Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1411e2589dfda757347871aff488a7c5b39f762fe857b7248a6767a9a2d838b3
+oid sha256:05030e503b160bc7361b19d6d4e584f44e3e6bdbf1dc770eded719f4f73c8c04
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56594128c7594580f49086e61a4a3d2833be1c4c5fb6b7d78f9b6bac541e86df
+oid sha256:0435aeb4ff31a82680a8702e172133c80e1e8d359ec3bddd30ccc6e396c167c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012621665574407146,
+  "epoch": 0.002524333114881429,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 28.549,
       "eval_steps_per_second": 14.278,
       "step": 13
+    },
+    {
+      "epoch": 0.0019417947037549455,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.7588,
+      "step": 20
+    },
+    {
+      "epoch": 0.002524333114881429,
+      "eval_loss": NaN,
+      "eval_runtime": 152.0217,
+      "eval_samples_per_second": 28.529,
+      "eval_steps_per_second": 14.268,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2672822958686208.0,
+  "total_flos": 5345645917372416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null