Model save

README.md

@@ -1,6 +1,6 @@
 ---
-license: llama3
-base_model: meta-llama/Meta-Llama-3-8B
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
 - generated_from_trainer
 model-index:
@@ -13,19 +13,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-full
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1891
-- Rewards/chosen: 0.2333
-- Rewards/rejected: -3.7392
+- Loss: 0.5274
+- Rewards/chosen: -0.0838
+- Rewards/rejected: -1.1574
 - Rewards/accuracies: 0.7579
-- Rewards/margins: 3.9725
-- Logps/rejected: -349.7088
-- Logps/chosen: -352.8180
-- Logits/rejected: -0.9260
-- Logits/chosen: -0.9366
-- Use Label: 3014.7302
-- Pred Label: 5005.2700
+- Rewards/margins: 1.0735
+- Logps/rejected: -273.2137
+- Logps/chosen: -289.3620
+- Logits/rejected: -2.7815
+- Logits/chosen: -2.7866
+- Use Label: 0.0
+- Pred Label: 0.0
 
 ## Model description
 
@@ -45,13 +45,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-07
-- train_batch_size: 2
+- train_batch_size: 8
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -62,7 +61,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Use Label | Pred Label |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:---------:|:----------:|
-| 0.1714        | 1.0   | 1910 | 0.1891          | 0.2333         | -3.7392          | 0.7579             | 3.9725          | -349.7088      | -352.8180    | -0.9260         | -0.9366       | 2959.7302 | 4808.2700  |
+| 0.6368        | 0.1   | 100  | 0.6040          | 0.1800         | -0.4000          | 0.6746             | 0.5800          | -265.6400      | -286.7236    | -2.8083         | -2.8249       | 0.0       | 0.0        |
+| 0.558         | 0.21  | 200  | 0.5652          | 0.1323         | -0.7862          | 0.7421             | 0.9186          | -269.5020      | -287.2001    | -2.7981         | -2.8081       | 0.0       | 0.0        |
+| 0.553         | 0.31  | 300  | 0.5432          | -0.0674        | -1.0423          | 0.7341             | 0.9749          | -272.0630      | -289.1978    | -2.7421         | -2.7517       | 0.0       | 0.0        |
+| 0.5019        | 0.42  | 400  | 0.5371          | 0.1229         | -0.9260          | 0.7540             | 1.0490          | -270.9003      | -287.2944    | -2.7871         | -2.7961       | 0.0       | 0.0        |
+| 0.5303        | 0.52  | 500  | 0.5362          | 0.0755         | -0.9534          | 0.7381             | 1.0290          | -271.1743      | -287.7682    | -2.7415         | -2.7495       | 0.0       | 0.0        |
+| 0.5791        | 0.63  | 600  | 0.5281          | 0.0277         | -1.0275          | 0.7460             | 1.0552          | -271.9149      | -288.2469    | -2.7518         | -2.7595       | 0.0       | 0.0        |
+| 0.5238        | 0.73  | 700  | 0.5295          | 0.0341         | -1.0667          | 0.7540             | 1.1008          | -272.3072      | -288.1828    | -2.7262         | -2.7338       | 0.0       | 0.0        |
+| 0.515         | 0.84  | 800  | 0.5258          | -0.0054        | -1.1189          | 0.7540             | 1.1135          | -272.8286      | -288.5772    | -2.7479         | -2.7544       | 0.0       | 0.0        |
+| 0.5166        | 0.94  | 900  | 0.5273          | -0.0792        | -1.1432          | 0.7619             | 1.0640          | -273.0717      | -289.3157    | -2.7775         | -2.7829       | 0.0       | 0.0        |
 
