commit 37413496322651a5a4f6ed60d212737e39913302 Author: ModelHub XC Date: Thu May 7 10:57:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: pmahdavi/Llama-3.1-8B-coding Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..77bdf07 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +library_name: transformers +license: other +base_model: meta-llama/Llama-3.1-8B +tags: +- llama-factory +- full +- generated_from_trainer +datasets: +- tulu3_category_loader +model-index: +- name: Llama-3.1-8B_tulu3_mixture_coding_full_ebs128_lr5e-06 + results: [] +--- + + + +# Llama-3.1-8B_tulu3_mixture_coding_full_ebs128_lr5e-06 + +This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the tulu3_mixture_coding dataset. This checkpoint was released alongside https://arxiv.org/abs/2509.11167. + +## 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: 5e-06 +- train_batch_size: 2 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 2 +- gradient_accumulation_steps: 32 +- total_train_batch_size: 128 +- total_eval_batch_size: 16 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.03 +- num_epochs: 1.0 + +### Training results + + + +### Framework versions + +- Transformers 4.51.1 +- Pytorch 2.6.0+cu124 +- Datasets 3.4.1 +- Tokenizers 0.21.0 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..b53e79f --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 0.9995220557226798, + "total_flos": 145966987345920.0, + "train_loss": 0.845390060482317, + "train_runtime": 63839.4451, + "train_samples_per_second": 2.229, + "train_steps_per_second": 0.017 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..473ed92 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/export/exp_avg_sq.safetensors b/export/exp_avg_sq.safetensors new file mode 100644 index 0000000..69d360f --- /dev/null +++ b/export/exp_avg_sq.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0af75bc627783ba0187e3f8b2264e4ba60696e0ded25993c9a3bec8bd7c88c +size 32121079000 diff --git a/export/fisher_diag_s1024_bs128.safetensors b/export/fisher_diag_s1024_bs128.safetensors new file mode 100644 index 0000000..951fba1 --- /dev/null +++ b/export/fisher_diag_s1024_bs128.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ad01a1a1cebb118a5b35a93ffb1692681771b4973b8fcbc4522675ec85145b +size 32121079000 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..ba91d8f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.51.1" +} diff --git a/latest b/latest new file mode 100644 index 0000000..88367b1 --- /dev/null +++ b/latest @@ -0,0 +1 @@ +global_step1111 \ No newline at end of file diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..ec844ed --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01aabe91e0e8bd9d90749107831611e150ac3582fd141e612323de374e9bb9d8 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..bc5584e --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e147cf033413e63247a438c0b23632c7bafaad032c717431b7b77c1b24972a +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..5d6b9f0 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4f96a5d98f58401c550db8dc8495f6f9606541520d57070c7be3e650b42d82 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..cf8149f --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bd0a4746e3a0712c57bdfdf184d65fe3542e4e1a8600a2285269f632df28d4 +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0fd8120 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/model_states/zero_pp_rank_0_mp_rank_00_model_states.pt b/model_states/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000..69f897d --- /dev/null +++ b/model_states/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1cbccd213c73f5f14cd8ef82d784b903a600bb3fcefec401a7b6839aae1be2 +size 149093 diff --git a/model_states/zero_pp_rank_1_mp_rank_00_model_states.pt b/model_states/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000..73f2989 --- /dev/null +++ b/model_states/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f77c8df7fbe5a5055801516cc593d0504d6a0928671f8cfb7ae449d08be203b +size 149093 diff --git a/rng_state_0.pth b/rng_state_0.pth new file mode 100644 index 0000000..b24ba52 --- /dev/null +++ b/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4 +size 14512 diff --git a/rng_state_1.pth b/rng_state_1.pth new file mode 100644 index 0000000..9350a82 --- /dev/null +++ b/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6 +size 14512 diff --git a/scheduler.pt b/scheduler.pt new file mode 100644 index 0000000..683c907 --- /dev/null +++ b/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36dd5f953aa6491cbd5bcc3e1bb0bb52769f592a7ef677e16c6afe767515245d +size 1064 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..04829af --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..02d4abd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..b53e79f --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 0.9995220557226798, + "total_flos": 145966987345920.0, + "train_loss": 0.845390060482317, + "train_runtime": 63839.4451, + "train_samples_per_second": 2.229, + "train_steps_per_second": 0.017 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..f3a4d55 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,112 @@ +{"current_steps": 10, "total_steps": 1111, "loss": 1.1112, "lr": 1.323529411764706e-06, "epoch": 0.00899659816132025, "percentage": 0.9, "elapsed_time": "0:09:34", "remaining_time": "17:35:06"} +{"current_steps": 20, "total_steps": 1111, "loss": 0.9362, "lr": 2.7941176470588237e-06, "epoch": 0.0179931963226405, "percentage": 1.8, "elapsed_time": "0:19:07", "remaining_time": "17:23:32"} +{"current_steps": 30, "total_steps": 1111, "loss": 0.8806, "lr": 4.264705882352942e-06, "epoch": 0.02698979448396075, "percentage": 2.7, "elapsed_time": "0:28:40", "remaining_time": "17:13:04"} +{"current_steps": 40, "total_steps": 1111, "loss": 0.8947, "lr": 4.9997341046993195e-06, "epoch": 0.035986392645281, "percentage": 3.6, "elapsed_time": "0:38:10", "remaining_time": "17:02:02"} +{"current_steps": 50, "total_steps": 1111, "loss": 0.8764, "lr": 4.997607281643338e-06, "epoch": 0.04498299080660125, "percentage": 4.5, "elapsed_time": "0:47:51", "remaining_time": "16:55:29"} +{"current_steps": 60, "total_steps": 1111, "loss": 0.8758, "lr": 4.993355445074358e-06, "epoch": 0.0539795889679215, "percentage": 