Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral_yt_transcribe_classification_4096
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mistral_yt_transcribe_classification_4096
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0436
+
+## 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-07
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0349        | 1.0   | 640  | 0.0343          |
+| 0.0289        | 2.0   | 1281 | 0.0311          |
+| 0.0153        | 3.0   | 1921 | 0.0351          |
+| 0.008         | 4.0   | 2560 | 0.0436          |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.04360830411314964,
+    "eval_runtime": 139.6808,
+    "eval_samples": 1132,
+    "eval_samples_per_second": 8.104,
+    "eval_steps_per_second": 1.017,
+    "train_loss": 0.14580336088401963,
+    "train_runtime": 21789.2225,
+    "train_samples": 10247,
+    "train_samples_per_second": 1.881,
+    "train_steps_per_second": 0.117
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.04360830411314964,
+    "eval_runtime": 139.6808,
+    "eval_samples": 1132,
+    "eval_samples_per_second": 8.104,
+    "eval_steps_per_second": 1.017
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfe4e51c5d9225e36b0a44fda5f3f69ca3876a5b786ba47cd5e25ea6807c0b5
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42a8791b1625a7caa6e1ba81109f20c83b7f99d8f220adda49c26427aaff712
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2497d0b2c3a3f2d11b765b06d970e3ff795b0577c617e676e6c7938816c7a791
+size 4540516344

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Input:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### Instruction:' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '\n###Response :\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '###Response :\n' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.14580336088401963,
+    "train_runtime": 21789.2225,
+    "train_samples": 10247,
+    "train_samples_per_second": 1.881,
+    "train_steps_per_second": 0.117
+}

trainer_state.json

@@ -0,0 +1,1598 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9968774395003903,
+  "eval_steps": 500,
+  "global_step": 2560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9531249999999998e-08,
+      "loss": 7.581,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9062499999999997e-08,
+      "loss": 7.3045,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.8593749999999995e-08,
+      "loss": 6.5971,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.812499999999999e-08,
+      "loss": 4.5283,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.765624999999999e-08,
+      "loss": 2.648,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.1718749999999999e-07,
+      "loss": 0.7747,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.3671875e-07,
+      "loss": 0.3446,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.5624999999999999e-07,
+      "loss": 0.2374,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.7578124999999998e-07,
+      "loss": 0.2114,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9531249999999998e-07,
+      "loss": 0.1836,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1484374999999998e-07,
+      "loss": 0.1666,
+      "step": 110
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.3437499999999998e-07,
+      "loss": 0.1569,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.5390625e-07,
+      "loss": 0.1352,
+      "step": 130
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.734375e-07,
+      "loss": 0.1093,
+      "step": 140
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9296875e-07,
+      "loss": 0.0876,
+      "step": 150
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.1249999999999997e-07,
+      "loss": 0.075,
+      "step": 160
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.3203124999999997e-07,
+      "loss": 0.0649,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.5156249999999997e-07,
+      "loss": 0.0656,
+      "step": 180
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.7109374999999997e-07,
+      "loss": 0.0641,
+      "step": 190
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.9062499999999997e-07,
+      "loss": 0.0609,
+      "step": 200
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.1015624999999996e-07,
+      "loss": 0.0588,
+      "step": 210
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.2968749999999996e-07,
+      "loss": 0.0637,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.4921874999999996e-07,
+      "loss": 0.062,
+      "step": 230
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.6874999999999996e-07,
+      "loss": 0.0538,
+      "step": 240
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.8828125e-07,
+      "loss": 0.0625,
+      "step": 250
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.999962815348554e-07,
+      "loss": 0.0576,
+      "step": 260
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.999544500723222e-07,
+      "loss": 0.0533,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.998661468690914e-07,
+      "loss": 0.0429,
+      "step": 280
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.997313883425684e-07,
+      "loss": 0.0468,
+      "step": 290
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.995501995471711e-07,
+      "loss": 0.0486,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.993226141696726e-07,
+      "loss": 0.045,
+      "step": 310
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.990486745229364e-07,
