Training in progress, epoch 1

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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483916325a780f6eb7e6e9e7c55571aabfa9767680ac37de6a354b77b342fcec
-size 267832560
+oid sha256:d2418add4901ab4e859f7d66bc71a339c1b436407a41925c93616d9e8b4325e2
+size 437958648

run-0/checkpoint-134/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-134/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49d1ed4e9c66ddc49cc1d45d7fc2289aa41b88aba5ecbf842f00fea48083639
-size 267832560
+oid sha256:d2418add4901ab4e859f7d66bc71a339c1b436407a41925c93616d9e8b4325e2
+size 437958648

run-0/checkpoint-134/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1416666752de715396196264bd7a1fb002f8c3dd1e4533676a45cc16e903966d
-size 535727290
+oid sha256:471707b6360b6cd03834be03bbd3096246f995a56ab10cd0f37409559447e6f2
+size 876032762

run-0/checkpoint-134/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a370ee2267e26c5daf7b741d62be810509ce8dc65b6212f645244047641c5af
-size 14244
+oid sha256:b31cbd5c208388a18cca9abcdc24b0a64efba0e167045a774074f677ac37a75c
+size 13990

run-0/checkpoint-134/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2b15eae9b4eede4556ff7be2318f195d64ee5f12e70f364b49b9a12e0fc2e4
+oid sha256:bc255cd4b975e801e4f2aef7e50347eed9b5ecf7832a1c329f17d6e220970b9f
 size 1064

run-0/checkpoint-134/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0,
+  "best_metric": 0.48713384617299826,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-134",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "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
     }
   ],
@@ -24,12 +24,12 @@
   "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-134/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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5127b6b2a923f326f3eabd70d69017ceba509896441c1673ca4a47369a7144
+size 4990

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd22d926bf51e4e4dfb85da966e12cec78c95d5e0214bb73fd7de43b59d0463b
+oid sha256:28b64311d0cf6f55cb7835778299cd66ed26a46899481d14efde44e87fb33dde
 size 4984