Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17fce54bd0a6cc40b60ba225aa1c0d6428967ac23278b1e4779f9ff86cc19f95
+oid sha256:000527a3a265b9e05cd020128ba800f14f377bfbabae4998412c2918195d8125
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d5748edc7979e819f3b71a0a40dee945e7c26acf2012c6a5ec934764f9dcee
+oid sha256:e6432fe547941a7690c2fe66075c977ac4220863b31602ffec25432621ebfa96
 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": 389.199,
       "eval_steps_per_second": 64.996,
       "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.5018299221992493,
+      "learning_rate": 3.254352716947074e-06,
+      "loss": 21.052398681640625,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5535529255867004,
+      "learning_rate": 3.1214301147033453e-06,
+      "loss": 20.81998291015625,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.6942564249038696,
+      "learning_rate": 2.9808470076610163e-06,
+      "loss": 20.625360107421876,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6362656950950623,
+      "learning_rate": 2.833563720990581e-06,
+      "loss": 20.59354248046875,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.06626984126984127,
+      "eval_loss": 10.32943344116211,
+      "eval_runtime": 2.5422,
+      "eval_samples_per_second": 393.359,
+      "eval_steps_per_second": 65.691,
+      "step": 80
     }
   ],
   "logging_steps": 5,