初始化项目，由ModelHub XC社区提供模型
Model: laion/Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B-v6 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
137
README.md
Normal file
137
README.md
Normal file
@@ -0,0 +1,137 @@
|
||||
---
|
||||
library_name: transformers
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
# datasets: (stripped — invalid local path)
|
||||
_datasets_:
|
||||
- laion/Sera-4.6-Lite-T2-v4-1000
|
||||
model-index:
|
||||
- name: e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B-v6
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
||||
<details><summary>See axolotl config</summary>
|
||||
|
||||
axolotl version: `0.16.0.dev0`
|
||||
```yaml
|
||||
# Sera v6 — scale data 316→1000 + num_epochs 3→6.
|
||||
#
|
||||
# Background: Sera v3 (316 rows × 6 epochs, SLURM 391242) passed turn-1 cleanly
|
||||
# but collapsed at turn-3+ (degenerate tokens, 4.4.4.4… or for-the-for-the…)
|
||||
# once a tool observation >~20 KB entered context. Greedy decoding didn't save
|
||||
# it, so the root cause is under-training rather than sampling. See
|
||||
# /Users/benjaminfeuer/Documents/notes/ot-agent/sera_braces_diagnosis.md for
|
||||
# evidence (per-token probe + turn-3 replay).
|
||||
#
|
||||
# v6 = F3 fix: 3× more rows to give the model enough updates to stay stable
|
||||
# in long multi-turn contexts.
|
||||
|
||||
base_model: Qwen/Qwen3-8B
|
||||
deepspeed: /e/scratch/jureap59/feuer1/code/axolotl/deepspeed_configs/zero3_bf16.json
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
|
||||
chat_template: tokenizer_default
|
||||
# datasets: (stripped — invalid local path)
|
||||
_datasets_:
|
||||
- laion/Sera-4.6-Lite-T2-v4-1000
|
||||
type: chat_template
|
||||
field_messages: messages
|
||||
ds_type: json
|
||||
message_field_training: train
|
||||
|
||||
dataset_prepared_path: /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000-v6
|
||||
output_dir: /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B-v6
|
||||
|
||||
sequence_len: 32768
|
||||
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name: sera-v4-1000-axolotl__Qwen3-8B-v6
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 8
|
||||
micro_batch_size: 1
|
||||
num_epochs: 6
|
||||
optimizer: adamw_torch
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 1e-5
|
||||
adam_beta1: 0.9
|
||||
adam_beta2: 0.95
|
||||
|
||||
bf16: auto
|
||||
tf32: false
|
||||
|
||||
gradient_checkpointing: true
|
||||
activation_offloading: true
|
||||
resume_from_checkpoint:
|
||||
logging_steps: 1
|
||||
flash_attention: true
|
||||
|
||||
loss_watchdog_threshold: 5.0
|
||||
loss_watchdog_patience: 3
|
||||
|
||||
warmup_ratio: 0.1875
|
||||
evals_per_epoch: 0
|
||||
save_strategy: epoch
|
||||
|
||||
weight_decay: 0.01
|
||||
max_grad_norm: 1.0
|
||||
special_tokens:
|
||||
|
||||
```
|
||||
|
||||
</details><br>
|
||||
|
||||
# e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B-v6
|
||||
|
||||
- laion/Sera-4.6-Lite-T2-v4-1000
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 4
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 20
|
||||
- training_steps: 109
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 5.5.0
|
||||
- Pytorch 2.9.1+cu130
|
||||
- Datasets 4.5.0
|
||||
- Tokenizers 0.22.2
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
716
debug.log
Normal file
716
debug.log
Normal file
@@ -0,0 +1,716 @@
|
||||
[2026-04-24 20:51:03,702] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:293513] bf16 support detected, enabling for this configuration.
