Upload folder using huggingface_hub

cola/roberta-base_lr1e-05/classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5141ce17fe52592b8578b7fbc28a0e021c36f262f9118ea79310dda82b6b47f4
+size 2371407

cola/roberta-base_lr1e-05/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

cola/roberta-base_lr1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ec7931db4b523d0aa2b6e8655e229a3a55f9059ec192a194ad0cf8122e9f29
+size 498612824

cola/roberta-base_lr1e-05/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>"
+}

cola/roberta-base_lr1e-05/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>"
+}

cola/roberta-base_lr1e-05/trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": 0.6136322073831847,
+  "best_model_checkpoint": "./save_models/cola/roberta-base_lr1e-05/checkpoint-248",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5821298956871033,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.557,
+      "eval_samples_per_second": 549.767,
+      "eval_steps_per_second": 2.569,
+      "step": 31
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4815237522125244,
+      "eval_matthews_correlation": 0.09833128071522987,
+      "eval_runtime": 1.2301,
+      "eval_samples_per_second": 695.896,
+      "eval_steps_per_second": 3.252,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4497840702533722,
+      "eval_matthews_correlation": 0.5200031718306268,
+      "eval_runtime": 1.2175,
+      "eval_samples_per_second": 703.099,
+      "eval_steps_per_second": 3.286,
+      "step": 93
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.45493587851524353,
+      "eval_matthews_correlation": 0.5526832237492683,
+      "eval_runtime": 1.456,
+      "eval_samples_per_second": 587.894,
+      "eval_steps_per_second": 2.747,
+      "step": 124
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.4303121268749237,
+      "eval_matthews_correlation": 0.5818251601933869,
+      "eval_runtime": 1.3482,
+      "eval_samples_per_second": 634.941,
+      "eval_steps_per_second": 2.967,
+      "step": 155
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.4925920367240906,
+      "eval_matthews_correlation": 0.5730783192190388,
+      "eval_runtime": 1.4104,
+      "eval_samples_per_second": 606.924,
+      "eval_steps_per_second": 2.836,
+      "step": 186
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.4559820294380188,
+      "eval_matthews_correlation": 0.5895848105106377,
+      "eval_runtime": 1.2207,
+      "eval_samples_per_second": 701.208,
+      "eval_steps_per_second": 3.277,
+      "step": 217
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.4101633131504059,
+      "eval_matthews_correlation": 0.6136322073831847,
+      "eval_runtime": 1.1981,
+      "eval_samples_per_second": 714.473,
+      "eval_steps_per_second": 3.339,
+      "step": 248
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.4428262710571289,
+      "eval_matthews_correlation": 0.608505850822177,
+      "eval_runtime": 1.2411,
+      "eval_samples_per_second": 689.717,
+      "eval_steps_per_second": 3.223,
+      "step": 279
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.4468447268009186,
+      "eval_matthews_correlation": 0.6052396882783275,
+      "eval_runtime": 1.4122,
+      "eval_samples_per_second": 606.156,
+      "eval_steps_per_second": 2.833,
+      "step": 310
+    },
+    {
+      "epoch": 10.0,
+      "step": 310,
+      "total_flos": 1166187850116420.0,
+      "train_loss": 0.3865204349640877,
+      "train_runtime": 143.4469,
+      "train_samples_per_second": 536.436,
+      "train_steps_per_second": 2.161
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1166187850116420.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

cola/roberta-base_lr1e-05/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8b9a70202047a46707b4bf2b2259dde8b824c5f9419c6f8d59245944630184
+size 4347

mnli/roberta-base_lr1e-05/classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29e735718dcbfc85857a32c8184f59173a48d73df659c330618299620d6b304
+size 2374479

mnli/roberta-base_lr1e-05/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

mnli/roberta-base_lr1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc9a6abbb0b48c8f80deeda37976db09f744f9e1413fea5a063ea28b7a796d7
+size 498615900

mnli/roberta-base_lr1e-05/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>"
+}

mnli/roberta-base_lr1e-05/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>"
+}

