Training in progress, step 37800, checkpoint

last-checkpoint/README.md

@@ -1269,6 +1269,10 @@ You can finetune this model on your own dataset.
 | 0.6626 | 37500 | 0.3288        |
 | 0.6635 | 37550 | 0.4221        |
 | 0.6644 | 37600 | 0.3711        |
+| 0.6653 | 37650 | 0.2418        |
+| 0.6662 | 37700 | 0.3           |
+| 0.6671 | 37750 | 0.3147        |
+| 0.6680 | 37800 | 0.2895        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49cc2b93728e49de217dc60cd367d1893bf2f9bed3ceb4afe515eabf48f6ed08
+oid sha256:e2bc434db7c929c75024a831ecc5cc03d8b7a4eddd4dd3db1978cf30bffea991
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336c01379450b237f69846bbca72ce99e84b15f94ed370646502b855f060fb86
+oid sha256:0610d398ebf6d38b0b9cbf0894fccceee41b5214e963879ca6b28162561c192a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1e5086acf3138ad2715b1b0217454786680720f4c61739eebdb529556b78ae
+oid sha256:5d58558a83c013260c9bf646c050a79e224f490d790bbdf4116e8fa1e264f106
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa03be736ad2e04b4837e2c32a43b6b3386812b76663243651e6e6a4bb8fb202
+oid sha256:381cb302a73675bf2179ed8dcab807616061c0bb5718d119ea0e96650e118eb1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:188c2cbd8075ea7a1b7865239bd6d95b63ebe7d536a5366864b0e98bf73e24a0
+oid sha256:2a32f613d93659adf5731cade217c9a9122ff518b0d84ca3c2508b48b15899d8
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.664416603346822,
+  "epoch": 0.667950734215688,
   "eval_steps": 500,
-  "global_step": 37600,
+  "global_step": 37800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5272,6 +5272,34 @@
       "learning_rate": 1.8657595570477705e-05,
       "loss": 0.3711,
       "step": 37600
+    },
+    {
+      "epoch": 0.6653001360640385,
+      "grad_norm": 1.907202959060669,
+      "learning_rate": 1.860850955213917e-05,
+      "loss": 0.2418,
+      "step": 37650
+    },
+    {
+      "epoch": 0.666183668781255,
+      "grad_norm": 1.4358186721801758,
+      "learning_rate": 1.855942353380063e-05,
+      "loss": 0.3,
+      "step": 37700
+    },
+    {
+      "epoch": 0.6670672014984715,
+      "grad_norm": 1.4791388511657715,
+      "learning_rate": 1.85103375154621e-05,
+      "loss": 0.3147,
+      "step": 37750
+    },
+    {
+      "epoch": 0.667950734215688,
+      "grad_norm": 1.383799433708191,
+      "learning_rate": 1.846125149712356e-05,
+      "loss": 0.2895,
+      "step": 37800
     }
   ],
   "logging_steps": 50,