5.4, "elapsed_time": "0:57:26", "remaining_time": "16:46:14"} +{"current_steps": 70, "total_steps": 1111, "loss": 0.8839, "lr": 4.986982212538754e-06, "epoch": 0.06297618712924176, "percentage": 6.3, "elapsed_time": "1:07:01", "remaining_time": "16:36:41"} +{"current_steps": 80, "total_steps": 1111, "loss": 0.8741, "lr": 4.978493006508408e-06, "epoch": 0.071972785290562, "percentage": 7.2, "elapsed_time": "1:16:24", "remaining_time": "16:24:40"} +{"current_steps": 90, "total_steps": 1111, "loss": 0.8859, "lr": 4.967895049767168e-06, "epoch": 0.08096938345188226, "percentage": 8.1, "elapsed_time": "1:26:02", "remaining_time": "16:16:00"} +{"current_steps": 100, "total_steps": 1111, "loss": 0.8506, "lr": 4.9551973592655565e-06, "epoch": 0.0899659816132025, "percentage": 9.0, "elapsed_time": "1:35:30", "remaining_time": "16:05:31"} +{"current_steps": 110, "total_steps": 1111, "loss": 0.9021, "lr": 4.940410738448974e-06, "epoch": 0.09896257977452276, "percentage": 9.9, "elapsed_time": "1:44:58", "remaining_time": "15:55:17"} +{"current_steps": 120, "total_steps": 1111, "loss": 0.8752, "lr": 4.923547768065916e-06, "epoch": 0.107959177935843, "percentage": 10.8, "elapsed_time": "1:54:30", "remaining_time": "15:45:38"} +{"current_steps": 130, "total_steps": 1111, "loss": 0.8824, "lr": 4.904622795464018e-06, "epoch": 0.11695577609716326, "percentage": 11.7, "elapsed_time": "2:03:56", "remaining_time": "15:35:18"} +{"current_steps": 140, "total_steps": 1111, "loss": 0.8519, "lr": 4.883651922383059e-06, "epoch": 0.12595237425848352, "percentage": 12.6, "elapsed_time": "2:13:35", "remaining_time": "15:26:33"} +{"current_steps": 150, "total_steps": 1111, "loss": 0.8565, "lr": 4.860652991255274e-06, "epoch": 0.13494897241980378, "percentage": 13.5, "elapsed_time": "2:23:06", "remaining_time": "15:16:51"} +{"current_steps": 160, "total_steps": 1111, "loss": 0.8884, "lr": 4.835645570024666e-06, "epoch": 0.143945570581124, "percentage": 14.4, "elapsed_time": "2:32:26", "remaining_time": "15:06:07"} +{"current_steps": 170, "total_steps": 1111, "loss": 0.8394, "lr": 4.808650935498216e-06, "epoch": 0.15294216874244426, "percentage": 15.3, "elapsed_time": "2:41:57", "remaining_time": "14:56:27"} +{"current_steps": 180, "total_steps": 1111, "loss": 0.8542, "lr": 4.779692055243149e-06, "epoch": 0.16193876690376452, "percentage": 16.2, "elapsed_time": "2:51:30", "remaining_time": "14:47:02"} +{"current_steps": 190, "total_steps": 1111, "loss": 0.8633, "lr": 4.748793568045682e-06, "epoch": 0.17093536506508478, "percentage": 17.1, "elapsed_time": "3:00:52", "remaining_time": "14:36:45"} +{"current_steps": 200, "total_steps": 1111, "loss": 0.8532, "lr": 4.715981762947854e-06, "epoch": 0.179931963226405, "percentage": 18.0, "elapsed_time": "3:10:27", "remaining_time": "14:27:31"} +{"current_steps": 210, "total_steps": 1111, "loss": 0.8544, "lr": 4.681284556880294e-06, "epoch": 0.18892856138772526, "percentage": 18.9, "elapsed_time": "3:19:50", "remaining_time": "14:17:24"} +{"current_steps": 220, "total_steps": 1111, "loss": 0.8463, "lr": 4.6447314709099436e-06, "epoch": 0.19792515954904552, "percentage": 19.8, "elapsed_time": "3:29:20", "remaining_time": "14:07:48"} +{"current_steps": 230, "total_steps": 1111, "loss": 0.8652, "lr": 4.606353605122954e-06, "epoch": 0.20692175771036578, "percentage": 20.7, "elapsed_time": "3:38:52", "remaining_time": "13:58:21"} +{"current_steps": 240, "total_steps": 1111, "loss": 0.8737, "lr": 4.566183612164116e-06, "epoch": 0.215918355871686, "percentage": 21.6, "elapsed_time": "3:48:22", "remaining_time": "13:48:47"} +{"current_steps": 250, "total_steps": 1111, "loss": 0.8448, "lr": 4.52425566945535e-06, "epoch": 0.22491495403300626, "percentage": 22.5, "elapsed_time": "3:57:54", "remaining_time": "13:39:20"} +{"current_steps": 260, "total_steps": 1111, "loss": 0.8531, "lr": 4.480605450116879e-06, "epoch": 0.23391155219432652, "percentage": 23.4, "elapsed_time": "4:07:39", "remaining_time": "13:30:35"} +{"current_steps": 270, "total_steps": 1111, "loss": 0.8569, "lr": 4.435270092615835e-06, "epoch": 0.24290815035564678, "percentage": 24.3, "elapsed_time": "4:17:12", "remaining_time": "13:21:09"} +{"current_steps": 280, "total_steps": 1111, "loss": 0.8559, "lr": 4.388288169168121e-06, "epoch": 0.25190474851696704, "percentage": 25.2, "elapsed_time": "4:26:43", "remaining_time": "13:11:34"} +{"current_steps": 290, "total_steps": 1111, "loss": 0.8487, "lr": 4.339699652920407e-06, "epoch": 0.2609013466782873, "percentage": 26.1, "elapsed_time": "4:36:12", "remaining_time": "13:01:56"} +{"current_steps": 300, "total_steps": 1111, "loss": 0.8427, "lr": 4.28954588394019e-06, "epoch": 0.26989794483960755, "percentage": 27.0, "elapsed_time": "4:45:47", "remaining_time": "12:52:36"} +{"current_steps": 310, "total_steps": 1111, "loss": 0.8645, "lr": 4.237869534042848e-06, "epoch": 0.27889454300092775, "percentage": 27.9, "elapsed_time": "4:55:26", "remaining_time": "12:43:22"} +{"current_steps": 320, "total_steps": 1111, "loss": 0.8739, "lr": 4.184714570485619e-06, "epoch": 0.287891141162248, "percentage": 28.8, "elapsed_time": "5:04:52", "remaining_time": "12:33:35"} +{"current_steps": 330, "total_steps": 1111, "loss": 0.8388, "lr": 4.130126218559396e-06, "epoch": 0.29688773932356827, "percentage": 29.7, "elapsed_time": "5:14:23", "remaining_time": "12:24:03"} +{"current_steps": 340, "total_steps": 1111, "loss": 0.8344, "lr": 4.074150923110149e-06, "epoch": 0.3058843374848885, "percentage": 30.6, "elapsed_time": "5:23:57", "remaining_time": "12:14:37"} +{"current_steps": 350, "total_steps": 1111, "loss": 0.8489, "lr": 4.0168363090227425e-06, "epoch": 0.3148809356462088, "percentage": 31.5, "elapsed_time": "5:33:35", "remaining_time": "12:05:19"} +{"current_steps": 360, "total_steps": 1111, "loss": 0.8827, "lr": 3.958231140700742e-06, "epoch": 0.32387753380752904, "percentage": 32.4, "elapsed_time": "5:43:11", "remaining_time": "11:55:55"} +{"current_steps": 370, "total_steps": 1111, "loss": 0.8257, "lr": 3.898385280576696e-06, "epoch": 0.3328741319688493, "percentage": 33.3, "elapsed_time": "5:52:40", "remaining_time": "11:46:17"} +{"current_steps": 380, "total_steps": 1111, "loss": 0.8586, "lr": 3.8373496466881986e-06, "epoch": 0.34187073013016955, "percentage": 