初始化项目，由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-sft-hh-helpful-4xh200
Source: Original Platform

.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

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- Anthropic/hh-rlhf
+model-index:
+- name: llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-3-8b-base-sft-hh-helpful-4xh200-batch-64-20260416-162101
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the Anthropic/hh-rlhf dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1934
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.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: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.5069        | 0.3868 | 100  | 1.4891          |
+| 1.2171        | 0.7737 | 200  | 1.1934          |
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.21.4

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.9980657640232108,
+    "eval_loss": 1.1544486284255981,
+    "eval_runtime": 4.7384,
+    "eval_samples": 2339,
+    "eval_samples_per_second": 188.882,
+    "eval_steps_per_second": 5.909,
+    "total_flos": 9.517157411769549e+16,
+    "train_loss": 1.5008004404777704,
+    "train_runtime": 885.0234,
+    "train_samples": 43598,
+    "train_samples_per_second": 18.662,
+    "train_steps_per_second": 0.292
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "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": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9980657640232108,
+    "eval_loss": 1.1544486284255981,
+    "eval_runtime": 4.7384,
+    "eval_samples": 2339,
+    "eval_samples_per_second": 188.882,
+    "eval_steps_per_second": 5.909
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63acddb29e8f0ed6f4e9d0422e14f80225b62368bf370b2838136748230dea10
+size 4886466168

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d271e235c71953dd45337c032b0c7eca1d76c31b075b4b46a6f3722d93c9214
+size 4832007448

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9968b2c022b47fa23905b0a2ded51109c455b221175296a6a5d8fc9e9755ec7e
+size 4999813112

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f010008c89e13a82181b417fdb617253dade4fa20a955577f9048e9d619d35e
+size 4999813128

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404ec71d5f67b57bbdf86e1ed88a6d6c79b3559a2085c8326923951fa9f45c0a
+size 4832007496

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9f040fc6ed794359d4c82bba8cee124ffa169d39926cbc8a6d5c903b647d05
+size 4999813120

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dece8a2d1d81f91bed319afee674c2f1da795ea9c59bfba2123ec96f4214707
+size 2571158184

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

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|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9980657640232108,
+    "total_flos": 9.517157411769549e+16,
+    "train_loss": 1.5008004404777704,
+    "train_runtime": 885.0234,
+    "train_samples": 43598,
+    "train_samples_per_second": 18.662,
+    "train_steps_per_second": 0.292
+}

