Training in progress, step 16800, checkpoint

last-checkpoint/README.md

@@ -1359,6 +1359,10 @@ You can finetune this model on your own dataset.
 | 0.2916 | 16500 | 0.3065        |
 | 0.2924 | 16550 | 0.4003        |
 | 0.2933 | 16600 | 0.5295        |
+| 0.2942 | 16650 | 0.3582        |
+| 0.2951 | 16700 | 0.3299        |
+| 0.2960 | 16750 | 0.3493        |
+| 0.2969 | 16800 | 0.2752        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc8b58e69308ebfbfc0eb50f8d94cc9702cadcdc42e3254287236a6a1b09a4e
+oid sha256:c6e1b391f33422456061353bd355bf2435eeb4195f81389af6dbc0e8fc66d25b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705df85026bb51643b710bf960103e3bb1661185afb2f1e06a383d34dc56e4bf
+oid sha256:e9de93effda738b0b5fd57692fb67723566f34b54c872aac7a9626fa31feaf70
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f891a9e7af458bc02af6e87abb160c7f8d056d1f22f1437aa987e99557c38c6d
+oid sha256:dd3be6ab84a32000b2bae6b4e86032ac0554f86e01256b1d6d073b96f56c8ada
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec9685408ff856249d18165c59f9d1d95d1e000415171f3550ac55d011d4b84
+oid sha256:caeb14c75258126c0a61054123d2b052c3f92789f4356192be834a257bdfec4c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4750d7049889a8742682de7ab1e907cdb0b4e5ab032bf6b9deca530e9913b39d
+oid sha256:1ba1c971d0e3bd3fc6e84348fd8cbae570fbf4f01d4c3efacd1f9719190d9e71
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29333286211588416,
+  "epoch": 0.2968669929847502,
   "eval_steps": 500,
-  "global_step": 16600,
+  "global_step": 16800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2332,6 +2332,34 @@
       "learning_rate": 3.926390606899531e-05,
       "loss": 0.5295,
       "step": 16600
+    },
+    {
+      "epoch": 0.2942163948331007,
+      "grad_norm": 1.9425716400146484,
+      "learning_rate": 3.9214820050656776e-05,
+      "loss": 0.3582,
+      "step": 16650
+    },
+    {
+      "epoch": 0.29509992755031716,
+      "grad_norm": 3.003871440887451,
+      "learning_rate": 3.9165734032318234e-05,
+      "loss": 0.3299,
+      "step": 16700
+    },
+    {
+      "epoch": 0.2959834602675337,
+      "grad_norm": 3.689194679260254,
+      "learning_rate": 3.91166480139797e-05,
+      "loss": 0.3493,
+      "step": 16750
+    },
+    {
+      "epoch": 0.2968669929847502,
+      "grad_norm": 1.9439842700958252,
+      "learning_rate": 3.906756199564116e-05,
+      "loss": 0.2752,
+      "step": 16800
     }
   ],
   "logging_steps": 50,