34.2, "elapsed_time": "6:02:11", "remaining_time": "11:36:44"} +{"current_steps": 390, "total_steps": 1111, "loss": 0.8633, "lr": 3.775176169355816e-06, "epoch": 0.35086732829148976, "percentage": 35.1, "elapsed_time": "6:11:39", "remaining_time": "11:27:05"} +{"current_steps": 400, "total_steps": 1111, "loss": 0.8385, "lr": 3.7119177469997506e-06, "epoch": 0.35986392645281, "percentage": 36.0, "elapsed_time": "6:21:02", "remaining_time": "11:17:17"} +{"current_steps": 410, "total_steps": 1111, "loss": 0.8167, "lr": 3.647628201132818e-06, "epoch": 0.36886052461413027, "percentage": 36.9, "elapsed_time": "6:30:52", "remaining_time": "11:08:18"} +{"current_steps": 420, "total_steps": 1111, "loss": 0.8331, "lr": 3.582362230568044e-06, "epoch": 0.3778571227754505, "percentage": 37.8, "elapsed_time": "6:40:24", "remaining_time": "10:58:46"} +{"current_steps": 430, "total_steps": 1111, "loss": 0.8337, "lr": 3.5161753648798367e-06, "epoch": 0.3868537209367708, "percentage": 38.7, "elapsed_time": "6:50:05", "remaining_time": "10:49:27"} +{"current_steps": 440, "total_steps": 1111, "loss": 0.8371, "lr": 3.449123917158331e-06, "epoch": 0.39585031909809104, "percentage": 39.6, "elapsed_time": "6:59:37", "remaining_time": "10:39:55"} +{"current_steps": 450, "total_steps": 1111, "loss": 0.8368, "lr": 3.3812649360970988e-06, "epoch": 0.4048469172594113, "percentage": 40.5, "elapsed_time": "7:09:12", "remaining_time": "10:30:27"} +{"current_steps": 460, "total_steps": 1111, "loss": 0.8322, "lr": 3.3126561574549975e-06, "epoch": 0.41384351542073156, "percentage": 41.4, "elapsed_time": "7:18:48", "remaining_time": "10:21:00"} +{"current_steps": 470, "total_steps": 1111, "loss": 0.8295, "lr": 3.2433559549334475e-06, "epoch": 0.4228401135820518, "percentage": 42.3, "elapsed_time": "7:28:15", "remaining_time": "10:11:20"} +{"current_steps": 480, "total_steps": 1111, "loss": 0.8343, "lr": 3.173423290510937e-06, "epoch": 0.431836711743372, "percentage": 43.2, "elapsed_time": "7:37:47", "remaining_time": "10:01:48"} +{"current_steps": 490, "total_steps": 1111, "loss": 0.8548, "lr": 3.102917664277007e-06, "epoch": 0.44083330990469227, "percentage": 44.1, "elapsed_time": "7:47:22", "remaining_time": "9:52:19"} +{"current_steps": 500, "total_steps": 1111, "loss": 0.8558, "lr": 3.0318990638084055e-06, "epoch": 0.44982990806601253, "percentage": 45.0, "elapsed_time": "7:56:45", "remaining_time": "9:42:35"} +{"current_steps": 510, "total_steps": 1111, "loss": 0.8441, "lr": 2.9604279131304685e-06, "epoch": 0.4588265062273328, "percentage": 45.9, "elapsed_time": "8:06:05", "remaining_time": "9:32:49"} +{"current_steps": 520, "total_steps": 1111, "loss": 0.8346, "lr": 2.8885650213071746e-06, "epoch": 0.46782310438865304, "percentage": 46.8, "elapsed_time": "8:15:32", "remaining_time": "9:23:11"} +{"current_steps": 530, "total_steps": 1111, "loss": 0.8363, "lr": 2.8163715307035897e-06, "epoch": 0.4768197025499733, "percentage": 47.7, "elapsed_time": "8:25:07", "remaining_time": "9:13:44"} +{"current_steps": 540, "total_steps": 1111, "loss": 0.8637, "lr": 2.743908864964741e-06, "epoch": 0.48581630071129356, "percentage": 48.6, "elapsed_time": "8:34:33", "remaining_time": "9:04:05"} +{"current_steps": 550, "total_steps": 1111, "loss": 0.8439, "lr": 2.6712386767551663e-06, "epoch": 0.4948128988726138, "percentage": 49.5, "elapsed_time": "8:44:05", "remaining_time": "8:54:34"} +{"current_steps": 560, "total_steps": 1111, "loss": 0.8485, "lr": 2.5984227953036124e-06, "epoch": 0.5038094970339341, "percentage": 50.41, "elapsed_time": "8:53:31", "remaining_time": "8:44:56"} +{"current_steps": 570, "total_steps": 1111, "loss": 0.8279, "lr": 2.52552317379751e-06, "epoch": 0.5128060951952543, "percentage": 51.31, "elapsed_time": "9:03:08", "remaining_time": "8:35:30"} +{"current_steps": 580, "total_steps": 1111, "loss": 0.8744, "lr": 2.452601836671977e-06, "epoch": 0.5218026933565746, "percentage": 52.21, "elapsed_time": "9:12:39", "remaining_time": "8:25:57"} +{"current_steps": 590, "total_steps": 1111, "loss": 0.817, "lr": 2.3797208268382096e-06, "epoch": 0.5307992915178948, "percentage": 53.11, "elapsed_time": "9:22:10", "remaining_time": "8:16:26"} +{"current_steps": 600, "total_steps": 1111, "loss": 0.8454, "lr": 2.3069421528961493e-06, "epoch": 0.5397958896792151, "percentage": 54.01, "elapsed_time": "9:31:40", "remaining_time": "8:06:52"} +{"current_steps": 610, "total_steps": 1111, "loss": 0.821, "lr": 2.2343277363763437e-06, "epoch": 0.5487924878405352, "percentage": 54.91, "elapsed_time": "9:42:43", "remaining_time": "7:58:35"} +{"current_steps": 620, "total_steps": 1111, "loss": 0.8444, "lr": 2.1619393590558857e-06, "epoch": 0.5577890860018555, "percentage": 55.81, "elapsed_time": "9:52:14", "remaining_time": "7:49:01"} +{"current_steps": 630, "total_steps": 1111, "loss": 0.8296, "lr": 2.0898386103932634e-06, "epoch": 0.5667856841631758, "percentage": 56.71, "elapsed_time": "10:01:44", "remaining_time": "7:39:25"} +{"current_steps": 640, "total_steps": 1111, "loss": 0.8425, "lr": 2.018086835126831e-06, "epoch": 0.575782282324496, "percentage": 57.61, "elapsed_time": "10:11:16", "remaining_time": "7:29:51"} +{"current_steps": 650, "total_steps": 1111, "loss": 0.8356, "lr": 1.9467450810814984e-06, "epoch": 0.5847788804858163, "percentage": 58.51, "elapsed_time": "10:20:53", "remaining_time": "7:20:21"} +{"current_steps": 660, "total_steps": 1111, "loss": 0.8123, "lr": 1.8758740472280372e-06, "epoch": 0.5937754786471365, "percentage": 59.41, "elapsed_time": "10:30:33", "remaining_time": "7:10:52"} +{"current_steps": 670, "total_steps": 1111, "loss": 0.8124, "lr": 1.8055340320392002e-06, "epoch": 0.6027720768084568, "percentage": 60.31, "elapsed_time": "10:40:13", "remaining_time": "7:01:24"} +{"current_steps": 680, "total_steps": 1111, "loss": 0.8469, "lr": 1.7357848821865914e-06, "epoch": 0.611768674969777, "percentage": 61.21, "elapsed_time": "10:49:55", "remaining_time": "6:51:56"} +{"current_steps": 690, "total_steps": 1111, "loss": 0.8171, "lr": 1.6666859416219384e-06, "epoch": 0.6207652731310973, "percentage": 62.11, "elapsed_time": "10:59:27", "remaining_time": "6:42:21"} +{"current_steps": 700, "total_steps": 1111, "loss": 0.8105, "lr": 1.5982960010860882e-06, "epoch": 0.6297618712924176, "percentage": 