Training in progress, step 55800, checkpoint

last-checkpoint/README.md

@@ -1269,6 +1269,10 @@ You can finetune this model on your own dataset.
 | 0.9807 | 55500 | 0.3559        |
 | 0.9816 | 55550 | 0.4382        |
 | 0.9825 | 55600 | 0.2588        |
+| 0.9834 | 55650 | 0.3132        |
+| 0.9843 | 55700 | 0.2922        |
+| 0.9851 | 55750 | 0.2409        |
+| 0.9860 | 55800 | 0.2704        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4757af97769f9bf496f79482c67b4ad52305ab54793692a8f0992bfb1b3e1d99
+oid sha256:90fcb416e3f1fd9c1877f4daf0be2fc8df1e1250a64fe3f07aae6546f23d2ab0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0ad85e5b5865c2909f3ef475b6781df3d6695ce915b04da508edcabe1e676c
+oid sha256:5e61e9433fbd41b3556eca2c0125db34a8ece386095ac01a954bcccc5ae50de3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53cd51ebdd8de8dece2e081300401e55897bd6527506b231b719e81675496d96
+oid sha256:404572bee52c0f6fd3f51338bcd9d76b45287337ee0a6f0be420d6125dc37b05
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cadf5e13e62099775fee57e6f6e29864a5e8da9a1f19033bf424bca204d48d8
+oid sha256:87465185b3464123ac777bc7dfe2dec56250d184ec4a7d3aafc9cf39b60be6dc
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c3ccdbd565485480694df123a18cb3bc6089aca7ac0b1c3670702db7f9e007
+oid sha256:55ccf2bc2593182b06063b40af4f602a3ba516c801f8e0f593c69740ab2da6ec
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9824883815447686,
+  "epoch": 0.9860225124136347,
   "eval_steps": 500,
-  "global_step": 55600,
+  "global_step": 55800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7792,6 +7792,34 @@
       "learning_rate": 9.954644519055192e-07,
       "loss": 0.2588,
       "step": 55600
+    },
+    {
+      "epoch": 0.9833719142619851,
+      "grad_norm": 1.011873483657837,
+      "learning_rate": 9.463784335669829e-07,
+      "loss": 0.3132,
+      "step": 55650
+    },
+    {
+      "epoch": 0.9842554469792016,
+      "grad_norm": 2.5110092163085938,
+      "learning_rate": 8.972924152284464e-07,
+      "loss": 0.2922,
+      "step": 55700
+    },
+    {
+      "epoch": 0.9851389796964182,
+      "grad_norm": 1.2086411714553833,
+      "learning_rate": 8.4820639688991e-07,
+      "loss": 0.2409,
+      "step": 55750
+    },
+    {
+      "epoch": 0.9860225124136347,
+      "grad_norm": 1.5035746097564697,
+      "learning_rate": 7.991203785513735e-07,
+      "loss": 0.2704,
+      "step": 55800
     }
   ],
   "logging_steps": 50,