Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8970588235294118,
+    "eval_combined_score": 0.9106232745805904,
+    "eval_f1": 0.924187725631769,
+    "eval_loss": 0.3507114052772522,
+    "eval_runtime": 1.101,
+    "eval_samples": 408,
+    "eval_samples_per_second": 370.585,
+    "eval_steps_per_second": 46.323,
+    "train_loss": 0.20570029414218405,
+    "train_runtime": 332.3723,
+    "train_samples": 3668,
+    "train_samples_per_second": 110.358,
+    "train_steps_per_second": 3.46
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8970588235294118,
+    "eval_combined_score": 0.9106232745805904,
+    "eval_f1": 0.924187725631769,
+    "eval_loss": 0.3507114052772522,
+    "eval_runtime": 1.101,
+    "eval_samples": 408,
+    "eval_samples_per_second": 370.585,
+    "eval_steps_per_second": 46.323
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b73d460b691552cfa8560b867ad4f3b3da03661070fb89ccb622d0101709c89
+size 498674093

special_tokens_map.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.20570029414218405,
+    "train_runtime": 332.3723,
+    "train_samples": 3668,
+    "train_samples_per_second": 110.358,
+    "train_steps_per_second": 3.46
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.8970588235294118,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-575",
+  "epoch": 10.0,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.6336,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.538364589214325,
+      "eval_runtime": 1.089,
+      "eval_samples_per_second": 374.663,
+      "eval_steps_per_second": 46.833,
+      "step": 115
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.482,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8357843137254902,
+      "eval_combined_score": 0.8625202560362988,
+      "eval_f1": 0.8892561983471075,
+      "eval_loss": 0.40759965777397156,
+      "eval_runtime": 1.0806,
+      "eval_samples_per_second": 377.572,
+      "eval_steps_per_second": 47.196,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.3576,
+      "step": 345
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.875,
+      "eval_combined_score": 0.8912205081669691,
+      "eval_f1": 0.9074410163339381,
+      "eval_loss": 0.2955787181854248,
+      "eval_runtime": 1.0806,
+      "eval_samples_per_second": 377.557,
+      "eval_steps_per_second": 47.195,
+      "step": 345
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2205,
+      "step": 460
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9076168929110106,
+      "eval_f1": 0.923076923076923,
+      "eval_loss": 0.3020019829273224,
+      "eval_runtime": 1.0822,
+      "eval_samples_per_second": 376.994,
+      "eval_steps_per_second": 47.124,
+      "step": 460
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1258,
+      "step": 575
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9106232745805904,
+      "eval_f1": 0.924187725631769,
+      "eval_loss": 0.3507114052772522,
+      "eval_runtime": 1.0903,
+      "eval_samples_per_second": 374.196,
+      "eval_steps_per_second": 46.775,
+      "step": 575
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0893,
+      "step": 690
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.8994403520091766,
+      "eval_f1": 0.9140767824497258,
+      "eval_loss": 0.46679043769836426,
+      "eval_runtime": 1.0897,
+      "eval_samples_per_second": 374.408,
+      "eval_steps_per_second": 46.801,
+      "step": 690
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0635,
+      "step": 805
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.906510086048808,
+      "eval_f1": 0.9208633093525179,
+      "eval_loss": 0.5193934440612793,
+      "eval_runtime": 1.1035,
+      "eval_samples_per_second": 369.736,
+      "eval_steps_per_second": 46.217,
+      "step": 805
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 5e-06,
+      "loss": 0.0391,
+      "step": 920
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9040180954414434,
+      "eval_f1": 0.9183303085299456,
+      "eval_loss": 0.642646312713623,
+      "eval_runtime": 1.0978,
+      "eval_samples_per_second": 371.638,
+      "eval_steps_per_second": 46.455,
+      "step": 920
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0294,
+      "step": 1035
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.9003626047914693,
+      "eval_f1": 0.9159212880143113,
+      "eval_loss": 0.6596136689186096,
+      "eval_runtime": 1.1007,
+      "eval_samples_per_second": 370.671,
+      "eval_steps_per_second": 46.334,
+      "step": 1035
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0163,
+      "step": 1150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9063672400368089,
+      "eval_f1": 0.9205776173285197,
+      "eval_loss": 0.6627745628356934,
+      "eval_runtime": 1.1037,
+      "eval_samples_per_second": 369.676,
+      "eval_steps_per_second": 46.209,
+      "step": 1150
+    },
+    {
+      "epoch": 10.0,
+      "step": 1150,
+      "total_flos": 2412728377651200.0,
+      "train_loss": 0.20570029414218405,
+      "train_runtime": 332.3723,
+      "train_samples_per_second": 110.358,
+      "train_steps_per_second": 3.46
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 10,
+  "total_flos": 2412728377651200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a284c958d847bca1ed75dfe235d4e054d6fb6636da319cbdb061a25d6e03a50
+size 2671