Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfe01881473de8e1a7ac516dc8e77e0be29a7a45de5d717f37977a8554b0515
+oid sha256:c2fe3ddb97ed5a3946d0cd6798bfb3c71cdf970e09bb12eaa4801982dea5a915
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b414c8ef6e9245bee4c2cd8d344348d2e648da20b563df8113241485402611
+oid sha256:39acb5a2530dc832149c5d18e7a15da6846a800c716036ccf187a7e397862da3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006499221447430777,
+  "epoch": 0.009748832171146166,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.658,
       "eval_steps_per_second": 4.83,
       "step": 18
+    },
+    {
+      "epoch": 0.007582425022002573,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.008665628596574368,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.009748832171146166,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.009748832171146166,
+      "eval_loss": NaN,
+      "eval_runtime": 965.839,
+      "eval_samples_per_second": 9.659,
+      "eval_steps_per_second": 4.83,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.54951167555666e+16,
+  "total_flos": 1.4324267513334989e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null