Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ea57d95f189e14afef9705561103ee91a6e9ba01e5482796d19fc2459d71e2
+oid sha256:8b6245f03704115816d35e603ca29927b3a3ea2bead3845506165cbe21320666
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b13a9b1047bb4b6f08d1c4cdf00a090f9620623f2a2765a0675250b296d77fd
+oid sha256:4d4c7644a5ae0da2702bffc998ab434f80e9981db184c373d82506de4898b577
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c70e1001ae0e367150867105486fed534a3bc9b59aab53fe74124dba56db2a
+oid sha256:97bd3d1a2f58ae7c5971df94ab38f5e952b7947bc754ebd01bb0045964a824d2
 size 14645

last-checkpoint/trainer_state.json

@@ -11,39 +11,39 @@
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.1988103836774826,
+      "grad_norm": 0.2323141247034073,
       "learning_rate": 1.6e-06,
-      "loss": 21.93964385986328,
+      "loss": 21.980325317382814,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.19530963897705078,
+      "grad_norm": 0.2334250658750534,
       "learning_rate": 3.6e-06,
-      "loss": 21.938941955566406,
+      "loss": 21.9706298828125,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.20022961497306824,
+      "grad_norm": 0.22430387139320374,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 21.935198974609374,
+      "loss": 21.961314392089843,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.18916556239128113,
+      "grad_norm": 0.2190800905227661,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 21.938011169433594,
+      "loss": 21.96648712158203,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 1.3431013431013431e-05,
-      "eval_loss": 10.96605396270752,
-      "eval_runtime": 91.788,
-      "eval_samples_per_second": 10.895,
-      "eval_steps_per_second": 1.819,
+      "eval_accuracy": 3.131115459882583e-05,
+      "eval_loss": 10.98162841796875,
+      "eval_runtime": 6.0042,
+      "eval_samples_per_second": 166.549,
+      "eval_steps_per_second": 27.814,
       "step": 20
     }
   ],