Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b84975742968de29fcc37417fd70fd74f60f37cd15555f7babcb1cdef75951e
+oid sha256:ac5b9baf6de14780fa86a9b96945cdf7b72a2583aad39bcb5b7af228742f8ade
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f719b4df5d66bc5bd871112ccc5eb12d3fbfde0f855e6872e7a7160b2634b9
+oid sha256:98e9dc05c94cca6b374b4e8da945f6ab78f100d5bbd3f9b87005250dd7e07039
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f69188d3c3cb82763f1a7c417921df2b36ee8c259c8364d649bc865aa50546
+oid sha256:d655e73147f6c05694f6b0b5c2c321535c695e45d8c7329d033e75bc36a25404
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328cdb13c08312010f0f3f68164c591fc4e8d678a48048f3b4795580c806f456
+oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.5,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,43 @@
       "eval_samples_per_second": 382.842,
       "eval_steps_per_second": 63.935,
       "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.260957270860672,
+      "learning_rate": 2.680586348883286e-06,
+      "loss": 22.034954833984376,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2659424841403961,
+      "learning_rate": 2.5229598819076393e-06,
+      "loss": 22.037962341308592,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.2600838541984558,
+      "learning_rate": 2.36176106866422e-06,
+      "loss": 21.996064758300783,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2419586181640625,
+      "learning_rate": 2.198091060500926e-06,
+      "loss": 22.00383605957031,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.012611389160156,
+      "eval_runtime": 2.6096,
+      "eval_samples_per_second": 383.201,
+      "eval_steps_per_second": 63.995,
+      "step": 100
     }
   ],
   "logging_steps": 5,