Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b7b79ad7d628ee954291594a9c617d6f0042ff7ff358712495239061c1e8cb
+oid sha256:e1a0a59447ca75a0f90f0983f0fcbfc47ae0ee11d40bba80baf61ee7800aaf0f
 size 267832560

run-6/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-6/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6bc8a04cc435a7b40b65f3adf41b4d72a1cd6f3e3dfeb32dcfce8111aa0ea8
+oid sha256:e1a0a59447ca75a0f90f0983f0fcbfc47ae0ee11d40bba80baf61ee7800aaf0f
 size 267832560

run-6/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:476dde5796ec692ecad7dc45322c392277a3230ef79176a3761bb1ecdaa05d26
+oid sha256:e88c4edc2f294aabdbb02205635444fc46b224d32fd55dc6e271851ce2bbf53a
 size 535727290

run-6/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6adef909c722787fec62e68e29d36d8bd96e201138f6d91b406f157aee940cf
-size 14308
+oid sha256:e5ab2e0270bd067529d0c30545777c33add7857664e16953fec59df1a0449276
+size 14244

run-6/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1707e5ae47bc1eb0399c327357c1a3a6280d4b0ca3fff4d30eaf83c1c665f3fd
+oid sha256:3b03cd15ef59e513b02e299f1682ad2ea8c323808a0c6c409a9dcbbad9d03d80
 size 1064

run-6/checkpoint-2138/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4279924761510222,
+  "best_metric": 0.47921629302778096,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,48 +10,54 @@
   "log_history": [
     {
       "epoch": 0.23,
-      "learning_rate": 4.8198594968909895e-06,
-      "loss": 0.6022,
+      "grad_norm": 17.90995979309082,
+      "learning_rate": 1.8573493164868257e-05,
+      "loss": 0.6076,
       "step": 500
     },
     {
       "epoch": 0.47,
-      "learning_rate": 4.583360012254533e-06,
-      "loss": 0.5521,
+      "grad_norm": 25.591594696044922,
+      "learning_rate": 1.700319445292471e-05,
+      "loss": 0.5721,
       "step": 1000
     },
     {
       "epoch": 0.7,
-      "learning_rate": 4.346860527618076e-06,
-      "loss": 0.5166,
+      "grad_norm": 17.508258819580078,
+      "learning_rate": 1.5432895740981165e-05,
+      "loss": 0.5514,
       "step": 1500
     },
     {
       "epoch": 0.94,
-      "learning_rate": 4.110361042981619e-06,
-      "loss": 0.5388,
+      "grad_norm": 47.17720031738281,
+      "learning_rate": 1.3862597029037618e-05,
+      "loss": 0.5529,
       "step": 2000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.6151991486549377,
-      "eval_matthews_correlation": 0.4279924761510222,
-      "eval_runtime": 0.7154,
-      "eval_samples_per_second": 1457.835,
-      "eval_steps_per_second": 92.25,
+      "eval_loss": 0.4856245219707489,
+      "eval_matthews_correlation": 0.47921629302778096,
+      "eval_runtime": 0.8291,
+      "eval_samples_per_second": 1258.047,
+      "eval_steps_per_second": 79.608,
       "step": 2138
     }
   ],
   "logging_steps": 500,
-  "max_steps": 10690,
-  "num_train_epochs": 5,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 36863452007628.0,
+  "total_flos": 83994162312648.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.056358981527446e-06,
-    "num_train_epochs": 5,
+    "learning_rate": 2.01437918768118e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 4,
-    "seed": 13
+    "seed": 9
   }
 }

run-6/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50705ae525f9e6a06c3db42e472a08e563496b4d579b21777c60dadaa477aaad
-size 4664
+oid sha256:a1c579802743ec5bde7ffe4a1b22c8900fae6cd071e374192c2957c3eec29367
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555115.6e5f088ca464.226.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb771b9f1e48f46d53021af54b80b5f0798ad10bead145d492084671cbd6cce1
+size 4922

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555138.6e5f088ca464.226.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a225ed22ce8ed4520e73bf4770006b543dbf5969c3bc97769e580ca0fe45a46a
+size 6398

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a12fdc24cb9dc9a62bc10545627abe46debf8706f86ab2fc532296984bfd9c9
+oid sha256:a1c579802743ec5bde7ffe4a1b22c8900fae6cd071e374192c2957c3eec29367
 size 4984