63.01, "elapsed_time": "11:09:01", "remaining_time": "6:32:48"} +{"current_steps": 710, "total_steps": 1111, "loss": 0.8342, "lr": 1.530673248088687e-06, "epoch": 0.6387584694537378, "percentage": 63.91, "elapsed_time": "11:18:33", "remaining_time": "6:23:14"} +{"current_steps": 720, "total_steps": 1111, "loss": 0.8715, "lr": 1.463875217401099e-06, "epoch": 0.6477550676150581, "percentage": 64.81, "elapsed_time": "11:28:05", "remaining_time": "6:13:40"} +{"current_steps": 730, "total_steps": 1111, "loss": 0.8355, "lr": 1.397958742104687e-06, "epoch": 0.6567516657763783, "percentage": 65.71, "elapsed_time": "11:37:35", "remaining_time": "6:04:04"} +{"current_steps": 740, "total_steps": 1111, "loss": 0.8148, "lr": 1.3329799052361094e-06, "epoch": 0.6657482639376986, "percentage": 66.61, "elapsed_time": "11:47:05", "remaining_time": "5:54:29"} +{"current_steps": 750, "total_steps": 1111, "loss": 0.8229, "lr": 1.2689939920707667e-06, "epoch": 0.6747448620990188, "percentage": 67.51, "elapsed_time": "11:56:45", "remaining_time": "5:45:00"} +{"current_steps": 760, "total_steps": 1111, "loss": 0.8409, "lr": 1.2060554430849951e-06, "epoch": 0.6837414602603391, "percentage": 68.41, "elapsed_time": "12:06:22", "remaining_time": "5:35:28"} +{"current_steps": 770, "total_steps": 1111, "loss": 0.8258, "lr": 1.1442178076370426e-06, "epoch": 0.6927380584216594, "percentage": 69.31, "elapsed_time": "12:15:57", "remaining_time": "5:25:55"} +{"current_steps": 780, "total_steps": 1111, "loss": 0.8162, "lr": 1.0835336984062122e-06, "epoch": 0.7017346565829795, "percentage": 70.21, "elapsed_time": "12:25:41", "remaining_time": "5:16:26"} +{"current_steps": 790, "total_steps": 1111, "loss": 0.808, "lr": 1.0240547466289646e-06, "epoch": 0.7107312547442998, "percentage": 71.11, "elapsed_time": "12:35:10", "remaining_time": "5:06:51"} +{"current_steps": 800, "total_steps": 1111, "loss": 0.8314, "lr": 9.65831558170037e-07, "epoch": 0.71972785290562, "percentage": 72.01, "elapsed_time": "12:44:58", "remaining_time": "4:57:23"} +{"current_steps": 810, "total_steps": 1111, "loss": 0.8437, "lr": 9.089136704659823e-07, "epoch": 0.7287244510669403, "percentage": 72.91, "elapsed_time": "12:54:27", "remaining_time": "4:47:47"} +{"current_steps": 820, "total_steps": 1111, "loss": 0.8052, "lr": 8.533495103777367e-07, "epoch": 0.7377210492282605, "percentage": 73.81, "elapsed_time": "13:04:01", "remaining_time": "4:38:13"} +{"current_steps": 830, "total_steps": 1111, "loss": 0.7951, "lr": 7.991863529880936e-07, "epoch": 0.7467176473895808, "percentage": 74.71, "elapsed_time": "13:13:30", "remaining_time": "4:28:38"} +{"current_steps": 840, "total_steps": 1111, "loss": 0.8461, "lr": 7.464702813791308e-07, "epoch": 0.755714245550901, "percentage": 75.61, "elapsed_time": "13:23:03", "remaining_time": "4:19:04"} +{"current_steps": 850, "total_steps": 1111, "loss": 0.8045, "lr": 6.952461474238182e-07, "epoch": 0.7647108437122213, "percentage": 76.51, "elapsed_time": "13:32:40", "remaining_time": "4:09:32"} +{"current_steps": 860, "total_steps": 1111, "loss": 0.8562, "lr": 6.455575336251549e-07, "epoch": 0.7737074418735416, "percentage": 77.41, "elapsed_time": "13:42:03", "remaining_time": "3:59:55"} +{"current_steps": 870, "total_steps": 1111, "loss": 0.8345, "lr": 5.974467160353226e-07, "epoch": 0.7827040400348618, "percentage": 78.31, "elapsed_time": "13:51:29", "remaining_time": "3:50:19"} +{"current_steps": 880, "total_steps": 1111, "loss": 0.8344, "lr": 5.509546282863806e-07, "epoch": 0.7917006381961821, "percentage": 79.21, "elapsed_time": "14:00:56", "remaining_time": "3:40:44"} +{"current_steps": 890, "total_steps": 1111, "loss": 0.8256, "lr": 5.061208267631315e-07, "epoch": 0.8006972363575023, "percentage": 80.11, "elapsed_time": "14:10:26", "remaining_time": "3:31:10"} +{"current_steps": 900, "total_steps": 1111, "loss": 0.8427, "lr": 4.629834569477626e-07, "epoch": 0.8096938345188226, "percentage": 81.01, "elapsed_time": "14:19:56", "remaining_time": "3:21:36"} +{"current_steps": 910, "total_steps": 1111, "loss": 0.8195, "lr": 4.21579220964923e-07, "epoch": 0.8186904326801429, "percentage": 81.91, "elapsed_time": "14:29:37", "remaining_time": "3:12:04"} +{"current_steps": 920, "total_steps": 1111, "loss": 0.8277, "lr": 3.8194334635482777e-07, "epoch": 0.8276870308414631, "percentage": 82.81, "elapsed_time": "14:39:09", "remaining_time": "3:02:31"} +{"current_steps": 930, "total_steps": 1111, "loss": 0.811, "lr": 3.4410955610097745e-07, "epoch": 0.8366836290027834, "percentage": 83.71, "elapsed_time": "14:48:59", "remaining_time": "2:53:01"} +{"current_steps": 940, "total_steps": 1111, "loss": 0.8187, "lr": 3.0811003993797327e-07, "epoch": 0.8456802271641036, "percentage": 84.61, "elapsed_time": "14:58:35", "remaining_time": "2:43:28"} +{"current_steps": 950, "total_steps": 1111, "loss": 0.8352, "lr": 2.7397542696386145e-07, "epoch": 0.8546768253254238, "percentage": 85.51, "elapsed_time": "15:08:06", "remaining_time": "2:33:53"} +{"current_steps": 960, "total_steps": 1111, "loss": 0.8076, "lr": 2.4173475958028855e-07, "epoch": 0.863673423486744, "percentage": 86.41, "elapsed_time": "15:17:39", "remaining_time": "2:24:20"} +{"current_steps": 970, "total_steps": 1111, "loss": 0.8357, "lr": 2.1141546878265696e-07, "epoch": 0.8726700216480643, "percentage": 87.31, "elapsed_time": "15:27:13", "remaining_time": "2:14:46"} +{"current_steps": 980, "total_steps": 1111, "loss": 0.8375, "lr": 1.8304335082129032e-07, "epoch": 0.8816666198093845, "percentage": 88.21, "elapsed_time": "15:36:42", "remaining_time": "2:05:12"} +{"current_steps": 990, "total_steps": 1111, "loss": 0.8482, "lr": 1.566425452534784e-07, "epoch": 0.8906632179707048, "percentage": 89.11, "elapsed_time": "15:46:15", "remaining_time": "1:55:39"} +{"current_steps": 1000, "total_steps": 1111, "loss": 0.8334, "lr": 1.3223551440506244e-07, "epoch": 0.8996598161320251, "percentage": 90.01, "elapsed_time": "15:55:56", "remaining_time": "1:46:06"} +{"current_steps": 1010, "total_steps": 1111, "loss": 0.8218, "lr": 1.0984302425904869e-07, "epoch": 0.9086564142933453, "percentage": 90.91, "elapsed_time": "16:05:38", "remaining_time": "1:36:33"} +{"current_steps": 1020, "total_steps": 1111, "loss": 0.8242, "lr": 8.94841267874974e-08, "epoch": 