Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: oh-mistral-bs2048_lr2.00E-06_schedulercosine_with_min_lr_warmup1.00E-01_minlr5.00E-07
+  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. -->
+
+# oh-mistral-bs2048_lr2.00E-06_schedulercosine_with_min_lr_warmup1.00E-01_minlr5.00E-07
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
+
+## 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-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2048
+- total_eval_batch_size: 1024
+- 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_with_min_lr
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2589607581450240.0,
+    "train_loss": 0.5680107090824335,
+    "train_runtime": 5717.0554,
+    "train_samples_per_second": 138.517,
+    "train_steps_per_second": 0.068
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/marianna/models/mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3dd0c28d9148e52318288ccc2c798a251b2cda164ed26402711283bfa2fb5ff
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5479e7bc8e8ef77af9b6ad3d8899c92f0e8416fa0822f3e94c3ce1a5c57206
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a216388653bcd713c358d4bdbfc4e54b6601c01580f1fb8a87e2cee27ed207a0
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2589607581450240.0,
+    "train_loss": 0.5680107090824335,
+    "train_runtime": 5717.0554,
+    "train_samples_per_second": 138.517,
+    "train_steps_per_second": 0.068
+}

trainer_log.jsonl

@@ -0,0 +1,39 @@
+{"current_steps": 10, "total_steps": 387, "loss": 0.8373, "learning_rate": 5.128205128205127e-07, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:02:26", "remaining_time": "1:31:44"}
+{"current_steps": 20, "total_steps": 387, "loss": 0.7427, "learning_rate": 1.0256410256410255e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:04:49", "remaining_time": "1:28:29"}
+{"current_steps": 30, "total_steps": 387, "loss": 0.6724, "learning_rate": 1.5384615384615385e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:07:13", "remaining_time": "1:25:56"}
+{"current_steps": 40, "total_steps": 387, "loss": 0.6388, "learning_rate": 1.9999694388582144e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:09:37", "remaining_time": "1:23:27"}
+{"current_steps": 50, "total_steps": 387, "loss": 0.6189, "learning_rate": 1.996305114539343e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:12:01", "remaining_time": "1:21:03"}
+{"current_steps": 60, "total_steps": 387, "loss": 0.604, "learning_rate": 1.986562762056617e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:14:26", "remaining_time": "1:18:43"}
+{"current_steps": 70, "total_steps": 387, "loss": 0.5985, "learning_rate": 1.970821724686156e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "0:16:51", "remaining_time": "1:16:18"}
+{"current_steps": 80, "total_steps": 387, "loss": 0.5944, "learning_rate": 1.9492101999528085e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "0:19:15", "remaining_time": "1:13:54"}
+{"current_steps": 90, "total_steps": 387, "loss": 0.5848, "learning_rate": 1.921904195569016e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:21:40", "remaining_time": "1:11:33"}
+{"current_steps": 100, "total_steps": 387, "loss": 0.5861, "learning_rate": 1.8891260959998633e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "0:24:05", "remaining_time": "1:09:09"}
+{"current_steps": 110, "total_steps": 387, "loss": 0.5834, "learning_rate": 1.851142851328443e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "0:26:30", "remaining_time": "1:06:46"}
+{"current_steps": 120, "total_steps": 387, "loss": 0.5796, "learning_rate": 1.8082638031717025e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:28:56", "remaining_time": "1:04:23"}
+{"current_steps": 130, "total_steps": 387, "loss": 0.5742, "learning_rate": 1.7608381653528608e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "0:31:42", "remaining_time": "1:02:40"}
+{"current_steps": 140, "total_steps": 387, "loss": 0.5583, "learning_rate": 1.7092521798482026e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "0:34:08", "remaining_time": "1:00:14"}
+{"current_steps": 150, "total_steps": 387, "loss": 0.5509, "learning_rate": 1.653925971170678e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "0:36:34", "remaining_time": "0:57:47"}
+{"current_steps": 160, "total_steps": 387, "loss": 0.5531, "learning_rate": 1.595310124808702e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "0:39:00", "remaining_time": "0:55:20"}
+{"current_steps": 170, "total_steps": 387, "loss": 0.5528, "learning_rate": 1.5338820175859021e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "0:41:26", "remaining_time": "0:52:53"}
+{"current_steps": 180, "total_steps": 387, "loss": 0.5528, "learning_rate": 1.4701419298279508e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "0:43:51", "remaining_time": "0:50:26"}
+{"current_steps": 190, "total_steps": 387, "loss": 0.5503, "learning_rate": 1.4046089709996126e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "0:46:17", "remaining_time": "0:47:59"}
+{"current_steps": 200, "total_steps": 387, "loss": 0.5497, "learning_rate": 1.3378168519942735e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "0:48:42", "remaining_time": "0:45:32"}
