Training in progress, step 27200, checkpoint

last-checkpoint/README.md

@@ -1201,6 +1201,10 @@ You can finetune this model on your own dataset.
 | 0.4753 | 26900 | 0.5175        |
 | 0.4762 | 26950 | 0.3398        |
 | 0.4771 | 27000 | 0.3683        |
+| 0.4780 | 27050 | 0.341         |
+| 0.4789 | 27100 | 0.2753        |
+| 0.4798 | 27150 | 0.35          |
+| 0.4806 | 27200 | 0.3143        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:157a36f69c8d6be89b19a5fc2041a6a70bae891ca7bdb6e1f8c5561949e9bafa
+oid sha256:08045e1f2a8cd2432e9fa2b0ef00df2ac4ced1a000f41148266acaf751aa00fe
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf3f6a255c756d17edb6da60dbf398937995bd4e9513159583e5e4237f23a63
+oid sha256:91e8be442cecb8de3b11e871dbe4b21251728bce4db99665346a4ae741dd9661
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b7843d303f1fcbcb7ded0ee18633ae1a240b93a82ce64b7dc80620210cefa4
+oid sha256:527a9946e2b187cf3aeaac98a6c12f5dc108889d1a7d08a9def35306b103680a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f721603f06800f16238813b709df823dd021b986d5f3f64a3fdb3ad2473f4313
+oid sha256:f6d84e0b16c16a3884265f119b778a7531d56abad22c7b0d844e8a1a93c8456c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9c472a19e7b9448212aaddb68f6d9878d89c838a06487c2d680b2179532b97
+oid sha256:d1ac0dfa5e821d2ce353420d7dc3f3a06dc98c820a2502851855c1f7447269ad
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47710766729692,
+  "epoch": 0.48064179816578606,
   "eval_steps": 500,
-  "global_step": 27000,
+  "global_step": 27200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3788,6 +3788,34 @@
       "learning_rate": 2.905990457678035e-05,
       "loss": 0.3683,
       "step": 27000
+    },
+    {
+      "epoch": 0.47799120001413653,
+      "grad_norm": 1.1095103025436401,
+      "learning_rate": 2.9010818558441815e-05,
+      "loss": 0.341,
+      "step": 27050
+    },
+    {
+      "epoch": 0.47887473273135306,
+      "grad_norm": 1.5168321132659912,
+      "learning_rate": 2.8961732540103276e-05,
+      "loss": 0.2753,
+      "step": 27100
+    },
+    {
+      "epoch": 0.4797582654485696,
+      "grad_norm": 1.9980124235153198,
+      "learning_rate": 2.891264652176474e-05,
+      "loss": 0.35,
+      "step": 27150
+    },
+    {
+      "epoch": 0.48064179816578606,
+      "grad_norm": 1.6252918243408203,
+      "learning_rate": 2.8863560503426205e-05,
+      "loss": 0.3143,
+      "step": 27200
     }
   ],
   "logging_steps": 50,