Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0719fed60e9318276761def82f7efa080ae59ab6c2baf25c074e5ce01b18e5ca
+oid sha256:c77554997fc9372d2f41138d5724d1fb0cf6940cbf2e4a35b5ff66d9db597aaf
 size 267832560

run-0/checkpoint-2138/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-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a449f5ba8d475db833357bb2a8e66d95f049863cfcf9a02e6b387a5e18218e
+oid sha256:c77554997fc9372d2f41138d5724d1fb0cf6940cbf2e4a35b5ff66d9db597aaf
 size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed069420c568f99a89b1955fe08ef09cb877b068c6d8a9fb7b78bc7e3e9e1704
+oid sha256:b7c4acbf29aee80bdaedfcc1ecdb85d5eb6e4e2b3b53854a2fe2810c68f8e681
 size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172382e51eea4b612f92e96325ff52d51e3f94993499db917d83eb34dc31402c
-size 14244
+oid sha256:3ecee28ec0d36e12d2a69d8440b854f0bb324c6899b79460571e75a4f0858ec9
+size 14308

run-0/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60e27aef9e14addcecd59a048c0436b9257803bc2e4a736b74b3d2ea97f1435
+oid sha256:b764fbf1f3cb45f22e3739f3d6144dc33a78eb8bc8dc38b08acdc1f16b7b1adc
 size 1064

run-0/checkpoint-2138/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.12300105566407585,
+  "best_metric": 0.41870797137315424,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,57 +10,63 @@
   "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
     }
   ],
   "logging_steps": 500,
   "max_steps": 3207,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 75548589472164.0,
+  "total_flos": 75492963513744.0,
+  "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-2138/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:d0778b483e02ac32d52ec3b2a5dfa1bb4b42ba00cdcaa3f12b4939d2d6ca472f
-size 5345
+oid sha256:ac7778f58cb3039c820ca741293fa3121735d684832990ccb4eded482d24e50a
+size 6102