Upload 12 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "roberta-large-mnli",
+  "_num_labels": 3,
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb2afc7e8556d7129209e71786da4fb81cbaf07340924df20e806745b3aedfa
+size 1421495416

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a61d5ece527368bdc9077b296ade9879a69f21f4b3ea3a9f2db46c56c8f834
+size 2843211832

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7115fcd198f9a024a0ba7f8ad5b53f017f3dbc232c0c00d507816579b5a2d8c5
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0ee035866b3f2ff8fa72347e508cbfe42245d9bd713693a5fc24ed94b1837c
+size 627

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.03092513605952263,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.4044,
+      "step": 10
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.03055603615939617,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3836,
+      "step": 20
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.023527173325419426,
+      "learning_rate": 3e-06,
+      "loss": 0.0017,
+      "step": 30
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.02501656673848629,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0008,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.968421052631579,
+      "eval_f1": 0.9770992366412214,
+      "eval_loss": 0.23919111490249634,
+      "eval_precision": 0.9696969696969697,
+      "eval_recall": 0.9846153846153847,
+      "eval_runtime": 2.2913,
+      "eval_samples_per_second": 41.461,
+      "eval_steps_per_second": 2.619,
+      "step": 48
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.027175450697541237,
+      "learning_rate": 5e-06,
+      "loss": 0.0007,
+      "step": 50
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.017659997567534447,
+      "learning_rate": 6e-06,
+      "loss": 0.0006,
+      "step": 60
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.01459481567144394,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 0.0007,
+      "step": 70
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.011688518337905407,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.0028,
+      "step": 80
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.08688002079725266,
+      "learning_rate": 9e-06,
+      "loss": 0.0006,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9052631578947369,
+      "eval_f1": 0.9312977099236641,
+      "eval_loss": 0.7143413424491882,
+      "eval_precision": 0.9242424242424242,
+      "eval_recall": 0.9384615384615385,
+      "eval_runtime": 2.2819,
+      "eval_samples_per_second": 41.632,
+      "eval_steps_per_second": 2.629,
+      "step": 96
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.029978642240166664,
+      "learning_rate": 1e-05,
+      "loss": 0.1005,
+      "step": 100
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.010506043210625648,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.0003,
+      "step": 110
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 413.86444091796875,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1257,
+      "step": 120
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.022496210411190987,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.0018,
+      "step": 130
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 4.833926677703857,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.0823,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9473684210526315,
+      "eval_f1": 0.962406015037594,
+      "eval_loss": 0.2848361134529114,
+      "eval_precision": 0.9411764705882353,
+      "eval_recall": 0.9846153846153847,
+      "eval_runtime": 2.3284,
+      "eval_samples_per_second": 40.8,
+      "eval_steps_per_second": 2.577,
+      "step": 144
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 133.06631469726562,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0298,
+      "step": 150
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 5.606410503387451,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1977,
+      "step": 160
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 1.3438758850097656,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.0345,
+      "step": 170
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 219.62388610839844,
+      "learning_rate": 1.8e-05,
+      "loss": 0.2788,
+      "step": 180
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 0.02319713868200779,
+      "learning_rate": 1.9e-05,
+      "loss": 0.0778,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.9285714285714286,
+      "eval_loss": 0.73874431848526,
+      "eval_precision": 0.8666666666666667,
+      "eval_recall": 1.0,
+      "eval_runtime": 2.3292,
+      "eval_samples_per_second": 40.786,
+      "eval_steps_per_second": 2.576,
+      "step": 192
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.07177528738975525,
+      "learning_rate": 2e-05,
+      "loss": 0.2188,
+      "step": 200
+    },
+    {
+      "epoch": 4.375,
+      "grad_norm": 0.025927864015102386,
+      "learning_rate": 2.1e-05,
+      "loss": 0.0018,
+      "step": 210
+    },
+    {
+      "epoch": 4.583333333333333,
+      "grad_norm": 0.25771522521972656,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.2547,
+      "step": 220
+    },
+    {
+      "epoch": 4.791666666666667,
+      "grad_norm": 0.1835576444864273,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.1684,
+      "step": 230
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.051910556852817535,
+      "learning_rate": 2.4e-05,
+      "loss": 0.1683,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9263157894736842,
+      "eval_f1": 0.9465648854961831,
+      "eval_loss": 0.482939213514328,
+      "eval_precision": 0.9393939393939394,
+      "eval_recall": 0.9538461538461539,
+      "eval_runtime": 2.321,
+      "eval_samples_per_second": 40.931,
+      "eval_steps_per_second": 2.585,
+      "step": 240
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 442667397580800.0,
+  "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 sha256:151cb57fe6f6dd6868dab0332bf529b0a1669722782bf2482317a4427c537e5d
+size 4475