Upload RoBERTa LIAR surrogate model

checkpoint-1280/config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-1280/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0d5b236dff28232bebe9bd286f4105e70498f8b17b6772c5100111789a9162
+size 498612800

checkpoint-1280/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b88bc6698fb6d8189331ae7482ca36edb0640adb406236a5237c4296211f0c
+size 997348747

checkpoint-1280/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a299e674aedbcb4b28be3cc84da6eca69c017eec0c59b83eee5043c60d5c49e1
+size 14645

checkpoint-1280/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2943c4c9e070ad7bbbbc5cf3564e0da64ba89b079a24bb0c3f2f65f0d92958
+size 1465

checkpoint-1280/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-1280/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_global_step": 1280,
+  "best_metric": 0.5727788279773157,
+  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-1280",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.4061976671218872,
+      "learning_rate": 1.485e-05,
+      "loss": 0.6982453918457031,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.2753427028656006,
+      "learning_rate": 2.985e-05,
+      "loss": 0.6896881866455078,
+      "step": 200
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 6.735152721405029,
+      "learning_rate": 2.8741525423728816e-05,
+      "loss": 0.683045654296875,
+      "step": 300
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.8760987520217896,
+      "learning_rate": 2.7470338983050847e-05,
+      "loss": 0.6780765533447266,
+      "step": 400
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 1.938730001449585,
+      "learning_rate": 2.6199152542372882e-05,
+      "loss": 0.6746772766113281,
+      "step": 500
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.237790584564209,
+      "learning_rate": 2.4927966101694917e-05,
+      "loss": 0.6706379699707031,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6082554517133957,
+      "eval_f1": 0.4830421377183967,
+      "eval_loss": 0.6857937574386597,
+      "eval_runtime": 9.9211,
+      "eval_samples_per_second": 129.421,
+      "eval_steps_per_second": 8.164,
+      "step": 640
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 2.4777538776397705,
+      "learning_rate": 2.365677966101695e-05,
+      "loss": 0.6513714599609375,
+      "step": 700
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.130825996398926,
+      "learning_rate": 2.2385593220338984e-05,
+      "loss": 0.6446173858642578,
+      "step": 800
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 5.078433513641357,
+      "learning_rate": 2.111440677966102e-05,
+      "loss": 0.6381737899780273,
+      "step": 900
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 4.769000053405762,
+      "learning_rate": 1.984322033898305e-05,
+      "loss": 0.6448619842529297,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 6.341429233551025,
+      "learning_rate": 1.8572033898305086e-05,
+      "loss": 0.6350166702270508,
+      "step": 1100
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 3.228231191635132,
+      "learning_rate": 1.730084745762712e-05,
+      "loss": 0.6343123626708984,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6479750778816199,
+      "eval_f1": 0.5727788279773157,
+      "eval_loss": 0.651949405670166,
+      "eval_runtime": 10.1237,
+      "eval_samples_per_second": 126.832,
+      "eval_steps_per_second": 8.001,
+      "step": 1280
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1347128603443200.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1280/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce7329f843c289211f742e393b21295cec5cc6e4683261510f17fb514adb81
+size 5265

checkpoint-1920/config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-1920/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43995c4222b3f2fa511640028e8e159ce0fba5c44287793a1e4f3fbb6331b934
+size 498612800

checkpoint-1920/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dcfaa60c270c5767ef410cf1dd326b2cf844aa130ebd74fd59c5eb4672f5f9
+size 997348747

checkpoint-1920/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7f2a6dc9c28b977bd4c5b62fc52d960a484bef8e37b2ece37eccf84abae3d8
+size 14645

checkpoint-1920/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f8aa29c2ba71c116cacecc945109b9f0318be3d83a2df15339e2e0e41de640
+size 1465

