Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf8b1843a48d89902e6a38d9dc7ae22eb5e6ee38261b349c2a716fe1bae9c51
+oid sha256:d32c5624e3b33a9857e9efd7b8d874b3d60078bfdbc51ab512c2223db4b8340c
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683579e6a4e531b635154a102854d233c0780acdf55cf1d2eb4d7bfa7e3e8607
+oid sha256:785cb22f7dae101b2ada102c39c8104abc5b7575c9c0d8d0d07d237969af222c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.275,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 206.995,
       "eval_steps_per_second": 25.917,
       "step": 90
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.275,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9586,
+      "eval_samples_per_second": 205.164,
+      "eval_steps_per_second": 25.688,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1617835327488000.0,
+  "total_flos": 1779618860236800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null