Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf924b4f11caa68ec11b11f3be550565f8db57ebaadfa9db13c6e8dddda4834f
+oid sha256:4f468eb4f0acbf19a5233da76bd6e7daeec96385f93f13fa0c419ba0ac7edd23
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c577fa0d5440076aa59215302dbde6f36234cd1bbefdcf145b0d95592f175e6c
+oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
 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": 0.017069701280227598,
+  "epoch": 0.034139402560455195,
   "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": 73.175,
       "eval_steps_per_second": 36.588,
       "step": 3
+    },
+    {
+      "epoch": 0.02275960170697013,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.034139402560455195,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.034139402560455195,
+      "eval_loss": NaN,
+      "eval_runtime": 1.0638,
+      "eval_samples_per_second": 69.559,
+      "eval_steps_per_second": 34.779,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 76737593475072.0,
+  "total_flos": 153475186950144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null