Model save

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+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 the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9361
+
+## 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: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8975        | 1.0   | 1090 | 0.9361          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9360857009887695,
+    "eval_runtime": 142.4328,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 108.339,
+    "eval_steps_per_second": 1.699,
+    "train_loss": 0.07633444366105106,
+    "train_runtime": 563.397,
+    "train_samples": 207865,
+    "train_samples_per_second": 247.474,
+    "train_steps_per_second": 1.935
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9360857009887695,
+    "eval_runtime": 142.4328,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 108.339,
+    "eval_steps_per_second": 1.699
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f785798732c7ef26d34f5056ed95c789cca31876fc2729a8688e91a64f158975
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177eaac08f7ca90baa649f6c2eb979843b9bdd29897c8f18f53902c60c19df52
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e07e16b881fdcd0767315f89c90e17b12c08f7fa9626f3a9c98af34ef8e11de
+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/Jan04_05-23-59_ip-26-0-160-100/events.out.tfevents.1704346142.ip-26-0-160-100.3382977.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa99e8098751a7bc69139160fb9105027bfaf4928160bcb0f4974559c60c363
-size 35882
+oid sha256:e9e4f18870fd9b2fa6ebc8e60565df475d173cd762054df5c59399f71bb03e38
+size 39333

runs/Jan04_05-23-59_ip-26-0-160-100/events.out.tfevents.1704351859.ip-26-0-160-100.3382977.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af0caf924e1a63ca51364db8adfb97a89fa9796794426262d1ca9deea12eaf2
+size 359

runs/Jan04_07-04-47_ip-26-0-160-100/events.out.tfevents.1704351950.ip-26-0-160-100.3392767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b6db0e9c1cd7ef4de9cde93e9331b9633ba559e2af230c366ae0ce8f3e1764
+size 7882

runs/Jan04_07-04-47_ip-26-0-160-100/events.out.tfevents.1704352657.ip-26-0-160-100.3392767.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b18c2e6bc972deff43a5ecd96b6ca9aa5c395034de5a372cc2241f84302830
+size 359

runs/Jan04_10-30-54_ip-26-0-173-202/events.out.tfevents.1704364329.ip-26-0-173-202.762419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853512e77891740a2010e079ab848b85183c1c0be0c74f48acda22b33e19123a
+size 7882

runs/Jan04_10-30-54_ip-26-0-173-202/events.out.tfevents.1704365035.ip-26-0-173-202.762419.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59b08daba3595cd19aee855aac0abb19971d7fbbe561ce4a09cb2d613e352ac
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.07633444366105106,
+    "train_runtime": 563.397,
+    "train_samples": 207865,
+    "train_samples_per_second": 247.474,
+    "train_steps_per_second": 1.935
+}

trainer_state.json

@@ -0,0 +1,1352 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999958464785925e-05,
+      "loss": 1.6972,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9998961636899736e-05,
+      "loss": 2.1281,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9995846763238514e-05,
+      "loss": 1.4126,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9990656025890315e-05,
+      "loss": 1.2437,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9983390502829168e-05,
+      "loss": 1.1895,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.997405170290528e-05,
+      "loss": 1.1382,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9962641565531694e-05,
+      "loss": 1.0928,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.994916246028154e-05,
+      "loss": 1.0789,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 1.0751,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9916008972202586e-05,
+      "loss": 1.07,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9896341474445526e-05,
+      "loss": 1.0541,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.987461877752552e-05,
+      "loss": 1.0326,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.985084539265195e-05,
+      "loss": 1.0559,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.982502625690595e-05,
+      "loss": 1.0275,
+      "step": 65
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9797166732215078e-05,
+      "loss": 1.0187,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9767272604239823e-05,
+      "loss": 1.017,
+      "step": 75
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.973535008117207e-05,
+      "loss": 1.0065,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9701405792445815e-05,
+      "loss": 1.0279,
+      "step": 85
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 1.0082,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.962748053361675e-05,
+      "loss": 1.0237,
+      "step": 95
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9587514915766124e-05,
+      "loss": 1.0222,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9545558233573136e-05,
+      "loss": 0.9915,
+      "step": 105
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.950161920029191e-05,
+      "loss": 1.0055,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9455706940856602e-05,
+      "loss": 1.0128,
+      "step": 115
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.940783098998643e-05,
+      "loss": 1.0022,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9358001290205542e-05,
