Model save

last-checkpoint/config.json

@@ -1,38 +0,0 @@
-{
-  "_name_or_path": "roberta-large",
-  "architectures": [
-    "RobertaForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "id2label": {
-    "0": "entailment",
-    "1": "neutral",
-    "2": "contradiction"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "contradiction": 2,
-    "entailment": 0,
-    "neutral": 1
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "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/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:43b746406019bd322df48fd0f5832641bf2c23f192d1ba2c1bcf2cc6ec4661ff
-size 2843228158

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c70a2b61096d5fd16d601664f84ccd8cb72633596aa2bd5105a81863e667c6b3
-size 1421588461

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b11b41a45679a6cc286e868bec1372008710d641cbd28a995ea530dff638bd50
-size 14503

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad34206adf67443db75af07189b4384fe36c9a4922d3cd2b4375c9ae9591e609
-size 559

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ce44e4c1c23e749cd9382e42f9e5375956ba931527c483dc2fade7c594fb4a25
-size 623

last-checkpoint/special_tokens_map.json

@@ -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_config.json

@@ -1,15 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,288 +0,0 @@
-{
-  "best_metric": 0.9274853061519247,
-  "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-base/checkpoint-6000",
-  "epoch": 0.7921714818266542,
-  "global_step": 6800,
-  "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": 0.9995,
-      "step": 400
-    },
-    {
-      "epoch": 0.05,
-      "eval_accuracy": 0.8464742938427149,
-      "eval_f1": 0.8436602565292818,
-      "eval_loss": 0.42355620861053467,
-      "eval_runtime": 9.7799,
-      "eval_samples_per_second": 1006.353,
-      "eval_steps_per_second": 15.747,
-      "step": 400
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 6.187888198757764e-06,
-      "loss": 0.4089,
-      "step": 800
-    },
-    {
-      "epoch": 0.09,
-      "eval_accuracy": 0.8933143669985776,
-      "eval_f1": 0.8925604380368285,
-      "eval_loss": 0.2960757315158844,
-      "eval_runtime": 9.9483,
-      "eval_samples_per_second": 989.314,
-      "eval_steps_per_second": 15.48,
-      "step": 800
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 9.285714285714288e-06,
-      "loss": 0.3681,
-      "step": 1200
-    },
-    {
-      "epoch": 0.14,
-      "eval_accuracy": 0.8923999187157082,
-      "eval_f1": 0.8914399447140089,
-      "eval_loss": 0.2979675531387329,
-      "eval_runtime": 11.3415,
-      "eval_samples_per_second": 867.789,
-      "eval_steps_per_second": 13.578,
-      "step": 1200
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 9.874100719424462e-06,
-      "loss": 0.3467,
-      "step": 1600
-    },
-    {
-      "epoch": 0.19,
-      "eval_accuracy": 0.89900426742532,
-      "eval_f1": 0.8976972154704725,
-      "eval_loss": 0.28719303011894226,
-      "eval_runtime": 9.8854,
-      "eval_samples_per_second": 995.605,
-      "eval_steps_per_second": 15.578,
-      "step": 1600
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 9.71100392413342e-06,
-      "loss": 0.324,
-      "step": 2000
-    },
-    {
-      "epoch": 0.23,
-      "eval_accuracy": 0.9109937004673847,
-      "eval_f1": 0.9105643338042256,
-      "eval_loss": 0.2506079077720642,
-      "eval_runtime": 9.9303,
-      "eval_samples_per_second": 991.111,
-      "eval_steps_per_second": 15.508,
-      "step": 2000
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 9.547498364944409e-06,
-      "loss": 0.3222,
-      "step": 2400
-    },
-    {
-      "epoch": 0.28,
-      "eval_accuracy": 0.9128225970331233,
-      "eval_f1": 0.9131812993042298,
-      "eval_loss": 0.2551884353160858,
-      "eval_runtime": 9.9844,
-      "eval_samples_per_second": 985.737,
-      "eval_steps_per_second": 15.424,
-      "step": 2400
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 9.383992805755397e-06,
-      "loss": 0.3138,
-      "step": 2800
-    },
-    {
-      "epoch": 0.33,
-      "eval_accuracy": 0.9183092867303394,
-      "eval_f1": 0.9182731413386942,
-      "eval_loss": 0.23789888620376587,
-      "eval_runtime": 10.0071,
-      "eval_samples_per_second": 983.498,
-      "eval_steps_per_second": 15.389,
-      "step": 2800
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 9.220487246566384e-06,
-      "loss": 0.3107,
