初始化项目，由ModelHub XC社区提供模型

Model: HuggingFaceH4/mistral-7b-grok
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/grok-conversation-harmless
+- HuggingFaceH4/ultrachat_200k
+model-index:
+- name: mistral-7b-grok
+  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. -->
+
+# Mistral 7B Grok
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that has been aligned via Constitutional AI to mimic the style of [xAI's Grok assistant](https://grok.x.ai/).
+
+It achieves the following results on the evaluation set:
+- Loss: 0.9348
+
+## 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: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9326        | 1.0   | 545  | 0.9348          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.934799313545227,
+    "eval_runtime": 142.2532,
+    "eval_samples": 24266,
+    "eval_samples_per_second": 109.024,
+    "eval_steps_per_second": 1.708,
+    "perplexity": 2.5467023177917714,
+    "train_loss": 0.9725383741046311,
+    "train_runtime": 5277.8235,
+    "train_samples": 211055,
+    "train_samples_per_second": 26.46,
+    "train_steps_per_second": 0.103
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.934799313545227,
+    "eval_runtime": 142.2532,
+    "eval_samples": 24266,
+    "eval_samples_per_second": 109.024,
+    "eval_steps_per_second": 1.708,
+    "perplexity": 2.5467023177917714
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8e5d6996e054b7c10c1f891947d59e5e462db78fc33252fa58424451d706ea
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed331b509cdee31d8323097ac2b434359b7d8fae383c530753695b221139108c
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a38af2f763dfd084506059d5663c66a2410432723f91502dc3d828cad3d822
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9725383741046311,
+    "train_runtime": 5277.8235,
+    "train_samples": 211055,
+    "train_samples_per_second": 26.46,
+    "train_steps_per_second": 0.103
+}

