Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea7aee0acdcae3efed24176f2c4c8ced4e25f1c8859da868dca484ac61418e5
+oid sha256:5eb69cffb024d0acadfed017480ed2bbab1e828a601aab179623209cf230ebe5
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7f1807a79f764cdbf1638aa0e0db1154794499b1015a5180c25c186b8d6d94
+oid sha256:55f5b8fc91a819fc39bd479452495c8f8f43e1c210ee91583af5c241cfc6079a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26899798251513113,
+  "epoch": 0.4034969737726967,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 21.064,
       "eval_steps_per_second": 10.599,
       "step": 100
+    },
+    {
+      "epoch": 0.29589778076664425,
+      "grad_norm": NaN,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.32279757901815737,
+      "grad_norm": NaN,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.3496973772696705,
+      "grad_norm": NaN,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.3765971755211836,
+      "grad_norm": NaN,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.4034969737726967,
+      "grad_norm": NaN,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4034969737726967,
+      "eval_loss": NaN,
+      "eval_runtime": 7.4505,
+      "eval_samples_per_second": 21.072,
+      "eval_steps_per_second": 10.603,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.173290868736e+16,
+  "total_flos": 4.759936303104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null