Upload folder using huggingface_hub

gpt2-eli5-final-by-Yvens-Yan/special_tokens_map.json

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

gpt2-eli5-final-by-Yvens-Yan/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|>"
+}

gpt2-eli5-final-by-Yvens/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": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gpt2-eli5-final-by-Yvens/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": "4.57.3"
+}

gpt2-eli5-final-by-Yvens/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bbe70ac1e467013a740686bcd5cb1576ce2c70134f3adfcf535fdfcad273d4
+size 327657928

gpt2-eli5-final-by-Yvens/special_tokens_map.json

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

gpt2-eli5-final-by-Yvens/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|>"
+}

gpt2-eli5-final-by-Yvens/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df40388a7fc006cad21a16f1e843b1a6de7a55741fabf5cd70900fe1a2186c2f
+size 5841

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/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": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/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": "4.57.3"
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d941b8217e715b4cf88747b8c5061c2bd45c770a50ba810876fe14ccb868f6b6
+size 327657928

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2368a2a27ec60ddb1fe8d4bd1957459629e208ada4b4720201f9aefb6fc776
+size 655362763

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842c78c5af0fe75a5fee647b2a44387e9e616631df773da0340a779b06e603d8
+size 14455

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cecd9662819a2b5eca8a0133c1afeee7b3bb3d98a0cffffb7a24d299094a8ac
+size 1465

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/special_tokens_map.json

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

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/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|>"
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_global_step": 1116,
+  "best_metric": 3.806886911392212,
+  "best_model_checkpoint": "./gpt2-eli5-finetuned-by-yvens/checkpoint-1116",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08960573476702509,
+      "grad_norm": 5.001793384552002,
+      "learning_rate": 3.96e-06,
+      "loss": 4.0385,
+      "step": 100
+    },
+    {
+      "epoch": 0.17921146953405018,
+      "grad_norm": 4.920190811157227,
+      "learning_rate": 7.960000000000002e-06,
+      "loss": 4.0278,
+      "step": 200
+    },
+    {
+      "epoch": 0.26881720430107525,
+      "grad_norm": 5.068778991699219,
+      "learning_rate": 1.196e-05,
+      "loss": 3.9832,
+      "step": 300
+    },
+    {
+      "epoch": 0.35842293906810035,
+      "grad_norm": 4.9818525314331055,
+      "learning_rate": 1.5960000000000003e-05,
+      "loss": 3.9571,
+      "step": 400
+    },
+    {
+      "epoch": 0.44802867383512546,
+      "grad_norm": 5.104599952697754,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 3.941,
+      "step": 500
+    },
+    {
+      "epoch": 0.5376344086021505,
+      "grad_norm": 5.533235549926758,
+      "learning_rate": 1.9304775280898877e-05,
+      "loss": 3.9193,
+      "step": 600
+    },
+    {
+      "epoch": 0.6272401433691757,
+      "grad_norm": 5.129825592041016,
+      "learning_rate": 1.860252808988764e-05,
+      "loss": 3.9058,
+      "step": 700
+    },
+    {
+      "epoch": 0.7168458781362007,
+      "grad_norm": 4.828098773956299,
+      "learning_rate": 1.7900280898876406e-05,
+      "loss": 3.8911,
+      "step": 800
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 4.615754127502441,
+      "learning_rate": 1.719803370786517e-05,
+      "loss": 3.898,
+      "step": 900
+    },
+    {
+      "epoch": 0.8960573476702509,
+      "grad_norm": 4.701573371887207,
+      "learning_rate": 1.6495786516853935e-05,
+      "loss": 3.9061,
+      "step": 1000
+    },
+    {
+      "epoch": 0.985663082437276,
+      "grad_norm": 4.873327255249023,
+      "learning_rate": 1.5793539325842696e-05,
+      "loss": 3.9055,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.806886911392212,
+      "eval_runtime": 216.4202,
+      "eval_samples_per_second": 10.831,
+      "eval_steps_per_second": 1.354,
+      "step": 1116
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 291574511566848.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-1116/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df40388a7fc006cad21a16f1e843b1a6de7a55741fabf5cd70900fe1a2186c2f
+size 5841

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/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": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/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": "4.57.3"
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d850c9361398f131400b607805a3af037a6e660e4194da2f4ad3c118829804c4
+size 327657928

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6990318122fee5ae156681219db11aaa9a09185ec96e2766e358ff5bd2263c
+size 655362763

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e1159454344ea29d8f6dc41e44e1487b918f50e97024bc69655f2f5356f533
+size 14455

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d9ceaed5269550269bcf5a9a284f40bb077f2eecd25f54cf0d1342e4dfef66
+size 1465