|
||||
[2026-04-24 20:51:03,717] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:293513] baseline 0.000GB ()
|
||||
[2026-04-24 20:51:03,718] [INFO] [axolotl.cli.config.load_cfg:341] [PID:293513] config:
|
||||
{
|
||||
"activation_offloading": true,
|
||||
"adam_beta1": 0.9,
|
||||
"adam_beta2": 0.95,
|
||||
"axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_sera_v4_1000_v6.yaml",
|
||||
"base_model": "Qwen/Qwen3-8B",
|
||||
"base_model_config": "Qwen/Qwen3-8B",
|
||||
"batch_size": 32,
|
||||
"bf16": true,
|
||||
"capabilities": {
|
||||
"bf16": true,
|
||||
"compute_capability": "sm_90",
|
||||
"fp8": true,
|
||||
"n_gpu": 4,
|
||||
"n_node": 1,
|
||||
"tf32": true
|
||||
},
|
||||
"chat_template": "tokenizer_default",
|
||||
"context_parallel_size": 1,
|
||||
"dataloader_num_workers": 4,
|
||||
"dataloader_pin_memory": true,
|
||||
"dataloader_prefetch_factor": 256,
|
||||
"dataset_num_proc": 288,
|
||||
"dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000-v6",
|
||||
"datasets": [
|
||||
{
|
||||
"chat_template": "tokenizer_default",
|
||||
"ds_type": "json",
|
||||
"field_messages": "messages",
|
||||
"message_field_training": "train",
|
||||
"message_property_mappings": {
|
||||
"content": "content",
|
||||
"role": "role"
|
||||
},
|
||||
"path": "/e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--Sera-4.6-Lite-T2-v4-1000/snapshots/310c2661cea97bd8eb283374416193b64733fffb/sera-4.6-lite-t2_v4_1000.jsonl",
|
||||
"trust_remote_code": false,
|
||||
"type": "chat_template"
|
||||
}
|
||||
],
|
||||
"ddp": true,
|
||||
"deepspeed": {
|
||||
"bf16": {
|
||||
"enabled": true
|
||||
},
|
||||
"gradient_accumulation_steps": "auto",
|
||||
"gradient_clipping": "auto",
|
||||
"train_batch_size": "auto",
|
||||
"train_micro_batch_size_per_gpu": "auto",
|
||||
"wall_clock_breakdown": false,
|
||||
"zero_optimization": {
|
||||
"contiguous_gradients": true,
|
||||
"gather_16bit_weights_on_model_save": true,
|
||||
"max_live_parameters": 0,
|
||||
"max_reuse_distance": 0,
|
||||
"overlap_comm": true,
|
||||
"reduce_bucket_size": "auto",
|
||||
"stage": 3,
|
||||
"stage3_param_persistence_threshold": "auto",
|
||||
"stage3_prefetch_bucket_size": "auto",
|
||||
"sub_group_size": 0
|
||||
}
|
||||
},
|
||||
"device": "cuda:0",
|
||||
"device_map": {
|
||||
"": 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": 1,
|
||||
"eval_causal_lm_metrics": [
|
||||
"sacrebleu",
|
||||
"comet",
|
||||
"ter",
|
||||
"chrf"
|
||||
],
|
||||
"eval_max_new_tokens": 128,
|
||||
"eval_table_size": 0,
|
||||
"evals_per_epoch": 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,
|
||||
"gradient_checkpointing_kwargs": {
|
||||
"use_reentrant": true
|
||||
},
|
||||
"include_tkps": true,
|
||||
"layer_offloading": false,
|
||||
"learning_rate": 1e-05,
|
||||
"lisa_layers_attribute": "model.layers",
|
||||
"load_best_model_at_end": false,
|
||||
"load_in_4bit": false,
|
||||
"load_in_8bit": false,
|
||||
"local_rank": 0,
|
||||
"logging_steps": 1,
|
||||
"lora_dropout": 0.0,
|
||||
"loraplus_lr_embedding": 1e-06,
|
||||
"loss_watchdog_patience": 3,
|
||||
"loss_watchdog_threshold": 5.0,
|
||||
"lr_scheduler": "cosine",
|
||||
"max_grad_norm": 1.0,
|
||||
"mean_resizing_embeddings": false,
|
||||
"merge_method": "memory_efficient",
|
||||
"micro_batch_size": 1,
|
||||
"model_config_type": "qwen3",
|
||||
"num_epochs": 6.0,
|
||||
"num_generation_samples": 3,
|
||||
"optimizer": "adamw_torch",
|
||||
"otel_metrics_host": "localhost",
|
||||
"otel_metrics_port": 8000,
|
||||
"output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B-v6",
|
||||
"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
|
||||
},
|
||||
"sample_packing_bin_size": 200,
|
||||
"sample_packing_group_size": 100000,
|
||||
"save_only_model": false,
|
||||
"save_safetensors": true,
|
||||
"save_strategy": "epoch",
|
||||
"sequence_len": 32768,
|
||||
"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": false,
|
||||
"tiled_mlp_use_original_mlp": true,
|
||||
"tokenizer_config": "Qwen/Qwen3-8B",
|
||||
"tokenizer_save_jinja_files": true,
|
||||
"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
|
||||
},
|
||||
"use_otel_metrics": false,
|
||||
"use_ray": false,
|
||||
"val_set_size": 0.0,
|
||||
"vllm": {
|
||||
"device": "auto",
|
||||
"dtype": "auto",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"host": "0.0.0.0",
|
||||
"port": 8000
|
||||
},
|
||||
"wandb_name": "sera-v4-1000-axolotl__Qwen3-8B-v6",
|
||||
"warmup_ratio": 0.1875,
|
||||
"weight_decay": 0.01,
|
||||
"world_size": 4
|
||||
}
|
||||
[2026-04-24 20:51:03,814] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:293513] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
|
||||
[2026-04-24 20:51:03,972] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:389099] bf16 support detected, enabling for this configuration.
