Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<sep>": 50257
+}

checkpoint-250/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "Gnider/model_old_working",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 800,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

checkpoint-250/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0.dev0"
+}

checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3159381e8e7224152e85626c4570d3c846c75cc3cf4dd2b6ec5f6f86ad597e8f
+size 500941440

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543f877a26423f1b2695ec4551c6d6d3cf82bb2f298c73f983bcb7e16a93b7dc
+size 1001976762

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6144905bd63fe531404d93bd3c8b7e957a94c6390f767d6674c172555e9993bc
+size 14244

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e3a4d7cd8780e40f2b2333952528e054b1881d8e2ea1f4f3933ea5b17b59ae
+size 1064

checkpoint-250/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": 2.437453269958496,
+  "best_model_checkpoint": "/kaggle/working/mix_15k/checkpoint-250",
+  "epoch": 5.329780146568954,
+  "eval_steps": 125,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5329780146568954,
+      "grad_norm": 0.5363643169403076,
+      "learning_rate": 2.5e-05,
+      "loss": 2.9777,
+      "step": 25
+    },
+    {
+      "epoch": 1.0659560293137909,
+      "grad_norm": 0.5214653015136719,
+      "learning_rate": 5e-05,
+      "loss": 2.8188,
+      "step": 50
+    },
+    {
+      "epoch": 1.598934043970686,
+      "grad_norm": 0.4909350275993347,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.6787,
+      "step": 75
+    },
+    {
+      "epoch": 2.1319120586275817,
+      "grad_norm": 0.4978727698326111,
+      "learning_rate": 0.0001,
+      "loss": 2.6019,
+      "step": 100
+    },
+    {
+      "epoch": 2.664890073284477,
+      "grad_norm": 0.5111510753631592,
+      "learning_rate": 8.579545454545454e-05,
+      "loss": 2.5312,
+      "step": 125
+    },
+    {
+      "epoch": 2.664890073284477,
+      "eval_loss": 2.476147174835205,
+      "eval_runtime": 122.0106,
+      "eval_samples_per_second": 24.531,
+      "eval_steps_per_second": 12.269,
+      "step": 125
+    },
+    {
+      "epoch": 3.1978680879413726,
+      "grad_norm": 0.4439743459224701,
+      "learning_rate": 7.15909090909091e-05,
+      "loss": 2.4952,
+      "step": 150
+    },
+    {
+      "epoch": 3.7308461025982678,
+      "grad_norm": 0.44518163800239563,
+      "learning_rate": 5.738636363636364e-05,
+      "loss": 2.4425,
+      "step": 175
+    },
+    {
+      "epoch": 4.263824117255163,
+      "grad_norm": 0.44307246804237366,
+      "learning_rate": 4.318181818181819e-05,
+      "loss": 2.4063,
+      "step": 200
+    },
+    {
+      "epoch": 4.796802131912059,
+      "grad_norm": 0.42895805835723877,
+      "learning_rate": 2.8977272727272732e-05,
+      "loss": 2.3821,
+      "step": 225
+    },
+    {
+      "epoch": 5.329780146568954,
+      "grad_norm": 0.4111803472042084,
+      "learning_rate": 1.4772727272727274e-05,
+      "loss": 2.3574,
+      "step": 250
+    },
+    {
+      "epoch": 5.329780146568954,
+      "eval_loss": 2.437453269958496,
+      "eval_runtime": 121.955,
+      "eval_samples_per_second": 24.542,
+      "eval_steps_per_second": 12.275,
+      "step": 250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 125,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.619247976064e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01aed42d128ead6106af4b09e0f3ea8f3963e1bf560c2b1a2e502a58ded18dec
+size 5112

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "Gnider/model_old_working",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 800,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3159381e8e7224152e85626c4570d3c846c75cc3cf4dd2b6ec5f6f86ad597e8f
+size 500941440

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,69 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sep_token": "<sep>",
+  "strip_accents": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}