Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-full
+  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. -->
+
+# zephyr-7b-sft-full
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9246
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9135        | 0.67  | 544  | 0.9247          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 0.9246010184288025,
+    "eval_runtime": 737.4475,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 31.338,
+    "eval_steps_per_second": 0.98,
+    "train_loss": 0.9617018822361442,
+    "train_runtime": 25636.5929,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.108,
+    "train_steps_per_second": 0.032
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 0.9246010184288025,
+    "eval_runtime": 737.4475,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 31.338,
+    "eval_steps_per_second": 0.98
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2baa73d6485e394ec7024b7ada4daabea603850599f0d262707adb926143a5ba
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2b1eb9098fa58f83a78b7100312aa8c7edfc7845770225f978b8afcf2bff39
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fceaf8fb151e4093c1491598c28c12fb26e26e22cbe3220329e486008ccdfc76
+size 4540516344

model.safetensors.index.json

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

runs/Nov20_02-58-43_a800/events.out.tfevents.1700449150.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e65a96a53724ebab844a4105f9a123ffb80f76dc21294ef084728ceb23a736
+size 4176

runs/Nov20_03-00-03_a800/events.out.tfevents.1700449231.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62de772aa608542e808e7088d04e48c07b16e8e26c90ef8c60af0d51af658a8
+size 4176

runs/Nov20_03-02-07_a800/events.out.tfevents.1700449354.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd04d7ff037f06b97858b30a26f571d966f5aa53e9d9ad976906cc1083aad88b
+size 4176

runs/Nov20_03-03-25_a800/events.out.tfevents.1700449432.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb830fcb45741376effecf772648e23c97043ccfff40305c41fa1484ba8f2bf
+size 4330

runs/Nov20_03-06-29_a800/events.out.tfevents.1700449616.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056a1307827f029b4aa16324cacc8b15c80325ba5860680d2c45a272f0acbd01
+size 21835

runs/Nov20_03-06-29_a800/events.out.tfevents.1700475989.a800

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c981ba7cf69ecb15cba546d679feebd3513c8390e12e998cee543e86d717a3e7
+size 40

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_config.json

@@ -0,0 +1,41 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|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": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "train_loss": 0.9617018822361442,
+    "train_runtime": 25636.5929,
+    "train_samples": 207865,
+    "train_samples_per_second": 8.108,
+    "train_steps_per_second": 0.032
+}