+{"current_steps": 210, "total_steps": 387, "loss": 0.5452, "learning_rate": 1.2703095385071009e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "0:51:08", "remaining_time": "0:43:05"}
+{"current_steps": 220, "total_steps": 387, "loss": 0.5479, "learning_rate": 1.2026368208914614e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "0:53:33", "remaining_time": "0:40:39"}
+{"current_steps": 230, "total_steps": 387, "loss": 0.5464, "learning_rate": 1.1353498365783853e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "0:55:59", "remaining_time": "0:38:12"}
+{"current_steps": 240, "total_steps": 387, "loss": 0.5466, "learning_rate": 1.0689965815252208e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "0:58:25", "remaining_time": "0:35:46"}
+{"current_steps": 250, "total_steps": 387, "loss": 0.5447, "learning_rate": 1.0041174472489488e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "1:00:50", "remaining_time": "0:33:20"}
+{"current_steps": 260, "total_steps": 387, "loss": 0.5393, "learning_rate": 9.412408197912775e-07, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "1:03:34", "remaining_time": "0:31:03"}
+{"current_steps": 270, "total_steps": 387, "loss": 0.5208, "learning_rate": 8.808787764582444e-07, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "1:06:07", "remaining_time": "0:28:39"}
+{"current_steps": 280, "total_steps": 387, "loss": 0.5208, "learning_rate": 8.235229153807735e-07, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "1:08:33", "remaining_time": "0:26:11"}
+{"current_steps": 290, "total_steps": 387, "loss": 0.5183, "learning_rate": 7.696403518609027e-07, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "1:10:59", "remaining_time": "0:23:44"}
+{"current_steps": 300, "total_steps": 387, "loss": 0.5193, "learning_rate": 7.196699141100894e-07, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "1:13:25", "remaining_time": "0:21:17"}
+{"current_steps": 310, "total_steps": 387, "loss": 0.5205, "learning_rate": 6.740185693620994e-07, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "1:15:51", "remaining_time": "0:18:50"}
+{"current_steps": 320, "total_steps": 387, "loss": 0.5197, "learning_rate": 6.33058109466795e-07, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "1:18:17", "remaining_time": "0:16:23"}
+{"current_steps": 330, "total_steps": 387, "loss": 0.5188, "learning_rate": 5.97122122957871e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "1:20:43", "remaining_time": "0:13:56"}
+{"current_steps": 340, "total_steps": 387, "loss": 0.5194, "learning_rate": 5.665032782545057e-07, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "1:23:11", "remaining_time": "0:11:29"}
+{"current_steps": 350, "total_steps": 387, "loss": 0.5189, "learning_rate": 5.414509401229674e-07, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "1:25:38", "remaining_time": "0:09:03"}
+{"current_steps": 360, "total_steps": 387, "loss": 0.5179, "learning_rate": 5.221691388100914e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "1:28:04", "remaining_time": "0:06:36"}
+{"current_steps": 370, "total_steps": 387, "loss": 0.5209, "learning_rate": 5.088149083883318e-07, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "1:30:30", "remaining_time": "0:04:09"}
+{"current_steps": 380, "total_steps": 387, "loss": 0.5183, "learning_rate": 5.014970078451707e-07, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "1:32:57", "remaining_time": "0:01:42"}
+{"current_steps": 387, "total_steps": 387, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:35:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,308 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 387,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 10.039299147323163,
+      "learning_rate": 5.128205128205127e-07,
+      "loss": 0.8373,
+      "step": 10
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 5.1785620605635225,
+      "learning_rate": 1.0256410256410255e-06,
+      "loss": 0.7427,
+      "step": 20
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.2486956723274947,
+      "learning_rate": 1.5384615384615385e-06,
+      "loss": 0.6724,
+      "step": 30
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.1501605682975615,
+      "learning_rate": 1.9999694388582144e-06,
+      "loss": 0.6388,
+      "step": 40
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 2.434351003885209,
+      "learning_rate": 1.996305114539343e-06,
+      "loss": 0.6189,
+      "step": 50
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 2.201413453329991,
+      "learning_rate": 1.986562762056617e-06,
+      "loss": 0.604,
+      "step": 60
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.837540953963318,
+      "learning_rate": 1.970821724686156e-06,
+      "loss": 0.5985,
+      "step": 70
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 2.0815002297699996,
+      "learning_rate": 1.9492101999528085e-06,
+      "loss": 0.5944,
+      "step": 80
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 2.7291188254550263,
+      "learning_rate": 1.921904195569016e-06,
+      "loss": 0.5848,
+      "step": 90
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.6524130286283214,
