Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6982bcc60cdab0257c5094b578ba6dd17785574ecd91ea21df18552dbdab50
+oid sha256:d21cee069e647b1dc485876bb526cd2a034f86889d63f949f981856c2a0bf78c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfc6c9a79d5a3b2c5d198ce0b76d564b33522114642fd45d0f84103f7381088
+oid sha256:88abfd0964de8635d40395a658f59c81d24f5a44cd2bc9d3629b24d56183e900
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000125233835051385,
+  "epoch": 0.00018785075257707752,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 4.049,
       "eval_steps_per_second": 4.049,
       "step": 4
+    },
+    {
+      "epoch": 0.00015654229381423127,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00018785075257707752,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00018785075257707752,
+      "eval_loss": NaN,
+      "eval_runtime": 3370.752,
+      "eval_samples_per_second": 3.99,
+      "eval_steps_per_second": 3.99,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2812517994725376.0,
+  "total_flos": 4218776992088064.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null