Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1913442b5ba9db501a59f636cff09ffec76c661222feb7039f2ed622f862c39f
+oid sha256:296451955b91a879b69542db0ed8f120795369ac922259c8fd78ab3b037e8e8f
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988fcbcbd8e15b27e3171e61f2536e36c47149cb01b30ac5fb63f10668acc3a9
+oid sha256:421372eadde9efaf736416f68e72ffb171c721f0dbad12b193f1b2885ea775f5
 size 1386414411

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f4cb4b203fe2f79e7881bacfacd90f4cda067284c21971e82acaddee89f0dae
+oid sha256:3cd719d277ab3a3c6d7d709a00e4a19652ccafb36d0add1dae3055b0f75c16da
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
+oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
 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": 0.5,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,80 @@
       "eval_samples_per_second": 174.439,
       "eval_steps_per_second": 29.131,
       "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 4.671233177185059,
+      "learning_rate": 3.254352716947074e-06,
+      "loss": 19.091270446777344,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.2631611824035645,
+      "learning_rate": 3.1214301147033453e-06,
+      "loss": 19.065214538574217,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 4.104111671447754,
+      "learning_rate": 2.9808470076610163e-06,
+      "loss": 19.055906677246092,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.979343414306641,
+      "learning_rate": 2.833563720990581e-06,
+      "loss": 18.942726135253906,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.06987084148727984,
+      "eval_loss": 9.471638679504395,
+      "eval_runtime": 5.8172,
+      "eval_samples_per_second": 171.903,
+      "eval_steps_per_second": 28.708,
+      "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 4.60034704208374,
+      "learning_rate": 2.680586348883286e-06,
+      "loss": 18.900166320800782,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.487170696258545,
+      "learning_rate": 2.5229598819076393e-06,
+      "loss": 18.824652099609374,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 4.3784661293029785,
+      "learning_rate": 2.36176106866422e-06,
+      "loss": 18.77193603515625,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.88219952583313,
+      "learning_rate": 2.198091060500926e-06,
+      "loss": 18.777445983886718,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.07486888454011742,
+      "eval_loss": 9.392426490783691,
+      "eval_runtime": 5.7667,
+      "eval_samples_per_second": 173.409,
+      "eval_steps_per_second": 28.959,
+      "step": 100
     }
   ],
   "logging_steps": 5,