Model save

README.md

@@ -0,0 +1,66 @@
+---
+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-math_code
+  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-math_code
+
+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: 0.9659
+
+## 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
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9313        | 1.0   | 1134 | 0.9659          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9658820033073425,
+    "eval_runtime": 299.5536,
+    "eval_samples": 23310,
+    "eval_samples_per_second": 51.623,
+    "eval_steps_per_second": 0.808,
+    "train_loss": 1.0355008869995306,
+    "train_runtime": 11406.2159,
+    "train_samples": 241210,
+    "train_samples_per_second": 12.721,
+    "train_steps_per_second": 0.099
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9658820033073425,
+    "eval_runtime": 299.5536,
+    "eval_samples": 23310,
+    "eval_samples_per_second": 51.623,
+    "eval_steps_per_second": 0.808
+}

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:c9d9ee425137192891dbd0adce37174cd97b6ceb677f664c39af9dc5d0cc7b61
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da729d00f5c5cad0feab5c2246c65c8d56e3722976800bcc976f5fcb9191fcb3
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4995985940ccc02543f665058e07bc5022cdad2e2ff2b50ca9cda20f108411ce
+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/Feb02_03-31-08_dsw-250-99c5474d8-m866l/events.out.tfevents.1706845527.dsw-250-99c5474d8-m866l.1793162.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6fe18dbf011540ad9068a6f82b666e7d8ef7961243dc8c1434d070ce8da5dc
-size 35939
+oid sha256:450deb0fe269102fafe4dcd7d3414ad3b82d0496ccdb9a16c3ac7644e34ef10c
+size 40646

runs/Feb02_03-31-08_dsw-250-99c5474d8-m866l/events.out.tfevents.1706857233.dsw-250-99c5474d8-m866l.1793162.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17416fd19ec7555f6cdf29df1b4aea98c52ab45234d890e4333c76d1ff7a9d2b
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.0355008869995306,
+    "train_runtime": 11406.2159,
+    "train_samples": 241210,
+    "train_samples_per_second": 12.721,
+    "train_steps_per_second": 0.099
+}

trainer_state.json

@@ -0,0 +1,1400 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.7543859649122808e-07,
+      "loss": 1.1293,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 1.1128,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7543859649122807e-06,
+      "loss": 1.05,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 1.0162,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5087719298245615e-06,
+      "loss": 0.9927,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.385964912280702e-06,
+      "loss": 0.9693,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.9767,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.140350877192983e-06,
+      "loss": 0.9709,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.017543859649123e-06,
+      "loss": 0.9477,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 0.9612,
+      "step": 45
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.771929824561405e-06,
+      "loss": 0.9665,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.649122807017545e-06,
+      "loss": 0.9478,
+      "step": 55
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.962,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1403508771929826e-05,
+      "loss": 0.941,
+      "step": 65
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2280701754385966e-05,
+      "loss": 0.9651,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3157894736842108e-05,
+      "loss": 0.9546,
+      "step": 75
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4035087719298246e-05,
+      "loss": 0.9602,
+      "step": 80
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4912280701754388e-05,
+      "loss": 0.9564,
+      "step": 85
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.578947368421053e-05,
+      "loss": 0.9636,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.9915,
+      "step": 95
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.754385964912281e-05,
+      "loss": 0.9807,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.9863,
+      "step": 105
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.929824561403509e-05,
+      "loss": 1.0003,
+      "step": 110
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999952568259327e-05,
+      "loss": 0.9932,
+      "step": 115
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998292504580528e-05,
+      "loss": 0.9928,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9994261303802982e-05,
+      "loss": 0.9956,
+      "step": 125
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.99878599219429e-05,
+      "loss": 0.9901,
+      "step": 130
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9979089877114905e-05,
+      "loss": 1.001,
+      "step": 135
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.996795324917199e-05,
+      "loss": 0.9797,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9954452679212297e-05,
+      "loss": 0.9936,
+      "step": 145
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.993859136895274e-05,
+      "loss": 1.0019,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9920373079969725e-05,
+      "loss": 0.9875,
+      "step": 155
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9899802132807073e-05,
+      "loss": 0.9972,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.9897,
+      "step": 165
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9851622334675065e-05,
+      "loss": 1.0089,
