Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887ff07c00d031a39b0ba1dac930e46878bfe35ea70bcd973da896b8116c8886
+oid sha256:6a605582c38a0c725a08493abc72794cb54c84e8bfb09f90dab88345dc4f2c30
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1fb96d9009ad7a4255d9ca47aa50400c1330b43cd2cca7c951575e89172800b
+oid sha256:262cf807bd2b5ce4d5dc934dea831b9e6d987331eb8b54f0e3b980d3f8472f99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006387429538667901,
+  "epoch": 0.0012774859077335802,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 26.98,
       "eval_steps_per_second": 13.49,
       "step": 10
+    },
+    {
+      "epoch": 0.0007664915446401482,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009581144308001853,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009581144308001853,
+      "eval_loss": NaN,
+      "eval_runtime": 301.093,
+      "eval_samples_per_second": 21.894,
+      "eval_steps_per_second": 10.947,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011497373169602222,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012774859077335802,
+      "eval_loss": NaN,
+      "eval_runtime": 536.7934,
+      "eval_samples_per_second": 12.28,
+      "eval_steps_per_second": 6.14,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 980720642162688.0,
+  "total_flos": 2001470698291200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null