|
||||
[2026-04-24 20:51:04,002] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:389099] baseline 0.000GB ()
|
||||
[2026-04-24 20:51:04,002] [INFO] [axolotl.cli.config.load_cfg:341] [PID:389099] config:
|
||||
{
|
||||
"activation_offloading": true,
|
||||
"adam_beta1": 0.9,
|
||||
"adam_beta2": 0.95,
|
||||
"axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_sera_v4_1000_v6.yaml",
|
||||
"base_model": "Qwen/Qwen3-8B",
|
||||
"base_model_config": "Qwen/Qwen3-8B",
|
||||
"batch_size": 32,
|
||||
"bf16": true,
|
||||
"capabilities": {
|
||||
"bf16": true,
|
||||
"compute_capability": "sm_90",
|
||||
"fp8": true,
|
||||
"n_gpu": 4,
|
||||
"n_node": 1,
|
||||
"tf32": true
|
||||
},
|
||||
"chat_template": "tokenizer_default",
|
||||
"context_parallel_size": 1,
|
||||
"dataloader_num_workers": 4,
|
||||
"dataloader_pin_memory": true,
|
||||
"dataloader_prefetch_factor": 256,
|
||||
"dataset_num_proc": 288,
|
||||
"dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000-v6",
|
||||
"datasets": [
|
||||
{
|
||||
"chat_template": "tokenizer_default",
|
||||
"ds_type": "json",
|
||||
"field_messages": "messages",
|
||||
"message_field_training": "train",
|
||||
"message_property_mappings": {
|
||||
"content": "content",
|
||||
"role": "role"
|
||||
},
|
||||
"path": "/e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--Sera-4.6-Lite-T2-v4-1000/snapshots/310c2661cea97bd8eb283374416193b64733fffb/sera-4.6-lite-t2_v4_1000.jsonl",
|
||||
"trust_remote_code": false,
|
||||
"type": "chat_template"
|
||||
}
|
||||
],
|
||||
"ddp": true,
|
||||
"deepspeed": {
|
||||
"bf16": {
|
||||
"enabled": true
|
||||
},
|
||||
"gradient_accumulation_steps": "auto",
|
||||
"gradient_clipping": "auto",
|
||||
"train_batch_size": "auto",
|
||||
"train_micro_batch_size_per_gpu": "auto",
|
||||
"wall_clock_breakdown": false,
|
||||
"zero_optimization": {
|
||||
"contiguous_gradients": true,
|
||||
"gather_16bit_weights_on_model_save": true,
|
||||
"max_live_parameters": 0,
|
||||
"max_reuse_distance": 0,
|
||||
"overlap_comm": true,
|
||||
"reduce_bucket_size": "auto",
|
||||
"stage": 3,
|
||||
"stage3_param_persistence_threshold": "auto",
|
||||
"stage3_prefetch_bucket_size": "auto",
|
||||
"sub_group_size": 0
|
||||
}
|
||||
},
|
||||
"device": "cuda:0",
|
||||
"device_map": {
|
||||
"": 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": 1,
|
||||
"eval_causal_lm_metrics": [
|
||||
"sacrebleu",
|
||||
"comet",
|
||||
"ter",
|
||||
"chrf"
|
||||
],
|
||||
"eval_max_new_tokens": 128,
|
||||
"eval_table_size": 0,
|
||||
"evals_per_epoch": 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,
|
||||
"gradient_checkpointing_kwargs": {
|
||||
"use_reentrant": true
|
||||
},
|
||||
"include_tkps": true,
|
||||
"layer_offloading": false,
|
||||
"learning_rate": 1e-05,
|
||||
"lisa_layers_attribute": "model.layers",
|
||||
"load_best_model_at_end": false,
|
||||
"load_in_4bit": false,
|
||||
"load_in_8bit": false,
|
||||
"local_rank": 0,
|
||||
"logging_steps": 1,
|
||||
"lora_dropout": 0.0,
|
||||
"loraplus_lr_embedding": 1e-06,
|
||||
"loss_watchdog_patience": 3,
|
||||
"loss_watchdog_threshold": 5.0,
|
||||
"lr_scheduler": "cosine",
|
||||
"max_grad_norm": 1.0,
|
||||
"mean_resizing_embeddings": false,
|
||||
"merge_method": "memory_efficient",
|
||||
"micro_batch_size": 1,
|
||||
"model_config_type": "qwen3",
|
||||
"num_epochs": 6.0,
|
||||
"num_generation_samples": 3,
|
||||
"optimizer": "adamw_torch",
|
||||
"otel_metrics_host": "localhost",
|
||||
"otel_metrics_port": 8000,
|
||||
