Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d595b6097d5ea5899017cb7419914a5d343c686564ed5b44e6da8fdea58e73f
+oid sha256:a87cf68cd73cc09d84eddf6b24047ae93ec7ea3179286a9d0dd608a941983944
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb1aabbefe84157d031c54ae6b3bd21383d0d9b97f5b647a54f8f924461e50b
+oid sha256:c65ac5d1996759fc101d94091483fe68e76afe4e0ed9d35bfcbbe3519ad4cbd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027777777777777776,
+  "epoch": 0.05555555555555555,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.217,
       "eval_steps_per_second": 6.608,
       "step": 3
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.655,
+      "step": 5
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": NaN,
+      "eval_runtime": 3.4916,
+      "eval_samples_per_second": 13.174,
+      "eval_steps_per_second": 6.587,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1427980890931200.0,
+  "total_flos": 2776629510144000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null