/margins': '19.78', 'logps/chosen': '-58.96', 'logps/rejected': '-328.3', 'epoch': '1.776'}
|
||
|
||
59%|█████▉ | 600/1013 [1:23:55<51:42, 7.51s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.30it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.63it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.34it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.97it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.04it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.27it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.01it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.26it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.15it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.19it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.91it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.82it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.63it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.95it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.22it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.30it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.83it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.63it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.71it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.67it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.74it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.67it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.82it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.98it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.55it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.46it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.39it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.64it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.85it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.88it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.77it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.96it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.96it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.95it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.71it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.89it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:26, 3.90it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.67it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.62it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.70it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.86it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.10it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.17it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:28, 3.37it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.41it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.46it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.49it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.60it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:23, 3.76it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.51it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.61it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:23, 3.78it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.81it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.09it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.20it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 3.99it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.24it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:22, 3.63it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:16<00:23, 3.43it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.42it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.14it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.33it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.42it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.09it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.40it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.45it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.47it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:19<00:20, 3.41it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.37it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.50it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.62it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:16, 3.93it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.94it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.38it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.72it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:17, 3.39it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.28it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.30it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:16, 3.47it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 3.99it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.08it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:13, 3.94it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:14, 3.81it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.84it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.12it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:24<00:12, 3.97it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:12, 3.97it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.68it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:25<00:14, 3.30it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:25<00:13, 3.53it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.86it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 3.98it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:26<00:11, 3.78it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.52it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.76it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.72it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:27<00:11, 3.54it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.77it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.69it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.64it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:28<00:09, 3.79it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.93it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.94it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.04it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:29<00:08, 3.67it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.82it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.33it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:30<00:08, 3.50it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.50it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.70it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:31<00:07, 3.54it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:31<00:06, 3.87it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:05, 4.15it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.94it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.76it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:32<00:05, 4.19it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.91it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:06, 2.87it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:05, 3.39it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:04, 3.60it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:04, 3.57it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:04, 3.51it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 3.71it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 3.89it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.04it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.02it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.54it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.52it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.41it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.63it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.60it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.92it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.84it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.73it/s][A
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.70it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '6.924e-06', 'eval_runtime': '39.07', 'eval_samples_per_second': '7.294', 'eval_steps_per_second': '3.66', 'eval_entropy': '1.281', 'eval_num_tokens': '5.528e+06', 'eval_logits/chosen': '2.244', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6635', 'eval_rewards/chosen': '4.315', 'eval_rewards/rejected': '-15.15', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.47', 'eval_logps/chosen': '-68', 'eval_logps/rejected': '-326.6', 'epoch': '1.776'}
|
||
|
||
59%|█████▉ | 600/1013 [1:24:34<51:42, 7.51s/it]
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.70it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:32<00:00, 32.47s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:32<00:00, 32.47s/it]
|
||
|
||
59%|█████▉ | 601/1013 [1:25:55<4:43:21, 41.27s/it]
|
||
59%|█████▉ | 602/1013 [1:26:03<3:33:52, 31.22s/it]
|
||
60%|█████▉ | 603/1013 [1:26:10<2:44:17, 24.04s/it]
|
||
60%|█████▉ | 604/1013 [1:26:17<2:08:43, 18.88s/it]
|
||
60%|█████▉ | 605/1013 [1:26:25<1:45:09, 15.46s/it]
|
||
60%|█████▉ | 606/1013 [1:26:32<1:28:32, 13.05s/it]
|
||
60%|█████▉ | 607/1013 [1:26:39<1:16:14, 11.27s/it]
|
||
60%|██████ | 608/1013 [1:26:47<1:09:32, 10.30s/it]
|
||
60%|██████ | 609/1013 [1:26:55<1:03:31, 9.43s/it]
|
||
60%|██████ | 610/1013 [1:27:02<59:40, 8.88s/it]
|
||
|
||
{'loss': '3.902e-08', 'grad_norm': '1.305e-05', 'learning_rate': '2.055e-05', 'entropy': '1.272', 'num_tokens': '5.62e+06', 'logits/chosen': '2.32', 'logits/rejected': '-1.133', 'mean_token_accuracy': '0.6726', 'rewards/chosen': '4.585', 'rewards/rejected': '-15.43', 'rewards/accuracies': '1', 'rewards/margins': '20.02', 'logps/chosen': '-60.81', 'logps/rejected': '-332.6', 'epoch': '1.806'}
|
||
|
||
60%|██████ | 610/1013 [1:27:02<59:40, 8.88s/it]
|
||
60%|██████ | 611/1013 [1:27:10<56:33, 8.44s/it]
|
||
60%|██████ | 612/1013 [1:27:17<53:51, 8.06s/it]
|
||
61%|██████ | 613/1013 [1:27:24<52:41, 7.90s/it]
|
||
61%|██████ | 614/1013 [1:27:32<52:15, 7.86s/it]
|
||
61%|██████ | 615/1013 [1:27:40<51:09, 7.71s/it]
|
||
61%|██████ | 616/1013 [1:27:46<49:31, 7.48s/it]
|
||
61%|██████ | 617/1013 [1:27:54<49:03, 7.43s/it]
|
||
61%|██████ | 618/1013 [1:28:01<48:26, 7.36s/it]
|
||
61%|██████ | 619/1013 [1:28:09<49:56, 7.60s/it]
|
||
61%|██████ | 620/1013 [1:28:17<49:33, 7.57s/it]
|
||
|
||
{'loss': '1.713e-07', 'grad_norm': '1.633e-05', 'learning_rate': '1.97e-05', 'entropy': '1.265', 'num_tokens': '5.713e+06', 'logits/chosen': '2.259', 'logits/rejected': '-1.05', 'mean_token_accuracy': '0.6619', 'rewards/chosen': '4.14', 'rewards/rejected': '-15.06', 'rewards/accuracies': '1', 'rewards/margins': '19.2', 'logps/chosen': '-66.24', 'logps/rejected': '-322.6', 'epoch': '1.836'}
|
||
|
||
61%|██████ | 620/1013 [1:28:17<49:33, 7.57s/it]
|
||
61%|██████▏ | 621/1013 [1:28:24<48:42, 7.46s/it]
|
||
61%|██████▏ | 622/1013 [1:28:32<49:41, 7.62s/it]
|
||
62%|██████▏ | 623/1013 [1:28:39<49:03, 7.55s/it]
|
||
62%|██████▏ | 624/1013 [1:28:47<48:42, 7.51s/it]
|
||
62%|██████▏ | 625/1013 [1:28:54<48:36, 7.52s/it]
|
||
62%|██████▏ | 626/1013 [1:29:02<48:35, 7.53s/it]
|
||
62%|██████▏ | 627/1013 [1:29:09<48:04, 7.47s/it]
|
||
62%|██████▏ | 628/1013 [1:29:16<47:44, 7.44s/it]
|
||
62%|██████▏ | 629/1013 [1:29:24<46:58, 7.34s/it]
|
||
62%|██████▏ | 630/1013 [1:29:31<46:46, 7.33s/it]
|
||
|
||
{'loss': '9.81e-08', 'grad_norm': '2.956e-05', 'learning_rate': '1.886e-05', 'entropy': '1.268', 'num_tokens': '5.804e+06', 'logits/chosen': '2.307', 'logits/rejected': '-1.197', 'mean_token_accuracy': '0.6677', 'rewards/chosen': '4.233', 'rewards/rejected': '-15.13', 'rewards/accuracies': '1', 'rewards/margins': '19.36', 'logps/chosen': '-65.75', 'logps/rejected': '-326.6', 'epoch': '1.865'}
|
||
|
||
62%|██████▏ | 630/1013 [1:29:31<46:46, 7.33s/it]
|
||
62%|██████▏ | 631/1013 [1:29:38<46:51, 7.36s/it]
|
||
62%|██████▏ | 632/1013 [1:29:46<47:20, 7.46s/it]
|
||
