Upload folder using huggingface_hub

README.md

@@ -1,3 +1,63 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: llm-jp/llm-jp-3-3.7b-instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [llm-jp/llm-jp-3-3.7b-instruct](https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct) on the cot_normal and the cot_math datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.5311
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9972714870395634,
+    "eval_loss": 0.5310924649238586,
+    "eval_runtime": 6.0236,
+    "eval_samples_per_second": 39.345,
+    "eval_steps_per_second": 9.961,
+    "total_flos": 53584849797120.0,
+    "train_loss": 0.48227007988372134,
+    "train_runtime": 1900.9535,
+    "train_samples_per_second": 24.658,
+    "train_steps_per_second": 0.193
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "llm-jp/llm-jp-3-3.7b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 99584
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9972714870395634,
+    "eval_loss": 0.5310924649238586,
+    "eval_runtime": 6.0236,
+    "eval_samples_per_second": 39.345,
+    "eval_steps_per_second": 9.961
+}

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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9849de8f5ca77debe626b69cf868054b3b4d74b28db51687396395c50396e378
+size 4990951344

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8f323922f7ab41cb5cd5be4406ef4c0d391c7271d55d1ebcd6197920044f9c
+size 2574904248

model.safetensors.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 7565826048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,86 @@
+{
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% set system_message = '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\n\n' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '\n\n### 指示:\n' + content + '\n\n### 応答:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "padding_side": "right",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9972714870395634,
+    "total_flos": 53584849797120.0,
+    "train_loss": 0.48227007988372134,
+    "train_runtime": 1900.9535,
+    "train_samples_per_second": 24.658,
+    "train_steps_per_second": 0.193
+}

trainer_log.jsonl

@@ -0,0 +1,37 @@
+{"current_steps": 10, "total_steps": 366, "loss": 0.7385, "lr": 2.702702702702703e-06, "epoch": 0.054570259208731244, "percentage": 2.73, "elapsed_time": "0:01:05", "remaining_time": "0:38:45"}
+{"current_steps": 20, "total_steps": 366, "loss": 0.6258, "lr": 5.405405405405406e-06, "epoch": 0.10914051841746249, "percentage": 5.46, "elapsed_time": "0:02:00", "remaining_time": "0:34:48"}
+{"current_steps": 30, "total_steps": 366, "loss": 0.5777, "lr": 8.108108108108109e-06, "epoch": 0.16371077762619374, "percentage": 8.2, "elapsed_time": "0:02:58", "remaining_time": "0:33:15"}
+{"current_steps": 40, "total_steps": 366, "loss": 0.5768, "lr": 9.997948550797227e-06, "epoch": 0.21828103683492497, "percentage": 10.93, "elapsed_time": "0:03:52", "remaining_time": "0:31:31"}
+{"current_steps": 50, "total_steps": 366, "loss": 0.5571, "lr": 9.961525153583327e-06, "epoch": 0.2728512960436562, "percentage": 13.66, "elapsed_time": "0:04:43", "remaining_time": "0:29:52"}
+{"current_steps": 60, "total_steps": 366, "loss": 0.5579, "lr": 9.879896064123961e-06, "epoch": 0.3274215552523875, "percentage": 16.39, "elapsed_time": "0:05:32", "remaining_time": "0:28:15"}
