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_lr5.00E-06_schedulerconstant_warmup5.00E-02_minlr
+  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_lr5.00E-06_schedulerconstant_warmup5.00E-02_minlr
+
+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: 5e-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: constant
+- lr_scheduler_warmup_ratio: 0.05
+- 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": 0.5259489261518769,
+    "train_runtime": 12288.9627,
+    "train_samples_per_second": 64.441,
+    "train_steps_per_second": 0.031
+}

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:fae952fbfd87dddc4f119e297c96b4e7a203aa7ca60908dd0a3022ebc7476185
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36891c5c57ebd22a77ec90f10d36ba730162569eaac75fc4b6ba1037d59919c
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83edd5f3f1059f1929b3eba4ecf6cb58c5a54ae9bbb2a9e002d55610f12f44c
+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": 0.5259489261518769,
+    "train_runtime": 12288.9627,
+    "train_samples_per_second": 64.441,
+    "train_steps_per_second": 0.031
+}

trainer_log.jsonl

@@ -0,0 +1,39 @@
+{"current_steps": 10, "total_steps": 387, "loss": 0.7501, "learning_rate": 5e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:26:48", "remaining_time": "16:50:46"}
+{"current_steps": 20, "total_steps": 387, "loss": 0.6417, "learning_rate": 5e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:36:11", "remaining_time": "11:04:03"}
+{"current_steps": 30, "total_steps": 387, "loss": 0.6086, "learning_rate": 5e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:48:01", "remaining_time": "9:31:33"}
+{"current_steps": 40, "total_steps": 387, "loss": 0.598, "learning_rate": 5e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:55:47", "remaining_time": "8:03:58"}
+{"current_steps": 50, "total_steps": 387, "loss": 0.5869, "learning_rate": 5e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "1:03:46", "remaining_time": "7:09:48"}
+{"current_steps": 60, "total_steps": 387, "loss": 0.5776, "learning_rate": 5e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "1:18:45", "remaining_time": "7:09:16"}
+{"current_steps": 70, "total_steps": 387, "loss": 0.5742, "learning_rate": 5e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "1:34:10", "remaining_time": "7:06:26"}
+{"current_steps": 80, "total_steps": 387, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "1:49:59", "remaining_time": "7:02:05"}
+{"current_steps": 90, "total_steps": 387, "loss": 0.5648, "learning_rate": 5e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "1:57:47", "remaining_time": "6:28:42"}
+{"current_steps": 100, "total_steps": 387, "loss": 0.5661, "learning_rate": 5e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "2:01:54", "remaining_time": "5:49:53"}
+{"current_steps": 110, "total_steps": 387, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "2:05:13", "remaining_time": "5:15:19"}
+{"current_steps": 120, "total_steps": 387, "loss": 0.5603, "learning_rate": 5e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "2:07:45", "remaining_time": "4:44:15"}
+{"current_steps": 130, "total_steps": 387, "loss": 0.5535, "learning_rate": 5e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "2:10:36", "remaining_time": "4:18:12"}
+{"current_steps": 140, "total_steps": 387, "loss": 0.5174, "learning_rate": 5e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "2:13:05", "remaining_time": "3:54:48"}
+{"current_steps": 150, "total_steps": 387, "loss": 0.51, "learning_rate": 5e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "2:16:06", "remaining_time": "3:35:03"}
+{"current_steps": 160, "total_steps": 387, "loss": 0.5111, "learning_rate": 5e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "2:19:31", "remaining_time": "3:17:56"}
+{"current_steps": 170, "total_steps": 387, "loss": 0.5109, "learning_rate": 5e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "2:22:01", "remaining_time": "3:01:16"}
+{"current_steps": 180, "total_steps": 387, "loss": 0.5113, "learning_rate": 5e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "2:24:29", "remaining_time": "2:46:10"}
+{"current_steps": 190, "total_steps": 387, "loss": 0.5098, "learning_rate": 5e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "2:27:27", "remaining_time": "2:32:53"}
+{"current_steps": 200, "total_steps": 387, "loss": 0.5105, "learning_rate": 5e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "2:29:57", "remaining_time": "2:20:12"}
