Training in progress, step 46000, checkpoint

last-checkpoint/README.md

@@ -1209,6 +1209,10 @@ You can finetune this model on your own dataset.
 | 0.8075 | 45700 | 0.3975        |
 | 0.8084 | 45750 | 0.391         |
 | 0.8093 | 45800 | 0.3055        |
+| 0.8102 | 45850 | 0.2434        |
+| 0.8111 | 45900 | 0.285         |
+| 0.8120 | 45950 | 0.3952        |
+| 0.8129 | 46000 | 0.2802        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd5b7a0c7bbd9cd3c1ef7b582da35f4528606a4ac86bb04de178a7045ffef85
+oid sha256:fbc453c795079d8ded19817daacd8fec5d095bba6393f23049cff77eeb1abaf9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229981f79739c953722cfecdcfd1ea3bc38fb99e716343cc7272446d9e5bd67a
+oid sha256:303c03bcbf6290c5fb7fcf2c4927d56af5a210c091c12a9beba5ee6c9213f174
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0858441a43126cd8171b6b37146cb192258791649fae1dc1b48ff841ebace857
+oid sha256:431f36421847b278b660e6526fb15af6b02fbddb625572cac02bb7ad994d2dda
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791a23171b5f58ee5e75b5820d77158a2c7a8600431496a1df7bd6fb2c50e26f
+oid sha256:89e42fd89832885ab30327a4c2371265408743318772a17d94083f8bfb054483
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb572362d72f52e385494a9e0afaacf81d8323c35f20a7a978751625112b3a58
+oid sha256:3e4d32ff62b246761d94af48903691044aacc80825efb2f5658f28d83287222c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.809315968970331,
+  "epoch": 0.8128500998391971,
   "eval_steps": 500,
-  "global_step": 45800,
+  "global_step": 46000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6420,6 +6420,34 @@
       "learning_rate": 1.061141544442481e-05,
       "loss": 0.3055,
       "step": 45800
+    },
+    {
+      "epoch": 0.8101995016875475,
+      "grad_norm": 1.3673596382141113,
+      "learning_rate": 1.0562329426086275e-05,
+      "loss": 0.2434,
+      "step": 45850
+    },
+    {
+      "epoch": 0.811083034404764,
+      "grad_norm": 2.5049281120300293,
+      "learning_rate": 1.0513243407747738e-05,
+      "loss": 0.285,
+      "step": 45900
+    },
+    {
+      "epoch": 0.8119665671219806,
+      "grad_norm": 4.577225208282471,
+      "learning_rate": 1.04641573894092e-05,
+      "loss": 0.3952,
+      "step": 45950
+    },
+    {
+      "epoch": 0.8128500998391971,
+      "grad_norm": 1.4778873920440674,
+      "learning_rate": 1.0415071371070664e-05,
+      "loss": 0.2802,
+      "step": 46000
     }
   ],
   "logging_steps": 50,