+      "step": 170
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9824024909747383e-05,
+      "loss": 0.9974,
+      "step": 175
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.979409767601366e-05,
+      "loss": 0.9756,
+      "step": 180
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9761847730843195e-05,
+      "loss": 0.9808,
+      "step": 185
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.972728272244605e-05,
+      "loss": 0.9849,
+      "step": 190
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9690410848059278e-05,
+      "loss": 0.9978,
+      "step": 195
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.965124085200289e-05,
+      "loss": 0.9947,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9609782023606124e-05,
+      "loss": 0.9907,
+      "step": 205
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.956604419500441e-05,
+      "loss": 0.9924,
+      "step": 210
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9520037738807674e-05,
+      "loss": 0.9869,
+      "step": 215
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9471773565640405e-05,
+      "loss": 0.9895,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9421263121554163e-05,
+      "loss": 0.9917,
+      "step": 225
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9368518385313108e-05,
+      "loss": 0.9919,
+      "step": 230
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9313551865553164e-05,
+      "loss": 1.0015,
+      "step": 235
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9256376597815565e-05,
+      "loss": 0.9698,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.919700614145541e-05,
+      "loss": 0.9783,
+      "step": 245
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.9932,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9071736499939765e-05,
+      "loss": 0.988,
+      "step": 255
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9005867023006374e-05,
+      "loss": 0.9871,
+      "step": 260
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.89378617668492e-05,
+      "loss": 0.9673,
+      "step": 265
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.886773685920062e-05,
+      "loss": 0.9999,
+      "step": 270
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.879550893047728e-05,
+      "loss": 1.0106,
+      "step": 275
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.872119510983611e-05,
+      "loss": 0.9705,
+      "step": 280
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.864481302111208e-05,
+      "loss": 0.9844,
+      "step": 285
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.856638077863863e-05,
+      "loss": 1.0078,
+      "step": 290
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8485916982951777e-05,
+      "loss": 0.9838,
+      "step": 295
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.840344071637893e-05,
+      "loss": 1.0826,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.831897153851342e-05,
+      "loss": 1.2311,
+      "step": 305
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8232529481575874e-05,
+      "loss": 5.7978,
+      "step": 310
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8144135045663486e-05,
+      "loss": 4.4919,
+      "step": 315
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8053809193888326e-05,
+      "loss": 4.4859,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7961573347405864e-05,
+      "loss": 1.8311,
+      "step": 325
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7867449380334834e-05,
+      "loss": 1.4734,
+      "step": 330
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.777145961456971e-05,
+      "loss": 1.2965,
+      "step": 335
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.767362681448697e-05,
+      "loss": 1.1761,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.757397418154643e-05,
+      "loss": 1.1421,
+      "step": 345
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.747252534878891e-05,
+      "loss": 1.1046,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.736930437523158e-05,
+      "loss": 1.0928,
+      "step": 355
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7264335740162244e-05,
+      "loss": 1.0886,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7157644337333975e-05,
+      "loss": 1.066,
+      "step": 365
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.7049255469061476e-05,
+      "loss": 1.0555,
+      "step": 370
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6939194840220497e-05,
+      "loss": 1.0727,
+      "step": 375
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.6827488552151855e-05,
+      "loss": 1.0532,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.671416309647136e-05,
+      "loss": 1.027,
+      "step": 385
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.659924534878723e-05,
+      "loss": 1.0237,
+      "step": 390
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6482762562326414e-05,
+      "loss": 0.9972,
+      "step": 395
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6364742361471416e-05,
+      "loss": 1.0156,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6245212735208994e-05,
+      "loss": 1.0124,
+      "step": 405
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.61242020304925e-05,
+      "loss": 1.0392,
+      "step": 410
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6001738945519278e-05,
+      "loss": 1.0376,
+      "step": 415
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.0139,
+      "step": 420
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.575257214289479e-05,
