Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbc25b315eaec6fdfa5a96894be799d4505aeaa0569efe9adef0b9c9c0e39f4
+oid sha256:8b84975742968de29fcc37417fd70fd74f60f37cd15555f7babcb1cdef75951e
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa7c0721a4a3d85b588484718933d2b751de2198ec9cfb9e99b53e008d4e3d5
+oid sha256:c2f719b4df5d66bc5bd871112ccc5eb12d3fbfde0f855e6872e7a7160b2634b9
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f891a168fb4edd3efbb37e4906a84228928d2ce90f434f192d8f2e669611925b
+oid sha256:08f69188d3c3cb82763f1a7c417921df2b36ee8c259c8364d649bc865aa50546
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
+oid sha256:328cdb13c08312010f0f3f68164c591fc4e8d678a48048f3b4795580c806f456
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.4,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,43 @@
       "eval_samples_per_second": 401.523,
       "eval_steps_per_second": 67.054,
       "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.26950836181640625,
+      "learning_rate": 3.254352716947074e-06,
+      "loss": 22.037962341308592,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.25924476981163025,
+      "learning_rate": 3.1214301147033453e-06,
+      "loss": 22.014053344726562,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.31555065512657166,
+      "learning_rate": 2.9808470076610163e-06,
+      "loss": 21.961640930175783,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2712528705596924,
+      "learning_rate": 2.833563720990581e-06,
+      "loss": 21.988558959960937,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.01443099975586,
+      "eval_runtime": 2.612,
+      "eval_samples_per_second": 382.842,
+      "eval_steps_per_second": 63.935,
+      "step": 80
     }
   ],
   "logging_steps": 5,