Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24dd02e32ff8c92c80325e163a2677fcda5b674080dba270b04e22909088d6ab
+oid sha256:8b3dc784443d20d2b1cfc406fac9da85139cf5dbd33a67844ff95ae130ba5365
 size 267832560

run-1/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": "4.39.3",
+  "vocab_size": 30522
+}

run-1/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3dc784443d20d2b1cfc406fac9da85139cf5dbd33a67844ff95ae130ba5365
+size 267832560

run-1/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7accd1988733146582b6b5523d32af52bb52355e7239de6e2bfa4f1c79368cb
+size 535727290

run-1/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fc6508ba45e9e0842afb0e5dacc6abe7b220936e427628ec9427a8e21c7e48
+size 14244

run-1/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7b930459a2589976d29c2781e35b74a8bf5023acc71ab3a497b8051f336ff
+size 1064

run-1/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-1/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-1/checkpoint-5345/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.5235221651747541,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
+  "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": 8.518925666809082,
+      "learning_rate": 8.972995831812351e-06,
+      "loss": 0.5555,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 15.430549621582031,
+      "learning_rate": 8.046990070015412e-06,
+      "loss": 0.509,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5366330146789551,
+      "eval_matthews_correlation": 0.4025454740592728,
+      "eval_runtime": 0.8238,
+      "eval_samples_per_second": 1266.155,
+      "eval_steps_per_second": 80.121,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 22.634355545043945,
+      "learning_rate": 7.120984308218471e-06,
+      "loss": 0.3856,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 40.38935089111328,
+      "learning_rate": 6.194978546421531e-06,
+      "loss": 0.3925,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6002808213233948,
+      "eval_matthews_correlation": 0.4915876892254164,
+      "eval_runtime": 0.7672,
+      "eval_samples_per_second": 1359.42,
+      "eval_steps_per_second": 86.023,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 33.39309310913086,
+      "learning_rate": 5.2689727846245905e-06,
+      "loss": 0.3121,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 28.698448181152344,
+      "learning_rate": 4.34296702282765e-06,
+      "loss": 0.2998,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6921499371528625,
+      "eval_matthews_correlation": 0.48652176899433314,
+      "eval_runtime": 0.7643,
+      "eval_samples_per_second": 1364.583,
+      "eval_steps_per_second": 86.349,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 21.138490676879883,
+      "learning_rate": 3.4169612610307096e-06,
+      "loss": 0.2739,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 41.86164855957031,
+      "learning_rate": 2.4909554992337696e-06,
+      "loss": 0.2377,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8213266730308533,
+      "eval_matthews_correlation": 0.5235221651747541,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 1398.662,
+      "eval_steps_per_second": 88.506,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 67.9949722290039,
+      "learning_rate": 1.564949737436829e-06,
+      "loss": 0.2091,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 0.08398620784282684,
+      "learning_rate": 6.389439756398889e-07,
+      "loss": 0.2098,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.894464910030365,
+      "eval_matthews_correlation": 0.5232236706415442,
+      "eval_runtime": 0.7735,
+      "eval_samples_per_second": 1348.488,
+      "eval_steps_per_second": 85.331,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 188221943593836.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.899001593609293e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 30
+  }
+}

run-1/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700e5a8d2a7a3275e73e65bff8334235b4a5dc3f98246bcca9062835dce46dee
+size 4984

runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712325014.48c5213de69d.790.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193fa6b3e17630514d09ead436ce2a672cbf9224ffd18ca0bd6a6f361030c660
-size 7831
+oid sha256:2b3d0886edd7632039e0998afe18cdbd9fa7ab8060ae9b6f4ea962485b879e06
+size 8731