+      "loss": 0.047,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.987284315380512e-07,
+      "loss": 0.0448,
+      "step": 330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.98361944754861e-07,
+      "loss": 0.0486,
+      "step": 340
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.979492823108956e-07,
+      "loss": 0.0453,
+      "step": 350
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.974905209287019e-07,
+      "loss": 0.0494,
+      "step": 360
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.969857459015806e-07,
+      "loss": 0.052,
+      "step": 370
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.964350510777272e-07,
+      "loss": 0.0491,
+      "step": 380
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.958385388427848e-07,
+      "loss": 0.0306,
+      "step": 390
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.951963201008075e-07,
+      "loss": 0.037,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.94508514253642e-07,
+      "loss": 0.0565,
+      "step": 410
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.937752491787272e-07,
+      "loss": 0.0409,
+      "step": 420
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.929966612053198e-07,
+      "loss": 0.0465,
+      "step": 430
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.921728950891483e-07,
+      "loss": 0.04,
+      "step": 440
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.913041039854986e-07,
+      "loss": 0.0511,
+      "step": 450
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.903904494207405e-07,
+      "loss": 0.0439,
+      "step": 460
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.894321012622957e-07,
+      "loss": 0.0375,
+      "step": 470
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.884292376870567e-07,
+      "loss": 0.0418,
+      "step": 480
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.873820451482591e-07,
+      "loss": 0.0337,
+      "step": 490
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.86290718340817e-07,
+      "loss": 0.0384,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.851554601651241e-07,
+      "loss": 0.0404,
+      "step": 510
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.839764816893315e-07,
+      "loss": 0.0418,
+      "step": 520
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.827540021101046e-07,
+      "loss": 0.0353,
+      "step": 530
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.814882487118707e-07,
+      "loss": 0.0428,
+      "step": 540
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.801794568245619e-07,
+      "loss": 0.0408,
+      "step": 550
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.788278697798618e-07,
+      "loss": 0.0469,
+      "step": 560
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.774337388659657e-07,
+      "loss": 0.0373,
+      "step": 570
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.7599732328086083e-07,
+      "loss": 0.0386,
+      "step": 580
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.745188900841357e-07,
+      "loss": 0.0371,
+      "step": 590
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.729987141473285e-07,
+      "loss": 0.0399,
+      "step": 600
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.7143707810282263e-07,
+      "loss": 0.0385,
+      "step": 610
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.6983427229129924e-07,
+      "loss": 0.0361,
+      "step": 620
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.681905947077572e-07,
+      "loss": 0.0371,
+      "step": 630
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.6650635094610966e-07,
+      "loss": 0.0349,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.03431869298219681,
+      "eval_runtime": 141.0835,
+      "eval_samples_per_second": 8.024,
+      "eval_steps_per_second": 1.006,
+      "step": 640
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.647818541423671e-07,
+      "loss": 0.033,
+      "step": 650
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.6301742491641966e-07,
+      "loss": 0.0299,
+      "step": 660
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.612133913124268e-07,
+      "loss": 0.0289,
+      "step": 670
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.5937008873782697e-07,
+      "loss": 0.0403,
+      "step": 680
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.574878599009787e-07,
+      "loss": 0.0356,
+      "step": 690
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.5556705474744374e-07,
+      "loss": 0.0364,
+      "step": 700
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.53608030394925e-07,
+      "loss": 0.0347,
+      "step": 710
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.5161115106687066e-07,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.4957678802475785e-07,
+      "loss": 0.0409,
+      "step": 730
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 4.4750531949906723e-07,
+      "loss": 0.0372,
+      "step": 740
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.4539713061896194e-07,
+      "loss": 0.0256,
+      "step": 750
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 4.432526133406842e-07,
+      "loss": 0.0397,
+      "step": 760
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.4107216637468247e-07,
+      "loss": 0.0382,
+      "step": 770
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.3885619511148284e-07,
+      "loss": 0.0301,
+      "step": 780