+      "loss": 1.0152,
+      "step": 125
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9306228189778255e-05,
+      "loss": 1.0172,
+      "step": 130
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.925252244055998e-05,
+      "loss": 1.0245,
+      "step": 135
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 1.021,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9139358007647085e-05,
+      "loss": 0.9968,
+      "step": 145
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.907992282510675e-05,
+      "loss": 0.9947,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.901860199120344e-05,
+      "loss": 1.0144,
+      "step": 155
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8955408240595396e-05,
+      "loss": 1.0033,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8890354696894374e-05,
+      "loss": 1.0049,
+      "step": 165
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8823454869940243e-05,
+      "loss": 0.9873,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8754722652995346e-05,
+      "loss": 1.0093,
+      "step": 175
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8684172319859258e-05,
+      "loss": 0.9972,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.861181852190451e-05,
+      "loss": 0.9873,
+      "step": 185
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 1.0001,
+      "step": 190
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8461761006559982e-05,
+      "loss": 0.9967,
+      "step": 195
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.838408845200758e-05,
+      "loss": 1.0163,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8304674751839583e-05,
+      "loss": 0.9769,
+      "step": 205
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8223536398107177e-05,
+      "loss": 0.9999,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8140690241024872e-05,
+      "loss": 0.9799,
+      "step": 215
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8056153485471167e-05,
+      "loss": 1.0117,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7969943687415575e-05,
+      "loss": 1.0062,
+      "step": 225
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.788207875027274e-05,
+      "loss": 0.9884,
+      "step": 230
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7792576921184374e-05,
+      "loss": 0.983,
+      "step": 235
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 1.0082,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7608737271566004e-05,
+      "loss": 1.0129,
+      "step": 245
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.751443762949772e-05,
+      "loss": 0.9906,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.741857744447869e-05,
+      "loss": 0.9831,
+      "step": 255
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.732117662404469e-05,
+      "loss": 0.9964,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7222255395679298e-05,
+      "loss": 1.0063,
+      "step": 265
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.712183430261319e-05,
+      "loss": 0.9783,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7019934199557868e-05,
+      "loss": 0.9893,
+      "step": 275
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.691657624837472e-05,
+      "loss": 0.9931,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6811781913680273e-05,
+      "loss": 0.9965,
+      "step": 285
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 1.0013,
+      "step": 290
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.659797143919165e-05,
+      "loss": 0.9802,
+      "step": 295
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6488999701978905e-05,
+      "loss": 0.9741,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6378680377196526e-05,
+      "loss": 0.9751,
+      "step": 305
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6267036375147728e-05,
+      "loss": 0.9728,
+      "step": 310
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.615409088123493e-05,
+      "loss": 0.9754,
+      "step": 315
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6039867351144778e-05,
+      "loss": 0.984,
+      "step": 320
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5924389505977038e-05,
+      "loss": 0.9737,
+      "step": 325
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5807681327318372e-05,
+      "loss": 0.996,
+      "step": 330
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5689767052262028e-05,
+      "loss": 0.9795,
+      "step": 335
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 0.984,
+      "step": 340
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.545041840860986e-05,
+      "loss": 0.9932,
+      "step": 345
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5329033746173975e-05,
+      "loss": 0.9787,
+      "step": 350
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.520654238933767e-05,
+      "loss": 0.9825,
+      "step": 355
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5082969776201948e-05,
+      "loss": 0.9931,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.4958341569415149e-05,
+      "loss": 0.9568,
+      "step": 365
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.483268365084351e-05,
+      "loss": 0.9846,
+      "step": 370
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4706022116196208e-05,
+      "loss": 0.9818,
+      "step": 375
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4578383269606004e-05,
+      "loss": 0.984,
+      "step": 380
