Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5f6237cf161b70d614d045480ee4f1ec0163f33f25c09e40fe37001ed40835
+oid sha256:060f48fcb919eff7f1e0407050f947b2b241fab41b0aa9bf321c0411a78ebde8
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5b0618184cfb839688f64e61325ac9acc489430f0044385aca5966a2e98dab
+oid sha256:24b3fa9427c043135df5032cea261a6a3e2e32da0b7e7a54546daafc21845f7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012175818823815902,
+  "epoch": 0.0024351637647631805,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 46.201,
       "eval_steps_per_second": 23.107,
       "step": 10
+    },
+    {
+      "epoch": 0.0014610982588579083,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0018263728235723851,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018263728235723851,
+      "eval_loss": NaN,
+      "eval_runtime": 75.0397,
+      "eval_samples_per_second": 46.096,
+      "eval_steps_per_second": 23.054,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021916473882868624,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0024351637647631805,
+      "eval_loss": NaN,
+      "eval_runtime": 75.3071,
+      "eval_samples_per_second": 45.932,
+      "eval_steps_per_second": 22.973,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 229804183388160.0,
+  "total_flos": 486644153057280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null