Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e9a1856bc0396ac5c40b0f805eea1c6e8de71a42e63785c7756ab4bbacdff1
+oid sha256:14bd0c06c80d61f1927477e9f0617d8d72e5acff9a5971f02a2e4348d4603c84
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d4ea992391a465d87dac2c0339dae9597ed5248711b14fda3f39f75c9b9b58
+oid sha256:76dcee882f4dc2e4d687c8630a2c8cc6fd9f77ee85547cd089ac94eda9a85c52
 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": 0.0005659576475027119,
+  "epoch": 0.0011319152950054238,
   "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": 63.788,
       "eval_steps_per_second": 31.894,
       "step": 3
+    },
+    {
+      "epoch": 0.0007546101966702826,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0009432627458378531,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0011319152950054238,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011319152950054238,
+      "eval_loss": NaN,
+      "eval_runtime": 35.1195,
+      "eval_samples_per_second": 63.554,
+      "eval_steps_per_second": 31.777,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26552602460160.0,
+  "total_flos": 50449944674304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null