Model save

Browse files

Files changed (14) hide show

last-checkpoint/config.json +0 -39
last-checkpoint/merges.txt +0 -0
last-checkpoint/optimizer.pt +0 -3
last-checkpoint/pytorch_model.bin +0 -3
last-checkpoint/rng_state.pth +0 -3
last-checkpoint/scaler.pt +0 -3
last-checkpoint/scheduler.pt +0 -3
last-checkpoint/special_tokens_map.json +0 -15
last-checkpoint/tokenizer.json +0 -0
last-checkpoint/tokenizer_config.json +0 -64
last-checkpoint/trainer_state.json +0 -368
last-checkpoint/training_args.bin +0 -3
last-checkpoint/vocab.json +0 -0
pytorch_model.bin +1 -1

last-checkpoint/config.json DELETED Viewed

@@ -1,39 +0,0 @@
-{
-  "_name_or_path": "textattack/roberta-base-MNLI",
-  "architectures": [
-    "RobertaForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "finetuning_task": "mnli",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "entailment",
-    "1": "neutral",
-    "2": "contradiction"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "contradiction": 2,
-    "entailment": 0,
-    "neutral": 1
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.27.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}

last-checkpoint/merges.txt DELETED Viewed

The diff for this file is too large to render. See raw diff

last-checkpoint/optimizer.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a10e9d1b17c22c8b81855d9e4b54c63fbb2c987aee21637eb45ddab0c9f1d31
-size 997349515

last-checkpoint/pytorch_model.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b4f713ac5da9d171cb132cf2c74cf0f0fa401b25773e9acb38e22d818270f5c
-size 498663405

last-checkpoint/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc559e8f3be7931753acd7e14135ef3c355c45429768068a18a2cdbd924ae84e
-size 14503

last-checkpoint/scaler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a96da2617fd1df0df7952478b447c0cfa383a6f4b13ae4ecb6da8a8b8fde5bdf
-size 559

last-checkpoint/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:601c2aea291c4f39ce9473e44c77e21714bd96f90420b8d09477bbcfeffc6321
-size 623

last-checkpoint/special_tokens_map.json DELETED Viewed

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

last-checkpoint/tokenizer.json DELETED Viewed

The diff for this file is too large to render. See raw diff

last-checkpoint/tokenizer_config.json DELETED Viewed

@@ -1,64 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "special_tokens_map_file": "/home/s5431786/.cache/huggingface/hub/models--textattack--roberta-base-MNLI/snapshots/6f2e633322381bc5897405e417ec531ea3633a3f/special_tokens_map.json",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