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4449793618166594e-05,
+      "loss": 0.9678,
+      "step": 385
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 0.9944,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4189868910849779e-05,
+      "loss": 0.9879,
+      "step": 395
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4058587834217356e-05,
+      "loss": 0.9791,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.392646390001569e-05,
+      "loss": 0.9614,
+      "step": 405
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3793524546768358e-05,
+      "loss": 0.996,
+      "step": 410
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3659797382339162e-05,
+      "loss": 0.9549,
+      "step": 415
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3525310178198707e-05,
+      "loss": 0.9819,
+      "step": 420
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3390090863657048e-05,
+      "loss": 0.9993,
+      "step": 425
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.325416752006351e-05,
+      "loss": 0.9746,
+      "step": 430
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.311756837497499e-05,
+      "loss": 0.9756,
+      "step": 435
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.9647,
+      "step": 440
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.284245628637665e-05,
+      "loss": 0.963,
+      "step": 445
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2704000476115079e-05,
+      "loss": 0.974,
+      "step": 450
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.256498311899001e-05,
+      "loss": 0.9874,
+      "step": 455
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2425433085100224e-05,
+      "loss": 0.9654,
+      "step": 460
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2285379355166893e-05,
+      "loss": 0.9704,
+      "step": 465
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2144851014515055e-05,
+      "loss": 0.9639,
+      "step": 470
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2003877247033411e-05,
+      "loss": 0.9734,
+      "step": 475
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1862487329113606e-05,
+      "loss": 0.971,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.172071062357035e-05,
+      "loss": 0.9701,
+      "step": 485
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.9624,
+      "step": 490
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1436114696383749e-05,
+      "loss": 0.9673,
+      "step": 495
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1293354577522264e-05,
+      "loss": 0.9452,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1150325864327003e-05,
+      "loss": 0.977,
+      "step": 505
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1007058259945584e-05,
+      "loss": 0.9575,
+      "step": 510
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0863581517136776e-05,
+      "loss": 0.9677,
+      "step": 515
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0719925432091671e-05,
+      "loss": 0.9542,
+      "step": 520
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0576119838245843e-05,
+      "loss": 0.9599,
+      "step": 525
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.043219460008374e-05,
+      "loss": 0.969,
+      "step": 530
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0288179606936666e-05,
+      "loss": 0.9527,
+      "step": 535
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.972,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.9699,
+      "step": 545
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.855895233224431e-06,
+      "loss": 0.9501,
+      "step": 550
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.711820393063337e-06,
+      "loss": 0.9573,
+      "step": 555
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.56780539991626e-06,
+      "loss": 0.9764,
+      "step": 560
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.423880161754158e-06,
+      "loss": 0.9346,
+      "step": 565
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.28007456790833e-06,
+      "loss": 0.9478,
+      "step": 570
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.13641848286323e-06,
+      "loss": 0.9674,
+      "step": 575
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.992941740054418e-06,
+      "loss": 0.9302,
+      "step": 580
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.849674135672999e-06,
+      "loss": 0.9536,
+      "step": 585
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.9476,
+      "step": 590
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.563885303616253e-06,
+      "loss": 0.9606,
+      "step": 595
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.42142342645646e-06,
+      "loss": 0.9574,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.279289376429653e-06,
+      "loss": 0.9551,
+      "step": 605
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.137512670886397e-06,
+      "loss": 0.9431,
+      "step": 610
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.996122752966596e-06,
+      "loss": 0.9636,
+      "step": 615
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.855148985484946e-06,
+      "loss": 0.9409,
+      "step": 620
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.71462064483311e-06,
+      "loss": 0.955,
+      "step": 625
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.574566914899779e-06,
+      "loss": 0.9336,
+      "step": 630
