Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc9b1c2430d9c24f6d4ded3940048177b0d473f99e6e36da13a5ab4a6505f14
+oid sha256:4ed58cfbcaae38345ff1479ed04cdec936f68a03189cbe89adafac63e2cae843
 size 267832560

run-0/checkpoint-268/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": "4.45.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47901ece7b116834723473a7e7f1592e6b0234bb35337411c42c6f43a7e9aa4
+size 267832560

run-0/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba4028c8b04943e18f6e0669f42c69badb33712515df548381b34978c295aac
+size 535727290

run-0/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f13a294644e988ad1093c208302e60e03128ddce54f0ff29db12c195efcdf87
+size 14244

run-0/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f69f00b9da8888392a5ded20ef1498081c42085ca9731224ff3861cfa35a5a6
+size 1064

run-0/checkpoint-268/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-268/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-268/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.4210344655831915,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5353219509124756,
+      "eval_matthews_correlation": 0.2835704013245166,
+      "eval_runtime": 1.3472,
+      "eval_samples_per_second": 774.178,
+      "eval_steps_per_second": 48.989,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.514467716217041,
+      "eval_matthews_correlation": 0.4210344655831915,
+      "eval_runtime": 0.8237,
+      "eval_samples_per_second": 1266.262,
+      "eval_steps_per_second": 80.128,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.211792523053304e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 38
+  }
+}

run-0/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed124d14dc79b84cb07ed86b8da4c02956606d59537d7769f990e0b60eecf882
+size 5304

run-0/checkpoint-402/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": "4.45.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427623ce3e664498c01527f58defa6b6eda102438383b66632db504340ff6ef6
+size 267832560

run-0/checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f98221478aab7bba719e560ec5887e975b11969697dc6b6f226e67879472e7
+size 535727290

run-0/checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131584404be8796e549daf1f6dc59e0866963d858d798152a1e6535e4ff210ae
+size 14244

run-0/checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0761bd54cd26597b30759be20ccf2fc8b948709f5513520143c6530862a8f518
+size 1064

run-0/checkpoint-402/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-402/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-402/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.43765045412808823,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-402",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 402,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5353219509124756,
+      "eval_matthews_correlation": 0.2835704013245166,
+      "eval_runtime": 1.3472,
+      "eval_samples_per_second": 774.178,
+      "eval_steps_per_second": 48.989,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.514467716217041,
+      "eval_matthews_correlation": 0.4210344655831915,
+      "eval_runtime": 0.8237,
+      "eval_samples_per_second": 1266.262,
+      "eval_steps_per_second": 80.128,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5049848556518555,
+      "eval_matthews_correlation": 0.43765045412808823,
+      "eval_runtime": 0.8256,
+      "eval_samples_per_second": 1263.398,
+      "eval_steps_per_second": 79.947,
+      "step": 402
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.211792523053304e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 38
+  }
+}

run-0/checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed124d14dc79b84cb07ed86b8da4c02956606d59537d7769f990e0b60eecf882
+size 5304

run-0/checkpoint-536/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": "4.45.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed58cfbcaae38345ff1479ed04cdec936f68a03189cbe89adafac63e2cae843
+size 267832560

run-0/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23c360e6d2d8de225eb6bbac0cb21ce54f0a621b03927e39fb959917b3e0f4d
+size 535727290

run-0/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860e5620759cfc6a0927515baa36a9b7a79688a7206a0f1ec0b8de3c71ab9a4e
+size 14244

run-0/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080230f4dd64c32a400e0b37b7850232873e64309b150cb7a31e9780a0ccbaf6
+size 1064

run-0/checkpoint-536/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-536/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-536/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.43765045412808823,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-402",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5353219509124756,
+      "eval_matthews_correlation": 0.2835704013245166,
+      "eval_runtime": 1.3472,
+      "eval_samples_per_second": 774.178,
+      "eval_steps_per_second": 48.989,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.514467716217041,
+      "eval_matthews_correlation": 0.4210344655831915,
+      "eval_runtime": 0.8237,
+      "eval_samples_per_second": 1266.262,
+      "eval_steps_per_second": 80.128,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5049848556518555,
+      "eval_matthews_correlation": 0.43765045412808823,
+      "eval_runtime": 0.8256,
+      "eval_samples_per_second": 1263.398,
+      "eval_steps_per_second": 79.947,
+      "step": 402
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 6.807294845581055,
+      "learning_rate": 5.515383037871622e-07,
+      "loss": 0.4793,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5229844450950623,
+      "eval_matthews_correlation": 0.43643553358388004,
+      "eval_runtime": 0.9434,
+      "eval_samples_per_second": 1105.555,
+      "eval_steps_per_second": 69.958,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 209747119699272.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.211792523053304e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 38
+  }
+}

run-0/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed124d14dc79b84cb07ed86b8da4c02956606d59537d7769f990e0b60eecf882
+size 5304

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727357973.f266a1036e13.258.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a8a7e5a9fd80c37ba3467141ffec7a295c1b938cf0ccb3a9fdf54d80e77546
-size 5295
+oid sha256:7d4b7d37008fe911ff15ae53ff2927d429ddc3a57516dd133c0d5012607ab539
+size 6865