Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a101c402afaf74f956b89a827bf8901a0ab5d7c8c859c32d66cb04672e72516d
+oid sha256:586c0c7eb90a261946f8ea74a1268cb02478562821ccbd056f155359c5cc2c57
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172aeb48af9586a198746bc68bf5d4bdd20f0201d148d0a93190535d1641e37b
+oid sha256:200b84040938cd43fcea5483819d3e12d1d5f95dfddbfe435f19ecf452dea1b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008086366890820007,
+  "epoch": 0.008895003579902009,
   "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": 26.823,
       "eval_steps_per_second": 13.411,
       "step": 90
+    },
+    {
+      "epoch": 0.008355912453847342,
+      "grad_norm": NaN,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.008625458016874676,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.008895003579902009,
+      "grad_norm": NaN,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.008895003579902009,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.3879,
+      "eval_samples_per_second": 26.829,
+      "eval_steps_per_second": 13.414,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.409536599261184e+16,
+  "total_flos": 1.0355962791591936e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null