Training in progress, step 130, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b894b16459384adc9eae088c49c6239b3d317b6a2aad7c22d872e9a4a95a5ab5
+oid sha256:0286051627e6304668e950769d3d0ae229f4fdf123708da947d2347976384293
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ff8b11311c3c56642b3255a3d8006dc750a14cb5908fb3673f7444f527b18f
+oid sha256:43da8c862366b3e2ebfa7b330e46a7ff17280b46e3a69cf9fb9698df9bd584d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
+oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016531844996290932,
+  "epoch": 0.01836871666254548,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 50.554,
       "eval_steps_per_second": 6.319,
       "step": 117
+    },
+    {
+      "epoch": 0.01695573845773429,
+      "grad_norm": NaN,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.017379631919177647,
+      "grad_norm": NaN,
+      "learning_rate": 8.899896227604509e-06,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 0.017803525380621004,
+      "grad_norm": NaN,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 0.0,
+      "step": 126
+    },
+    {
+      "epoch": 0.01822741884206436,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 0.01836871666254548,
+      "eval_loss": NaN,
+      "eval_runtime": 235.7866,
+      "eval_samples_per_second": 50.554,
+      "eval_steps_per_second": 6.319,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4957829873926144e+16,
+  "total_flos": 2.773092208214016e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null