62%|██████▏ | 633/1013 [1:29:53<45:39, 7.21s/it]
|
||
63%|██████▎ | 634/1013 [1:30:00<46:43, 7.40s/it]
|
||
63%|██████▎ | 635/1013 [1:30:08<46:17, 7.35s/it]
|
||
63%|██████▎ | 636/1013 [1:30:15<46:39, 7.43s/it]
|
||
63%|██████▎ | 637/1013 [1:30:23<47:14, 7.54s/it]
|
||
63%|██████▎ | 638/1013 [1:30:30<46:28, 7.44s/it]
|
||
63%|██████▎ | 639/1013 [1:30:37<45:29, 7.30s/it]
|
||
63%|██████▎ | 640/1013 [1:30:45<45:51, 7.38s/it]
|
||
|
||
{'loss': '5.206e-08', 'grad_norm': '1.371e-06', 'learning_rate': '1.803e-05', 'entropy': '1.274', 'num_tokens': '5.897e+06', 'logits/chosen': '2.277', 'logits/rejected': '-1.106', 'mean_token_accuracy': '0.6642', 'rewards/chosen': '4.304', 'rewards/rejected': '-15.57', 'rewards/accuracies': '1', 'rewards/margins': '19.88', 'logps/chosen': '-64.37', 'logps/rejected': '-329.2', 'epoch': '1.895'}
|
||
|
||
63%|██████▎ | 640/1013 [1:30:45<45:51, 7.38s/it]
|
||
63%|██████▎ | 641/1013 [1:30:53<46:26, 7.49s/it]
|
||
63%|██████▎ | 642/1013 [1:31:00<45:29, 7.36s/it]
|
||
63%|██████▎ | 643/1013 [1:31:07<45:40, 7.41s/it]
|
||
64%|██████▎ | 644/1013 [1:31:14<44:56, 7.31s/it]
|
||
64%|██████▎ | 645/1013 [1:31:22<45:21, 7.39s/it]
|
||
64%|██████▍ | 646/1013 [1:31:29<45:33, 7.45s/it]
|
||
64%|██████▍ | 647/1013 [1:31:37<45:24, 7.44s/it]
|
||
64%|██████▍ | 648/1013 [1:31:45<46:21, 7.62s/it]
|
||
64%|██████▍ | 649/1013 [1:31:52<45:51, 7.56s/it]
|
||
64%|██████▍ | 650/1013 [1:32:00<45:20, 7.49s/it]
|
||
|
||
{'loss': '1.451e-07', 'grad_norm': '5.102e-05', 'learning_rate': '1.721e-05', 'entropy': '1.276', 'num_tokens': '5.99e+06', 'logits/chosen': '2.327', 'logits/rejected': '-1.143', 'mean_token_accuracy': '0.6677', 'rewards/chosen': '4.312', 'rewards/rejected': '-15.41', 'rewards/accuracies': '1', 'rewards/margins': '19.72', 'logps/chosen': '-66.03', 'logps/rejected': '-332.1', 'epoch': '1.924'}
|
||
|
||
64%|██████▍ | 650/1013 [1:32:00<45:20, 7.49s/it]
|
||
64%|██████▍ | 651/1013 [1:32:07<45:42, 7.58s/it]
|
||
64%|██████▍ | 652/1013 [1:32:15<46:19, 7.70s/it]
|
||
64%|██████▍ | 653/1013 [1:32:22<45:03, 7.51s/it]
|
||
65%|██████▍ | 654/1013 [1:32:30<44:46, 7.48s/it]
|
||
65%|██████▍ | 655/1013 [1:32:37<44:36, 7.48s/it]
|
||
65%|██████▍ | 656/1013 [1:32:44<43:44, 7.35s/it]
|
||
65%|██████▍ | 657/1013 [1:32:52<43:47, 7.38s/it]
|
||
65%|██████▍ | 658/1013 [1:33:00<44:42, 7.56s/it]
|
||
65%|██████▌ | 659/1013 [1:33:08<44:55, 7.61s/it]
|
||
65%|██████▌ | 660/1013 [1:33:15<44:50, 7.62s/it]
|
||
|
||
{'loss': '1.29e-07', 'grad_norm': '2.456e-05', 'learning_rate': '1.64e-05', 'entropy': '1.27', 'num_tokens': '6.084e+06', 'logits/chosen': '2.289', 'logits/rejected': '-1.128', 'mean_token_accuracy': '0.6573', 'rewards/chosen': '4.226', 'rewards/rejected': '-15.23', 'rewards/accuracies': '1', 'rewards/margins': '19.46', 'logps/chosen': '-64.96', 'logps/rejected': '-326.5', 'epoch': '1.954'}
|
||
|
||
65%|██████▌ | 660/1013 [1:33:15<44:50, 7.62s/it]
|
||
65%|██████▌ | 661/1013 [1:33:23<44:47, 7.63s/it]
|
||
65%|██████▌ | 662/1013 [1:33:30<43:37, 7.46s/it]
|
||
65%|██████▌ | 663/1013 [1:33:37<42:59, 7.37s/it]
|
||
66%|██████▌ | 664/1013 [1:33:45<43:29, 7.48s/it]
|
||
66%|██████▌ | 665/1013 [1:33:52<42:47, 7.38s/it]
|
||
66%|██████▌ | 666/1013 [1:33:59<42:40, 7.38s/it]
|
||
66%|██████▌ | 667/1013 [1:34:06<42:07, 7.30s/it]
|
||
66%|██████▌ | 668/1013 [1:34:15<43:42, 7.60s/it]
|
||
66%|██████▌ | 669/1013 [1:34:22<43:47, 7.64s/it]
|
||
66%|██████▌ | 670/1013 [1:34:30<42:57, 7.52s/it]
|
||
|
||
{'loss': '2.275e-07', 'grad_norm': '1.907e-06', 'learning_rate': '1.559e-05', 'entropy': '1.264', 'num_tokens': '6.177e+06', 'logits/chosen': '2.304', 'logits/rejected': '-1.173', 'mean_token_accuracy': '0.6636', 'rewards/chosen': '4.288', 'rewards/rejected': '-15.12', 'rewards/accuracies': '1', 'rewards/margins': '19.41', 'logps/chosen': '-65.31', 'logps/rejected': '-323.9', 'epoch': '1.984'}
|
||
|
||
66%|██████▌ | 670/1013 [1:34:30<42:57, 7.52s/it]
|
||
66%|██████▌ | 671/1013 [1:34:37<42:55, 7.53s/it]
|
||
66%|██████▋ | 672/1013 [1:34:44<41:54, 7.37s/it]
|
||
66%|██████▋ | 673/1013 [1:34:51<41:17, 7.29s/it]
|
||
67%|██████▋ | 674/1013 [1:34:59<41:59, 7.43s/it]
|
||
67%|██████▋ | 675/1013 [1:35:06<41:40, 7.40s/it]
|
||
67%|██████▋ | 676/1013 [1:35:10<35:28, 6.32s/it]
|
||
67%|██████▋ | 677/1013 [1:35:18<38:25, 6.86s/it]
|
||
67%|██████▋ | 678/1013 [1:35:26<39:19, 7.04s/it]
|
||
67%|██████▋ | 679/1013 [1:35:33<39:02, 7.01s/it]
|
||
67%|██████▋ | 680/1013 [1:35:39<38:21, 6.91s/it]
|
||
|
||
{'loss': '3.613e-07', 'grad_norm': '0.0002556', 'learning_rate': '1.48e-05', 'entropy': '1.278', 'num_tokens': '6.263e+06', 'logits/chosen': '2.397', 'logits/rejected': '-1.121', 'mean_token_accuracy': '0.6631', 'rewards/chosen': '4.139', 'rewards/rejected': '-15.08', 'rewards/accuracies': '1', 'rewards/margins': '19.22', 'logps/chosen': '-61.41', 'logps/rejected': '-324.1', 'epoch': '2.012'}
|
||
|
||
67%|██████▋ | 680/1013 [1:35:39<38:21, 6.91s/it]
|
||
67%|██████▋ | 681/1013 [1:35:48<40:11, 7.26s/it]
|
||
67%|██████▋ | 682/1013 [1:35:55<40:02, 7.26s/it]
|
||
67%|██████▋ | 683/1013 [1:36:02<39:41, 7.22s/it]
|
||
68%|██████▊ | 684/1013 [1:36:10<40:34, 7.40s/it]
|
||
68%|██████▊ | 685/1013 [1:36:17<40:20, 7.38s/it]
|
||
68%|██████▊ | 686/1013 [1:36:25<40:25, 7.42s/it]
|
||
68%|██████▊ | 687/1013 [1:36:32<39:35, 7.29s/it]
|
||
68%|██████▊ | 688/1013 [1:36:39<40:27, 7.47s/it]
|
||
68%|██████▊ | 689/1013 [1:36:47<40:34, 7.51s/it]
|
||
68%|██████▊ | 690/1013 [1:36:55<40:36, 7.54s/it]
|
||
|
||
{'loss': '7.074e-08', 'grad_norm': '4.489e-07', 'learning_rate': '1.402e-05', 'entropy': '1.267', 'num_tokens': '6.358e+06', 'logits/chosen': '2.315', 'logits/rejected': '-1.152', 'mean_token_accuracy': '0.6725', 'rewards/chosen': '4.411', 'rewards/rejected': '-15.46', 'rewards/accuracies': '1', 'rewards/margins': '19.87', 'logps/chosen': '-62.28', 'logps/rejected': '-331.9', 'epoch': '2.041'}
|
||
|
||
68%|██████▊ | 690/1013 [1:36:55<40:36, 7.54s/it]
|
||
68%|██████▊ | 691/1013 [1:37:02<40:07, 7.48s/it]
|
||
68%|██████▊ | 692/1013 [1:37:09<39:40, 7.42s/it]
|
||
68%|██████▊ | 693/1013 [1:37:17<40:15, 7.55s/it]
|
||
69%|██████▊ | 694/1013 [1:37:24<38:46, 7.29s/it]
|
||
69%|██████▊ | 695/1013 [1:37:31<39:11, 7.39s/it]
|
||
69%|██████▊ | 696/1013 [1:37:39<39:07, 7.41s/it]
|
||
69%|██████▉ | 697/1013 [1:37:46<38:50, 7.37s/it]
|
||
69%|██████▉ | 698/1013 [1:37:54<38:37, 7.36s/it]
|
||
69%|██████▉ | 699/1013 [1:38:01<38:34, 7.37s/it]
|
||
69%|██████▉ | 700/1013 [1:38:09<39:20, 7.54s/it]
|
||
|
||
{'loss': '2.164e-07', 'grad_norm': '0.0002995', 'learning_rate': '1.325e-05', 'entropy': '1.267', 'num_tokens': '6.45e+06', 'logits/chosen': '2.292', 'logits/rejected': '-1.126', 'mean_token_accuracy': '0.6636', 'rewards/chosen': '4.283', 'rewards/rejected': '-15.47', 'rewards/accuracies': '1', 'rewards/margins': '19.75', 'logps/chosen': '-65.86', 'logps/rejected': '-331.4', 'epoch': '2.071'}
|
||
|
||
69%|██████▉ | 700/1013 [1:38:09<39:20, 7.54s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.23it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.60it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.32it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.95it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.06it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.27it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.02it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.27it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.16it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.90it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.81it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.61it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.94it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.21it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.29it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.82it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:05<00:33, 3.62it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.70it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.64it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.72it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.67it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.82it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.98it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.54it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.46it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.39it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.44it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.64it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.85it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.88it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.76it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.94it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.95it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.94it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.69it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.89it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:26, 3.90it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.67it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.60it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.68it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.84it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.09it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.17it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:28, 3.36it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:13<00:27, 3.40it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.46it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.48it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.59it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:24, 3.75it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.50it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.60it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:23, 3.78it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.81it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.10it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.20it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 3.98it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.23it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:22, 3.62it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:17<00:23, 3.42it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.41it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:17<00:24, 3.13it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:17<00:22, 3.32it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:22, 3.40it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:24, 3.08it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:18<00:21, 3.38it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.44it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.47it/s][A
|
||
|
||
