Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1adb6e2e68cc0af22cfe354c881e1b8a5fe01253b938367238463c9ae7a0450
+oid sha256:19a6fa0c896b9cbc1fe6f65bf31302294ced630037ebaff264708f2b7a41a0ae
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dccb565a82f507a4b0cc3379f6d021cf484cdaa45c0f2ea13578afacca7f880
-size 350603
+oid sha256:e195a040254afcd7ad74e1c0c7df243f68d666eb967a4e474c95a92a8e154c70
+size 1386414411

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d1ea809ba32b7efd678ae04203f4d557f85f71b36f396a16e0baf7241d69c8
+oid sha256:9ec712ea0f3379427fe64173254cf253ed5682b59abb87f849afd6299b834917
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
+oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,86 +2,49 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.1,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.23910726606845856,
+      "grad_norm": 6.181037902832031,
       "learning_rate": 1.6e-06,
-      "loss": 21.99029541015625,
+      "loss": 21.926864624023438,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.2298264056444168,
+      "grad_norm": 5.942561149597168,
       "learning_rate": 3.6e-06,
-      "loss": 21.960894775390624,
+      "loss": 21.75578155517578,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.21482999622821808,
+      "grad_norm": 5.655824184417725,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 21.95319061279297,
+      "loss": 21.41462097167969,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.21504534780979156,
+      "grad_norm": 5.417076587677002,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 21.970616149902344,
+      "loss": 21.02429962158203,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 1.3698630136986302e-05,
-      "eval_loss": 10.982390403747559,
-      "eval_runtime": 5.4511,
-      "eval_samples_per_second": 183.448,
-      "eval_steps_per_second": 30.636,
+      "eval_accuracy": 0.062084148727984345,
+      "eval_loss": 10.375007629394531,
+      "eval_runtime": 5.7371,
+      "eval_samples_per_second": 174.305,
+      "eval_steps_per_second": 29.109,
       "step": 20
-    },
-    {
-      "epoch": 0.125,
-      "grad_norm": 0.21372699737548828,
-      "learning_rate": 3.9466531944960116e-06,
-      "loss": 21.970256042480468,
-      "step": 25
-    },
-    {
-      "epoch": 0.15,
-      "grad_norm": 0.22921456396579742,
-      "learning_rate": 3.902113032590307e-06,
-      "loss": 21.96063232421875,
-      "step": 30
-    },
-    {
-      "epoch": 0.175,
-      "grad_norm": 0.22464817762374878,
-      "learning_rate": 3.844579509954769e-06,
-      "loss": 21.94104461669922,
-      "step": 35
-    },
-    {
-      "epoch": 0.2,
-      "grad_norm": 0.22148464620113373,
-      "learning_rate": 3.7744456388872234e-06,
-      "loss": 21.96393585205078,
-      "step": 40
-    },
-    {
-      "epoch": 0.2,
-      "eval_accuracy": 1.3698630136986302e-05,
-      "eval_loss": 10.98119068145752,
-      "eval_runtime": 5.4313,
-      "eval_samples_per_second": 184.12,
-      "eval_steps_per_second": 30.748,
-      "step": 40
     }
   ],
   "logging_steps": 5,