Upload folder using huggingface_hub

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "facebook/bart-large-mnli",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "Applied computing",
+    "1": "Computer systems organization",
+    "2": "Computing methodologies",
+    "3": "General and reference",
+    "4": "Hardware",
+    "5": "Human-centered computing",
+    "6": "Information systems",
+    "7": "Mathematics of computing",
+    "8": "Networks",
+    "9": "Security and privacy",
+    "10": "Theory of computation"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Applied computing": 0,
+    "Computer systems organization": 1,
+    "Computing methodologies": 2,
+    "General and reference": 3,
+    "Hardware": 4,
+    "Human-centered computing": 5,
+    "Information systems": 6,
+    "Mathematics of computing": 7,
+    "Networks": 8,
+    "Security and privacy": 9,
+    "Theory of computation": 10
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee5f28e4740705a5419efdbcacf8c7a217febe4fb755e6a3a7c36136cb9d66d
+size 1629469764

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52e87599268a06ff0526eefdfbae8589e4178ef18665faac9d8a8e1ef0932c5
+size 3259250267

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8e4284e62fb18a1f03355bf3caa2f34c3cec6fd080ed67ac48efaea98524f0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c6516ad83f6c129c8ca1c3fe1a783db9bbc27c576b8ea61ee6ccd4d6241d26
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.886075949367089,
+  "eval_steps": 100,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 14.92142105102539,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.4108,
+      "step": 10
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 10.319029808044434,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.3752,
+      "step": 20
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 11.658527374267578,
+      "learning_rate": 3e-06,
+      "loss": 2.2968,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.538076400756836,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.1359,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 15.206498146057129,
+      "learning_rate": 5e-06,
+      "loss": 2.1211,
+      "step": 50
+    },
+    {
+      "epoch": 1.5063291139240507,
+      "grad_norm": 14.679222106933594,
+      "learning_rate": 6e-06,
+      "loss": 1.9345,
+      "step": 60
+    },
+    {
+      "epoch": 1.759493670886076,
+      "grad_norm": 14.933147430419922,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 1.715,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.749479293823242,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.5099,
+      "step": 80
+    },
+    {
+      "epoch": 2.2531645569620253,
+      "grad_norm": 16.478574752807617,
+      "learning_rate": 9e-06,
+      "loss": 1.3413,
+      "step": 90
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 11.706594467163086,
+      "learning_rate": 1e-05,
+      "loss": 1.0757,
+      "step": 100
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "eval_accuracy": 0.5857142857142857,
+      "eval_f1": 0.5055477855477856,
+      "eval_loss": 1.2395234107971191,
+      "eval_runtime": 5.2819,
+      "eval_samples_per_second": 13.253,
+      "eval_steps_per_second": 1.704,
+      "step": 100
+    },
+    {
+      "epoch": 2.759493670886076,
+      "grad_norm": 11.618650436401367,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.9368,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.1014986038208,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7523,
+      "step": 120
+    },
+    {
+      "epoch": 3.2531645569620253,
+      "grad_norm": 14.018274307250977,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.5237,
+      "step": 130
+    },
+    {
+      "epoch": 3.5063291139240507,
+      "grad_norm": 14.574962615966797,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.5173,
+      "step": 140
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 29.751333236694336,
+      "learning_rate": 1.5e-05,
+      "loss": 0.577,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 13.803457260131836,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4925,
+      "step": 160
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 11.551584243774414,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.2708,
+      "step": 170
+    },
+    {
+      "epoch": 4.506329113924051,
+      "grad_norm": 15.792594909667969,
+      "learning_rate": 1.8e-05,
+      "loss": 0.318,
+      "step": 180
+    },
+    {
+      "epoch": 4.759493670886076,
+      "grad_norm": 7.049367904663086,
+      "learning_rate": 1.9e-05,
+      "loss": 0.3567,
+      "step": 190
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 195,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1673689415946240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca08bc27073940b254418b4456ef30ec7b59fb3e7f39f1d8d49f5d6cfe588a13
+size 5304