Initial upload

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "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,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.53.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a88ff7a22916a98b1df01c37934af1f28f74cf1ff4ef0a4e2f5880a14582f9
+size 1419322880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373dd8c9768e0a53d8c62af5abf481afc8a92bf51dac48ad4b40368c01901cd4
+size 2838821579

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1e0d31acc437fbbd16411d0d11d500c5f4dbbc7561671dab7dbf23eb0f2c43
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7c588510530a706440149a66e8b356657c103fddced9123513cb8878ab587c
+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 +1,241 @@
+{
+  "best_global_step": 12524,
+  "best_metric": 1.614437222480774,
+  "best_model_checkpoint": "./PhaseII-checkpoint/checkpoint-12524",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 12524,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00015970614070110996,
+      "grad_norm": 5.020626068115234,
+      "learning_rate": 0.0,
+      "loss": 2.2838,
+      "step": 1
+    },
+    {
+      "epoch": 0.07985307035055497,
+      "grad_norm": 2.9836959838867188,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 1.9133,
+      "step": 500
+    },
+    {
+      "epoch": 0.15970614070110994,
+      "grad_norm": 2.8403663635253906,
+      "learning_rate": 9.584996673320027e-06,
+      "loss": 1.7518,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23955921105166494,
+      "grad_norm": 3.458155393600464,
+      "learning_rate": 9.169161676646707e-06,
+      "loss": 1.7446,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3194122814022199,
+      "grad_norm": 2.839137315750122,
+      "learning_rate": 8.753326679973387e-06,
+      "loss": 1.724,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3992653517527749,
+      "grad_norm": 3.0357747077941895,
+      "learning_rate": 8.337491683300067e-06,
+      "loss": 1.715,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4791184221033299,
+      "grad_norm": 2.7229244709014893,
+      "learning_rate": 7.921656686626747e-06,
+      "loss": 1.6993,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5589714924538849,
+      "grad_norm": 3.1533303260803223,
+      "learning_rate": 7.5058216899534275e-06,
+      "loss": 1.698,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6388245628044398,
+      "grad_norm": 3.5182504653930664,
+      "learning_rate": 7.089986693280108e-06,
+      "loss": 1.6914,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7186776331549948,
+      "grad_norm": 3.2433836460113525,
+      "learning_rate": 6.674151696606786e-06,
+      "loss": 1.6824,
+      "step": 4500
+    },
+    {
+      "epoch": 0.7985307035055498,
+      "grad_norm": 3.250410556793213,
+      "learning_rate": 6.258316699933466e-06,
+      "loss": 1.6893,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8783837738561048,
+      "grad_norm": 3.3924999237060547,
+      "learning_rate": 5.8424817032601465e-06,
+      "loss": 1.689,
+      "step": 5500
+    },
+    {
+      "epoch": 0.9582368442066598,
+      "grad_norm": 3.0635600090026855,
+      "learning_rate": 5.426646706586827e-06,
+      "loss": 1.6857,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6256579160690308,
+      "eval_runtime": 76.536,
+      "eval_samples_per_second": 10.453,
+      "eval_steps_per_second": 2.613,
+      "step": 6262
+    },
+    {
+      "epoch": 1.0380100614868641,
+      "grad_norm": 2.568723440170288,
+      "learning_rate": 5.010811709913507e-06,
+      "loss": 1.6553,
+      "step": 6500
+    },
+    {
+      "epoch": 1.117863131837419,
+      "grad_norm": 3.2197988033294678,
+      "learning_rate": 4.594976713240187e-06,
+      "loss": 1.6466,
+      "step": 7000
+    },
+    {
+      "epoch": 1.1977162021879741,
+      "grad_norm": 3.12034273147583,
+      "learning_rate": 4.179141716566867e-06,
+      "loss": 1.6405,
+      "step": 7500
+    },
+    {
+      "epoch": 1.277569272538529,
+      "grad_norm": 3.1645143032073975,
+      "learning_rate": 3.7633067198935464e-06,
+      "loss": 1.6411,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3574223428890841,
+      "grad_norm": 3.349564552307129,
+      "learning_rate": 3.3474717232202266e-06,
+      "loss": 1.6245,
+      "step": 8500
+    },
+    {
+      "epoch": 1.437275413239639,
+      "grad_norm": 3.0371181964874268,
+      "learning_rate": 2.9316367265469064e-06,
+      "loss": 1.6196,
+      "step": 9000
+    },
+    {
+      "epoch": 1.5171284835901941,
+      "grad_norm": 3.2543323040008545,
+      "learning_rate": 2.5158017298735865e-06,
+      "loss": 1.6328,
+      "step": 9500
+    },
+    {
+      "epoch": 1.596981553940749,
+      "grad_norm": 2.7459099292755127,
+      "learning_rate": 2.0999667332002663e-06,
+      "loss": 1.631,
+      "step": 10000
+    },
+    {
+      "epoch": 1.676834624291304,
+      "grad_norm": 3.7493247985839844,
+      "learning_rate": 1.6841317365269464e-06,
+      "loss": 1.6266,
+      "step": 10500
+    },
+    {
+      "epoch": 1.756687694641859,
+      "grad_norm": 2.981618881225586,
+      "learning_rate": 1.2682967398536262e-06,
+      "loss": 1.625,
+      "step": 11000
+    },
+    {
+      "epoch": 1.836540764992414,
+      "grad_norm": 3.362718105316162,
+      "learning_rate": 8.524617431803061e-07,
+      "loss": 1.6317,
+      "step": 11500
+    },
+    {
+      "epoch": 1.9163938353429688,
+      "grad_norm": 3.9580516815185547,
+      "learning_rate": 4.366267465069861e-07,
+      "loss": 1.6084,
+      "step": 12000
+    },
+    {
+      "epoch": 1.996246905693524,
+      "grad_norm": 2.7975428104400635,
+      "learning_rate": 2.0791749833666e-08,
+      "loss": 1.6257,
+      "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.614437222480774,
+      "eval_runtime": 76.4918,
+      "eval_samples_per_second": 10.459,
+      "eval_steps_per_second": 2.615,
+      "step": 12524
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12524,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.651861778890752e+16,
+  "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 sha256:9a7a75717520b5541c6130c09f7d7ad77ff3d52e037b636c0a92af21296b499e
+size 5777