upload model

Roberta_constraint_2021

@@ -0,0 +1 @@
+Subproject commit f9b8fafc88ba775564b2d5ead1fb4b6e99b729f7

checkpoint-1206/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-1206/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11048198d49c43f2a0f789cd336b3959b7ef92cdfef9eb86de1afd4886c5cdea
+size 498612800

checkpoint-1206/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b7c771413fb65d5d9c64c753cd7ca7a34c21809ded7c4c7052515345f30438
+size 997348747

checkpoint-1206/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61c1dbaa830424f57cd4cb76d2741cd386fe98971a6c1a76d442d402d3248dc
+size 14645

checkpoint-1206/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5fe909c1a5b889c774ad8e6e18388760484ac3a2e0af66c3df8a09ce4dac46
+size 1465

checkpoint-1206/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-1206/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 804,
+  "best_metric": 0.9697508896797153,
+  "best_model_checkpoint": "/content/drive/MyDrive/adv_gen/02_Models/Surrogates/RoBERTa_Constraint2021/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1206,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 12.755484580993652,
+      "learning_rate": 1.485e-05,
+      "loss": 0.5675763320922852,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 20.837379455566406,
+      "learning_rate": 2.985e-05,
+      "loss": 0.28434215545654296,
+      "step": 200
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.7691614627838135,
+      "learning_rate": 2.7890625000000002e-05,
+      "loss": 0.16768863677978516,
+      "step": 300
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 19.097896575927734,
+      "learning_rate": 2.575994318181818e-05,
+      "loss": 0.19632043838500976,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9485981308411215,
+      "eval_f1": 0.9526678141135972,
+      "eval_loss": 0.23201586306095123,
+      "eval_runtime": 14.1506,
+      "eval_samples_per_second": 151.23,
+      "eval_steps_per_second": 9.47,
+      "step": 402
+    },
+    {
+      "epoch": 1.243781094527363,
+      "grad_norm": 41.2952880859375,
+      "learning_rate": 2.3629261363636365e-05,
+      "loss": 0.11888823509216309,
+      "step": 500
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 6.743992328643799,
+      "learning_rate": 2.1498579545454548e-05,
+      "loss": 0.10398503303527833,
+      "step": 600
+    },
+    {
+      "epoch": 1.7412935323383083,
+      "grad_norm": 0.04455677047371864,
+      "learning_rate": 1.9367897727272727e-05,
+      "loss": 0.13183796882629395,
+      "step": 700
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 25.297327041625977,
+      "learning_rate": 1.723721590909091e-05,
+      "loss": 0.09564775466918946,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9682242990654205,
+      "eval_f1": 0.9697508896797153,
+      "eval_loss": 0.14717483520507812,
+      "eval_runtime": 14.1045,
+      "eval_samples_per_second": 151.725,
+      "eval_steps_per_second": 9.501,
+      "step": 804
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 0.056198760867118835,
+      "learning_rate": 1.5106534090909092e-05,
+      "loss": 0.07061147212982177,
+      "step": 900
+    },
+    {
+      "epoch": 2.487562189054726,
+      "grad_norm": 0.029216887429356575,
+      "learning_rate": 1.2975852272727275e-05,
+      "loss": 0.051020784378051756,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7363184079601988,
+      "grad_norm": 0.06548340618610382,
+      "learning_rate": 1.0845170454545454e-05,
+      "loss": 0.041219482421875,
+      "step": 1100
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.07763787358999252,
+      "learning_rate": 8.714488636363636e-06,
+      "loss": 0.023678507804870606,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9649532710280374,
+      "eval_f1": 0.9673771204871683,
+      "eval_loss": 0.20711995661258698,
+      "eval_runtime": 14.1306,
+      "eval_samples_per_second": 151.445,
+      "eval_steps_per_second": 9.483,
+      "step": 1206
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1608,
+  "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": 1266879731558400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1206/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b393afc515b0ea5ded0feb1055896f807d0df51df646cb449c6a8dec0aaf75d
+size 5265

checkpoint-1608/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-1608/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bb17f346c8cbbcc13d0f695b1c7b44b70bb40d1a31c4cb27c3f606829ee79a
+size 498612800

checkpoint-1608/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a191fb24236fda3120a1402f87a4a417ccffb0bac02c7f353ae5675e318720
+size 997348747

checkpoint-1608/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bed34cd434519d37d7dd407d3c29d2b73c240a89000bc9a8db7ceeed9fffeb
+size 14645

checkpoint-1608/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcfb3640dc021c9cf47eae4c38a5f63813c23cbe4e368432158645d119c33e9
+size 1465

