Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e0658a466d23d18bec8dd6df8b12c5738c285dbabaefec00c779f8e99f0506
+oid sha256:16e9353f754dc20cf77ef7626d29c2c848a1e0d3596071fa01d0d59ff344ff74
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92dec5022e8046bcb71cd16fd53b66de4d7abe1b87b9003b9ed2ad83377f2e02
+oid sha256:4bbce49a637c64091bf19abfd402b75bee59db4098db4ce7e395e345424f398f
 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": 0.027932960893854747,
+  "epoch": 0.055865921787709494,
   "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": 36.876,
       "eval_steps_per_second": 4.64,
       "step": 5
+    },
+    {
+      "epoch": 0.0335195530726257,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.05027932960893855,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "eval_loss": NaN,
+      "eval_runtime": 8.2028,
+      "eval_samples_per_second": 36.817,
+      "eval_steps_per_second": 4.633,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1360723653427200.0,
+  "total_flos": 2721447306854400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null