Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e569b5db4920ffae00ac4039564af28eb158a3e747021c96a08102a0ff9865a
+oid sha256:38042cd2489098d9b4939a59988ffa044fb5d29acc22328bcc59b69df59cd348
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cc77b0b0bf090ec2a03f2d6f01581488c32af3545b07c31844fee6e2c39c13
+oid sha256:2caab57c9738a6223b66a33175b22839bf9437a089ed80e62b0e4247b5a00c6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00041632406665348306,
+  "epoch": 0.0008326481333069661,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0004995888799841797,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006244860999802246,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006661185066455729,
+      "eval_loss": NaN,
+      "eval_runtime": 223.5077,
+      "eval_samples_per_second": 45.251,
+      "eval_steps_per_second": 22.626,
+      "step": 16
+    },
+    {
+      "epoch": 0.0007493833199762695,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 592730073858048.0,
+  "total_flos": 1233846276194304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null