Training in progress, step 420, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaac6881df4f9c17d91449206e0a2a594f42c6e20b4c268fe7c634c24ea1a23b
+oid sha256:f06539a97078f4c0d92767cc0e150d2a513b0f8a07cdfb982a87634c993416d0
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019d764b8c1173a11348d363d9c80b9a732cc706db87376a2e2f30a82e520afa
+oid sha256:1f1b52bf45667416d27a79e876f73a7096ab7bec6f0337ef1273ce52b2ceeb8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac207b57c6cefba3838e335ba7ebf320ffdaee8162f1c0afc72ea9ad9f0725f
+oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02009008649898354,
+  "epoch": 0.022322318332203932,
   "eval_steps": 42,
-  "global_step": 378,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -969,6 +969,112 @@
       "eval_samples_per_second": 13.38,
       "eval_steps_per_second": 1.673,
       "step": 378
+    },
+    {
+      "epoch": 0.02024953162992785,
+      "grad_norm": NaN,
+      "learning_rate": 1.3860256808630428e-05,
+      "loss": 0.0,
+      "step": 381
+    },
+    {
+      "epoch": 0.020408976760872166,
+      "grad_norm": NaN,
+      "learning_rate": 1.3202379370768252e-05,
+      "loss": 0.0,
+      "step": 384
+    },
+    {
+      "epoch": 0.020568421891816478,
+      "grad_norm": NaN,
+      "learning_rate": 1.2558115014363592e-05,
+      "loss": 0.0,
+      "step": 387
+    },
+    {
+      "epoch": 0.020727867022760794,
+      "grad_norm": NaN,
+      "learning_rate": 1.1927702081543279e-05,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.020887312153705106,
+      "grad_norm": NaN,
+      "learning_rate": 1.1311373790174657e-05,
+      "loss": 0.0,
+      "step": 393
+    },
+    {
+      "epoch": 0.02104675728464942,
+      "grad_norm": NaN,
+      "learning_rate": 1.0709358147587884e-05,
+      "loss": 0.0,
+      "step": 396
+    },
+    {
+      "epoch": 0.021206202415593733,
+      "grad_norm": NaN,
+      "learning_rate": 1.0121877866225781e-05,
+      "loss": 0.0,
+      "step": 399
+    },
+    {
+      "epoch": 0.02136564754653805,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 402
+    },
+    {
+      "epoch": 0.02152509267748236,
+      "grad_norm": NaN,
+      "learning_rate": 8.991387270152201e-06,
+      "loss": 0.0,
+      "step": 405
+    },
+    {
+      "epoch": 0.021684537808426677,
+      "grad_norm": NaN,
+      "learning_rate": 8.448795174344804e-06,
+      "loss": 0.0,
+      "step": 408
+    },
+    {
+      "epoch": 0.02184398293937099,
+      "grad_norm": NaN,
+      "learning_rate": 7.921574722852343e-06,
+      "loss": 0.0,
+      "step": 411
+    },
+    {
+      "epoch": 0.022003428070315304,
+      "grad_norm": NaN,
+      "learning_rate": 7.409920958039795e-06,
+      "loss": 0.0,
+      "step": 414
+    },
+    {
+      "epoch": 0.022162873201259616,
+      "grad_norm": NaN,
+      "learning_rate": 6.9140231634602485e-06,
+      "loss": 0.0,
+      "step": 417
+    },
+    {
+      "epoch": 0.022322318332203932,
+      "grad_norm": NaN,
+      "learning_rate": 6.43406479383053e-06,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.022322318332203932,
+      "eval_loss": NaN,
+      "eval_runtime": 2368.3875,
+      "eval_samples_per_second": 13.38,
+      "eval_steps_per_second": 1.673,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.785149574490358e+17,
+  "total_flos": 6.433810413351076e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null