Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eadee4ebe800fa691214be7857fcfe10fe82b86351955878498e9f8e40bc735
+oid sha256:d1adb6e2e68cc0af22cfe354c881e1b8a5fe01253b938367238463c9ae7a0450
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac44e1e06d6c7b9ab5257395e1650b841528708459b68719bfb341fb9f24a5c
+oid sha256:1dccb565a82f507a4b0cc3379f6d021cf484cdaa45c0f2ea13578afacca7f880
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bd3d1a2f58ae7c5971df94ab38f5e952b7947bc754ebd01bb0045964a824d2
+oid sha256:e9d1ea809ba32b7efd678ae04203f4d557f85f71b36f396a16e0baf7241d69c8
 size 14645

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.2,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,43 @@
       "eval_samples_per_second": 183.448,
       "eval_steps_per_second": 30.636,
       "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,