+{"current_steps": 210, "total_steps": 387, "loss": 0.5073, "learning_rate": 5e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "2:32:25", "remaining_time": "2:08:28"}
+{"current_steps": 220, "total_steps": 387, "loss": 0.5113, "learning_rate": 5e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "2:35:02", "remaining_time": "1:57:41"}
+{"current_steps": 230, "total_steps": 387, "loss": 0.5104, "learning_rate": 5e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "2:37:33", "remaining_time": "1:47:33"}
+{"current_steps": 240, "total_steps": 387, "loss": 0.5119, "learning_rate": 5e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "2:42:30", "remaining_time": "1:39:32"}
+{"current_steps": 250, "total_steps": 387, "loss": 0.5111, "learning_rate": 5e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "2:45:59", "remaining_time": "1:30:57"}
+{"current_steps": 260, "total_steps": 387, "loss": 0.5034, "learning_rate": 5e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "2:49:32", "remaining_time": "1:22:48"}
+{"current_steps": 270, "total_steps": 387, "loss": 0.4659, "learning_rate": 5e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:51:59", "remaining_time": "1:14:31"}
+{"current_steps": 280, "total_steps": 387, "loss": 0.4658, "learning_rate": 5e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "2:54:27", "remaining_time": "1:06:40"}
+{"current_steps": 290, "total_steps": 387, "loss": 0.4645, "learning_rate": 5e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "2:57:34", "remaining_time": "0:59:23"}
+{"current_steps": 300, "total_steps": 387, "loss": 0.4667, "learning_rate": 5e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "3:00:14", "remaining_time": "0:52:16"}
+{"current_steps": 310, "total_steps": 387, "loss": 0.47, "learning_rate": 5e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "3:02:41", "remaining_time": "0:45:22"}
+{"current_steps": 320, "total_steps": 387, "loss": 0.4705, "learning_rate": 5e-06, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "3:05:07", "remaining_time": "0:38:45"}
+{"current_steps": 330, "total_steps": 387, "loss": 0.4707, "learning_rate": 5e-06, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "3:07:59", "remaining_time": "0:32:28"}
+{"current_steps": 340, "total_steps": 387, "loss": 0.4725, "learning_rate": 5e-06, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "3:11:43", "remaining_time": "0:26:30"}
+{"current_steps": 350, "total_steps": 387, "loss": 0.4722, "learning_rate": 5e-06, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "3:14:38", "remaining_time": "0:20:34"}
+{"current_steps": 360, "total_steps": 387, "loss": 0.4711, "learning_rate": 5e-06, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "3:17:31", "remaining_time": "0:14:48"}
+{"current_steps": 370, "total_steps": 387, "loss": 0.4743, "learning_rate": 5e-06, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "3:19:57", "remaining_time": "0:09:11"}
+{"current_steps": 380, "total_steps": 387, "loss": 0.4716, "learning_rate": 5e-06, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "3:22:24", "remaining_time": "0:03:43"}
+{"current_steps": 387, "total_steps": 387, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:24:44", "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": 2.9215729246190634,
+      "learning_rate": 5e-06,
+      "loss": 0.7501,
+      "step": 10
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 1.7390484139778606,
+      "learning_rate": 5e-06,
+      "loss": 0.6417,
+      "step": 20
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 2.6303600299328775,
+      "learning_rate": 5e-06,
+      "loss": 0.6086,
+      "step": 30
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.7365672816191515,
+      "learning_rate": 5e-06,
+      "loss": 0.598,
+      "step": 40
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 2.5822057210689393,
+      "learning_rate": 5e-06,
+      "loss": 0.5869,
+      "step": 50
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.746996607003936,
+      "learning_rate": 5e-06,
+      "loss": 0.5776,
+      "step": 60
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.8948006480184871,
+      "learning_rate": 5e-06,
+      "loss": 0.5742,
+      "step": 70
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 2.4400520626498414,
+      "learning_rate": 5e-06,
+      "loss": 0.5726,
+      "step": 80
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 2.067112415972005,
+      "learning_rate": 5e-06,
+      "loss": 0.5648,
+      "step": 90
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.78188199676091,
