Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17adbea14ecbcf6a9bfe1ed44cd6b3671e13e14f3eaffca8ea02fdad14c6c0ec
+oid sha256:3ce20cc9615e6a8fa8f7c042a6053a55ca2e1afb1d89eae96292d9bd5d53bc02
 size 498692800

run-2/checkpoint-1088/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-2/checkpoint-1088/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1a16b5374370cc006f6486f12a0754f3b69c3a01cc1599b9a35d9895dbd2e2
+size 498692800

run-2/checkpoint-1088/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51c93e5854fb869dbf0dbe9206f0b54d797fff4fe05ead0426f4c9256052714
+size 997505402

run-2/checkpoint-1088/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3faf913fa0ad77d3972295a8c6854f979ff888732e7c6f55572fadf20dbddcf7
+size 14244

run-2/checkpoint-1088/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9063f095c6f95be3bcce64886fc78ae8de8e96c66f02e483c1e3b3cbb9c0423
+size 1064

run-2/checkpoint-1088/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-2/checkpoint-1088/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-2/checkpoint-1088/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.44638949671772427,
+  "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-1088",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1088,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.14686410129070282,
+      "eval_runtime": 1.7545,
+      "eval_samples_per_second": 154.456,
+      "eval_steps_per_second": 1.14,
+      "step": 272
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.1942744706258144e-05,
+      "loss": 0.1695,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.36888888888888893,
+      "eval_loss": 0.1315886378288269,
+      "eval_runtime": 1.7708,
+      "eval_samples_per_second": 153.041,
+      "eval_steps_per_second": 1.129,
+      "step": 544
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.3105263157894737,
+      "eval_loss": 0.11998622119426727,
+      "eval_runtime": 1.7637,
+      "eval_samples_per_second": 153.651,
+      "eval_steps_per_second": 1.134,
+      "step": 816
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 9.185334993317363e-06,
+      "loss": 0.1238,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.44638949671772427,
+      "eval_loss": 0.11326660960912704,
+      "eval_runtime": 1.7653,
+      "eval_samples_per_second": 153.518,
+      "eval_steps_per_second": 1.133,
+      "step": 1088
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1360,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 525160677709824.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.470015441919893e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 7
+  }
+}

run-2/checkpoint-1088/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7290d20858275a66442eaed93c05ae857c34a03bf3647ee7d3dfed18744afe18
+size 4600

run-2/checkpoint-1360/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-2/checkpoint-1360/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce20cc9615e6a8fa8f7c042a6053a55ca2e1afb1d89eae96292d9bd5d53bc02
+size 498692800

run-2/checkpoint-1360/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6677d537ee85abd1438639a11ac2ed7174a8702456182b23e0b78a8eab3c1182
+size 997505402

run-2/checkpoint-1360/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4e168f4fbb3e4bf180de743900e4d8b4d24724ecc4aebf1cc052a9bdc7290f
+size 14244

run-2/checkpoint-1360/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1901f87afdadabea7b7809542c1632544e3e1fe32a98363b2d42c7792a4e51
+size 1064

run-2/checkpoint-1360/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-2/checkpoint-1360/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-2/checkpoint-1360/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.46724890829694316,
+  "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-1360",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1360,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.14686410129070282,
+      "eval_runtime": 1.7545,
+      "eval_samples_per_second": 154.456,
+      "eval_steps_per_second": 1.14,
+      "step": 272
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.1942744706258144e-05,
+      "loss": 0.1695,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.36888888888888893,
+      "eval_loss": 0.1315886378288269,
+      "eval_runtime": 1.7708,
+      "eval_samples_per_second": 153.041,
+      "eval_steps_per_second": 1.129,
+      "step": 544
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.3105263157894737,
+      "eval_loss": 0.11998622119426727,
+      "eval_runtime": 1.7637,
+      "eval_samples_per_second": 153.651,
+      "eval_steps_per_second": 1.134,
+      "step": 816
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 9.185334993317363e-06,
+      "loss": 0.1238,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.44638949671772427,
+      "eval_loss": 0.11326660960912704,
+      "eval_runtime": 1.7653,
+      "eval_samples_per_second": 153.518,
+      "eval_steps_per_second": 1.133,
+      "step": 1088
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.46724890829694316,
+      "eval_loss": 0.1113906130194664,
+      "eval_runtime": 1.761,
+      "eval_samples_per_second": 153.893,
+      "eval_steps_per_second": 1.136,
+      "step": 1360
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1360,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 525160677709824.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.470015441919893e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 7
+  }
+}

run-2/checkpoint-1360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7290d20858275a66442eaed93c05ae857c34a03bf3647ee7d3dfed18744afe18
+size 4600

run-2/checkpoint-544/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125565a86d838d44d48347046d3a3e9470bda27e3bb04eff713789bb1a113f7b
+oid sha256:de2a314f7db0374ba30fcde1d941e574a004d3419c17a9e40ed8fda104719644
 size 498692800

run-2/checkpoint-544/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ded4bcbab80684b1352005427759991b9aabf1d8de69e15f43bac85da7772cc
+oid sha256:7a11fcc5bb2beac1122f3a18c6be6c4b1113b80f0ab3b880fea9a8763fc709a7
 size 997505402