+{"current_steps": 70, "total_steps": 366, "loss": 0.5437, "lr": 9.75380502539778e-06, "epoch": 0.3819918144611187, "percentage": 19.13, "elapsed_time": "0:06:27", "remaining_time": "0:27:19"}
+{"current_steps": 80, "total_steps": 366, "loss": 0.5459, "lr": 9.584400884284546e-06, "epoch": 0.43656207366984995, "percentage": 21.86, "elapsed_time": "0:07:21", "remaining_time": "0:26:19"}
+{"current_steps": 90, "total_steps": 366, "loss": 0.5455, "lr": 9.373227124134888e-06, "epoch": 0.49113233287858116, "percentage": 24.59, "elapsed_time": "0:08:14", "remaining_time": "0:25:15"}
+{"current_steps": 100, "total_steps": 366, "loss": 0.5388, "lr": 9.122207801708802e-06, "epoch": 0.5457025920873124, "percentage": 27.32, "elapsed_time": "0:09:05", "remaining_time": "0:24:11"}
+{"current_steps": 110, "total_steps": 366, "loss": 0.5489, "lr": 8.833630016614976e-06, "epoch": 0.6002728512960437, "percentage": 30.05, "elapsed_time": "0:09:52", "remaining_time": "0:22:58"}
+{"current_steps": 120, "total_steps": 366, "loss": 0.5442, "lr": 8.51012307297624e-06, "epoch": 0.654843110504775, "percentage": 32.79, "elapsed_time": "0:10:36", "remaining_time": "0:21:45"}
+{"current_steps": 130, "total_steps": 366, "loss": 0.5359, "lr": 8.154634523184389e-06, "epoch": 0.7094133697135061, "percentage": 35.52, "elapsed_time": "0:11:25", "remaining_time": "0:20:45"}
+{"current_steps": 140, "total_steps": 366, "loss": 0.5318, "lr": 7.77040331201572e-06, "epoch": 0.7639836289222374, "percentage": 38.25, "elapsed_time": "0:12:17", "remaining_time": "0:19:50"}
+{"current_steps": 150, "total_steps": 366, "loss": 0.5323, "lr": 7.360930265797934e-06, "epoch": 0.8185538881309686, "percentage": 40.98, "elapsed_time": "0:13:06", "remaining_time": "0:18:52"}
+{"current_steps": 160, "total_steps": 366, "loss": 0.5171, "lr": 6.929946195508933e-06, "epoch": 0.8731241473396999, "percentage": 43.72, "elapsed_time": "0:14:01", "remaining_time": "0:18:03"}
+{"current_steps": 170, "total_steps": 366, "loss": 0.5234, "lr": 6.481377904428171e-06, "epoch": 0.927694406548431, "percentage": 46.45, "elapsed_time": "0:14:49", "remaining_time": "0:17:05"}
+{"current_steps": 180, "total_steps": 366, "loss": 0.5209, "lr": 6.019312410053286e-06, "epoch": 0.9822646657571623, "percentage": 49.18, "elapsed_time": "0:15:34", "remaining_time": "0:16:05"}
+{"current_steps": 190, "total_steps": 366, "loss": 0.4878, "lr": 5.547959706265068e-06, "epoch": 1.0368349249658937, "percentage": 51.91, "elapsed_time": "0:16:30", "remaining_time": "0:15:17"}
+{"current_steps": 200, "total_steps": 366, "loss": 0.4144, "lr": 5.071614405023938e-06, "epoch": 1.0914051841746248, "percentage": 54.64, "elapsed_time": "0:17:15", "remaining_time": "0:14:19"}
+{"current_steps": 210, "total_steps": 366, "loss": 0.4102, "lr": 4.594616607090028e-06, "epoch": 1.145975443383356, "percentage": 57.38, "elapsed_time": "0:18:07", "remaining_time": "0:13:27"}
+{"current_steps": 220, "total_steps": 366, "loss": 0.3954, "lr": 4.121312358283464e-06, "epoch": 1.2005457025920874, "percentage": 60.11, "elapsed_time": "0:19:06", "remaining_time": "0:12:41"}
