Training in progress, step 27400, checkpoint

last-checkpoint/README.md

@@ -1205,6 +1205,10 @@ You can finetune this model on your own dataset.
 | 0.4789 | 27100 | 0.2753        |
 | 0.4798 | 27150 | 0.35          |
 | 0.4806 | 27200 | 0.3143        |
+| 0.4815 | 27250 | 0.3968        |
+| 0.4824 | 27300 | 0.3246        |
+| 0.4833 | 27350 | 0.3131        |
+| 0.4842 | 27400 | 0.3078        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08045e1f2a8cd2432e9fa2b0ef00df2ac4ced1a000f41148266acaf751aa00fe
+oid sha256:e42bafc26f64fc942eebe9b36d05cb9ebd690bc7e84350aba5ef5927bebd23aa
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e8be442cecb8de3b11e871dbe4b21251728bce4db99665346a4ae741dd9661
+oid sha256:86493a89e1b924fce58823b6948f096f29423c5ce2b1e2b2de815c28e7f95699
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527a9946e2b187cf3aeaac98a6c12f5dc108889d1a7d08a9def35306b103680a
+oid sha256:f1ffba3c8137c0af09582c28fee3245b77ce6875ddb2ff1a79f1003af6257b2b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d84e0b16c16a3884265f119b778a7531d56abad22c7b0d844e8a1a93c8456c
+oid sha256:d79db97c4b1cd4a4d432cc88a5b1b07dc74a6838264e86b10e57ab5d0be29f45
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ac0dfa5e821d2ce353420d7dc3f3a06dc98c820a2502851855c1f7447269ad
+oid sha256:10c98a9a1e72b7cb62494c74d5b84c2a61b0c8fb7089e16aa24c2bd64d181a5f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48064179816578606,
+  "epoch": 0.4841759290346522,
   "eval_steps": 500,
-  "global_step": 27200,
+  "global_step": 27400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3816,6 +3816,34 @@
       "learning_rate": 2.8863560503426205e-05,
       "loss": 0.3143,
       "step": 27200
+    },
+    {
+      "epoch": 0.4815253308830026,
+      "grad_norm": 1.6409038305282593,
+      "learning_rate": 2.8814474485087667e-05,
+      "loss": 0.3968,
+      "step": 27250
+    },
+    {
+      "epoch": 0.4824088636002191,
+      "grad_norm": 1.4830607175827026,
+      "learning_rate": 2.876538846674913e-05,
+      "loss": 0.3246,
+      "step": 27300
+    },
+    {
+      "epoch": 0.48329239631743565,
+      "grad_norm": 1.6359367370605469,
+      "learning_rate": 2.87163024484106e-05,
+      "loss": 0.3131,
+      "step": 27350
+    },
+    {
+      "epoch": 0.4841759290346522,
+      "grad_norm": 1.1834681034088135,
+      "learning_rate": 2.8667216430072057e-05,
+      "loss": 0.3078,
+      "step": 27400
     }
   ],
   "logging_steps": 50,