Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288305345d2feb79d5744e4f5f78dcc3aff20b98008d2805ec252857352c7e12
+oid sha256:ef76c0c202b1a1c3a6f77cf15e3708521009eebcae6684592011f2cd0eab4515
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece6e267f981c73f1acc656bdf2eeb13bb97f374268684768a57b00f6c3e1ade
+oid sha256:ecba24a2e9d82f9a8477398ba47d19289c176eac2160a25b25f398204068b1ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01593625498007968,
+  "epoch": 0.03187250996015936,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 35.09,
       "eval_steps_per_second": 8.872,
       "step": 5
+    },
+    {
+      "epoch": 0.019123505976095617,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.028685258964143426,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.03187250996015936,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5738,
+      "eval_samples_per_second": 34.989,
+      "eval_steps_per_second": 8.846,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 662210221178880.0,
+  "total_flos": 1324420442357760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null