Training in progress, step 29400, checkpoint

last-checkpoint/README.md

@@ -1245,6 +1245,10 @@ You can finetune this model on your own dataset.
 | 0.5142 | 29100 | 0.2647        |
 | 0.5151 | 29150 | 0.4395        |
 | 0.5160 | 29200 | 0.295         |
+| 0.5169 | 29250 | 0.3927        |
+| 0.5178 | 29300 | 0.3492        |
+| 0.5186 | 29350 | 0.3304        |
+| 0.5195 | 29400 | 0.3557        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6302ef96cfec2421b0ca1ae5faa95bc5dd4d222138074480f8f7e034e0f55fc2
+oid sha256:52be879aebe70d6a3b2a056beedca08f2be73f61ebc46f06911a85e46d41c0c2
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd6b7448710e566b9e15662a68fba694d10e1ca083c5858cb67b26f8f1705c9
+oid sha256:06028c42fad3044c4b23353b232592f0571645864a036fae7f9a4aff967be12e
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1049af8581efffa2917702c9f959fe2570b21616b1ec430cb670ed82abab5b37
+oid sha256:83cd1380c57226aa3ea98011ce1f02c69976c7ca7a80455b341682a640b1d651
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019221f3192f4927c921b123577a1666f9b9f4c37e86b8641ed6cf124537ad31
+oid sha256:c77541b39dbb71635c2f0939f339b7fa24c5c0af9ad45520c78a03f92ccdb59e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8bdd077ed24c7c735344da9353b0b35d61ed70a50b66211d3c4d79475e4b984
+oid sha256:5f226454d5f7fa5a1b29f0c7888dfe13f17698107b349cee7ac0fbf136bdbea6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5159831068544468,
+  "epoch": 0.5195172377233129,
   "eval_steps": 500,
-  "global_step": 29200,
+  "global_step": 29400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4096,6 +4096,34 @@
       "learning_rate": 2.6900119769884745e-05,
       "loss": 0.295,
       "step": 29200
+    },
+    {
+      "epoch": 0.5168666395716633,
+      "grad_norm": 1.1258848905563354,
+      "learning_rate": 2.6851033751546213e-05,
+      "loss": 0.3927,
+      "step": 29250
+    },
+    {
+      "epoch": 0.5177501722888799,
+      "grad_norm": 2.5667836666107178,
+      "learning_rate": 2.680194773320767e-05,
+      "loss": 0.3492,
+      "step": 29300
+    },
+    {
+      "epoch": 0.5186337050060964,
+      "grad_norm": 1.7218468189239502,
+      "learning_rate": 2.675286171486914e-05,
+      "loss": 0.3304,
+      "step": 29350
+    },
+    {
+      "epoch": 0.5195172377233129,
+      "grad_norm": 2.4908971786499023,
+      "learning_rate": 2.6703775696530603e-05,
+      "loss": 0.3557,
+      "step": 29400
     }
   ],
   "logging_steps": 50,