Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa2cad664ab7ccc19bc4219c4c9d7e76e7143ac95828876a0285f21e4855322
+oid sha256:960cd9845c564bfc5e3103367fd2ab34c17fd8f491a601ce226f7d51fce43bb8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef253e11659d5aef54389108a2bf218699473114178cb597eed9d736723ab18c
+oid sha256:a2fd0c79908375df31b4d42400cbae3a7cc90777b0421863e61c40a6745f5979
 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": 3.519381527352926e-05,
+  "epoch": 7.038763054705852e-05,
   "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": 6.997,
       "eval_steps_per_second": 3.498,
       "step": 3
+    },
+    {
+      "epoch": 4.692508703137235e-05,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 5.865635878921544e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 7.038763054705852e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 7.038763054705852e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 5125.1509,
+      "eval_samples_per_second": 7.003,
+      "eval_steps_per_second": 3.502,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 903740324315136.0,
+  "total_flos": 1684243331678208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null