Upload folder using huggingface_hub

README.md

@@ -1,3 +1,71 @@
 ---
-license: cc-by-nc-sa-4.0
+base_model: meta-llama/Llama-2-13b-hf
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Llama-2-13b-lr-5e-5
+  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. -->
+
+# Llama-2-13b-lr-5e-5
+
+This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1454
+- Accuracy: 0.2150
+
+## 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-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.955         | 0.37  | 10   | 0.9061          | 0.2182   |
+| 0.8899        | 0.74  | 20   | 0.8734          | 0.2196   |
+| 0.879         | 1.11  | 30   | 0.9091          | 0.2174   |
+| 0.3295        | 1.48  | 40   | 0.9803          | 0.2173   |
+| 0.3711        | 1.85  | 50   | 0.9820          | 0.2174   |
+| 0.2927        | 2.22  | 60   | 1.0270          | 0.2153   |
+| 0.1703        | 2.59  | 70   | 1.0966          | 0.2131   |
+| 0.2011        | 2.96  | 80   | 1.1488          | 0.2145   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<PAD>": 32000
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.21497912092642818,
+    "eval_loss": 1.145392894744873,
+    "eval_runtime": 45.4464,
+    "eval_samples": 36,
+    "eval_samples_per_second": 0.792,
+    "eval_steps_per_second": 0.044,
+    "perplexity": 3.1436762481096006,
+    "train_loss": 0.5814771251178082,
+    "train_runtime": 6697.7067,
+    "train_samples": 841,
+    "train_samples_per_second": 0.377,
+    "train_steps_per_second": 0.012
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32008
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.21497912092642818,
+    "eval_loss": 1.145392894744873,
+    "eval_runtime": 45.4464,
+    "eval_samples": 36,
+    "eval_samples_per_second": 0.792,
+    "eval_steps_per_second": 0.044,
+    "perplexity": 3.1436762481096006
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.7,
+  "top_p": 1.0,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec4ddd133a7ec3378d6778c6e065a95dbb1bfa0025bf1492299b3f5c69b7fa5
+size 4978347720

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7324136ec8db6d6a5e060c59d9b33e6997c27ea774b3136e1c44efc3ad88e52
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4996950bab8d475d4a1e4d86c4587251d37e67551b1a300824a0352fbffce3
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc33bd10d3e4f30b5b5c67f369e1096d1ab0d2f7e15427621e35af205df3adfd
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d892cc263edd47885b2a4f2ae98bb5f580e73d3e93e14683067cdb6c29a833
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9fdaa981eb641a140196ad37e0b2432f5ea40edf73ea8dd88856a258197b8b
+size 1245318840

