Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda58c25904c45927a8840cffb6d449d06938bd427a2d5f5dd4ae0695a2a46b9
+oid sha256:d6ebc1e30feaf6b7e07227620b074e3ba1f467c3a1bddf9b2508d7e773f1e9c5
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df86d97abf7dbf8cf703d6ce1eaf472b410fb0a2ec62a2c3d6c4d5ccc69614af
+oid sha256:68912860d2b0bafb9eb9c52986dd9904435ca9d770ab8503a4973c92e75a6fca
 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": 0.000998502246630055,
+  "epoch": 0.00199700449326011,
   "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": 18.672,
       "eval_steps_per_second": 9.343,
       "step": 3
+    },
+    {
+      "epoch": 0.0013313363288400732,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0016641704110500915,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00199700449326011,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00199700449326011,
+      "eval_loss": NaN,
+      "eval_runtime": 67.9596,
+      "eval_samples_per_second": 18.614,
+      "eval_steps_per_second": 9.314,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 971625021308928.0,
+  "total_flos": 1943250042617856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null