Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77554997fc9372d2f41138d5724d1fb0cf6940cbf2e4a35b5ff66d9db597aaf
+oid sha256:c70c13e5d04c26d3f1731e0285668d3d574cdf941b52bb758883a9e4048d8a5b
 size 267832560

run-0/checkpoint-3207/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-0/checkpoint-3207/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b5a5907d61f119e37cb48d5085a194789fe19c47f09c0950ee7254b10c53b
+oid sha256:c70c13e5d04c26d3f1731e0285668d3d574cdf941b52bb758883a9e4048d8a5b
 size 267832560

run-0/checkpoint-3207/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517170c57b9be3696da3dd842a49bd5336ec92bc76d685ea7ccaefdb308aa19b
+oid sha256:0762713d693092e8633e570b159f155f90374816f34b422ea7e34aa6b57ae9e8
 size 535727290

run-0/checkpoint-3207/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86d21d26c9cb146bee42e59ef53f8aa2fcf92189b222d0f5ca339b6dbf1f9b6
-size 14244
+oid sha256:445ae490ad11c5908dee003a7cb2af17d54315221652bcb189faa8802c82ae3c
+size 14308

run-0/checkpoint-3207/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6ff343cdc8c697c60c82591ed7de93723747ee6e3240097235400049bd0d1f
+oid sha256:7669f715960383560f0bdbf6de5a8609a9498796c5d5deb7e7783436b5764a75
 size 1064

run-0/checkpoint-3207/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.166651669293941,
+  "best_metric": 0.4386209168112411,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-3207",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,78 +10,86 @@
   "log_history": [
     {
       "epoch": 0.47,
-      "learning_rate": 9.447053301406701e-07,
-      "loss": 0.6327,
+      "grad_norm": 5.35684061050415,
+      "learning_rate": 2.775809181053764e-06,
+      "loss": 0.5956,
       "step": 500
     },
     {
       "epoch": 0.94,
-      "learning_rate": 7.702122880016472e-07,
-      "loss": 0.5907,
+      "grad_norm": 11.188376426696777,
+      "learning_rate": 2.263099690648562e-06,
+      "loss": 0.5375,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.5891121625900269,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6963,
-      "eval_samples_per_second": 1497.889,
-      "eval_steps_per_second": 94.785,
+      "eval_loss": 0.5379385948181152,
+      "eval_matthews_correlation": 0.29871168199754417,
+      "eval_runtime": 0.7649,
+      "eval_samples_per_second": 1363.614,
+      "eval_steps_per_second": 86.288,
       "step": 1069
     },
     {
       "epoch": 1.4,
-      "learning_rate": 5.957192458626242e-07,
-      "loss": 0.5573,
+      "grad_norm": 10.391807556152344,
+      "learning_rate": 1.7503902002433598e-06,
+      "loss": 0.4937,
       "step": 1500
     },
     {
       "epoch": 1.87,
-      "learning_rate": 4.2122620372360136e-07,
-      "loss": 0.5487,
+      "grad_norm": 19.357559204101562,
+      "learning_rate": 1.2376807098381578e-06,
+      "loss": 0.4738,
       "step": 2000
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.55595862865448,
-      "eval_matthews_correlation": 0.12300105566407585,
-      "eval_runtime": 0.7049,
-      "eval_samples_per_second": 1479.688,
-      "eval_steps_per_second": 93.633,
+      "eval_loss": 0.526983916759491,
+      "eval_matthews_correlation": 0.41870797137315424,
+      "eval_runtime": 0.7468,
+      "eval_samples_per_second": 1396.551,
+      "eval_steps_per_second": 88.372,
       "step": 2138
     },
     {
       "epoch": 2.34,
-      "learning_rate": 2.4673316158457843e-07,
-      "loss": 0.5211,
+      "grad_norm": 11.473833084106445,
+      "learning_rate": 7.249712194329557e-07,
+      "loss": 0.4364,
       "step": 2500
     },
     {
       "epoch": 2.81,
-      "learning_rate": 7.22401194455555e-08,
-      "loss": 0.5205,
+      "grad_norm": 12.574313163757324,
+      "learning_rate": 2.1226172902775366e-07,
+      "loss": 0.4349,
       "step": 3000
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.55258709192276,
-      "eval_matthews_correlation": 0.166651669293941,
-      "eval_runtime": 1.1749,
-      "eval_samples_per_second": 887.771,
-      "eval_steps_per_second": 56.177,
+      "eval_loss": 0.5435938239097595,
+      "eval_matthews_correlation": 0.4386209168112411,
+      "eval_runtime": 0.7548,
+      "eval_samples_per_second": 1381.78,
+      "eval_steps_per_second": 87.438,
       "step": 3207
     }
   ],
   "logging_steps": 500,
   "max_steps": 3207,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 113236081840572.0,
+  "total_flos": 113055491519748.0,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.119198372279693e-06,
+    "learning_rate": 3.288518671458966e-06,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 8,
-    "seed": 19
+    "seed": 24
   }
 }

run-0/checkpoint-3207/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2697eed6b7ac5cb3358c6f6a74efea40e321a5f5e6bfffafbe5f4a6b261625ae
-size 4664
+oid sha256:1d71decb8fd1c3b29f479f69dd55dfb41734b34761f0097d998f78bf9dd25bdb
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710553848.6e5f088ca464.226.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7778f58cb3039c820ca741293fa3121735d684832990ccb4eded482d24e50a
-size 6102
+oid sha256:566b6d43e3a3d98e058f41bbd4d4be4f9fd3352b7212b447b67a36376d5b16df
+size 7213