+{"current_steps": 230, "total_steps": 366, "loss": 0.4026, "lr": 3.656014051577713e-06, "epoch": 1.2551159618008185, "percentage": 62.84, "elapsed_time": "0:20:03", "remaining_time": "0:11:51"}
+{"current_steps": 240, "total_steps": 366, "loss": 0.4061, "lr": 3.202961135812437e-06, "epoch": 1.30968622100955, "percentage": 65.57, "elapsed_time": "0:20:53", "remaining_time": "0:10:58"}
+{"current_steps": 250, "total_steps": 366, "loss": 0.4072, "lr": 2.766281489018482e-06, "epoch": 1.364256480218281, "percentage": 68.31, "elapsed_time": "0:21:38", "remaining_time": "0:10:02"}
+{"current_steps": 260, "total_steps": 366, "loss": 0.4081, "lr": 2.3499538082923607e-06, "epoch": 1.4188267394270122, "percentage": 71.04, "elapsed_time": "0:22:33", "remaining_time": "0:09:11"}
+{"current_steps": 270, "total_steps": 366, "loss": 0.4033, "lr": 1.9577713588953797e-06, "epoch": 1.4733969986357436, "percentage": 73.77, "elapsed_time": "0:23:27", "remaining_time": "0:08:20"}
+{"current_steps": 280, "total_steps": 366, "loss": 0.4045, "lr": 1.5933074128684333e-06, "epoch": 1.5279672578444747, "percentage": 76.5, "elapsed_time": "0:24:18", "remaining_time": "0:07:28"}
+{"current_steps": 290, "total_steps": 366, "loss": 0.4101, "lr": 1.2598826920598773e-06, "epoch": 1.5825375170532059, "percentage": 79.23, "elapsed_time": "0:25:05", "remaining_time": "0:06:34"}
+{"current_steps": 300, "total_steps": 366, "loss": 0.4028, "lr": 9.605351122011308e-07, "epoch": 1.6371077762619373, "percentage": 81.97, "elapsed_time": "0:26:01", "remaining_time": "0:05:43"}
+{"current_steps": 310, "total_steps": 366, "loss": 0.4015, "lr": 6.979921036993042e-07, "epoch": 1.6916780354706686, "percentage": 84.7, "elapsed_time": "0:26:51", "remaining_time": "0:04:51"}
+{"current_steps": 320, "total_steps": 366, "loss": 0.3958, "lr": 4.7464576133899043e-07, "epoch": 1.7462482946793996, "percentage": 87.43, "elapsed_time": "0:27:44", "remaining_time": "0:03:59"}
+{"current_steps": 330, "total_steps": 366, "loss": 0.4015, "lr": 2.925310493105099e-07, "epoch": 1.800818553888131, "percentage": 90.16, "elapsed_time": "0:28:29", "remaining_time": "0:03:06"}
+{"current_steps": 340, "total_steps": 366, "loss": 0.3974, "lr": 1.5330726014397668e-07, "epoch": 1.8553888130968623, "percentage": 92.9, "elapsed_time": "0:29:17", "remaining_time": "0:02:14"}
+{"current_steps": 350, "total_steps": 366, "loss": 0.3824, "lr": 5.824289648152126e-08, "epoch": 1.9099590723055935, "percentage": 95.63, "elapsed_time": "0:30:07", "remaining_time": "0:01:22"}
+{"current_steps": 360, "total_steps": 366, "loss": 0.4059, "lr": 8.204113433559202e-09, "epoch": 1.9645293315143246, "percentage": 98.36, "elapsed_time": "0:30:58", "remaining_time": "0:00:30"}
+{"current_steps": 366, "total_steps": 366, "epoch": 1.9972714870395634, "percentage": 100.0, "elapsed_time": "0:31:39", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,294 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9972714870395634,
+  "eval_steps": 500,
+  "global_step": 366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.054570259208731244,
+      "grad_norm": 2.4109368924528636,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.7385,
+      "step": 10
+    },
+    {
+      "epoch": 0.10914051841746249,
+      "grad_norm": 1.411542387667167,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.6258,
+      "step": 20