 
 ### Framework versions

all_results.json

@@ -1,23 +1,23 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -0.9365912079811096,
-    "eval_logits/rejected": -0.926014244556427,
-    "eval_logps/chosen": -352.8179626464844,
-    "eval_logps/rejected": -349.7088317871094,
-    "eval_loss": 0.18906600773334503,
-    "eval_pred_label": 5005.27001953125,
+    "eval_logits/chosen": -2.7866196632385254,
+    "eval_logits/rejected": -2.781510353088379,
+    "eval_logps/chosen": -289.3619689941406,
+    "eval_logps/rejected": -273.2136535644531,
+    "eval_loss": 0.5273504853248596,
+    "eval_pred_label": 0.0,
     "eval_rewards/accuracies": 0.7579365372657776,
-    "eval_rewards/chosen": 0.2332553267478943,
-    "eval_rewards/margins": 3.972490072250366,
-    "eval_rewards/rejected": -3.7392351627349854,
-    "eval_runtime": 277.9429,
+    "eval_rewards/chosen": -0.08383701741695404,
+    "eval_rewards/margins": 1.0735403299331665,
+    "eval_rewards/rejected": -1.1573774814605713,
+    "eval_runtime": 151.8269,
     "eval_samples": 2000,
-    "eval_samples_per_second": 7.196,
-    "eval_steps_per_second": 0.227,
-    "eval_use_label": 3014.730224609375,
-    "train_loss": 0.2926436502271922,
-    "train_runtime": 13370.5554,
+    "eval_samples_per_second": 13.173,
+    "eval_steps_per_second": 0.415,
+    "eval_use_label": 0.0,
+    "train_loss": 0.5461576643349236,
+    "train_runtime": 10580.1696,
     "train_samples": 61135,
-    "train_samples_per_second": 4.572,
-    "train_steps_per_second": 0.143
+    "train_samples_per_second": 5.778,
+    "train_steps_per_second": 0.09
 }

eval_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -0.9365912079811096,
-    "eval_logits/rejected": -0.926014244556427,
-    "eval_logps/chosen": -352.8179626464844,
-    "eval_logps/rejected": -349.7088317871094,
-    "eval_loss": 0.18906600773334503,
-    "eval_pred_label": 5005.27001953125,
+    "eval_logits/chosen": -2.7866196632385254,
+    "eval_logits/rejected": -2.781510353088379,
+    "eval_logps/chosen": -289.3619689941406,
+    "eval_logps/rejected": -273.2136535644531,
+    "eval_loss": 0.5273504853248596,
+    "eval_pred_label": 0.0,
     "eval_rewards/accuracies": 0.7579365372657776,
-    "eval_rewards/chosen": 0.2332553267478943,
-    "eval_rewards/margins": 3.972490072250366,
-    "eval_rewards/rejected": -3.7392351627349854,
-    "eval_runtime": 277.9429,
+    "eval_rewards/chosen": -0.08383701741695404,
+    "eval_rewards/margins": 1.0735403299331665,
+    "eval_rewards/rejected": -1.1573774814605713,
+    "eval_runtime": 151.8269,
     "eval_samples": 2000,
-    "eval_samples_per_second": 7.196,
-    "eval_steps_per_second": 0.227,
-    "eval_use_label": 3014.730224609375
+    "eval_samples_per_second": 13.173,
+    "eval_steps_per_second": 0.415,
+    "eval_use_label": 0.0
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.35.0"
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94098b0c217c3dc970af6ee830f7f43e9989c63c48a350c38759555b8a4bb9b5
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e5e12326ff29c415e670fd5094d3b75dc9fff933404b0f3c12154425f059b7
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9936c3bd0e2f2f63f1001a9c70e4e7768f8e7307aecaa3aa65335f3c2c97a7f5
+size 4540516344

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 16060522496
+    "total_size": 14483464192
   },
   "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
+    "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/Aug06_12-34-04_n122-220-008/events.out.tfevents.1722929614.n122-220-008.93384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a467fbfff6ca52d54d6ff8b40ed9cea736740d456c69b89fde628a11ae23fa
+size 935

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.2926436502271922,
-    "train_runtime": 13370.5554,
+    "train_loss": 0.5461576643349236,
+    "train_runtime": 10580.1696,
     "train_samples": 61135,
-    "train_samples_per_second": 4.572,
-    "train_steps_per_second": 0.143
+    "train_samples_per_second": 5.778,
+    "train_steps_per_second": 0.09
 }