Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e23ba7e6a01947e1110b485a53afa57f07a9d2e17f35a044f4f9578e369115
+oid sha256:35b7b79ad7d628ee954291594a9c617d6f0042ff7ff358712495239061c1e8cb
 size 267832560

run-3/checkpoint-1070/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": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1325b144e673bc8c704ac594ed6a686faac301721deb7a7ce160c17f59a0c4aa
+size 267832560

run-3/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fef9fa81f9a474aed1f3a6bdcb13ae81532eed2c2265898974ed10ab429392
+size 535727290

run-3/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b1fdb9e2fa8c5a5da2db0687852f5f05e14f913960dc4bb4008cfc508b4d6d
+size 14308

run-3/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac922cde13cebd09a494231e46545dfb5fa8c69b7031eb000ec46ad56f00a6f9
+size 1064

run-3/checkpoint-1070/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-1070/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-1070/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.4998717031733986,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.447902679443359,
+      "learning_rate": 1.6748372574003986e-05,
+      "loss": 0.5233,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.51726233959198,
+      "eval_matthews_correlation": 0.3954714111531051,
+      "eval_runtime": 0.832,
+      "eval_samples_per_second": 1253.624,
+      "eval_steps_per_second": 79.328,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.607208251953125,
+      "learning_rate": 2.0568176845268055e-06,
+      "loss": 0.3131,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5029475688934326,
+      "eval_matthews_correlation": 0.4998717031733986,
+      "eval_runtime": 0.7988,
+      "eval_samples_per_second": 1305.636,
+      "eval_steps_per_second": 82.619,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 85092192859320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.143992746348117e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 29
+  }
+}

run-3/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ae918fb7e79815debd9294bc997f157b1a5d89758d8f836242669ec44a6fca
+size 4984

run-4/checkpoint-134/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": "4.38.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b7b79ad7d628ee954291594a9c617d6f0042ff7ff358712495239061c1e8cb
+size 267832560

run-4/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624c7d0678ee103872690eea9636756712f9c1352f32a056649a0c52d0bb9431
+size 535727290

run-4/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b229645b40fbde71bfefe569bc58bee6d1d10d8f74232c3f3372fca937d6d3
+size 14244

run-4/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b8f80f8d88a81e1c1d461e7e75d2259bb99880860ab571ad3113bd523146cb
+size 1064

run-4/checkpoint-134/special_tokens_map.json

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

run-4/checkpoint-134/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-4/checkpoint-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5651528239250183,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8455,
+      "eval_samples_per_second": 1233.59,
+      "eval_steps_per_second": 78.06,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 134,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0647254903827648e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 64,
+    "seed": 35
+  }
+}

run-4/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a12fdc24cb9dc9a62bc10545627abe46debf8706f86ab2fc532296984bfd9c9
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555004.6e5f088ca464.226.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727b13acc6d3a9714d0d4e22ad0fc867304cf6824756cab0d59d6790591379ce
+size 5279

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ae918fb7e79815debd9294bc997f157b1a5d89758d8f836242669ec44a6fca
+oid sha256:9a12fdc24cb9dc9a62bc10545627abe46debf8706f86ab2fc532296984bfd9c9
 size 4984