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/special_tokens_map.json

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

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/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|>"
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_global_step": 2232,
+  "best_metric": 3.794713258743286,
+  "best_model_checkpoint": "./gpt2-eli5-finetuned-by-yvens/checkpoint-2232",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2232,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08960573476702509,
+      "grad_norm": 5.001793384552002,
+      "learning_rate": 3.96e-06,
+      "loss": 4.0385,
+      "step": 100
+    },
+    {
+      "epoch": 0.17921146953405018,
+      "grad_norm": 4.920190811157227,
+      "learning_rate": 7.960000000000002e-06,
+      "loss": 4.0278,
+      "step": 200
+    },
+    {
+      "epoch": 0.26881720430107525,
+      "grad_norm": 5.068778991699219,
+      "learning_rate": 1.196e-05,
+      "loss": 3.9832,
+      "step": 300
+    },
+    {
+      "epoch": 0.35842293906810035,
+      "grad_norm": 4.9818525314331055,
+      "learning_rate": 1.5960000000000003e-05,
+      "loss": 3.9571,
+      "step": 400
+    },
+    {
+      "epoch": 0.44802867383512546,
+      "grad_norm": 5.104599952697754,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 3.941,
+      "step": 500
+    },
+    {
+      "epoch": 0.5376344086021505,
+      "grad_norm": 5.533235549926758,
+      "learning_rate": 1.9304775280898877e-05,
+      "loss": 3.9193,
+      "step": 600
+    },
+    {
+      "epoch": 0.6272401433691757,
+      "grad_norm": 5.129825592041016,
+      "learning_rate": 1.860252808988764e-05,
+      "loss": 3.9058,
+      "step": 700
+    },
+    {
+      "epoch": 0.7168458781362007,
+      "grad_norm": 4.828098773956299,
+      "learning_rate": 1.7900280898876406e-05,
+      "loss": 3.8911,
+      "step": 800
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 4.615754127502441,
+      "learning_rate": 1.719803370786517e-05,
+      "loss": 3.898,
+      "step": 900
+    },
+    {
+      "epoch": 0.8960573476702509,
+      "grad_norm": 4.701573371887207,
+      "learning_rate": 1.6495786516853935e-05,
+      "loss": 3.9061,
+      "step": 1000
+    },
+    {
+      "epoch": 0.985663082437276,
+      "grad_norm": 4.873327255249023,
+      "learning_rate": 1.5793539325842696e-05,
+      "loss": 3.9055,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.806886911392212,
+      "eval_runtime": 216.4202,
+      "eval_samples_per_second": 10.831,
+      "eval_steps_per_second": 1.354,
+      "step": 1116
+    },
+    {
+      "epoch": 1.075268817204301,
+      "grad_norm": 4.852152347564697,
+      "learning_rate": 1.509129213483146e-05,
+      "loss": 3.8508,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1648745519713262,
+      "grad_norm": 4.97360372543335,
+      "learning_rate": 1.4389044943820225e-05,
+      "loss": 3.8355,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2544802867383513,
+      "grad_norm": 5.336327075958252,
+      "learning_rate": 1.368679775280899e-05,
+      "loss": 3.8389,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3440860215053765,
+      "grad_norm": 4.8845391273498535,
+      "learning_rate": 1.2984550561797752e-05,
+      "loss": 3.8434,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4336917562724014,
+      "grad_norm": 5.234856128692627,
+      "learning_rate": 1.2282303370786517e-05,
+      "loss": 3.8194,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5232974910394266,
+      "grad_norm": 5.9331865310668945,
+      "learning_rate": 1.1580056179775281e-05,
+      "loss": 3.8246,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 5.067050933837891,
+      "learning_rate": 1.0877808988764044e-05,
+      "loss": 3.8345,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7025089605734767,
+      "grad_norm": 5.266586780548096,
+      "learning_rate": 1.0175561797752809e-05,
+      "loss": 3.8354,
+      "step": 1900
+    },
+    {
+      "epoch": 1.7921146953405018,
+      "grad_norm": 4.780787944793701,
+      "learning_rate": 9.473314606741573e-06,
+      "loss": 3.8364,
+      "step": 2000
+    },
+    {
+      "epoch": 1.881720430107527,
+      "grad_norm": 4.910538196563721,
+      "learning_rate": 8.771067415730338e-06,
+      "loss": 3.8148,
+      "step": 2100
+    },
+    {
+      "epoch": 1.971326164874552,
+      "grad_norm": 5.021151065826416,
+      "learning_rate": 8.068820224719102e-06,
+      "loss": 3.8147,
+      "step": 2200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.794713258743286,
+      "eval_runtime": 219.9998,
+      "eval_samples_per_second": 10.655,
+      "eval_steps_per_second": 1.332,
+      "step": 2232
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 583149023133696.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-2232/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df40388a7fc006cad21a16f1e843b1a6de7a55741fabf5cd70900fe1a2186c2f
+size 5841

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/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": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/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": "4.57.3"
+}

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bbe70ac1e467013a740686bcd5cb1576ce2c70134f3adfcf535fdfcad273d4
+size 327657928

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53465fadd00e9798f08db1f22fb7db9df089516b41b995491bc7c441a728b0a4
+size 655362763

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6169b4431d49d166de3b34de957b534726a26586fb8bc6a800362473218ee71
+size 14455

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d279d20f9cc838eedba1fcafa52ed1b7fb5c2ef58289537fdfe6a7fb47d3dfb
+size 1465

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/special_tokens_map.json

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

gpt2-eli5-finetuned-by-yvens/checkpoint-3348/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|>"
+}