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.366051115463184e-07,
+      "loss": 0.0327,
+      "step": 790
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.34319334202531e-07,
+      "loss": 0.0279,
+      "step": 800
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.3199928805375866e-07,
+      "loss": 0.0396,
+      "step": 810
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.296454044449245e-07,
+      "loss": 0.0321,
+      "step": 820
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 4.2725812101204046e-07,
+      "loss": 0.0275,
+      "step": 830
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 4.248378816008418e-07,
+      "loss": 0.0344,
+      "step": 840
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.223851361842667e-07,
+      "loss": 0.0408,
+      "step": 850
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.1990034077879736e-07,
+      "loss": 0.0286,
+      "step": 860
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.1738395735967656e-07,
+      "loss": 0.0352,
+      "step": 870
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.1483645377501717e-07,
+      "loss": 0.0316,
+      "step": 880
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.122583036588192e-07,
+      "loss": 0.0265,
+      "step": 890
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.096499863429113e-07,
+      "loss": 0.0342,
+      "step": 900
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.0701198676783356e-07,
+      "loss": 0.0331,
+      "step": 910
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.043447953926762e-07,
+      "loss": 0.0302,
+      "step": 920
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 4.0164890810389363e-07,
+      "loss": 0.0356,
+      "step": 930
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.9892482612310836e-07,
+      "loss": 0.0326,
+      "step": 940
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.961730559139236e-07,
+      "loss": 0.0367,
+      "step": 950
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.933941090877615e-07,
+      "loss": 0.0374,
+      "step": 960
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.9058850230874327e-07,
+      "loss": 0.0342,
+      "step": 970
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.87756757197631e-07,
+      "loss": 0.0254,
+      "step": 980
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.8489940023484736e-07,
+      "loss": 0.027,
+      "step": 990
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.8201696266259197e-07,
+      "loss": 0.0259,
+      "step": 1000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.7910998038607237e-07,
+      "loss": 0.0378,
+      "step": 1010
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 3.76178993873868e-07,
+      "loss": 0.0296,
+      "step": 1020
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.73224548057446e-07,
+      "loss": 0.03,
+      "step": 1030
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.702471922298469e-07,
+      "loss": 0.0292,
+      "step": 1040
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.6724747994355973e-07,
+      "loss": 0.0318,
+      "step": 1050
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.6422596890760513e-07,
+      "loss": 0.0341,
+      "step": 1060
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.6118322088384547e-07,
+      "loss": 0.0297,
+      "step": 1070
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.581198015825415e-07,
+      "loss": 0.0331,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.550362805571756e-07,
+      "loss": 0.0292,
+      "step": 1090
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.5193323109855914e-07,
+      "loss": 0.032,
+      "step": 1100
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.4881123012824637e-07,
+      "loss": 0.0248,
+      "step": 1110
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.4567085809127245e-07,
+      "loss": 0.025,
+      "step": 1120
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.4251269884823654e-07,
+      "loss": 0.0285,
+      "step": 1130
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3933733956675e-07,
+      "loss": 0.0377,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.3614537061227013e-07,
+      "loss": 0.0295,
+      "step": 1150
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.329373854383381e-07,
+      "loss": 0.0292,
+      "step": 1160
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.29713980476244e-07,
+      "loss": 0.0344,
+      "step": 1170
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.264757550241384e-07,
+      "loss": 0.0313,
+      "step": 1180
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.232233111356091e-07,
+      "loss": 0.0283,
+      "step": 1190
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.19957253507748e-07,
+      "loss": 0.0281,
+      "step": 1200
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.166781893687246e-07,
+      "loss": 0.0376,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.133867283648899e-07,
+      "loss": 0.0241,
+      "step": 1220
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.100834824474302e-07,
+      "loss": 0.0287,
+      "step": 1230
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.0676906575859327e-07,
+      "loss": 0.0327,
+      "step": 1240
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.0344409451750563e-07,
+      "loss": 0.0259,
+      "step": 1250
