Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b2ca7f43ca82877578ec1206cfea3f964d5873185512c28a549470009218c3
+oid sha256:a87d93160841f3ca161a25e0a81f69b0a48553729a0db355b0fd20c590ea97cd
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c7e81fb1d098a007f5ef31c25604a306a2978ec61a39d7d8174e4540b17e99
+oid sha256:241920909455841b12c88c41a3e9b3a02a138ad47ca175a12b49447b059cf563
 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": 0.0002789166875854182,
+  "epoch": 0.0005578333751708364,
   "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": 0.0003347000251025019,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.00041837503137812733,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004462667001366692,
+      "eval_loss": NaN,
+      "eval_runtime": 2334.0846,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 3.234,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005020500376537528,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4658232928763904.0,
+  "total_flos": 9668030606868480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null