+      "learning_rate": 5e-06,
+      "loss": 0.5661,
+      "step": 100
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.8707814480818752,
+      "learning_rate": 5e-06,
+      "loss": 0.5637,
+      "step": 110
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.1858683276722362,
+      "learning_rate": 5e-06,
+      "loss": 0.5603,
+      "step": 120
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 2.4440942695562193,
+      "learning_rate": 5e-06,
+      "loss": 0.5535,
+      "step": 130
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 3.010730904678519,
+      "learning_rate": 5e-06,
+      "loss": 0.5174,
+      "step": 140
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 2.260676020857914,
+      "learning_rate": 5e-06,
+      "loss": 0.51,
+      "step": 150
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 2.8965772384726995,
+      "learning_rate": 5e-06,
+      "loss": 0.5111,
+      "step": 160
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 2.561493912479322,
+      "learning_rate": 5e-06,
+      "loss": 0.5109,
+      "step": 170
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 2.381325960362653,
+      "learning_rate": 5e-06,
+      "loss": 0.5113,
+      "step": 180
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 2.597163347347591,
+      "learning_rate": 5e-06,
+      "loss": 0.5098,
+      "step": 190
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 2.3386390647615833,
+      "learning_rate": 5e-06,
+      "loss": 0.5105,
+      "step": 200
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 2.423259280958861,
+      "learning_rate": 5e-06,
+      "loss": 0.5073,
+      "step": 210
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.8305441285397837,
+      "learning_rate": 5e-06,
+      "loss": 0.5113,
+      "step": 220
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.972210760081399,
+      "learning_rate": 5e-06,
+      "loss": 0.5104,
+      "step": 230
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 2.1286521963156813,
+      "learning_rate": 5e-06,
+      "loss": 0.5119,
+      "step": 240
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 2.384913511133737,
+      "learning_rate": 5e-06,
+      "loss": 0.5111,
+      "step": 250
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 2.287778661831066,
+      "learning_rate": 5e-06,
+      "loss": 0.5034,
+      "step": 260
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.5497189232645128,
+      "learning_rate": 5e-06,
+      "loss": 0.4659,
+      "step": 270
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 1.1700554228567934,
+      "learning_rate": 5e-06,
+      "loss": 0.4658,
+      "step": 280
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 1.3050664193052923,
+      "learning_rate": 5e-06,
+      "loss": 0.4645,
+      "step": 290
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.4446705398465065,
+      "learning_rate": 5e-06,
+      "loss": 0.4667,
+      "step": 300
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 1.4968160462249973,
+      "learning_rate": 5e-06,
+      "loss": 0.47,
+      "step": 310
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 1.4716364495623662,
+      "learning_rate": 5e-06,
+      "loss": 0.4705,
+      "step": 320
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.172790704057467,
+      "learning_rate": 5e-06,
+      "loss": 0.4707,
+      "step": 330
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 1.7971924928025738,
+      "learning_rate": 5e-06,
+      "loss": 0.4725,
+      "step": 340
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 1.9994960190730922,
+      "learning_rate": 5e-06,
+      "loss": 0.4722,
+      "step": 350
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 1.1272436920505606,
+      "learning_rate": 5e-06,
+      "loss": 0.4711,
+      "step": 360
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 1.297666789751404,
+      "learning_rate": 5e-06,
+      "loss": 0.4743,
+      "step": 370
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 1.3226222258312366,
+      "learning_rate": 5e-06,
+      "loss": 0.4716,
+      "step": 380
+    },
+    {
+      "epoch": 3.0,
+      "step": 387,
+      "total_flos": 2589607581450240.0,
+      "train_loss": 0.5259489261518769,
+      "train_runtime": 12288.9627,
+      "train_samples_per_second": 64.441,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "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 sha256:5f470d0870263cbb1baae3fe7321cd82f3a03a6b00dbd3b89556045ef53b0cce
+size 7544