Upload folder using huggingface_hub

checkpoint-15/config.json

@@ -0,0 +1,46 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-15/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": "4.57.0"
+}

checkpoint-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4034139a735100dbcedfe0e53e8b08662be1878ed9fa9158b9a24ebcca3976
+size 327657928

checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeaadba84ac4b3c1dd5f77f5935b344127dbdfeb3918934c48f2ec126755136c
+size 655365963

checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5669da21ccf81a24666ad857b92da86b0bd95217aae695d8bd0f5899acfe328
+size 14645

checkpoint-15/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa9e1fdd8e74ce642796ebb33fe035045a7e910fababc0a0ae69985378e577f
+size 1383

checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24afd91f5235b6266df9f0b8ffb3028b228bb71c80b52ee05fe96e19da24806
+size 1465

checkpoint-15/special_tokens_map.json

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

checkpoint-15/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|>"
+}

checkpoint-15/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 4.8075,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 2.5e-05,
+      "loss": 4.4804,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": Infinity,
+      "learning_rate": 5e-05,
+      "loss": 4.8127,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": Infinity,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 4.5227,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.056394577026367,
+      "learning_rate": 4.230769230769231e-05,
+      "loss": 4.6393,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 22.853288650512695,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 4.0617,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 20.53002166748047,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 3.7637,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 19.108043670654297,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 3.3392,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 17.581727981567383,
+      "learning_rate": 2.6923076923076923e-05,
+      "loss": 2.976,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 18.167375564575195,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 2.7688,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 17.9623966217041,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 2.6739,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 17.046262741088867,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 2.4183,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 16.45479393005371,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 2.2617,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 15.66003704071045,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 2.1825,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 15.448290824890137,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 2.1376,
+      "step": 15
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 137793208320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a4e2a11633fd0f6bb5e0d7cb6373f4ecf42b38e751b09725a816e40aa4a0d9
+size 6097

config.json

@@ -0,0 +1,46 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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": "4.57.0",
+  "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": "4.57.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4034139a735100dbcedfe0e53e8b08662be1878ed9fa9158b9a24ebcca3976
+size 327657928

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|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a4e2a11633fd0f6bb5e0d7cb6373f4ecf42b38e751b09725a816e40aa4a0d9
+size 6097