Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: other
+base_model: 01-ai/Yi-34B-200K
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-34b-sft-full_epoch1
+  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-34b-sft-full_epoch1
+
+This model is a fine-tuned version of [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9533
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9435        | 1.0   | 1026 | 0.9533          |
+
+
+### 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": 0.9532989859580994,
+    "eval_runtime": 1248.9995,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 11.64,
+    "eval_steps_per_second": 0.183,
+    "train_loss": 0.9775699134226199,
+    "train_runtime": 79518.8807,
+    "train_samples": 207865,
+    "train_samples_per_second": 1.652,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9532989859580994,
+    "eval_runtime": 1248.9995,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 11.64,
+    "eval_steps_per_second": 0.183
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0589c0b1e61d3985d0faaa54f6cdf54b58940eb5a46c14a050a506008da1c255
+size 4793130760

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fbaf612d5e3dcf45ae495a34809e65a47a8878db2dc634b6dd24dca7a3a779
+size 4756459720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e553676e05ff187256a5a465e56a434f471b5bb5c52ccbd27d23d0cb09708fcc
+size 4991370136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8ee3000caf0c8382294788c462ffb891ca8204b3f3c890b0d67b54770ae9ea
+size 4756459760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de96a9a26e013a0198a83b2ddcbc599473b0a807b3e16d8dca62a7ad697ee7a
+size 4756459760

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1609a6fce4f2589f2ad267b653e7e7f3c9db322813cba94046fccfce2350e916
+size 4991370160

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dbbbfe41ba61cb50d6257c3567d4b916d5655f8dedaf1174844b63f2a8f128
+size 4756459760

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b472b912669a5425d0ab73f910963692865d9da9b0a86bb3174a8b74a92d170a
+size 4756459760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ba66961bc4a9e2a3068b03ae8f83431af9c644f30162b6cd605aad46859b09
+size 4991370160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc925fd3258bb992ccccbfdb8af3dca22aa6b77fd8842bf5bcb53fe635b6eb7
+size 4756459760

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd92e353b14a082bf35cb490e3959ddb92f1ca0ca85edb8567b030c25f01f652
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339a4a9c184dac0010a33ff29def318aa01e070d8f0c3cdaf9865bcb8f753e40
+size 4991370160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d1ddc285ca4daa00cb60c90b1792d63db242e4a8efef01e1fa4b3c560d8837
+size 4756459760

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31ef69e8fe425fc93ebd6e14ddd988a34b204478fb594224c5dff156bc4dbb1
+size 4756459760

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad18b3375459def589a78cb2a0372066ed83c6ea1839e2d1424328e5e44cad7
+size 1211148856

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706596853.dsw-250-99c5474d8-m866l.2566213.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df263a302839384ba9b9aa6300cd4cfd845ad921cf13755fef44bf01c576cf8
-size 36010
+oid sha256:468ee9a01a4b1af94010c67a1fbd678c2c6b45cf9a0c7ca92f21464d2fedf80e
+size 37420

runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706677621.dsw-250-99c5474d8-m866l.2566213.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d002847dc79960d2b53913ac3b8ea3f2829327465358b462de346082763b7d
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9775699134226199,
+    "train_runtime": 79518.8807,
+    "train_samples": 207865,
+    "train_samples_per_second": 1.652,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,1274 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997563946406821,
+  "eval_steps": 500,
+  "global_step": 1026,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.941747572815534e-07,
+      "loss": 1.527,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.70873786407767e-07,
+      "loss": 1.5166,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 1.3897,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 1.1756,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.883495145631068e-06,
+      "loss": 1.1025,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.854368932038836e-06,
+      "loss": 1.0531,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.825242718446602e-06,
+      "loss": 1.0663,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.79611650485437e-06,
+      "loss": 1.0582,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.766990291262136e-06,
+      "loss": 1.0537,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.737864077669904e-06,
+      "loss": 1.042,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.708737864077671e-06,
+      "loss": 1.0136,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0679611650485437e-05,
+      "loss": 1.0165,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1650485436893204e-05,
+      "loss": 1.0045,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2621359223300974e-05,
+      "loss": 1.0122,
+      "step": 65
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.359223300970874e-05,
+      "loss": 1.0107,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4563106796116507e-05,
+      "loss": 1.01,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.5533980582524273e-05,
+      "loss": 1.0034,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.650485436893204e-05,
+      "loss": 0.9995,
+      "step": 85
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7475728155339808e-05,
+      "loss": 0.994,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8446601941747575e-05,
+      "loss": 1.015,
+      "step": 95
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9417475728155343e-05,
+      "loss": 0.9897,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999976830073192e-05,
+      "loss": 1.0033,
+      "step": 105
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.99971618072711e-05,
+      "loss": 1.0027,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9991659953668803e-05,
+      "loss": 0.9943,
+      "step": 115
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.998326433336204e-05,
+      "loss": 1.0269,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.997197737787537e-05,
+      "loss": 0.9755,
+      "step": 125
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9957802356116665e-05,
+      "loss": 1.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.994074337343041e-05,
+      "loss": 0.9923,
+      "step": 135
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9920805370408695e-05,
+      "loss": 1.0044,
+      "step": 140
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9897994121460322e-05,
+      "loss": 0.9956,
+      "step": 145
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9872316233138463e-05,
+      "loss": 1.0046,
+      "step": 150
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9843779142227258e-05,
+      "loss": 0.9857,
+      "step": 155
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.981239111358799e-05,
+      "loss": 1.0008,
+      "step": 160
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9778161237765438e-05,
+      "loss": 1.0068,
+      "step": 165
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9741099428355075e-05,
+      "loss": 1.0073,
+      "step": 170
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9701216419131934e-05,
+      "loss": 0.9601,
+      "step": 175
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9658523760941882e-05,
+      "loss": 1.0001,
+      "step": 180
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9613033818356322e-05,
+      "loss": 1.0086,
+      "step": 185
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.956475976609114e-05,
+      "loss": 1.0117,
+      "step": 190
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.951371558519111e-05,
+      "loss": 0.9955,
+      "step": 195
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9459916058980707e-05,
+      "loss": 1.0014,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9403376768782592e-05,
+      "loss": 0.9803,
+      "step": 205
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9344114089404983e-05,
+      "loss": 0.9847,
+      "step": 210
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9282145184399197e-05,
+      "loss": 0.9946,
+      "step": 215
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9217488001088784e-05,
+      "loss": 0.9886,
+      "step": 220
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9150161265371663e-05,
+      "loss": 0.981,
+      "step": 225
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.908018447629674e-05,
+      "loss": 0.9863,
+      "step": 230
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9007577900416648e-05,
+      "loss": 0.9907,
+      "step": 235
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8932362565918167e-05,
+      "loss": 0.9721,
+      "step": 240
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 1.0003,
+      "step": 245
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.877419350522429e-05,
+      "loss": 0.9749,
+      "step": 250
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.869128558766965e-05,
+      "loss": 0.9967,
+      "step": 255
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8605860515511158e-05,
