Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d577a4af63db8c09b1ec8312f6fc9cb0fd9e9961dd5efbe77ffd6cc420192e
+oid sha256:4e60997407deca636d9fc0145f755fa984d1737bfc8400b79a605021e9112b1e
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f8f406b32f3d21b161f37f720d2b4d914b88053f5e49d79ca3167ac1d82da2
+oid sha256:f8ef3109a2051671d0427813ffa2e4c489b4d95173cb82b60acdada432e66e51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0796812749003984,
+  "epoch": 0.09561752988047809,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 34.946,
       "eval_steps_per_second": 8.835,
       "step": 25
+    },
+    {
+      "epoch": 0.08605577689243028,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.09561752988047809,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.09561752988047809,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5712,
+      "eval_samples_per_second": 35.001,
+      "eval_steps_per_second": 8.849,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3311051105894400.0,
+  "total_flos": 3973261327073280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null