mnli/roberta-base_lr1e-05/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.86832522726694,
+  "best_model_checkpoint": "./save_models/mnli/roberta-base_lr1e-05/checkpoint-8286",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 13810,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.031363088057901e-06,
+      "loss": 0.8769,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.86826900855096e-06,
+      "loss": 0.4908,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8439306358381503,
+      "eval_loss": 0.40705999732017517,
+      "eval_runtime": 30.2499,
+      "eval_samples_per_second": 1298.219,
+      "eval_steps_per_second": 5.091,
+      "step": 1381
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.483090670980664e-06,
+      "loss": 0.4345,
+      "step": 1500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.09791233341037e-06,
+      "loss": 0.3978,
+      "step": 2000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.712733995840074e-06,
+      "loss": 0.3855,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8618318861246212,
+      "eval_loss": 0.3706605136394501,
+      "eval_runtime": 30.5079,
+      "eval_samples_per_second": 1287.241,
+      "eval_steps_per_second": 5.048,
+      "step": 2762
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.32755565826978e-06,
+      "loss": 0.3572,
+      "step": 3000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.942377320699485e-06,
+      "loss": 0.3368,
+      "step": 3500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 7.557198983129189e-06,
+      "loss": 0.3354,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8657533548929235,
+      "eval_loss": 0.36279234290122986,
+      "eval_runtime": 30.3356,
+      "eval_samples_per_second": 1294.551,
+      "eval_steps_per_second": 5.077,
+      "step": 4143
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 7.172020645558895e-06,
+      "loss": 0.3097,
+      "step": 4500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 6.7868423079885995e-06,
+      "loss": 0.2998,
+      "step": 5000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 6.401663970418303e-06,
+      "loss": 0.3005,
+      "step": 5500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8673066639504978,
+      "eval_loss": 0.36057987809181213,
+      "eval_runtime": 30.2539,
+      "eval_samples_per_second": 1298.049,
+      "eval_steps_per_second": 5.09,
+      "step": 5524
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.016485632848009e-06,
+      "loss": 0.2734,
+      "step": 6000
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 5.631307295277714e-06,
+      "loss": 0.2724,
+      "step": 6500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8679178019403632,
+      "eval_loss": 0.3738739490509033,
+      "eval_runtime": 30.6701,
+      "eval_samples_per_second": 1280.434,
+      "eval_steps_per_second": 5.021,
+      "step": 6905
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 5.2461289577074194e-06,
+      "loss": 0.2667,
+      "step": 7000
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 4.860950620137123e-06,
+      "loss": 0.2466,
+      "step": 7500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 4.475772282566829e-06,
+      "loss": 0.2481,
+      "step": 8000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.86832522726694,
+      "eval_loss": 0.3865111470222473,
+      "eval_runtime": 30.6524,
+      "eval_samples_per_second": 1281.174,
+      "eval_steps_per_second": 5.024,
+      "step": 8286
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 4.090593944996534e-06,
+      "loss": 0.2394,
+      "step": 8500
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 3.705415607426239e-06,
+      "loss": 0.2269,
+      "step": 9000
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 3.3202372698559437e-06,
+      "loss": 0.2264,
+      "step": 9500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8672557357846757,
+      "eval_loss": 0.3937914967536926,
+      "eval_runtime": 30.6252,
+      "eval_samples_per_second": 1282.311,
+      "eval_steps_per_second": 5.029,
+      "step": 9667
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 2.935058932285649e-06,
+      "loss": 0.2181,
+      "step": 10000
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 2.5498805947153533e-06,
+      "loss": 0.2134,
+      "step": 10500
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 2.164702257145058e-06,
+      "loss": 0.2145,
+      "step": 11000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8681469786865627,
+      "eval_loss": 0.4055633544921875,
+      "eval_runtime": 30.7036,
+      "eval_samples_per_second": 1279.035,
+      "eval_steps_per_second": 5.016,
+      "step": 11048
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 1.7795239195747632e-06,
+      "loss": 0.2017,
+      "step": 11500
+    },
+    {
+      "epoch": 8.69,
+      "learning_rate": 1.3943455820044682e-06,
+      "loss": 0.2008,
+      "step": 12000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8672811998675868,
+      "eval_loss": 0.41524767875671387,
+      "eval_runtime": 30.8769,
+      "eval_samples_per_second": 1271.856,
+      "eval_steps_per_second": 4.988,
+      "step": 12429
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 1.0091672444341732e-06,
+      "loss": 0.2013,
+      "step": 12500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 6.239889068638781e-07,
+      "loss": 0.1909,
+      "step": 13000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.3881056929358295e-07,
+      "loss": 0.1936,
+      "step": 13500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8680960505207405,
+      "eval_loss": 0.42063575983047485,
+      "eval_runtime": 30.2907,
+      "eval_samples_per_second": 1296.472,
+      "eval_steps_per_second": 5.084,
+      "step": 13810
+    },
+    {
+      "epoch": 10.0,
+      "step": 13810,
+      "total_flos": 2.1610790039821677e+17,
+      "train_loss": 0.29975197396357794,
+      "train_runtime": 5291.5699,
+      "train_samples_per_second": 667.913,
+      "train_steps_per_second": 2.61
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13810,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.1610790039821677e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

