Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf6f139ba02be458b3ccaf2c430f90c16d331d63746331f20cb2e189fca6e26
+oid sha256:f89274085e5a72669b27a32bb3a39b89af8a49f4ae0f8903954443ef6fc0bf50
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41810fe096e6b4d052f8f28df59f954f31c494aaf06ad1a1e4ef360b424e255b
+oid sha256:1bdfd9e9d4cf201a170f3d9d8b5c4c4a884efa6cc0815364fa54a40ea6d2f93f
 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": 0.04319654427645788,
+  "epoch": 0.08639308855291576,
   "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": 4.227,
       "eval_steps_per_second": 0.542,
       "step": 5
+    },
+    {
+      "epoch": 0.05183585313174946,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.07775377969762419,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "eval_loss": NaN,
+      "eval_runtime": 46.1495,
+      "eval_samples_per_second": 4.225,
+      "eval_steps_per_second": 0.542,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5087486212440064e+16,
+  "total_flos": 5.149536643606118e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null