Training in progress, step 38200, checkpoint

last-checkpoint/README.md

@@ -1277,6 +1277,10 @@ You can finetune this model on your own dataset.
 | 0.6697 | 37900 | 0.287         |
 | 0.6706 | 37950 | 0.267         |
 | 0.6715 | 38000 | 0.2862        |
+| 0.6724 | 38050 | 0.2931        |
+| 0.6733 | 38100 | 0.3039        |
+| 0.6741 | 38150 | 0.3067        |
+| 0.6750 | 38200 | 0.3072        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d08023f1bb62ce1d0130d07526322a2c5fda70606088482affec032e342b5c
+oid sha256:75ff9aaaf5100bcdf47810c9aef74f277666d0563b69786a02f96d2765837422
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b44bc19e6a23e08867d09cb20779d3a37e861123bffe86f50954d881ed4c90
+oid sha256:4e4f4dca1f6c69a542bde78c0327dd4270176a1625067e2256ceced634a93d6c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b8300b2a2312e0bd0c6c541da810ac2f229a1e589baac1c616b441c52c2040
+oid sha256:21df5a3de36303453637c6260c11dc60608b83605f06af49a76c4215097f965f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9e92d7ca7e11f8c8280a110c0e95f7fc8368104e07cf4940880e3ea39426da
+oid sha256:254ca1be196224bf5f7fb5303e3156f8228d188caec22f35ae76f9309a50e396
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:604774c1c43f2a9fc2aaee736abd7cd490fcb173a1997d86fd932e858e22ca53
+oid sha256:c8546f3abee9c0d442ca93d26c327328480bf0ee1f8248e94c717f8d8cb3ba4b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6714848650845541,
+  "epoch": 0.6750189959534202,
   "eval_steps": 500,
-  "global_step": 38000,
+  "global_step": 38200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5328,6 +5328,34 @@
       "learning_rate": 1.8264907423769416e-05,
       "loss": 0.2862,
       "step": 38000
+    },
+    {
+      "epoch": 0.6723683978017706,
+      "grad_norm": 1.389864444732666,
+      "learning_rate": 1.8215821405430877e-05,
+      "loss": 0.2931,
+      "step": 38050
+    },
+    {
+      "epoch": 0.6732519305189871,
+      "grad_norm": 1.2709695100784302,
+      "learning_rate": 1.816673538709234e-05,
+      "loss": 0.3039,
+      "step": 38100
+    },
+    {
+      "epoch": 0.6741354632362037,
+      "grad_norm": 1.2036606073379517,
+      "learning_rate": 1.8117649368753806e-05,
+      "loss": 0.3067,
+      "step": 38150
+    },
+    {
+      "epoch": 0.6750189959534202,
+      "grad_norm": 1.3336296081542969,
+      "learning_rate": 1.8068563350415268e-05,
+      "loss": 0.3072,
+      "step": 38200
     }
   ],
   "logging_steps": 50,