Training in progress, step 30600, checkpoint

last-checkpoint/README.md

@@ -1269,6 +1269,10 @@ You can finetune this model on your own dataset.
 | 0.5354 | 30300 | 0.2758        |
 | 0.5363 | 30350 | 0.3166        |
 | 0.5372 | 30400 | 0.35          |
+| 0.5381 | 30450 | 0.3391        |
+| 0.5390 | 30500 | 0.3576        |
+| 0.5398 | 30550 | 0.295         |
+| 0.5407 | 30600 | 0.3449        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf79ddb807641f21ab4f124fe2a7f27110c30ccaaa038e866819c2a6c3894db3
+oid sha256:5fa3b9879e14ec9f5b4cd6c1fd0c5f2042c31d8024c507b2d4eb4e6f03a86557
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceffaa43e4f0c60b5feed0fbc2c3565eef53e3ad867186e6797fe95254c2affe
+oid sha256:2d918c870830ed1534f9d4acc1377f61959ec7838ebd0b23de0425c2b516e9d4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80122c84195c17eb984e073adfb25182010304afad0586ccdcb1a261a3a0f848
+oid sha256:c0b4ef05441e098f1fa59f720976907d8a3ce65ffd05fdaf038eebceb3ab3d49
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528a5407336a16734f58a4f46d586ee071f6f4a258839c4070d301e8f708f0a5
+oid sha256:5927361a532fb6c132d07b4ab7a520caf5f685a6698e2682d0ac3b35fea7ca5e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2e19f20627e37fe99b4ad87f03b959017a779a9fc1b80f764c9a8c0220d435
+oid sha256:9ea5eebe3d97676cf6ae4d334b17697b9e89bbac0efa0396db84f4cb8e005a81
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5371878920676433,
+  "epoch": 0.5407220229365094,
   "eval_steps": 500,
-  "global_step": 30400,
+  "global_step": 30600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4264,6 +4264,34 @@
       "learning_rate": 2.572205532975987e-05,
       "loss": 0.35,
       "step": 30400
+    },
+    {
+      "epoch": 0.5380714247848598,
+      "grad_norm": 1.1287676095962524,
+      "learning_rate": 2.5672969311421334e-05,
+      "loss": 0.3391,
+      "step": 30450
+    },
+    {
+      "epoch": 0.5389549575020763,
+      "grad_norm": 1.7524675130844116,
+      "learning_rate": 2.5623883293082802e-05,
+      "loss": 0.3576,
+      "step": 30500
+    },
+    {
+      "epoch": 0.5398384902192929,
+      "grad_norm": 1.1238594055175781,
+      "learning_rate": 2.5575778995111033e-05,
+      "loss": 0.295,
+      "step": 30550
+    },
+    {
+      "epoch": 0.5407220229365094,
+      "grad_norm": 0.9298042058944702,
+      "learning_rate": 2.5526692976772498e-05,
+      "loss": 0.3449,
+      "step": 30600
     }
   ],
   "logging_steps": 50,