Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749512039905e54b4fda9b285bfa58998f095aabc18773c9ece09be87caff2a0
+oid sha256:cc542b89b2fb409ffa2a15b109a533053ba9987b3cb65f997a66fde03c3ca98f
 size 20312676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6089a8858f8deb2de47fb0521be50994912c13387776ea61d86b7928ecdc7e3
+oid sha256:d93b8ffb6cde37ebd1d1f1709c31c7b1e2378a4fc738f0c955225ffcdfe0b8dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7b358298aa83a40c1b56e5c320426fa83976856684a928a0b4adb7fc547539
+oid sha256:5c3f3d5c4a86eb24d6104ecbafd33bca7426420d96c84e1b2c30df274293a5af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
+  "epoch": 0.96,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,21 @@
       "eval_samples_per_second": 70.793,
       "eval_steps_per_second": 23.598,
       "step": 8
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": NaN,
+      "eval_runtime": 0.0834,
+      "eval_samples_per_second": 71.935,
+      "eval_steps_per_second": 23.978,
+      "step": 12
     }
   ],
   "logging_steps": 10,
@@ -50,7 +65,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22801104764928.0,
+  "total_flos": 34201657147392.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null