mnli/roberta-base_lr1e-05/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a381407731b0402ac4f328df0350af493419c58d93f78a051ff6a50c6d632ca2
+size 4283

mrpc/roberta-base_lr1e-05/classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435024607635c1d86f68a56717c1e67c952f3cb7680f30ba13eb391ed286bdbf
+size 2371407

mrpc/roberta-base_lr1e-05/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

mrpc/roberta-base_lr1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ea247447fd32b0393ba18fe7185d02329a50ce4b4fe47aad0b59f7f49e1c78
+size 498612824

mrpc/roberta-base_lr1e-05/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>"
+}

mrpc/roberta-base_lr1e-05/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>"
+}

mrpc/roberta-base_lr1e-05/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": 0.84512111394795,
+  "best_model_checkpoint": "./save_models/mrpc/roberta-base_lr1e-05/checkpoint-117",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6839237057220708,
+      "eval_averaged_scores": 0.7481107201749513,
+      "eval_f1": 0.8122977346278317,
+      "eval_loss": 0.6196000576019287,
+      "eval_runtime": 0.9135,
+      "eval_samples_per_second": 401.752,
+      "eval_steps_per_second": 2.189,
+      "step": 13
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6839237057220708,
+      "eval_averaged_scores": 0.7481107201749513,
+      "eval_f1": 0.8122977346278317,
+      "eval_loss": 0.5717987418174744,
+      "eval_runtime": 0.9146,
+      "eval_samples_per_second": 401.283,
+      "eval_steps_per_second": 2.187,
+      "step": 26
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7084468664850136,
+      "eval_averaged_scores": 0.7630820363089463,
+      "eval_f1": 0.8177172061328791,
+      "eval_loss": 0.5101604461669922,
+      "eval_runtime": 0.9281,
+      "eval_samples_per_second": 395.44,
+      "eval_steps_per_second": 2.155,
+      "step": 39
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7956403269754768,
+      "eval_averaged_scores": 0.8287593900070754,
+      "eval_f1": 0.861878453038674,
+      "eval_loss": 0.45689526200294495,
+      "eval_runtime": 0.9188,
+      "eval_samples_per_second": 399.445,
+      "eval_steps_per_second": 2.177,
+      "step": 52
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.771117166212534,
+      "eval_averaged_scores": 0.7961968809786075,
+      "eval_f1": 0.8212765957446809,
+      "eval_loss": 0.42808404564857483,
+      "eval_runtime": 0.9515,
+      "eval_samples_per_second": 385.719,
+      "eval_steps_per_second": 2.102,
+      "step": 65
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8092643051771117,
+      "eval_averaged_scores": 0.8343510280905638,
+      "eval_f1": 0.859437751004016,
+      "eval_loss": 0.4162532687187195,
+      "eval_runtime": 0.9128,
+      "eval_samples_per_second": 402.06,
+      "eval_steps_per_second": 2.191,
+      "step": 78
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8147138964577657,
+      "eval_averaged_scores": 0.8396278645635442,
+      "eval_f1": 0.8645418326693227,
+      "eval_loss": 0.41786280274391174,
+      "eval_runtime": 1.0619,
+      "eval_samples_per_second": 345.592,
+      "eval_steps_per_second": 1.883,
+      "step": 91
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8065395095367848,
+      "eval_averaged_scores": 0.8318411833398209,
+      "eval_f1": 0.8571428571428572,
+      "eval_loss": 0.4168005883693695,
+      "eval_runtime": 0.9219,
+      "eval_samples_per_second": 398.082,
+      "eval_steps_per_second": 2.169,
+      "step": 104
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8201634877384196,
+      "eval_averaged_scores": 0.84512111394795,
+      "eval_f1": 0.8700787401574802,
+      "eval_loss": 0.42427295446395874,
+      "eval_runtime": 0.9217,
+      "eval_samples_per_second": 398.165,
+      "eval_steps_per_second": 2.17,
+      "step": 117
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8119891008174387,
+      "eval_averaged_scores": 0.8374060812238286,
+      "eval_f1": 0.8628230616302187,
+      "eval_loss": 0.42201152443885803,
+      "eval_runtime": 0.9117,
+      "eval_samples_per_second": 402.525,
+      "eval_steps_per_second": 2.194,
+      "step": 130
+    },
+    {
+      "epoch": 10.0,
+      "step": 130,
+      "total_flos": 1559281933489620.0,
+      "train_loss": 0.44359661982609677,
+      "train_runtime": 101.3918,
+      "train_samples_per_second": 325.569,
+      "train_steps_per_second": 1.282
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1559281933489620.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

