Training in progress, step 170, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06fefafb99b72eb9a89a4f22d4957163eefd15702bb61db525be3f17d1edf9c
+oid sha256:174629798f1751855c82463a7705c720340837ee6db0dcd2d86197123ea64184
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcdf6ad7bcb0673e059b6db1cf40c1b430a276d46df182e42ba7b0335dbf78a
+oid sha256:a7cb893c0f1716ccf6d17f8f4d4752e2f3ce2e01dcdaef4cfc910abf78001071
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76ff8614026ec7c5c2d9793615ca4e2f707e550ce0b5a4376af475431afe3f1
+oid sha256:c9a138d58efee4722b14f409e14731dcd0935c0eaa8a6078a4918744b9529bab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1681203214064968,
+  "epoch": 0.1868003571183298,
   "eval_steps": 50,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1110,6 +1110,125 @@
       "learning_rate": 2.385012299531262e-05,
       "loss": 0.0,
       "step": 153
+    },
+    {
+      "epoch": 0.16921914703660462,
+      "grad_norm": NaN,
+      "learning_rate": 2.2900622215575197e-05,
+      "loss": 0.0,
+      "step": 154
+    },
+    {
+      "epoch": 0.17031797266671245,
+      "grad_norm": NaN,
+      "learning_rate": 2.1966991411008938e-05,
+      "loss": 0.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.17141679829682027,
+      "grad_norm": NaN,
+      "learning_rate": 2.1049514974601175e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.1725156239269281,
+      "grad_norm": NaN,
+      "learning_rate": 2.0148472378562215e-05,
+      "loss": 0.0,
+      "step": 157
+    },
+    {
+      "epoch": 0.17361444955703592,
+      "grad_norm": NaN,
+      "learning_rate": 1.926413808919542e-05,
+      "loss": 0.0,
+      "step": 158
+    },
+    {
+      "epoch": 0.17471327518714375,
+      "grad_norm": NaN,
+      "learning_rate": 1.8396781483292098e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.17581210081725157,
+      "grad_norm": NaN,
+      "learning_rate": 1.7546666766076655e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1769109264473594,
+      "grad_norm": NaN,
+      "learning_rate": 1.671405289072718e-05,
+      "loss": 0.0,
+      "step": 161
+    },
+    {
+      "epoch": 0.17800975207746722,
+      "grad_norm": NaN,
+      "learning_rate": 1.5899193479495857e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.17910857770757502,
+      "grad_norm": NaN,
+      "learning_rate": 1.5102336746453053e-05,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.18020740333768284,
+      "grad_norm": NaN,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 0.18130622896779067,
+      "grad_norm": NaN,
+      "learning_rate": 1.3563596678325606e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.1824050545978985,
+      "grad_norm": NaN,
+      "learning_rate": 1.2822182058371878e-05,
+      "loss": 0.0,
+      "step": 166
+    },
+    {
+      "epoch": 0.18350388022800632,
+      "grad_norm": NaN,
+      "learning_rate": 1.2099707404093203e-05,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 0.18460270585811414,
+      "grad_norm": NaN,
+      "learning_rate": 1.1396392788268052e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.18570153148822197,
+      "grad_norm": NaN,
+      "learning_rate": 1.0712452447341582e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 0.1868003571183298,
+      "grad_norm": NaN,
+      "learning_rate": 1.0048094716167095e-05,
+      "loss": 0.0,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1129,7 +1248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.953713627035075e+17,
+  "total_flos": 9.933231490785608e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null