0.9176530124546656, "percentage": 91.81, "elapsed_time": "16:15:10", "remaining_time": "1:27:00"} +{"current_steps": 1030, "total_steps": 1111, "loss": 0.8276, "lr": 7.117614374173353e-08, "epoch": 0.9266496106159858, "percentage": 92.71, "elapsed_time": "16:24:46", "remaining_time": "1:17:26"} +{"current_steps": 1040, "total_steps": 1111, "loss": 0.8399, "lr": 5.493465191465458e-08, "epoch": 0.9356462087773061, "percentage": 93.61, "elapsed_time": "16:34:25", "remaining_time": "1:07:53"} +{"current_steps": 1050, "total_steps": 1111, "loss": 0.8231, "lr": 4.0773469887692154e-08, "epoch": 0.9446428069386263, "percentage": 94.51, "elapsed_time": "16:44:05", "remaining_time": "0:58:20"} +{"current_steps": 1060, "total_steps": 1111, "loss": 0.8089, "lr": 2.8704646273687298e-08, "epoch": 0.9536394050999466, "percentage": 95.41, "elapsed_time": "16:53:30", "remaining_time": "0:48:45"} +{"current_steps": 1070, "total_steps": 1111, "loss": 0.8546, "lr": 1.873844946569614e-08, "epoch": 0.9626360032612669, "percentage": 96.31, "elapsed_time": "17:02:54", "remaining_time": "0:39:11"} +{"current_steps": 1080, "total_steps": 1111, "loss": 0.8213, "lr": 1.0883358900435626e-08, "epoch": 0.9716326014225871, "percentage": 97.21, "elapsed_time": "17:12:27", "remaining_time": "0:29:38"} +{"current_steps": 1090, "total_steps": 1111, "loss": 0.8261, "lr": 5.146057843814223e-09, "epoch": 0.9806291995839074, "percentage": 98.11, "elapsed_time": "17:22:11", "remaining_time": "0:20:04"} +{"current_steps": 1100, "total_steps": 1111, "loss": 0.8431, "lr": 1.531427704675459e-09, "epoch": 0.9896257977452276, "percentage": 99.01, "elapsed_time": "17:31:46", "remaining_time": "0:10:31"} +{"current_steps": 1110, "total_steps": 1111, "loss": 0.8082, "lr": 4.25438816009649e-11, "epoch": 0.9986223959065479, "percentage": 99.91, "elapsed_time": "17:41:19", "remaining_time": "0:00:57"} +{"current_steps": 1111, "total_steps": 1111, "epoch": 0.9995220557226798, "percentage": 100.0, "elapsed_time": "17:43:58", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..cbdc01b --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,811 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9995220557226798, + "eval_steps": 500, + "global_step": 1111, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00899659816132025, + "grad_norm": 9.407082207126406, + "learning_rate": 1.323529411764706e-06, + "loss": 1.1112, + "step": 10 + }, + { + "epoch": 0.0179931963226405, + "grad_norm": 1.6078560053885997, + "learning_rate": 2.7941176470588237e-06, + "loss": 0.9362, + "step": 20 + }, + { + "epoch": 0.02698979448396075, + "grad_norm": 1.624171273563677, + "learning_rate": 4.264705882352942e-06, + "loss": 0.8806, + "step": 30 + }, + { + "epoch": 0.035986392645281, + "grad_norm": 1.4554360159842772, + "learning_rate": 4.9997341046993195e-06, + "loss": 0.8947, + "step": 40 + }, + { + "epoch": 0.04498299080660125, + "grad_norm": 1.4128774633791414, + "learning_rate": 4.997607281643338e-06, + "loss": 0.8764, + "step": 50 + }, + { + "epoch": 0.0539795889679215, + "grad_norm": 1.4582318570520234, + "learning_rate": 4.993355445074358e-06, + "loss": 0.8758, + "step": 60 + }, + { + "epoch": 0.06297618712924176, + "grad_norm": 1.241568669359911, + "learning_rate": 4.986982212538754e-06, + "loss": 0.8839, + "step": 70 + }, + { + "epoch": 0.071972785290562, + "grad_norm": 1.4053494360834542, + "learning_rate": 4.978493006508408e-06, + "loss": 0.8741, + "step": 80 + }, + { + "epoch": 0.08096938345188226, + "grad_norm": 1.4737910013351594, + "learning_rate": 4.967895049767168e-06, + "loss": 0.8859, + "step": 90 + }, + { + "epoch": 0.0899659816132025, + "grad_norm": 1.3138356543765093, + "learning_rate": 4.9551973592655565e-06, + "loss": 0.8506, + "step": 100 + }, + { + "epoch": 0.09896257977452276, + "grad_norm": 1.3758428201688702, + "learning_rate": 4.940410738448974e-06, + "loss": 0.9021, + "step": 110 + }, + { + "epoch": 0.107959177935843, + "grad_norm": 1.4334286224262116, + "learning_rate": 4.923547768065916e-06, + "loss": 0.8752, + "step": 120 + }, + { + "epoch": 0.11695577609716326, + "grad_norm": 1.3787955824383673, + "learning_rate": 4.904622795464018e-06, + "loss": 0.8824, + "step": 130 + }, + { + "epoch": 0.12595237425848352, + "grad_norm": 1.3627983383165039, + "learning_rate": 4.883651922383059e-06, + "loss": 0.8519, + "step": 140 + }, + { + "epoch": 0.13494897241980378, + "grad_norm": 1.3424633268190644, + "learning_rate": 4.860652991255274e-06, + "loss": 0.8565, + "step": 150 + }, + { + "epoch": 0.143945570581124, + "grad_norm": 1.4227597124829214, + "learning_rate": 4.835645570024666e-06, + "loss": 0.8884, + "step": 160 + }, + { + "epoch": 0.15294216874244426, + "grad_norm": 1.3745439024877604, + "learning_rate": 4.808650935498216e-06, + "loss": 0.8394, + "step": 170 + }, + { + "epoch": 0.16193876690376452, + "grad_norm": 1.1913982454389247, + "learning_rate": 4.779692055243149e-06, + "loss": 0.8542, + "step": 180 + }, + { + "epoch": 0.17093536506508478, + "grad_norm": 1.3183554482150048, + "learning_rate": 4.748793568045682e-06, + "loss": 0.8633, + "step": 190 + }, + { + "epoch": 0.179931963226405, + "grad_norm": 1.4397694519607327, + "learning_rate": 4.715981762947854e-06, + "loss": 0.8532, + "step": 200 + }, + { + "epoch": 0.18892856138772526, + "grad_norm": 1.2038269967391835, + "learning_rate": 4.681284556880294e-06, + "loss": 0.8544, + "step": 210 + }, + { + "epoch": 0.19792515954904552, + "grad_norm": 1.2701132880820947, + "learning_rate": 4.6447314709099436e-06, + "loss": 0.8463, + "step": 220 + }, + { + "epoch": 0.20692175771036578, + "grad_norm": 1.3356581457961003, + "learning_rate": 4.606353605122954e-06, + "loss": 0.8652, + "step": 230 + }, + { + "epoch": 0.215918355871686, + "grad_norm": 1.3140257601689191, + "learning_rate": 4.566183612164116e-06, + "loss": 0.8737, + "step": 240 + }, + { + "epoch": 0.22491495403300626, + "grad_norm": 1.2150684493886468, + "learning_rate": 4.52425566945535e-06, + "loss": 0.8448, + "step": 250 + }, + { + "epoch": 0.23391155219432652, + "grad_norm": 1.3356045800197514, + "learning_rate": 4.480605450116879e-06, + "loss": 0.8531, + "step": 260 + }, + { + "epoch": 0.24290815035564678, + "grad_norm": 1.3621827029728837, + "learning_rate": 4.435270092615835e-06, + "loss": 0.8569, + "step": 