Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c91030bc8084ea00e0f71210185b91e20a3b75ce14c36d2ff8a9690d9350e7
+oid sha256:87fe88de4833fabc6ccb9c3dfdbd970c638bdfca11344dd77472ca8d985c95a3
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7464f5b235389d31ecd982ed7450519fe52799d2b9b239759a23ad7e4f2c8e6a
+oid sha256:9097bc16a0c76788ee7a5f684c31f0d7c36e318e22db7989c97c5d118999d57e
 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": 0.011019283746556474,
+  "epoch": 0.02203856749311295,
   "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": 19.526,
       "eval_steps_per_second": 9.848,
       "step": 3
+    },
+    {
+      "epoch": 0.014692378328741965,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.018365472910927456,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.02203856749311295,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.02203856749311295,
+      "eval_loss": NaN,
+      "eval_runtime": 5.9226,
+      "eval_samples_per_second": 19.417,
+      "eval_steps_per_second": 9.793,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 926930687754240.0,
+  "total_flos": 1853861375508480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null