+      "learning_rate": 1.8891260959998633e-06,
+      "loss": 0.5861,
+      "step": 100
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 2.091678454206057,
+      "learning_rate": 1.851142851328443e-06,
+      "loss": 0.5834,
+      "step": 110
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.68816760971438,
+      "learning_rate": 1.8082638031717025e-06,
+      "loss": 0.5796,
+      "step": 120
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 1.8829601528908666,
+      "learning_rate": 1.7608381653528608e-06,
+      "loss": 0.5742,
+      "step": 130
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.7829734798182293,
+      "learning_rate": 1.7092521798482026e-06,
+      "loss": 0.5583,
+      "step": 140
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.5200265288867116,
+      "learning_rate": 1.653925971170678e-06,
+      "loss": 0.5509,
+      "step": 150
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.1398642517762878,
+      "learning_rate": 1.595310124808702e-06,
+      "loss": 0.5531,
+      "step": 160
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 0.8689365392456778,
+      "learning_rate": 1.5338820175859021e-06,
+      "loss": 0.5528,
+      "step": 170
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 0.7870429524311625,
+      "learning_rate": 1.4701419298279508e-06,
+      "loss": 0.5528,
+      "step": 180
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 0.8053474144825696,
+      "learning_rate": 1.4046089709996126e-06,
+      "loss": 0.5503,
+      "step": 190
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 0.9448992836235834,
+      "learning_rate": 1.3378168519942735e-06,
+      "loss": 0.5497,
+      "step": 200
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 0.7454427253803518,
+      "learning_rate": 1.2703095385071009e-06,
+      "loss": 0.5452,
+      "step": 210
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 0.6468706573667633,
+      "learning_rate": 1.2026368208914614e-06,
+      "loss": 0.5479,
+      "step": 220
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 0.7163984884527171,
+      "learning_rate": 1.1353498365783853e-06,
+      "loss": 0.5464,
+      "step": 230
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 0.7290248205550818,
+      "learning_rate": 1.0689965815252208e-06,
+      "loss": 0.5466,
+      "step": 240
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 0.6443651162746207,
+      "learning_rate": 1.0041174472489488e-06,
+      "loss": 0.5447,
+      "step": 250
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 0.8246280857609625,
+      "learning_rate": 9.412408197912775e-07,
+      "loss": 0.5393,
+      "step": 260
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.7369363690149312,
+      "learning_rate": 8.808787764582444e-07,
+      "loss": 0.5208,
+      "step": 270
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 0.6741562153186622,
+      "learning_rate": 8.235229153807735e-07,
+      "loss": 0.5208,
+      "step": 280
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 0.6964395937752723,
+      "learning_rate": 7.696403518609027e-07,
+      "loss": 0.5183,
+      "step": 290
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.6584023989662436,
+      "learning_rate": 7.196699141100894e-07,
+      "loss": 0.5193,
+      "step": 300
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 0.6020138502643662,
+      "learning_rate": 6.740185693620994e-07,
+      "loss": 0.5205,
+      "step": 310
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 0.6348057726982681,
+      "learning_rate": 6.33058109466795e-07,
+      "loss": 0.5197,
+      "step": 320
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.6387533494670745,
+      "learning_rate": 5.97122122957871e-07,
+      "loss": 0.5188,
+      "step": 330
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 0.5836651843279197,
+      "learning_rate": 5.665032782545057e-07,
+      "loss": 0.5194,
+      "step": 340
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 0.584290228370155,
+      "learning_rate": 5.414509401229674e-07,
+      "loss": 0.5189,
+      "step": 350
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.6662656055411553,
+      "learning_rate": 5.221691388100914e-07,
+      "loss": 0.5179,
+      "step": 360
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 0.6072209105290904,
+      "learning_rate": 5.088149083883318e-07,
+      "loss": 0.5209,
+      "step": 370
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 0.7886919060292821,
+      "learning_rate": 5.014970078451707e-07,
+      "loss": 0.5183,
+      "step": 380
+    },
+    {
+      "epoch": 3.0,
+      "step": 387,
+      "total_flos": 2589607581450240.0,
+      "train_loss": 0.5680107090824335,
+      "train_runtime": 5717.0554,
+      "train_samples_per_second": 138.517,
+      "train_steps_per_second": 0.068
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 387,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2589607581450240.0,
+  "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 sha256:0bba4bd0a5d336c0c5cbdd87b57d1aa066927594c71e9dcc9b80de7d1d21b667
+size 7672