Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f5000117bd7663f548a98f03ef52c55de96e06edf5a12fe5379735a8bcf10b
+oid sha256:0857a937c68c840dd24f04556915949db53732da4a4a835f9521c7a20ade84b9
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02cfb08abee12b17337b98567ba9f28dd70ea9e907b1536d2d444555c87a1e6f
+oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0026582149064512833,
+  "epoch": 0.003987322359676924,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 21.386,
       "eval_steps_per_second": 10.696,
       "step": 26
+    },
+    {
+      "epoch": 0.0030671710459053265,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.003987322359676924,
+      "eval_loss": NaN,
+      "eval_runtime": 192.6149,
+      "eval_samples_per_second": 21.385,
+      "eval_steps_per_second": 10.695,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8250556258713600.0,
+  "total_flos": 1.23758343880704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null