trainer_state.json

@@ -0,0 +1,698 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9986257443884563,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.6363636363636366e-07,
+      "loss": 1.7361,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.597,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.2948,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.1706,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.1151,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0596,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 1.0556,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 1.0255,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 1.0134,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 1.0155,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 1.0141,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 1.0085,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999486216200688e-05,
+      "loss": 0.9965,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.9977,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9953791129491985e-05,
+      "loss": 1.0026,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.991790013823246e-05,
+      "loss": 0.9994,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9871817834144506e-05,
+      "loss": 0.9864,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9815591569910654e-05,
+      "loss": 1.0066,
+      "step": 85
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.9878,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9672948630390296e-05,
+      "loss": 0.989,
+      "step": 95
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9586678530366607e-05,
+      "loss": 0.9942,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.949055747010669e-05,
+      "loss": 1.0028,
+      "step": 105
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9384684220497605e-05,
+      "loss": 0.9865,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.926916757346022e-05,
+      "loss": 0.9907,
+      "step": 115
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9144126230158127e-05,
+      "loss": 0.984,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.9891,
+      "step": 125
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8865993063730003e-05,
+      "loss": 0.9858,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8713187041233896e-05,
+      "loss": 0.9872,
+      "step": 135
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8551427630053464e-05,
+      "loss": 0.9844,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8380881048918406e-05,
+      "loss": 0.9842,
+      "step": 145
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.820172254596956e-05,
+      "loss": 0.984,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8014136218679566e-05,
+      "loss": 0.9975,
+      "step": 155
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.9799,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.9936,
+      "step": 165
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7402779970753156e-05,
+      "loss": 0.9711,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7183493500977277e-05,
+      "loss": 0.9767,
+      "step": 175
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6956825506034866e-05,
+      "loss": 0.9754,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.672300890261317e-05,
+      "loss": 0.9858,
+      "step": 185
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6482283953077887e-05,
+      "loss": 0.9779,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.9868,
+      "step": 195
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.598110530491216e-05,
+      "loss": 0.9786,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5721166601221697e-05,
+      "loss": 0.9665,
+      "step": 205
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5455349012105488e-05,
+      "loss": 0.9734,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5183925683105254e-05,
+      "loss": 0.961,
+      "step": 215
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.4907175520039381e-05,
+      "loss": 0.9664,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4625382902408356e-05,
+      "loss": 0.9566,
+      "step": 225
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.9733,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.4047833431223938e-05,
+      "loss": 0.9753,
+      "step": 235
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.3752670048793744e-05,
+      "loss": 0.9666,
+      "step": 240
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3453650544213078e-05,
+      "loss": 0.9485,
+      "step": 245
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.315108218023621e-05,
+      "loss": 0.9666,
+      "step": 250
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2845275866310325e-05,
+      "loss": 0.9539,
+      "step": 255
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2536545839095074e-05,
+      "loss": 0.9516,
+      "step": 260
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.9611,
+      "step": 265
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.1911586287013726e-05,
+      "loss": 0.964,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1595998950333794e-05,
+      "loss": 0.9584,
+      "step": 275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.1278771616845061e-05,
+      "loss": 0.9472,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0960230259076819e-05,
+      "loss": 0.9521,
+      "step": 285
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.064070219980713e-05,
+      "loss": 0.9426,
+      "step": 290
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0320515775716556e-05,
+      "loss": 0.9434,
+      "step": 295
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.9592,
+      "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.67948422428345e-06,
+      "loss": 0.9556,
+      "step": 305
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.359297800192873e-06,
+      "loss": 0.9445,
+      "step": 310
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.039769740923183e-06,
+      "loss": 0.9506,
+      "step": 315
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.721228383154939e-06,
+      "loss": 0.9342,
+      "step": 320
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.404001049666211e-06,
+      "loss": 0.9377,
+      "step": 325
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.08841371298628e-06,
+      "loss": 0.9539,
+      "step": 330
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.9461,
+      "step": 335
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.463454160904928e-06,
+      "loss": 0.9457,
+      "step": 340
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.154724133689677e-06,
+      "loss": 0.9402,
+      "step": 345
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.848917819763794e-06,
+      "loss": 0.9472,
+      "step": 350
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.546349455786926e-06,
+      "loss": 0.9309,
+      "step": 355
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.24732995120626e-06,
+      "loss": 0.9274,
+      "step": 360
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.9432,
+      "step": 365
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.9349,
+      "step": 370
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.37461709759165e-06,
+      "loss": 0.9517,
+      "step": 375
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.092824479960625e-06,
+      "loss": 0.9277,
+      "step": 380
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.81607431689475e-06,
+      "loss": 0.9399,
+      "step": 385
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.544650987894514e-06,
+      "loss": 0.9413,
+      "step": 390
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.278833398778306e-06,
+      "loss": 0.9442,
+      "step": 395
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.01889469508784e-06,
+      "loss": 0.9457,
+      "step": 400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.929,
+      "step": 405
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.5177160469221184e-06,
+      "loss": 0.9365,
+      "step": 410
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.2769910973868314e-06,
+      "loss": 0.9393,
+      "step": 415
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.0431744939651365e-06,
+      "loss": 0.9292,
+      "step": 420
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.8165064990227255e-06,
+      "loss": 0.9208,
+      "step": 425
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.597220029246846e-06,
+      "loss": 0.9307,
+      "step": 430
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.3855404163086558e-06,
+      "loss": 0.9311,
+      "step": 435
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.9253,
+      "step": 440
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9858637813204352e-06,
+      "loss": 0.9221,
+      "step": 445
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7982774540304404e-06,
+      "loss": 0.9256,
+      "step": 450
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6191189510815942e-06,
+      "loss": 0.9384,
+      "step": 455
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4485723699465392e-06,
+      "loss": 0.9402,
+      "step": 460
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.286812958766106e-06,
+      "loss": 0.9339,
+      "step": 465
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.134006936269999e-06,
+      "loss": 0.9241,
+      "step": 470
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.9247,
+      "step": 475
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.558737698418762e-07,
+      "loss": 0.9238,
+      "step": 480
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.308324265397837e-07,
+      "loss": 0.9252,
+      "step": 485
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.153157795023956e-07,
+      "loss": 0.9266,
+      "step": 490
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.094425298933136e-07,
+      "loss": 0.931,
+      "step": 495
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.133214696333943e-07,
+      "loss": 0.9207,
+      "step": 500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.2705136960970554e-07,
+      "loss": 0.9194,
+      "step": 505
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.9219,
+      "step": 510
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.844084300893456e-07,
+      "loss": 0.923,
+      "step": 515
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2818216585549824e-07,
+      "loss": 0.9317,
+      "step": 520
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.209986176753947e-08,
+      "loss": 0.9299,
+      "step": 525
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.6208870508017703e-08,
+      "loss": 0.9231,
+      "step": 530
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.054607249663665e-08,
+      "loss": 0.9343,
+      "step": 535
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.137837993121064e-09,
+      "loss": 0.9226,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.9326,
+      "step": 545
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.934799313545227,
+      "eval_runtime": 143.5923,
+      "eval_samples_per_second": 108.007,
+      "eval_steps_per_second": 1.692,
+      "step": 545
+    },
+    {
+      "epoch": 1.0,
+      "step": 545,
+      "total_flos": 456238269726720.0,
+      "train_loss": 0.9725383741046311,
+      "train_runtime": 5277.8235,
+      "train_samples_per_second": 26.46,
+      "train_steps_per_second": 0.103
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 545,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 55,
+  "total_flos": 456238269726720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97393c2a78f330ed3bfc7e5d7c10eb73f641d9d68463a042f14a4296fc7f29d8
+size 6264