51%|█████ | 73/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:20<00:20, 3.41it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.35it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.50it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:20<00:18, 3.62it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:16, 3.91it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.92it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:21<00:18, 3.37it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:21<00:16, 3.71it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:18, 3.38it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.27it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:22<00:17, 3.29it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:16, 3.45it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 3.96it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.04it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:23<00:14, 3.92it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:19, 2.76it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:17, 3.03it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:15, 3.43it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:25<00:14, 3.48it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:13, 3.60it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:14, 3.45it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:26<00:15, 3.17it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:26<00:13, 3.42it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:12, 3.77it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 3.91it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:27<00:11, 3.74it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.49it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.73it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.69it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:28<00:11, 3.52it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.77it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.68it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:29<00:10, 3.64it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:29<00:09, 3.80it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.93it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.94it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.04it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:30<00:08, 3.67it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.82it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:08, 3.34it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.69it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:32<00:07, 3.54it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:32<00:06, 3.87it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:05, 4.16it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.94it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:33<00:05, 3.76it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:33<00:05, 4.19it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.92it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.01it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:33<00:04, 4.43it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:03, 4.37it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:03, 4.06it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:03, 3.84it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:34<00:03, 3.96it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 4.08it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.20it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.12it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:35<00:02, 3.58it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.55it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.44it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:36<00:01, 3.64it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.50it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.59it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:37<00:00, 3.92it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.84it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.73it/s][A
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.75it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '7.35e-06', 'eval_runtime': '39.13', 'eval_samples_per_second': '7.283', 'eval_steps_per_second': '3.654', 'eval_entropy': '1.28', 'eval_num_tokens': '6.45e+06', 'eval_logits/chosen': '2.243', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6639', 'eval_rewards/chosen': '4.313', 'eval_rewards/rejected': '-15.16', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.47', 'eval_logps/chosen': '-68.03', 'eval_logps/rejected': '-326.7', 'epoch': '2.071'}
|
||
|
||
69%|██████▉ | 700/1013 [1:38:48<39:20, 7.54s/it]
|
||
|
||
100%|██████████| 143/143 [00:38<00:00, 3.75it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.80s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.80s/it]
|
||
|
||
69%|██████▉ | 701/1013 [1:40:09<3:34:39, 41.28s/it]
|
||
69%|██████▉ | 702/1013 [1:40:16<2:41:14, 31.11s/it]
|
||
69%|██████▉ | 703/1013 [1:40:23<2:03:10, 23.84s/it]
|
||
69%|██████▉ | 704/1013 [1:40:31<1:37:53, 19.01s/it]
|
||
70%|██████▉ | 705/1013 [1:40:38<1:19:40, 15.52s/it]
|
||
70%|██████▉ | 706/1013 [1:40:45<1:06:20, 12.97s/it]
|
||
70%|██████▉ | 707/1013 [1:40:53<58:17, 11.43s/it]
|
||
70%|██████▉ | 708/1013 [1:41:01<52:10, 10.26s/it]
|
||
70%|██████▉ | 709/1013 [1:41:08<47:20, 9.34s/it]
|
||
70%|███████ | 710/1013 [1:41:15<44:23, 8.79s/it]
|
||
|
||
{'loss': '2.142e-07', 'grad_norm': '8.821e-05', 'learning_rate': '1.25e-05', 'entropy': '1.273', 'num_tokens': '6.54e+06', 'logits/chosen': '2.256', 'logits/rejected': '-1.122', 'mean_token_accuracy': '0.6676', 'rewards/chosen': '4.438', 'rewards/rejected': '-14.91', 'rewards/accuracies': '1', 'rewards/margins': '19.35', 'logps/chosen': '-61.83', 'logps/rejected': '-323.8', 'epoch': '2.101'}
|
||
|
||
70%|███████ | 710/1013 [1:41:15<44:23, 8.79s/it]
|
||
70%|███████ | 711/1013 [1:41:23<42:23, 8.42s/it]
|
||
70%|███████ | 712/1013 [1:41:30<40:54, 8.15s/it]
|
||
70%|███████ | 713/1013 [1:41:38<39:34, 7.92s/it]
|
||
70%|███████ | 714/1013 [1:41:45<38:53, 7.80s/it]
|
||
71%|███████ | 715/1013 [1:41:53<38:05, 7.67s/it]
|
||
71%|███████ | 716/1013 [1:42:00<37:08, 7.50s/it]
|
||
71%|███████ | 717/1013 [1:42:07<36:20, 7.36s/it]
|
||
71%|███████ | 718/1013 [1:42:14<36:12, 7.36s/it]
|
||
71%|███████ | 719/1013 [1:42:21<35:41, 7.28s/it]
|
||
71%|███████ | 720/1013 [1:42:29<35:39, 7.30s/it]
|
||
|
||
{'loss': '7.845e-08', 'grad_norm': '6.771e-05', 'learning_rate': '1.176e-05', 'entropy': '1.271', 'num_tokens': '6.63e+06', 'logits/chosen': '2.269', 'logits/rejected': '-1.176', 'mean_token_accuracy': '0.6651', 'rewards/chosen': '4.375', 'rewards/rejected': '-15.26', 'rewards/accuracies': '1', 'rewards/margins': '19.63', 'logps/chosen': '-65.25', 'logps/rejected': '-325.6', 'epoch': '2.13'}
|
||
|
||
71%|███████ | 720/1013 [1:42:29<35:39, 7.30s/it]
|
||
71%|███████ | 721/1013 [1:42:36<35:11, 7.23s/it]
|
||
71%|███████▏ | 722/1013 [1:42:43<35:35, 7.34s/it]
|
||
71%|███████▏ | 723/1013 [1:42:51<36:03, 7.46s/it]
|
||
71%|███████▏ | 724/1013 [1:42:59<36:21, 7.55s/it]
|
||
72%|███████▏ | 725/1013 [1:43:06<35:21, 7.37s/it]
|
||
72%|███████▏ | 726/1013 [1:43:13<35:10, 7.35s/it]
|
||
72%|███████▏ | 727/1013 [1:43:20<35:04, 7.36s/it]
|
||
72%|███████▏ | 728/1013 [1:43:28<35:27, 7.46s/it]
|
||
72%|███████▏ | 729/1013 [1:43:35<34:55, 7.38s/it]
|
||
72%|███████▏ | 730/1013 [1:43:42<34:20, 7.28s/it]
|
||
|
||
{'loss': '6.327e-07', 'grad_norm': '0.000679', 'learning_rate': '1.104e-05', 'entropy': '1.263', 'num_tokens': '6.722e+06', 'logits/chosen': '2.3', 'logits/rejected': '-1.124', 'mean_token_accuracy': '0.6666', 'rewards/chosen': '4.219', 'rewards/rejected': '-15.22', 'rewards/accuracies': '1', 'rewards/margins': '19.43', 'logps/chosen': '-65.31', 'logps/rejected': '-327.7', 'epoch': '2.16'}
|
||
|
||
72%|███████▏ | 730/1013 [1:43:42<34:20, 7.28s/it]
|
||
72%|███████▏ | 731/1013 [1:43:50<34:15, 7.29s/it]
|
||
72%|███████▏ | 732/1013 [1:43:57<34:05, 7.28s/it]
|
||
72%|███████▏ | 733/1013 [1:44:04<34:13, 7.34s/it]
|
||
72%|███████▏ | 734/1013 [1:44:12<34:10, 7.35s/it]
|
||
73%|███████▎ | 735/1013 [1:44:19<34:02, 7.35s/it]
|
||
73%|███████▎ | 736/1013 [1:44:27<34:11, 7.41s/it]
|
||
73%|███████▎ | 737/1013 [1:44:34<33:48, 7.35s/it]
|
||
73%|███████▎ | 738/1013 [1:44:41<34:00, 7.42s/it]
|
||
73%|███████▎ | 739/1013 [1:44:49<33:34, 7.35s/it]
|
||
73%|███████▎ | 740/1013 [1:44:56<33:56, 7.46s/it]
|
||
|
||
{'loss': '1.791e-07', 'grad_norm': '9.06e-06', 'learning_rate': '1.033e-05', 'entropy': '1.284', 'num_tokens': '6.813e+06', 'logits/chosen': '2.292', 'logits/rejected': '-1.282', 'mean_token_accuracy': '0.6699', 'rewards/chosen': '4.311', 'rewards/rejected': '-15.31', 'rewards/accuracies': '1', 'rewards/margins': '19.62', 'logps/chosen': '-66.78', 'logps/rejected': '-333.5', 'epoch': '2.19'}
|
||
|
||
73%|███████▎ | 740/1013 [1:44:56<33:56, 7.46s/it]
|
||
73%|███████▎ | 741/1013 [1:45:04<34:19, 7.57s/it]
|
||
73%|███████▎ | 742/1013 [1:45:12<34:22, 7.61s/it]
|
||
73%|███████▎ | 743/1013 [1:45:19<33:37, 7.47s/it]
|
||
73%|███████▎ | 744/1013 [1:45:27<33:37, 7.50s/it]
|
||
74%|███████▎ | 745/1013 [1:45:34<32:46, 7.34s/it]
|
||
74%|███████▎ | 746/1013 [1:45:41<32:37, 7.33s/it]
|
||
74%|███████▎ | 747/1013 [1:45:48<32:50, 7.41s/it]
|
||
74%|███████▍ | 748/1013 [1:45:56<32:54, 7.45s/it]
|
||
74%|███████▍ | 749/1013 [1:46:03<32:35, 7.41s/it]
|
||
74%|███████▍ | 750/1013 [1:46:11<32:45, 7.47s/it]
|
||
|
||
{'loss': '3.619e-07', 'grad_norm': '2.825e-05', 'learning_rate': '9.645e-06', 'entropy': '1.283', 'num_tokens': '6.906e+06', 'logits/chosen': '2.296', 'logits/rejected': '-1.138', 'mean_token_accuracy': '0.6705', 'rewards/chosen': '4.348', 'rewards/rejected': '-15.13', 'rewards/accuracies': '1', 'rewards/margins': '19.48', 'logps/chosen': '-65.19', 'logps/rejected': '-333.2', 'epoch': '2.219'}
|
||
|
||
74%|███████▍ | 750/1013 [1:46:11<32:45, 7.47s/it]
|
||
74%|███████▍ | 751/1013 [1:46:18<32:36, 7.47s/it]
|
||
74%|███████▍ | 752/1013 [1:46:26<32:11, 7.40s/it]
|
||
74%|███████▍ | 753/1013 [1:46:34<32:43, 7.55s/it]
|
||
74%|███████▍ | 754/1013 [1:46:42<33:08, 7.68s/it]
|
||
75%|███████▍ | 755/1013 [1:46:49<32:52, 7.64s/it]
|
||
75%|███████▍ | 756/1013 [1:46:56<32:12, 7.52s/it]
|
||
75%|███████▍ | 757/1013 [1:47:04<32:37, 7.65s/it]
|
||
75%|███████▍ | 758/1013 [1:47:12<32:32, 7.66s/it]
|
||
75%|███████▍ | 759/1013 [1:47:20<32:51, 7.76s/it]
|
||
75%|███████▌ | 760/1013 [1:47:27<32:03, 7.60s/it]
|
||
|
||
{'loss': '2.773e-07', 'grad_norm': '3.672e-05', 'learning_rate': '8.974e-06', 'entropy': '1.289', 'num_tokens': '7.004e+06', 'logits/chosen': '2.274', 'logits/rejected': '-1.197', 'mean_token_accuracy': '0.6637', 'rewards/chosen': '4.223', 'rewards/rejected': '-15.38', 'rewards/accuracies': '1', 'rewards/margins': '19.61', 'logps/chosen': '-62.73', 'logps/rejected': '-335.8', 'epoch': '2.249'}
|
||
|
||
75%|███████▌ | 760/1013 [1:47:27<32:03, 7.60s/it]
|
||
75%|███████▌ | 761/1013 [1:47:34<30:58, 7.38s/it]
|
||
75%|███████▌ | 762/1013 [1:47:41<30:30, 7.29s/it]
|
||
75%|███████▌ | 763/1013 [1:47:48<30:01, 7.21s/it]
|
||
75%|███████▌ | 764/1013 [1:47:55<29:33, 7.12s/it]
|
||
76%|███████▌ | 765/1013 [1:48:03<30:17, 7.33s/it]
|
||
76%|███████▌ | 766/1013 [1:48:10<30:16, 7.35s/it]
|
||
76%|███████▌ | 767/1013 [1:48:18<30:30, 7.44s/it]
|
||
76%|███████▌ | 768/1013 [1:48:25<30:32, 7.48s/it]
|
||
76%|███████▌ | 769/1013 [1:48:33<30:20, 7.46s/it]
|
||
76%|███████▌ | 770/1013 [1:48:40<29:47, 7.35s/it]
|
||
|
||
{'loss': '6.9e-08', 'grad_norm': '6.819e-05', 'learning_rate': '8.323e-06', 'entropy': '1.271', 'num_tokens': '7.092e+06', 'logits/chosen': '2.315', 'logits/rejected': '-1.184', 'mean_token_accuracy': '0.6749', 'rewards/chosen': '4.219', 'rewards/rejected': '-15.19', 'rewards/accuracies': '1', 'rewards/margins': '19.41', 'logps/chosen': '-60.06', 'logps/rejected': '-324.1', 'epoch': '2.279'}
|
||
|
||
76%|███████▌ | 770/1013 [1:48:40<29:47, 7.35s/it]
|
||
76%|███████▌ | 771/1013 [1:48:47<29:42, 7.36s/it]
|
||
76%|███████▌ | 772/1013 [1:48:55<29:31, 7.35s/it]
|
||
76%|███████▋ | 773/1013 [1:49:02<29:11, 7.30s/it]
|
||
76%|███████▋ | 774/1013 [1:49:10<29:33, 7.42s/it]
|
||
77%|███████▋ | 775/1013 [1:49:17<29:37, 7.47s/it]
|
||
77%|███████▋ | 776/1013 [1:49:25<29:37, 7.50s/it]
|
||
77%|███████▋ | 777/1013 [1:49:33<29:51, 7.59s/it]
|
||
77%|███████▋ | 778/1013 [1:49:40<29:17, 7.48s/it]
|
||
77%|███████▋ | 779/1013 [1:49:47<28:26, 7.29s/it]
|
||
77%|███████▋ | 780/1013 [1:49:54<28:46, 7.41s/it]
|
||
|
||
{'loss': '1.486e-07', 'grad_norm': '7.677e-05', 'learning_rate': '7.691e-06', 'entropy': '1.28', 'num_tokens': '7.183e+06', 'logits/chosen': '2.255', 'logits/rejected': '-1.151', 'mean_token_accuracy': '0.6621', 'rewards/chosen': '4.272', 'rewards/rejected': '-15.11', 'rewards/accuracies': '1', 'rewards/margins': '19.38', 'logps/chosen': '-63.52', 'logps/rejected': '-325.3', 'epoch': '2.308'}
|
||
|
||
77%|███████▋ | 780/1013 [1:49:54<28:46, 7.41s/it]
|
||
77%|███████▋ | 781/1013 [1:50:02<29:00, 7.50s/it]
|
||
77%|███████▋ | 782/1013 [1:50:09<28:25, 7.38s/it]
|
||
77%|███████▋ | 783/1013 [1:50:17<28:37, 7.47s/it]
|
||
77%|███████▋ | 784/1013 [1:50:24<28:34, 7.49s/it]
|
||
77%|███████▋ | 785/1013 [1:50:31<27:58, 7.36s/it]
