Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c00e25cdc0159a953b89e31ee75fb9f4f04268f163b9148e898a67d1ad3fe2
+oid sha256:dc5bdefdaf7ffa59db1d2244a9bf82cb79bb779b47177bfcfe82cbe4e23b05d1
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ec1a2907af41bcd49fe20d0461096a9770864c1c9061542df1c79e4a507473
+oid sha256:27b83988569e6745308f920b05adabfd2539a9e6e063c09c7eb24770d002a296
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a091ed1da45753ae33db029e7b844183915b5f9838c10180e2883aeefdf91d
+oid sha256:c247b88b6d33018a1baf3f963dc59f2afb08b3ad86ca462a6417c10f3bb5cf51
 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": 414.406,
       "eval_steps_per_second": 69.206,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.4181952476501465,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 10.07513656616211,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5301581025123596,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 10.312834930419921,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.5450895428657532,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 10.073713684082032,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4884032905101776,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 10.02478485107422,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.06626984126984127,
+      "eval_loss": 10.08950138092041,
+      "eval_runtime": 2.5801,
+      "eval_samples_per_second": 387.588,
+      "eval_steps_per_second": 64.727,
+      "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.45030277967453003,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 10.068260192871094,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.47731924057006836,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 10.119559478759765,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.4541228711605072,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 10.025191497802734,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5474848747253418,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 9.916156005859374,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.06855555555555555,
+      "eval_loss": 9.982182502746582,
+      "eval_runtime": 2.4782,
+      "eval_samples_per_second": 403.514,
+      "eval_steps_per_second": 67.387,
+      "step": 140
     }
   ],
   "logging_steps": 5,