Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed58cfbcaae38345ff1479ed04cdec936f68a03189cbe89adafac63e2cae843
+oid sha256:ca8fe9f4d3b1eda4a732430841ce9a13e294d4165cbbeecd8e420652e2ca1d59
 size 267832560

run-1/checkpoint-268/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-1/checkpoint-268/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc9878783b0818c688c28abea8a5d61ace7dcab7d3f290e5b80a5cde21639f4f
+oid sha256:ca8fe9f4d3b1eda4a732430841ce9a13e294d4165cbbeecd8e420652e2ca1d59
 size 267832560

run-1/checkpoint-268/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e636934686b41a0f79de6208f706315ddc2a3cfa0585cee3ba2d34a439b209db
+oid sha256:3b516537655b6bf969c53f4695a44925a5b4bc725eee0618aaac9e3bcc64f989
 size 535727290

run-1/checkpoint-268/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7df60d1f16fe9e85b40c9a61615d24bef5f0ce05b0f715ad8da2204ad48db8
-size 14308
+oid sha256:acf4e24f2f10c1479c3cc0c08f6c5b0ec1f4f7435d026a8a835334c7aebd88cb
+size 14244

run-1/checkpoint-268/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e697567a35a41b5d63da1ecc000461d81bd321d5860f5da26db618d04341e
+oid sha256:64657bb9ceab0aa97e483aa39f8608b0faee3d21fe29168f23a470df6b267123
 size 1064

run-1/checkpoint-268/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4141806938515634,
+  "best_metric": 0.3637991719695883,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5035493969917297,
-      "eval_matthews_correlation": 0.4141806938515634,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 1405.832,
-      "eval_steps_per_second": 88.96,
+      "eval_loss": 0.5182795524597168,
+      "eval_matthews_correlation": 0.3637991719695883,
+      "eval_runtime": 0.8749,
+      "eval_samples_per_second": 1192.137,
+      "eval_steps_per_second": 75.437,
       "step": 268
     }
   ],
@@ -23,13 +23,25 @@
   "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": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0221265871912396e-05,
+    "learning_rate": 7.650877926980232e-06,
     "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 8
+    "seed": 28
   }
 }

run-1/checkpoint-268/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
-size 4984
+oid sha256:55916040b5530f85fbbef38cd42dcd18934cd6b77c8a8a1a110fdc3d400f34d0
+size 5304

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727358189.f266a1036e13.258.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf518373c6afe38ee8e31b1e4a6d789d20ac210800b0f4d65682c148044d916
+size 5841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed124d14dc79b84cb07ed86b8da4c02956606d59537d7769f990e0b60eecf882
+oid sha256:55916040b5530f85fbbef38cd42dcd18934cd6b77c8a8a1a110fdc3d400f34d0
 size 5304