End of training

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+base_model: facebook/opt-1.3b
+tags:
+- generated_from_trainer
+model-index:
+- name: opt_2.7b_wiki_ce
+  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_2.7b_wiki_ce
+
+This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4190
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.6033        | 0.4354 | 500  | 2.4562          |
+| 2.5267        | 0.8707 | 1000 | 2.4247          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-1.3b",
+  "_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": 8192,
+  "hidden_size": 2048,
+  "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": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2048
+}

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 sha256:96aa3ddbc231ea6a9f5fae145e0c9ed3b26faa7a71da753736e566aff9b11473
+size 4994509120

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641a88bfe3de3f8c1b296218ee478c7ae955b947438e2829bd7e13a6dfdec747
+size 268568856

model.safetensors.index.json

@@ -0,0 +1,395 @@
+{
+  "metadata": {
+    "total_size": 5263032320
+  },
+  "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-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-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.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"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2ae51663e185ee9eb5dbf974c787c4cbdce2c9b2b392cf79e989d36d1b4a96
+size 4920