Training in progress, step 18000, checkpoint

last-checkpoint/README.md

@@ -1383,6 +1383,10 @@ You can finetune this model on your own dataset.
 | 0.3128 | 17700 | 0.3352        |
 | 0.3137 | 17750 | 0.4406        |
 | 0.3145 | 17800 | 0.3822        |
+| 0.3154 | 17850 | 0.287         |
+| 0.3163 | 17900 | 0.4349        |
+| 0.3172 | 17950 | 0.3633        |
+| 0.3181 | 18000 | 0.3431        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23dcacb737e2af42314c6ab6136446e4982fee8745c6c03e350fd15717250aa
+oid sha256:263f64c6b42b021ab57121e4e8f46faeb44f9ada3d36f39ddf425a7f3b1b4803
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb8f9bc1642eae53fb943b388f6c8e06377f86d8a4ed25c9948af7605742194
+oid sha256:da85b40c1057dfca9ce7e42a72509e47f1514b529359402a8efecc5d091d6623
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116d3f323503837c4f5074c61dce27aa590a7a4580eb34472179dff367b43737
+oid sha256:d09d3ba87b7d0d8353c76a87036ebe87fa73b37b061f2207c2f20b469a834fce
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d3b315ce89145171b35cb9993d6540d84cc0fc327f65af910fcf8f238d2633
+oid sha256:c3082f8a8f0fc48d5193f80a2b266926a441fdb9c5495b02e03465c770eb219c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb6755a2a28890a2c297eec26254b464de2f60f49387af25b290236695ca25d
+oid sha256:2e92ded4afb81b531dc70334badaddabe870b22624bf7150b157aaa93592eb3b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.31453764732908057,
+  "epoch": 0.3180717781979467,
   "eval_steps": 500,
-  "global_step": 17800,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2500,6 +2500,34 @@
       "learning_rate": 3.8086823349237206e-05,
       "loss": 0.3822,
       "step": 17800
+    },
+    {
+      "epoch": 0.3154211800462971,
+      "grad_norm": 1.5267698764801025,
+      "learning_rate": 3.803773733089867e-05,
+      "loss": 0.287,
+      "step": 17850
+    },
+    {
+      "epoch": 0.31630471276351363,
+      "grad_norm": 2.647895574569702,
+      "learning_rate": 3.798865131256013e-05,
+      "loss": 0.4349,
+      "step": 17900
+    },
+    {
+      "epoch": 0.31718824548073016,
+      "grad_norm": 1.5159648656845093,
+      "learning_rate": 3.793956529422159e-05,
+      "loss": 0.3633,
+      "step": 17950
+    },
+    {
+      "epoch": 0.3180717781979467,
+      "grad_norm": 1.9135470390319824,
+      "learning_rate": 3.7890479275883064e-05,
+      "loss": 0.3431,
+      "step": 18000
     }
   ],
   "logging_steps": 50,