Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c8828f0c952bfd7e0f6b8752d6e727e74feecc165f92d15440c2af3875b4b72
+oid sha256:6cdf939b2a74df15ba8a2f38d403706c9df7d8ee88e0dda4ee5d196396602210
 size 498692800

run-4/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-4/checkpoint-1086/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1153289a1674f43eeb85c828a4ceba1e95d7b1e93ba7585e98d4f83f011ee8b2
+size 498692800

run-4/checkpoint-1086/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6227637809c8ef8a035c9fde4b56bf3b696af76481987547ff3d4ee326e30f41
+size 997505402

run-4/checkpoint-1086/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f52f8513935eb3865676e71bf092afc10241ed0fc168fe8438c7fc6e24a7b8
+size 14180

run-4/checkpoint-1086/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4107e12e8ab73f45c302c752439a266b6beaae1e1138572cdf428f255a3cc6
+size 1064

run-4/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-4/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-4/checkpoint-1086/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.2672811059907834,
+  "best_model_checkpoint": "roberta-base-finetuned/run-4/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": 1.3902820899164913e-05,
+      "loss": 0.1893,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.147831991314888,
+      "eval_runtime": 1.7652,
+      "eval_samples_per_second": 153.527,
+      "eval_steps_per_second": 1.133,
+      "step": 543
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.745681439835899e-06,
+      "loss": 0.1497,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.2672811059907834,
+      "eval_loss": 0.13674059510231018,
+      "eval_runtime": 1.7897,
+      "eval_samples_per_second": 151.42,
+      "eval_steps_per_second": 1.117,
+      "step": 1086
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1629,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 263040890689536.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.0059960358493927e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 10
+  }
+}

run-4/checkpoint-1086/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73598134a004473190ca9f7b811959bc6f9532139f5dfec3ec88c71441ee8644
+size 4600

run-4/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-4/checkpoint-1629/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cdf939b2a74df15ba8a2f38d403706c9df7d8ee88e0dda4ee5d196396602210
+size 498692800

run-4/checkpoint-1629/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078d46fef8b66eb9332145a30e193bcc83fd52e7e7dec2f7474b11bea5363704
+size 997505402

run-4/checkpoint-1629/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76956792489f1242706c1649399c4271467c4773d3c78cbfcee5771c3ca0c49
+size 14180

run-4/checkpoint-1629/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d947ab688e207895d757cc4c134b07bf08b35f1232094e9c5775190eaef585b7
+size 1064

run-4/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-4/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-4/checkpoint-1629/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.33486238532110096,
+  "best_model_checkpoint": "roberta-base-finetuned/run-4/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": 1.3902820899164913e-05,
+      "loss": 0.1893,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.147831991314888,
+      "eval_runtime": 1.7652,
+      "eval_samples_per_second": 153.527,
+      "eval_steps_per_second": 1.133,
+      "step": 543
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.745681439835899e-06,
+      "loss": 0.1497,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.2672811059907834,
+      "eval_loss": 0.13674059510231018,
+      "eval_runtime": 1.7897,
+      "eval_samples_per_second": 151.42,
+      "eval_steps_per_second": 1.117,
+      "step": 1086
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.5885419805068856e-06,
+      "loss": 0.1384,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.33486238532110096,
+      "eval_loss": 0.1311427801847458,
+      "eval_runtime": 1.7683,
+      "eval_samples_per_second": 153.259,
+      "eval_steps_per_second": 1.131,
+      "step": 1629
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1629,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 394495542915072.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.0059960358493927e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 10
+  }
+}

run-4/checkpoint-1629/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73598134a004473190ca9f7b811959bc6f9532139f5dfec3ec88c71441ee8644
+size 4600

runs/Dec01_22-15-05_9632749e57d1/events.out.tfevents.1701469675.9632749e57d1.10239.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fc06c189ba0c0df15852c2f58ace165e5d571adcfe6ef20097d2edadaa3ea1
-size 5895
+oid sha256:87ea41a0a890207a5b2d108c21d4d7f6dcbfe42be23559a384048c492d1e12bd
+size 7197