trainer_state.json

@@ -0,0 +1,423 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9980657640232108,
+  "eval_steps": 100,
+  "global_step": 258,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0038684719535783366,
+      "grad_norm": 6.09610478125056e+18,
+      "learning_rate": 0.0,
+      "loss": 3.1242,
+      "step": 1
+    },
+    {
+      "epoch": 0.019342359767891684,
+      "grad_norm": 2697.71337890625,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 3.1772,
+      "step": 5
+    },
+    {
+      "epoch": 0.03868471953578337,
+      "grad_norm": 25.10409927368164,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 2.8881,
+      "step": 10
+    },
+    {
+      "epoch": 0.058027079303675046,
+      "grad_norm": 12.363713264465332,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 2.4609,
+      "step": 15
+    },
+    {
+      "epoch": 0.07736943907156674,
+      "grad_norm": 22.165477752685547,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 2.2508,
+      "step": 20
+    },
+    {
+      "epoch": 0.09671179883945841,
+      "grad_norm": 14.86285400390625,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 2.0898,
+      "step": 25
+    },
+    {
+      "epoch": 0.11605415860735009,
+      "grad_norm": 7.5494914054870605,
+      "learning_rate": 1.9991749570421146e-05,
+      "loss": 1.9877,
+      "step": 30
+    },
+    {
+      "epoch": 0.13539651837524178,
+      "grad_norm": 4.193073272705078,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 1.8119,
+      "step": 35
+    },
+    {
+      "epoch": 0.15473887814313347,
+      "grad_norm": 5.1745171546936035,
+      "learning_rate": 1.984545368367337e-05,
+      "loss": 1.7714,
+      "step": 40
+    },
+    {
+      "epoch": 0.17408123791102514,
+      "grad_norm": 6.300442695617676,
+      "learning_rate": 1.9704411482532116e-05,
+      "loss": 1.7391,
+      "step": 45
+    },
+    {
+      "epoch": 0.19342359767891681,
+      "grad_norm": 5.5538201332092285,
+      "learning_rate": 1.9518899287155558e-05,
+      "loss": 1.7088,
+      "step": 50
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 4.729171276092529,
+      "learning_rate": 1.9289767198167918e-05,
+      "loss": 1.6553,
+      "step": 55
+    },
+    {
+      "epoch": 0.23210831721470018,
+      "grad_norm": 2.736438512802124,
+      "learning_rate": 1.9018065202237083e-05,
+      "loss": 1.6234,
+      "step": 60
+    },
+    {
+      "epoch": 0.2514506769825919,
+      "grad_norm": 2.781848192214966,
+      "learning_rate": 1.8705038360561724e-05,
+      "loss": 1.6005,
+      "step": 65
+    },
+    {
+      "epoch": 0.27079303675048355,
+      "grad_norm": 30.041719436645508,
+      "learning_rate": 1.8352121103438804e-05,
+      "loss": 1.6161,
+      "step": 70
+    },
+    {
+      "epoch": 0.2901353965183752,
+      "grad_norm": 2.318030595779419,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 1.5743,
+      "step": 75
+    },
+    {
+      "epoch": 0.30947775628626695,
+      "grad_norm": 2.369173526763916,
+      "learning_rate": 1.7533259632633443e-05,
+      "loss": 1.537,
+      "step": 80
+    },
+    {
+      "epoch": 0.3288201160541586,
+      "grad_norm": 8.767570495605469,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.5716,
+      "step": 85
+    },
+    {
+      "epoch": 0.3481624758220503,
+      "grad_norm": 2.4866902828216553,
+      "learning_rate": 1.6576473166320644e-05,
+      "loss": 1.5327,
+      "step": 90
+    },
+    {
+      "epoch": 0.36750483558994196,
+      "grad_norm": 2.8688602447509766,
+      "learning_rate": 1.6051742151937655e-05,
+      "loss": 1.5223,
+      "step": 95
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "grad_norm": 9.360047340393066,
+      "learning_rate": 1.549927932310155e-05,
+      "loss": 1.5069,
+      "step": 100
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "eval_loss": 1.489111065864563,
+      "eval_runtime": 4.7946,
+      "eval_samples_per_second": 186.667,
+      "eval_steps_per_second": 5.84,
+      "step": 100
+    },
+    {
+      "epoch": 0.40618955512572535,
+      "grad_norm": 2.7148385047912598,
+      "learning_rate": 1.4921616313890073e-05,
+      "loss": 1.4631,
+      "step": 105
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 2.1432764530181885,
+      "learning_rate": 1.4321400236983459e-05,
+      "loss": 1.4502,
+      "step": 110
+    },
+    {
+      "epoch": 0.4448742746615087,
+      "grad_norm": 2.373682975769043,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 1.411,
+      "step": 115
+    },
+    {
+      "epoch": 0.46421663442940037,
+      "grad_norm": 2.2317380905151367,
+      "learning_rate": 1.3064401468637793e-05,
+      "loss": 1.4031,
+      "step": 120
+    },
+    {
+      "epoch": 0.4835589941972921,
+      "grad_norm": 1.9476709365844727,
+      "learning_rate": 1.2413378912997058e-05,
+      "loss": 1.3929,
+      "step": 125
+    },
+    {
+      "epoch": 0.5029013539651838,
+      "grad_norm": 1.9585973024368286,
+      "learning_rate": 1.175129716571531e-05,
+      "loss": 1.3855,
+      "step": 130
