Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: facebook/opt-2.7b
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: DPO-Zephyr-7B
+  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. -->
+
+# DPO-Zephyr-7B
+
+This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on the None dataset.
+
+## 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: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- total_eval_batch_size: 2
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.5192557334487234,
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 1.1312,
+    "train_samples": 40000,
+    "train_samples_per_second": 35360.967,
+    "train_steps_per_second": 1105.03
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd418fdddd3a80cfefe85a8306f00c640965e6dff3cc61d47601d265c4706f42
+size 4988545248

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f398442390d7b851d5567b3e136eb1aaccc772060868b996180ddb996b89d1
+size 314709704

model.safetensors.index.json

@@ -0,0 +1,523 @@
+{
+  "metadata": {
+    "total_size": 5303193600
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.5192557334487234,
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 1.1312,
+    "train_samples": 40000,
+    "train_samples_per_second": 35360.967,
+    "train_steps_per_second": 1105.03
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c17a9db0d3be32b2ec1b307d5580f279768a752d1d3bc281d95f097499eff59
+oid sha256:f347fba8e067f03eb28f172459c9032fc16083d48a2439ba08421388d465e55e
 size 6264