mrpc/roberta-base_lr1e-05/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fb8fcbef58709b5e705f221664ef997ef46f14ce6b8dc733b9920fff974d97
+size 4283

qnli/roberta-base_lr1e-05/classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eee208e5b34fe5933f5d0cfbbef33e9201f6006392125f56a1688072321d398
+size 2371407

qnli/roberta-base_lr1e-05/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

qnli/roberta-base_lr1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7078cfa1ace53ce5e8d06a424de44b2fec65d327346db34b251df196bc9432ca
+size 498612824

qnli/roberta-base_lr1e-05/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>"
+}

qnli/roberta-base_lr1e-05/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>"
+}

qnli/roberta-base_lr1e-05/trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": 0.915035799522673,
+  "best_model_checkpoint": "./save_models/qnli/roberta-base_lr1e-05/checkpoint-2214",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8865871121718377,
+      "eval_loss": 0.28326648473739624,
+      "eval_runtime": 8.5588,
+      "eval_samples_per_second": 1223.884,
+      "eval_steps_per_second": 4.79,
+      "step": 369
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 9.198385236447522e-06,
+      "loss": 0.4241,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9020525059665871,
+      "eval_loss": 0.24534918367862701,
+      "eval_runtime": 8.5693,
+      "eval_samples_per_second": 1222.389,
+      "eval_steps_per_second": 4.785,
+      "step": 738
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 7.756632064590542e-06,
+      "loss": 0.2508,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9043436754176611,
+      "eval_loss": 0.2600307762622833,
+      "eval_runtime": 8.557,
+      "eval_samples_per_second": 1224.147,
+      "eval_steps_per_second": 4.791,
+      "step": 1107
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9120763723150358,
+      "eval_loss": 0.23106025159358978,
+      "eval_runtime": 8.5249,
+      "eval_samples_per_second": 1228.76,
+      "eval_steps_per_second": 4.809,
+      "step": 1476
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 6.314878892733565e-06,
+      "loss": 0.2044,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9064439140811456,
+      "eval_loss": 0.2730174660682678,
+      "eval_runtime": 8.491,
+      "eval_samples_per_second": 1233.666,
+      "eval_steps_per_second": 4.829,
+      "step": 1845
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 4.873125720876586e-06,
+      "loss": 0.1703,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.915035799522673,
+      "eval_loss": 0.2521490752696991,
+      "eval_runtime": 8.662,
+      "eval_samples_per_second": 1209.303,
+      "eval_steps_per_second": 4.733,
+      "step": 2214
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 3.431372549019608e-06,
+      "loss": 0.1503,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9115990453460621,
+      "eval_loss": 0.26341933012008667,
+      "eval_runtime": 8.515,
+      "eval_samples_per_second": 1230.176,
+      "eval_steps_per_second": 4.815,
+      "step": 2583
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9114081145584726,
+      "eval_loss": 0.2649821639060974,
+      "eval_runtime": 8.6484,
+      "eval_samples_per_second": 1211.201,
+      "eval_steps_per_second": 4.741,
+      "step": 2952
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 1.9896193771626298e-06,
+      "loss": 0.1338,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9138902147971361,
+      "eval_loss": 0.2706736922264099,
+      "eval_runtime": 8.5199,
+      "eval_samples_per_second": 1229.479,
+      "eval_steps_per_second": 4.812,
+      "step": 3321
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 5.478662053056517e-07,
+      "loss": 0.1216,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9143675417661098,
+      "eval_loss": 0.2753640413284302,
+      "eval_runtime": 8.4934,
+      "eval_samples_per_second": 1233.316,
+      "eval_steps_per_second": 4.827,
+      "step": 3690
+    },
+    {
+      "epoch": 10.0,
+      "step": 3690,
+      "total_flos": 6.001437167232744e+16,
+      "train_loss": 0.20311757839792144,
+      "train_runtime": 1451.9977,
+      "train_samples_per_second": 649.23,
+      "train_steps_per_second": 2.541
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.001437167232744e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

