Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab0c8c520fb9100b11012b33ef3945592d78aeaf9785c7b9a9e26bc874aed84
+oid sha256:7078b3b1db14fae62d286394e370271149c52e7669446c720e9b52ba6270084c
 size 267832560

run-9/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-9/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa683f8eb8ed680b8eb4056a4ff7d9e8ebf5bdd64c79a76ba4deecbf2c4c6092
+size 267832560

run-9/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb26634a10dfa230029aa1f7f9cfb198aa22959b7b30ee760651514353ae0b2
+size 535727290

run-9/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912a21dd2faf9f53d6272ab6fe592dae1f2caea82de30009f8e16f928f4cb249
+size 14244

run-9/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45398392412e361ae8a356f38977bd7a204d551694f7c567672c17211411bb6b
+size 1064

run-9/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-9/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-9/checkpoint-1069/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.4043410378269883,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/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": 4.453324739094023e-05,
+      "loss": 0.5772,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.993745302655011e-05,
+      "loss": 0.5332,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5163644552230835,
+      "eval_matthews_correlation": 0.4043410378269883,
+      "eval_runtime": 0.8124,
+      "eval_samples_per_second": 1283.809,
+      "eval_steps_per_second": 81.238,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 151772969657784.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.9129041755330344e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-9/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d92480d808ffe52df127d4454620c53b0242efef3696b58490fc75fd6a6f454
+size 4664

run-9/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": "4.35.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756f896887da8ba2772762b5ef6e4ca5d8a6a04a1edcf388a4b2e5f9429fbc3f
+size 267832560

run-9/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430fe64ef42778d41e8bda96113399b14bd39d13e7a4500f4dbca4a6e5ffcd85
+size 535727290

run-9/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad52735ecd1a313dff823557ca3632ed4980154785d4da9806baf2e6c8ab2de
+size 14244

run-9/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c5f48138ec3983ba13ec77d87f79ddb9d9503334ea42074dab0e437c2e7a4d
+size 1064

run-9/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-9/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-9/checkpoint-2138/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.4092437141936731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.453324739094023e-05,
+      "loss": 0.5772,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.993745302655011e-05,
+      "loss": 0.5332,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5163644552230835,
+      "eval_matthews_correlation": 0.4043410378269883,
+      "eval_runtime": 0.8124,
+      "eval_samples_per_second": 1283.809,
+      "eval_steps_per_second": 81.238,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.5341658662159996e-05,
+      "loss": 0.4009,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.0745864297769874e-05,
+      "loss": 0.3795,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5874858498573303,
+      "eval_matthews_correlation": 0.4092437141936731,
+      "eval_runtime": 1.6757,
+      "eval_samples_per_second": 622.409,
+      "eval_steps_per_second": 39.385,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 189719963590356.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.9129041755330344e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-9/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d92480d808ffe52df127d4454620c53b0242efef3696b58490fc75fd6a6f454
+size 4664

run-9/checkpoint-3207/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-9/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7078b3b1db14fae62d286394e370271149c52e7669446c720e9b52ba6270084c
+size 267832560

run-9/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8e7d10fcd1cb9d31a4182893ee51b4ec7c469ddae91cdc4abc159c90426416
+size 535727290

run-9/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc50943c185b69deb40d8bc7130e1a94082a0711bb7d56b99c6de016c2c2385
+size 14244

run-9/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d53880fd19012bf144c7108a8842b7d62a41bc3efc54db82859f2e772849e2
+size 1064

run-9/checkpoint-3207/special_tokens_map.json

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

run-9/checkpoint-3207/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-9/checkpoint-3207/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.44799494293545944,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.453324739094023e-05,
+      "loss": 0.5772,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.993745302655011e-05,
+      "loss": 0.5332,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5163644552230835,
+      "eval_matthews_correlation": 0.4043410378269883,
+      "eval_runtime": 0.8124,
+      "eval_samples_per_second": 1283.809,
+      "eval_steps_per_second": 81.238,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.5341658662159996e-05,
+      "loss": 0.4009,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.0745864297769874e-05,
+      "loss": 0.3795,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5874858498573303,
+      "eval_matthews_correlation": 0.4092437141936731,
+      "eval_runtime": 1.6757,
+      "eval_samples_per_second": 622.409,
+      "eval_steps_per_second": 39.385,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.6150069933379758e-05,
+      "loss": 0.2679,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1554275568989645e-05,
+      "loss": 0.2669,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8904589414596558,
+      "eval_matthews_correlation": 0.44799494293545944,
+      "eval_runtime": 0.7124,
+      "eval_samples_per_second": 1464.018,
+      "eval_steps_per_second": 92.642,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 227521036404096.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.9129041755330344e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-9/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d92480d808ffe52df127d4454620c53b0242efef3696b58490fc75fd6a6f454
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700192285.faa202bf7ecf.336.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb5fab23e9ac9c47bf4721d198e06c79c907f580779463d0a8f30d76f71da01
+size 6833

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e036b0341157ca336e2f60d3c309f003686ef3e66d2f7e07090d6eda358d6255
+oid sha256:3d92480d808ffe52df127d4454620c53b0242efef3696b58490fc75fd6a6f454
 size 4664