Upload folder using huggingface_hub

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "pad_token_id": 50256,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fe9e82b1a3f3af61549377a4a3f7262cf980859320d81288a56fa4d9bf8be8
+size 1419322880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e69022da89a3c0e947578ca4f554541aa37bd7a24337f2cb1ebe7b9c5547c2
+size 2838833803

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e4d08610730ac21a86fb7de99b50287d5cf193d4d421a30288aadb9831a611
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfeea8e4447d7603087ddf9c6b046876057b7a98bce2b7f669464c51f2acc90
+size 1465

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.5440185070037842,
+      "learning_rate": 4.975e-05,
+      "loss": 1.3873,
+      "step": 200
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.1913411617279053,
+      "learning_rate": 4.3580645161290324e-05,
+      "loss": 0.0893,
+      "step": 400
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.7728761434555054,
+      "learning_rate": 3.7129032258064516e-05,
+      "loss": 0.0617,
+      "step": 600
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.8336076736450195,
+      "learning_rate": 3.067741935483871e-05,
+      "loss": 0.0527,
+      "step": 800
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.7497674822807312,
+      "learning_rate": 2.4225806451612903e-05,
+      "loss": 0.0414,
+      "step": 1000
+    },
+    {
+      "epoch": 6.857142857142857,
+      "grad_norm": 0.8337773084640503,
+      "learning_rate": 1.7774193548387098e-05,
+      "loss": 0.035,
+      "step": 1200
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5487708449363708,
+      "learning_rate": 1.132258064516129e-05,
+      "loss": 0.031,
+      "step": 1400
+    },
+    {
+      "epoch": 9.142857142857142,
+      "grad_norm": 0.49486181139945984,
+      "learning_rate": 4.870967741935484e-06,
+      "loss": 0.0264,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 1750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6500904861696000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f4fc6172790fcb1c4a21db97d5f309ed8a5593ee4935375dcc90d880289256
+size 5777