+      "loss": 1.0209,
+      "step": 425
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5625927516198235e-05,
+      "loss": 1.0046,
+      "step": 430
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5497948677140673e-05,
+      "loss": 0.9956,
+      "step": 435
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5368665976441802e-05,
+      "loss": 0.9862,
+      "step": 440
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.523811007403757e-05,
+      "loss": 1.0144,
+      "step": 445
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.510631193180907e-05,
+      "loss": 1.0134,
+      "step": 450
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.4973302806239796e-05,
+      "loss": 0.9988,
+      "step": 455
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4839114241003017e-05,
+      "loss": 0.993,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4703778059481096e-05,
+      "loss": 0.9854,
+      "step": 465
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4567326357218408e-05,
+      "loss": 0.9916,
+      "step": 470
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4429791494309769e-05,
+      "loss": 0.9933,
+      "step": 475
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.429120608772609e-05,
+      "loss": 0.9819,
+      "step": 480
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.415160300357914e-05,
+      "loss": 1.0046,
+      "step": 485
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.4011015349327188e-05,
+      "loss": 0.9986,
+      "step": 490
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.3869476465923455e-05,
+      "loss": 0.9993,
+      "step": 495
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.372701991990914e-05,
+      "loss": 0.9845,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3583679495453e-05,
+      "loss": 0.9756,
+      "step": 505
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3439489186339283e-05,
+      "loss": 0.9789,
+      "step": 510
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3294483187905938e-05,
+      "loss": 0.9969,
+      "step": 515
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.314869588893508e-05,
+      "loss": 0.9677,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.3002161863497529e-05,
+      "loss": 0.9821,
+      "step": 525
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2854915862753424e-05,
+      "loss": 0.9769,
+      "step": 530
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2706992806710839e-05,
+      "loss": 0.982,
+      "step": 535
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2558427775944357e-05,
+      "loss": 0.9792,
+      "step": 540
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2409256003275576e-05,
+      "loss": 0.9977,
+      "step": 545
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2259512865417478e-05,
+      "loss": 0.9833,
+      "step": 550
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.21092338745847e-05,
+      "loss": 0.9789,
+      "step": 555
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.1958454670071671e-05,
+      "loss": 0.9838,
+      "step": 560
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1807211009800592e-05,
+      "loss": 0.9623,
+      "step": 565
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.16555387618413e-05,
+      "loss": 0.9786,
+      "step": 570
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.1503473895905009e-05,
+      "loss": 0.9811,
+      "step": 575
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.135105247481393e-05,
+      "loss": 0.9707,
+      "step": 580
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1198310645948833e-05,
+      "loss": 0.9825,
+      "step": 585
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.943,
+      "step": 590
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0892010725759384e-05,
+      "loss": 0.981,
+      "step": 595
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.073852527474874e-05,
+      "loss": 0.9732,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0584864679364546e-05,
+      "loss": 0.952,
+      "step": 605
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0431065380862959e-05,
+      "loss": 0.9683,
+      "step": 610
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0277163853394166e-05,
+      "loss": 0.9479,
+      "step": 615
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.0123196595352385e-05,
+      "loss": 0.9826,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.96920012072012e-06,
+      "loss": 0.9723,
+      "step": 625
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.815210950408703e-06,
+      "loss": 0.9632,
+      "step": 630
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.661265603597223e-06,
+      "loss": 0.9551,
+      "step": 635
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.507400589071833e-06,
+      "loss": 0.9668,
+      "step": 640
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.353652396567558e-06,
+      "loss": 0.9498,
+      "step": 645
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.200057488114585e-06,
+      "loss": 0.9597,
+      "step": 650
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.04665228939114e-06,
+      "loss": 0.9802,
+      "step": 655
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.893473181084993e-06,
+      "loss": 0.978,
+      "step": 660
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.740556490265621e-06,
+      "loss": 0.9744,
+      "step": 665
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.58793848176909e-06,
