Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: other
+base_model: facebook/opt-6.7b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: opt-6.7b-sft
+  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. -->
+
+# opt-6.7b-sft
+
+This model is a fine-tuned version of [facebook/opt-6.7b](https://huggingface.co/facebook/opt-6.7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4492
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8817        | 0.08  | 20   | 1.4492          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.08,
+    "eval_loss": 1.44921875,
+    "eval_runtime": 79.3699,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 179.904,
+    "eval_steps_per_second": 0.353,
+    "train_loss": 1.8745559692382812,
+    "train_runtime": 266.5177,
+    "train_samples": 207865,
+    "train_samples_per_second": 38.421,
+    "train_steps_per_second": 0.075
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-6.7b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "hidden_size": 4096,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 4096
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.08,
+    "eval_loss": 1.44921875,
+    "eval_runtime": 79.3699,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 179.904,
+    "eval_steps_per_second": 0.353
+}

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": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a238c8eb52abdad746179f691016350d45345a2bd1bf5c1a065ab1f2a0c603
+size 4993283928

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2ae75313cd9c65c7b2a39d4c0919924c95434c0f304d74177ea54327f9e9db
+size 4967389600

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf36073a57afed545b43c124b7287ba64a9b93035a5d3baba829fece44d33404
+size 3356335328

model.safetensors.index.json

@@ -0,0 +1,523 @@
+{
+  "metadata": {
+    "total_size": 13316947968
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors"
+  }
+}

runs/Jan03_18-51-47_aga39/events.out.tfevents.1704329759.aga39.143926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c79e05b0fd4f2c45c81ba582d837a170c5c80abcccd8a7d4798946b04ff756c
+size 5250

runs/Jan03_18-51-47_aga39/events.out.tfevents.1704330105.aga39.143926.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eebbab0239ec27b5b6578a74e7520aee4d320c51c4f0d4abd73b0fc28ffa279
+size 354

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.08,
+    "train_loss": 1.8745559692382812,
+    "train_runtime": 266.5177,
+    "train_samples": 207865,
+    "train_samples_per_second": 38.421,
+    "train_steps_per_second": 0.075
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07905138339920949,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 1.8817,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.44921875,
+      "eval_runtime": 79.4742,
+      "eval_samples_per_second": 179.668,
+      "eval_steps_per_second": 0.352,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "step": 20,
+      "total_flos": 32315333935104.0,
+      "train_loss": 1.8745559692382812,
+      "train_runtime": 266.5177,
+      "train_samples_per_second": 38.421,
+      "train_steps_per_second": 0.075
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 32315333935104.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402b64c314fb1d2ccb1804f480a62b3e5ef5e1207665ac66ee405e3f0121a314
+size 5307