|
||
78%|███████▊ | 786/1013 [1:50:39<28:30, 7.54s/it]
|
||
78%|███████▊ | 787/1013 [1:50:47<28:03, 7.45s/it]
|
||
78%|███████▊ | 788/1013 [1:50:54<27:46, 7.40s/it]
|
||
78%|███████▊ | 789/1013 [1:51:01<27:27, 7.36s/it]
|
||
78%|███████▊ | 790/1013 [1:51:09<27:23, 7.37s/it]
|
||
|
||
{'loss': '3.456e-07', 'grad_norm': '6.646e-06', 'learning_rate': '7.08e-06', 'entropy': '1.283', 'num_tokens': '7.276e+06', 'logits/chosen': '2.311', 'logits/rejected': '-1.175', 'mean_token_accuracy': '0.6744', 'rewards/chosen': '4.2', 'rewards/rejected': '-15.66', 'rewards/accuracies': '1', 'rewards/margins': '19.86', 'logps/chosen': '-59.46', 'logps/rejected': '-336.6', 'epoch': '2.338'}
|
||
|
||
78%|███████▊ | 790/1013 [1:51:09<27:23, 7.37s/it]
|
||
78%|███████▊ | 791/1013 [1:51:16<27:28, 7.43s/it]
|
||
78%|███████▊ | 792/1013 [1:51:23<26:58, 7.32s/it]
|
||
78%|███████▊ | 793/1013 [1:51:31<27:45, 7.57s/it]
|
||
78%|███████▊ | 794/1013 [1:51:39<27:19, 7.48s/it]
|
||
78%|███████▊ | 795/1013 [1:51:46<27:32, 7.58s/it]
|
||
79%|███████▊ | 796/1013 [1:51:54<27:08, 7.51s/it]
|
||
79%|███████▊ | 797/1013 [1:52:02<27:23, 7.61s/it]
|
||
79%|███████▉ | 798/1013 [1:52:09<26:34, 7.42s/it]
|
||
79%|███████▉ | 799/1013 [1:52:16<26:16, 7.37s/it]
|
||
79%|███████▉ | 800/1013 [1:52:23<25:49, 7.28s/it]
|
||
|
||
{'loss': '6.806e-07', 'grad_norm': '0.0001593', 'learning_rate': '6.491e-06', 'entropy': '1.268', 'num_tokens': '7.367e+06', 'logits/chosen': '2.337', 'logits/rejected': '-1.123', 'mean_token_accuracy': '0.6766', 'rewards/chosen': '4.387', 'rewards/rejected': '-15.41', 'rewards/accuracies': '1', 'rewards/margins': '19.8', 'logps/chosen': '-58.35', 'logps/rejected': '-331.7', 'epoch': '2.367'}
|
||
|
||
79%|███████▉ | 800/1013 [1:52:23<25:49, 7.28s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.26it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.62it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.33it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.95it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.05it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.27it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.01it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.27it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.15it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.91it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.81it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.93it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:30, 4.19it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.27it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.80it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:05<00:34, 3.61it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:33, 3.69it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.65it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.73it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.67it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.82it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.99it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.55it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.47it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.40it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.63it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.85it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.89it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.78it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.96it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.97it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.94it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.70it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.90it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:26, 3.91it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.68it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.60it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.69it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.84it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.09it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.17it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:12<00:28, 3.37it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:12<00:27, 3.40it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:26, 3.45it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.47it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:13<00:25, 3.59it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:23, 3.75it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.51it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.62it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:14<00:22, 3.80it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.82it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.11it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.22it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:15<00:20, 4.00it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.24it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:16<00:22, 3.61it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:17<00:23, 3.42it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.41it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:18<00:32, 2.39it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:18<00:28, 2.69it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:25, 2.93it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:26, 2.79it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:19<00:23, 3.13it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:22, 3.25it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:21, 3.34it/s][A
|
||
|
||
51%|█████ | 73/143 [00:20<00:20, 3.34it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:20<00:20, 3.35it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.31it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.47it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:21<00:18, 3.60it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:16, 3.90it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.91it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:22<00:18, 3.37it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:22<00:16, 3.70it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:18, 3.37it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.27it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:23<00:17, 3.29it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:16, 3.46it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 3.99it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.08it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:24<00:14, 3.92it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:14, 3.79it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.83it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.12it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:25<00:12, 3.96it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:12, 3.96it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.67it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:26<00:14, 3.29it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:26<00:13, 3.53it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.86it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 3.97it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.52it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.71it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:28<00:11, 3.53it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.77it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.69it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:28<00:10, 3.65it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:29<00:09, 3.80it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.93it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.94it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:29<00:08, 4.03it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:30<00:08, 3.67it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.81it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:30<00:09, 3.33it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.48it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.67it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:32<00:07, 3.52it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:32<00:06, 3.85it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:05, 4.14it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.92it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:32<00:05, 3.75it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:33<00:05, 4.18it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.91it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:06, 3.08it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:34<00:05, 3.58it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:04, 3.75it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:04, 3.67it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:04, 3.58it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:35<00:03, 3.75it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 3.93it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.07it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.03it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:36<00:02, 3.53it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.52it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.41it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:37<00:01, 3.62it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.47it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.60it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:38<00:00, 3.91it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.82it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.71it/s][A
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.57it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '7.024e-06', 'eval_runtime': '39.41', 'eval_samples_per_second': '7.231', 'eval_steps_per_second': '3.628', 'eval_entropy': '1.28', 'eval_num_tokens': '7.367e+06', 'eval_logits/chosen': '2.244', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6632', 'eval_rewards/chosen': '4.313', 'eval_rewards/rejected': '-15.17', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.48', 'eval_logps/chosen': '-68.02', 'eval_logps/rejected': '-326.7', 'epoch': '2.367'}
|
||
|
||
79%|███████▉ | 800/1013 [1:53:02<25:49, 7.28s/it]
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.57it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.21s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.22s/it]
|
||
|
||
79%|███████▉ | 801/1013 [1:54:27<2:29:15, 42.24s/it]
|
||
79%|███████▉ | 802/1013 [1:54:34<1:51:27, 31.70s/it]
|
||
79%|███████▉ | 803/1013 [1:54:41<1:25:09, 24.33s/it]
|
||
79%|███████▉ | 804/1013 [1:54:48<1:06:33, 19.11s/it]
|
||
79%|███████▉ | 805/1013 [1:54:55<53:26, 15.42s/it]
|
||
80%|███████▉ | 806/1013 [1:55:02<44:56, 13.03s/it]
|
||
80%|███████▉ | 807/1013 [1:55:09<38:20, 11.17s/it]
|
||
80%|███████▉ | 808/1013 [1:55:16<34:20, 10.05s/it]
|
||
80%|███████▉ | 809/1013 [1:55:23<31:08, 9.16s/it]
|
||
80%|███████▉ | 810/1013 [1:55:31<29:14, 8.64s/it]
|
||
|
||
{'loss': '2.754e-07', 'grad_norm': '0.0001006', 'learning_rate': '5.923e-06', 'entropy': '1.254', 'num_tokens': '7.456e+06', 'logits/chosen': '2.306', 'logits/rejected': '-1.103', 'mean_token_accuracy': '0.6696', 'rewards/chosen': '4.309', 'rewards/rejected': '-14.81', 'rewards/accuracies': '1', 'rewards/margins': '19.12', 'logps/chosen': '-64.73', 'logps/rejected': '-316.8', 'epoch': '2.397'}
|
||
|
||
80%|███████▉ | 810/1013 [1:55:31<29:14, 8.64s/it]
|
||
80%|████████ | 811/1013 [1:55:38<27:58, 8.31s/it]
|
||
80%|████████ | 812/1013 [1:55:46<26:42, 7.97s/it]
|
||
80%|████████ | 813/1013 [1:55:53<26:27, 7.94s/it]
|
||
80%|████████ | 814/1013 [1:56:01<25:52, 7.80s/it]
|
||
80%|████████ | 815/1013 [1:56:08<24:52, 7.54s/it]
|
||
81%|████████ | 816/1013 [1:56:16<25:06, 7.65s/it]
|
||
81%|████████ | 817/1013 [1:56:23<24:23, 7.47s/it]
|
||
