Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05146d0139b00f4be557d2f9fb9850bd3c3eef0191546e8127aeaca409558595
+oid sha256:f6a427c8d68c66b1624c75f774a560c40fdebdb2d941db156176d4f64f868f39
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d763a617ca5e65007be84779b9da87d83b12cd96b4abaead9266b6ea7c245274
+oid sha256:43abfe5db79179aacaa8d41c7e4a05eb44e72d224079595d6d693845af52a2d8
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27d5e9c91dc5b481af1a74df9cf562559184e94009cb11852e3c2011ad2ace9
+oid sha256:172c187709f4e107d7af2bbca0feab9c6e8888e30d1d3ca9aacd5e9bf0ab1a69
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f189793170f205a894136fd88e55d8f1f19c6ff974d6ec6c00c36064a79076
+oid sha256:5253c46d70f6e7398a95913bd2b428f7e1052a7a71f011fabefce2b0c0342d83
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c546bfb0b72265a73baa6ed5d9e7f51e075e736bf2a6896c42c569e9647b77e7
+oid sha256:28ce995976843ea29dcf27303959f0b6a782b62ac5ec5d7682e78bdf61d82c85
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09,
+  "epoch": 0.1,
   "eval_steps": 5,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,31 @@
       "eval_samples_per_second": 13.864,
       "eval_steps_per_second": 6.932,
       "step": 90
+    },
+    {
+      "epoch": 0.095,
+      "eval_accuracy": 0.06873333333333333,
+      "eval_loss": 16.8882999420166,
+      "eval_runtime": 40.7406,
+      "eval_samples_per_second": 12.273,
+      "eval_steps_per_second": 6.136,
+      "step": 95
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.5192229747772217,
+      "learning_rate": 3.973800426880847e-06,
+      "loss": 144.29556640625,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.07646666666666667,
+      "eval_loss": 16.831998825073242,
+      "eval_runtime": 35.9838,
+      "eval_samples_per_second": 13.895,
+      "eval_steps_per_second": 6.948,
+      "step": 100
     }
   ],
   "logging_steps": 100,