Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
+model-index:
+- name: Llama-2-7b-hf-sft-full-3e
+  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-2-7b-hf-sft-full-3e
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the HuggingFaceH4/ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9247
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 512
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.931         | 0.7   | 285  | 0.9350          |
+| 0.8672        | 1.7   | 570  | 0.9245          |
+| 0.8189        | 2.7   | 855  | 0.9248          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.7,
+    "eval_loss": 0.9246993064880371,
+    "eval_runtime": 649.612,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 35.575,
+    "eval_steps_per_second": 0.557,
+    "train_loss": 0.8895609569828413,
+    "train_runtime": 69721.223,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.944,
+    "train_steps_per_second": 0.017
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.7,
+    "eval_loss": 0.9246993064880371,
+    "eval_runtime": 649.612,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 35.575,
+    "eval_steps_per_second": 0.557
+}

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": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd8f35e7d869e83ce4304ee5ad0aaef13aef0ff9c371a65cb7ae0f5774712b4
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b18ce61f613fb3a3a9693e20b6d5bdfeb1301aceece3f0247c81654fb3dc15b
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04beb61d164912b89745681d1d3b352a54a77a24fe8be36cb1238d5bce0c72bb
+size 3590488816

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "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-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.7,
+    "train_loss": 0.8895609569828413,
+    "train_runtime": 69721.223,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.944,
+    "train_steps_per_second": 0.017
+}

trainer_state.json

@@ -0,0 +1,1086 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.700431034482759,
+  "eval_steps": 500,
+  "global_step": 855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.999996673596474e-05,
+      "loss": 1.5474,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.999916841018338e-05,
+      "loss": 1.1821,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.999667377904184e-05,
+      "loss": 1.0465,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999251652147735e-05,
+      "loss": 1.0136,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9986697328916525e-05,
+      "loss": 1.0102,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.997921716919562e-05,
+      "loss": 0.9887,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 0.9841,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9959279200655044e-05,
+      "loss": 0.9791,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9946824707877695e-05,
+      "loss": 0.9779,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9932715879473385e-05,
+      "loss": 0.9757,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9916955061993724e-05,
+      "loss": 0.9683,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9899544876745774e-05,
+      "loss": 0.967,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 0.9688,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9859788259289104e-05,
+      "loss": 0.956,
+      "step": 65
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9837448439320027e-05,
+      "loss": 0.9524,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.981347247496222e-05,
+      "loss": 0.9517,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9787864353849232e-05,
+      "loss": 0.9568,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.976062833507162e-05,
+      "loss": 0.9546,
+      "step": 85
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 0.9612,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.970129099387443e-05,
+      "loss": 0.9496,
+      "step": 95
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.966919954032059e-05,
+      "loss": 0.9406,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.963549992519223e-05,
+      "loss": 0.9516,
+      "step": 105
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.96001977533407e-05,
+      "loss": 0.9667,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9563298896151325e-05,
+      "loss": 0.9505,
+      "step": 115
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 0.9409,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.948473593806691e-05,
+      "loss": 0.9459,
+      "step": 125
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9443084903603052e-05,
+      "loss": 0.9455,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.939986331449053e-05,
+      "loss": 0.9489,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.935507835925601e-05,
+      "loss": 0.9582,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.9386,
+      "step": 145
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 0.9492,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9211419074849275e-05,
+      "loss": 0.9403,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9160457721870483e-05,
+      "loss": 0.9418,
+      "step": 160
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.910797282022027e-05,
+      "loss": 0.9336,
+      "step": 165
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9053973099080585e-05,
+      "loss": 0.9359,
+      "step": 170
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.899846753957507e-05,
+      "loss": 0.942,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 0.9366,
+      "step": 180
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8882976080665573e-05,
+      "loss": 0.9332,
+      "step": 185
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8823009389565818e-05,
+      "loss": 0.9437,
+      "step": 190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8761575273514005e-05,
+      "loss": 0.9452,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8698683950107185e-05,
+      "loss": 0.9409,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.863434587930218e-05,
+      "loss": 0.9361,
+      "step": 205
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.9345,
+      "step": 210
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8501372536645607e-05,
+      "loss": 0.9343,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8432759380649565e-05,
+      "loss": 0.9368,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8362743705288127e-05,
+      "loss": 0.9482,
+      "step": 225
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8291337155425823e-05,
+      "loss": 0.9349,
+      "step": 230
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8218551607254594e-05,
+      "loss": 0.9381,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 0.9344,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8068892165500704e-05,
+      "loss": 0.9367,
+      "step": 245
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.799204316297159e-05,
+      "loss": 0.9392,
+      "step": 250
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.791386494010081e-05,
+      "loss": 0.9404,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7834370499331165e-05,
