Training in progress, step 14000, checkpoint

last-checkpoint/README.md

@@ -1303,6 +1303,10 @@ You can finetune this model on your own dataset.
 | 0.2421 | 13700 | 0.541         |
 | 0.2430 | 13750 | 0.3936        |
 | 0.2439 | 13800 | 0.3871        |
+| 0.2447 | 13850 | 0.2983        |
+| 0.2456 | 13900 | 0.4071        |
+| 0.2465 | 13950 | 0.3434        |
+| 0.2474 | 14000 | 0.3885        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31148f752a25ceb10b5c213db27c39897a7101ce74c3a2bf632bddbac89942e4
+oid sha256:34a2adb6bfbbea4a476d8b39550525184889426d7ad5ada0704bf7fd8a08014e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4531c62c1edbd90a082131f940d6f09413598c9a48c2db99b1d4be025b30823d
+oid sha256:d6a2ea9542b2fcc7b78ffb8a7db7115adb812d5622752385f67467dd05781af7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645652864b8ca64a5c235d7c8d3b0d5b69daae205059b96d011831548d91d7f1
+oid sha256:9dfd9fafd1943af1c942d00aedf93cc91b1f2ac9b2c40fb3cf2c6437e950a58a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8dae4393c167bd70d32b16d8177fd63b4e64aff7df734eda7e1fde5cf1c852
+oid sha256:e1201e8bd755a170476aeef974a56a5ac4ecf9ad78800bc8d10ac6b9ce01f61e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69637a5f3a8187f3f56ddcea39b1cc9e7b6880f429b26c35a70d27d68464427a
+oid sha256:68dc0af212086453eea98bd905245f2ef7726e76a3df4d950b27559bc0469f69
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24385502995175912,
+  "epoch": 0.24738916082062518,
   "eval_steps": 500,
-  "global_step": 13800,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1940,6 +1940,34 @@
       "learning_rate": 4.201174137558658e-05,
       "loss": 0.3871,
       "step": 13800
+    },
+    {
+      "epoch": 0.24473856266897565,
+      "grad_norm": 1.7289350032806396,
+      "learning_rate": 4.1962655357248045e-05,
+      "loss": 0.2983,
+      "step": 13850
+    },
+    {
+      "epoch": 0.24562209538619215,
+      "grad_norm": 1.792413592338562,
+      "learning_rate": 4.191356933890951e-05,
+      "loss": 0.4071,
+      "step": 13900
+    },
+    {
+      "epoch": 0.24650562810340867,
+      "grad_norm": 1.5456571578979492,
+      "learning_rate": 4.186448332057097e-05,
+      "loss": 0.3434,
+      "step": 13950
+    },
+    {
+      "epoch": 0.24738916082062518,
+      "grad_norm": 1.9666177034378052,
+      "learning_rate": 4.181539730223243e-05,
+      "loss": 0.3885,
+      "step": 14000
     }
   ],
   "logging_steps": 50,