Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a99e4b71ea57d5dfd637c8af4145423a4425283bb3e660d6fc3f3e4636b8b43
+oid sha256:96e4cf0a14390d8c3cec2477094799900764970c6a2458451fd1ced00c131dac
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83aaed516f64f5baf9a711eff221ac2ad8c7aee02d91f64dc7a32a15627f8e73
+oid sha256:62866db4807dd220d01832fd2dd27cfd8daed7e085bc5244025717f6e244ea6c
 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": 0.0004980947874380495,
+  "epoch": 0.000996189574876099,
   "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": 0.0005977137449256594,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007471421811570742,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007969516599008791,
+      "eval_loss": NaN,
+      "eval_runtime": 292.7216,
+      "eval_samples_per_second": 28.881,
+      "eval_steps_per_second": 14.44,
+      "step": 16
+    },
+    {
+      "epoch": 0.000896570617388489,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 527551495667712.0,
+  "total_flos": 1042235881684992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null