Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91c832b67c02aa33888ab224c025cb43af148cb1da4b1553a7c01333d38b303
+oid sha256:0716e8cd0716ed13e89d4d72d43d071a71741c79c2d481e68fc4ba0145fb0c6d
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8181bbb6dbbe773b6043f4d0c1ba0a1b3a6b72812530d5f0820e8cb22570383
+oid sha256:9908c81d4f08fa0707f543eeeb598037560bf300bf9c35b62655c74c41b96908
 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": 0.00036659131178591066,
+  "epoch": 0.0007331826235718213,
   "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": 41.703,
       "eval_steps_per_second": 20.852,
       "step": 3
+    },
+    {
+      "epoch": 0.0004887884157145475,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0006109855196431845,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007331826235718213,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0007331826235718213,
+      "eval_loss": NaN,
+      "eval_runtime": 82.3595,
+      "eval_samples_per_second": 41.841,
+      "eval_steps_per_second": 20.92,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 97289477554176.0,
+  "total_flos": 194578955108352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null