81%|████████ | 818/1013 [1:56:31<24:36, 7.57s/it]
|
||
81%|████████ | 819/1013 [1:56:38<24:35, 7.61s/it]
|
||
81%|████████ | 820/1013 [1:56:46<24:01, 7.47s/it]
|
||
|
||
{'loss': '9.869e-08', 'grad_norm': '3.844e-06', 'learning_rate': '5.378e-06', 'entropy': '1.269', 'num_tokens': '7.549e+06', 'logits/chosen': '2.276', 'logits/rejected': '-1.221', 'mean_token_accuracy': '0.6663', 'rewards/chosen': '4.394', 'rewards/rejected': '-15.49', 'rewards/accuracies': '1', 'rewards/margins': '19.88', 'logps/chosen': '-64.78', 'logps/rejected': '-330.2', 'epoch': '2.427'}
|
||
|
||
81%|████████ | 820/1013 [1:56:46<24:01, 7.47s/it]
|
||
81%|████████ | 821/1013 [1:56:52<23:23, 7.31s/it]
|
||
81%|████████ | 822/1013 [1:57:00<23:28, 7.37s/it]
|
||
81%|████████ | 823/1013 [1:57:07<23:08, 7.31s/it]
|
||
81%|████████▏ | 824/1013 [1:57:14<22:36, 7.18s/it]
|
||
81%|████████▏ | 825/1013 [1:57:21<22:05, 7.05s/it]
|
||
82%|████████▏ | 826/1013 [1:57:28<21:54, 7.03s/it]
|
||
82%|████████▏ | 827/1013 [1:57:36<22:35, 7.29s/it]
|
||
82%|████████▏ | 828/1013 [1:57:43<22:38, 7.34s/it]
|
||
82%|████████▏ | 829/1013 [1:57:51<22:39, 7.39s/it]
|
||
82%|████████▏ | 830/1013 [1:57:58<22:12, 7.28s/it]
|
||
|
||
{'loss': '1.597e-07', 'grad_norm': '1.574e-05', 'learning_rate': '4.856e-06', 'entropy': '1.276', 'num_tokens': '7.637e+06', 'logits/chosen': '2.261', 'logits/rejected': '-1.167', 'mean_token_accuracy': '0.6732', 'rewards/chosen': '4.313', 'rewards/rejected': '-15.15', 'rewards/accuracies': '1', 'rewards/margins': '19.46', 'logps/chosen': '-63.7', 'logps/rejected': '-323.2', 'epoch': '2.456'}
|
||
|
||
82%|████████▏ | 830/1013 [1:57:58<22:12, 7.28s/it]
|
||
82%|████████▏ | 831/1013 [1:58:05<21:58, 7.24s/it]
|
||
82%|████████▏ | 832/1013 [1:58:12<21:41, 7.19s/it]
|
||
82%|████████▏ | 833/1013 [1:58:19<21:24, 7.14s/it]
|
||
82%|████████▏ | 834/1013 [1:58:26<21:29, 7.20s/it]
|
||
82%|████████▏ | 835/1013 [1:58:34<21:39, 7.30s/it]
|
||
83%|████████▎ | 836/1013 [1:58:41<21:13, 7.19s/it]
|
||
83%|████████▎ | 837/1013 [1:58:48<21:12, 7.23s/it]
|
||
83%|████████▎ | 838/1013 [1:58:56<21:21, 7.32s/it]
|
||
83%|████████▎ | 839/1013 [1:59:03<21:24, 7.38s/it]
|
||
83%|████████▎ | 840/1013 [1:59:10<21:14, 7.37s/it]
|
||
|
||
{'loss': '1.426e-07', 'grad_norm': '0.0002842', 'learning_rate': '4.358e-06', 'entropy': '1.261', 'num_tokens': '7.726e+06', 'logits/chosen': '2.29', 'logits/rejected': '-1.247', 'mean_token_accuracy': '0.6746', 'rewards/chosen': '4.292', 'rewards/rejected': '-15.13', 'rewards/accuracies': '1', 'rewards/margins': '19.42', 'logps/chosen': '-62.79', 'logps/rejected': '-325', 'epoch': '2.486'}
|
||
|
||
83%|████████▎ | 840/1013 [1:59:10<21:14, 7.37s/it]
|
||
83%|████████▎ | 841/1013 [1:59:18<21:16, 7.42s/it]
|
||
83%|████████▎ | 842/1013 [1:59:25<21:16, 7.46s/it]
|
||
83%|████████▎ | 843/1013 [1:59:34<21:44, 7.67s/it]
|
||
83%|████████▎ | 844/1013 [1:59:41<21:28, 7.63s/it]
|
||
83%|████████▎ | 845/1013 [1:59:49<21:37, 7.72s/it]
|
||
84%|████████▎ | 846/1013 [1:59:57<21:18, 7.65s/it]
|
||
84%|████████▎ | 847/1013 [2:00:04<20:45, 7.50s/it]
|
||
84%|████████▎ | 848/1013 [2:00:12<20:57, 7.62s/it]
|
||
84%|████████▍ | 849/1013 [2:00:19<20:26, 7.48s/it]
|
||
84%|████████▍ | 850/1013 [2:00:26<20:13, 7.45s/it]
|
||
|
||
{'loss': '1.493e-07', 'grad_norm': '0.0002613', 'learning_rate': '3.884e-06', 'entropy': '1.27', 'num_tokens': '7.822e+06', 'logits/chosen': '2.386', 'logits/rejected': '-1.125', 'mean_token_accuracy': '0.679', 'rewards/chosen': '4.364', 'rewards/rejected': '-15.14', 'rewards/accuracies': '1', 'rewards/margins': '19.51', 'logps/chosen': '-61.92', 'logps/rejected': '-327.4', 'epoch': '2.516'}
|
||
|
||
84%|████████▍ | 850/1013 [2:00:26<20:13, 7.45s/it]
|
||
84%|████████▍ | 851/1013 [2:00:33<19:45, 7.32s/it]
|
||
84%|████████▍ | 852/1013 [2:00:41<19:47, 7.38s/it]
|
||
84%|████████▍ | 853/1013 [2:00:48<19:57, 7.48s/it]
|
||
84%|████████▍ | 854/1013 [2:00:56<20:10, 7.62s/it]
|
||
84%|████████▍ | 855/1013 [2:01:04<19:43, 7.49s/it]
|
||
85%|████████▍ | 856/1013 [2:01:11<19:43, 7.54s/it]
|
||
85%|████████▍ | 857/1013 [2:01:18<19:16, 7.41s/it]
|
||
85%|████████▍ | 858/1013 [2:01:26<19:19, 7.48s/it]
|
||
85%|████████▍ | 859/1013 [2:01:33<19:06, 7.44s/it]
|
||
85%|████████▍ | 860/1013 [2:01:41<18:56, 7.43s/it]
|
||
|
||
{'loss': '1.422e-07', 'grad_norm': '4.506e-05', 'learning_rate': '3.436e-06', 'entropy': '1.25', 'num_tokens': '7.916e+06', 'logits/chosen': '2.299', 'logits/rejected': '-1.106', 'mean_token_accuracy': '0.6769', 'rewards/chosen': '4.385', 'rewards/rejected': '-15.66', 'rewards/accuracies': '1', 'rewards/margins': '20.05', 'logps/chosen': '-65.89', 'logps/rejected': '-330', 'epoch': '2.545'}
|
||
|
||
85%|████████▍ | 860/1013 [2:01:41<18:56, 7.43s/it]
|
||
85%|████████▍ | 861/1013 [2:01:48<18:40, 7.37s/it]
|
||
85%|████████▌ | 862/1013 [2:01:55<18:22, 7.30s/it]
|
||
85%|████████▌ | 863/1013 [2:02:02<18:15, 7.30s/it]
|
||
85%|████████▌ | 864/1013 [2:02:10<18:36, 7.49s/it]
|
||
85%|████████▌ | 865/1013 [2:02:18<18:28, 7.49s/it]
|
||
85%|████████▌ | 866/1013 [2:02:25<18:01, 7.36s/it]
|
||
86%|████████▌ | 867/1013 [2:02:32<18:05, 7.43s/it]
|
||
86%|████████▌ | 868/1013 [2:02:40<17:46, 7.35s/it]
|
||
86%|████████▌ | 869/1013 [2:02:47<17:56, 7.48s/it]
|
||
86%|████████▌ | 870/1013 [2:02:54<17:27, 7.32s/it]
|
||
|
||
{'loss': '2.536e-07', 'grad_norm': '2.515e-05', 'learning_rate': '3.013e-06', 'entropy': '1.28', 'num_tokens': '8.007e+06', 'logits/chosen': '2.237', 'logits/rejected': '-1.122', 'mean_token_accuracy': '0.6659', 'rewards/chosen': '4.355', 'rewards/rejected': '-14.86', 'rewards/accuracies': '1', 'rewards/margins': '19.22', 'logps/chosen': '-65.73', 'logps/rejected': '-322.3', 'epoch': '2.575'}
|
||
|
||
86%|████████▌ | 870/1013 [2:02:54<17:27, 7.32s/it]
|
||
86%|████████▌ | 871/1013 [2:03:02<17:21, 7.34s/it]
|
||
86%|████████▌ | 872/1013 [2:03:09<17:18, 7.36s/it]
|
||
86%|████████▌ | 873/1013 [2:03:16<17:00, 7.29s/it]
|
||
86%|████████▋ | 874/1013 [2:03:24<17:08, 7.40s/it]
|
||
86%|████████▋ | 875/1013 [2:03:32<17:17, 7.52s/it]
|
||
86%|████████▋ | 876/1013 [2:03:39<17:04, 7.48s/it]
|
||
87%|████████▋ | 877/1013 [2:03:47<17:09, 7.57s/it]
|
||
87%|████████▋ | 878/1013 [2:03:55<17:02, 7.58s/it]
|
||
87%|████████▋ | 879/1013 [2:04:02<16:50, 7.54s/it]
|
||
87%|████████▋ | 880/1013 [2:04:09<16:39, 7.51s/it]
|
||
|
||
{'loss': '2.378e-07', 'grad_norm': '1.174e-05', 'learning_rate': '2.616e-06', 'entropy': '1.276', 'num_tokens': '8.1e+06', 'logits/chosen': '2.28', 'logits/rejected': '-1.132', 'mean_token_accuracy': '0.6662', 'rewards/chosen': '4.331', 'rewards/rejected': '-15.15', 'rewards/accuracies': '1', 'rewards/margins': '19.48', 'logps/chosen': '-61.99', 'logps/rejected': '-326.9', 'epoch': '2.604'}
|
||
|
||
87%|████████▋ | 880/1013 [2:04:09<16:39, 7.51s/it]
|
||
87%|████████▋ | 881/1013 [2:04:17<16:37, 7.55s/it]
|
||
87%|████████▋ | 882/1013 [2:04:24<16:20, 7.48s/it]
|
||
87%|████████▋ | 883/1013 [2:04:32<16:27, 7.60s/it]
|
||
87%|████████▋ | 884/1013 [2:04:40<16:08, 7.51s/it]
|
||
87%|████████▋ | 885/1013 [2:04:47<16:05, 7.55s/it]
|
||
87%|████████▋ | 886/1013 [2:04:55<15:56, 7.53s/it]
|
||
88%|████████▊ | 887/1013 [2:05:02<15:39, 7.46s/it]
|
||
88%|████████▊ | 888/1013 [2:05:10<15:40, 7.52s/it]
|
||
88%|████████▊ | 889/1013 [2:05:17<15:37, 7.56s/it]
|
||
88%|████████▊ | 890/1013 [2:05:25<15:31, 7.57s/it]
|
||
|
||
{'loss': '6.257e-08', 'grad_norm': '9.632e-05', 'learning_rate': '2.246e-06', 'entropy': '1.279', 'num_tokens': '8.194e+06', 'logits/chosen': '2.303', 'logits/rejected': '-1.171', 'mean_token_accuracy': '0.6666', 'rewards/chosen': '4.474', 'rewards/rejected': '-15.38', 'rewards/accuracies': '1', 'rewards/margins': '19.85', 'logps/chosen': '-65.01', 'logps/rejected': '-330.7', 'epoch': '2.634'}
|
||
|
||
88%|████████▊ | 890/1013 [2:05:25<15:31, 7.57s/it]
|
||
88%|████████▊ | 891/1013 [2:05:32<15:03, 7.41s/it]
|
||
88%|████████▊ | 892/1013 [2:05:39<15:03, 7.46s/it]
|
||
88%|████████▊ | 893/1013 [2:05:47<14:51, 7.43s/it]
|
||
88%|████████▊ | 894/1013 [2:05:54<14:50, 7.48s/it]
|
||
88%|████████▊ | 895/1013 [2:06:03<15:05, 7.68s/it]
|
||
88%|████████▊ | 896/1013 [2:06:10<14:41, 7.53s/it]
|
||
89%|████████▊ | 897/1013 [2:06:17<14:23, 7.44s/it]
|
||
89%|████████▊ | 898/1013 [2:06:24<14:00, 7.31s/it]
|
||
89%|████████▊ | 899/1013 [2:06:32<14:07, 7.43s/it]
|
||
89%|████████▉ | 900/1013 [2:06:39<13:45, 7.31s/it]
|
||
|
||
{'loss': '1.403e-07', 'grad_norm': '2.456e-05', 'learning_rate': '1.903e-06', 'entropy': '1.26', 'num_tokens': '8.286e+06', 'logits/chosen': '2.249', 'logits/rejected': '-1.094', 'mean_token_accuracy': '0.6666', 'rewards/chosen': '4.302', 'rewards/rejected': '-15', 'rewards/accuracies': '1', 'rewards/margins': '19.3', 'logps/chosen': '-64.42', 'logps/rejected': '-319.6', 'epoch': '2.664'}
|
||
|
||
89%|████████▉ | 900/1013 [2:06:39<13:45, 7.31s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:23, 5.98it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.52it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.28it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:35, 3.93it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.04it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.26it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.01it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.27it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.15it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.90it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.82it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.93it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:30, 4.19it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.28it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.80it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:05<00:34, 3.61it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:33, 3.69it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.65it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.72it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.66it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.81it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.97it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.54it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:33, 3.45it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.39it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.64it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.84it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.88it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.77it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.96it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.96it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.94it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.69it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.89it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:26, 3.90it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:10<00:27, 3.67it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:27, 3.62it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:26, 3.70it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:11<00:25, 3.86it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.09it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:39, 2.41it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:13<00:34, 2.73it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:13<00:32, 2.92it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:30, 3.09it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:28, 3.21it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:14<00:26, 3.39it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:25, 3.60it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:26, 3.42it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.55it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:15<00:23, 3.76it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.79it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.06it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:20, 4.17it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:16<00:21, 3.95it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.20it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.59it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:17<00:22, 3.61it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:17<00:23, 3.41it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.40it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:18<00:24, 3.13it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:18<00:22, 3.31it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:22, 3.41it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:24, 3.08it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:19<00:21, 3.38it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.47it/s][A
