Training in progress, step 12400, checkpoint

last-checkpoint/README.md

@@ -1269,6 +1269,10 @@ You can finetune this model on your own dataset.
 | 0.2138 | 12100 | 0.4082        |
 | 0.2147 | 12150 | 0.3855        |
 | 0.2156 | 12200 | 0.4567        |
+| 0.2165 | 12250 | 0.4368        |
+| 0.2173 | 12300 | 0.3686        |
+| 0.2182 | 12350 | 0.4163        |
+| 0.2191 | 12400 | 0.3595        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad55c4b6b6eb0c0378b40f5afe9b809839ef4dcaf65938b6be44df391f5a5ea4
+oid sha256:574b3805817f84c05fe61afaa266bdb741864872a08c8b02a26021f7f2d4b6a1
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6292ed9a900b0c859bfdd6c9df2c5387f1a04143b05826767cb8bedebe906bb1
+oid sha256:d4ffa53be833c86425bcb85e6adb4b16c9a27186fd568e0bc2763a7d2449b3db
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f520f013fa8b5071407e30d736875f828fde9d624a9e917e055760aba4e8b925
+oid sha256:6ef1f923f6a1dc64581eaa57f689d3afe64e52f3a89bbade50c868ec911b07ce
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400813ac47bbcdbc0fc813340b1eb9c8ae221654524666a11f89e971d58d1c7c
+oid sha256:3af4348a2f962e0a24bd0d54fa3ca7b60bf2d2d90f2e31ee6b869eaaa1d91a60
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038fcca02e593a472cc6365efd49e0401f5576654e492a85d64164b873c49869
+oid sha256:bd23584cb98398038b4f29f6fb0b60db3fae00d268a4c127abde12daed6ca267
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2155819830008305,
+  "epoch": 0.2191161138696966,
   "eval_steps": 500,
-  "global_step": 12200,
+  "global_step": 12400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1716,6 +1716,34 @@
       "learning_rate": 4.3581512242052976e-05,
       "loss": 0.4567,
       "step": 12200
+    },
+    {
+      "epoch": 0.21646551571804704,
+      "grad_norm": 2.0770373344421387,
+      "learning_rate": 4.353242622371444e-05,
+      "loss": 0.4368,
+      "step": 12250
+    },
+    {
+      "epoch": 0.21734904843526356,
+      "grad_norm": 1.4739536046981812,
+      "learning_rate": 4.3483340205375905e-05,
+      "loss": 0.3686,
+      "step": 12300
+    },
+    {
+      "epoch": 0.21823258115248007,
+      "grad_norm": 1.8857239484786987,
+      "learning_rate": 4.343425418703736e-05,
+      "loss": 0.4163,
+      "step": 12350
+    },
+    {
+      "epoch": 0.2191161138696966,
+      "grad_norm": 1.722424030303955,
+      "learning_rate": 4.3385168168698834e-05,
+      "loss": 0.3595,
+      "step": 12400
     }
   ],
   "logging_steps": 50,