Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2418add4901ab4e859f7d66bc71a339c1b436407a41925c93616d9e8b4325e2
+oid sha256:668d90c5128a6f2f43644ee453315316549ec854817d9dcc55f6fb3450cd53cd
 size 437958648

run-0/checkpoint-268/config.json

@@ -1,25 +1,27 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

run-0/checkpoint-268/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef00cc76dea411db3cd877af9d95936843ecaf98d12bb5016c296326d04fb73
-size 267832560
+oid sha256:668d90c5128a6f2f43644ee453315316549ec854817d9dcc55f6fb3450cd53cd
+size 437958648

run-0/checkpoint-268/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ff428f99ecc35d69e57eb499b2bc357d453d727ebcf387ecf31627a3b34719
-size 535727290
+oid sha256:d9ad3177ae6cc0a7d258c5c5cb86f4a5a30942c8549ba46120cb803647c15924
+size 876032762

run-0/checkpoint-268/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a7d2168f6f1ae4ea46d4afd75c71325902ae36a52993875e58941a85eff2df
-size 14244
+oid sha256:8b3965b69b49d517747b6cd36098d1f3f2c556b5c3184f398620acad85f4ec55
+size 13990

run-0/checkpoint-268/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5efa340ffab5b563a69a7611173efd483e5d2ffda28af24c45ad6c1869af4d
+oid sha256:0e1034233200764dc565b8c8a46c0125398fad8f69642cb863b7deffd3b1fd26
 size 1064

run-0/checkpoint-268/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0463559874942472,
+  "best_metric": 0.5069257203383023,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,20 +10,20 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6058756113052368,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.1108,
-      "eval_samples_per_second": 938.924,
-      "eval_steps_per_second": 59.414,
+      "eval_loss": 0.4828512966632843,
+      "eval_matthews_correlation": 0.48713384617299826,
+      "eval_runtime": 42.093,
+      "eval_samples_per_second": 24.778,
+      "eval_steps_per_second": 1.568,
       "step": 134
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5703422427177429,
-      "eval_matthews_correlation": 0.0463559874942472,
-      "eval_runtime": 1.1844,
-      "eval_samples_per_second": 880.626,
-      "eval_steps_per_second": 55.725,
+      "eval_loss": 0.5472354888916016,
+      "eval_matthews_correlation": 0.5069257203383023,
+      "eval_runtime": 42.0585,
+      "eval_samples_per_second": 24.799,
+      "eval_steps_per_second": 1.569,
       "step": 268
     }
   ],
@@ -33,12 +33,12 @@
   "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.205579826691781e-06,
+    "learning_rate": 4.8551725658168107e-05,
     "num_train_epochs": 4,
-    "per_device_train_batch_size": 64,
-    "seed": 12
+    "per_device_train_batch_size": 32,
+    "seed": 15
   }
 }

run-0/checkpoint-268/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
+oid sha256:28b64311d0cf6f55cb7835778299cd66ed26a46899481d14efde44e87fb33dde
 size 4984

runs/Mar05_08-10-31_6dbd81c6b707/events.out.tfevents.1709628605.6dbd81c6b707.254.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5127b6b2a923f326f3eabd70d69017ceba509896441c1673ca4a47369a7144
-size 4990
+oid sha256:9979b86052d31cf5e796ed7a5186c62ce976e5ad8171ac24ff9fbcbb581a8774
+size 5325