Training in progress, step 40, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681a208ef373053824021017b27708b23a588064e7003361364981ae70fa09cc
+oid sha256:720105d2b88abf15d23994fec61854b0a1497a10d1d208715bd59904ab5936ff
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b773cef476437d526f7c17ec504cec44088b25420cde09e2273e473904f2e5
+oid sha256:22f56733ac237ee5fada526e2a06e89d311e7ce1cb761f9b8f6986910b678378
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e632ea54fafa03fa867d58aa1615bc784b20c0be1d236538bd55ebff650daa
+oid sha256:31711beccc0b973ef7bf69d348d844233b185f6888f0520ae136ada35d74f983
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9951bfdfc286622c846de580f1aec65c1e44f78aa8094a852f758e9ef7b3ca
+oid sha256:5dcb4aaff4751c7031e867ff29e6e2b9b4b0674cc9dd1b3848e0ceb758301a28
 size 14710155092

last-checkpoint/trainer_state.json

@@ -11,37 +11,37 @@
     {
       "epoch": 0.019230769230769232,
       "eval_loss": 1.8673125505447388,
-      "eval_runtime": 14.8131,
-      "eval_samples_per_second": 101.329,
-      "eval_steps_per_second": 6.346,
+      "eval_runtime": 14.7715,
+      "eval_samples_per_second": 101.615,
+      "eval_steps_per_second": 6.364,
       "step": 1
     },
     {
       "epoch": 0.19230769230769232,
-      "grad_norm": 29.625,
+      "grad_norm": 18.375,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 2.4447,
+      "loss": 2.4377,
       "step": 10
     },
     {
       "epoch": 0.38461538461538464,
-      "grad_norm": 246.0,
+      "grad_norm": 80.5,
       "learning_rate": 0.00013333333333333334,
-      "loss": 3.8293,
+      "loss": 2.8471,
       "step": 20
     },
     {
       "epoch": 0.5769230769230769,
-      "grad_norm": 96.5,
+      "grad_norm": 1200.0,
       "learning_rate": 0.0002,
-      "loss": 6.931,
+      "loss": 7.8725,
       "step": 30
     },
     {
       "epoch": 0.7692307692307693,
-      "grad_norm": 804.0,
+      "grad_norm": 37.25,
       "learning_rate": 0.00019984815164333163,
-      "loss": 11.6713,
+      "loss": 13.1972,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0acef938a7d9ffe7b10254d7cbe4256ddc2dc212f47d8b0cfb76c4ad76b57933
+oid sha256:53ebcd35271d188c087a5f00ee35959f144cc8fbcdfc0d1744678c3f065510bd
 size 6776