|
||
|
||
51%|█████ | 73/143 [00:20<00:20, 3.42it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:20<00:20, 3.41it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.35it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.50it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:21<00:18, 3.62it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:16, 3.91it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.91it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:22<00:18, 3.37it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:22<00:16, 3.70it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:18, 3.38it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:22<00:18, 3.27it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:23<00:17, 3.30it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:16, 3.46it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 3.98it/s][A
|
||
|
||
61%|██████ | 87/143 [00:23<00:13, 4.07it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:24<00:13, 3.94it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:14, 3.79it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.83it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:24<00:12, 4.11it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:25<00:12, 3.96it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:12, 3.96it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.67it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:26<00:14, 3.29it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:26<00:13, 3.53it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.85it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:26<00:11, 3.96it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:27<00:11, 3.76it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.52it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:27<00:11, 3.70it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:28<00:11, 3.53it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.76it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.69it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:29<00:10, 3.65it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:29<00:12, 2.97it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:10, 3.27it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:30<00:09, 3.44it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:30<00:09, 3.66it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:30<00:09, 3.44it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.64it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:31<00:09, 3.23it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:31<00:08, 3.42it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.44it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.64it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:32<00:07, 3.50it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:32<00:06, 3.83it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:05, 4.12it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.90it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:33<00:05, 3.73it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:33<00:05, 4.17it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.91it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 3.99it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:34<00:04, 4.41it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:03, 4.35it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:03, 4.04it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:34<00:03, 3.83it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:35<00:03, 3.95it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 4.06it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.17it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:35<00:02, 4.10it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:36<00:02, 3.57it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.54it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:36<00:02, 3.42it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:37<00:01, 3.63it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.47it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:37<00:01, 3.59it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:38<00:00, 3.90it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.82it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.73it/s][A
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.57it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '6.497e-06', 'eval_runtime': '39.45', 'eval_samples_per_second': '7.224', 'eval_steps_per_second': '3.625', 'eval_entropy': '1.28', 'eval_num_tokens': '8.286e+06', 'eval_logits/chosen': '2.245', 'eval_logits/rejected': '-1.16', 'eval_mean_token_accuracy': '0.6639', 'eval_rewards/chosen': '4.317', 'eval_rewards/rejected': '-15.17', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.49', 'eval_logps/chosen': '-67.98', 'eval_logps/rejected': '-326.8', 'epoch': '2.664'}
|
||
|
||
89%|████████▉ | 900/1013 [2:07:18<13:45, 7.31s/it]
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.57it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.26s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:33<00:00, 33.26s/it]
|
||
|
||
89%|████████▉ | 901/1013 [2:08:37<1:15:36, 40.50s/it]
|
||
89%|████████▉ | 902/1013 [2:08:44<56:33, 30.57s/it]
|
||
89%|████████▉ | 903/1013 [2:08:52<43:34, 23.77s/it]
|
||
89%|████████▉ | 904/1013 [2:08:59<34:16, 18.87s/it]
|
||
89%|████████▉ | 905/1013 [2:09:07<27:49, 15.46s/it]
|
||
89%|████████▉ | 906/1013 [2:09:15<23:30, 13.18s/it]
|
||
90%|████████▉ | 907/1013 [2:09:22<20:16, 11.48s/it]
|
||
90%|████████▉ | 908/1013 [2:09:30<18:00, 10.29s/it]
|
||
90%|████████▉ | 909/1013 [2:09:37<16:08, 9.31s/it]
|
||
90%|████████▉ | 910/1013 [2:09:44<14:52, 8.66s/it]
|
||
|
||
{'loss': '9.889e-08', 'grad_norm': '2.205e-05', 'learning_rate': '1.587e-06', 'entropy': '1.284', 'num_tokens': '8.379e+06', 'logits/chosen': '2.341', 'logits/rejected': '-1.165', 'mean_token_accuracy': '0.661', 'rewards/chosen': '4.243', 'rewards/rejected': '-15.43', 'rewards/accuracies': '1', 'rewards/margins': '19.68', 'logps/chosen': '-65.78', 'logps/rejected': '-333.8', 'epoch': '2.693'}
|
||
|
||
90%|████████▉ | 910/1013 [2:09:44<14:52, 8.66s/it]
|
||
90%|████████▉ | 911/1013 [2:09:51<14:04, 8.28s/it]
|
||
90%|█████████ | 912/1013 [2:09:59<13:26, 7.99s/it]
|
||
90%|█████████ | 913/1013 [2:10:06<13:02, 7.83s/it]
|
||
90%|█████████ | 914/1013 [2:10:13<12:29, 7.57s/it]
|
||
90%|█████████ | 915/1013 [2:10:20<12:12, 7.48s/it]
|
||
90%|█████████ | 916/1013 [2:10:28<11:56, 7.39s/it]
|
||
91%|█████████ | 917/1013 [2:10:35<11:58, 7.48s/it]
|
||
91%|█████████ | 918/1013 [2:10:43<11:52, 7.50s/it]
|
||
91%|█████████ | 919/1013 [2:10:51<11:52, 7.59s/it]
|
||
91%|█████████ | 920/1013 [2:10:58<11:45, 7.59s/it]
|
||
|
||
{'loss': '5.674e-08', 'grad_norm': '2.933e-05', 'learning_rate': '1.299e-06', 'entropy': '1.282', 'num_tokens': '8.471e+06', 'logits/chosen': '2.308', 'logits/rejected': '-1.158', 'mean_token_accuracy': '0.6794', 'rewards/chosen': '4.262', 'rewards/rejected': '-15.31', 'rewards/accuracies': '1', 'rewards/margins': '19.57', 'logps/chosen': '-60.28', 'logps/rejected': '-329.9', 'epoch': '2.723'}
|
||
|
||
91%|█████████ | 920/1013 [2:10:58<11:45, 7.59s/it]
|
||
91%|█████████ | 921/1013 [2:11:05<11:24, 7.44s/it]
|
||
91%|█████████ | 922/1013 [2:11:13<11:29, 7.58s/it]
|
||
91%|█████████ | 923/1013 [2:11:20<11:08, 7.42s/it]
|
||
91%|█████████ | 924/1013 [2:11:27<10:48, 7.28s/it]
|
||
91%|█████████▏| 925/1013 [2:11:34<10:39, 7.26s/it]
|
||
91%|█████████▏| 926/1013 [2:11:42<10:41, 7.37s/it]
|
||
92%|█████████▏| 927/1013 [2:11:50<10:51, 7.57s/it]
|
||
92%|█████████▏| 928/1013 [2:11:58<10:49, 7.64s/it]
|
||
92%|█████████▏| 929/1013 [2:12:05<10:31, 7.52s/it]
|
||
92%|█████████▏| 930/1013 [2:12:13<10:27, 7.56s/it]
|
||
|
||
{'loss': '1.114e-07', 'grad_norm': '0.0001116', 'learning_rate': '1.039e-06', 'entropy': '1.262', 'num_tokens': '8.563e+06', 'logits/chosen': '2.324', 'logits/rejected': '-1.067', 'mean_token_accuracy': '0.6756', 'rewards/chosen': '4.329', 'rewards/rejected': '-15.12', 'rewards/accuracies': '1', 'rewards/margins': '19.45', 'logps/chosen': '-59.67', 'logps/rejected': '-327.1', 'epoch': '2.753'}
|
||
|
||
92%|█████████▏| 930/1013 [2:12:13<10:27, 7.56s/it]
|
||
92%|█████████▏| 931/1013 [2:12:21<10:26, 7.64s/it]
|
||
92%|█████████▏| 932/1013 [2:12:27<09:57, 7.38s/it]
|
||
92%|█████████▏| 933/1013 [2:12:35<10:00, 7.50s/it]
|
||
92%|█████████▏| 934/1013 [2:12:43<09:58, 7.58s/it]
|
||
92%|█████████▏| 935/1013 [2:12:50<09:48, 7.54s/it]
|
||
92%|█████████▏| 936/1013 [2:12:58<09:32, 7.44s/it]
|
||
92%|█████████▏| 937/1013 [2:13:04<09:12, 7.28s/it]
|
||
93%|█████████▎| 938/1013 [2:13:12<09:15, 7.40s/it]
|
||
93%|█████████▎| 939/1013 [2:13:20<09:17, 7.53s/it]
|
||
93%|█████████▎| 940/1013 [2:13:27<09:01, 7.42s/it]
|
||
|
||
{'loss': '1.418e-07', 'grad_norm': '0.000114', 'learning_rate': '8.078e-07', 'entropy': '1.295', 'num_tokens': '8.655e+06', 'logits/chosen': '2.221', 'logits/rejected': '-1.151', 'mean_token_accuracy': '0.6663', 'rewards/chosen': '4.4', 'rewards/rejected': '-15.25', 'rewards/accuracies': '1', 'rewards/margins': '19.65', 'logps/chosen': '-66.12', 'logps/rejected': '-330', 'epoch': '2.782'}
|
||
|
||
93%|█████████▎| 940/1013 [2:13:27<09:01, 7.42s/it]
|
||
93%|█████████▎| 941/1013 [2:13:35<08:54, 7.42s/it]
|
||
93%|█████████▎| 942/1013 [2:13:41<08:35, 7.27s/it]
|
||
93%|█████████▎| 943/1013 [2:13:49<08:38, 7.41s/it]
|
||
93%|█████████▎| 944/1013 [2:13:57<08:29, 7.39s/it]
|
||
93%|█████████▎| 945/1013 [2:14:04<08:28, 7.48s/it]
|
||
93%|█████████▎| 946/1013 [2:14:12<08:19, 7.46s/it]
|
||
93%|█████████▎| 947/1013 [2:14:19<08:00, 7.28s/it]
|
||
94%|█████████▎| 948/1013 [2:14:26<08:02, 7.42s/it]
|
||
94%|█████████▎| 949/1013 [2:14:33<07:46, 7.30s/it]
|
||
94%|█████████▍| 950/1013 [2:14:41<07:41, 7.33s/it]
|
||
|
||
{'loss': '2.465e-07', 'grad_norm': '0.0003052', 'learning_rate': '6.051e-07', 'entropy': '1.298', 'num_tokens': '8.746e+06', 'logits/chosen': '2.227', 'logits/rejected': '-1.133', 'mean_token_accuracy': '0.67', 'rewards/chosen': '4.108', 'rewards/rejected': '-14.89', 'rewards/accuracies': '1', 'rewards/margins': '19', 'logps/chosen': '-66.14', 'logps/rejected': '-324.2', 'epoch': '2.812'}
|
||
|
||
94%|█████████▍| 950/1013 [2:14:41<07:41, 7.33s/it]
|
||
94%|█████████▍| 951/1013 [2:14:48<07:41, 7.44s/it]
|
||
94%|█████████▍| 952/1013 [2:14:56<07:32, 7.42s/it]
|
||
94%|█████████▍| 953/1013 [2:15:04<07:32, 7.55s/it]
|
||
94%|█████████▍| 954/1013 [2:15:11<07:18, 7.44s/it]
|
||
94%|█████████▍| 955/1013 [2:15:19<07:18, 7.56s/it]
|
||
94%|█████████▍| 956/1013 [2:15:26<07:12, 7.58s/it]
|
||
94%|█████████▍| 957/1013 [2:15:34<07:01, 7.53s/it]
|
||
95%|█████████▍| 958/1013 [2:15:42<07:00, 7.64s/it]
|
||
95%|█████████▍| 959/1013 [2:15:49<06:50, 7.60s/it]
|
||
95%|█████████▍| 960/1013 [2:15:56<06:36, 7.48s/it]
|
||
|
||
{'loss': '1.341e-07', 'grad_norm': '2.444e-06', 'learning_rate': '4.313e-07', 'entropy': '1.264', 'num_tokens': '8.841e+06', 'logits/chosen': '2.29', 'logits/rejected': '-1.155', 'mean_token_accuracy': '0.6711', 'rewards/chosen': '4.389', 'rewards/rejected': '-15.3', 'rewards/accuracies': '1', 'rewards/margins': '19.69', 'logps/chosen': '-62.26', 'logps/rejected': '-332.4', 'epoch': '2.841'}
|
||
|
||
95%|█████████▍| 960/1013 [2:15:56<06:36, 7.48s/it]
|
||
95%|█████████▍| 961/1013 [2:16:03<06:20, 7.31s/it]
