Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7825181dc1b115dfb9ba64470adecc2fc108cec0772c8f3bbb182ef4026bb09
+oid sha256:ec5733327dbf4ff2d78f6d83da361a78ef7620e8d1c1eefc46be30a676689cf5
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448cfb393a9ab3ef1352a632ca10d4f4f9997c44ddbbcc9a3ac0490d983dd594
+oid sha256:d9888cf11cd46e40fd2c19a7119ded600ba7c80040c523b43fe2dacb551b1c0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014266117969821674,
+  "epoch": 0.02139917695473251,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.01646090534979424,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01646090534979424,
+      "eval_loss": NaN,
+      "eval_runtime": 29.7375,
+      "eval_samples_per_second": 25.826,
+      "eval_steps_per_second": 12.913,
+      "step": 30
+    },
+    {
+      "epoch": 0.019204389574759947,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2388186315620352.0,
+  "total_flos": 3582279473430528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null