checkpoint-1920/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-1920/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_global_step": 1920,
+  "best_metric": 0.6441558441558441,
+  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-1920",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.4061976671218872,
+      "learning_rate": 1.485e-05,
+      "loss": 0.6982453918457031,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.2753427028656006,
+      "learning_rate": 2.985e-05,
+      "loss": 0.6896881866455078,
+      "step": 200
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 6.735152721405029,
+      "learning_rate": 2.8741525423728816e-05,
+      "loss": 0.683045654296875,
+      "step": 300
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.8760987520217896,
+      "learning_rate": 2.7470338983050847e-05,
+      "loss": 0.6780765533447266,
+      "step": 400
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 1.938730001449585,
+      "learning_rate": 2.6199152542372882e-05,
+      "loss": 0.6746772766113281,
+      "step": 500
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.237790584564209,
+      "learning_rate": 2.4927966101694917e-05,
+      "loss": 0.6706379699707031,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6082554517133957,
+      "eval_f1": 0.4830421377183967,
+      "eval_loss": 0.6857937574386597,
+      "eval_runtime": 9.9211,
+      "eval_samples_per_second": 129.421,
+      "eval_steps_per_second": 8.164,
+      "step": 640
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 2.4777538776397705,
+      "learning_rate": 2.365677966101695e-05,
+      "loss": 0.6513714599609375,
+      "step": 700
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.130825996398926,
+      "learning_rate": 2.2385593220338984e-05,
+      "loss": 0.6446173858642578,
+      "step": 800
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 5.078433513641357,
+      "learning_rate": 2.111440677966102e-05,
+      "loss": 0.6381737899780273,
+      "step": 900
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 4.769000053405762,
+      "learning_rate": 1.984322033898305e-05,
+      "loss": 0.6448619842529297,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 6.341429233551025,
+      "learning_rate": 1.8572033898305086e-05,
+      "loss": 0.6350166702270508,
+      "step": 1100
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 3.228231191635132,
+      "learning_rate": 1.730084745762712e-05,
+      "loss": 0.6343123626708984,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6479750778816199,
+      "eval_f1": 0.5727788279773157,
+      "eval_loss": 0.651949405670166,
+      "eval_runtime": 10.1237,
+      "eval_samples_per_second": 126.832,
+      "eval_steps_per_second": 8.001,
+      "step": 1280
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 10.572697639465332,
+      "learning_rate": 1.6029661016949153e-05,
+      "loss": 0.6261093521118164,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 7.916661739349365,
+      "learning_rate": 1.4758474576271186e-05,
+      "loss": 0.549117546081543,
+      "step": 1400
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 17.981098175048828,
+      "learning_rate": 1.348728813559322e-05,
+      "loss": 0.5534476089477539,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.362517833709717,
+      "learning_rate": 1.2216101694915255e-05,
+      "loss": 0.5808805465698242,
+      "step": 1600
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 11.875460624694824,
+      "learning_rate": 1.0944915254237288e-05,
+      "loss": 0.5447834014892579,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 18.079544067382812,
+      "learning_rate": 9.673728813559322e-06,
+      "loss": 0.542778205871582,
+      "step": 1800
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 5.842272758483887,
+      "learning_rate": 8.402542372881357e-06,
+      "loss": 0.5418962860107421,
+      "step": 1900
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6799065420560748,
+      "eval_f1": 0.6441558441558441,
+      "eval_loss": 0.6514966487884521,
+      "eval_runtime": 9.8829,
+      "eval_samples_per_second": 129.921,
+      "eval_steps_per_second": 8.196,
+      "step": 1920
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2020692905164800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1920/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce7329f843c289211f742e393b21295cec5cc6e4683261510f17fb514adb81
+size 5265

checkpoint-2560/config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-2560/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6491fbb0b9585fa02f155396328e9da88bf46042b955ad39e8caf45330f6b265
+size 498612800

checkpoint-2560/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b781189b274c921ea2781724bd7b02dd46b2f6ad4ecf7b66a42dfdf63719678d
+size 997348747