+    },
+    {
+      "epoch": 0.16371077762619374,
+      "grad_norm": 1.1090603733773723,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.5777,
+      "step": 30
+    },
+    {
+      "epoch": 0.21828103683492497,
+      "grad_norm": 1.0114013426864816,
+      "learning_rate": 9.997948550797227e-06,
+      "loss": 0.5768,
+      "step": 40
+    },
+    {
+      "epoch": 0.2728512960436562,
+      "grad_norm": 1.0925544693817912,
+      "learning_rate": 9.961525153583327e-06,
+      "loss": 0.5571,
+      "step": 50
+    },
+    {
+      "epoch": 0.3274215552523875,
+      "grad_norm": 1.1229468005660994,
+      "learning_rate": 9.879896064123961e-06,
+      "loss": 0.5579,
+      "step": 60
+    },
+    {
+      "epoch": 0.3819918144611187,
+      "grad_norm": 1.1457306310920201,
+      "learning_rate": 9.75380502539778e-06,
+      "loss": 0.5437,
+      "step": 70
+    },
+    {
+      "epoch": 0.43656207366984995,
+      "grad_norm": 1.0550317300389418,
+      "learning_rate": 9.584400884284546e-06,
+      "loss": 0.5459,
+      "step": 80
+    },
+    {
+      "epoch": 0.49113233287858116,
+      "grad_norm": 1.1312778139498736,
+      "learning_rate": 9.373227124134888e-06,
+      "loss": 0.5455,
+      "step": 90
+    },
+    {
+      "epoch": 0.5457025920873124,
+      "grad_norm": 1.0356499530726737,
+      "learning_rate": 9.122207801708802e-06,
+      "loss": 0.5388,
+      "step": 100
+    },
+    {
+      "epoch": 0.6002728512960437,
+      "grad_norm": 1.0985324135142938,
+      "learning_rate": 8.833630016614976e-06,
+      "loss": 0.5489,
+      "step": 110
+    },
+    {
+      "epoch": 0.654843110504775,
+      "grad_norm": 1.1083844896783392,
+      "learning_rate": 8.51012307297624e-06,
+      "loss": 0.5442,
+      "step": 120
+    },
+    {
+      "epoch": 0.7094133697135061,
+      "grad_norm": 1.0400224538030558,
+      "learning_rate": 8.154634523184389e-06,
+      "loss": 0.5359,
+      "step": 130
+    },
+    {
+      "epoch": 0.7639836289222374,
+      "grad_norm": 1.0744202310569617,
+      "learning_rate": 7.77040331201572e-06,
+      "loss": 0.5318,
+      "step": 140
+    },
+    {
+      "epoch": 0.8185538881309686,
+      "grad_norm": 1.0968285492605718,
+      "learning_rate": 7.360930265797934e-06,
+      "loss": 0.5323,
+      "step": 150
+    },
+    {
+      "epoch": 0.8731241473396999,
+      "grad_norm": 1.021879688858344,
+      "learning_rate": 6.929946195508933e-06,
+      "loss": 0.5171,
+      "step": 160
+    },
+    {
+      "epoch": 0.927694406548431,
+      "grad_norm": 1.0678204884195794,
+      "learning_rate": 6.481377904428171e-06,
+      "loss": 0.5234,
+      "step": 170
+    },
+    {
+      "epoch": 0.9822646657571623,
+      "grad_norm": 0.9343628148722539,
+      "learning_rate": 6.019312410053286e-06,
+      "loss": 0.5209,
+      "step": 180
+    },
+    {
+      "epoch": 1.0368349249658937,
+      "grad_norm": 1.2427110143315105,
+      "learning_rate": 5.547959706265068e-06,
+      "loss": 0.4878,
+      "step": 190
+    },
+    {
+      "epoch": 1.0914051841746248,
+      "grad_norm": 1.0091906053534088,
+      "learning_rate": 5.071614405023938e-06,
+      "loss": 0.4144,
+      "step": 200
+    },
+    {
+      "epoch": 1.145975443383356,
+      "grad_norm": 1.007806012878209,
