Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf7f59ed13b888a0489281dcc27320b6e23a655d73a6a8f0c88a019a914167e
+oid sha256:ecb01d1b073d7cfbf29b42e97eab0297437f2fc9cb8d8feaa8b706b044304141
 size 267832560

run-0/checkpoint-2138/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf1717faa0588d657568e0008f9c35bbe78ca17d777e38ad72fac16f7808733
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f43ff59dcff70e4d9994cc91108ec78cdfb5189439af68649b980dee42e1506
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9c3dbd56ab50aa725efcd873b25a87b7ea19a02c95e891164d94e916cd40cd
+size 14308

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8550babb889c60a2208502c337bece0466cbb1d9c7e3aaa6a83685e377b02b
+size 1064

run-0/checkpoint-2138/special_tokens_map.json

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

run-0/checkpoint-2138/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.4467807407096838,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803922773535424e-05,
+      "loss": 0.5874,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6919057110953206e-05,
+      "loss": 0.5524,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5798886486552175e-05,
+      "loss": 0.5657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.4678715862151142e-05,
+      "loss": 0.5372,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5069713592529297,
+      "eval_matthews_correlation": 0.4467807407096838,
+      "eval_runtime": 0.7552,
+      "eval_samples_per_second": 1381.121,
+      "eval_steps_per_second": 87.396,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 43331327982240.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9159398359755275e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cc40459bd315d2cd00eaecc6a2c0666856322ff6f0db9d1b795484abcdc1d1
+size 4792

run-0/checkpoint-4276/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52920e58aa91e0b805addec957d4fae9a6cf5f4780f65988bc3ba00718182a33
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8059ce801dc8c01f76f567a837b4fc45189b8e2c19bc356e891b8b813e6972f2
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4d744d63771944a923989dff8d29085f87e171ec694f475cdec1803c695dab
+size 14308

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ac96b9313a5a84310ab2fe4d32d08d4070b95ca67d0b3870afd4ea3b9d29d7
+size 1064

run-0/checkpoint-4276/special_tokens_map.json

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

run-0/checkpoint-4276/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.4507129896372791,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803922773535424e-05,
+      "loss": 0.5874,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6919057110953206e-05,
+      "loss": 0.5524,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5798886486552175e-05,
+      "loss": 0.5657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.4678715862151142e-05,
+      "loss": 0.5372,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5069713592529297,
+      "eval_matthews_correlation": 0.4467807407096838,
+      "eval_runtime": 0.7552,
+      "eval_samples_per_second": 1381.121,
+      "eval_steps_per_second": 87.396,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3558545237750109e-05,
+      "loss": 0.4356,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.2438374613349074e-05,
+      "loss": 0.483,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.131820398894804e-05,
+      "loss": 0.4814,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0198033364547007e-05,
+      "loss": 0.4779,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9718611240386963,
+      "eval_matthews_correlation": 0.4507129896372791,
+      "eval_runtime": 0.7395,
+      "eval_samples_per_second": 1410.379,
+      "eval_steps_per_second": 89.247,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 75899679823680.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9159398359755275e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cc40459bd315d2cd00eaecc6a2c0666856322ff6f0db9d1b795484abcdc1d1
+size 4792

run-0/checkpoint-6414/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb01d1b073d7cfbf29b42e97eab0297437f2fc9cb8d8feaa8b706b044304141
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ee8b9f4bfc1f7f29e03886c578cd2cf841d61d877a70c2b2c4309b226a91db
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3d585e762e2cfdfb3e76b64a04bc53bde6883d59ef217a829b611dc67b6acf
+size 14308

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fda6391bfdc59fc209d0d57ca40cd369bc421a827d568e109232c26a7afb08
+size 1064

run-0/checkpoint-6414/special_tokens_map.json

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

run-0/checkpoint-6414/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-0/checkpoint-6414/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.525313763068796,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803922773535424e-05,
+      "loss": 0.5874,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6919057110953206e-05,
+      "loss": 0.5524,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5798886486552175e-05,
+      "loss": 0.5657,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.4678715862151142e-05,
+      "loss": 0.5372,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5069713592529297,
+      "eval_matthews_correlation": 0.4467807407096838,
+      "eval_runtime": 0.7552,
+      "eval_samples_per_second": 1381.121,
+      "eval_steps_per_second": 87.396,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3558545237750109e-05,
+      "loss": 0.4356,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.2438374613349074e-05,
+      "loss": 0.483,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.131820398894804e-05,
+      "loss": 0.4814,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0198033364547007e-05,
+      "loss": 0.4779,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9718611240386963,
+      "eval_matthews_correlation": 0.4507129896372791,
+      "eval_runtime": 0.7395,
+      "eval_samples_per_second": 1410.379,
+      "eval_steps_per_second": 89.247,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.077862740145974e-06,
+      "loss": 0.3391,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 7.957692115744941e-06,
+      "loss": 0.2438,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 6.8375214913439076e-06,
+      "loss": 0.2754,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 5.717350866942874e-06,
+      "loss": 0.3313,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9164708852767944,
+      "eval_matthews_correlation": 0.525313763068796,
+      "eval_runtime": 0.7554,
+      "eval_samples_per_second": 1380.726,
+      "eval_steps_per_second": 87.371,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 108625077975636.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9159398359755275e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cc40459bd315d2cd00eaecc6a2c0666856322ff6f0db9d1b795484abcdc1d1
+size 4792

runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298345.17d63b357dd6.603.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8767921543efbbdc7915515d7d244adb5edeab776c3b4955c5d8d00b1f66e98e
-size 5151
+oid sha256:3f4082687f00b9b81b3fd055f4eff9ed0bdb54e4a75a623a7387964f12ad09d3
+size 12612

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47916063c9d08da0ea406bcd37dc65026cf97e4bfd39252c5a02963e5d083a2f
+oid sha256:a9cc40459bd315d2cd00eaecc6a2c0666856322ff6f0db9d1b795484abcdc1d1
 size 4792