Training in progress, step 1800, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff4c2bfcf06b79be4317ff34bae31ba578e74123c84195af857650d6ba8cb3a
+oid sha256:26dc13cb6ac51441e383025409dcd9786671e900057035c195c0dae923cd1885
 size 1433527

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d557f86e74119e29eeada16320e8c22da2aceeed989c27520d68545e68a5a4bb
+oid sha256:0668a0b6a76a037af5c84414e9660a433c54cefe3a557b2c139d7d5be4ad983a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ac3cdc5933665fbcca9c0d47f11aec4f7c042b59be339c3da617730e30e090
+oid sha256:a94c005d0c7c69c9a33c6958114bdabd8692c02b64ade7fb506675e5058584d3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2903196540357456,
+  "epoch": 0.4354794810536184,
   "eval_steps": 600,
-  "global_step": 1200,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,22 @@
       "eval_steps_per_second": 0.849,
       "eval_wer": 1.0,
       "step": 1200
+    },
+    {
+      "epoch": 0.4354794810536184,
+      "grad_norm": NaN,
+      "learning_rate": 7.7075310748233e-05,
+      "loss": 0.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4354794810536184,
+      "eval_loss": NaN,
+      "eval_runtime": 1716.7066,
+      "eval_samples_per_second": 13.597,
+      "eval_steps_per_second": 0.85,
+      "eval_wer": 1.0,
+      "step": 1800
     }
   ],
   "logging_steps": 600,
@@ -58,7 +74,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.219217568495472e+18,
+  "total_flos": 1.2336249543125027e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null