Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4811fde242bfca38ce3d3c028e88cfa10c1f7847428a2306e99182a621f8cea
+oid sha256:bcfe01881473de8e1a7ac516dc8e77e0be29a7a45de5d717f37977a8554b0515
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b01d167e870132b740b486718ced50089645724510590f5e41cefd0db8468a
+oid sha256:30df0b38d5053bc4ffa0913ef08050702fd55c4cf4258d9396e935f765973a75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22712933753943218,
+  "epoch": 0.45425867507886436,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 8.711,
       "eval_steps_per_second": 4.355,
       "step": 9
+    },
+    {
+      "epoch": 0.3028391167192429,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.3785488958990536,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.45425867507886436,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.45425867507886436,
+      "eval_loss": NaN,
+      "eval_runtime": 15.4146,
+      "eval_samples_per_second": 8.693,
+      "eval_steps_per_second": 4.347,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.913979034750157e+16,
+  "total_flos": 9.943001056935936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null