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 sha256:44e2f957d6cccdb3cf233adcbd8816c7b747459f2f9c97c95046aa3b51183a80
+oid sha256:785ad6e5b59a84a0e4b7ad719a169ffabf6724dcf1230a8d0996043f3f7e8b46
 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": 0.00047441706003747893,
+  "epoch": 0.0009488341200749579,
   "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": 29.126,
       "eval_steps_per_second": 14.563,
       "step": 10
+    },
+    {
+      "epoch": 0.0005693004720449747,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007116255900562184,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007116255900562184,
+      "eval_loss": NaN,
+      "eval_runtime": 304.7906,
+      "eval_samples_per_second": 29.122,
+      "eval_steps_per_second": 14.561,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008539507080674621,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009488341200749579,
+      "eval_loss": NaN,
+      "eval_runtime": 304.849,
+      "eval_samples_per_second": 29.116,
+      "eval_steps_per_second": 14.558,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 820602986299392.0,
+  "total_flos": 1621191265615872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null