qnli/roberta-base_lr1e-05/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa18ae7a49399daaa388a810241480f86a86d0347e9005cbe9a492ed153797f
+size 4283

qqp/roberta-base_lr1e-05/classifier_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a4f879325b651c81b14593ad270283820f6f801b211aacac7dcad66e469042
+size 2371407

qqp/roberta-base_lr1e-05/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

qqp/roberta-base_lr1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cbaf169f4d2b46e5ac47e1e5ad45cedf24bc1ad219e3a20f7d4e694a77e7e7
+size 498612824

qqp/roberta-base_lr1e-05/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>"
+}

qqp/roberta-base_lr1e-05/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>"
+}

qqp/roberta-base_lr1e-05/trainer_state.json

@@ -0,0 +1,290 @@
+{
+  "best_metric": 0.8932172851340642,
+  "best_model_checkpoint": "./save_models/qqp/roberta-base_lr1e-05/checkpoint-12800",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 12800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.510416666666667e-06,
+      "loss": 0.488,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.807180851063832e-06,
+      "loss": 0.3263,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.879235948880033,
+      "eval_averaged_scores": 0.8598257175939353,
+      "eval_f1": 0.8404154863078377,
+      "eval_loss": 0.27544060349464417,
+      "eval_runtime": 30.2577,
+      "eval_samples_per_second": 1202.503,
+      "eval_steps_per_second": 4.726,
+      "step": 1280
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 9.391622340425532e-06,
+      "loss": 0.2866,
+      "step": 1500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.976063829787235e-06,
+      "loss": 0.2674,
+      "step": 2000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 8.560505319148937e-06,
+      "loss": 0.2554,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.891768585955751,
+      "eval_averaged_scores": 0.8743571206442515,
+      "eval_f1": 0.8569456553327521,
+      "eval_loss": 0.2498372197151184,
+      "eval_runtime": 27.6277,
+      "eval_samples_per_second": 1316.974,
+      "eval_steps_per_second": 5.176,
+      "step": 2560
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.144946808510639e-06,
+      "loss": 0.2339,
+      "step": 3000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 7.729388297872341e-06,
+      "loss": 0.2263,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8935825202693417,
+      "eval_averaged_scores": 0.8724041088244425,
+      "eval_f1": 0.8512256973795435,
+      "eval_loss": 0.2527249753475189,
+      "eval_runtime": 27.9,
+      "eval_samples_per_second": 1304.123,
+      "eval_steps_per_second": 5.125,
+      "step": 3840
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 7.313829787234044e-06,
+      "loss": 0.2159,
+      "step": 4000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.898271276595745e-06,
+      "loss": 0.2026,
+      "step": 4500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 6.482712765957447e-06,
+      "loss": 0.2011,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9005634189913426,
+      "eval_averaged_scores": 0.8845524747016884,
+      "eval_f1": 0.8685415304120341,
+      "eval_loss": 0.23971907794475555,
+      "eval_runtime": 27.6643,
+      "eval_samples_per_second": 1315.233,
+      "eval_steps_per_second": 5.169,
+      "step": 5120
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 6.06715425531915e-06,
+      "loss": 0.1871,
+      "step": 5500
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 5.651595744680851e-06,
+      "loss": 0.1803,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9041088360588154,
+      "eval_averaged_scores": 0.8878877207108364,
+      "eval_f1": 0.8716666053628573,
+      "eval_loss": 0.2404341995716095,
+      "eval_runtime": 27.871,
+      "eval_samples_per_second": 1305.48,