270 + }, + { + "epoch": 0.25190474851696704, + "grad_norm": 1.2958362488368202, + "learning_rate": 4.388288169168121e-06, + "loss": 0.8559, + "step": 280 + }, + { + "epoch": 0.2609013466782873, + "grad_norm": 1.315904667574477, + "learning_rate": 4.339699652920407e-06, + "loss": 0.8487, + "step": 290 + }, + { + "epoch": 0.26989794483960755, + "grad_norm": 1.192500405781859, + "learning_rate": 4.28954588394019e-06, + "loss": 0.8427, + "step": 300 + }, + { + "epoch": 0.27889454300092775, + "grad_norm": 1.3463647117462414, + "learning_rate": 4.237869534042848e-06, + "loss": 0.8645, + "step": 310 + }, + { + "epoch": 0.287891141162248, + "grad_norm": 1.302446463869839, + "learning_rate": 4.184714570485619e-06, + "loss": 0.8739, + "step": 320 + }, + { + "epoch": 0.29688773932356827, + "grad_norm": 1.2998957392856052, + "learning_rate": 4.130126218559396e-06, + "loss": 0.8388, + "step": 330 + }, + { + "epoch": 0.3058843374848885, + "grad_norm": 1.1895515530331358, + "learning_rate": 4.074150923110149e-06, + "loss": 0.8344, + "step": 340 + }, + { + "epoch": 0.3148809356462088, + "grad_norm": 1.2291112546963492, + "learning_rate": 4.0168363090227425e-06, + "loss": 0.8489, + "step": 350 + }, + { + "epoch": 0.32387753380752904, + "grad_norm": 1.2187350361306888, + "learning_rate": 3.958231140700742e-06, + "loss": 0.8827, + "step": 360 + }, + { + "epoch": 0.3328741319688493, + "grad_norm": 1.2251085843679796, + "learning_rate": 3.898385280576696e-06, + "loss": 0.8257, + "step": 370 + }, + { + "epoch": 0.34187073013016955, + "grad_norm": 1.2708814495416274, + "learning_rate": 3.8373496466881986e-06, + "loss": 0.8586, + "step": 380 + }, + { + "epoch": 0.35086732829148976, + "grad_norm": 1.3212728062854284, + "learning_rate": 3.775176169355816e-06, + "loss": 0.8633, + "step": 390 + }, + { + "epoch": 0.35986392645281, + "grad_norm": 1.3153556245818046, + "learning_rate": 3.7119177469997506e-06, + "loss": 0.8385, + "step": 400 + }, + { + "epoch": 0.36886052461413027, + "grad_norm": 1.2072741564966885, + "learning_rate": 3.647628201132818e-06, + "loss": 0.8167, + "step": 410 + }, + { + "epoch": 0.3778571227754505, + "grad_norm": 1.2379563543143086, + "learning_rate": 3.582362230568044e-06, + "loss": 0.8331, + "step": 420 + }, + { + "epoch": 0.3868537209367708, + "grad_norm": 1.2879168901856428, + "learning_rate": 3.5161753648798367e-06, + "loss": 0.8337, + "step": 430 + }, + { + "epoch": 0.39585031909809104, + "grad_norm": 1.29505065565257, + "learning_rate": 3.449123917158331e-06, + "loss": 0.8371, + "step": 440 + }, + { + "epoch": 0.4048469172594113, + "grad_norm": 1.2295083553559263, + "learning_rate": 3.3812649360970988e-06, + "loss": 0.8368, + "step": 450 + }, + { + "epoch": 0.41384351542073156, + "grad_norm": 1.3554176223589234, + "learning_rate": 3.3126561574549975e-06, + "loss": 0.8322, + "step": 460 + }, + { + "epoch": 0.4228401135820518, + "grad_norm": 1.3079414538272678, + "learning_rate": 3.2433559549334475e-06, + "loss": 0.8295, + "step": 470 + }, + { + "epoch": 0.431836711743372, + "grad_norm": 1.2635231121274326, + "learning_rate": 3.173423290510937e-06, + "loss": 0.8343, + "step": 480 + }, + { + "epoch": 0.44083330990469227, + "grad_norm": 1.3150644499613324, + "learning_rate": 3.102917664277007e-06, + "loss": 0.8548, + "step": 490 + }, + { + "epoch": 0.44982990806601253, + "grad_norm": 1.366414847286227, + "learning_rate": 3.0318990638084055e-06, + "loss": 0.8558, + "step": 500 + }, + { + "epoch": 0.4588265062273328, + "grad_norm": 1.2798875567653052, + "learning_rate": 2.9604279131304685e-06, + "loss": 0.8441, + "step": 510 + }, + { + "epoch": 0.46782310438865304, + "grad_norm": 1.2205525459157436, + "learning_rate": 2.8885650213071746e-06, + "loss": 0.8346, + "step": 520 + }, + { + "epoch": 0.4768197025499733, + "grad_norm": 1.3131391162470558, + "learning_rate": 2.8163715307035897e-06, + "loss": 0.8363, + "step": 530 + }, + { + "epoch": 0.48581630071129356, + "grad_norm": 1.2817420417534302, + "learning_rate": 2.743908864964741e-06, + "loss": 0.8637, + "step": 540 + }, + { + "epoch": 0.4948128988726138, + "grad_norm": 1.4117777334581971, + "learning_rate": 2.6712386767551663e-06, + "loss": 0.8439, + "step": 550 + }, + { + "epoch": 0.5038094970339341, + "grad_norm": 1.3316023582639032, + "learning_rate": 2.5984227953036124e-06, + "loss": 0.8485, + "step": 560 + }, + { + "epoch": 0.5128060951952543, + "grad_norm": 1.220300819321901, + "learning_rate": 2.52552317379751e-06, + "loss": 0.8279, + "step": 570 + }, + { + "epoch": 0.5218026933565746, + "grad_norm": 1.2405242839005477, + "learning_rate": 2.452601836671977e-06, + "loss": 0.8744, + "step": 580 + }, + { + "epoch": 0.5307992915178948, + "grad_norm": 1.160142751072927, + "learning_rate": 2.3797208268382096e-06, + "loss": 0.817, + "step": 590 + }, + { + "epoch": 0.5397958896792151, + "grad_norm": 1.2558513559088742, + "learning_rate": 2.3069421528961493e-06, + "loss": 0.8454, + "step": 600 + }, + { + "epoch": 0.5487924878405352, + "grad_norm": 1.2495369982031077, + "learning_rate": 2.2343277363763437e-06, + "loss": 0.821, + "step": 610 + }, + { + "epoch": 0.5577890860018555, + "grad_norm": 1.2645404439096872, + "learning_rate": 2.1619393590558857e-06, + "loss": 0.8444, + "step": 620 + }, + { + "epoch": 0.5667856841631758, + "grad_norm": 1.2701388082173177, + "learning_rate": 2.0898386103932634e-06, + "loss": 0.8296, + "step": 630 + }, + { + "epoch": 0.575782282324496, + "grad_norm": 1.2620244980098876, + "learning_rate": 2.018086835126831e-06, + "loss": 0.8425, + "step": 640 + }, + { + "epoch": 0.5847788804858163, + "grad_norm": 1.1594661341735868, + "learning_rate": 1.9467450810814984e-06, + "loss": 0.8356, + "step": 650 + }, + { + "epoch": 0.5937754786471365, + "grad_norm": 1.2189222560662132, + "learning_rate": 1.8758740472280372e-06, + "loss": 0.8123, + "step": 660 + }, + { + "epoch": 0.6027720768084568, + "grad_norm": 1.2444702547045237, + "learning_rate": 1.8055340320392002e-06, + "loss": 0.8124, + "step": 670 + }, + { + "epoch": 0.611768674969777, + "grad_norm": 1.2315293692576161, + "learning_rate": 1.7357848821865914e-06, + "loss": 0.8469, + "step": 680 + }, + { + "epoch": 0.6207652731310973, + "grad_norm": 1.2995895579660914, + "learning_rate": 1.6666859416219384e-06, + "loss": 0.8171, + "step": 690 + }, + { + "epoch": 0.6297618712924176, + "grad_norm": 1.2091823608533048, + "learning_rate": 1.5982960010860882e-06, + "loss": 0.8105, + "step": 700 + }, + { + "epoch": 0.6387584694537378, + "grad_norm": 1.2705740309640616, + "learning_rate": 1.530673248088687e-06, + "loss": 0.8342, + "step": 710 + }, + { + "epoch": 0.6477550676150581, + "grad_norm": 1.2981521802148184, + "learning_rate": 1.463875217401099e-06, + "loss": 0.8715, + "step": 720 + }, + { + "epoch": 0.6567516657763783, + "grad_norm": 1.1925093116586027, + "learning_rate": 1.397958742104687e-06, + "loss": 0.8355, + "step": 730 + }, + { + "epoch": 0.6657482639376986, + "grad_norm": 1.1985043813628813, + "learning_rate": 1.3329799052361094e-06, + "loss": 0.8148, + "step": 740 + }, + { + "epoch": 0.6747448620990188, + "grad_norm": 1.1010299588672359, + "learning_rate": 1.2689939920707667e-06, + "loss": 0.8229, + "step": 750 + }, + { + "epoch": 0.6837414602603391, + "grad_norm": 1.2430718303897152, + "learning_rate": 1.2060554430849951e-06, + "loss": 0.8409, + "step": 760 + }, + { + "epoch": 0.6927380584216594, + "grad_norm": 1.269761061806062, + "learning_rate": 1.1442178076370426e-06, + "loss": 0.8258, + "step": 770 + }, + { + "epoch": 0.7017346565829795, + "grad_norm": 1.157246567841852, + "learning_rate": 1.0835336984062122e-06, + "loss": 0.8162, + "step": 780 + }, + { + "epoch": 0.7107312547442998, + "grad_norm": 1.2172574409120116, + "learning_rate": 1.0240547466289646e-06, + "loss": 0.808, + "step": 790 + }, + { + "epoch": 0.71972785290562, + "grad_norm": 1.2870129001272486, + "learning_rate": 9.65831558170037e-07, + "loss": 0.8314, + "step": 800 + }, + { + "epoch": 0.7287244510669403, + "grad_norm": 1.2970054704276492, + "learning_rate": 9.089136704659823e-07, + "loss": 0.8437, + "step": 810 + }, + { + "epoch": 0.7377210492282605, + "grad_norm": 1.1999856118846624, + "learning_rate": 8.533495103777367e-07, + "loss": 0.8052, + "step": 820 + }, + { + "epoch": 0.7467176473895808, + "grad_norm": 1.233946813798178, + "learning_rate": 7.991863529880936e-07, + "loss": 0.7951, + "step": 830 + }, + { + "epoch": 0.755714245550901, + "grad_norm": 1.2668438696715465, + "learning_rate": 7.464702813791308e-07, + "loss": 0.8461, + "step": 840 + }, + { + "epoch": 0.7647108437122213, + "grad_norm": 1.2263597703226994, + "learning_rate": 6.952461474238182e-07, + "loss": 0.8045, + "step": 850 + }, + { + "epoch": 0.7737074418735416, + "grad_norm": 1.2325614523967854, + "learning_rate": 6.455575336251549e-07, + "loss": 0.8562, + "step": 860 + }, + { + "epoch": 0.7827040400348618, + "grad_norm": 1.243498384623771, + "learning_rate": 5.974467160353226e-07, + "loss": 0.8345, + "step": 870 + }, + { + "epoch": 0.7917006381961821, + "grad_norm": 1.158311860753632, + "learning_rate": 5.509546282863806e-07, + "loss": 0.8344, + "step": 880 + }, + { + "epoch": 0.8006972363575023, + "grad_norm": 1.2163583553306607, + "learning_rate": 5.061208267631315e-07, + "loss": 0.8256, + "step": 890 + }, + { + "epoch": 0.8096938345188226, + "grad_norm": 1.2102463242463388, + "learning_rate": 4.629834569477626e-07, + "loss": 0.8427, + "step": 900 + }, + { + "epoch": 0.8186904326801429, + "grad_norm": 1.1969681545587425, + "learning_rate": 4.21579220964923e-07, + "loss": 0.8195, + "step": 910 + }, + { + "epoch": 0.8276870308414631, + "grad_norm": 1.2573696493635405, + "learning_rate": 3.8194334635482777e-07, + "loss": 0.8277, + "step": 920 + }, + { + "epoch": 0.8366836290027834, + "grad_norm": 1.2979421497920385, + "learning_rate": 3.4410955610097745e-07, + "loss": 0.811, + "step": 930 + }, + { + "epoch": 0.8456802271641036, + "grad_norm": 1.1946033424208522, + "learning_rate": 3.0811003993797327e-07, + "loss": 0.8187, + "step": 940 + }, + { + "epoch": 0.8546768253254238, + "grad_norm": 1.1959972915578303, + "learning_rate": 2.7397542696386145e-07, + "loss": 0.8352, + "step": 950 + }, + { + "epoch": 0.863673423486744, + "grad_norm": 1.2612864041438945, + "learning_rate": 2.4173475958028855e-07, + "loss": 0.8076, + "step": 960 + }, + { + "epoch": 0.8726700216480643, + "grad_norm": 1.2393073900072233, + "learning_rate": 2.1141546878265696e-07, + "loss": 0.8357, + "step": 970 + }, + { + "epoch": 0.8816666198093845, + "grad_norm": 1.3961098525762, + "learning_rate": 1.8304335082129032e-07, + "loss": 0.8375, + "step": 980 + }, + { + "epoch": 0.8906632179707048, + "grad_norm": 1.2304674879812914, + "learning_rate": 1.566425452534784e-07, + "loss": 0.8482, + "step": 990 + }, + { + "epoch": 0.8996598161320251, + "grad_norm": 1.1275632452975384, + "learning_rate": 1.3223551440506244e-07, + "loss": 0.8334, + "step": 1000 + }, + { + "epoch": 0.9086564142933453, + "grad_norm": 1.1697390212239938, + "learning_rate": 1.0984302425904869e-07, + "loss": 0.8218, + "step": 1010 + }, + { + "epoch": 0.9176530124546656, + "grad_norm": 1.1549729040350385, + "learning_rate": 8.94841267874974e-08, + "loss": 0.8242, + "step": 1020 + }, + { + "epoch": 0.9266496106159858, + "grad_norm": 1.2550852449415948, + "learning_rate": 7.117614374173353e-08, + "loss": 0.8276, + "step": 1030 + }, + { + "epoch": 0.9356462087773061, + "grad_norm": 1.1789618223129013, + "learning_rate": 5.493465191465458e-08, + "loss": 0.8399, + "step": 1040 + }, + { + "epoch": 0.9446428069386263, + "grad_norm": 1.308555979964644, + "learning_rate": 4.0773469887692154e-08, + "loss": 0.8231, + "step": 1050 + }, + { + "epoch": 0.9536394050999466, + "grad_norm": 1.1941396262140982, + "learning_rate": 2.8704646273687298e-08, + "loss": 0.8089, + "step": 1060 + }, + { + "epoch": 0.9626360032612669, + "grad_norm": 1.2336678582691885, + "learning_rate": 1.873844946569614e-08, + "loss": 0.8546, + "step": 1070 + }, + { + "epoch": 0.9716326014225871, + "grad_norm": 1.2123027368688872, + "learning_rate": 1.0883358900435626e-08, + "loss": 0.8213, + "step": 1080 + }, + { + "epoch": 0.9806291995839074, + "grad_norm": 1.101205104982958, + "learning_rate": 5.146057843814223e-09, + "loss": 0.8261, + "step": 1090 + }, + { + "epoch": 0.9896257977452276, + "grad_norm": 1.138150004760349, + "learning_rate": 1.531427704675459e-09, + "loss": 0.8431, + "step": 1100 + }, + { + "epoch": 0.9986223959065479, + "grad_norm": 1.1694006998873614, + "learning_rate": 4.25438816009649e-11, + "loss": 0.8082, + "step": 1110 + } + ], + "logging_steps": 10, + "max_steps": 1111, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 600, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 145966987345920.