Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "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_embd": 384,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536add46d39849d7b3b245255cccc23496ae850b91c65686ce57ee5dfe97e20b
+size 163959712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5214c95addd6a189c3a7197314f893f40eb7b3210bf710d112b618750bd12c0
+size 328014219

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4227f776e5afdba1e7bb106947cc869825e2c0b5a0aaf93b1d26b22105a05c6
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d383d9981af3af3a4b738ded756a0ac8f2c9578645c7dcaa1743590117bcebb5
+size 1465

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.128,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0128,
+      "grad_norm": 3.444922924041748,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 8.219487915039062,
+      "step": 100
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 0.8677482008934021,
+      "learning_rate": 0.000199,
+      "loss": 2.852702331542969,
+      "step": 200
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 1.1583627462387085,
+      "learning_rate": 0.000299,
+      "loss": 1.72166259765625,
+      "step": 300
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 1.3285731077194214,
+      "learning_rate": 0.00039900000000000005,
+      "loss": 1.4859967041015625,
+      "step": 400
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.5119664669036865,
+      "learning_rate": 0.000499,
+      "loss": 1.3544009399414063,
+      "step": 500
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 0.5693696737289429,
+      "learning_rate": 0.0004999682018599242,
+      "loss": 1.2615775299072265,
+      "step": 600
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 0.38031378388404846,
+      "learning_rate": 0.0004998715277031906,
+      "loss": 1.1965968322753906,
+      "step": 700
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 0.4511842131614685,
+      "learning_rate": 0.0004997099993771365,
+      "loss": 1.137486572265625,
+      "step": 800
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 0.3763165771961212,
+      "learning_rate": 0.000499483658806448,
+      "loss": 1.0960751342773438,
+      "step": 900
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.39710113406181335,
+      "learning_rate": 0.0004991925647378331,
+      "loss": 1.0592382049560547,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 20000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4186636812288000.0,
+  "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:d506e9be2fe39cd58743591a577d74d565d20822a613e541a28dc0667748fd3e
+size 5137