+      "eval_steps_per_second": 5.131,
+      "step": 6400
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 5.236037234042554e-06,
+      "loss": 0.1775,
+      "step": 6500
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 4.820478723404256e-06,
+      "loss": 0.1644,
+      "step": 7000
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 4.404920212765958e-06,
+      "loss": 0.1654,
+      "step": 7500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9068297375292016,
+      "eval_averaged_scores": 0.8913133079820112,
+      "eval_f1": 0.8757968784348208,
+      "eval_loss": 0.24361343681812286,
+      "eval_runtime": 28.0056,
+      "eval_samples_per_second": 1299.207,
+      "eval_steps_per_second": 5.106,
+      "step": 7680
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 3.98936170212766e-06,
+      "loss": 0.1527,
+      "step": 8000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 3.5738031914893617e-06,
+      "loss": 0.1519,
+      "step": 8500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9057303833997526,
+      "eval_averaged_scores": 0.8910411109500566,
+      "eval_f1": 0.8763518385003605,
+      "eval_loss": 0.24579738080501556,
+      "eval_runtime": 28.1352,
+      "eval_samples_per_second": 1293.219,
+      "eval_steps_per_second": 5.083,
+      "step": 8960
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 3.1582446808510644e-06,
+      "loss": 0.1534,
+      "step": 9000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 2.7426861702127662e-06,
+      "loss": 0.138,
+      "step": 9500
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 2.327127659574468e-06,
+      "loss": 0.1418,
+      "step": 10000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9066923182630204,
+      "eval_averaged_scores": 0.8916345948024302,
+      "eval_f1": 0.8765768713418401,
+      "eval_loss": 0.25888094305992126,
+      "eval_runtime": 27.7859,
+      "eval_samples_per_second": 1309.477,
+      "eval_steps_per_second": 5.146,
+      "step": 10240
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 1.9115691489361704e-06,
+      "loss": 0.1366,
+      "step": 10500
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 1.4960106382978725e-06,
+      "loss": 0.1307,
+      "step": 11000
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 1.0804521276595746e-06,
+      "loss": 0.1327,
+      "step": 11500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9079840593651229,
+      "eval_averaged_scores": 0.8931944703014327,
+      "eval_f1": 0.8784048812377424,
+      "eval_loss": 0.25855743885040283,
+      "eval_runtime": 27.685,
+      "eval_samples_per_second": 1314.247,
+      "eval_steps_per_second": 5.165,
+      "step": 11520
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 6.648936170212766e-07,
+      "loss": 0.1271,
+      "step": 12000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 2.4933510638297876e-07,
+      "loss": 0.1257,
+      "step": 12500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9080665109248317,
+      "eval_averaged_scores": 0.8932172851340642,
+      "eval_f1": 0.8783680593432966,
+      "eval_loss": 0.26402151584625244,
+      "eval_runtime": 28.0618,
+      "eval_samples_per_second": 1296.601,
+      "eval_steps_per_second": 5.096,
+      "step": 12800
+    },
+    {
+      "epoch": 10.0,
+      "step": 12800,
+      "total_flos": 1.5831238702432614e+17,
+      "train_loss": 0.1970924124121666,
+      "train_runtime": 4395.9489,
+      "train_samples_per_second": 744.915,
+      "train_steps_per_second": 2.912
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.5831238702432614e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

qqp/roberta-base_lr1e-05/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6b8a821e8661f87bc7947be53a5663c95a6097fed5039e0548c58e69105c9f
+size 4283