Training in progress, step 54, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bd53e406d3ec1f854877d7973c4484bead90a7eec17d8008bd799eb224bb93
+oid sha256:f53293838445a6d8e66c7909589708a708049e2eff3d9cfaaf613030a90fe346
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2184dee4b408b279b5c02427b1aad0c6149bd58c42401dc540958e2815a56404
+oid sha256:2425b3861618a945a0437a5dfb29ac97fcd65c047bd59e2820e3ecf2bf6b2058
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
+oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05044666316342617,
+  "epoch": 0.0605359957961114,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 8.27,
       "eval_steps_per_second": 4.137,
       "step": 45
+    },
+    {
+      "epoch": 0.05380977404098791,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010904928748046599,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05717288491854966,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010095877928081196,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.0605359957961114,
+      "grad_norm": NaN,
+      "learning_rate": 9.25084022891929e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.0605359957961114,
+      "eval_loss": NaN,
+      "eval_runtime": 363.2733,
+      "eval_samples_per_second": 8.272,
+      "eval_steps_per_second": 4.137,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.909440763441971e+17,
+  "total_flos": 3.4913289161303654e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null