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..db2eee2 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb25bd9bed986bab5e24d067e0cc007f63f1029d8b2d36e7cd337b9ded77ec3 +size 7736 diff --git a/training_config.yaml b/training_config.yaml new file mode 100644 index 0000000..7949996 --- /dev/null +++ b/training_config.yaml @@ -0,0 +1,27 @@ +bf16: true +cutoff_len: 4096 +dataset: tulu3_mixture_coding +ddp_timeout: 180000000 +deepspeed: examples/deepspeed/ds_z3_config.json +do_train: true +eval_strategy: 'no' +finetuning_type: full +gradient_accumulation_steps: 32 +learning_rate: 5.0e-06 +logging_steps: 10 +lr_scheduler_type: cosine +model_name_or_path: meta-llama/Llama-3.1-8B +num_train_epochs: 1.0 +output_dir: /scratch/pxm5426/runs/lora-exploration/llama-factory/Llama-3.1-8B_tulu3_mixture_coding_full_ebs128_lr5e-06 +overwrite_cache: true +overwrite_output_dir: true +per_device_train_batch_size: 2 +plot_loss: true +preprocessing_num_workers: 16 +report_to: wandb +save_steps: 600 +save_strategy: steps +stage: sft +template: tulu_v3 +trust_remote_code: true +warmup_ratio: 0.03 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..6e59c6b Binary files /dev/null and b/training_loss.png differ diff --git a/zero_to_fp32.py b/zero_to_fp32.py new file mode 100644 index 0000000..0e75914 --- /dev/null +++ b/zero_to_fp32.py @@ -0,0 +1,760 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import gc +import json +import numpy as np +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device, weights_only=False) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in tqdm(files, desc='Loading checkpoint shards'): + state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +class GatheredTensor: + """ + A pseudo tensor that collects partitioned weights. + It is more memory efficient when there are multiple groups. + """ + + def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape): + self.flat_groups = flat_groups + self.flat_groups_offset = flat_groups_offset + self.offset = offset + self.partitioned_numel = partitioned_numel + self.shape = shape + self.dtype = self.flat_groups[0][0].dtype + + def contiguous(self): + """ + Merge partitioned weights from flat_groups into a single tensor. + """ + end_idx = self.offset + self.partitioned_numel + world_size = len(self.flat_groups) + pad_flat_param_chunks = [] + + for rank_i in range(world_size): + # for each rank, we need to collect weights from related group/groups + flat_groups_at_rank_i = self.flat_groups[rank_i] + start_group_id = None + end_group_id = None + for group_id in range(len(self.flat_groups_offset)): + if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]: + start_group_id = group_id + if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]: + end_group_id = group_id + break + # collect weights from related group/groups + for group_id in range(start_group_id, end_group_id + 1): + flat_tensor = flat_groups_at_rank_i[group_id] + start_offset = self.offset - self.flat_groups_offset[group_id] + end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id] + pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset]) + + # collect weights from all ranks + pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0) + param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous() + return param + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size + + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]])) + for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # memory efficient tensor + tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape) + state_dict[name] = tensor + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def to_torch_tensor(state_dict, return_empty_tensor=False): + """ + Convert state_dict of GatheredTensor to torch tensor + """ + torch_state_dict = {} + converted_tensors = {} + for name, tensor in state_dict.items(): + tensor_id = id(tensor) + if tensor_id in converted_tensors: # shared tensors + shared_tensor = torch_state_dict[converted_tensors[tensor_id]] + torch_state_dict[name] = shared_tensor + else: + converted_tensors[tensor_id] = name + if return_empty_tensor: + torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype) + else: + torch_state_dict[name] = tensor.contiguous() + return torch_state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag=None, + exclude_frozen_parameters=False, + lazy_mode=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient. + Convert the pesduo tensor to torch tensor by ``.contiguous()`` + + Returns: + - pytorch ``state_dict`` + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + Note: the above usage may not work if your application doesn't have sufficient free CPU memory. + You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. Or you can load state_dict in lazy mode :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu + for name, lazy_tensor in state_dict.item(): + tensor = lazy_tensor.contiguous() # to cpu + print(name, tensor) + # del tensor to release memory if it no longer in use + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + if lazy_mode: + return state_dict + else: + return to_torch_tensor(state_dict) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, + tag, + exclude_frozen_parameters, + lazy_mode=True) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + # an memory-efficient approach for sharding + empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True) + state_dict_split = split_torch_state_dict_into_shards(empty_state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model by shard + os.makedirs(output_dir, exist_ok=True) + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors} + shard_state_dict = to_torch_tensor(shard_state_dict) + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard_state_dict, output_path, metadata={"format": "pt"}) + else: + torch.save(shard_state_dict, output_path) + # release the memory of current shard + for tensor_name in list(shard_state_dict.keys()): + del state_dict[tensor_name] + del shard_state_dict[tensor_name] + del shard_state_dict + gc.collect() + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters)