Training in progress, step 12200, checkpoint

last-checkpoint/README.md

@@ -1265,6 +1265,10 @@ You can finetune this model on your own dataset.
 | 0.2103 | 11900 | 0.3404        |
 | 0.2112 | 11950 | 0.4013        |
 | 0.2120 | 12000 | 0.4278        |
+| 0.2129 | 12050 | 0.3905        |
+| 0.2138 | 12100 | 0.4082        |
+| 0.2147 | 12150 | 0.3855        |
+| 0.2156 | 12200 | 0.4567        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ee7d65436b3c3bdb265a584cb598d21c1152436f7bbe5e5b89abe72d05abfd
+oid sha256:ad55c4b6b6eb0c0378b40f5afe9b809839ef4dcaf65938b6be44df391f5a5ea4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacbc7b18200a700f9e868dccad3bd885c8a77978e6ef6450cc02303852cb1f4
+oid sha256:6292ed9a900b0c859bfdd6c9df2c5387f1a04143b05826767cb8bedebe906bb1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3ba6287442404e0fa92289c3fc1da4f9e94c42e35bf2cb41249702ce19aede
+oid sha256:f520f013fa8b5071407e30d736875f828fde9d624a9e917e055760aba4e8b925
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f76080c54c5059b8f1d78797380cba29afea4aa1d320a9c29f8474a65aad22
+oid sha256:400813ac47bbcdbc0fc813340b1eb9c8ae221654524666a11f89e971d58d1c7c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a38922a27408f3b8fdb8e3c0104dbbbeb511c2171a5f4ccac9abbb96798cd4
+oid sha256:038fcca02e593a472cc6365efd49e0401f5576654e492a85d64164b873c49869
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21204785213196445,
+  "epoch": 0.2155819830008305,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1688,6 +1688,34 @@
       "learning_rate": 4.3777856315407124e-05,
       "loss": 0.4278,
       "step": 12000
+    },
+    {
+      "epoch": 0.21293138484918098,
+      "grad_norm": 1.4981114864349365,
+      "learning_rate": 4.372877029706858e-05,
+      "loss": 0.3905,
+      "step": 12050
+    },
+    {
+      "epoch": 0.21381491756639748,
+      "grad_norm": 1.6444882154464722,
+      "learning_rate": 4.3679684278730046e-05,
+      "loss": 0.4082,
+      "step": 12100
+    },
+    {
+      "epoch": 0.214698450283614,
+      "grad_norm": 1.9731707572937012,
+      "learning_rate": 4.363059826039151e-05,
+      "loss": 0.3855,
+      "step": 12150
+    },
+    {
+      "epoch": 0.2155819830008305,
+      "grad_norm": 2.66648268699646,
+      "learning_rate": 4.3581512242052976e-05,
+      "loss": 0.4567,
+      "step": 12200
     }
   ],
   "logging_steps": 50,