Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe0b5ba0da18474d125e9bedb32b49c5ff506be7471975eff7806a1d2a8debf
+oid sha256:c706795f663366132ae852cd8642d4783fcd942a5d68f88712502a361c83cd14
 size 267832560

run-0/checkpoint-5345/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": "4.39.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa4fefa779287bdc7f1d8589a40b409ec8520f705fe14e1a996e8520d874b1e
+size 267832560

run-0/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd719212004043ceef4a40e47ee73cf3cb1167946bfc3bbe4f0508e379eabc9
+size 535727290

run-0/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992446a058e32559305e0c0d060daf2af3ffe07b21d09d6388db18d901a57c12
+size 14244

run-0/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6d1f10aa821da5a4bc08b1a1754beed5a836bdac2ce1f95127af38a68fa297
+size 1064

run-0/checkpoint-5345/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-5345/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-5345/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.40039137901723904,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-0\\checkpoint-5345",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.136430025100708,
+      "learning_rate": 1.057670968337005e-06,
+      "loss": 0.6141,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.4976818561553955,
+      "learning_rate": 9.485201976107919e-07,
+      "loss": 0.5835,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5739973187446594,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.1959,
+      "eval_samples_per_second": 474.985,
+      "eval_steps_per_second": 30.057,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.231539249420166,
+      "learning_rate": 8.393694268845788e-07,
+      "loss": 0.5608,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 7.4941792488098145,
+      "learning_rate": 7.302186561583657e-07,
+      "loss": 0.5232,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5443820953369141,
+      "eval_matthews_correlation": 0.2045620264226157,
+      "eval_runtime": 0.9649,
+      "eval_samples_per_second": 1080.926,
+      "eval_steps_per_second": 68.4,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 7.5233941078186035,
+      "learning_rate": 6.210678854321524e-07,
+      "loss": 0.5208,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 6.596949100494385,
+      "learning_rate": 5.119171147059394e-07,
+      "loss": 0.4937,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5387976169586182,
+      "eval_matthews_correlation": 0.3459293076636948,
+      "eval_runtime": 0.8998,
+      "eval_samples_per_second": 1159.164,
+      "eval_steps_per_second": 73.351,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 6.339045524597168,
+      "learning_rate": 4.0276634397972634e-07,
+      "loss": 0.4854,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 12.96947193145752,
+      "learning_rate": 2.936155732535133e-07,
+      "loss": 0.4801,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5404464602470398,
+      "eval_matthews_correlation": 0.3860262930745603,
+      "eval_runtime": 0.852,
+      "eval_samples_per_second": 1224.144,
+      "eval_steps_per_second": 77.463,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 15.995396614074707,
+      "learning_rate": 1.8446480252730014e-07,
+      "loss": 0.4664,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 14.75170612335205,
+      "learning_rate": 7.531403180108705e-08,
+      "loss": 0.4841,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5346407890319824,
+      "eval_matthews_correlation": 0.40039137901723904,
+      "eval_runtime": 1.0251,
+      "eval_samples_per_second": 1017.419,
+      "eval_steps_per_second": 64.381,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 188608220598120.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.166821739063218e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 23
+  }
+}

run-0/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec708c48a1d20e757d0e32ebecb11c5a942f99a1c01da631d491c2e4de94629
+size 4984

run-1/checkpoint-134/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": "4.39.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c706795f663366132ae852cd8642d4783fcd942a5d68f88712502a361c83cd14
+size 267832560

run-1/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb748b517d4b0c27df425b64137e96ebcdc44239ef586a7091f05f229306024
+size 535727290

run-1/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4f86e10eeffbfd07c20706be78413b69b097afade4fba68294f9c2f631d414
+size 14244

run-1/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3c4cb1e4c454b63572de77a3f5ea65bd8843fe1efbaa834dadf8e10b784ca6
+size 1064

run-1/checkpoint-134/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-134/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-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-1\\checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6127962470054626,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.3238,
+      "eval_samples_per_second": 787.877,
+      "eval_steps_per_second": 49.856,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 402,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.169416569899892e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 4
+  }
+}

run-1/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72358d0b557f55b659aab7830ef6b127c27bedaa90c1bc8f0ae19caf70cb325f
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec708c48a1d20e757d0e32ebecb11c5a942f99a1c01da631d491c2e4de94629
+oid sha256:72358d0b557f55b659aab7830ef6b127c27bedaa90c1bc8f0ae19caf70cb325f
 size 4984