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.4350168810099955e-06,
+      "loss": 0.9423,
+      "step": 635
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.9544,
+      "step": 640
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.157543713623353e-06,
+      "loss": 0.9384,
+      "step": 645
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.019678203706164e-06,
+      "loss": 0.9662,
+      "step": 650
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.882431625025016e-06,
+      "loss": 0.9527,
+      "step": 655
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.745832479936492e-06,
+      "loss": 0.952,
+      "step": 660
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.609909136342956e-06,
+      "loss": 0.9614,
+      "step": 665
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.474689821801295e-06,
+      "loss": 0.9555,
+      "step": 670
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.340202617660842e-06,
+      "loss": 0.9416,
+      "step": 675
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.206475453231644e-06,
+      "loss": 0.9413,
+      "step": 680
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.073536099984314e-06,
+      "loss": 0.9361,
+      "step": 685
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.9594,
+      "step": 690
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.810131089150228e-06,
+      "loss": 0.9547,
+      "step": 695
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.6797201335722064e-06,
+      "loss": 0.9376,
+      "step": 700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.550206381833409e-06,
+      "loss": 0.9512,
+      "step": 705
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.421616730394e-06,
+      "loss": 0.9445,
+      "step": 710
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.293977883803797e-06,
+      "loss": 0.9419,
+      "step": 715
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.167316349156495e-06,
+      "loss": 0.9328,
+      "step": 720
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.041658430584852e-06,
+      "loss": 0.9453,
+      "step": 725
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.917030223798057e-06,
+      "loss": 0.944,
+      "step": 730
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.793457610662334e-06,
+      "loss": 0.9309,
+      "step": 735
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.9394,
+      "step": 740
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.549581591390142e-06,
+      "loss": 0.9479,
+      "step": 745
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.429328831625565e-06,
+      "loss": 0.9465,
+      "step": 750
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.310232947737979e-06,
+      "loss": 0.943,
+      "step": 755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.192318672681631e-06,
+      "loss": 0.9366,
+      "step": 760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.0756104940229645e-06,
+      "loss": 0.9438,
+      "step": 765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.960132648855226e-06,
+      "loss": 0.9395,
+      "step": 770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.845909118765073e-06,
+      "loss": 0.9472,
+      "step": 775
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.732963624852275e-06,
+      "loss": 0.9317,
+      "step": 780
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6213196228034796e-06,
+      "loss": 0.9377,
+      "step": 785
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.9465,
+      "step": 790
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.402028560808357e-06,
+      "loss": 0.9264,
+      "step": 795
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.2944270416114256e-06,
+      "loss": 0.9412,
+      "step": 800
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.1882180863197308e-06,
+      "loss": 0.9301,
+      "step": 805
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.0834237516252817e-06,
+      "loss": 0.9333,
+      "step": 810
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.980065800442137e-06,
+      "loss": 0.9302,
+      "step": 815
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.878165697386812e-06,
+      "loss": 0.9481,
+      "step": 820
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.777744604320706e-06,
+      "loss": 0.9429,
+      "step": 825
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.678823375955314e-06,
+      "loss": 0.9343,
+      "step": 830
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.581422555521316e-06,
+      "loss": 0.9414,
+      "step": 835
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.919,
+      "step": 840
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.391262728433995e-06,
+      "loss": 0.946,
+      "step": 845
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.2985432127701945e-06,
+      "loss": 0.9358,
+      "step": 850
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.2074230788156325e-06,
+      "loss": 0.946,
+      "step": 855
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1179212497272582e-06,
+      "loss": 0.9148,
+      "step": 860
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.030056312584424e-06,
+      "loss": 0.9282,
+      "step": 865
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9438465145288377e-06,
+      "loss": 0.9295,
+      "step": 870
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8593097589751318e-06,
+      "loss": 0.9405,
+      "step": 875