checkpoint-1608/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-1608/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_global_step": 1608,
+  "best_metric": 0.9739053516143299,
+  "best_model_checkpoint": "/content/drive/MyDrive/adv_gen/02_Models/Surrogates/RoBERTa_Constraint2021/checkpoint-1608",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1608,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 12.755484580993652,
+      "learning_rate": 1.485e-05,
+      "loss": 0.5675763320922852,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 20.837379455566406,
+      "learning_rate": 2.985e-05,
+      "loss": 0.28434215545654296,
+      "step": 200
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.7691614627838135,
+      "learning_rate": 2.7890625000000002e-05,
+      "loss": 0.16768863677978516,
+      "step": 300
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 19.097896575927734,
+      "learning_rate": 2.575994318181818e-05,
+      "loss": 0.19632043838500976,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9485981308411215,
+      "eval_f1": 0.9526678141135972,
+      "eval_loss": 0.23201586306095123,
+      "eval_runtime": 14.1506,
+      "eval_samples_per_second": 151.23,
+      "eval_steps_per_second": 9.47,
+      "step": 402
+    },
+    {
+      "epoch": 1.243781094527363,
+      "grad_norm": 41.2952880859375,
+      "learning_rate": 2.3629261363636365e-05,
+      "loss": 0.11888823509216309,
+      "step": 500
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 6.743992328643799,
+      "learning_rate": 2.1498579545454548e-05,
+      "loss": 0.10398503303527833,
+      "step": 600
+    },
+    {
+      "epoch": 1.7412935323383083,
+      "grad_norm": 0.04455677047371864,
+      "learning_rate": 1.9367897727272727e-05,
+      "loss": 0.13183796882629395,
+      "step": 700
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 25.297327041625977,
+      "learning_rate": 1.723721590909091e-05,
+      "loss": 0.09564775466918946,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9682242990654205,
+      "eval_f1": 0.9697508896797153,
+      "eval_loss": 0.14717483520507812,
+      "eval_runtime": 14.1045,
+      "eval_samples_per_second": 151.725,
+      "eval_steps_per_second": 9.501,
+      "step": 804
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 0.056198760867118835,
+      "learning_rate": 1.5106534090909092e-05,
+      "loss": 0.07061147212982177,
+      "step": 900
+    },
+    {
+      "epoch": 2.487562189054726,
+      "grad_norm": 0.029216887429356575,
+      "learning_rate": 1.2975852272727275e-05,
+      "loss": 0.051020784378051756,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7363184079601988,
+      "grad_norm": 0.06548340618610382,
+      "learning_rate": 1.0845170454545454e-05,
+      "loss": 0.041219482421875,
+      "step": 1100
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.07763787358999252,
+      "learning_rate": 8.714488636363636e-06,
+      "loss": 0.023678507804870606,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9649532710280374,
+      "eval_f1": 0.9673771204871683,
+      "eval_loss": 0.20711995661258698,
+      "eval_runtime": 14.1306,
+      "eval_samples_per_second": 151.445,
+      "eval_steps_per_second": 9.483,
+      "step": 1206
+    },
+    {
+      "epoch": 3.2338308457711444,
+      "grad_norm": 0.006905850488692522,
+      "learning_rate": 6.5838068181818185e-06,
+      "loss": 0.006628125905990601,
+      "step": 1300
+    },
+    {
+      "epoch": 3.482587064676617,
+      "grad_norm": 0.0073797982186079025,
+      "learning_rate": 4.453125e-06,
+      "loss": 0.022305617332458495,
+      "step": 1400
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 0.2881132960319519,
+      "learning_rate": 2.3224431818181816e-06,
+      "loss": 0.020951387882232667,
+      "step": 1500
+    },
+    {
+      "epoch": 3.9800995024875623,
+      "grad_norm": 0.00679817283526063,
+      "learning_rate": 1.9176136363636366e-07,
+      "loss": 0.01815043807029724,
+      "step": 1600
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9724299065420561,
+      "eval_f1": 0.9739053516143299,
+      "eval_loss": 0.1720760464668274,
+      "eval_runtime": 14.1271,
+      "eval_samples_per_second": 151.482,
+      "eval_steps_per_second": 9.485,
+      "step": 1608
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1608,
+  "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": 1689172975411200.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1608/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b393afc515b0ea5ded0feb1055896f807d0df51df646cb449c6a8dec0aaf75d
+size 5265

checkpoint-402/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-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a765daa52fa437326719c8a1f95de12c4856d5bd0605ca37c8e70c78596c6db
+size 498612800

checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2dbfc706503297a8a97b722589d634360b672960288aa3c9d389fe7f186b2d4
+size 997348747

checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c52bd9544d61f09beb9d0f7f3a5c220a3d51e486657b9f379f42ebaa6f1004
+size 14645

checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cbbe4f4f50de494c1c5d26516eb6cb926416f16c1ad59177324598ac44caa5
+size 1465

checkpoint-402/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-402/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_global_step": 402,
+  "best_metric": 0.9526678141135972,
+  "best_model_checkpoint": "/content/drive/MyDrive/adv_gen/02_Models/Surrogates/RoBERTa_Constraint2021/checkpoint-402",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 402,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 12.755484580993652,
+      "learning_rate": 1.485e-05,
+      "loss": 0.5675763320922852,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 20.837379455566406,
+      "learning_rate": 2.985e-05,
+      "loss": 0.28434215545654296,
+      "step": 200
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.7691614627838135,
+      "learning_rate": 2.7890625000000002e-05,
+      "loss": 0.16768863677978516,
+      "step": 300
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 19.097896575927734,
+      "learning_rate": 2.575994318181818e-05,
+      "loss": 0.19632043838500976,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9485981308411215,
+      "eval_f1": 0.9526678141135972,
+      "eval_loss": 0.23201586306095123,
+      "eval_runtime": 14.1506,
+      "eval_samples_per_second": 151.23,
+      "eval_steps_per_second": 9.47,
+      "step": 402
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1608,
+  "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": 422293243852800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b393afc515b0ea5ded0feb1055896f807d0df51df646cb449c6a8dec0aaf75d
+size 5265

checkpoint-804/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-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d16fddbdf5cdd56bcb90553a061a517c955088fcca04971ec4ca269b098821a
+size 498612800

checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8bfff1e7fb652490b2042bbdec03ea2c832e2c0b6965e67e233f754dd548eb
+size 997348747

checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d0f09a11f9e8dd80f3aba8eb2c55dccfe3349a4b5d46bbc7c0e3fded9178bf
+size 14645

checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e72ef5d9798666984e3ebdc9f772660601a459b156c1cb89be7539f0bdd7de
+size 1465

checkpoint-804/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-804/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_global_step": 804,
+  "best_metric": 0.9697508896797153,
+  "best_model_checkpoint": "/content/drive/MyDrive/adv_gen/02_Models/Surrogates/RoBERTa_Constraint2021/checkpoint-804",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 12.755484580993652,
+      "learning_rate": 1.485e-05,
+      "loss": 0.5675763320922852,
+      "step": 100
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 20.837379455566406,
+      "learning_rate": 2.985e-05,
+      "loss": 0.28434215545654296,
+      "step": 200
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.7691614627838135,
+      "learning_rate": 2.7890625000000002e-05,
+      "loss": 0.16768863677978516,
+      "step": 300
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 19.097896575927734,
+      "learning_rate": 2.575994318181818e-05,
+      "loss": 0.19632043838500976,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9485981308411215,
+      "eval_f1": 0.9526678141135972,
+      "eval_loss": 0.23201586306095123,
+      "eval_runtime": 14.1506,
+      "eval_samples_per_second": 151.23,
+      "eval_steps_per_second": 9.47,
+      "step": 402
+    },
+    {
+      "epoch": 1.243781094527363,
+      "grad_norm": 41.2952880859375,
+      "learning_rate": 2.3629261363636365e-05,
+      "loss": 0.11888823509216309,
+      "step": 500
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 6.743992328643799,
+      "learning_rate": 2.1498579545454548e-05,
+      "loss": 0.10398503303527833,
+      "step": 600
+    },
+    {
+      "epoch": 1.7412935323383083,
+      "grad_norm": 0.04455677047371864,
+      "learning_rate": 1.9367897727272727e-05,
+      "loss": 0.13183796882629395,
+      "step": 700
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 25.297327041625977,
+      "learning_rate": 1.723721590909091e-05,
+      "loss": 0.09564775466918946,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9682242990654205,
+      "eval_f1": 0.9697508896797153,
+      "eval_loss": 0.14717483520507812,
+      "eval_runtime": 14.1045,
+      "eval_samples_per_second": 151.725,
+      "eval_steps_per_second": 9.501,
+      "step": 804
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1608,
+  "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": 844586487705600.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b393afc515b0ea5ded0feb1055896f807d0df51df646cb449c6a8dec0aaf75d
+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 sha256:43bb17f346c8cbbcc13d0f695b1c7b44b70bb40d1a31c4cb27c3f606829ee79a
+size 498612800

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 sha256:5b393afc515b0ea5ded0feb1055896f807d0df51df646cb449c6a8dec0aaf75d
+size 5265