Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d71684322ae157eaffc567f9cbe9b84a34d091b302f372957a12d6c437d2b57
+oid sha256:5f12d59d9eda5ce3a7a5c06a22c0ea3f0790d059dd154c77e8cad1df04b7777a
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77909621d5eba6b54e091d8d90586d0c5a8d0fda5747511df5d96ada36a5983d
+oid sha256:27664fe9ad8ed8445e33c7255f967acf6b37dd9b2ca722042210d22bd07b0640
 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": 0.0002531378546566818,
+  "epoch": 0.0005062757093133636,
   "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": 56.869,
       "eval_steps_per_second": 28.435,
       "step": 3
+    },
+    {
+      "epoch": 0.00033751713954224236,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.00042189642442780296,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005062757093133636,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 1.4847,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005062757093133636,
+      "eval_loss": NaN,
+      "eval_runtime": 88.5895,
+      "eval_samples_per_second": 56.327,
+      "eval_steps_per_second": 28.164,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 144327309262848.0,
+  "total_flos": 288654618525696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null