Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb01d1b073d7cfbf29b42e97eab0297437f2fc9cb8d8feaa8b706b044304141
+oid sha256:1fe3aaef1664168b504e33315f6633b7b596edf79c2dd00b22d443ce79dd297f
 size 267832560

run-0/checkpoint-8552/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-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53d93a78bc27857cbe44e73844a7a3315272ffa02fe351c0a449f38c90a9b30
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc947ca25c71c681d4dd6e16229cbee3e1eab8a957ff57f396f29378972db6f
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c655fdc7e737fd70140a9b80bf3ada85fd0d1f28ae93a4beec3658e0788ddc8
+size 14308

run-0/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ad863e4d53fc986a2a1985427cdc10813112beeb051ce95afcc1f000c8cb93
+size 1064

run-0/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": 0.5258663312307151,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "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
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.597180242541841e-06,
+      "loss": 0.284,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.4770096181408077e-06,
+      "loss": 0.1786,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.3568389937397744e-06,
+      "loss": 0.1405,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.2366683693387408e-06,
+      "loss": 0.2018,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.1649774493770747e-07,
+      "loss": 0.1787,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1422268152236938,
+      "eval_matthews_correlation": 0.5258663312307151,
+      "eval_runtime": 0.7488,
+      "eval_samples_per_second": 1392.867,
+      "eval_steps_per_second": 88.139,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 149325944938080.0,
+  "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-8552/training_args.bin

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

run-1/checkpoint-535/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-1/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe3aaef1664168b504e33315f6633b7b596edf79c2dd00b22d443ce79dd297f
+size 267832560

run-1/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2445a388e696a7730bd8b41d006bb738923aeb58447bc8b07cec514c5a7b9457
+size 535727290

run-1/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef104e2e0fc92f07429df53b0608736d2c27679bb32790be58be43a861f2b98c
+size 14244

run-1/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd5c115310ae2fec7557cbf4995e2ead87ea1843ff3e3576ace0a2585a5c585
+size 1064

run-1/checkpoint-535/special_tokens_map.json

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

run-1/checkpoint-535/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-1/checkpoint-535/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.4559278202620904,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8206261895616947e-05,
+      "loss": 0.5254,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4812505543231964,
+      "eval_matthews_correlation": 0.4559278202620904,
+      "eval_runtime": 0.73,
+      "eval_samples_per_second": 1428.785,
+      "eval_steps_per_second": 90.412,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 42935995589376.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.417666706721076e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 19
+  }
+}

run-1/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f24f981d79f17db058c213091fb3c5078f781cd40127f969745b1f0c26243ac
+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 sha256:3f4082687f00b9b81b3fd055f4eff9ed0bdb54e4a75a623a7387964f12ad09d3
-size 12612
+oid sha256:c553038bc18774e600c158338226716fdfff78fedd7c487eda2e1cf49cfbb071
+size 13772

runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298921.17d63b357dd6.603.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519d4f9af41a434e88e35b54efe01cdaafc331ce2d31bcf1b81523b256322b84
+size 5684

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9cc40459bd315d2cd00eaecc6a2c0666856322ff6f0db9d1b795484abcdc1d1
+oid sha256:9f24f981d79f17db058c213091fb3c5078f781cd40127f969745b1f0c26243ac
 size 4792