+    },
+    {
+      "epoch": 0.5222437137330754,
+      "grad_norm": 2.38059401512146,
+      "learning_rate": 1.1081190184239418e-05,
+      "loss": 1.3818,
+      "step": 135
+    },
+    {
+      "epoch": 0.5415860735009671,
+      "grad_norm": 2.2399237155914307,
+      "learning_rate": 1.0406128701262128e-05,
+      "loss": 1.334,
+      "step": 140
+    },
+    {
+      "epoch": 0.5609284332688588,
+      "grad_norm": 2.42098069190979,
+      "learning_rate": 9.729206153238658e-06,
+      "loss": 1.3365,
+      "step": 145
+    },
+    {
+      "epoch": 0.5802707930367504,
+      "grad_norm": 2.278903007507324,
+      "learning_rate": 9.053524504864391e-06,
+      "loss": 1.3288,
+      "step": 150
+    },
+    {
+      "epoch": 0.5996131528046421,
+      "grad_norm": 1.902079701423645,
+      "learning_rate": 8.382180034472353e-06,
+      "loss": 1.309,
+      "step": 155
+    },
+    {
+      "epoch": 0.6189555125725339,
+      "grad_norm": 1.8283921480178833,
+      "learning_rate": 7.718249145488143e-06,
+      "loss": 1.3069,
+      "step": 160
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 1.9884213209152222,
+      "learning_rate": 7.064774268960654e-06,
+      "loss": 1.2787,
+      "step": 165
+    },
+    {
+      "epoch": 0.6576402321083172,
+      "grad_norm": 2.0930237770080566,
+      "learning_rate": 6.4247499217695995e-06,
+      "loss": 1.2678,
+      "step": 170
+    },
+    {
+      "epoch": 0.6769825918762089,
+      "grad_norm": 2.522498369216919,
+      "learning_rate": 5.801108984397355e-06,
+      "loss": 1.2107,
+      "step": 175
+    },
+    {
+      "epoch": 0.6963249516441006,
+      "grad_norm": 2.825383424758911,
+      "learning_rate": 5.196709261146606e-06,
+      "loss": 1.2417,
+      "step": 180
+    },
+    {
+      "epoch": 0.7156673114119922,
+      "grad_norm": 2.353144645690918,
+      "learning_rate": 4.614320384390959e-06,
+      "loss": 1.2198,
+      "step": 185
+    },
+    {
+      "epoch": 0.7350096711798839,
+      "grad_norm": 2.3441641330718994,
+      "learning_rate": 4.056611122869106e-06,
+      "loss": 1.2026,
+      "step": 190
+    },
+    {
+      "epoch": 0.7543520309477756,
+      "grad_norm": 2.090709924697876,
+      "learning_rate": 3.5261371521817247e-06,
+      "loss": 1.1828,
+      "step": 195
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "grad_norm": 1.8887003660202026,
+      "learning_rate": 3.0253293435321797e-06,
+      "loss": 1.2171,
+      "step": 200
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "eval_loss": 1.193406581878662,
+      "eval_runtime": 4.7625,
+      "eval_samples_per_second": 187.926,
+      "eval_steps_per_second": 5.879,
+      "step": 200
+    },
+    {
+      "epoch": 0.793036750483559,
+      "grad_norm": 2.0174171924591064,
+      "learning_rate": 2.5564826243772965e-06,
+      "loss": 1.1818,
+      "step": 205
+    },
+    {
+      "epoch": 0.8123791102514507,
+      "grad_norm": 2.1461687088012695,
+      "learning_rate": 2.1217454620337842e-06,
+      "loss": 1.1851,
+      "step": 210
+    },
+    {
+      "epoch": 0.8317214700193424,
+      "grad_norm": 1.9792951345443726,
+      "learning_rate": 1.7231100184310955e-06,
+      "loss": 1.1799,
+      "step": 215
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 2.1498570442199707,
+      "learning_rate": 1.3624030211261684e-06,
+      "loss": 1.1748,
+      "step": 220
+    },
+    {
+      "epoch": 0.8704061895551257,
+      "grad_norm": 2.3734147548675537,
+      "learning_rate": 1.0412773924131202e-06,
+      "loss": 1.1529,
+      "step": 225
+    },
+    {
+      "epoch": 0.8897485493230174,
+      "grad_norm": 21.268768310546875,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 1.1486,
+      "step": 230
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 2.0091605186462402,
+      "learning_rate": 5.234682881719766e-07,
+      "loss": 1.1451,
+      "step": 235
+    },
+    {
+      "epoch": 0.9284332688588007,
+      "grad_norm": 1.8940573930740356,
+      "learning_rate": 3.2915764771193294e-07,
+      "loss": 1.1681,
+      "step": 240
+    },
+    {
+      "epoch": 0.9477756286266924,
+      "grad_norm": 2.0212926864624023,
+      "learning_rate": 1.791631725784404e-07,
+      "loss": 1.1391,
+      "step": 245
+    },
+    {
+      "epoch": 0.9671179883945842,
+      "grad_norm": 2.1692233085632324,
+      "learning_rate": 7.4172205167945e-08,
+      "loss": 1.1662,
+      "step": 250
+    },
+    {
+      "epoch": 0.9864603481624759,
+      "grad_norm": 1.9714499711990356,
+      "learning_rate": 1.4665861488761813e-08,
+      "loss": 1.163,
+      "step": 255
+    },
+    {
+      "epoch": 0.9980657640232108,
+      "step": 258,
+      "total_flos": 9.517157411769549e+16,
+      "train_loss": 1.5008004404777704,
+      "train_runtime": 885.0234,
+      "train_samples_per_second": 18.662,
+      "train_steps_per_second": 0.292
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 258,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.517157411769549e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}