Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945826e2756aee187ff6d9bdd54154b39351f77603e0170a083bc3c49be4ee68
+oid sha256:41163830d68c0c71e3d9e102767b6e13952332322e1a89db2f939c410a4d7099
 size 267832560

run-1/checkpoint-1072/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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1402dcc1a9ea22b48cf3678b18d6951fa650c0a1abcbdb78851001f2e57e5684
+size 267832560

run-1/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f59b3cca6548a79c47d82a0ccc726e3efc9117974e48cd30348e502599ae4f
+size 535727290

run-1/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb759deb6668166ad5e7f05d892e3ecfaf9feca83f38a2bee6fa5a21a732911
+size 14244

run-1/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12fcb7d20e914aced25dfedb2e8cc97640fb4986601ab9ad72a7518268a1cfe
+size 1064

run-1/checkpoint-1072/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-1072/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-1072/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.5290831606897504,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4801884889602661,
+      "eval_matthews_correlation": 0.4522326299878879,
+      "eval_runtime": 0.6893,
+      "eval_samples_per_second": 1513.095,
+      "eval_steps_per_second": 95.747,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0329146614031314e-05,
+      "loss": 0.4583,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5012368559837341,
+      "eval_matthews_correlation": 0.4810794261012942,
+      "eval_runtime": 1.1504,
+      "eval_samples_per_second": 906.647,
+      "eval_steps_per_second": 57.372,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5001268982887268,
+      "eval_matthews_correlation": 0.5202123212283704,
+      "eval_runtime": 0.6949,
+      "eval_samples_per_second": 1500.847,
+      "eval_steps_per_second": 94.972,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 4.180845058060293e-06,
+      "loss": 0.2539,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.561569333076477,
+      "eval_matthews_correlation": 0.5290831606897504,
+      "eval_runtime": 1.2387,
+      "eval_samples_per_second": 842.006,
+      "eval_steps_per_second": 53.281,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 191113458530124.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6477448170002332e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 34
+  }
+}

run-1/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
+size 4664

run-1/checkpoint-1340/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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda2aca029da002f4a3b91ab5cbebf12f876b8b6373398c79b0fd04515638919
+size 267832560

run-1/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30d5c5853b84230f05966c34d87297f3fe77f8f4ce73221a62bf522038f9cb6
+size 535727290

run-1/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa609c0a7dbcd18813699a319d28cdba4b144b9958eb3924cd5abe799124853
+size 14244

run-1/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fbfe1a4ca62e3bb95076f93c4889caef703a9882c4bd1e6a55787887fd9163
+size 1064

run-1/checkpoint-1340/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-1340/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-1340/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.5290831606897504,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1072",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4801884889602661,
+      "eval_matthews_correlation": 0.4522326299878879,
+      "eval_runtime": 0.6893,
+      "eval_samples_per_second": 1513.095,
+      "eval_steps_per_second": 95.747,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0329146614031314e-05,
+      "loss": 0.4583,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5012368559837341,
+      "eval_matthews_correlation": 0.4810794261012942,
+      "eval_runtime": 1.1504,
+      "eval_samples_per_second": 906.647,
+      "eval_steps_per_second": 57.372,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5001268982887268,
+      "eval_matthews_correlation": 0.5202123212283704,
+      "eval_runtime": 0.6949,
+      "eval_samples_per_second": 1500.847,
+      "eval_steps_per_second": 94.972,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 4.180845058060293e-06,
+      "loss": 0.2539,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.561569333076477,
+      "eval_matthews_correlation": 0.5290831606897504,
+      "eval_runtime": 1.2387,
+      "eval_samples_per_second": 842.006,
+      "eval_steps_per_second": 53.281,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.611440122127533,
+      "eval_matthews_correlation": 0.5120519207329847,
+      "eval_runtime": 0.8478,
+      "eval_samples_per_second": 1230.198,
+      "eval_steps_per_second": 77.846,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 191113458530124.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6477448170002332e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 34
+  }
+}

run-1/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
+size 4664

run-2/checkpoint-1069/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": "4.35.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41163830d68c0c71e3d9e102767b6e13952332322e1a89db2f939c410a4d7099
+size 267832560

run-2/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6a88e644f5cc0b480eb3a51b6213110478394b08ceb6e358fde234a6f2ee8b
+size 535727290

run-2/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e009f365ddfb98bb6b6b9ade87989fd612d8521b8a7d74857e43a2b3fd0b6ea
+size 14308

run-2/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1fd109213364555e57bddfa1217e61cca6a5f4408a0f5ab95fa173f3f53392f
+size 1064

run-2/checkpoint-1069/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-1069/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-1069/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.42854888313294803,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.944660653119031e-06,
+      "loss": 0.5558,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.157496901381872e-06,
+      "loss": 0.5053,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4907635748386383,
+      "eval_matthews_correlation": 0.42854888313294803,
+      "eval_runtime": 0.8054,
+      "eval_samples_per_second": 1295.012,
+      "eval_steps_per_second": 81.947,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 38129912781888.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.7318244048561916e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-2/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700190963.faa202bf7ecf.336.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd08b330f08079d72111a35fc732085984e5ace7d0a6a09684d502b89dff346
+size 5535

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
+oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
 size 4664