Training in progress, step 30800, checkpoint

last-checkpoint/README.md

@@ -1273,6 +1273,10 @@ You can finetune this model on your own dataset.
 | 0.5390 | 30500 | 0.3576        |
 | 0.5398 | 30550 | 0.295         |
 | 0.5407 | 30600 | 0.3449        |
+| 0.5416 | 30650 | 0.3274        |
+| 0.5425 | 30700 | 0.3094        |
+| 0.5434 | 30750 | 0.3077        |
+| 0.5443 | 30800 | 0.3505        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa3b9879e14ec9f5b4cd6c1fd0c5f2042c31d8024c507b2d4eb4e6f03a86557
+oid sha256:9fc88dfeec5a070e3fd948dba14887b72312540e53c8949b21909a348ea27a4e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d918c870830ed1534f9d4acc1377f61959ec7838ebd0b23de0425c2b516e9d4
+oid sha256:3258bbff978fc0ab89659d377622b7a63dc9652d486808dbd59a56dd9bf6ccc1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b4ef05441e098f1fa59f720976907d8a3ce65ffd05fdaf038eebceb3ab3d49
+oid sha256:ed992908f9b2d94cfacaa25bd3a16c1eb2cbd116a690892a1034cc00bf4ec453
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5927361a532fb6c132d07b4ab7a520caf5f685a6698e2682d0ac3b35fea7ca5e
+oid sha256:424edc0ec5b25fea421881d2bc754b25bc2bf24839236dba41579726e027f84d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea5eebe3d97676cf6ae4d334b17697b9e89bbac0efa0396db84f4cb8e005a81
+oid sha256:f1b1be98187efcd50aa0c5711a24f2a5afe8565001814025bf7b98b523a4dc07
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5407220229365094,
+  "epoch": 0.5442561538053754,
   "eval_steps": 500,
-  "global_step": 30600,
+  "global_step": 30800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4292,6 +4292,34 @@
       "learning_rate": 2.5526692976772498e-05,
       "loss": 0.3449,
       "step": 30600
+    },
+    {
+      "epoch": 0.5416055556537258,
+      "grad_norm": 1.5093685388565063,
+      "learning_rate": 2.547760695843396e-05,
+      "loss": 0.3274,
+      "step": 30650
+    },
+    {
+      "epoch": 0.5424890883709423,
+      "grad_norm": 1.4606502056121826,
+      "learning_rate": 2.5428520940095424e-05,
+      "loss": 0.3094,
+      "step": 30700
+    },
+    {
+      "epoch": 0.5433726210881589,
+      "grad_norm": 1.7957881689071655,
+      "learning_rate": 2.537943492175689e-05,
+      "loss": 0.3077,
+      "step": 30750
+    },
+    {
+      "epoch": 0.5442561538053754,
+      "grad_norm": 1.4665497541427612,
+      "learning_rate": 2.533034890341835e-05,
+      "loss": 0.3505,
+      "step": 30800
     }
   ],
   "logging_steps": 50,