+      "loss": 0.9864,
+      "step": 260
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8517943029405577e-05,
+      "loss": 1.0096,
+      "step": 265
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8427558591858164e-05,
+      "loss": 0.9643,
+      "step": 270
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.833473337984823e-05,
+      "loss": 1.001,
+      "step": 275
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.823949427724785e-05,
+      "loss": 0.996,
+      "step": 280
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8141868867035745e-05,
+      "loss": 0.9885,
+      "step": 285
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8041885423308808e-05,
+      "loss": 0.9818,
+      "step": 290
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7939572903093383e-05,
+      "loss": 0.9936,
+      "step": 295
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7834960937958775e-05,
+      "loss": 0.9733,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7728079825435426e-05,
+      "loss": 1.0035,
+      "step": 305
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.761896052024019e-05,
+      "loss": 1.0073,
+      "step": 310
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7507634625311283e-05,
+      "loss": 0.9821,
+      "step": 315
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7394134382655496e-05,
+      "loss": 0.99,
+      "step": 320
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7278492664010326e-05,
+      "loss": 0.9766,
+      "step": 325
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7160742961323714e-05,
+      "loss": 0.9783,
+      "step": 330
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.7040919377054182e-05,
+      "loss": 0.9922,
+      "step": 335
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6919056614294133e-05,
+      "loss": 0.9767,
+      "step": 340
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.6795189966719182e-05,
+      "loss": 0.9937,
+      "step": 345
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.666935530836651e-05,
+      "loss": 0.9702,
+      "step": 350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.654158908324504e-05,
+      "loss": 0.9906,
+      "step": 355
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6411928294780626e-05,
+      "loss": 0.9662,
+      "step": 360
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6280410495099165e-05,
+      "loss": 0.9802,
+      "step": 365
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6147073774150834e-05,
+      "loss": 0.9897,
+      "step": 370
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.601195674867853e-05,
+      "loss": 0.9696,
+      "step": 375
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.5875098551033765e-05,
+      "loss": 0.9859,
+      "step": 380
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5736538817843228e-05,
+      "loss": 0.9751,
+      "step": 385
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.559631767852929e-05,
+      "loss": 0.9815,
+      "step": 390
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.54544757436878e-05,
+      "loss": 0.9913,
+      "step": 395
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5311054093326508e-05,
+      "loss": 0.9652,
+      "step": 400
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5166094264967553e-05,
+      "loss": 0.9831,
+      "step": 405
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.5019638241617429e-05,
+      "loss": 0.9598,
+      "step": 410
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.4871728439607967e-05,
+      "loss": 0.9667,
+      "step": 415
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.472240769631176e-05,
+      "loss": 0.9764,
+      "step": 420
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4571719257735702e-05,
+      "loss": 0.9685,
+      "step": 425
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4419706765996153e-05,
+      "loss": 0.9872,
+      "step": 430
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4266414246679379e-05,
+      "loss": 0.9727,
+      "step": 435
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.4111886096090953e-05,
+      "loss": 0.9532,
+      "step": 440
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.3956167068397756e-05,
+      "loss": 0.9679,
+      "step": 445
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.3799302262666388e-05,
+      "loss": 0.9779,
+      "step": 450
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.364133710980162e-05,
+      "loss": 0.9906,
+      "step": 455
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3482317359388806e-05,
+      "loss": 0.9756,
+      "step": 460
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3322289066443947e-05,
+      "loss": 0.9799,
+      "step": 465
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.316129857807534e-05,
+      "loss": 0.9677,
+      "step": 470
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2999392520060594e-05,
+      "loss": 0.9738,
+      "step": 475
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2836617783342968e-05,
+      "loss": 0.9939,
+      "step": 480
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2673021510450893e-05,
+      "loss": 0.9618,
+      "step": 485
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.250865108184464e-05,
+      "loss": 0.9652,
+      "step": 490
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2343554102194073e-05,
+      "loss": 0.9915,
+      "step": 495
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2177778386591475e-05,
+      "loss": 0.9782,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2011371946703416e-05,
+      "loss": 0.9918,
+      "step": 505
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1844382976865714e-05,
+      "loss": 0.9813,
+      "step": 510
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1676859840125468e-05,
+      "loss": 0.9877,
+      "step": 515
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.1508851054234236e-05,
+      "loss": 0.9828,
+      "step": 520
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.1340405277596427e-05,