checkpoint-2560/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81bc53d8860350b112d790fdc5300468e019460a8d89b3b0fae6a3b3511ead8
+size 14645

checkpoint-2560/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df18367c60cedda4c838f8d9aa3316032455b35beaecbf8c55023baecaa0702
+size 1465

checkpoint-2560/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-2560/trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_global_step": 1920,
+  "best_metric": 0.6441558441558441,
+  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-1920",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.4061976671218872,
+      "learning_rate": 1.485e-05,
+      "loss": 0.6982453918457031,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.2753427028656006,
+      "learning_rate": 2.985e-05,
+      "loss": 0.6896881866455078,
+      "step": 200
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 6.735152721405029,
+      "learning_rate": 2.8741525423728816e-05,
+      "loss": 0.683045654296875,
+      "step": 300
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.8760987520217896,
+      "learning_rate": 2.7470338983050847e-05,
+      "loss": 0.6780765533447266,
+      "step": 400
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 1.938730001449585,
+      "learning_rate": 2.6199152542372882e-05,
+      "loss": 0.6746772766113281,
+      "step": 500
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.237790584564209,
+      "learning_rate": 2.4927966101694917e-05,
+      "loss": 0.6706379699707031,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6082554517133957,
+      "eval_f1": 0.4830421377183967,
+      "eval_loss": 0.6857937574386597,
+      "eval_runtime": 9.9211,
+      "eval_samples_per_second": 129.421,
+      "eval_steps_per_second": 8.164,
+      "step": 640
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 2.4777538776397705,
+      "learning_rate": 2.365677966101695e-05,
+      "loss": 0.6513714599609375,
+      "step": 700
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.130825996398926,
+      "learning_rate": 2.2385593220338984e-05,
+      "loss": 0.6446173858642578,
+      "step": 800
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 5.078433513641357,
+      "learning_rate": 2.111440677966102e-05,
+      "loss": 0.6381737899780273,
+      "step": 900
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 4.769000053405762,
+      "learning_rate": 1.984322033898305e-05,
+      "loss": 0.6448619842529297,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 6.341429233551025,
+      "learning_rate": 1.8572033898305086e-05,
+      "loss": 0.6350166702270508,
+      "step": 1100
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 3.228231191635132,
+      "learning_rate": 1.730084745762712e-05,
+      "loss": 0.6343123626708984,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6479750778816199,
+      "eval_f1": 0.5727788279773157,
+      "eval_loss": 0.651949405670166,
+      "eval_runtime": 10.1237,
+      "eval_samples_per_second": 126.832,
+      "eval_steps_per_second": 8.001,
+      "step": 1280
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 10.572697639465332,
+      "learning_rate": 1.6029661016949153e-05,
+      "loss": 0.6261093521118164,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 7.916661739349365,
+      "learning_rate": 1.4758474576271186e-05,
+      "loss": 0.549117546081543,
+      "step": 1400
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 17.981098175048828,
+      "learning_rate": 1.348728813559322e-05,
+      "loss": 0.5534476089477539,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.362517833709717,
+      "learning_rate": 1.2216101694915255e-05,
+      "loss": 0.5808805465698242,
+      "step": 1600
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 11.875460624694824,
+      "learning_rate": 1.0944915254237288e-05,
+      "loss": 0.5447834014892579,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 18.079544067382812,
+      "learning_rate": 9.673728813559322e-06,
+      "loss": 0.542778205871582,
+      "step": 1800
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 5.842272758483887,
+      "learning_rate": 8.402542372881357e-06,
+      "loss": 0.5418962860107421,
+      "step": 1900
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6799065420560748,
+      "eval_f1": 0.6441558441558441,
+      "eval_loss": 0.6514966487884521,
+      "eval_runtime": 9.8829,
+      "eval_samples_per_second": 129.921,
+      "eval_steps_per_second": 8.196,
+      "step": 1920
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 16.420164108276367,
+      "learning_rate": 7.13135593220339e-06,
+      "loss": 0.48551799774169924,
+      "step": 2000
+    },
+    {
+      "epoch": 3.28125,
+      "grad_norm": 15.341444969177246,
+      "learning_rate": 5.860169491525424e-06,
+      "loss": 0.4273301315307617,
+      "step": 2100
+    },
+    {
+      "epoch": 3.4375,
+      "grad_norm": 20.907245635986328,
+      "learning_rate": 4.588983050847458e-06,
+      "loss": 0.4307736587524414,
+      "step": 2200
+    },
+    {
+      "epoch": 3.59375,
+      "grad_norm": 17.784095764160156,
+      "learning_rate": 3.3177966101694917e-06,
+      "loss": 0.44722637176513674,
+      "step": 2300
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 15.452980995178223,
+      "learning_rate": 2.046610169491525e-06,
+      "loss": 0.4402835083007812,
+      "step": 2400
+    },
+    {
+      "epoch": 3.90625,
+      "grad_norm": 16.78668975830078,
+      "learning_rate": 7.754237288135593e-07,
+      "loss": 0.43862430572509764,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6612149532710281,
+      "eval_f1": 0.5975948196114709,
+      "eval_loss": 0.7282536625862122,
+      "eval_runtime": 9.8685,
+      "eval_samples_per_second": 130.111,
+      "eval_steps_per_second": 8.208,
+      "step": 2560
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2694257206886400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2560/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce7329f843c289211f742e393b21295cec5cc6e4683261510f17fb514adb81
+size 5265

