Training in progress, step 31000, checkpoint

last-checkpoint/README.md

@@ -1277,6 +1277,10 @@ You can finetune this model on your own dataset.
 | 0.5425 | 30700 | 0.3094        |
 | 0.5434 | 30750 | 0.3077        |
 | 0.5443 | 30800 | 0.3505        |
+| 0.5451 | 30850 | 0.3485        |
+| 0.5460 | 30900 | 0.331         |
+| 0.5469 | 30950 | 0.2846        |
+| 0.5478 | 31000 | 0.3647        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc88dfeec5a070e3fd948dba14887b72312540e53c8949b21909a348ea27a4e
+oid sha256:88d75ffa8acb9d0ae6da6b85c5ebacb5d6d497b0b7f8d1e0cc906632d66303da
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3258bbff978fc0ab89659d377622b7a63dc9652d486808dbd59a56dd9bf6ccc1
+oid sha256:1ce5db6bab84b13b8d6237d74a48b1c574cceb26d03115a289d544fd81b83fe0
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed992908f9b2d94cfacaa25bd3a16c1eb2cbd116a690892a1034cc00bf4ec453
+oid sha256:225aac588847ab0002b2ca78215dc480b08f8f2752e40d301dfd2554473eaa86
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424edc0ec5b25fea421881d2bc754b25bc2bf24839236dba41579726e027f84d
+oid sha256:f17b09e37e3cf1eb4e07e5a39443f3088190a89ec52eee73b652e920bd5e3c6d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b1be98187efcd50aa0c5711a24f2a5afe8565001814025bf7b98b523a4dc07
+oid sha256:2d9c6b8e683bd0522d336f6d260614dd403087df118f434096a2340dd6c2f5dd
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5442561538053754,
+  "epoch": 0.5477902846742415,
   "eval_steps": 500,
-  "global_step": 30800,
+  "global_step": 31000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4320,6 +4320,34 @@
       "learning_rate": 2.533034890341835e-05,
       "loss": 0.3505,
       "step": 30800
+    },
+    {
+      "epoch": 0.5451396865225919,
+      "grad_norm": 1.785367488861084,
+      "learning_rate": 2.5281262885079815e-05,
+      "loss": 0.3485,
+      "step": 30850
+    },
+    {
+      "epoch": 0.5460232192398085,
+      "grad_norm": 4.639885425567627,
+      "learning_rate": 2.523217686674128e-05,
+      "loss": 0.331,
+      "step": 30900
+    },
+    {
+      "epoch": 0.546906751957025,
+      "grad_norm": 1.308772325515747,
+      "learning_rate": 2.518309084840274e-05,
+      "loss": 0.2846,
+      "step": 30950
+    },
+    {
+      "epoch": 0.5477902846742415,
+      "grad_norm": 1.3961265087127686,
+      "learning_rate": 2.5134004830064205e-05,
+      "loss": 0.3647,
+      "step": 31000
     }
   ],
   "logging_steps": 50,