added model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "output_gpt4/checkpoint-1200",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 50258
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f94dacc1399d14e64e72be571c72b749505df495eb1db8002af9dcd2fcd16b
+size 2847164079

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d6bbfe316e303d3f445676f42e59513b1ed0b88c856aa439e3258cda61cc4b
+size 1524270287

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b759e48a711f137615aa53bfe22d44c369ecf36cb990d31d4d4ea11a373c8dfa
+size 14655

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b660e8d89a0a30735050ac6fbc95ab1a01bd99e0d21d15fa819380a79832f4
+size 623

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 49.20634920634921,
+  "global_step": 3100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.998412698412699e-05,
+      "loss": 0.7311,
+      "step": 1
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.841269841269841e-05,
+      "loss": 0.5136,
+      "step": 100
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.682539682539683e-05,
+      "loss": 0.2476,
+      "step": 200
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 4.523809523809524e-05,
+      "loss": 0.1161,
+      "step": 300
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 0.0731,
+      "step": 400
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 4.2063492063492065e-05,
+      "loss": 0.0539,
+      "step": 500
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.0429,
+      "step": 600
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.0388,
+      "step": 700
+    },
+    {
+      "epoch": 12.7,
+      "learning_rate": 3.730158730158731e-05,
+      "loss": 0.0356,
+      "step": 800
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.0332,
+      "step": 900
+    },
+    {
+      "epoch": 15.87,
+      "learning_rate": 3.412698412698413e-05,
+      "loss": 0.0321,
+      "step": 1000
+    },
+    {
+      "epoch": 17.46,
+      "learning_rate": 3.253968253968254e-05,
+      "loss": 0.03,
+      "step": 1100
+    },
+    {
+      "epoch": 19.05,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.03,
+      "step": 1200
+    },
+    {
+      "epoch": 20.63,
+      "learning_rate": 2.9365079365079366e-05,
+      "loss": 0.028,
+      "step": 1300
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.0282,
+      "step": 1400
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 2.6190476190476192e-05,
+      "loss": 0.0275,
+      "step": 1500
+    },
+    {
+      "epoch": 25.4,
+      "learning_rate": 2.4603174603174602e-05,
+      "loss": 0.0271,
+      "step": 1600
+    },
+    {
+      "epoch": 26.98,
+      "learning_rate": 2.3015873015873015e-05,
+      "loss": 0.027,
+      "step": 1700
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0257,
+      "step": 1800
+    },
+    {
+      "epoch": 30.16,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 0.0262,
+      "step": 1900
+    },
+    {
+      "epoch": 31.75,
+      "learning_rate": 1.8253968253968254e-05,
+      "loss": 0.0257,
+      "step": 2000
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0254,
+      "step": 2100
+    },
+    {
+      "epoch": 34.92,
+      "learning_rate": 1.5079365079365079e-05,
+      "loss": 0.0253,
+      "step": 2200
+    },
+    {
+      "epoch": 36.51,
+      "learning_rate": 1.3492063492063492e-05,
+      "loss": 0.0247,
+      "step": 2300
+    },
+    {
+      "epoch": 38.1,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.0251,
+      "step": 2400
+    },
+    {
+      "epoch": 39.68,
+      "learning_rate": 1.0317460317460318e-05,
+      "loss": 0.0243,
+      "step": 2500
+    },
+    {
+      "epoch": 41.27,
+      "learning_rate": 8.73015873015873e-06,
+      "loss": 0.0246,
+      "step": 2600
+    },
+    {
+      "epoch": 42.86,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0243,
+      "step": 2700
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.024,
+      "step": 2800
+    },
+    {
+      "epoch": 46.03,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 0.0239,
+      "step": 2900
+    },
+    {
+      "epoch": 47.62,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.0234,
+      "step": 3000
+    },
+    {
+      "epoch": 49.21,
+      "learning_rate": 7.936507936507937e-07,
+      "loss": 0.0232,
+      "step": 3100
+    }
+  ],
+  "max_steps": 3150,
+  "num_train_epochs": 50,
+  "total_flos": 5712437972041728.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afa158dfef7c9afca23a97cabe0b8686ea04a980c679798acf3fc3d9ebce82a
+size 3503