Model save

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+base_model: EleutherAI/gpt-neo-2.7B
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt-neo-2.7B_LAMA_TREx_finetuning_eda
+  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. -->
+
+# gpt-neo-2.7B_LAMA_TREx_finetuning_eda
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 0
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 1.13.1
+- Datasets 2.14.5
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-2.7B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      16
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 20,
+  "num_layers": 32,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 50258,
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c54d6c585a741be029b38e018fa536faec6b499de4bbc146013ce4bc709948
+size 9976023949

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f0853a80bd6a105c20ca0920310c5e8a5c9e54c2baf1ce05f48b6bbea19ec9
+size 1144001205

pytorch_model.bin.index.json

@@ -0,0 +1,428 @@
+{
+  "metadata": {
+    "total_size": 11119882240
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.attention.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.attention.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.attention.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.attention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.attention.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.attention.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.attention.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.attention.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.attention.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.attention.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179578041c616948ccfb1aeb5f5d84b3f0ea655f3980b79fc4a36650ddee1883
+size 5691