trainer_state.json

@@ -0,0 +1,690 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6699507389162561,
+  "eval_steps": 500,
+  "global_step": 544,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.999992515597253e-05,
+      "loss": 1.1285,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9998128955328933e-05,
+      "loss": 1.5788,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.999251652147735e-05,
+      "loss": 1.1258,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9983164798668152e-05,
+      "loss": 1.0657,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 1.0275,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9953258882135594e-05,
+      "loss": 1.0167,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9932715879473385e-05,
+      "loss": 1.0005,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.990845596578807e-05,
+      "loss": 1.0064,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 1.0102,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9848823105958023e-05,
+      "loss": 0.9914,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.981347247496222e-05,
+      "loss": 0.9773,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9774449554890615e-05,
+      "loss": 0.9906,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 0.9641,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.968544662716026e-05,
+      "loss": 0.9709,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.963549992519223e-05,
+      "loss": 0.9926,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9581947533066577e-05,
+      "loss": 0.9775,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 0.9635,
+      "step": 80
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9464107179259126e-05,
+      "loss": 0.9849,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.939986331449053e-05,
+      "loss": 0.9601,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9332101936889262e-05,
+      "loss": 0.9798,
+      "step": 95
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 0.9764,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.918612937763622e-05,
+      "loss": 0.9676,
+      "step": 105
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.910797282022027e-05,
+      "loss": 0.9765,
+      "step": 110
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9026407978002415e-05,
+      "loss": 0.9701,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 0.9618,
+      "step": 120
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8853176792320598e-05,
+      "loss": 0.9644,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8761575273514005e-05,
+      "loss": 0.9595,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.866669509496227e-05,
+      "loss": 0.9624,
+      "step": 135
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.9506,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.9753,
+      "step": 145
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8362743705288127e-05,
+      "loss": 0.9533,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.825511600488435e-05,
+      "loss": 0.9807,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 0.9633,
+      "step": 160
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.803063462082095e-05,
+      "loss": 0.9619,
+      "step": 165
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.791386494010081e-05,
+      "loss": 0.9757,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7794133820415916e-05,
+      "loss": 0.9585,
+      "step": 175
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 0.9634,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7545967573401336e-05,
+      "loss": 0.9576,
+      "step": 185
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7417625312098453e-05,
+      "loss": 0.9413,
+      "step": 190
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.728650730913312e-05,
+      "loss": 0.9632,
+      "step": 195
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 0.9615,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7016141360674307e-05,
+      "loss": 0.9733,
+      "step": 205
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6876994588534234e-05,
+      "loss": 0.9777,
+      "step": 210
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6735274383578593e-05,
+      "loss": 0.9604,
+      "step": 215
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 0.9508,
+      "step": 220
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6444326750244145e-05,
+      "loss": 0.9489,
+      "step": 225
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.629520819706912e-05,
+      "loss": 0.953,
+      "step": 230
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.614373392074402e-05,
+      "loss": 0.9653,
+      "step": 235
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 0.9487,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5833945791074943e-05,
+      "loss": 0.9563,
+      "step": 245
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.56757478632168e-05,
+      "loss": 0.9516,
+      "step": 250
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5515426019799898e-05,
+      "loss": 0.9662,
+      "step": 255
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 0.9555,
+      "step": 260
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5188651334092373e-05,
+      "loss": 0.9644,
+      "step": 265
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5022320773808612e-05,
+      "loss": 0.96,
+      "step": 270
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4854110816220805e-05,
+      "loss": 0.9467,
+      "step": 275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.9477,
+      "step": 280
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4512305171541287e-05,
+      "loss": 0.9559,
+      "step": 285
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.9474,
+      "step": 290
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4163745979093997e-05,
+      "loss": 0.942,
+      "step": 295
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 0.9546,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3808954925925042e-05,
+      "loss": 0.9417,
+      "step": 305
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3629388050819547e-05,
+      "loss": 0.9466,
+      "step": 310
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3448463026279706e-05,
+      "loss": 0.9335,
+      "step": 315
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 0.9339,
+      "step": 320
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3082809826835707e-05,
+      "loss": 0.9574,
+      "step": 325
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2898218482625606e-05,
+      "loss": 0.9381,
+      "step": 330
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2712542599165998e-05,
+      "loss": 0.9493,
+      "step": 335
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 0.9451,
+      "step": 340
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.233821552063977e-05,
+      "loss": 0.9284,
+      "step": 345
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2149704402110243e-05,
+      "loss": 0.94,
+      "step": 350
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1960388844987529e-05,
+      "loss": 0.9369,
+      "step": 355
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1770339692844484e-05,
+      "loss": 0.9409,
+      "step": 360
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.157962806377179e-05,
+      "loss": 0.9426,
+      "step": 365
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1388325323764889e-05,
+      "loss": 0.9556,
+      "step": 370
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1196503060018243e-05,
+      "loss": 0.9442,
+      "step": 375
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1004233054136726e-05,
+      "loss": 0.9408,
+      "step": 380
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0811587255274313e-05,
+      "loss": 0.9436,
+      "step": 385
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0618637753210086e-05,
+      "loss": 0.9396,
+      "step": 390
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0425456751371564e-05,
+      "loss": 0.9268,
+      "step": 395
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0232116539815558e-05,
+      "loss": 0.9396,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0038689468176575e-05,
+      "loss": 0.9339,
+      "step": 405
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.845247918592937e-06,
+      "loss": 0.9394,
+      "step": 410
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.651864278620752e-06,
+      "loss": 0.9319,
+      "step": 415
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.9357,
+      "step": 420
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.26556014230371e-06,
+      "loss": 0.9407,
+      "step": 425
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.072784204417995e-06,
+      "loss": 0.9477,
+      "step": 430
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.9394,
+      "step": 435
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.688345254588579e-06,
+      "loss": 0.9255,
+      "step": 440
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.496826103134572e-06,
+      "loss": 0.9359,
+      "step": 445
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.305869452782446e-06,
+      "loss": 0.9344,
+      "step": 450
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.115546761216822e-06,
+      "loss": 0.9328,
+      "step": 455
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.92592924888925e-06,
+      "loss": 0.9309,
+      "step": 460
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.73708787236694e-06,
+      "loss": 0.9287,
+      "step": 465
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.549093297780133e-06,
+      "loss": 0.9301,
+      "step": 470
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.362015874378219e-06,
+      "loss": 0.9322,
+      "step": 475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.175925608204428e-06,
+      "loss": 0.9352,
+      "step": 480
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.990892135898937e-06,
+      "loss": 0.9297,
+      "step": 485
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.806984698640202e-06,
+      "loss": 0.9461,
+      "step": 490
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.624272116234319e-06,
+      "loss": 0.9305,
+      "step": 495
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.442822761362015e-06,
+      "loss": 0.9159,
+      "step": 500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.262704533992995e-06,
+      "loss": 0.9159,
+      "step": 505
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.083984835977154e-06,
+      "loss": 0.9177,
+      "step": 510
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.9067305458222054e-06,
+      "loss": 0.9323,
+      "step": 515
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.731007993667155e-06,
+      "loss": 0.9287,
+      "step": 520
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.556882936460966e-06,
+      "loss": 0.9137,
+      "step": 525
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.38442053335571e-06,
+      "loss": 0.9218,
+      "step": 530
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.213685321323451e-06,
+      "loss": 0.9275,
+      "step": 535
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.044741191005908e-06,
+      "loss": 0.9135,
+      "step": 540
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.9246816039085388,
+      "eval_runtime": 737.1423,
+      "eval_samples_per_second": 31.351,
+      "eval_steps_per_second": 0.981,
+      "step": 544
+    },
+    {
+      "epoch": 0.67,
+      "step": 544,
+      "total_flos": 455937286471680.0,
+      "train_loss": 0.9617018822361442,
+      "train_runtime": 25636.5929,
+      "train_samples_per_second": 8.108,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 812,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 455937286471680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb105c40e0207a8f0efcc9ba31619d2557b599d4bbc2d1d0ecf8ee40488a38cd
+size 5624