checkpoint-640/config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-640/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b513afb7e7e777b21ba3b6449340ec154ea9f7f483e078f54d8dd8b5793bfb6
+size 498612800

checkpoint-640/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72827503960349e5e761f4df73e9ea0d7d612a7ce987758ed4a2e7b12cce0f4e
+size 997348747

checkpoint-640/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b7f8e832839949c04aa0123b9b52d54c2808e2ee898fe0be55ee62ca8bb3dc
+size 14645

checkpoint-640/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf6892d6b964ed70edf622c631a378608baf31423085f2aacae4d9dec076663
+size 1465

checkpoint-640/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-640/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_global_step": 640,
+  "best_metric": 0.4830421377183967,
+  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-640",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.4061976671218872,
+      "learning_rate": 1.485e-05,
+      "loss": 0.6982453918457031,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.2753427028656006,
+      "learning_rate": 2.985e-05,
+      "loss": 0.6896881866455078,
+      "step": 200
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 6.735152721405029,
+      "learning_rate": 2.8741525423728816e-05,
+      "loss": 0.683045654296875,
+      "step": 300
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.8760987520217896,
+      "learning_rate": 2.7470338983050847e-05,
+      "loss": 0.6780765533447266,
+      "step": 400
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 1.938730001449585,
+      "learning_rate": 2.6199152542372882e-05,
+      "loss": 0.6746772766113281,
+      "step": 500
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.237790584564209,
+      "learning_rate": 2.4927966101694917e-05,
+      "loss": 0.6706379699707031,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6082554517133957,
+      "eval_f1": 0.4830421377183967,
+      "eval_loss": 0.6857937574386597,
+      "eval_runtime": 9.9211,
+      "eval_samples_per_second": 129.421,
+      "eval_steps_per_second": 8.164,
+      "step": 640
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 673564301721600.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-640/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce7329f843c289211f742e393b21295cec5cc6e4683261510f17fb514adb81
+size 5265

config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3f97dd968736a8146ded02a384f456564b3b447132cc1fee1724450aabd408
+size 498612800

runs/Feb23_14-52-56_dc07af8eaf33/events.out.tfevents.1771858380.dc07af8eaf33.4128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a0a4b8acd6c28a401430571f099b0320f5907e28e6afc247c4ee52c9553e74
+size 5128

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce7329f843c289211f742e393b21295cec5cc6e4683261510f17fb514adb81
+size 5265