full_finetune_orpo_pythia2_hh_filtered

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: EleutherAI/pythia-2.8b
-library_name: peft
+library_name: transformers
 license: apache-2.0
+base_model: EleutherAI/pythia-2.8b
 tags:
 - trl
 - orpo
@@ -14,7 +14,6 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sert121/huggingface/runs/yy4vdz6d)
 # orpo_pythia2_hh_filtered
 
 This model is a fine-tuned version of [EleutherAI/pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) on the None dataset.
@@ -37,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 8e-06
-- train_batch_size: 3
-- eval_batch_size: 8
+- train_batch_size: 12
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 12
+- total_train_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 150
@@ -53,8 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.42.0
-- Pytorch 2.4.0+cu121
-- Datasets 2.15.0
-- Tokenizers 0.19.1
+- Transformers 4.45.0
+- Pytorch 2.5.0+cu124
+- Datasets 2.19.2
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "EleutherAI/pythia-2.8b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5df3380db5e0cb754e23e705a5701efa95a8595e957210f4e8324fe95dcbc5
+size 4999731368

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5da108c49818b307151e1269f781c7f7c30c5b85e38032d741b576974e1f63
+size 4956643296

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b23aefa020faa44b0aae847fb5fc5b4633bd1ba564c10d0f7617b865d40cf89
+size 1144507000

model.safetensors.index.json

@@ -0,0 +1,395 @@
+{
+  "metadata": {
+    "total_size": 11100835840
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d720ea34ff954e88085c74debbf0df2925f77416f650f4a1e0fc4ab00c527063
-size 5432
+oid sha256:b2659c7a9d41636e2f7ae6f831262e5e02b8ddb546e9d258593209cf10976fac
+size 5560