Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9cfc40a69e124b74399e1454bae2ac31282de984d4eedd739c2d7a274c8b4eb
+oid sha256:b481d2a59e6ef9fb2aba7bf4cd5189e1f6a56ca1148e85be7dbfc262cff8b692
 size 498692800

run-2/checkpoint-272/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c1c3a94c1d64ced9feafe0c0a9ff2534be1c6e7cb0e2da6f1ba954c864e5a4
+oid sha256:0b46e339f93424117a6613f5d34c025a24e1858badd9d5d5b746a44b0f5a6793
 size 498692800

run-2/checkpoint-272/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b4ee002500dee293fb21de0138b8f67e2e6a8b6298d7ec60c38c1f99de707f
+oid sha256:873e2266063f63a5cb383e02d02fa053772d53c97c1439ef3f5ea555124fec11
 size 997505402

run-2/checkpoint-272/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb81777b8f7153326916c00944e123e7b0eafbbd400f5b200a643710e1a4d2c
+oid sha256:f835c9476d8d619a293ecce9b0856abf16983489434b4ada23df22abc91ee772
 size 14308

run-2/checkpoint-272/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20af819ca69d2ea01859a0057a2dfe88d4dabb05a34a78e90a91ae1680ea1069
+oid sha256:4423747469ae19bf4ea132909766d14aca0151db5dd1c6c2888db8c748dda6f6
 size 1064

run-2/checkpoint-272/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.0,
-  "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-136",
+  "best_metric": 0.26763990267639903,
+  "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-272",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 272,
@@ -11,32 +11,32 @@
     {
       "epoch": 1.0,
       "eval_f1": 0.0,
-      "eval_loss": 0.1484704464673996,
-      "eval_runtime": 1.7708,
-      "eval_samples_per_second": 153.038,
-      "eval_steps_per_second": 1.129,
+      "eval_loss": 0.14901714026927948,
+      "eval_runtime": 1.8968,
+      "eval_samples_per_second": 142.871,
+      "eval_steps_per_second": 1.054,
       "step": 136
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.0,
-      "eval_loss": 0.14706860482692719,
-      "eval_runtime": 1.7893,
-      "eval_samples_per_second": 151.458,
-      "eval_steps_per_second": 1.118,
+      "eval_f1": 0.26763990267639903,
+      "eval_loss": 0.13827788829803467,
+      "eval_runtime": 1.9156,
+      "eval_samples_per_second": 141.472,
+      "eval_steps_per_second": 1.044,
       "step": 272
     }
   ],
   "logging_steps": 500,
-  "max_steps": 680,
-  "num_train_epochs": 5,
+  "max_steps": 544,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.356363868064411e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.999322422094324e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 16,
-    "seed": 17
+    "seed": 31
   }
 }

run-2/checkpoint-272/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b4b571495d2d3af592eaa59e396bd9f2868fc92a95d7c44c370053edc46bc9
+oid sha256:478f5a631e389ceaab04cc59d49cfeb16dbccccc6cede957d93719a2804d5527
 size 4600

run-2/checkpoint-408/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97bf7a484c60a0beba653212d2b9d9a8a1d7dfa9c1b80e4ef4b0f228cffca75
+oid sha256:51c67704c4d902f9c2504e0a03bec3617a0c9e80f3ce10296bc9bd0cc63b7340
 size 498692800

run-2/checkpoint-408/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9157c1e3da0ff057f970b1585afe5d0d093a91b1216449fc77ccff58c1d74998
+oid sha256:4cf99dbb5d3db059884ea33689e3e7eaf7f8d69ef279c8f80cdbe92db33e575e
 size 997505402

run-2/checkpoint-408/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7972fb1c109e1b9f6df9c86c129050c9817577a740484d64fc1483c3d4db4369
+oid sha256:8f5866fa29142427585ab94c8ca1f1e15cb2fe96e03a359a2b1f2ac56a524d60
 size 14308

run-2/checkpoint-408/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7799256647b6bf87a8e05c626e74eba7f9737133cf71c1e16e2b74c05056c48b
+oid sha256:cc4118b342d4d1e42e7707d849f804ac329856e21bfe2eadcf91f9fd2214a02d
 size 1064