+      "learning_rate": 4.594616607090028e-06,
+      "loss": 0.4102,
+      "step": 210
+    },
+    {
+      "epoch": 1.2005457025920874,
+      "grad_norm": 0.9761625285978685,
+      "learning_rate": 4.121312358283464e-06,
+      "loss": 0.3954,
+      "step": 220
+    },
+    {
+      "epoch": 1.2551159618008185,
+      "grad_norm": 0.9057196288186306,
+      "learning_rate": 3.656014051577713e-06,
+      "loss": 0.4026,
+      "step": 230
+    },
+    {
+      "epoch": 1.30968622100955,
+      "grad_norm": 0.9923780381040166,
+      "learning_rate": 3.202961135812437e-06,
+      "loss": 0.4061,
+      "step": 240
+    },
+    {
+      "epoch": 1.364256480218281,
+      "grad_norm": 0.9366887214418035,
+      "learning_rate": 2.766281489018482e-06,
+      "loss": 0.4072,
+      "step": 250
+    },
+    {
+      "epoch": 1.4188267394270122,
+      "grad_norm": 0.9615122411717134,
+      "learning_rate": 2.3499538082923607e-06,
+      "loss": 0.4081,
+      "step": 260
+    },
+    {
+      "epoch": 1.4733969986357436,
+      "grad_norm": 0.9926176178093427,
+      "learning_rate": 1.9577713588953797e-06,
+      "loss": 0.4033,
+      "step": 270
+    },
+    {
+      "epoch": 1.5279672578444747,
+      "grad_norm": 0.940790518539519,
+      "learning_rate": 1.5933074128684333e-06,
+      "loss": 0.4045,
+      "step": 280
+    },
+    {
+      "epoch": 1.5825375170532059,
+      "grad_norm": 0.9731821866758915,
+      "learning_rate": 1.2598826920598773e-06,
+      "loss": 0.4101,
+      "step": 290
+    },
+    {
+      "epoch": 1.6371077762619373,
+      "grad_norm": 0.9806874432871104,
+      "learning_rate": 9.605351122011308e-07,
+      "loss": 0.4028,
+      "step": 300
+    },
+    {
+      "epoch": 1.6916780354706686,
+      "grad_norm": 0.9218297203583149,
+      "learning_rate": 6.979921036993042e-07,
+      "loss": 0.4015,
+      "step": 310
+    },
+    {
+      "epoch": 1.7462482946793996,
+      "grad_norm": 0.9247290967153217,
+      "learning_rate": 4.7464576133899043e-07,
+      "loss": 0.3958,
+      "step": 320
+    },
+    {
+      "epoch": 1.800818553888131,
+      "grad_norm": 0.9418425606930034,
+      "learning_rate": 2.925310493105099e-07,
+      "loss": 0.4015,
+      "step": 330
+    },
+    {
+      "epoch": 1.8553888130968623,
+      "grad_norm": 0.9321370632360508,
+      "learning_rate": 1.5330726014397668e-07,
+      "loss": 0.3974,
+      "step": 340
+    },
+    {
+      "epoch": 1.9099590723055935,
+      "grad_norm": 0.9562537189946939,
+      "learning_rate": 5.824289648152126e-08,
+      "loss": 0.3824,
+      "step": 350
+    },
+    {
+      "epoch": 1.9645293315143246,
+      "grad_norm": 0.9275908894260719,
+      "learning_rate": 8.204113433559202e-09,
+      "loss": 0.4059,
+      "step": 360
+    },
+    {
+      "epoch": 1.9972714870395634,
+      "step": 366,
+      "total_flos": 53584849797120.0,
+      "train_loss": 0.48227007988372134,
+      "train_runtime": 1900.9535,
+      "train_samples_per_second": 24.658,
+      "train_steps_per_second": 0.193
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 53584849797120.0,
+  "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 sha256:1f8435baf91e26a9349dbe5c55a628ac3fdb0531f6a6ee1bf33e431230b92833
+size 7160