last-checkpoint/trainer_state.json DELETED Viewed

@@ -1,368 +0,0 @@
-{
-  "best_metric": 0.9114793850238726,
-  "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/textattack-roberta-base-MNLI-e-snli-classification-nli-base/checkpoint-7600",
-  "epoch": 1.0251630941286114,
-  "global_step": 8800,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.05,
-      "learning_rate": 3.082298136645963e-06,
-      "loss": 1.5376,
-      "step": 400
-    },
-    {
-      "epoch": 0.05,
-      "eval_accuracy": 0.8556187766714083,
-      "eval_f1": 0.8556462363132852,
-      "eval_loss": 0.40095046162605286,
-      "eval_runtime": 4.2759,
-      "eval_samples_per_second": 2301.749,
-      "eval_steps_per_second": 36.016,
-      "step": 400
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 6.187888198757764e-06,
-      "loss": 0.4352,
-      "step": 800
-    },
-    {
-      "epoch": 0.09,
-      "eval_accuracy": 0.8800040642145905,
-      "eval_f1": 0.8795301912940783,
-      "eval_loss": 0.3349034786224365,
-      "eval_runtime": 4.5813,
-      "eval_samples_per_second": 2148.309,
-      "eval_steps_per_second": 33.615,
-      "step": 800
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 9.293478260869566e-06,
-      "loss": 0.4,
-      "step": 1200
-    },
-    {
-      "epoch": 0.14,
-      "eval_accuracy": 0.8853891485470433,
-      "eval_f1": 0.8850952248341096,
-      "eval_loss": 0.31801462173461914,
-      "eval_runtime": 4.595,
-      "eval_samples_per_second": 2141.913,
-      "eval_steps_per_second": 33.515,
-      "step": 1200
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 9.87369195552649e-06,
-      "loss": 0.3801,
-      "step": 1600
-    },
-    {
-      "epoch": 0.19,
-      "eval_accuracy": 0.8920951026214184,
-      "eval_f1": 0.8917568158937579,
-      "eval_loss": 0.29749178886413574,
-      "eval_runtime": 4.426,
-      "eval_samples_per_second": 2223.668,
-      "eval_steps_per_second": 34.794,
-      "step": 1600
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 9.710186396337476e-06,
-      "loss": 0.3599,
-      "step": 2000
-    },
-    {
-      "epoch": 0.23,
-      "eval_accuracy": 0.8955496850233692,
-      "eval_f1": 0.8950963090954073,
-      "eval_loss": 0.29492226243019104,
-      "eval_runtime": 4.2584,
-      "eval_samples_per_second": 2311.208,
-      "eval_steps_per_second": 36.164,
-      "step": 2000
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 9.546680837148464e-06,
-      "loss": 0.3612,
-      "step": 2400
-    },
-    {
-      "epoch": 0.28,
-      "eval_accuracy": 0.8986994513310302,
-      "eval_f1": 0.8986773852884219,
-      "eval_loss": 0.2801545560359955,
-      "eval_runtime": 4.4994,
-      "eval_samples_per_second": 2187.409,
-      "eval_steps_per_second": 34.227,
-      "step": 2400
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 9.38317527795945e-06,
-      "loss": 0.3519,
-      "step": 2800
-    },
-    {
-      "epoch": 0.33,
-      "eval_accuracy": 0.8979882137776874,
-      "eval_f1": 0.8976730067239987,
-      "eval_loss": 0.2762671411037445,
-      "eval_runtime": 4.4383,
-      "eval_samples_per_second": 2217.515,
-      "eval_steps_per_second": 34.698,
-      "step": 2800
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 9.219669718770439e-06,
-      "loss": 0.349,
-      "step": 3200
-    },
-    {
-      "epoch": 0.37,
-      "eval_accuracy": 0.9022556390977443,
-      "eval_f1": 0.9020033896210373,
-      "eval_loss": 0.27657467126846313,
-      "eval_runtime": 4.5933,
-      "eval_samples_per_second": 2142.703,
-      "eval_steps_per_second": 33.527,
-      "step": 3200
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 9.056164159581427e-06,
-      "loss": 0.3432,
-      "step": 3600
-    },
-    {
-      "epoch": 0.42,
-      "eval_accuracy": 0.9001219264377159,
-      "eval_f1": 0.8999893300639911,
-      "eval_loss": 0.2747589945793152,
-      "eval_runtime": 4.3172,
-      "eval_samples_per_second": 2279.706,
-      "eval_steps_per_second": 35.671,
-      "step": 3600
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 8.892658600392414e-06,
-      "loss": 0.3435,
-      "step": 4000
-    },
-    {
-      "epoch": 0.47,
-      "eval_accuracy": 0.9051005893111156,
-      "eval_f1": 0.9051215853221407,
-      "eval_loss": 0.27019360661506653,
-      "eval_runtime": 4.5917,
-      "eval_samples_per_second": 2143.426,
-      "eval_steps_per_second": 33.539,
-      "step": 4000
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 8.729153041203402e-06,
-      "loss": 0.3352,
-      "step": 4400
-    },
-    {
-      "epoch": 0.51,
-      "eval_accuracy": 0.9038813249339566,
-      "eval_f1": 0.9034061899733951,
-      "eval_loss": 0.2727869153022766,
-      "eval_runtime": 4.4338,
-      "eval_samples_per_second": 2219.754,
-      "eval_steps_per_second": 34.733,
-      "step": 4400
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 8.565647482014388e-06,
-      "loss": 0.3277,
