Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f3ea2f7c36b85b78f4675a519b37633b89406ff14bb91c0fe4b301eb6e2e46
+oid sha256:a6b4969fac86432f3cee79d008398290ac6dcea40d838e3acd70b61f78ece2ec
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539d12dbc0cccedee74b1639e23f9cf3acab6b36f1c67255f9d80da19df4d222
+oid sha256:0095105e2ac4bdcaf4a00e372b1dcd57138f2181ff7db0cd40cccf4c4d8a7b92
 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": 0.001484230055658627,
+  "epoch": 0.002968460111317254,
   "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": 13.37,
       "eval_steps_per_second": 1.673,
       "step": 5
+    },
+    {
+      "epoch": 0.0017810760667903525,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.002671614100185529,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.002968460111317254,
+      "eval_loss": NaN,
+      "eval_runtime": 424.248,
+      "eval_samples_per_second": 13.374,
+      "eval_steps_per_second": 1.674,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6985170460606464.0,
+  "total_flos": 1.4302968086003712e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null