+      "loss": 0.9602,
+      "step": 670
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.9641,
+      "step": 675
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.283743208336403e-06,
+      "loss": 0.9695,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.13223808458814e-06,
+      "loss": 0.96,
+      "step": 685
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.9811759084299e-06,
+      "loss": 0.9601,
+      "step": 690
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.8305925048918e-06,
+      "loss": 0.9455,
+      "step": 695
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.680523585461021e-06,
+      "loss": 0.9624,
+      "step": 700
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.531004739612668e-06,
+      "loss": 0.9691,
+      "step": 705
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.382071426369597e-06,
+      "loss": 0.9533,
+      "step": 710
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.23375896589313e-06,
+      "loss": 0.9578,
+      "step": 715
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.086102531106755e-06,
+      "loss": 0.9647,
+      "step": 720
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.939137139354704e-06,
+      "loss": 0.9565,
+      "step": 725
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.7928976440974504e-06,
+      "loss": 0.9504,
+      "step": 730
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.647418726646065e-06,
+      "loss": 0.9621,
+      "step": 735
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.502734887937389e-06,
+      "loss": 0.9562,
+      "step": 740
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.3588804403520044e-06,
+      "loss": 0.9438,
+      "step": 745
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.215889499576898e-06,
+      "loss": 0.962,
+      "step": 750
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.073795976514785e-06,
+      "loss": 0.9606,
+      "step": 755
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.9284,
+      "step": 760
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.7924357550168534e-06,
+      "loss": 0.9583,
+      "step": 765
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.653235782340351e-06,
+      "loss": 0.9583,
+      "step": 770
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.515066663071199e-06,
+      "loss": 0.9197,
+      "step": 775
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.3779611645968696e-06,
+      "loss": 0.9554,
+      "step": 780
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.241951802062696e-06,
+      "loss": 0.9463,
+      "step": 785
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.107070830660765e-06,
+      "loss": 0.9402,
+      "step": 790
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.973350237980466e-06,
+      "loss": 0.951,
+      "step": 795
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.8408217364224886e-06,
+      "loss": 0.9491,
+      "step": 800
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.709516755678113e-06,
+      "loss": 0.9496,
+      "step": 805
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.579466435275506e-06,
+      "loss": 0.9454,
+      "step": 810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.450701617194864e-06,
+      "loss": 0.9669,
+      "step": 815
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.323252838554099e-06,
+      "loss": 0.9583,
+      "step": 820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.197150324366844e-06,
+      "loss": 0.9417,
+      "step": 825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.0724239803744524e-06,
+      "loss": 0.9574,
+      "step": 830
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.949103385953732e-06,
+      "loss": 0.97,
+      "step": 835
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.827217787102072e-06,
+      "loss": 0.9531,
+      "step": 840
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.7067960895016277e-06,
+      "loss": 0.9292,
+      "step": 845
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.587866851664219e-06,
+      "loss": 0.9357,
+      "step": 850
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.4704582781585596e-06,
+      "loss": 0.9451,
+      "step": 855
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.3545982129214227e-06,
+      "loss": 0.9502,
+      "step": 860
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.2403141326543365e-06,
+      "loss": 0.9528,
+      "step": 865
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.1276331403073733e-06,
+      "loss": 0.9545,
+      "step": 870
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.016581958651559e-06,
+      "loss": 0.9563,
+      "step": 875
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.907186923941466e-06,
+      "loss": 0.9422,
+      "step": 880
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.799473979669456e-06,
+      "loss": 0.9539,
+      "step": 885
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.6934686704130698e-06,
+      "loss": 0.9589,
+      "step": 890
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.5891961357770267e-06,
+      "loss": 0.9447,
+      "step": 895
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.4866811044312667e-06,
+      "loss": 0.943,
+      "step": 900
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.3859478882464273e-06,
+      "loss": 0.9417,
+      "step": 905
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.287020376528193e-06,
+      "loss": 0.9289,
+      "step": 910