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.001091869056051e-07,
+      "loss": 0.0359,
+      "step": 1260
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.96764962951708e-07,
+      "loss": 0.0218,
+      "step": 1270
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.934120444167326e-07,
+      "loss": 0.0289,
+      "step": 1280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.03114560805261135,
+      "eval_runtime": 140.5702,
+      "eval_samples_per_second": 8.053,
+      "eval_steps_per_second": 1.01,
+      "step": 1281
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.900510546781011e-07,
+      "loss": 0.0225,
+      "step": 1290
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.8668261861384043e-07,
+      "loss": 0.0327,
+      "step": 1300
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.83307362486405e-07,
+      "loss": 0.0243,
+      "step": 1310
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.799259138262406e-07,
+      "loss": 0.0333,
+      "step": 1320
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.765389013151144e-07,
+      "loss": 0.0221,
+      "step": 1330
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.731469546692289e-07,
+      "loss": 0.02,
+      "step": 1340
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.6975070452214547e-07,
+      "loss": 0.0209,
+      "step": 1350
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.663507823075358e-07,
+      "loss": 0.0221,
+      "step": 1360
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.6294782014178547e-07,
+      "loss": 0.0282,
+      "step": 1370
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 2.595424507064704e-07,
+      "loss": 0.0206,
+      "step": 1380
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 2.561353071307281e-07,
+      "loss": 0.0205,
+      "step": 1390
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 2.5272702287354557e-07,
+      "loss": 0.0237,
+      "step": 1400
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 2.493182316059865e-07,
+      "loss": 0.0211,
+      "step": 1410
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.459095670933783e-07,
+      "loss": 0.0181,
+      "step": 1420
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.425016630774818e-07,
+      "loss": 0.0238,
+      "step": 1430
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.39095153158666e-07,
+      "loss": 0.0204,
+      "step": 1440
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.3569067067810788e-07,
+      "loss": 0.0212,
+      "step": 1450
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.3228884860004148e-07,
+      "loss": 0.0199,
+      "step": 1460
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.288903193940767e-07,
+      "loss": 0.0099,
+      "step": 1470
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.2549571491760981e-07,
+      "loss": 0.0184,
+      "step": 1480
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.221056662983482e-07,
+      "loss": 0.027,
+      "step": 1490
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.1872080381697023e-07,
+      "loss": 0.0134,
+      "step": 1500
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.153417567899433e-07,
+      "loss": 0.021,
+      "step": 1510
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1196915345252082e-07,
+      "loss": 0.0276,
+      "step": 1520
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.0860362084193982e-07,
+      "loss": 0.0232,
+      "step": 1530
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0524578468084185e-07,
+      "loss": 0.0209,
+      "step": 1540
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.0189626926093834e-07,
+      "loss": 0.0196,
+      "step": 1550
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.9855569732694128e-07,
+      "loss": 0.0242,
+      "step": 1560
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.9522468996078255e-07,
+      "loss": 0.0152,
+      "step": 1570
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.9190386646614138e-07,
+      "loss": 0.0187,
+      "step": 1580
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.8859384425330316e-07,
+      "loss": 0.0168,
+      "step": 1590
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.8529523872436977e-07,
+      "loss": 0.0254,
+      "step": 1600
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.8200866315884395e-07,
+      "loss": 0.0152,
+      "step": 1610
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.7873472859960736e-07,
+      "loss": 0.0213,
+      "step": 1620
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.7547404373931508e-07,
+      "loss": 0.0167,
+      "step": 1630
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.722272148072273e-07,
+      "loss": 0.0249,
+      "step": 1640
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.689948454564983e-07,
+      "loss": 0.0212,
+      "step": 1650
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.6577753665194498e-07,
+      "loss": 0.0267,
+      "step": 1660
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.6257588655831478e-07,
+      "loss": 0.0244,
+      "step": 1670
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.593904904290746e-07,
+      "loss": 0.0184,
+      "step": 1680
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.5622194049574046e-07,
+      "loss": 0.0215,
+      "step": 1690
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 1.530708258577698e-07,
+      "loss": 0.0251,
+      "step": 1700