|
||
95%|█████████▍| 962/1013 [2:16:11<06:15, 7.35s/it]
|
||
95%|█████████▌| 963/1013 [2:16:18<06:07, 7.35s/it]
|
||
95%|█████████▌| 964/1013 [2:16:25<06:02, 7.39s/it]
|
||
95%|█████████▌| 965/1013 [2:16:33<05:52, 7.35s/it]
|
||
95%|█████████▌| 966/1013 [2:16:40<05:47, 7.39s/it]
|
||
95%|█████████▌| 967/1013 [2:16:48<05:45, 7.52s/it]
|
||
96%|█████████▌| 968/1013 [2:16:55<05:34, 7.44s/it]
|
||
96%|█████████▌| 969/1013 [2:17:03<05:25, 7.39s/it]
|
||
96%|█████████▌| 970/1013 [2:17:10<05:16, 7.35s/it]
|
||
|
||
{'loss': '1.441e-07', 'grad_norm': '1.836e-05', 'learning_rate': '2.866e-07', 'entropy': '1.286', 'num_tokens': '8.932e+06', 'logits/chosen': '2.317', 'logits/rejected': '-1.187', 'mean_token_accuracy': '0.669', 'rewards/chosen': '4.227', 'rewards/rejected': '-15.06', 'rewards/accuracies': '1', 'rewards/margins': '19.29', 'logps/chosen': '-62.73', 'logps/rejected': '-326.8', 'epoch': '2.871'}
|
||
|
||
96%|█████████▌| 970/1013 [2:17:10<05:16, 7.35s/it]
|
||
96%|█████████▌| 971/1013 [2:17:18<05:13, 7.47s/it]
|
||
96%|█████████▌| 972/1013 [2:17:25<05:07, 7.49s/it]
|
||
96%|█████████▌| 973/1013 [2:17:33<05:03, 7.59s/it]
|
||
96%|█████████▌| 974/1013 [2:17:40<04:51, 7.48s/it]
|
||
96%|█████████▌| 975/1013 [2:17:47<04:41, 7.40s/it]
|
||
96%|█████████▋| 976/1013 [2:17:55<04:40, 7.57s/it]
|
||
96%|█████████▋| 977/1013 [2:18:03<04:35, 7.64s/it]
|
||
97%|█████████▋| 978/1013 [2:18:11<04:28, 7.68s/it]
|
||
97%|█████████▋| 979/1013 [2:18:18<04:18, 7.59s/it]
|
||
97%|█████████▋| 980/1013 [2:18:26<04:11, 7.62s/it]
|
||
|
||
{'loss': '1.181e-07', 'grad_norm': '4.888e-06', 'learning_rate': '1.713e-07', 'entropy': '1.278', 'num_tokens': '9.029e+06', 'logits/chosen': '2.352', 'logits/rejected': '-1.175', 'mean_token_accuracy': '0.6487', 'rewards/chosen': '4.309', 'rewards/rejected': '-15.18', 'rewards/accuracies': '1', 'rewards/margins': '19.49', 'logps/chosen': '-69.6', 'logps/rejected': '-329.8', 'epoch': '2.901'}
|
||
|
||
97%|█████████▋| 980/1013 [2:18:26<04:11, 7.62s/it]
|
||
97%|█████████▋| 981/1013 [2:18:33<03:55, 7.37s/it]
|
||
97%|█████████▋| 982/1013 [2:18:40<03:49, 7.42s/it]
|
||
97%|█████████▋| 983/1013 [2:18:47<03:39, 7.32s/it]
|
||
97%|█████████▋| 984/1013 [2:18:55<03:31, 7.30s/it]
|
||
97%|█████████▋| 985/1013 [2:19:03<03:30, 7.51s/it]
|
||
97%|█████████▋| 986/1013 [2:19:10<03:25, 7.60s/it]
|
||
97%|█████████▋| 987/1013 [2:19:18<03:16, 7.58s/it]
|
||
98%|█████████▊| 988/1013 [2:19:26<03:10, 7.60s/it]
|
||
98%|█████████▊| 989/1013 [2:19:33<02:59, 7.50s/it]
|
||
98%|█████████▊| 990/1013 [2:19:40<02:51, 7.47s/it]
|
||
|
||
{'loss': '1.604e-07', 'grad_norm': '7.063e-06', 'learning_rate': '8.539e-08', 'entropy': '1.266', 'num_tokens': '9.121e+06', 'logits/chosen': '2.306', 'logits/rejected': '-1.07', 'mean_token_accuracy': '0.6714', 'rewards/chosen': '4.18', 'rewards/rejected': '-15.49', 'rewards/accuracies': '1', 'rewards/margins': '19.67', 'logps/chosen': '-65.15', 'logps/rejected': '-333.3', 'epoch': '2.93'}
|
||
|
||
98%|█████████▊| 990/1013 [2:19:40<02:51, 7.47s/it]
|
||
98%|█████████▊| 991/1013 [2:19:47<02:42, 7.38s/it]
|
||
98%|█████████▊| 992/1013 [2:19:55<02:34, 7.36s/it]
|
||
98%|█████████▊| 993/1013 [2:20:03<02:29, 7.49s/it]
|
||
98%|█████████▊| 994/1013 [2:20:10<02:20, 7.39s/it]
|
||
98%|█████████▊| 995/1013 [2:20:17<02:14, 7.45s/it]
|
||
98%|█████████▊| 996/1013 [2:20:25<02:09, 7.64s/it]
|
||
98%|█████████▊| 997/1013 [2:20:33<02:01, 7.60s/it]
|
||
99%|█████████▊| 998/1013 [2:20:40<01:53, 7.54s/it]
|
||
99%|█████████▊| 999/1013 [2:20:48<01:46, 7.62s/it]
|
||
99%|█████████▊| 1000/1013 [2:20:55<01:36, 7.44s/it]
|
||
|
||
{'loss': '1.205e-07', 'grad_norm': '3.263e-06', 'learning_rate': '2.907e-08', 'entropy': '1.28', 'num_tokens': '9.214e+06', 'logits/chosen': '2.326', 'logits/rejected': '-1.083', 'mean_token_accuracy': '0.6543', 'rewards/chosen': '4.286', 'rewards/rejected': '-15.53', 'rewards/accuracies': '1', 'rewards/margins': '19.81', 'logps/chosen': '-65.36', 'logps/rejected': '-333.5', 'epoch': '2.96'}
|
||
|
||
99%|█████████▊| 1000/1013 [2:20:55<01:36, 7.44s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.31it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.62it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.32it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.95it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.05it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.28it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 4.02it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.28it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.14it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.18it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.89it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.82it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.61it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.63it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.93it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.20it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.27it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.80it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:05<00:34, 3.61it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:33, 3.69it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.65it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.73it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.67it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:31, 3.81it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.97it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.53it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:33, 3.45it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.38it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.43it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.64it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.85it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.88it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.76it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.94it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.94it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:09<00:26, 3.93it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:28, 3.69it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:26, 3.88it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:36, 2.81it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:11<00:34, 2.93it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:32, 3.07it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:30, 3.28it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:12<00:27, 3.52it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:32, 2.94it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:31, 3.06it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:13<00:29, 3.27it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:13<00:28, 3.33it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:27, 3.39it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.43it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:14<00:25, 3.55it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:24, 3.72it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.49it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.60it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:15<00:22, 3.79it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.82it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.09it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:20, 4.19it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:16<00:20, 3.97it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.21it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.59it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:17<00:22, 3.61it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:17<00:23, 3.41it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.41it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:18<00:24, 3.13it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:18<00:22, 3.32it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:22, 3.40it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:24, 3.08it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:19<00:21, 3.39it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
51%|█████ | 73/143 [00:20<00:20, 3.42it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:20<00:20, 3.40it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.35it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:20<00:19, 3.49it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:21<00:18, 3.62it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:16, 3.92it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:16, 3.92it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:22<00:18, 3.36it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:22<00:16, 3.69it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:18, 3.37it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:23<00:22, 2.65it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:23<00:20, 2.82it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:18, 3.08it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:15, 3.61it/s][A
|
||
|
||
61%|██████ | 87/143 [00:24<00:14, 3.78it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:24<00:14, 3.74it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:14, 3.68it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:14, 3.75it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:25<00:12, 4.04it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:25<00:13, 3.90it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:12, 3.91it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:26<00:13, 3.65it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:26<00:14, 3.28it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:26<00:13, 3.51it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.85it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:27<00:11, 3.97it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.50it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.74it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:28<00:11, 3.69it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:28<00:11, 3.52it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.77it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:29<00:10, 3.68it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:29<00:10, 3.63it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:29<00:09, 3.79it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.92it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:30<00:08, 3.91it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:30<00:08, 4.01it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:30<00:08, 3.65it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.80it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:31<00:09, 3.32it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.49it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.68it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:32<00:07, 3.52it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:32<00:06, 3.85it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:05, 4.14it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:32<00:05, 3.93it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:33<00:05, 3.75it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:33<00:05, 4.17it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.90it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:33<00:04, 4.00it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:34<00:05, 3.35it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:04, 3.58it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:04, 3.55it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:35<00:04, 3.50it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:35<00:03, 3.69it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 3.88it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.03it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:36<00:02, 4.00it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:36<00:02, 3.52it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.51it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:37<00:02, 3.40it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:37<00:01, 3.62it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.47it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.46it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:38<00:01, 3.59it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:38<00:00, 3.90it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.82it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.73it/s][A
