Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296451955b91a879b69542db0ed8f120795369ac922259c8fd78ab3b037e8e8f
+oid sha256:c5e352bbc53dcdadcadec8245e6c4f457ebf7790fac51411b3b999cf44649beb
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421372eadde9efaf736416f68e72ffb171c721f0dbad12b193f1b2885ea775f5
+oid sha256:0a9d95665e37557687138c324ea96e1690e085e25829ffe4d8d0d87a57bee2f6
 size 1386414411

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd719d277ab3a3c6d7d709a00e4a19652ccafb36d0add1dae3055b0f75c16da
+oid sha256:134a484e532ba4537112198f3087f08c6b36bc828e582ece1b5ba2be14f856b0
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
+oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.7,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,80 @@
       "eval_samples_per_second": 173.409,
       "eval_steps_per_second": 28.959,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 3.9933605194091797,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 18.811434936523437,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.9667704105377197,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 18.78875732421875,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 4.048539161682129,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 18.773907470703126,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.9434831142425537,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 18.89387664794922,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.0761252446183953,
+      "eval_loss": 9.337961196899414,
+      "eval_runtime": 5.872,
+      "eval_samples_per_second": 170.3,
+      "eval_steps_per_second": 28.44,
+      "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 3.8308157920837402,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 18.72384033203125,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.8196702003479,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 18.456109619140626,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 8.1970796585083,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 18.59037628173828,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.069243907928467,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 18.677517700195313,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.0767279843444227,
+      "eval_loss": 9.3079252243042,
+      "eval_runtime": 5.854,
+      "eval_samples_per_second": 170.824,
+      "eval_steps_per_second": 28.528,
+      "step": 140
     }
   ],
   "logging_steps": 5,