+      "loss": 0.9661,
+      "step": 525
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1171571295176915e-05,
+      "loss": 0.9682,
+      "step": 530
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1002398004372048e-05,
+      "loss": 0.9666,
+      "step": 535
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0832934400848063e-05,
+      "loss": 0.9526,
+      "step": 540
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.066322956435104e-05,
+      "loss": 0.9546,
+      "step": 545
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0493332644492534e-05,
+      "loss": 0.9561,
+      "step": 550
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0323292846514927e-05,
+      "loss": 0.9602,
+      "step": 555
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.015315941704071e-05,
+      "loss": 0.9579,
+      "step": 560
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.982981629809776e-06,
+      "loss": 0.959,
+      "step": 565
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.812808771408804e-06,
+      "loss": 0.9512,
+      "step": 570
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.64269012699702e-06,
+      "loss": 0.9554,
+      "step": 575
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.472674966032276e-06,
+      "loss": 0.9724,
+      "step": 580
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.302812528001741e-06,
+      "loss": 0.9691,
+      "step": 585
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.133152008161235e-06,
+      "loss": 0.9676,
+      "step": 590
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.963742543287397e-06,
+      "loss": 0.9603,
+      "step": 595
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.9526,
+      "step": 600
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.625872947785968e-06,
+      "loss": 0.9561,
+      "step": 605
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.457510670346976e-06,
+      "loss": 0.9543,
+      "step": 610
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.2895951259118e-06,
+      "loss": 0.9663,
+      "step": 615
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.122174945880409e-06,
+      "loss": 0.9763,
+      "step": 620
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.955298618186227e-06,
+      "loss": 0.9621,
+      "step": 625
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.78901447325314e-06,
+      "loss": 0.9487,
+      "step": 630
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.623370669998115e-06,
+      "loss": 0.9383,
+      "step": 635
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.458415181883506e-06,
+      "loss": 0.9694,
+      "step": 640
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.294195783023072e-06,
+      "loss": 0.9491,
+      "step": 645
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.130760034345708e-06,
+      "loss": 0.963,
+      "step": 650
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.968155269820951e-06,
+      "loss": 0.9512,
+      "step": 655
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.806428582750191e-06,
+      "loss": 0.9609,
+      "step": 660
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.645626812127588e-06,
+      "loss": 0.9574,
+      "step": 665
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.485796529074662e-06,
+      "loss": 0.9631,
+      "step": 670
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.326984023352435e-06,
+      "loss": 0.9627,
+      "step": 675
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.169235289955073e-06,
+      "loss": 0.9568,
+      "step": 680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.012596015788903e-06,
+      "loss": 0.9528,
+      "step": 685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.8571115664406655e-06,
+      "loss": 0.9639,
+      "step": 690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.702826973038776e-06,
+      "loss": 0.9609,
+      "step": 695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.549786919211532e-06,
+      "loss": 0.9379,
+      "step": 700
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.3980357281459e-06,
+      "loss": 0.9382,
+      "step": 705
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.247617349750717e-06,
+      "loss": 0.9388,
+      "step": 710
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.0985753479279824e-06,
+      "loss": 0.9692,
+      "step": 715
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.950952887955992e-06,
+      "loss": 0.9653,
+      "step": 720
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.80479272398786e-06,
+      "loss": 0.9613,
+      "step": 725
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.660137186669131e-06,
+      "loss": 0.943,
+      "step": 730
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.5170281708780865e-06,
+      "loss": 0.9451,
+      "step": 735
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.375507123592194e-06,
+      "loss": 0.951,
+      "step": 740
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.235615031884326e-06,
+      "loss": 0.9433,
+      "step": 745
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.097392411052149e-06,
+      "loss": 0.9385,
+      "step": 750
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.9608792928841596e-06,
+      "loss": 0.9488,
+      "step": 755
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.826115214065739e-06,
+      "loss": 0.9413,
+      "step": 760
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.693139204728623e-06,
+      "loss": 0.9535,
+      "step": 765
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.561989777147059e-06,
+      "loss": 0.9384,
+      "step": 770
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.4327049145839496e-06,
+      "loss": 0.9451,
+      "step": 775
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.3053220602902057e-06,
+      "loss": 0.9663,
+      "step": 780
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.1798781066605076e-06,
+      "loss": 0.9551,
+      "step": 785
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.056409384548575e-06,