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.56it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '6.491e-06', 'eval_runtime': '39.71', 'eval_samples_per_second': '7.177', 'eval_steps_per_second': '3.601', 'eval_entropy': '1.28', 'eval_num_tokens': '9.214e+06', 'eval_logits/chosen': '2.244', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6638', 'eval_rewards/chosen': '4.315', 'eval_rewards/rejected': '-15.16', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.48', 'eval_logps/chosen': '-68', 'eval_logps/rejected': '-326.7', 'epoch': '2.96'}
|
||
|
||
99%|█████████▊| 1000/1013 [2:21:35<01:36, 7.44s/it]
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.56it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:32<00:00, 32.22s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:32<00:00, 32.22s/it]
|
||
|
||
99%|█████████▉| 1001/1013 [2:22:56<08:16, 41.38s/it]
|
||
99%|█████████▉| 1002/1013 [2:23:03<05:43, 31.20s/it]
|
||
99%|█████████▉| 1003/1013 [2:23:11<04:01, 24.10s/it]
|
||
99%|█████████▉| 1004/1013 [2:23:18<02:51, 19.06s/it]
|
||
99%|█████████▉| 1005/1013 [2:23:26<02:05, 15.69s/it]
|
||
99%|█████████▉| 1006/1013 [2:23:33<01:32, 13.20s/it]
|
||
99%|█████████▉| 1007/1013 [2:23:41<01:08, 11.47s/it]
|
||
100%|█████████▉| 1008/1013 [2:23:48<00:51, 10.22s/it]
|
||
100%|█████████▉| 1009/1013 [2:23:55<00:37, 9.31s/it]
|
||
100%|█████████▉| 1010/1013 [2:24:03<00:26, 8.86s/it]
|
||
|
||
{'loss': '1.837e-07', 'grad_norm': '2.098e-05', 'learning_rate': '2.373e-09', 'entropy': '1.275', 'num_tokens': '9.308e+06', 'logits/chosen': '2.248', 'logits/rejected': '-1.168', 'mean_token_accuracy': '0.6662', 'rewards/chosen': '4.232', 'rewards/rejected': '-15.46', 'rewards/accuracies': '1', 'rewards/margins': '19.69', 'logps/chosen': '-62.23', 'logps/rejected': '-334.2', 'epoch': '2.99'}
|
||
|
||
100%|█████████▉| 1010/1013 [2:24:03<00:26, 8.86s/it]
|
||
100%|█████████▉| 1011/1013 [2:24:11<00:17, 8.53s/it]
|
||
100%|█████████▉| 1012/1013 [2:24:18<00:08, 8.17s/it]
|
||
100%|██████████| 1013/1013 [2:24:25<00:00, 7.96s/it]
|
||
|
||
0%| | 0/143 [00:00<?, ?it/s][A
|
||
|
||
1%|▏ | 2/143 [00:00<00:22, 6.27it/s][A
|
||
|
||
2%|▏ | 3/143 [00:00<00:30, 4.62it/s][A
|
||
|
||
3%|▎ | 4/143 [00:00<00:32, 4.34it/s][A
|
||
|
||
3%|▎ | 5/143 [00:01<00:34, 3.96it/s][A
|
||
|
||
4%|▍ | 6/143 [00:01<00:33, 4.04it/s][A
|
||
|
||
5%|▍ | 7/143 [00:01<00:31, 4.26it/s][A
|
||
|
||
6%|▌ | 8/143 [00:01<00:33, 3.99it/s][A
|
||
|
||
6%|▋ | 9/143 [00:02<00:31, 4.26it/s][A
|
||
|
||
7%|▋ | 10/143 [00:02<00:32, 4.14it/s][A
|
||
|
||
8%|▊ | 11/143 [00:02<00:31, 4.19it/s][A
|
||
|
||
8%|▊ | 12/143 [00:02<00:33, 3.90it/s][A
|
||
|
||
9%|▉ | 13/143 [00:03<00:34, 3.82it/s][A
|
||
|
||
10%|▉ | 14/143 [00:03<00:35, 3.62it/s][A
|
||
|
||
10%|█ | 15/143 [00:03<00:35, 3.63it/s][A
|
||
|
||
11%|█ | 16/143 [00:03<00:32, 3.94it/s][A
|
||
|
||
12%|█▏ | 17/143 [00:04<00:29, 4.21it/s][A
|
||
|
||
13%|█▎ | 18/143 [00:04<00:29, 4.29it/s][A
|
||
|
||
13%|█▎ | 19/143 [00:04<00:32, 3.83it/s][A
|
||
|
||
14%|█▍ | 20/143 [00:04<00:33, 3.63it/s][A
|
||
|
||
15%|█▍ | 21/143 [00:05<00:32, 3.71it/s][A
|
||
|
||
15%|█▌ | 22/143 [00:05<00:33, 3.66it/s][A
|
||
|
||
16%|█▌ | 23/143 [00:05<00:32, 3.74it/s][A
|
||
|
||
17%|█▋ | 24/143 [00:06<00:32, 3.68it/s][A
|
||
|
||
17%|█▋ | 25/143 [00:06<00:30, 3.82it/s][A
|
||
|
||
18%|█▊ | 26/143 [00:06<00:29, 3.99it/s][A
|
||
|
||
19%|█▉ | 27/143 [00:06<00:32, 3.54it/s][A
|
||
|
||
20%|█▉ | 28/143 [00:07<00:33, 3.44it/s][A
|
||
|
||
20%|██ | 29/143 [00:07<00:32, 3.46it/s][A
|
||
|
||
21%|██ | 30/143 [00:07<00:33, 3.39it/s][A
|
||
|
||
22%|██▏ | 31/143 [00:08<00:32, 3.44it/s][A
|
||
|
||
22%|██▏ | 32/143 [00:08<00:30, 3.64it/s][A
|
||
|
||
23%|██▎ | 33/143 [00:08<00:28, 3.85it/s][A
|
||
|
||
24%|██▍ | 34/143 [00:08<00:28, 3.89it/s][A
|
||
|
||
24%|██▍ | 35/143 [00:09<00:28, 3.76it/s][A
|
||
|
||
25%|██▌ | 36/143 [00:09<00:27, 3.95it/s][A
|
||
|
||
26%|██▌ | 37/143 [00:09<00:26, 3.95it/s][A
|
||
|
||
27%|██▋ | 38/143 [00:10<00:36, 2.84it/s][A
|
||
|
||
27%|██▋ | 39/143 [00:10<00:35, 2.95it/s][A
|
||
|
||
28%|██▊ | 40/143 [00:10<00:31, 3.28it/s][A
|
||
|
||
29%|██▊ | 41/143 [00:10<00:29, 3.44it/s][A
|
||
|
||
29%|██▉ | 42/143 [00:11<00:29, 3.38it/s][A
|
||
|
||
30%|███ | 43/143 [00:11<00:29, 3.41it/s][A
|
||
|
||
31%|███ | 44/143 [00:11<00:27, 3.54it/s][A
|
||
|
||
31%|███▏ | 45/143 [00:12<00:26, 3.72it/s][A
|
||
|
||
32%|███▏ | 46/143 [00:12<00:31, 3.04it/s][A
|
||
|
||
33%|███▎ | 47/143 [00:12<00:30, 3.13it/s][A
|
||
|
||
34%|███▎ | 48/143 [00:13<00:28, 3.33it/s][A
|
||
|
||
34%|███▍ | 49/143 [00:13<00:27, 3.39it/s][A
|
||
|
||
35%|███▍ | 50/143 [00:13<00:27, 3.44it/s][A
|
||
|
||
36%|███▌ | 51/143 [00:13<00:26, 3.47it/s][A
|
||
|
||
36%|███▋ | 52/143 [00:14<00:25, 3.59it/s][A
|
||
|
||
37%|███▋ | 53/143 [00:14<00:24, 3.74it/s][A
|
||
|
||
38%|███▊ | 54/143 [00:14<00:25, 3.50it/s][A
|
||
|
||
38%|███▊ | 55/143 [00:14<00:24, 3.61it/s][A
|
||
|
||
39%|███▉ | 56/143 [00:15<00:22, 3.79it/s][A
|
||
|
||
40%|███▉ | 57/143 [00:15<00:22, 3.83it/s][A
|
||
|
||
41%|████ | 58/143 [00:15<00:20, 4.10it/s][A
|
||
|
||
41%|████▏ | 59/143 [00:15<00:19, 4.20it/s][A
|
||
|
||
42%|████▏ | 60/143 [00:16<00:20, 3.99it/s][A
|
||
|
||
43%|████▎ | 61/143 [00:16<00:19, 4.23it/s][A
|
||
|
||
43%|████▎ | 62/143 [00:16<00:22, 3.60it/s][A
|
||
|
||
44%|████▍ | 63/143 [00:17<00:22, 3.62it/s][A
|
||
|
||
45%|████▍ | 64/143 [00:17<00:23, 3.42it/s][A
|
||
|
||
45%|████▌ | 65/143 [00:17<00:22, 3.41it/s][A
|
||
|
||
46%|████▌ | 66/143 [00:18<00:24, 3.13it/s][A
|
||
|
||
47%|████▋ | 67/143 [00:18<00:22, 3.32it/s][A
|
||
|
||
48%|████▊ | 68/143 [00:18<00:21, 3.41it/s][A
|
||
|
||
48%|████▊ | 69/143 [00:18<00:23, 3.09it/s][A
|
||
|
||
49%|████▉ | 70/143 [00:19<00:21, 3.38it/s][A
|
||
|
||
50%|████▉ | 71/143 [00:19<00:20, 3.43it/s][A
|
||
|
||
50%|█████ | 72/143 [00:19<00:20, 3.46it/s][A
|
||
|
||
51%|█████ | 73/143 [00:20<00:20, 3.42it/s][A
|
||
|
||
52%|█████▏ | 74/143 [00:20<00:20, 3.41it/s][A
|
||
|
||
52%|█████▏ | 75/143 [00:20<00:20, 3.36it/s][A
|
||
|
||
53%|█████▎ | 76/143 [00:21<00:24, 2.72it/s][A
|
||
|
||
54%|█████▍ | 77/143 [00:21<00:21, 3.01it/s][A
|
||
|
||
55%|█████▍ | 78/143 [00:21<00:19, 3.39it/s][A
|
||
|
||
55%|█████▌ | 79/143 [00:21<00:18, 3.54it/s][A
|
||
|
||
56%|█████▌ | 80/143 [00:22<00:19, 3.17it/s][A
|
||
|
||
57%|█████▋ | 81/143 [00:22<00:17, 3.53it/s][A
|
||
|
||
57%|█████▋ | 82/143 [00:22<00:18, 3.28it/s][A
|
||
|
||
58%|█████▊ | 83/143 [00:23<00:18, 3.20it/s][A
|
||
|
||
59%|█████▊ | 84/143 [00:23<00:18, 3.24it/s][A
|
||
|
||
59%|█████▉ | 85/143 [00:23<00:17, 3.41it/s][A
|
||
|
||
60%|██████ | 86/143 [00:23<00:14, 3.93it/s][A
|
||
|
||
61%|██████ | 87/143 [00:24<00:13, 4.02it/s][A
|
||
|
||
62%|██████▏ | 88/143 [00:24<00:14, 3.90it/s][A
|
||
|
||
62%|██████▏ | 89/143 [00:24<00:14, 3.78it/s][A
|
||
|
||
63%|██████▎ | 90/143 [00:24<00:13, 3.83it/s][A
|
||
|
||
64%|██████▎ | 91/143 [00:25<00:12, 4.11it/s][A
|
||
|
||
64%|██████▍ | 92/143 [00:25<00:12, 3.95it/s][A
|
||
|
||
65%|██████▌ | 93/143 [00:25<00:12, 3.95it/s][A
|
||
|
||
66%|██████▌ | 94/143 [00:25<00:13, 3.67it/s][A
|
||
|
||
66%|██████▋ | 95/143 [00:26<00:14, 3.29it/s][A
|
||
|
||
67%|██████▋ | 96/143 [00:26<00:13, 3.52it/s][A
|
||
|
||
68%|██████▊ | 97/143 [00:26<00:11, 3.86it/s][A
|
||
|
||
69%|██████▊ | 98/143 [00:27<00:11, 3.98it/s][A
|
||
|
||
69%|██████▉ | 99/143 [00:27<00:11, 3.77it/s][A
|
||
|
||
70%|██████▉ | 100/143 [00:27<00:12, 3.51it/s][A
|
||
|
||
71%|███████ | 101/143 [00:27<00:11, 3.75it/s][A
|
||
|
||
71%|███████▏ | 102/143 [00:28<00:11, 3.69it/s][A
|
||
|
||
72%|███████▏ | 103/143 [00:28<00:11, 3.52it/s][A
|
||
|
||
73%|███████▎ | 104/143 [00:28<00:10, 3.77it/s][A
|
||
|
||
73%|███████▎ | 105/143 [00:28<00:10, 3.69it/s][A
|
||
|
||
74%|███████▍ | 106/143 [00:29<00:10, 3.65it/s][A
|
||
|
||
75%|███████▍ | 107/143 [00:29<00:09, 3.80it/s][A
|
||
|
||
76%|███████▌ | 108/143 [00:29<00:08, 3.93it/s][A
|
||
|
||
76%|███████▌ | 109/143 [00:29<00:08, 3.93it/s][A
|
||
|
||
77%|███████▋ | 110/143 [00:30<00:08, 4.03it/s][A
|
||
|
||
78%|███████▊ | 111/143 [00:30<00:08, 3.66it/s][A
|
||
|
||
78%|███████▊ | 112/143 [00:30<00:08, 3.82it/s][A
|
||
|
||
79%|███████▉ | 113/143 [00:31<00:09, 3.32it/s][A
|
||
|
||
80%|███████▉ | 114/143 [00:31<00:08, 3.48it/s][A
|
||
|
||
80%|████████ | 115/143 [00:31<00:08, 3.48it/s][A
|
||
|
||
81%|████████ | 116/143 [00:31<00:07, 3.69it/s][A
|
||
|
||
82%|████████▏ | 117/143 [00:32<00:09, 2.81it/s][A
|
||
|
||
83%|████████▎ | 118/143 [00:32<00:07, 3.23it/s][A
|
||
|
||
83%|████████▎ | 119/143 [00:32<00:06, 3.61it/s][A
|
||
|
||
84%|████████▍ | 120/143 [00:33<00:06, 3.58it/s][A
|
||
|
||
85%|████████▍ | 121/143 [00:33<00:06, 3.52it/s][A
|
||
|
||
85%|████████▌ | 122/143 [00:33<00:05, 3.97it/s][A
|
||
|
||
86%|████████▌ | 123/143 [00:33<00:05, 3.78it/s][A
|
||
|
||
87%|████████▋ | 124/143 [00:34<00:04, 3.91it/s][A
|
||
|
||
87%|████████▋ | 125/143 [00:34<00:04, 4.34it/s][A
|
||
|
||
88%|████████▊ | 126/143 [00:34<00:03, 4.31it/s][A
|
||
|
||
89%|████████▉ | 127/143 [00:34<00:03, 4.02it/s][A
|
||
|
||
90%|████████▉ | 128/143 [00:35<00:03, 3.82it/s][A
|
||
|
||
90%|█████████ | 129/143 [00:35<00:03, 3.92it/s][A
|
||
|
||
91%|█████████ | 130/143 [00:35<00:03, 4.06it/s][A
|
||
|
||
92%|█████████▏| 131/143 [00:35<00:02, 4.17it/s][A
|
||
|
||
92%|█████████▏| 132/143 [00:36<00:02, 4.09it/s][A
|
||
|
||
93%|█████████▎| 133/143 [00:36<00:02, 3.56it/s][A
|
||
|
||
94%|█████████▎| 134/143 [00:36<00:02, 3.54it/s][A
|
||
|
||
94%|█████████▍| 135/143 [00:37<00:02, 3.42it/s][A
|
||
|
||
95%|█████████▌| 136/143 [00:37<00:01, 3.63it/s][A
|
||
|
||
96%|█████████▌| 137/143 [00:37<00:01, 3.49it/s][A
|
||
|
||
97%|█████████▋| 138/143 [00:37<00:01, 3.48it/s][A
|
||
|
||
97%|█████████▋| 139/143 [00:38<00:01, 3.60it/s][A
|
||
|
||
98%|█████████▊| 140/143 [00:38<00:00, 3.90it/s][A
|
||
|
||
99%|█████████▊| 141/143 [00:38<00:00, 3.81it/s][A
|
||
|
||
99%|█████████▉| 142/143 [00:38<00:00, 3.70it/s][A
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.55it/s][A
|
||
|
||
|
||
|
||
[A{'eval_loss': '6.491e-06', 'eval_runtime': '39.69', 'eval_samples_per_second': '7.181', 'eval_steps_per_second': '3.603', 'eval_entropy': '1.28', 'eval_num_tokens': '9.336e+06', 'eval_logits/chosen': '2.244', 'eval_logits/rejected': '-1.159', 'eval_mean_token_accuracy': '0.6638', 'eval_rewards/chosen': '4.315', 'eval_rewards/rejected': '-15.16', 'eval_rewards/accuracies': '1', 'eval_rewards/margins': '19.48', 'eval_logps/chosen': '-68', 'eval_logps/rejected': '-326.7', 'epoch': '2.999'}
|
||
|
||
100%|██████████| 1013/1013 [2:25:05<00:00, 7.96s/it]
|
||
|
||
100%|██████████| 143/143 [00:39<00:00, 3.55it/s][A
|
||
|
||
[A
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s][A
|
||
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.93s/it][A
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.93s/it]
|
||
|
||
|
||
{'train_runtime': '8781', 'train_samples_per_second': '1.846', 'train_steps_per_second': '0.115', 'train_loss': '0.005771', 'epoch': '2.999'}
|
||
|
||
100%|██████████| 1013/1013 [2:26:21<00:00, 7.96s/it]
|
||
100%|██████████| 1013/1013 [2:26:21<00:00, 8.67s/it]
|
||
[2026-04-16 13:05:08,498] [INFO] [axolotl.train.save_trained_model:267] [PID:135] Training completed! Saving trained model to kikiyaa/qwen-dpo-finetuned-ver2.
|
||
|
||
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.34s/it]
|
||
Writing model shards: 100%|██████████| 1/1 [00:34<00:00, 34.34s/it]
|
||
[2026-04-16 13:05:42,881] [INFO] [axolotl.train.save_trained_model:386] [PID:135] Model successfully saved to kikiyaa/qwen-dpo-finetuned-ver2
|