Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10239be6e3cd4f5e89f2ac25a3b3c925a1d419acc365d80f558a325fd438b16
+oid sha256:17fce54bd0a6cc40b60ba225aa1c0d6428967ac23278b1e4779f9ff86cc19f95
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4558c7ef3834ff59ddefc932ce8df0fd0dd2dc9c93b1481f3635fd4818e96c8
+oid sha256:06d5748edc7979e819f3b71a0a40dee945e7c26acf2012c6a5ec934764f9dcee
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17c78731e93c053cc5bdd46a999e26416061fc6f401c1eac6682002c6f7cf23
+oid sha256:f891a168fb4edd3efbb37e4906a84228928d2ce90f434f192d8f2e669611925b
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
 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": 0.3,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,80 @@
       "eval_samples_per_second": 408.879,
       "eval_steps_per_second": 68.283,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.34710416197776794,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 21.448446655273436,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.41463083028793335,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 21.42731628417969,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.4001413583755493,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 21.273895263671875,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.37236735224723816,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 21.325396728515624,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.03863492063492063,
+      "eval_loss": 10.63491153717041,
+      "eval_runtime": 2.5692,
+      "eval_samples_per_second": 389.224,
+      "eval_steps_per_second": 65.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.6012778878211975,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 21.228472900390624,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.496539831161499,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 21.14513244628906,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.48418062925338745,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 21.062947082519532,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.542204737663269,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 20.998651123046876,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.05380952380952381,
+      "eval_loss": 10.491544723510742,
+      "eval_runtime": 2.5694,
+      "eval_samples_per_second": 389.199,
+      "eval_steps_per_second": 64.996,
+      "step": 60
     }
   ],
   "logging_steps": 5,