Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a6fa0c896b9cbc1fe6f65bf31302294ced630037ebaff264708f2b7a41a0ae
+oid sha256:1913442b5ba9db501a59f636cff09ffec76c661222feb7039f2ed622f862c39f
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e195a040254afcd7ad74e1c0c7df243f68d666eb967a4e474c95a92a8e154c70
+oid sha256:988fcbcbd8e15b27e3171e61f2536e36c47149cb01b30ac5fb63f10668acc3a9
 size 1386414411

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec712ea0f3379427fe64173254cf253ed5682b59abb87f849afd6299b834917
+oid sha256:6f4cb4b203fe2f79e7881bacfacd90f4cda067284c21971e82acaddee89f0dae
 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": 174.305,
       "eval_steps_per_second": 29.109,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 5.290545463562012,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 20.648074340820312,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.464421272277832,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 20.324154663085938,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 5.148286819458008,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 20.022116088867186,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.950249195098877,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 19.932040405273437,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.06708610567514676,
+      "eval_loss": 9.851630210876465,
+      "eval_runtime": 5.7231,
+      "eval_samples_per_second": 174.73,
+      "eval_steps_per_second": 29.18,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 4.990023612976074,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 19.716999816894532,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.726850986480713,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 19.490966796875,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 5.667174339294434,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 19.308076477050783,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.216722011566162,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 19.342814636230468,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.06902348336594911,
+      "eval_loss": 9.606650352478027,
+      "eval_runtime": 5.7327,
+      "eval_samples_per_second": 174.439,
+      "eval_steps_per_second": 29.131,
+      "step": 60
     }
   ],
   "logging_steps": 5,