Training in progress, step 4000, checkpoint

checkpoint-4000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485c24a64cc513c61db4a5fb7ebb750447a2ef377b9cd1ce879d45afbf09a0d1
+oid sha256:a88cb6e0ab6672d817f87d2f4500b7f467a13480d0113077d617dd8f96de6e93
 size 14809584

checkpoint-4000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f38a770c8e1554824ca217546c158b104708a1a10cfe19791451a77050630d
+oid sha256:4f8ba9555dd3ecfc7ec0901f512c82d3b1fae64fd968843e911587fa20bb820e
 size 29680378

checkpoint-4000/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.003616819658138206,
-      "grad_norm": 0.14744244515895844,
+      "grad_norm": 0.14744240045547485,
       "learning_rate": 0.0001,
       "loss": 0.7697,
       "step": 2000
@@ -18,14 +18,14 @@
     {
       "epoch": 0.003616819658138206,
       "eval_loss": 0.19154727458953857,
-      "eval_runtime": 110.4273,
-      "eval_samples_per_second": 330.851,
-      "eval_steps_per_second": 20.683,
+      "eval_runtime": 91.812,
+      "eval_samples_per_second": 397.933,
+      "eval_steps_per_second": 24.877,
       "step": 2000
     },
     {
       "epoch": 0.007233639316276412,
-      "grad_norm": 0.1623348891735077,
+      "grad_norm": 0.1623348593711853,
       "learning_rate": 0.0001,
       "loss": 0.1884,
       "step": 4000
@@ -33,9 +33,9 @@
     {
       "epoch": 0.007233639316276412,
       "eval_loss": 0.17771275341510773,
-      "eval_runtime": 90.2021,
-      "eval_samples_per_second": 405.035,
-      "eval_steps_per_second": 25.321,
+      "eval_runtime": 99.0721,
+      "eval_samples_per_second": 368.772,
+      "eval_steps_per_second": 23.054,
       "step": 4000
     }
   ],

checkpoint-4000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a3b67ff96aad171c21e5c77947a3759ef9af49c075132a399cacc48fed219d
+oid sha256:f5e294196a968439ae6368c7b1ef6eb6e2124702ff760349c5ba2ea15623271d
 size 5496