Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cbb923a4355813b46ea8954e05ab8effa2eda9f1b8f64d439a26f31842a1f7
+oid sha256:272d2902a0945322b1098e2370c32c855495b60f146a82a0560640b3ab47d30e
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cae84f72cdbd7570e20899135afc83db92d91a9d4d25239d3b1a7bf152a5288
+oid sha256:0363580c9aec52148e73233c0c10a7e3aba961c3d2c84bd54d368bef6fe0d04c
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974b44f0327aeed05d181ead40f57037df659928bde69b43d9f210068728bd5d
+oid sha256:683fad27550de1ffc9b0cc6c790b518e58ed323e4f2ac3633bf01ad829ce6017
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119a850c14f30baeb469a3d205fd6f7c599519c63cd1111506a3c44f6d44bd04
+oid sha256:215ffe1bec7733c0fb3f3e9bb274c5f02ff2056776126fa80e3e4a6ddd3853be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5638089776039124,
+  "best_metric": 0.4708317220211029,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
   "epoch": 0.19047619047619047,
   "eval_steps": 500,
@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 0.19047619047619047,
-      "grad_norm": 280717.46875,
-      "learning_rate": 7.616146230007617e-05,
-      "loss": 0.396,
+      "grad_norm": 239228.203125,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.3542,
       "step": 500
     },
     {
       "epoch": 0.19047619047619047,
-      "eval_loss": 0.5638089776039124,
-      "eval_runtime": 244.4233,
-      "eval_samples_per_second": 106.991,
-      "eval_steps_per_second": 0.839,
+      "eval_loss": 0.4708317220211029,
+      "eval_runtime": 244.6397,
+      "eval_samples_per_second": 106.896,
+      "eval_steps_per_second": 0.838,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2625,
+  "max_steps": 5250,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -41,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2120385527808000.0,
+  "total_flos": 3999047105445888.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2108f8a59b7a937ff2416112d40f2053ee3034987ade2881502fa804a2fd165f
+oid sha256:1d5fac56a66d1b1aa648adc29f8deb76c1a558742c90ccc8ea8112bd9750d963
 size 5240