Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53752a5719d957ec705120edefcb193e8f2ac13b08ec68d9fb434c410db1eb5
+oid sha256:0d576d6497b53097822f0c192a2e506acdf16500e8c835c7e8a2c19a82775bad
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca82a561ff77829be4f53f199829857bccfb693ef73aa2d0668f096c355cee4
+oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00048258181269793395,
+  "epoch": 0.0009651636253958679,
   "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": 16.603,
       "eval_steps_per_second": 8.302,
       "step": 3
+    },
+    {
+      "epoch": 0.0006434424169305786,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008043030211632232,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009651636253958679,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009651636253958679,
+      "eval_loss": NaN,
+      "eval_runtime": 631.2792,
+      "eval_samples_per_second": 16.585,
+      "eval_steps_per_second": 8.293,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135045208375296.0,
+  "total_flos": 6270090416750592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null