+      "loss": 0.9367,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7753573062016146e-05,
+      "loss": 0.9228,
+      "step": 265
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 0.934,
+      "step": 270
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7588123164487583e-05,
+      "loss": 0.932,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7503498221564026e-05,
+      "loss": 0.9342,
+      "step": 280
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7417625312098453e-05,
+      "loss": 0.931,
+      "step": 285
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 0.9349672198295593,
+      "eval_runtime": 647.743,
+      "eval_samples_per_second": 35.678,
+      "eval_steps_per_second": 0.559,
+      "step": 285
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.9067,
+      "step": 290
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.724219292755474e-05,
+      "loss": 0.9057,
+      "step": 295
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 0.8938,
+      "step": 300
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.7061942716231295e-05,
+      "loss": 0.9137,
+      "step": 305
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.697004827449941e-05,
+      "loss": 0.9014,
+      "step": 310
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.6876994588534234e-05,
+      "loss": 0.8978,
+      "step": 315
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.6782797134835305e-05,
+      "loss": 0.8976,
+      "step": 320
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.6687471580131266e-05,
+      "loss": 0.9012,
+      "step": 325
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 0.8996,
+      "step": 330
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.6493499770102906e-05,
+      "loss": 0.8946,
+      "step": 335
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.6394885775774976e-05,
+      "loss": 0.893,
+      "step": 340
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.629520819706912e-05,
+      "loss": 0.8968,
+      "step": 345
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.6194483612157232e-05,
+      "loss": 0.8834,
+      "step": 350
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.6092728773347118e-05,
+      "loss": 0.8833,
+      "step": 355
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 0.8822,
+      "step": 360
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.588619619719746e-05,
+      "loss": 0.8876,
+      "step": 365
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.578145280993533e-05,
+      "loss": 0.8854,
+      "step": 370
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.56757478632168e-05,
+      "loss": 0.8896,
+      "step": 375
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.556909893767332e-05,
+      "loss": 0.8805,
+      "step": 380
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.546152377093697e-05,
+      "loss": 0.8744,
+      "step": 385
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 0.886,
+      "step": 390
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.5243666431691061e-05,
+      "loss": 0.893,
+      "step": 395
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.5133420492770463e-05,
+      "loss": 0.8829,
+      "step": 400
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5022320773808612e-05,
+      "loss": 0.8776,
+      "step": 405
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4910385752684506e-05,
+      "loss": 0.8792,
+      "step": 410
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.4797634046202876e-05,
+      "loss": 0.8786,
+      "step": 415
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.881,
+      "step": 420
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.456975572041432e-05,
+      "loss": 0.8899,
+      "step": 425
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.4454667001366429e-05,
+      "loss": 0.8753,
+      "step": 430
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.8837,
+      "step": 435
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.4222286154386641e-05,
+      "loss": 0.8724,
+      "step": 440
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.4105032675563928e-05,
+      "loss": 0.8752,
+      "step": 445
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 0.8671,
+      "step": 450
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.3868497110808394e-05,
+      "loss": 0.8731,
+      "step": 455
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.3749254364988955e-05,
+      "loss": 0.8749,
+      "step": 460
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3629388050819547e-05,
+      "loss": 0.8738,
+      "step": 465
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3508918104221414e-05,
+      "loss": 0.8704,
+      "step": 470
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3387864561510713e-05,
+      "loss": 0.8744,
+      "step": 475
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 0.8796,
+      "step": 480
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3144087314980295e-05,
+      "loss": 0.8792,
+      "step": 485
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.3021404155695728e-05,
+      "loss": 0.8711,
+      "step": 490
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2898218482625606e-05,
+      "loss": 0.8706,
+      "step": 495
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2774550783760182e-05,
+      "loss": 0.8745,
+      "step": 500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2650421627259264e-05,
+      "loss": 0.8705,
+      "step": 505
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 0.8833,
+      "step": 510
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2400861594300015e-05,
+      "loss": 0.8743,
+      "step": 515
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.2275472224158089e-05,
+      "loss": 0.8744,
+      "step": 520
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.2149704402110243e-05,
+      "loss": 0.8711,
+      "step": 525
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.2023579045604485e-05,
+      "loss": 0.8738,
+      "step": 530
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.1897117131553239e-05,
+      "loss": 0.8754,
+      "step": 535
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.1770339692844484e-05,
+      "loss": 0.8788,
+      "step": 540
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.1643267814843624e-05,
+      "loss": 0.8776,
+      "step": 545
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.1515922631886605e-05,
+      "loss": 0.8595,
+      "step": 550
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.1388325323764889e-05,
+      "loss": 0.8736,
+      "step": 555
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.1260497112202895e-05,
+      "loss": 0.869,
+      "step": 560
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1132459257328423e-05,
+      "loss": 0.8741,
+      "step": 565
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1004233054136726e-05,
+      "loss": 0.8672,
+      "step": 570
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.9244597554206848,
+      "eval_runtime": 648.5324,
