Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121806b01241056a95decc2f67d29ad6d869f702fdf9ae9c62cd960f641c6e60
+oid sha256:9b2bf4ba55112ac493fbfdf4fc212ea31e5e3c2df0a9a8f006552c0f9d7ffced
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f318b3e94880cce9a0b14efd0342e17d85587d5e8d2bd6c25d5adc106e4a5a
+oid sha256:75b6469988d6f22d7b6a42244e542a23529124dbec8bae8b086fba39a800d1b6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5f25037891bc7aff564a65fa1037a698161cc4670f7bf98409bc80c41ace77
+oid sha256:390c0027bbfe2ad79f7eebbbab1c6be6399953d2c307f3b30d4435c5cefb6d38
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5925925925925926,
+  "epoch": 0.7407407407407407,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,13 +59,26 @@
       "eval_samples_per_second": 1.904,
       "eval_steps_per_second": 0.239,
       "step": 400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0,
+      "loss": 8.2845,
+      "step": 500
+    },
+    {
+      "epoch": 0.74,
+      "eval_runtime": 788.246,
+      "eval_samples_per_second": 1.903,
+      "eval_steps_per_second": 0.239,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.3296159531008e+16,
+  "total_flos": 1.0412019941376e+17,
   "trial_name": null,
   "trial_params": null
 }