Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163d37d6b9fceee22a578d700aae69b7b0e703b099be640a69f378cc531d6b53
+oid sha256:3c80786f21b04dacd0121a08116c3031f398b934ebb747edbcff6003d02eb5f2
 size 1113205088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2be16c3705b887610fd67dd4ad40090620ba33b7c16453cb6394c6f1bb9d74
+oid sha256:b6765ea4bc1e8fb9531bc9ad3d92b5afa8a3b1f854e380e58bd359ecb37ee83b
 size 2226533707

last-checkpoint/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 500,
-  "best_metric": 2.053861141204834,
+  "best_metric": 2.0580365657806396,
   "best_model_checkpoint": "yiddish-roberta-checkpoints/checkpoint-500",
   "epoch": 0.009312070771737865,
   "eval_steps": 500,
@@ -11,17 +11,17 @@
   "log_history": [
     {
       "epoch": 0.009312070771737865,
-      "grad_norm": 3.7046830654144287,
+      "grad_norm": 3.368424415588379,
       "learning_rate": 1.9938043977601472e-05,
-      "loss": 2.3727,
+      "loss": 2.3724,
       "step": 500
     },
     {
       "epoch": 0.009312070771737865,
-      "eval_loss": 2.053861141204834,
-      "eval_runtime": 18213.8878,
-      "eval_samples_per_second": 9.93,
-      "eval_steps_per_second": 1.241,
+      "eval_loss": 2.0580365657806396,
+      "eval_runtime": 19330.252,
+      "eval_samples_per_second": 9.356,
+      "eval_steps_per_second": 1.17,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77922081a4b5289b9df60ce8a10e07f6c0d8d6a1e1d3692001ab9042ccb6c447
+oid sha256:10d4f51450bbb56f73a03215590eebeaa5446fdb66c1700d73b34c09cf9341ca
 size 5905