"output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B-v6",
|
||||
"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
|
||||
},
|
||||
"sample_packing_bin_size": 200,
|
||||
"sample_packing_group_size": 100000,
|
||||
"save_only_model": false,
|
||||
"save_safetensors": true,
|
||||
"save_strategy": "epoch",
|
||||
"sequence_len": 32768,
|
||||
"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": false,
|
||||
"tiled_mlp_use_original_mlp": true,
|
||||
"tokenizer_config": "Qwen/Qwen3-8B",
|
||||
"tokenizer_save_jinja_files": true,
|
||||
"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
|
||||
},
|
||||
"use_otel_metrics": false,
|
||||
"use_ray": false,
|
||||
"val_set_size": 0.0,
|
||||
"vllm": {
|
||||
"device": "auto",
|
||||
"dtype": "auto",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"host": "0.0.0.0",
|
||||
"port": 8000
|
||||
},
|
||||
"wandb_name": "sera-v4-1000-axolotl__Qwen3-8B-v6",
|
||||
"warmup_ratio": 0.1875,
|
||||
"weight_decay": 0.01,
|
||||
"world_size": 4
|
||||
}
|
||||
[2026-04-24 20:51:04,003] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:389099] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
|
||||
[2026-04-24 20:51:04,211] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:293515] Loading raw datasets...
|
||||
[2026-04-24 20:51:04,276] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:293513] EOS: 151645 / <|im_end|>
|
||||
[2026-04-24 20:51:04,277] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:293513] BOS: None / None
|
||||
[2026-04-24 20:51:04,277] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:293513] PAD: 151643 / <|endoftext|>
|
||||
[2026-04-24 20:51:04,277] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:293513] UNK: None / None
|
||||
|
||||
Generating train split: 0 examples [00:00, ? examples/s][2026-04-24 20:51:04,483] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:389099] EOS: 151645 / <|im_end|>
|
||||
[2026-04-24 20:51:04,485] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:389099] BOS: None / None
|
||||
[2026-04-24 20:51:04,485] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:389099] PAD: 151643 / <|endoftext|>
|
||||
[2026-04-24 20:51:04,485] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:389099] UNK: None / None
|
||||
[2026-04-24 20:51:04,492] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:389102] Loading raw datasets...
|
||||
|
||||
Generating train split: 0 examples [00:00, ? examples/s]
|
||||
Generating train split: 110 examples [00:00, 1063.19 examples/s]
|
||||
Generating train split: 110 examples [00:00, 700.23 examples/s]
|
||||
Generating train split: 220 examples [00:00, 839.79 examples/s]
|
||||
Generating train split: 220 examples [00:00, 765.21 examples/s]
|
||||
Generating train split: 499 examples [00:00, 1342.34 examples/s]
|
||||
Generating train split: 499 examples [00:00, 1422.37 examples/s]
|
||||
Generating train split: 712 examples [00:00, 1464.18 examples/s]
|
||||
Generating train split: 867 examples [00:00, 1304.67 examples/s]
|
||||
Generating train split: 712 examples [00:00, 1199.03 examples/s]
|
||||
Generating train split: 1000 examples [00:00, 1350.71 examples/s][2026-04-24 20:51:05,234] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:480] [PID:293513] Unable to find prepared dataset in /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000-v6/2e177ea5edfa924e1ca4b12580e4789b
|
||||
[2026-04-24 20:51:05,234] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:293513] Loading raw datasets...
