Training in progress, step 14200, checkpoint

last-checkpoint/README.md

@@ -1307,6 +1307,10 @@ You can finetune this model on your own dataset.
 | 0.2456 | 13900 | 0.4071        |
 | 0.2465 | 13950 | 0.3434        |
 | 0.2474 | 14000 | 0.3885        |
+| 0.2483 | 14050 | 0.4296        |
+| 0.2492 | 14100 | 0.3853        |
+| 0.2500 | 14150 | 0.4068        |
+| 0.2509 | 14200 | 0.4071        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a2adb6bfbbea4a476d8b39550525184889426d7ad5ada0704bf7fd8a08014e
+oid sha256:b4503e7e25e7a5b0e3fa0b1c8a23c410d156686b9c3f0b8c96dc82d39a0e1b1c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a2ea9542b2fcc7b78ffb8a7db7115adb812d5622752385f67467dd05781af7
+oid sha256:4d5d943bf4dc121c9308255043fd16448b3eb77f764283d83e12427c3022fba6
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfd9fafd1943af1c942d00aedf93cc91b1f2ac9b2c40fb3cf2c6437e950a58a
+oid sha256:215f5b0f373f4e3ad43a7c01ffdbf3925bbe7ae7185a457cfe9021eb94481c4b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1201e8bd755a170476aeef974a56a5ac4ecf9ad78800bc8d10ac6b9ce01f61e
+oid sha256:f2ca0c424595d60ecac702728b12c84553636fe40229728f0d7faf3360276035
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dc0af212086453eea98bd905245f2ef7726e76a3df4d950b27559bc0469f69
+oid sha256:639b76dd84e3ff9b63a4b686b5478e8730dc63d794913f7a823faab8ec6c2e15
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24738916082062518,
+  "epoch": 0.25092329168949123,
   "eval_steps": 500,
-  "global_step": 14000,
+  "global_step": 14200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1968,6 +1968,34 @@
       "learning_rate": 4.181539730223243e-05,
       "loss": 0.3885,
       "step": 14000
+    },
+    {
+      "epoch": 0.2482726935378417,
+      "grad_norm": 2.5290989875793457,
+      "learning_rate": 4.17663112838939e-05,
+      "loss": 0.4296,
+      "step": 14050
+    },
+    {
+      "epoch": 0.24915622625505823,
+      "grad_norm": 1.9654839038848877,
+      "learning_rate": 4.171722526555536e-05,
+      "loss": 0.3853,
+      "step": 14100
+    },
+    {
+      "epoch": 0.25003975897227476,
+      "grad_norm": 1.68603515625,
+      "learning_rate": 4.166813924721683e-05,
+      "loss": 0.4068,
+      "step": 14150
+    },
+    {
+      "epoch": 0.25092329168949123,
+      "grad_norm": 1.9062405824661255,
+      "learning_rate": 4.161905322887829e-05,
+      "loss": 0.4071,
+      "step": 14200
     }
   ],
   "logging_steps": 50,