Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9dd3a7e46ef5f8d7d09d3f7286186356d27c92fa5bd204daaf8189b395f11b
+oid sha256:ffecd53831e2fda4561907f162811184d1b27cd72a6174a56135df37ba3efaf4
 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 sha256:2a210262a3a0b06b6e6052aa3acc334843c8d17af65443bb815ef1db7f316e42
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5648db7ee6699dc0b1f12f0cff394550d673019d5b0690574215616a9ce28a9
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669e8a42fcc46b89570af02d297ebd425222f1895a17bcb7b917731c0e4ff319
+size 14244

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2728c2f843509e109330d2b1b16631de8738441d052908c19a5757b1ae554085
+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 +1,68 @@
+{
+  "best_metric": 0.4491534084057902,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-0/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": 2.7326435592927605e-06,
+      "loss": 0.5977,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4506370000262214e-06,
+      "loss": 0.5335,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5340704321861267,
+      "eval_matthews_correlation": 0.36161681105121063,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.534,
+      "eval_steps_per_second": 89.131,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.168630440759683e-06,
+      "loss": 0.4751,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.886623881493144e-06,
+      "loss": 0.4579,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5136641263961792,
+      "eval_matthews_correlation": 0.4491534084057902,
+      "eval_runtime": 0.906,
+      "eval_samples_per_second": 1151.249,
+      "eval_steps_per_second": 72.85,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 75156879234732.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.014650118559299e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fe9927effe1f0b016401f7ae93dae94ecab2821cb36372747f5f4e611c428e
+size 4728

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

run-0/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5df1ec3ce150d4d0bd84f10f02333e006540fa336a024ae0db74864d30d51ff
+size 267832560

run-0/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff1523c79f173c83aa5eab3930fa3cfa97743cb3fc126891c95d535d2d2f057
+size 535727290

run-0/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3cf8ba03edf4aab739b99b2fbc1771c3e0085e1078b77e13fb3ed47eaf2c3bd
+size 14244

run-0/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e02d919d1bb6ccc29e426eecf544d0e5d41e91bdc71d11985a479482826e2fc
+size 1064

run-0/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-0/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-0/checkpoint-3207/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.45115517656589194,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-0/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": 2.7326435592927605e-06,
+      "loss": 0.5977,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4506370000262214e-06,
+      "loss": 0.5335,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5340704321861267,
+      "eval_matthews_correlation": 0.36161681105121063,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.534,
+      "eval_steps_per_second": 89.131,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.168630440759683e-06,
+      "loss": 0.4751,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.886623881493144e-06,
+      "loss": 0.4579,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5136641263961792,
+      "eval_matthews_correlation": 0.4491534084057902,
+      "eval_runtime": 0.906,
+      "eval_samples_per_second": 1151.249,
+      "eval_steps_per_second": 72.85,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.6046173222266052e-06,
+      "loss": 0.4286,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.3226107629600667e-06,
+      "loss": 0.4101,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5329485535621643,
+      "eval_matthews_correlation": 0.45115517656589194,
+      "eval_runtime": 0.7978,
+      "eval_samples_per_second": 1307.396,
+      "eval_steps_per_second": 82.731,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 112981754784168.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.014650118559299e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fe9927effe1f0b016401f7ae93dae94ecab2821cb36372747f5f4e611c428e
+size 4728

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:ffecd53831e2fda4561907f162811184d1b27cd72a6174a56135df37ba3efaf4
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e548f3286a7c3abdf75cced946d0a83e7936b610f2758669a1972762e203429
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6ab4081361d01ba74a185d70e72d4bae90638ed30c15c6aad7f95a02d8c1b2
+size 14244

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41feb947253f2ca44e48a6549ac48764a36c4e2117e49a9ce16d2bd2b113040b
+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 +1,110 @@
+{
+  "best_metric": 0.45354879777314566,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7326435592927605e-06,
+      "loss": 0.5977,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4506370000262214e-06,
+      "loss": 0.5335,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5340704321861267,
+      "eval_matthews_correlation": 0.36161681105121063,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.534,
+      "eval_steps_per_second": 89.131,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.168630440759683e-06,
+      "loss": 0.4751,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.886623881493144e-06,
+      "loss": 0.4579,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5136641263961792,
+      "eval_matthews_correlation": 0.4491534084057902,
+      "eval_runtime": 0.906,
+      "eval_samples_per_second": 1151.249,
+      "eval_steps_per_second": 72.85,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.6046173222266052e-06,
+      "loss": 0.4286,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.3226107629600667e-06,
+      "loss": 0.4101,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5329485535621643,
+      "eval_matthews_correlation": 0.45115517656589194,
+      "eval_runtime": 0.7978,
+      "eval_samples_per_second": 1307.396,
+      "eval_steps_per_second": 82.731,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.0406042036935279e-06,
+      "loss": 0.3981,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 7.585976444269893e-07,
+      "loss": 0.3845,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5448588728904724,
+      "eval_matthews_correlation": 0.45354879777314566,
+      "eval_runtime": 0.7443,
+      "eval_samples_per_second": 1401.396,
+      "eval_steps_per_second": 88.679,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 150407158334532.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.014650118559299e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 16
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fe9927effe1f0b016401f7ae93dae94ecab2821cb36372747f5f4e611c428e
+size 4728

runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703297989.42b18358a534.403.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a1cba10986429cede09506c9530dd389ad0d421046d7fb4646d435c548b172
-size 4935
+oid sha256:5b4e8d5625fe31c52a2d5068f50c794c680ec420655cbc8dfeeaf057b1265e3c
+size 7039