Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86ba9385bb768d29deab79937c811ef79a601d619335c9e94af62c9f11709ce
+oid sha256:c3161d89e2ad1b44a18bf418bfb17aa903d17835c252c09465b64747372bac3f
 size 70667778

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1de991a5e8b028670d79166d941671fcf1f558f0044b08eaf5154d066f0048
+oid sha256:06ab5129ab155330a39a9371aacd2f73f3677218096c1c34b3766d995f841a91
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5995616407d184ecedacf74ac31cd0731474c7e2323f03405d89945bad93ff
+oid sha256:81435bd0a6a3789b553c69a79f8c384151f9688d0cd7d745e20e5aadeece4761
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b375860c66674ec9637bb873a1ff676ec525ee5502840d2f1d554d4237b8f0c4
+oid sha256:844a9e8b65ea1c19a7e6553433121a4f8c699c309e7900990529efa7ada6321b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.512,
+  "epoch": 0.768,
   "eval_steps": 12,
-  "global_step": 24,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -199,6 +199,98 @@
       "eval_samples_per_second": 21.061,
       "eval_steps_per_second": 5.332,
       "step": 24
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": NaN,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 5.8e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 6.2e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": NaN,
+      "learning_rate": 6.6e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": NaN,
+      "learning_rate": 7.2e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.768,
+      "eval_loss": NaN,
+      "eval_runtime": 3.6511,
+      "eval_samples_per_second": 21.637,
+      "eval_steps_per_second": 5.478,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -218,7 +310,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3460580643962880.0,
+  "total_flos": 5190870965944320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null