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1899220303518465e-06,
+      "loss": 0.9407,
+      "step": 915
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.0946758769983666e-06,
+      "loss": 0.9457,
+      "step": 920
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.0013045044934243e-06,
+      "loss": 0.9301,
+      "step": 925
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.9405,
+      "step": 930
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.8202742258196183e-06,
+      "loss": 0.9345,
+      "step": 935
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7326582517423662e-06,
+      "loss": 0.9381,
+      "step": 940
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6470029125153463e-06,
+      "loss": 0.9382,
+      "step": 945
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5633285216623384e-06,
+      "loss": 0.9548,
+      "step": 950
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4816549229168864e-06,
+      "loss": 0.9384,
+      "step": 955
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4020014855162755e-06,
+      "loss": 0.9395,
+      "step": 960
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.32438709960804e-06,
+      "loss": 0.9368,
+      "step": 965
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2488301717700735e-06,
+      "loss": 0.9434,
+      "step": 970
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1753486206454433e-06,
+      "loss": 0.9372,
+      "step": 975
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1039598726929046e-06,
+      "loss": 0.9348,
+      "step": 980
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.0346808580541411e-06,
+      "loss": 0.9426,
+      "step": 985
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.675280065387117e-07,
+      "loss": 0.9423,
+      "step": 990
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.02517243727653e-07,
+      "loss": 0.9335,
+      "step": 995
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.39663987196665e-07,
+      "loss": 0.9263,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.78983142859755e-07,
+      "loss": 0.9433,
+      "step": 1005
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.204891014342552e-07,
+      "loss": 0.9473,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.641957350279838e-07,
+      "loss": 0.9459,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.101163938494359e-07,
+      "loss": 0.9526,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.582639030417114e-07,
+      "loss": 0.9232,
+      "step": 1025
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.086505596409885e-07,
+      "loss": 0.9597,
+      "step": 1030
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.6128812966021894e-07,
+      "loss": 0.9503,
+      "step": 1035
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.161878452987778e-07,
+      "loss": 0.9484,
+      "step": 1040
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.733604022786963e-07,
+      "loss": 0.9475,
+      "step": 1045
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.328159573081258e-07,
+      "loss": 0.9354,
+      "step": 1050
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9456412567263394e-07,
+      "loss": 0.9559,
+      "step": 1055
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.5861397895489914e-07,
+      "loss": 0.9425,
+      "step": 1060
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.2497404288334245e-07,
+      "loss": 0.9456,
+      "step": 1065
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9365229531022267e-07,
+      "loss": 0.9462,
+      "step": 1070
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.646561643196465e-07,
+      "loss": 0.9515,
+      "step": 1075
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3799252646597428e-07,
+      "loss": 0.9428,
+      "step": 1080
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.136677051430135e-07,
+      "loss": 0.9593,
+      "step": 1085
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.168746908439718e-08,
+      "loss": 0.9402,
+      "step": 1090
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.205703099551042e-08,
+      "loss": 0.9397,
+      "step": 1095
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.9444,
+      "step": 1100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.986361212205969e-08,
+      "loss": 0.9399,
+      "step": 1105
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.7308266142119788e-08,
+      "loss": 0.933,
+      "step": 1110
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.7117985930525938e-08,
+      "loss": 0.9344,
+      "step": 1115
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.29518815506847e-09,
+      "loss": 0.9505,
+      "step": 1120
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.8417280251257235e-09,
+      "loss": 0.9476,
+      "step": 1125
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.588988516937789e-10,
+      "loss": 0.9313,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9658820033073425,
+      "eval_runtime": 299.772,
+      "eval_samples_per_second": 51.586,
+      "eval_steps_per_second": 0.807,
+      "step": 1134
+    },
+    {
+      "epoch": 1.0,
+      "step": 1134,
+      "total_flos": 1.2682771336104247e+19,
+      "train_loss": 1.0355008869995306,
+      "train_runtime": 11406.2159,
+      "train_samples_per_second": 12.721,
+      "train_steps_per_second": 0.099
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1134,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1.2682771336104247e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}