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.4993773237303528e-07,
+      "loss": 0.0198,
+      "step": 1710
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.4682324254890133e-07,
+      "loss": 0.0246,
+      "step": 1720
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.4372793543392469e-07,
+      "loss": 0.0198,
+      "step": 1730
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.4065238651019646e-07,
+      "loss": 0.0198,
+      "step": 1740
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.3759716758634832e-07,
+      "loss": 0.0235,
+      "step": 1750
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.3456284669124157e-07,
+      "loss": 0.0217,
+      "step": 1760
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.3154998796835804e-07,
+      "loss": 0.0236,
+      "step": 1770
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.2855915157091495e-07,
+      "loss": 0.016,
+      "step": 1780
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.2559089355772017e-07,
+      "loss": 0.0208,
+      "step": 1790
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2264576578978955e-07,
+      "loss": 0.0167,
+      "step": 1800
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.197243158277442e-07,
+      "loss": 0.0206,
+      "step": 1810
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.1682708683000774e-07,
+      "loss": 0.0293,
+      "step": 1820
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1395461745182198e-07,
+      "loss": 0.0187,
+      "step": 1830
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.1110744174509951e-07,
+      "loss": 0.0163,
+      "step": 1840
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.0828608905913211e-07,
+      "loss": 0.0174,
+      "step": 1850
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.0549108394217417e-07,
+      "loss": 0.017,
+      "step": 1860
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.027229460439179e-07,
+      "loss": 0.0259,
+      "step": 1870
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 9.998219001887978e-08,
+      "loss": 0.0202,
+      "step": 1880
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 9.726932543071531e-08,
+      "loss": 0.0248,
+      "step": 1890
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 9.45848566574807e-08,
+      "loss": 0.025,
+      "step": 1900
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 9.192928279785864e-08,
+      "loss": 0.0166,
+      "step": 1910
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.930309757836516e-08,
+      "loss": 0.0153,
+      "step": 1920
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.035065386444330215,
+      "eval_runtime": 140.1636,
+      "eval_samples_per_second": 8.076,
+      "eval_steps_per_second": 1.013,
+      "step": 1921
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 8.670678926155586e-08,
+      "loss": 0.0134,
+      "step": 1930
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 8.414084055524725e-08,
+      "loss": 0.008,
+      "step": 1940
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 8.160572852277192e-08,
+      "loss": 0.0088,
+      "step": 1950
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 7.910192449428216e-08,
+      "loss": 0.0084,
+      "step": 1960
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 7.662989397911993e-08,
+      "loss": 0.0107,
+      "step": 1970
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.419009657926898e-08,
+      "loss": 0.011,
+      "step": 1980
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 7.178298590390508e-08,
+      "loss": 0.01,
+      "step": 1990
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 6.940900948506112e-08,
+      "loss": 0.0074,
+      "step": 2000
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 6.706860869442113e-08,
+      "loss": 0.0069,
+      "step": 2010
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 6.476221866126027e-08,
+      "loss": 0.0107,
+      "step": 2020
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 6.249026819154502e-08,
+      "loss": 0.0116,
+      "step": 2030
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 6.025317968820954e-08,
+      "loss": 0.011,
+      "step": 2040
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 5.805136907262198e-08,
+      "loss": 0.0104,
+      "step": 2050
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 5.5885245707256115e-08,
+      "loss": 0.0104,
+      "step": 2060
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 5.3755212319582105e-08,
+      "loss": 0.0068,
+      "step": 2070
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.166166492719124e-08,
+      "loss": 0.0133,
+      "step": 2080
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 4.960499276416819e-08,
+      "loss": 0.0058,
+      "step": 2090
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 4.758557820872397e-08,
+      "loss": 0.005,
+      "step": 2100
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 4.5603796712104096e-08,
+      "loss": 0.0056,
+      "step": 2110
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 4.366001672878406e-08,
+      "loss": 0.0058,
+      "step": 2120
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 4.175459964796635e-08,
+      "loss": 0.0059,
+      "step": 2130
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.988789972639045e-08,
+      "loss": 0.0107,
+      "step": 2140
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.806026402246926e-08,
