Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7ea03cbb2ef8acdcd0daa0fde218e4cd440636b7165d47e5f66b8276d76d8b
+oid sha256:7f3d39af8eaf5db8c9342afd21b6daca84a6b7eb421a18e1ded6fe0fb9e1769a
 size 267832560

run-0/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65ea46da3ca47cefe8a2cfbf43b46848a5b1fb2abf441bba7be1bd6ffc4aaaf
+oid sha256:7f3d39af8eaf5db8c9342afd21b6daca84a6b7eb421a18e1ded6fe0fb9e1769a
 size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022a11ae30aea8fac11fb2a1311ba454344532f15d273f4b9b0a2d97594c9d97
+oid sha256:1364b6c19bf7a3565df25e7200296546a23a2653c62bc826d5c8febd365b4023
 size 535724410

run-0/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc984c538d815b2dcbcc83dd5d4f9fdb9b42a881f3c4b008b398f97027ea172a
-size 13990
+oid sha256:6ad16f0c4d7a66e49599653968d72067cedd0854ee14b22cc581f6d8e4564719
+size 14054

run-0/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965a51e45bda376bbffcc05aff621e2e469f0b3daa7d9fb7a9e594a9125b97ef
+oid sha256:da210971ebe84d4f26ae3da094d81caba11e5482960ce50f043ff98cf1c8d6a4
 size 1064

run-0/checkpoint-2138/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.3803319076352094,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 2138,
@@ -10,48 +10,48 @@
   "log_history": [
     {
       "epoch": 0.4677268475210477,
-      "grad_norm": 7.03068733215332,
-      "learning_rate": 1.9917409151067755e-06,
-      "loss": 0.5954,
+      "grad_norm": 1.7254643440246582,
+      "learning_rate": 1.1968622152407689e-06,
+      "loss": 0.6226,
       "step": 500
     },
     {
       "epoch": 0.9354536950420954,
-      "grad_norm": 7.087599754333496,
-      "learning_rate": 1.3837613927909097e-06,
-      "loss": 0.5462,
+      "grad_norm": 7.422174453735352,
+      "learning_rate": 8.315196586959675e-07,
+      "loss": 0.5927,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.5302711129188538,
-      "eval_matthews_correlation": 0.3184146642206088,
-      "eval_runtime": 33.164,
-      "eval_samples_per_second": 31.45,
-      "eval_steps_per_second": 1.99,
+      "eval_loss": 0.5829020738601685,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 32.3413,
+      "eval_samples_per_second": 32.25,
+      "eval_steps_per_second": 2.041,
       "step": 1069
     },
     {
       "epoch": 1.4031805425631432,
-      "grad_norm": 10.998974800109863,
-      "learning_rate": 7.757818704750443e-07,
-      "loss": 0.5095,
+      "grad_norm": 3.6254794597625732,
+      "learning_rate": 4.661771021511663e-07,
+      "loss": 0.5612,
       "step": 1500
     },
     {
       "epoch": 1.8709073900841908,
-      "grad_norm": 8.676448822021484,
-      "learning_rate": 1.6780234815917888e-07,
-      "loss": 0.4851,
+      "grad_norm": 4.46693229675293,
+      "learning_rate": 1.0083454560636514e-07,
+      "loss": 0.5373,
       "step": 2000
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5344046354293823,
-      "eval_matthews_correlation": 0.3803319076352094,
-      "eval_runtime": 34.2159,
-      "eval_samples_per_second": 30.483,
-      "eval_steps_per_second": 1.929,
+      "eval_loss": 0.5621180534362793,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 28.7656,
+      "eval_samples_per_second": 36.259,
+      "eval_steps_per_second": 2.294,
       "step": 2138
     }
   ],
@@ -60,13 +60,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 75421814032044.0,
+  "total_flos": 75003196354260.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.599720437422641e-06,
+    "learning_rate": 1.56220477178557e-06,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 8,
-    "seed": 23
+    "seed": 21
   }
 }

run-0/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3851731c9251ecf7b27e7c164fec575b150a35fa273ebb279f85322b83ff1b
+oid sha256:dacdab469fdcefaf9db3c5881569ed8f6809388c6a56ea9627c14d9ffaa0fc76
 size 5048

runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713912557.949a71f95aca.1272.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a585ed1019c7b682f66058432da448eba291446b6bbfd2a807db3c1eccab2ad7
-size 5405
+oid sha256:c51bac0046fa9bc7d7afbd72de75bae006babf73388d45e3140b6b1bdbce386f
+size 6516