|
||||
[2026-04-24 20:51:05,234] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:293513] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
|
||||
[2026-04-24 20:51:05,239] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:480] [PID:389099] Unable to find prepared dataset in /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000-v6/2e177ea5edfa924e1ca4b12580e4789b
|
||||
[2026-04-24 20:51:05,241] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:389099] Loading raw datasets...
|
||||
[2026-04-24 20:51:05,241] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:389099] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
|
||||
[2026-04-24 20:51:05,275] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:293513] Loading dataset: /e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--Sera-4.6-Lite-T2-v4-1000/snapshots/310c2661cea97bd8eb283374416193b64733fffb/sera-4.6-lite-t2_v4_1000.jsonl with base_type: chat_template and prompt_style: None
|
||||
[2026-04-24 20:51:05,276] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:389099] Loading dataset: /e/data1/datasets/playground/ot-baf/hf_hub/datasets--laion--Sera-4.6-Lite-T2-v4-1000/snapshots/310c2661cea97bd8eb283374416193b64733fffb/sera-4.6-lite-t2_v4_1000.jsonl with base_type: chat_template and prompt_style: None
|
||||
[2026-04-24 20:51:05,281] [INFO] [axolotl.prompt_strategies.chat_template.__call__:998] [PID:293513] Using chat template:
|
||||
---
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
---
|
||||
|
||||
Generating train split: 1000 examples [00:00, 1611.64 examples/s][2026-04-24 20:51:05,282] [INFO] [axolotl.prompt_strategies.chat_template.__call__:998] [PID:389099] Using chat template:
|
||||
---
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
---
|
||||
[2026-04-24 20:51:05,285] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:293514] Loading raw datasets...
|
||||
[2026-04-24 20:51:05,291] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:389100] Loading raw datasets...
|
||||
|
||||
Generating train split: 1000 examples [00:00, 1356.77 examples/s]
|
||||
[rank3]: Traceback (most recent call last):
|
||||
[rank3]: File "<frozen runpy>", line 198, in _run_module_as_main
|
||||
[rank3]: File "<frozen runpy>", line 88, in _run_code
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 124, in <module>
|
||||
[rank3]: fire.Fire(do_cli)
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 135, in Fire
|
||||
[rank3]: component_trace = _Fire(component, args, parsed_flag_args, context, name)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 468, in _Fire
|
||||
[rank3]: component, remaining_args = _CallAndUpdateTrace(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
|
||||
[rank3]: component = fn(*varargs, **kwargs)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 91, in do_cli
|
||||
[rank3]: do_train(parsed_cfg, parsed_cli_args)
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 43, in do_train
|
||||
[rank3]: dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/telemetry/errors.py", line 124, in wrapper
|
||||
[rank3]: return func(*args, **kwargs)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/common/datasets.py", line 61, in load_datasets
|
||||
[rank3]: train_dataset, eval_dataset, total_num_steps, prompters = prepare_datasets(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/utils.py", line 50, in wrapper
|
||||
[rank3]: return func(*args, **kwargs)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 65, in prepare_datasets
|
||||
[rank3]: return _prepare_standard_dataset(cfg, tokenizer, processor)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 98, in _prepare_standard_dataset
|
||||
[rank3]: train_dataset, eval_dataset, prompters = loader.load(_load_datasets)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/lock.py", line 38, in load
|
||||
[rank3]: result = load_fn()
|
||||
[rank3]: ^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 77, in _load_datasets
|
||||
[rank3]: train_dataset, eval_dataset, prompters = _load_and_prepare_datasets(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 496, in _load_and_prepare_datasets
|
||||
[rank3]: dataset, prompters = _load_tokenized_prepared_datasets(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 299, in _load_tokenized_prepared_datasets
|
||||
[rank3]: dataset, prompters = _load_raw_datasets(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 331, in _load_raw_datasets
|
||||
[rank3]: dataset_wrapper, dataset_prompter = _load_and_process_single_dataset(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 384, in _load_and_process_single_dataset
|
||||
[rank3]: dataset = load_dataset_with_config(
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/shared.py", line 118, in load_dataset_with_config
|
||||
[rank3]: return _load_from_local_path(dataset_config, load_dataset_kwargs)
|
||||
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/shared.py", line 247, in _load_from_local_path
|
||||
[rank3]: return load_dataset(
|
||||
[rank3]: ^^^^^^^^^^^^^
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/datasets/load.py", line 1508, in load_dataset
|
||||
[rank3]: builder_instance.download_and_prepare(
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/datasets/builder.py", line 884, in download_and_prepare
|
||||
[rank3]: self._download_and_prepare(
|
||||
[rank3]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/datasets/builder.py", line 949, in _download_and_prepare
|
||||
[rank3]: raise OSError("Cannot find data file. " + "\nOriginal error:\n" + str(e)) from None
|
||||
[rank3]: OSError: Cannot find data file.