-      "step": 3200
-    },
-    {
-      "epoch": 0.37,
-      "eval_accuracy": 0.9155659418817313,
-      "eval_f1": 0.9151783750171821,
-      "eval_loss": 0.23962362110614777,
-      "eval_runtime": 9.9366,
-      "eval_samples_per_second": 990.484,
-      "eval_steps_per_second": 15.498,
-      "step": 3200
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 9.056981687377372e-06,
-      "loss": 0.304,
-      "step": 3600
-    },
-    {
-      "epoch": 0.42,
-      "eval_accuracy": 0.9176996545417598,
-      "eval_f1": 0.9174168238144101,
-      "eval_loss": 0.23535017669200897,
-      "eval_runtime": 9.936,
-      "eval_samples_per_second": 990.544,
-      "eval_steps_per_second": 15.499,
-      "step": 3600
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 8.893476128188358e-06,
-      "loss": 0.3027,
-      "step": 4000
-    },
-    {
-      "epoch": 0.47,
-      "eval_accuracy": 0.9191221296484454,
-      "eval_f1": 0.9190571565466592,
-      "eval_loss": 0.23602379858493805,
-      "eval_runtime": 10.6438,
-      "eval_samples_per_second": 924.674,
-      "eval_steps_per_second": 14.469,
-      "step": 4000
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 8.729970568999347e-06,
-      "loss": 0.2968,
-      "step": 4400
-    },
-    {
-      "epoch": 0.51,
-      "eval_accuracy": 0.9187157081893924,
-      "eval_f1": 0.9182261319193824,
-      "eval_loss": 0.23287305235862732,
-      "eval_runtime": 9.9312,
-      "eval_samples_per_second": 991.014,
-      "eval_steps_per_second": 15.507,
-      "step": 4400
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 8.566465009810335e-06,
-      "loss": 0.2888,
-      "step": 4800
-    },
-    {
-      "epoch": 0.56,
-      "eval_accuracy": 0.9196301564722618,
-      "eval_f1": 0.9189361658403055,
-      "eval_loss": 0.24621723592281342,
-      "eval_runtime": 9.9085,
-      "eval_samples_per_second": 993.291,
-      "eval_steps_per_second": 15.542,
-      "step": 4800
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 8.402959450621321e-06,
-      "loss": 0.2898,
-      "step": 5200
-    },
-    {
-      "epoch": 0.61,
-      "eval_accuracy": 0.9211542369437107,
-      "eval_f1": 0.9206360860900841,
-      "eval_loss": 0.23345668613910675,
-      "eval_runtime": 10.0954,
-      "eval_samples_per_second": 974.901,
-      "eval_steps_per_second": 15.254,
-      "step": 5200
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 8.23945389143231e-06,
-      "loss": 0.288,
-      "step": 5600
-    },
-    {
-      "epoch": 0.65,
-      "eval_accuracy": 0.9222718959561065,
-      "eval_f1": 0.9220252130752401,
-      "eval_loss": 0.23495520651340485,
-      "eval_runtime": 9.9904,
-      "eval_samples_per_second": 985.146,
-      "eval_steps_per_second": 15.415,
-      "step": 5600
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 8.07635709614127e-06,
-      "loss": 0.2746,
-      "step": 6000
-    },
-    {
-      "epoch": 0.7,
-      "eval_accuracy": 0.9277585856533225,
-      "eval_f1": 0.9274853061519247,
-      "eval_loss": 0.22077496349811554,
-      "eval_runtime": 9.9415,
-      "eval_samples_per_second": 989.988,
-      "eval_steps_per_second": 15.491,
-      "step": 6000
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 7.912851536952257e-06,
-      "loss": 0.2756,
-      "step": 6400
-    },
-    {
-      "epoch": 0.75,
-      "eval_accuracy": 0.9215606584027637,
-      "eval_f1": 0.9208559714907353,
-      "eval_loss": 0.23040013015270233,
-      "eval_runtime": 9.916,
-      "eval_samples_per_second": 992.538,
-      "eval_steps_per_second": 15.53,
-      "step": 6400
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 7.749345977763243e-06,
-      "loss": 0.272,
-      "step": 6800
-    },
-    {
-      "epoch": 0.79,
-      "eval_accuracy": 0.9237959764275554,
-      "eval_f1": 0.9236808650336354,
-      "eval_loss": 0.2243068963289261,
-      "eval_runtime": 11.5455,
-      "eval_samples_per_second": 852.451,
-      "eval_steps_per_second": 13.338,
-      "step": 6800
-    }
-  ],
-  "max_steps": 25752,
-  "num_train_epochs": 3,
-  "total_flos": 4.208639555132851e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c226ff8a79fc8c43647efdd29cbdbc642d1c7fa8c770b0a81535e6a61aee411
-size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70a2b61096d5fd16d601664f84ccd8cb72633596aa2bd5105a81863e667c6b3
+oid sha256:7d27bd0c8fce811ee26a2630d332b495ceabc992b88ed7e0afd7cdda82dc97b4
 size 1421588461