run-2/checkpoint-408/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.17079889807162535,
+  "best_metric": 0.33898305084745767,
   "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-408",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,41 +11,41 @@
     {
       "epoch": 1.0,
       "eval_f1": 0.0,
-      "eval_loss": 0.1484704464673996,
-      "eval_runtime": 1.7708,
-      "eval_samples_per_second": 153.038,
-      "eval_steps_per_second": 1.129,
+      "eval_loss": 0.14901714026927948,
+      "eval_runtime": 1.8968,
+      "eval_samples_per_second": 142.871,
+      "eval_steps_per_second": 1.054,
       "step": 136
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.0,
-      "eval_loss": 0.14706860482692719,
-      "eval_runtime": 1.7893,
-      "eval_samples_per_second": 151.458,
-      "eval_steps_per_second": 1.118,
+      "eval_f1": 0.26763990267639903,
+      "eval_loss": 0.13827788829803467,
+      "eval_runtime": 1.9156,
+      "eval_samples_per_second": 141.472,
+      "eval_steps_per_second": 1.044,
       "step": 272
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.17079889807162535,
-      "eval_loss": 0.13669927418231964,
-      "eval_runtime": 1.7608,
-      "eval_samples_per_second": 153.909,
-      "eval_steps_per_second": 1.136,
+      "eval_f1": 0.33898305084745767,
+      "eval_loss": 0.12684059143066406,
+      "eval_runtime": 1.8988,
+      "eval_samples_per_second": 142.721,
+      "eval_steps_per_second": 1.053,
       "step": 408
     }
   ],
   "logging_steps": 500,
-  "max_steps": 680,
-  "num_train_epochs": 5,
+  "max_steps": 544,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.356363868064411e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.999322422094324e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 16,
-    "seed": 17
+    "seed": 31
   }
 }

run-2/checkpoint-408/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b4b571495d2d3af592eaa59e396bd9f2868fc92a95d7c44c370053edc46bc9
+oid sha256:478f5a631e389ceaab04cc59d49cfeb16dbccccc6cede957d93719a2804d5527
 size 4600

run-2/checkpoint-544/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb546fb9d1d107141aa2e49308256faf48136cdcbfcb70a8a25a5a105d52523
+oid sha256:125565a86d838d44d48347046d3a3e9470bda27e3bb04eff713789bb1a113f7b
 size 498692800

run-2/checkpoint-544/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77424b132459b9ccfcf10fdbdf152692da50142cdb365159bfff0a6d1fc22fe5
+oid sha256:7ded4bcbab80684b1352005427759991b9aabf1d8de69e15f43bac85da7772cc
 size 997505402

run-2/checkpoint-544/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677e17b336143d1d9247c424ecb07d3e6d20a7032b8e6478c7a7032a58430331
+oid sha256:c2c1710153d93e71bf5ffb3bfe50b98424aa6777e66ff1426f7f597b30d66e0e
 size 14308

run-2/checkpoint-544/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97c03e638b62bd1ce0ee2ab739a2060b52ab45d7605fbd42405e9be0dd66cfe
+oid sha256:05dfdcb8cd0fd125409678dd5eb511bccdb190b9d23f1a0791f35f691811dbf3
 size 1064

run-2/checkpoint-544/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.31499999999999995,
+  "best_metric": 0.37122969837587005,
   "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-544",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -11,56 +11,56 @@
     {
       "epoch": 1.0,
       "eval_f1": 0.0,
-      "eval_loss": 0.1484704464673996,
-      "eval_runtime": 1.7708,
-      "eval_samples_per_second": 153.038,
-      "eval_steps_per_second": 1.129,
+      "eval_loss": 0.14901714026927948,
+      "eval_runtime": 1.8968,
+      "eval_samples_per_second": 142.871,
+      "eval_steps_per_second": 1.054,
       "step": 136
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.0,
-      "eval_loss": 0.14706860482692719,
-      "eval_runtime": 1.7893,
-      "eval_samples_per_second": 151.458,
-      "eval_steps_per_second": 1.118,
+      "eval_f1": 0.26763990267639903,
+      "eval_loss": 0.13827788829803467,
+      "eval_runtime": 1.9156,
+      "eval_samples_per_second": 141.472,
+      "eval_steps_per_second": 1.044,
       "step": 272
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.17079889807162535,
-      "eval_loss": 0.13669927418231964,
-      "eval_runtime": 1.7608,
-      "eval_samples_per_second": 153.909,
-      "eval_steps_per_second": 1.136,
+      "eval_f1": 0.33898305084745767,
+      "eval_loss": 0.12684059143066406,
+      "eval_runtime": 1.8988,
+      "eval_samples_per_second": 142.721,
+      "eval_steps_per_second": 1.053,
       "step": 408
     },
     {
       "epoch": 3.68,
-      "learning_rate": 1.417861023899403e-05,
-      "loss": 0.1602,
+      "learning_rate": 4.0435696061057036e-06,
+      "loss": 0.1582,
       "step": 500
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.31499999999999995,
-      "eval_loss": 0.12515465915203094,
-      "eval_runtime": 1.8296,
-      "eval_samples_per_second": 148.117,
-      "eval_steps_per_second": 1.093,
+      "eval_f1": 0.37122969837587005,
+      "eval_loss": 0.12343773245811462,
+      "eval_runtime": 1.9028,
+      "eval_samples_per_second": 142.425,
+      "eval_steps_per_second": 1.051,
       "step": 544
     }
   ],
   "logging_steps": 500,
-  "max_steps": 680,
-  "num_train_epochs": 5,
+  "max_steps": 544,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 525160677709824.0,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.356363868064411e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 4.999322422094324e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 16,
-    "seed": 17
+    "seed": 31
   }
 }

