Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9341337fe75b4774a0ec41f29c999e21bf5b10b633c07b804a59a9b3102a1f
+oid sha256:4b60547a7940a2b5e2c26fbd77f1ef79d0d342325c626b31264d19ee163878f4
 size 267832560

run-2/checkpoint-28/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7299518973143069fe19a7dffdc6306cfc2f1bed81556be82e5bff05d7fddb
+size 267832560

run-2/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fa435a0188c06c701a1ca5723791871143993a1a01873052256852081fee03
+size 535727290

run-2/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc36f9eb920a6c89e2fa6d5af3217dfa8b6a4addb2fd9e3640535336f63d888
+size 14308

run-2/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af07b339bc1cfca233162a9f5abef3ba01fc9bf9fc6c735bc234a5d26229c29c
+size 1064

run-2/checkpoint-28/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-28/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6781402826309204,
+      "eval_matthews_correlation": 0.03026012901076368,
+      "eval_runtime": 0.7361,
+      "eval_samples_per_second": 1416.967,
+      "eval_steps_per_second": 89.664,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6716493368148804,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 1309.204,
+      "eval_steps_per_second": 82.845,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3629352837381431e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6da5ceb94a23f23fc8909247e2e94a7f4d8114e07c0d5ec21c7537a527fd94
+size 4984

run-2/checkpoint-42/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c180c7114b84412c3343a2d462e545467f74b8e26fc6f8d7558ed8d848187561
+size 267832560

run-2/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5495e258113c22e0600dd1408ccc92f59a858fc188367183257cd0b924b5c55e
+size 535727290

run-2/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4351b22bdcc61e76de8acd65d8fb65e5aa258557cf250f57ae4aace13f907a65
+size 14308

run-2/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4adae4c9465ab6e78b6736a0d02d4b0b07438b621181dcdaba6a98d839122a
+size 1064

run-2/checkpoint-42/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-42/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-28",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6781402826309204,
+      "eval_matthews_correlation": 0.03026012901076368,
+      "eval_runtime": 0.7361,
+      "eval_samples_per_second": 1416.967,
+      "eval_steps_per_second": 89.664,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6716493368148804,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 1309.204,
+      "eval_steps_per_second": 82.845,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6693518161773682,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 1335.149,
+      "eval_steps_per_second": 84.487,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3629352837381431e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 17
+  }
+}

run-2/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6da5ceb94a23f23fc8909247e2e94a7f4d8114e07c0d5ec21c7537a527fd94
+size 4984

run-3/checkpoint-54/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b60547a7940a2b5e2c26fbd77f1ef79d0d342325c626b31264d19ee163878f4
+size 267832560

run-3/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c559f5d555708e3d0c68d6bfd1c1e12afd9210cc0d594e9282557eeb95f63a63
+size 535727290

run-3/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a74ac3e4252a439bb91fbfbcf6b2c0960fb674021010d4ffa5db1893512fd83
+size 14244

run-3/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e04e5fe50904e9faaf902dd0cad94067e6ada77cb9836a84a2c592f57e075ae
+size 1064

run-3/checkpoint-54/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-54/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-54/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": -0.005611728519192225,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6924968957901001,
+      "eval_matthews_correlation": -0.005611728519192225,
+      "eval_runtime": 0.7923,
+      "eval_samples_per_second": 1316.385,
+      "eval_steps_per_second": 83.3,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.050736457234489e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-3/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da39f33b4bb8e4310e19df3a6352ef7a7c2649d8ebd43556efe5e99735f481d
+size 4984

runs/Feb27_13-15-48_39d530476097/events.out.tfevents.1709040462.39d530476097.262.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689ccf589ce3fa8706d22ba698432923fe6debd4c4c9314d374edc648b4c1643
+size 5548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6da5ceb94a23f23fc8909247e2e94a7f4d8114e07c0d5ec21c7537a527fd94
+oid sha256:2da39f33b4bb8e4310e19df3a6352ef7a7c2649d8ebd43556efe5e99735f481d
 size 4984