run-2/checkpoint-544/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c1710153d93e71bf5ffb3bfe50b98424aa6777e66ff1426f7f597b30d66e0e
-size 14308
+oid sha256:72f131295a7879e4d7d11dfeeb3f1b3700af2b3cabdd238e5c497b28bf924ac2
+size 14244

run-2/checkpoint-544/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dfdcb8cd0fd125409678dd5eb511bccdb190b9d23f1a0791f35f691811dbf3
+oid sha256:9450f0a9c73b3be74565c2e9defcb5f8ca11179d3fd62c7909ef00f625b46f22
 size 1064

run-2/checkpoint-544/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.37122969837587005,
+  "best_metric": 0.36888888888888893,
   "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-544",
-  "epoch": 4.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 544,
   "is_hyper_param_search": true,
@@ -11,56 +11,38 @@
     {
       "epoch": 1.0,
       "eval_f1": 0.0,
-      "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": 0.26763990267639903,
-      "eval_loss": 0.13827788829803467,
-      "eval_runtime": 1.9156,
-      "eval_samples_per_second": 141.472,
-      "eval_steps_per_second": 1.044,
+      "eval_loss": 0.14686410129070282,
+      "eval_runtime": 1.7545,
+      "eval_samples_per_second": 154.456,
+      "eval_steps_per_second": 1.14,
       "step": 272
     },
     {
-      "epoch": 3.0,
-      "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": 4.0435696061057036e-06,
-      "loss": 0.1582,
+      "epoch": 1.84,
+      "learning_rate": 2.1942744706258144e-05,
+      "loss": 0.1695,
       "step": 500
     },
     {
-      "epoch": 4.0,
-      "eval_f1": 0.37122969837587005,
-      "eval_loss": 0.12343773245811462,
-      "eval_runtime": 1.9028,
-      "eval_samples_per_second": 142.425,
-      "eval_steps_per_second": 1.051,
+      "epoch": 2.0,
+      "eval_f1": 0.36888888888888893,
+      "eval_loss": 0.1315886378288269,
+      "eval_runtime": 1.7708,
+      "eval_samples_per_second": 153.041,
+      "eval_steps_per_second": 1.129,
       "step": 544
     }
   ],
   "logging_steps": 500,
-  "max_steps": 544,
-  "num_train_epochs": 4,
+  "max_steps": 1360,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 525160677709824.0,
+  "total_flos": 262777718212608.0,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.999322422094324e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 16,
-    "seed": 31
+    "learning_rate": 3.470015441919893e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 7
   }
 }

run-2/checkpoint-544/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478f5a631e389ceaab04cc59d49cfeb16dbccccc6cede957d93719a2804d5527
+oid sha256:7290d20858275a66442eaed93c05ae857c34a03bf3647ee7d3dfed18744afe18
 size 4600

run-2/checkpoint-816/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-2/checkpoint-816/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6232081fecb2417673b5387ee455e8e2b35cdee183ffb3ef4af67a81b5b0a200
+size 498692800

run-2/checkpoint-816/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054e606ece42635472b56148ee7e2d04b3d1f34b15682697240fa9073aaa8790
+size 997505402

run-2/checkpoint-816/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6183a9480bd464db77ab7f1b19a48b4d0b91e3d9322ab284e1b034b3d90c5734
+size 14244

run-2/checkpoint-816/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0ae7215f3d93c636200421112d82a94386aa5a09f3c2830d830ab623cbef97
+size 1064

run-2/checkpoint-816/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-2/checkpoint-816/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-2/checkpoint-816/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.36888888888888893,
+  "best_model_checkpoint": "roberta-base-finetuned/run-2/checkpoint-544",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 816,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.14686410129070282,
+      "eval_runtime": 1.7545,
+      "eval_samples_per_second": 154.456,
+      "eval_steps_per_second": 1.14,
+      "step": 272
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.1942744706258144e-05,
+      "loss": 0.1695,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.36888888888888893,
+      "eval_loss": 0.1315886378288269,
+      "eval_runtime": 1.7708,
+      "eval_samples_per_second": 153.041,
+      "eval_steps_per_second": 1.129,
+      "step": 544
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.3105263157894737,
+      "eval_loss": 0.11998622119426727,
+      "eval_runtime": 1.7637,
+      "eval_samples_per_second": 153.651,
+      "eval_steps_per_second": 1.134,
+      "step": 816
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1360,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 262777718212608.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.470015441919893e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 7
+  }
+}

run-2/checkpoint-816/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7290d20858275a66442eaed93c05ae857c34a03bf3647ee7d3dfed18744afe18
+size 4600

runs/Dec02_03-40-52_bab1a73aa7e5/events.out.tfevents.1701488785.bab1a73aa7e5.959.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f73561129601bcf7b108e3ed4a5b2b763a5981bf3545fb1e19ef2221fad6ec4
-size 5736
+oid sha256:e62adee9bf2f7b90d1f819b5032f974a2f8db613ef29a0243342b3aea3e82404
+size 7672