-      "step": 4800
-    },
-    {
-      "epoch": 0.56,
-      "eval_accuracy": 0.9042877463930096,
-      "eval_f1": 0.9039391226328383,
-      "eval_loss": 0.2633576989173889,
-      "eval_runtime": 4.474,
-      "eval_samples_per_second": 2199.802,
-      "eval_steps_per_second": 34.421,
-      "step": 4800
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 8.402550686723349e-06,
-      "loss": 0.3307,
-      "step": 5200
-    },
-    {
-      "epoch": 0.61,
-      "eval_accuracy": 0.9057102214996952,
-      "eval_f1": 0.9050187432087493,
-      "eval_loss": 0.26230183243751526,
-      "eval_runtime": 4.1881,
-      "eval_samples_per_second": 2349.966,
-      "eval_steps_per_second": 36.77,
-      "step": 5200
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 8.239045127534336e-06,
-      "loss": 0.3247,
-      "step": 5600
-    },
-    {
-      "epoch": 0.65,
-      "eval_accuracy": 0.9063198536882747,
-      "eval_f1": 0.9059067839331951,
-      "eval_loss": 0.26849961280822754,
-      "eval_runtime": 4.4315,
-      "eval_samples_per_second": 2220.93,
-      "eval_steps_per_second": 34.751,
-      "step": 5600
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 8.075539568345324e-06,
-      "loss": 0.3175,
-      "step": 6000
-    },
-    {
-      "epoch": 0.7,
-      "eval_accuracy": 0.90835196098354,
-      "eval_f1": 0.9081309299681798,
-      "eval_loss": 0.25888413190841675,
-      "eval_runtime": 4.4315,
-      "eval_samples_per_second": 2220.898,
-      "eval_steps_per_second": 34.751,
-      "step": 6000
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 7.912034009156312e-06,
-      "loss": 0.3144,
-      "step": 6400
-    },
-    {
-      "epoch": 0.75,
-      "eval_accuracy": 0.9092664092664092,
-      "eval_f1": 0.9087749519181698,
-      "eval_loss": 0.2586296796798706,
-      "eval_runtime": 4.4165,
-      "eval_samples_per_second": 2228.443,
-      "eval_steps_per_second": 34.869,
-      "step": 6400
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 7.7485284499673e-06,
-      "loss": 0.3102,
-      "step": 6800
-    },
-    {
-      "epoch": 0.79,
-      "eval_accuracy": 0.9089615931721194,
-      "eval_f1": 0.9088222146205912,
-      "eval_loss": 0.2547251582145691,
-      "eval_runtime": 4.5049,
-      "eval_samples_per_second": 2184.723,
-      "eval_steps_per_second": 34.185,
-      "step": 6800
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 7.585022890778288e-06,
-      "loss": 0.3223,
-      "step": 7200
-    },
-    {
-      "epoch": 0.84,
-      "eval_accuracy": 0.909571225360699,
-      "eval_f1": 0.9093158037084038,
-      "eval_loss": 0.25255095958709717,
-      "eval_runtime": 4.2651,
-      "eval_samples_per_second": 2307.581,
-      "eval_steps_per_second": 36.107,
-      "step": 7200
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 7.421517331589274e-06,
-      "loss": 0.3166,
-      "step": 7600
-    },
-    {
-      "epoch": 0.89,
-      "eval_accuracy": 0.9118065433854907,
-      "eval_f1": 0.9114793850238726,
-      "eval_loss": 0.24902105331420898,
-      "eval_runtime": 4.4308,
-      "eval_samples_per_second": 2221.264,
-      "eval_steps_per_second": 34.757,
-      "step": 7600
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 7.258011772400262e-06,
-      "loss": 0.3124,
-      "step": 8000
-    },
-    {
-      "epoch": 0.93,
-      "eval_accuracy": 0.9106888843730949,
-      "eval_f1": 0.9105538161740804,
-      "eval_loss": 0.2503485083580017,
-      "eval_runtime": 4.4709,
-      "eval_samples_per_second": 2201.33,
-      "eval_steps_per_second": 34.445,
-      "step": 8000
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 7.0949149771092216e-06,
-      "loss": 0.3053,
-      "step": 8400
-    },
-    {
-      "epoch": 0.98,
-      "eval_accuracy": 0.9100792521845154,
-      "eval_f1": 0.9098862073513235,
-      "eval_loss": 0.2452017217874527,
-      "eval_runtime": 4.4231,
-      "eval_samples_per_second": 2225.145,
-      "eval_steps_per_second": 34.817,
-      "step": 8400
-    },
-    {
-      "epoch": 1.03,
-      "learning_rate": 6.93140941792021e-06,
-      "loss": 0.2908,
-      "step": 8800
-    },
-    {
-      "epoch": 1.03,
-      "eval_accuracy": 0.911908148750254,
-      "eval_f1": 0.9113463195976007,
-      "eval_loss": 0.2575433552265167,
-      "eval_runtime": 4.383,
-      "eval_samples_per_second": 2245.491,
-      "eval_steps_per_second": 35.136,
-      "step": 8800
-    }
-  ],
-  "max_steps": 25752,
-  "num_train_epochs": 3,
-  "total_flos": 1.536997071500478e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1902e90a9e14b843b5170a79e45072d9242111eb8136de151581eceb0f4c7e52
-size 3759

last-checkpoint/vocab.json DELETED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4f713ac5da9d171cb132cf2c74cf0f0fa401b25773e9acb38e22d818270f5c
 size 498663405

 version https://git-lfs.github.com/spec/v1
+oid sha256:28f1b2bc7c2c05add017e0a368f237527ae4bdd70f14d7023a384e1ec6d2289c
 size 498663405