Training in progress, step 160, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9609f4b966903c1d1f1a328439486f5617f052e946ef1bb6f248d37466f6f3d6
+oid sha256:6b767492292e2934ea3c30fcff6c6a19e7a5964603cd8ec03c783e96c6fe6e87
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f897f47a5a189148c5723ae6d5e03dd35a40403877646007518e71bba38617d3
+oid sha256:5a57842f4acc224ad21928a1671f2ab7b0dd97d6032dc5a65914f1349f4a489a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
+oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2728435412817962,
+  "epoch": 0.3637913883757283,
   "eval_steps": 40,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 8.374,
       "eval_steps_per_second": 4.193,
       "step": 120
+    },
+    {
+      "epoch": 0.3637913883757283,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.3637913883757283,
+      "eval_loss": NaN,
+      "eval_runtime": 88.4091,
+      "eval_samples_per_second": 8.381,
+      "eval_steps_per_second": 4.196,
+      "step": 160
     }
   ],
   "logging_steps": 40,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.72058597523456e+17,
+  "total_flos": 2.300322237948887e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null