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031892480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "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": 3.0,
+    "train_loss": 0.5814771251178082,
+    "train_runtime": 6697.7067,
+    "train_samples": 841,
+    "train_samples_per_second": 0.377,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,586 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 1.0172,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.1546487678572864e-05,
+      "loss": 2.3198,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5e-05,
+      "loss": 2.4795,
+      "step": 3
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5e-05,
+      "loss": 1.551,
+      "step": 4
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5e-05,
+      "loss": 1.2034,
+      "step": 5
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5e-05,
+      "loss": 1.0527,
+      "step": 6
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5e-05,
+      "loss": 0.9743,
+      "step": 7
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5e-05,
+      "loss": 0.9738,
+      "step": 8
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 5e-05,
+      "loss": 0.939,
+      "step": 9
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 5e-05,
+      "loss": 0.955,
+      "step": 10
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.2181755564165483,
+      "eval_loss": 0.9061336517333984,
+      "eval_runtime": 44.217,
+      "eval_samples_per_second": 0.814,
+      "eval_steps_per_second": 0.045,
+      "step": 10
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5e-05,
+      "loss": 0.9513,
+      "step": 11
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5e-05,
+      "loss": 0.94,
+      "step": 12
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5e-05,
+      "loss": 0.9211,
+      "step": 13
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5e-05,
+      "loss": 0.8762,
+      "step": 14
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5e-05,
+      "loss": 0.9013,
+      "step": 15
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5e-05,
+      "loss": 0.8758,
+      "step": 16
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5e-05,
+      "loss": 0.8919,
+      "step": 17
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5e-05,
+      "loss": 0.8589,
+      "step": 18
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5e-05,
+      "loss": 0.8775,
+      "step": 19
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5e-05,
+      "loss": 0.8899,
+      "step": 20
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.21962848163933016,
+      "eval_loss": 0.8734426498413086,
+      "eval_runtime": 44.8031,
+      "eval_samples_per_second": 0.804,
+      "eval_steps_per_second": 0.045,
+      "step": 20
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 0.9011,
+      "step": 21
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5e-05,
+      "loss": 0.9195,
+      "step": 22
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5e-05,
+      "loss": 0.815,
+      "step": 23
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5e-05,
+      "loss": 0.8216,
+      "step": 24
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5e-05,
+      "loss": 0.8559,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5e-05,
+      "loss": 0.9071,
+      "step": 26
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5e-05,
+      "loss": 0.6228,
+      "step": 27
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 5e-05,
+      "loss": 0.3934,
+      "step": 28
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 5e-05,
+      "loss": 0.8846,
+      "step": 29
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 5e-05,
+      "loss": 0.879,
+      "step": 30
+    },
+    {
+      "epoch": 1.11,
+      "eval_accuracy": 0.2173899005553403,
+      "eval_loss": 0.9090863466262817,
+      "eval_runtime": 45.3228,
+      "eval_samples_per_second": 0.794,
+      "eval_steps_per_second": 0.044,
+      "step": 30
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 5e-05,
+      "loss": 0.8277,
+      "step": 31
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 5e-05,
+      "loss": 0.6593,
+      "step": 32
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 5e-05,
+      "loss": 0.5255,
+      "step": 33
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 5e-05,
+      "loss": 0.4102,
+      "step": 34
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5e-05,
+      "loss": 0.5839,
+      "step": 35
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5e-05,
+      "loss": 0.6197,
+      "step": 36
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5e-05,
+      "loss": 0.4026,
+      "step": 37
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5e-05,
+      "loss": 0.3835,
+      "step": 38
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5e-05,
+      "loss": 0.3433,
+      "step": 39
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5e-05,
+      "loss": 0.3295,
+      "step": 40
+    },
+    {
+      "epoch": 1.48,
+      "eval_accuracy": 0.21730380128287916,
+      "eval_loss": 0.9803322553634644,
+      "eval_runtime": 44.8946,
+      "eval_samples_per_second": 0.802,
+      "eval_steps_per_second": 0.045,
+      "step": 40
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 5e-05,
+      "loss": 0.3101,
+      "step": 41
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5e-05,
+      "loss": 0.3492,
+      "step": 42
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5e-05,
+      "loss": 0.2991,
+      "step": 43
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5e-05,
+      "loss": 0.3412,
+      "step": 44
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 5e-05,
+      "loss": 0.3824,
+      "step": 45
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 5e-05,
+      "loss": 0.3694,
+      "step": 46
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5e-05,
+      "loss": 0.3926,
+      "step": 47
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5e-05,
+      "loss": 0.3993,
+      "step": 48
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 5e-05,
+      "loss": 0.3678,
+      "step": 49
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 5e-05,
+      "loss": 0.3711,
+      "step": 50
+    },
+    {
+      "epoch": 1.85,
+      "eval_accuracy": 0.2173576133281674,
+      "eval_loss": 0.9820255637168884,
+      "eval_runtime": 44.7843,
+      "eval_samples_per_second": 0.804,
+      "eval_steps_per_second": 0.045,
+      "step": 50
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 5e-05,
+      "loss": 0.3825,
+      "step": 51
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5e-05,
+      "loss": 0.3914,
+      "step": 52
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5e-05,
+      "loss": 0.3962,
+      "step": 53
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5e-05,
+      "loss": 0.2342,
+      "step": 54
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5e-05,
+      "loss": 0.1572,
+      "step": 55
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5e-05,
+      "loss": 0.4409,
+      "step": 56
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5e-05,
+      "loss": 0.4072,
+      "step": 57
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 5e-05,
+      "loss": 0.4306,
+      "step": 58
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5e-05,
+      "loss": 0.338,
+      "step": 59
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5e-05,
+      "loss": 0.2927,
+      "step": 60
+    },
+    {
+      "epoch": 2.22,
+      "eval_accuracy": 0.2152804683800422,
+      "eval_loss": 1.0269818305969238,
+      "eval_runtime": 44.7279,
+      "eval_samples_per_second": 0.805,
+      "eval_steps_per_second": 0.045,
+      "step": 60
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 5e-05,
+      "loss": 0.3043,
+      "step": 61
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 5e-05,
+      "loss": 0.3134,
+      "step": 62
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5e-05,
+      "loss": 0.2565,
+      "step": 63
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5e-05,
+      "loss": 0.2333,
+      "step": 64
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 5e-05,
+      "loss": 0.2291,
+      "step": 65
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5e-05,
+      "loss": 0.1783,
+      "step": 66
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 5e-05,
+      "loss": 0.2058,
+      "step": 67
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5e-05,
+      "loss": 0.208,
+      "step": 68
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5e-05,
+      "loss": 0.1745,
+      "step": 69
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 5e-05,
+      "loss": 0.1703,
+      "step": 70
+    },
+    {
+      "epoch": 2.59,
+      "eval_accuracy": 0.2131279865685135,
+      "eval_loss": 1.0966472625732422,
+      "eval_runtime": 44.8433,
+      "eval_samples_per_second": 0.803,
+      "eval_steps_per_second": 0.045,
+      "step": 70
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 5e-05,
+      "loss": 0.2235,
+      "step": 71
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5e-05,
+      "loss": 0.2062,
+      "step": 72
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5e-05,
+      "loss": 0.2094,
+      "step": 73
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 5e-05,
+      "loss": 0.2123,
+      "step": 74
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 5e-05,
+      "loss": 0.2144,
+      "step": 75
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 5e-05,
+      "loss": 0.2091,
+      "step": 76
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5e-05,
+      "loss": 0.2116,
+      "step": 77
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5e-05,
+      "loss": 0.2123,
+      "step": 78
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5e-05,
+      "loss": 0.1891,
+      "step": 79
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5e-05,
+      "loss": 0.2011,
+      "step": 80
+    },
+    {
+      "epoch": 2.96,
+      "eval_accuracy": 0.2144840501097766,
+      "eval_loss": 1.1488189697265625,
+      "eval_runtime": 44.8519,
+      "eval_samples_per_second": 0.803,
+      "eval_steps_per_second": 0.045,
+      "step": 80
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5e-05,
+      "loss": 0.1493,
+      "step": 81
+    },
+    {
+      "epoch": 3.0,
+      "step": 81,
+      "total_flos": 10840779079680.0,
+      "train_loss": 0.5814771251178082,
+      "train_runtime": 6697.7067,
+      "train_samples_per_second": 0.377,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 81,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 10840779079680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b740b40b7d6c74e88739ff155f5ea28ccc990627785a092baa971031ecaaba4
+size 6712