Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9083026baf394fb415584f9450a9815f04c4f920e1a3d7e0792f399cb0c8f14
+oid sha256:90f76a8de4a111f94e4874506056d5e56c27cb584b307fff785cefe3e47d1d2d
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24494dcec7b740a1ea000f51e050a81a7bb6c3b4ff898bada8de0f3588a1a971
+oid sha256:41f2969ae4ead3c37528f775e9e2b2006500a194b7c4533156d56ae7e07b5b5a
 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": 0.02313475997686524,
+  "epoch": 0.04626951995373048,
   "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": 13.542,
       "eval_steps_per_second": 6.771,
       "step": 10
+    },
+    {
+      "epoch": 0.027761711972238288,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.03470213996529786,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03470213996529786,
+      "eval_loss": NaN,
+      "eval_runtime": 13.5144,
+      "eval_samples_per_second": 13.467,
+      "eval_steps_per_second": 6.734,
+      "step": 15
+    },
+    {
+      "epoch": 0.04164256795835743,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.04626951995373048,
+      "eval_loss": NaN,
+      "eval_runtime": 13.5194,
+      "eval_samples_per_second": 13.462,
+      "eval_steps_per_second": 6.731,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 7077766769934336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null