Training in progress, step 550, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457ea60d64db7108be0259f24e397d19fe5ff7dc5efa5e76d938a0c21604a326
+oid sha256:03e72bc52453741a5a977061d349ab0a06726b5829e937ad47a1c11012b1540f
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90884f4c593fcabac0b3930a1fc340afcd016fedb3640704d17b8ab041a1059
+oid sha256:a4560fb5425fea78ba74f156be382a1cbcb58e351eba39bc932b5701d939b057
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e00cf017b71358b07c8c2c8b20cbd10a881dae50181b31232805c6f5faced7
+oid sha256:a9d51e4a7056c3558a387ed54a4d13c51368f1e567102a0ee859969fb5f31cd3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b5493d245f39afc7c313900f9bd075608d678324a8dee69773a4ada7717fca
+oid sha256:1204ca9be37de89665f7f1742f206de4543c6c56db448f2a4968fb174cdf1393
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628e045b78e5d559e9fcef6658ed03e911773af6f7354bf6b3b679b0ff34bfdb
+oid sha256:0160b3598707f8907336269c674f5ce56b2bbdea80b3e53648f4959f2a4937ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 38.46153846153846,
+  "epoch": 42.30769230769231,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -445,6 +445,49 @@
       "eval_samples_per_second": 265.206,
       "eval_steps_per_second": 4.24,
       "step": 500
+    },
+    {
+      "epoch": 39.23076923076923,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 9.1771,
+      "step": 510
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.41796875,
+      "learning_rate": 9.564283930242257e-06,
+      "loss": 9.1775,
+      "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": 9.1787,
+      "step": 540
+    },
+    {
+      "epoch": 42.30769230769231,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.7731999690749585e-06,
+      "loss": 9.1761,
+      "step": 550
+    },
+    {
+      "epoch": 42.30769230769231,
+      "eval_loss": 9.19363784790039,
+      "eval_runtime": 5.2646,
+      "eval_samples_per_second": 285.113,
+      "eval_steps_per_second": 4.559,
+      "step": 550
     }
   ],
   "logging_steps": 10,
@@ -464,7 +507,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 204579274752000.0,
+  "total_flos": 225037202227200.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null