Training in progress, step 378, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c845921dd5d38c1bc9a1cff2de771649f69d3bc50aeb640737c71d999adb45d0
+oid sha256:aaac6881df4f9c17d91449206e0a2a594f42c6e20b4c268fe7c634c24ea1a23b
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6155b2f406e14ae258f21b07526ec14202a94f19efd93172b191f2e0672456
+oid sha256:019d764b8c1173a11348d363d9c80b9a732cc706db87376a2e2f30a82e520afa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
+oid sha256:6ac207b57c6cefba3838e335ba7ebf320ffdaee8162f1c0afc72ea9ad9f0725f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017857854665763145,
+  "epoch": 0.02009008649898354,
   "eval_steps": 42,
-  "global_step": 336,
+  "global_step": 378,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -863,6 +863,112 @@
       "eval_samples_per_second": 13.378,
       "eval_steps_per_second": 1.673,
       "step": 336
+    },
+    {
+      "epoch": 0.018017299796707457,
+      "grad_norm": NaN,
+      "learning_rate": 2.43550361297047e-05,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 0.018176744927651773,
+      "grad_norm": NaN,
+      "learning_rate": 2.353425010381063e-05,
+      "loss": 0.0,
+      "step": 342
+    },
+    {
+      "epoch": 0.018336190058596085,
+      "grad_norm": NaN,
+      "learning_rate": 2.272325493947257e-05,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.0184956351895404,
+      "grad_norm": NaN,
+      "learning_rate": 2.192235065998126e-05,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 0.018655080320484713,
+      "grad_norm": NaN,
+      "learning_rate": 2.1131833555559037e-05,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 0.018814525451429028,
+      "grad_norm": NaN,
+      "learning_rate": 2.0351996073748713e-05,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 0.01897397058237334,
+      "grad_norm": NaN,
+      "learning_rate": 1.9583126711224343e-05,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 0.019133415713317656,
+      "grad_norm": NaN,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.019292860844261968,
+      "grad_norm": NaN,
+      "learning_rate": 1.807942593751973e-05,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 0.019452305975206283,
+      "grad_norm": NaN,
+      "learning_rate": 1.7345150812337564e-05,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 0.019611751106150595,
+      "grad_norm": NaN,
+      "learning_rate": 1.66229561726426e-05,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 0.01977119623709491,
+      "grad_norm": NaN,
+      "learning_rate": 1.5913109190450032e-05,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 0.019930641368039223,
+      "grad_norm": NaN,
+      "learning_rate": 1.5215872469825682e-05,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.02009008649898354,
+      "grad_norm": NaN,
+      "learning_rate": 1.4531503949737108e-05,
+      "loss": 0.0,
+      "step": 378
+    },
+    {
+      "epoch": 0.02009008649898354,
+      "eval_loss": NaN,
+      "eval_runtime": 2368.4689,
+      "eval_samples_per_second": 13.38,
+      "eval_steps_per_second": 1.673,
+      "step": 378
     }
   ],
   "logging_steps": 3,
@@ -882,7 +988,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.13648873562964e+17,
+  "total_flos": 5.785149574490358e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null