+      "loss": 0.0055,
+      "step": 2150
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 3.62720323317634e-08,
+      "loss": 0.01,
+      "step": 2160
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.452353712380646e-08,
+      "loss": 0.0111,
+      "step": 2170
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 3.281510348029193e-08,
+      "loss": 0.0142,
+      "step": 2180
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 3.114704903463367e-08,
+      "loss": 0.0062,
+      "step": 2190
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 2.9519683912911263e-08,
+      "loss": 0.0044,
+      "step": 2200
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.793331067621099e-08,
+      "loss": 0.0048,
+      "step": 2210
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.6388224264373703e-08,
+      "loss": 0.0055,
+      "step": 2220
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.4884711941159124e-08,
+      "loss": 0.009,
+      "step": 2230
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.3423053240837514e-08,
+      "loss": 0.0063,
+      "step": 2240
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.200351991621871e-08,
+      "loss": 0.0167,
+      "step": 2250
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.0626375888127183e-08,
+      "loss": 0.0073,
+      "step": 2260
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 1.92918771963341e-08,
+      "loss": 0.0134,
+      "step": 2270
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.800027195195389e-08,
+      "loss": 0.0113,
+      "step": 2280
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.675180029131529e-08,
+      "loss": 0.0061,
+      "step": 2290
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 1.5546694331315086e-08,
+      "loss": 0.0113,
+      "step": 2300
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.4385178126262609e-08,
+      "loss": 0.0097,
+      "step": 2310
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.3267467626223605e-08,
+      "loss": 0.004,
+      "step": 2320
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.2193770636870187e-08,
+      "loss": 0.0061,
+      "step": 2330
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.1164286780845995e-08,
+      "loss": 0.0056,
+      "step": 2340
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.0179207460651595e-08,
+      "loss": 0.0095,
+      "step": 2350
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 9.238715823059323e-09,
+      "loss": 0.0103,
+      "step": 2360
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 8.342986725062118e-09,
+      "loss": 0.0092,
+      "step": 2370
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 7.492186701364006e-09,
+      "loss": 0.0053,
+      "step": 2380
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 6.68647393341798e-09,
+      "loss": 0.0116,
+      "step": 2390
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 5.925998220016659e-09,
+      "loss": 0.0082,
+      "step": 2400
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 5.210900949441571e-09,
+      "loss": 0.0096,
+      "step": 2410
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 4.5413150731761775e-09,
+      "loss": 0.01,
+      "step": 2420
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 3.917365081187396e-09,
+      "loss": 0.0083,
+      "step": 2430
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.3391669787802555e-09,
+      "loss": 0.0097,
+      "step": 2440
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 2.806828265030231e-09,
+      "loss": 0.0078,
+      "step": 2450
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.3204479127968414e-09,
+      "loss": 0.0102,
+      "step": 2460
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.880116350322508e-09,
+      "loss": 0.0065,
+      "step": 2470
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.4859154444200883e-09,
+      "loss": 0.0073,
+      "step": 2480
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.1379184852521872e-09,
+      "loss": 0.0044,
+      "step": 2490
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 8.361901727049203e-10,
+      "loss": 0.0062,
+      "step": 2500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 5.807866043588128e-10,
+      "loss": 0.011,
+      "step": 2510
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 3.7175526505922594e-10,
+      "loss": 0.0061,
+      "step": 2520
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 2.091350180878082e-10,
+      "loss": 0.0057,
+      "step": 2530
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 9.295609793708025e-11,
+      "loss": 0.0074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 2.324010468920945e-11,
+      "loss": 0.005,
+      "step": 2550
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.008,
+      "step": 2560
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.04360830411314964,
+      "eval_runtime": 140.4293,
+      "eval_samples_per_second": 8.061,
+      "eval_steps_per_second": 1.011,
+      "step": 2560
+    },
+    {
+      "epoch": 4.0,
+      "step": 2560,
+      "total_flos": 170146989342720.0,
+      "train_loss": 0.14580336088401963,
+      "train_runtime": 21789.2225,
+      "train_samples_per_second": 1.881,
+      "train_steps_per_second": 0.117
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 170146989342720.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e44618c2b67b19d30030653ce511f938985c4890cb2d1a742a4f310fb96d5d
+size 5371