run-2/checkpoint-544/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b4b571495d2d3af592eaa59e396bd9f2868fc92a95d7c44c370053edc46bc9
+oid sha256:478f5a631e389ceaab04cc59d49cfeb16dbccccc6cede957d93719a2804d5527
 size 4600

run-3/checkpoint-1086/config.json

@@ -0,0 +1,87 @@
+{
+  "_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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-1086/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468160aece4fec7ee5735edf08ac220410b9383090a1751036ca720ccb84fb4a
+size 498692800

run-3/checkpoint-1086/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc9cbf55c78a7e27fd1a716f3cd488837ad4c8ee1f64705e6c79fa79149e0ca
+size 997505402

run-3/checkpoint-1086/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e788f0fc5814483b9ce396c33d231966503b4fba624ef1c134638d3079e160e7
+size 14244

run-3/checkpoint-1086/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db00b443230fcb0c2b486f874cbfd73f9c5e4dd40fe427ee1410063584610c3b
+size 1064

run-3/checkpoint-1086/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>"
+}

run-3/checkpoint-1086/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-1086/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.2677165354330709,
+  "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-1086",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1086,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2656891209426917e-05,
+      "loss": 0.1946,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.14112180471420288,
+      "eval_runtime": 1.88,
+      "eval_samples_per_second": 144.15,
+      "eval_steps_per_second": 1.064,
+      "step": 543
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.871935704215516e-06,
+      "loss": 0.1403,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.2677165354330709,
+      "eval_loss": 0.1291145235300064,
+      "eval_runtime": 1.9148,
+      "eval_samples_per_second": 141.528,
+      "eval_steps_per_second": 1.044,
+      "step": 1086
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2172,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 263040890689536.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6441846714638314e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 40
+  }
+}

run-3/checkpoint-1086/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a4c217dcde9602151e3e0480e1d005b395a60fc3831c12ee593721be3ea743
+size 4600

run-3/checkpoint-1629/config.json

@@ -0,0 +1,87 @@
+{
+  "_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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-1629/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1b9ef4d49251b901229a781a4c75487be1b19f3e4d25167427a16574de93cb
+size 498692800

run-3/checkpoint-1629/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5bb92f151e5c4a71d3d4c07f7d774a9f288e4770b107abbcb823184d7b3eb5
+size 997505402

run-3/checkpoint-1629/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b587a5684c5b51dcfe04a76f0bdbc0257602d2bc0fb2fc6e77db17847edcb6
+size 14244

run-3/checkpoint-1629/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a0f6d45d820e623cf3be7b85825366cb5a3e77a21036b34d1b97205d70fc8e
+size 1064

run-3/checkpoint-1629/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>"
+}

run-3/checkpoint-1629/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-1629/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.37986270022883295,
+  "best_model_checkpoint": "roberta-base-finetuned/run-3/checkpoint-1629",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1629,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2656891209426917e-05,
+      "loss": 0.1946,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.14112180471420288,
+      "eval_runtime": 1.88,
+      "eval_samples_per_second": 144.15,
+      "eval_steps_per_second": 1.064,
+      "step": 543
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.871935704215516e-06,
+      "loss": 0.1403,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.2677165354330709,
+      "eval_loss": 0.1291145235300064,
+      "eval_runtime": 1.9148,
+      "eval_samples_per_second": 141.528,
+      "eval_steps_per_second": 1.044,
+      "step": 1086
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 5.0869801990041196e-06,
+      "loss": 0.1261,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.37986270022883295,
+      "eval_loss": 0.11919566243886948,
+      "eval_runtime": 1.9044,
+      "eval_samples_per_second": 142.305,
+      "eval_steps_per_second": 1.05,
+      "step": 1629
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2172,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 394495542915072.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6441846714638314e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 40
+  }
+}

run-3/checkpoint-1629/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a4c217dcde9602151e3e0480e1d005b395a60fc3831c12ee593721be3ea743
+size 4600

run-3/checkpoint-2172/config.json

@@ -0,0 +1,87 @@
+{
+  "_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",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-2172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d668735f12266e3bb7b0cd4fcc8f86c31312c2541c2b3740896425886a7bb70d
+size 498692800

run-3/checkpoint-2172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5680f209dceab5b8c21d63df4ba97fcfac9e0a59715d7fa232079980191d1a5e
+size 997505402

run-3/checkpoint-2172/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af584f77cd7821d0223ca6a6026e5fc5dd84c80dde9950efaf5318e91d21ccc5
+size 14244

run-3/checkpoint-2172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6258e3e36e2c375c65995732dcd09049d813cad2fbdb76d6c3a91454376531d
+size 1064

run-3/checkpoint-2172/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>"
+}