Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b666fd64552ff6de5ded57be4f781b43a0a116804dd16e67e35e68595de21627
+oid sha256:b180053fb5b80d9b8d5416d16744ea598106e22cdf92b17f74691344ed112311
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409890ae4ab6336c9dd854eb8bf235cb7c71903b578d3d35205c7c0d6dfb35a5
+oid sha256:e53d645ede4d879dfdacf196da80e0fcc385e952923e33d856fdefa597b33f22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008086366890820008,
+  "epoch": 0.0016172733781640017,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 26.766,
       "eval_steps_per_second": 13.383,
       "step": 9
+    },
+    {
+      "epoch": 0.0010781822521093345,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.001347727815136668,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016172733781640017,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016172733781640017,
+      "eval_loss": NaN,
+      "eval_runtime": 1400.0163,
+      "eval_samples_per_second": 26.778,
+      "eval_steps_per_second": 13.389,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9335496454963200.0,
+  "total_flos": 1.879975837827072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null