model upload

added_tokens.json

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "4.42.3",
+  "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": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501ba19b58853b2a815ef04b51df2976adb43f9809d148183b60c3ac8357466b
+size 497777280

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e73bed8ae8164f8e279a894f423babb234097d0cf34dd06ef716718c2703ca1
+size 995648442

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c06975b6a00f94e153f34a2492131eb4b66e7e5b437c86255a2d354e9ef755
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd75506ae50bd20b70aa1f0070376537e145ed3847a59044b0dfda35dd4a4538
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 7200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 2.268265724182129,
+      "learning_rate": 4.652777777777778e-05,
+      "loss": 4.1035,
+      "step": 500
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.183037042617798,
+      "learning_rate": 4.305555555555556e-05,
+      "loss": 3.466,
+      "step": 1000
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.792080044746399,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 3.4238,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.926161289215088,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 3.4524,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 1.772346019744873,
+      "learning_rate": 3.263888888888889e-05,
+      "loss": 3.3802,
+      "step": 2500
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.6004018783569336,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 3.291,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 1.678238868713379,
+      "learning_rate": 2.5694444444444445e-05,
+      "loss": 3.2758,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.821945309638977,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 3.2967,
+      "step": 4000
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.7575188875198364,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3131,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 1.59396493434906,
+      "learning_rate": 1.527777777777778e-05,
+      "loss": 3.2545,
+      "step": 5000
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 1.741965889930725,
+      "learning_rate": 1.1805555555555555e-05,
+      "loss": 3.2134,
+      "step": 5500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.6898822784423828,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.2174,
+      "step": 6000
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 1.7870033979415894,
+      "learning_rate": 4.861111111111111e-06,
+      "loss": 3.2234,
+      "step": 6500
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 1.8400541543960571,
+      "learning_rate": 1.388888888888889e-06,
+      "loss": 3.2134,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7525210521600000.0,
+  "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 sha256:0165f77851900d151c50efa84fc70759dea1bd3f501c83a911527b2ef78f3338
+size 5112