+      "eval_samples_per_second": 35.634,
+      "eval_steps_per_second": 0.558,
+      "step": 570
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0875839828948758e-05,
+      "loss": 0.8471,
+      "step": 575
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.8476,
+      "step": 580
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.0618637753210086e-05,
+      "loss": 0.8358,
+      "step": 585
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.0489871679984777e-05,
+      "loss": 0.8481,
+      "step": 590
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.0361024132299364e-05,
+      "loss": 0.8443,
+      "step": 595
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.0232116539815558e-05,
+      "loss": 0.8424,
+      "step": 600
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.0103170342181595e-05,
+      "loss": 0.8359,
+      "step": 605
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.974206985466442e-06,
+      "loss": 0.842,
+      "step": 610
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.845247918592937e-06,
+      "loss": 0.8403,
+      "step": 615
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.71631458977043e-06,
+      "loss": 0.8332,
+      "step": 620
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.587428442927581e-06,
+      "loss": 0.8351,
+      "step": 625
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.8371,
+      "step": 630
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.3298834280942e-06,
+      "loss": 0.8245,
+      "step": 635
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.201267394465997e-06,
+      "loss": 0.8248,
+      "step": 640
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.072784204417995e-06,
+      "loss": 0.8198,
+      "step": 645
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 8.944455227012667e-06,
+      "loss": 0.83,
+      "step": 650
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.816301805664188e-06,
+      "loss": 0.8298,
+      "step": 655
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.688345254588579e-06,
+      "loss": 0.8299,
+      "step": 660
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.560606855258808e-06,
+      "loss": 0.8229,
+      "step": 665
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.433107852865299e-06,
+      "loss": 0.8186,
+      "step": 670
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.305869452782446e-06,
+      "loss": 0.8281,
+      "step": 675
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.178912817041816e-06,
+      "loss": 0.8346,
+      "step": 680
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.052259060812489e-06,
+      "loss": 0.8253,
+      "step": 685
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 7.92592924888925e-06,
+      "loss": 0.8222,
+      "step": 690
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 7.799944392189128e-06,
+      "loss": 0.82,
+      "step": 695
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 0.8186,
+      "step": 700
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 7.549093297780133e-06,
+      "loss": 0.8291,
+      "step": 705
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 7.4242687811143795e-06,
+      "loss": 0.8318,
+      "step": 710
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 7.29987265481902e-06,
+      "loss": 0.8179,
+      "step": 715
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 7.175925608204428e-06,
+      "loss": 0.8286,
+      "step": 720
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.8162,
+      "step": 725
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 6.9294611343803594e-06,
+      "loss": 0.8194,
+      "step": 730
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 6.806984698640202e-06,
+      "loss": 0.8151,
+      "step": 735
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 6.685039318701827e-06,
+      "loss": 0.816,
+      "step": 740
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 6.563645276272466e-06,
+      "loss": 0.8222,
+      "step": 745
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.442822761362015e-06,
+      "loss": 0.8187,
+      "step": 750
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.322591868925082e-06,
+      "loss": 0.8177,
+      "step": 755
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 6.2029725955188165e-06,
+      "loss": 0.8203,
+      "step": 760
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 6.083984835977154e-06,
+      "loss": 0.8251,
+      "step": 765
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.965648380101916e-06,
+      "loss": 0.8249,
+      "step": 770
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.847982909371438e-06,
+      "loss": 0.8193,
+      "step": 775
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.731007993667155e-06,
+      "loss": 0.8212,
+      "step": 780
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 5.6147430880188145e-06,
+      "loss": 0.8196,
+      "step": 785
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 5.499207529368734e-06,
+      "loss": 0.8201,
+      "step": 790
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.38442053335571e-06,
+      "loss": 0.8295,
+      "step": 795
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.270401191119143e-06,
+      "loss": 0.8242,
+      "step": 800
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.1571684661238075e-06,
+      "loss": 0.8222,
+      "step": 805
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 5.044741191005908e-06,
+      "loss": 0.8251,
+      "step": 810
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.933138064440866e-06,
+      "loss": 0.822,
+      "step": 815
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.822377648033394e-06,
+      "loss": 0.828,
+      "step": 820
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 4.712478363230361e-06,
+      "loss": 0.8295,
+      "step": 825
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.603458488256992e-06,
+      "loss": 0.8257,
+      "step": 830
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 4.495336155076848e-06,
+      "loss": 0.8129,
+      "step": 835
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 0.8254,
+      "step": 840
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.281855892573056e-06,
+      "loss": 0.8204,
+      "step": 845
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.176533468851877e-06,
+      "loss": 0.8223,
+      "step": 850
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.07217959222365e-06,
+      "loss": 0.8189,
+      "step": 855
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.9248305559158325,
+      "eval_runtime": 648.4552,
+      "eval_samples_per_second": 35.639,
+      "eval_steps_per_second": 0.558,
+      "step": 855
+    },
+    {
+      "epoch": 2.7,
+      "step": 855,
+      "total_flos": 1433386950328320.0,
+      "train_loss": 0.8895609569828413,
+      "train_runtime": 69721.223,
+      "train_samples_per_second": 8.944,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1433386950328320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821198ddb8097e153fcc21966defc73e859eaa7016c0cec42b584ca094b982b3
+size 5880