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7764636018928249e-06,
+      "loss": 0.9349,
+      "step": 880
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6953252481604198e-06,
+      "loss": 0.935,
+      "step": 885
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.9241,
+      "step": 890
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5382389934400199e-06,
+      "loss": 0.9334,
+      "step": 895
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.462323714966114e-06,
+      "loss": 0.9485,
+      "step": 900
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3881814780954916e-06,
+      "loss": 0.9365,
+      "step": 905
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3158276801407432e-06,
+      "loss": 0.9249,
+      "step": 910
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2452773470046543e-06,
+      "loss": 0.9212,
+      "step": 915
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.1765451300597574e-06,
+      "loss": 0.9377,
+      "step": 920
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1096453031056265e-06,
+      "loss": 0.926,
+      "step": 925
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0445917594046073e-06,
+      "loss": 0.9171,
+      "step": 930
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.813980087965625e-07,
+      "loss": 0.9296,
+      "step": 935
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.9218,
+      "step": 940
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.606419923529175e-07,
+      "loss": 0.9351,
+      "step": 945
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.031048042356393e-07,
+      "loss": 0.9317,
+      "step": 950
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.474775594400252e-07,
+      "loss": 0.9417,
+      "step": 955
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.937718102217461e-07,
+      "loss": 0.9272,
+      "step": 960
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.41998709794458e-07,
+      "loss": 0.9199,
+      "step": 965
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.921690100135713e-07,
+      "loss": 0.9145,
+      "step": 970
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.442930591433992e-07,
+      "loss": 0.9287,
+      "step": 975
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.983807997080925e-07,
+      "loss": 0.94,
+      "step": 980
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.544417664268652e-07,
+      "loss": 0.9284,
+      "step": 985
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.9295,
+      "step": 990
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.725194663832521e-07,
+      "loss": 0.9277,
+      "step": 995
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.345532126395579e-07,
+      "loss": 0.9265,
+      "step": 1000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.985942075541848e-07,
+      "loss": 0.9267,
+      "step": 1005
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.646499188279328e-07,
+      "loss": 0.9119,
+      "step": 1010
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3272739576017945e-07,
+      "loss": 0.9308,
+      "step": 1015
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.028332677849254e-07,
+      "loss": 0.9358,
+      "step": 1020
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7497374309405346e-07,
+      "loss": 0.9223,
+      "step": 1025
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.49154607348051e-07,
+      "loss": 0.9168,
+      "step": 1030
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2538122247448325e-07,
+      "loss": 0.9243,
+      "step": 1035
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.9139,
+      "step": 1040
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.39910277974132e-08,
+      "loss": 0.9425,
+      "step": 1045
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.638281360408339e-08,
+      "loss": 0.9361,
+      "step": 1050
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.083753971846239e-08,
+      "loss": 0.9223,
+      "step": 1055
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.735843446830867e-08,
+      "loss": 0.9228,
+      "step": 1060
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.5948297094724463e-08,
+      "loss": 0.9145,
+      "step": 1065
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6609497170834154e-08,
+      "loss": 0.929,
+      "step": 1070
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.343974109685684e-09,
+      "loss": 0.9278,
+      "step": 1075
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.153236761488266e-09,
+      "loss": 0.9477,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0383631002686133e-09,
+      "loss": 0.9181,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.8975,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9360857009887695,
+      "eval_runtime": 143.3612,
+      "eval_samples_per_second": 107.637,
+      "eval_steps_per_second": 1.688,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "step": 1090,
+      "total_flos": 456447649382400.0,
+      "train_loss": 0.07633444366105106,
+      "train_runtime": 563.397,
+      "train_samples_per_second": 247.474,
+      "train_steps_per_second": 1.935
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 456447649382400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb0998c0608fdf72a6621877f24b651a1057b225e1ec18592940c06004cd02c
-size 5816
+oid sha256:0691346a7ead143f31dee13e381834e39d381f00c48ab175103779bd8ed770fd
+size 5880