Training in progress, step 540, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1c83fafb8e02dd0f717cc5a39162f05d7404832c5fc4fbc8120bc5a28a3a34
+oid sha256:76cf2cfb8acb6251db267638caae88710cf88816ace06f8acd7cae72037b7e23
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4511333d8901550e499feb301ed012fb58032713f2be7e20a710ee1fa928aed4
+oid sha256:29600bcee487c1a01dc32b2722f7c8862c9e02614484b036be9fdfa628bf8bb9
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e9e6580a84fd0db2b771e56099822d173da85eac47864d93760d074b498333
+oid sha256:f9238b7add585066cbb06da0e32e6be6507c64165fbe42aa9ed19eca4092e8ab
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d380d2d68225342e540efbf7273fe50dde428b916e607285dece60ac093c01c5
+oid sha256:672fecd4dfa047902993b09ba8fc51ecd2a72c6903902bf77e4b09f779d46548
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839bffb3b2b97ea56ce77fd476927b3e7c6d86a97c322429166a0d05d8bba56a
+oid sha256:db496ff339a198f08c0b8942170220cef7c7f05387b73d30643172645a9da2c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 40.0,
+  "epoch": 41.53846153846154,
   "eval_steps": 40,
-  "global_step": 520,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,20 @@
       "eval_samples_per_second": 284.736,
       "eval_steps_per_second": 4.553,
       "step": 520
+    },
+    {
+      "epoch": 40.76923076923077,
+      "grad_norm": 0.416015625,
+      "learning_rate": 7.350593278519824e-06,
+      "loss": 9.1773,
+      "step": 530
+    },
+    {
+      "epoch": 41.53846153846154,
+      "grad_norm": 0.41796875,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 9.1786,
+      "step": 540
     }
   ],
   "logging_steps": 10,
@@ -502,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 212762445742080.0,
+  "total_flos": 220945616732160.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null