Training in progress, step 24200, checkpoint

last-checkpoint/README.md

@@ -1507,6 +1507,10 @@ You can finetune this model on your own dataset.
 | 0.4223 | 23900 | 0.3431        |
 | 0.4232 | 23950 | 0.2902        |
 | 0.4241 | 24000 | 0.3136        |
+| 0.4250 | 24050 | 0.4001        |
+| 0.4259 | 24100 | 0.285         |
+| 0.4267 | 24150 | 0.4717        |
+| 0.4276 | 24200 | 0.3391        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f90e824e1a9ffb638cde5da629726eeb7bc12cd6362fbb12d7d04ce5372c8f5
+oid sha256:0181c21b9f6765739bd5007a2c66971b2b61c54adeae3d64ef7c903bb8f2e6e4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a99a7427fcc196b3d93d1ed84e8a7ea1d28d3ea047d1257af87399a72693de
+oid sha256:f6c65cd16ad4911950d1c8397919ae661398f9d0a619f0171434d20572ef27e7
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66083f07808429ecf1c592a46d5e2fa5fd55c02b1303e07c74cebcc8fc44243c
+oid sha256:4fde7e047e37c5aa11f699d0fe33f27bebcb79d0fc8db66d93c60380391a735e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367e0d39f4bf5ffc122ff5c01987f9ae3492dd527c06b1748807449df9f2581e
+oid sha256:32780bd86329e2b09cbb8ee735964e2604497b85f5cbf997d9829eaba3fba7af
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33058f7a86733565c00edc7dc90e657260ca9633bceae0708704d9688e1a076c
+oid sha256:8be018c87a0e7096cac9e25fc24ea9075d875ad05ab63ff4844349cf5f7d7251
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4240957042639289,
+  "epoch": 0.42762983513279496,
   "eval_steps": 500,
-  "global_step": 24000,
+  "global_step": 24200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3368,6 +3368,34 @@
       "learning_rate": 3.2003102236359e-05,
       "loss": 0.3136,
       "step": 24000
+    },
+    {
+      "epoch": 0.4249792369811454,
+      "grad_norm": 4.797271251678467,
+      "learning_rate": 3.195401621802046e-05,
+      "loss": 0.4001,
+      "step": 24050
+    },
+    {
+      "epoch": 0.42586276969836195,
+      "grad_norm": 1.4796360731124878,
+      "learning_rate": 3.190493019968193e-05,
+      "loss": 0.285,
+      "step": 24100
+    },
+    {
+      "epoch": 0.4267463024155784,
+      "grad_norm": 1.4410722255706787,
+      "learning_rate": 3.1855844181343386e-05,
+      "loss": 0.4717,
+      "step": 24150
+    },
+    {
+      "epoch": 0.42762983513279496,
+      "grad_norm": 1.398037075996399,
+      "learning_rate": 3.180675816300485e-05,
+      "loss": 0.3391,
+      "step": 24200
     }
   ],
   "logging_steps": 50,