+      "loss": 0.958,
+      "step": 790
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.934951652745123e-06,
+      "loss": 0.949,
+      "step": 795
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.8155400876214365e-06,
+      "loss": 0.9504,
+      "step": 800
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.698209272941659e-06,
+      "loss": 0.9387,
+      "step": 805
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.5829931898467143e-06,
+      "loss": 0.9194,
+      "step": 810
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.469925207012741e-06,
+      "loss": 0.9436,
+      "step": 815
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.3590380709869175e-06,
+      "loss": 0.9401,
+      "step": 820
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.2503638967034668e-06,
+      "loss": 0.9462,
+      "step": 825
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1439341581825855e-06,
+      "loss": 0.9553,
+      "step": 830
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.039779679414996e-06,
+      "loss": 0.9485,
+      "step": 835
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9379306254347487e-06,
+      "loss": 0.9417,
+      "step": 840
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.838416493582893e-06,
+      "loss": 0.933,
+      "step": 845
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7412661049645097e-06,
+      "loss": 0.9501,
+      "step": 850
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6465075961015697e-06,
+      "loss": 0.9522,
+      "step": 855
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.554168410784117e-06,
+      "loss": 0.9434,
+      "step": 860
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.4642752921220272e-06,
+      "loss": 0.938,
+      "step": 865
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3768542747997215e-06,
+      "loss": 0.943,
+      "step": 870
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2919306775360495e-06,
+      "loss": 0.9551,
+      "step": 875
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.209529095751527e-06,
+      "loss": 0.9459,
+      "step": 880
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1296733944450445e-06,
+      "loss": 0.9526,
+      "step": 885
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.0523867012821444e-06,
+      "loss": 0.963,
+      "step": 890
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.776913998968196e-07,
+      "loss": 0.9422,
+      "step": 895
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.056091234088038e-07,
+      "loss": 0.9408,
+      "step": 900
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.361607481582312e-07,
+      "loss": 0.9512,
+      "step": 905
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.693663876594648e-07,
+      "loss": 0.9401,
+      "step": 910
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.052453867758525e-07,
+      "loss": 0.9523,
+      "step": 915
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.438163161171096e-07,
+      "loss": 0.9332,
+      "step": 920
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.850969666609363e-07,
+      "loss": 0.9443,
+      "step": 925
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.291043446004074e-07,
+      "loss": 0.9423,
+      "step": 930
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.7585466641868696e-07,
+      "loss": 0.9509,
+      "step": 935
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.25363354192434e-07,
+      "loss": 0.9512,
+      "step": 940
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.776450311252866e-07,
+      "loss": 0.953,
+      "step": 945
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.3271351731271717e-07,
+      "loss": 0.9282,
+      "step": 950
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.9639,
+      "step": 955
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.512621585108155e-07,
+      "loss": 0.9543,
+      "step": 960
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1476590331849566e-07,
+      "loss": 0.956,
+      "step": 965
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.811036301427449e-07,
+      "loss": 0.9625,
+      "step": 970
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.502850881909801e-07,
+      "loss": 0.9435,
+      "step": 975
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2231920307425927e-07,
+      "loss": 0.9538,
+      "step": 980
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.721407422226492e-08,
+      "loss": 0.9398,
+      "step": 985
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.497697253756265e-08,
+      "loss": 0.939,
+      "step": 990
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.5614338289812216e-08,
+      "loss": 0.9302,
+      "step": 995
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.913177925055189e-08,
+      "loss": 0.9574,
+      "step": 1000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.5534069069081957e-08,
+      "loss": 0.9528,
+      "step": 1005
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.482514588993067e-08,
+      "loss": 0.9216,
+      "step": 1010
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.0081112122966086e-09,
+      "loss": 0.9417,
+      "step": 1015
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.0852289917971947e-09,
+      "loss": 0.9419,
+      "step": 1020
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.792498478651709e-11,
+      "loss": 0.9435,
+      "step": 1025
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9532989859580994,
+      "eval_runtime": 1250.6177,
+      "eval_samples_per_second": 11.625,
+      "eval_steps_per_second": 0.182,
+      "step": 1026
+    },
+    {
+      "epoch": 1.0,
+      "step": 1026,
+      "total_flos": 1399316853817344.0,
+      "train_loss": 0.9775699134226199,
+      "train_runtime": 79518.8807,
+      "train_samples_per_second": 1.652,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1026,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1399316853817344.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}