Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bcbd3ef09d1fb642fc86e31c099f5efe1ec156012f9dfbf6b652322849976b
+oid sha256:4b49f051077a72cc026e7aa4861918fffcb8ea97e982efa4abd6591b98fae9c8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1cddb81a0f217517c0500b0f01493decc296111738c617b0b321989b1fc2b0
+oid sha256:03a67e1218a684240a269d75069a02f196a9c9742eb0114d107b808e267b1450
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00639386189258312,
+  "epoch": 0.01278772378516624,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 0.0,
       "step": 5
+    },
+    {
+      "epoch": 0.0076726342710997444,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0076726342710997444,
+      "eval_loss": NaN,
+      "eval_runtime": 39.595,
+      "eval_samples_per_second": 8.334,
+      "eval_steps_per_second": 4.167,
+      "step": 6
+    },
+    {
+      "epoch": 0.008951406649616368,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.010230179028132993,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.011508951406649617,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.011508951406649617,
+      "eval_loss": NaN,
+      "eval_runtime": 39.6053,
+      "eval_samples_per_second": 8.332,
+      "eval_steps_per_second": 4.166,
+      "step": 9
+    },
+    {
+      "epoch": 0.01278772378516624,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null