|
||||
[rank3]: Original error:
|
||||
[rank3]: [Errno 2] No such file or directory: '/e/data1/datasets/playground/ot-baf/hf_hub/datasets/json/default-b49d7fb735d1a400/0.0.0/ff8895240c1c6d49c1ae5a8af7cd4b065d168a612f3f6bd42470270b78a42c18.incomplete/json-train-00000-00000-of-NNNNN.arrow'
|
||||
|
||||
[rank2]: Traceback (most recent call last):
|
||||
[rank2]: File "<frozen runpy>", line 198, in _run_module_as_main
|
||||
[rank2]: File "<frozen runpy>", line 88, in _run_code
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 124, in <module>
|
||||
[rank2]: fire.Fire(do_cli)
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 135, in Fire
|
||||
[rank2]: component_trace = _Fire(component, args, parsed_flag_args, context, name)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 468, in _Fire
|
||||
[rank2]: component, remaining_args = _CallAndUpdateTrace(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/miniforge3/envs/sera-axolotl/lib/python3.12/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
|
||||
[rank2]: component = fn(*varargs, **kwargs)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 91, in do_cli
|
||||
[rank2]: do_train(parsed_cfg, parsed_cli_args)
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/cli/train.py", line 43, in do_train
|
||||
[rank2]: dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/telemetry/errors.py", line 124, in wrapper
|
||||
[rank2]: return func(*args, **kwargs)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/common/datasets.py", line 61, in load_datasets
|
||||
[rank2]: train_dataset, eval_dataset, total_num_steps, prompters = prepare_datasets(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/utils.py", line 50, in wrapper
|
||||
[rank2]: return func(*args, **kwargs)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 65, in prepare_datasets
|
||||
[rank2]: return _prepare_standard_dataset(cfg, tokenizer, processor)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 98, in _prepare_standard_dataset
|
||||
[rank2]: train_dataset, eval_dataset, prompters = loader.load(_load_datasets)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/lock.py", line 38, in load
|
||||
[rank2]: result = load_fn()
|
||||
[rank2]: ^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 77, in _load_datasets
|
||||
[rank2]: train_dataset, eval_dataset, prompters = _load_and_prepare_datasets(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 496, in _load_and_prepare_datasets
|
||||
[rank2]: dataset, prompters = _load_tokenized_prepared_datasets(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 299, in _load_tokenized_prepared_datasets
|
||||
[rank2]: dataset, prompters = _load_raw_datasets(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 331, in _load_raw_datasets
|
||||
[rank2]: dataset_wrapper, dataset_prompter = _load_and_process_single_dataset(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/sft.py", line 384, in _load_and_process_single_dataset
|
||||
[rank2]: dataset = load_dataset_with_config(
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/shared.py", line 118, in load_dataset_with_config
|
||||
[rank2]: return _load_from_local_path(dataset_config, load_dataset_kwargs)
|
||||
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
[rank2]: File "/e/scratch/jureap59/feuer1/code/axolotl/src/axolotl/utils/data/shared.py", line 247, in _load_from_local_path
|
||||
[rank2]: return load_dataset(
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6671061a692712c3f3df3adb7ae49b2bea7cde9732394f92357e8509b37e0864
|
||||
size 16381517176
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b39da5995918d05e1dd379f1b323f9fce4aab59db6e38b6a768789d795b5b693
|
||||
size 12689
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user