Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4392506bee67a933be2d6f6b5932268dbdea7b2de83ed7dc9c85afe23c68f84e
+oid sha256:8c7755db217291b6bb9b913f26e773f85206608a5b23dd05eb5ea8fd216c683e
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1a78e8cc4706bded81d43c19ec252b7fe917b88d916087e57308bdf7089fa5
+oid sha256:4bf4a70b2f1e0083900a8a144d37753c55636b180594109e7e6c3f925b4e7d11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00011937804040946667,
+  "epoch": 0.00023875608081893335,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 281.746,
       "eval_steps_per_second": 140.873,
       "step": 3
+    },
+    {
+      "epoch": 0.00015917072054595557,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019896340068244447,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00023875608081893335,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00023875608081893335,
+      "eval_loss": NaN,
+      "eval_runtime": 37.9988,
+      "eval_samples_per_second": 278.483,
+      "eval_steps_per_second": 139.241,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6449258299392.0,
+  "total_flos": 12898516598784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null