Training in progress, step 19600, checkpoint

last-checkpoint/README.md

@@ -1415,6 +1415,10 @@ You can finetune this model on your own dataset.
 | 0.3410 | 19300 | 0.3238        |
 | 0.3419 | 19350 | 0.3043        |
 | 0.3428 | 19400 | 0.3902        |
+| 0.3437 | 19450 | 0.3085        |
+| 0.3446 | 19500 | 0.3162        |
+| 0.3455 | 19550 | 0.345         |
+| 0.3463 | 19600 | 0.3017        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c809593a4e810558b7888d3e612f15efc51c5db37b7d0556584318528272574d
+oid sha256:ee5355e90f9d05aafbab0c12494b27835f95ccb60172ff8fbe78fd57d6b61d67
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415abbc1cb409cdbfc5f39cef8004307a437f7f9f53d32a212cdbb581c0e45e1
+oid sha256:cfe72551b76baf33ba47fef562d43a709c57a754ed9cdde4263ce1cd0a109508
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2ab8a0a44cb42f1e8599f3d83384df303f90a2cb7c743c1865d9517262e7ef
+oid sha256:be3ce8b220887769ad7876242753f4d51d8fa743fffcf793c5f91b58a8f4c701
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1362f5572f2c24512c1a63574772877b23a9cc814bbc44fff72e3cde5341c40a
+oid sha256:7402b49777be73c34eb03204101175d67711cc065bdfdb2c545471bf86e49076
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404504f0a70dc9bf558ab7039928bcb08279726175fd39a9b8bf44633e9ee073
+oid sha256:88ee56c6db80ef2379420c7b71a3a71ecc892a7c8e43c85a15d491461e416ad9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3428106942800092,
+  "epoch": 0.34634482514887527,
   "eval_steps": 500,
-  "global_step": 19400,
+  "global_step": 19600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2724,6 +2724,34 @@
       "learning_rate": 3.651705248277081e-05,
       "loss": 0.3902,
       "step": 19400
+    },
+    {
+      "epoch": 0.3436942269972257,
+      "grad_norm": 1.5135536193847656,
+      "learning_rate": 3.6467966464432276e-05,
+      "loss": 0.3085,
+      "step": 19450
+    },
+    {
+      "epoch": 0.3445777597144422,
+      "grad_norm": 2.2533581256866455,
+      "learning_rate": 3.6418880446093734e-05,
+      "loss": 0.3162,
+      "step": 19500
+    },
+    {
+      "epoch": 0.34546129243165874,
+      "grad_norm": 1.625067949295044,
+      "learning_rate": 3.63697944277552e-05,
+      "loss": 0.345,
+      "step": 19550
+    },
+    {
+      "epoch": 0.34634482514887527,
+      "grad_norm": 1.1573612689971924,
+      "learning_rate": 3.632070840941666e-05,
+      "loss": 0.3017,
+      "step": 19600
     }
   ],
   "logging_steps": 50,