Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f98e2d76bd6c0f8afe79bec80dc3523cba76746606cf9c88bcfb380552ceb78
+oid sha256:77f448118bdd20ff0d8551fafb2c1d52a2a17c7ffa6d5229afd660f2efdaa643
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a08dc19b9a7c3ecd3247c5f0dcd658f23ca965a8ffd0212cc9b1da207d0f23
+oid sha256:ca43a57921ff47a143b83fdf9ec868d1cb12aa335e0dca9f8ada312e1b5ce0f5
 size 18902665

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.5014102458953857,
+  "best_metric": 2.5020904541015625,
   "best_model_checkpoint": "./outputs/checkpoint-500",
   "epoch": 0.36429872495446264,
   "eval_steps": 100,
@@ -16,66 +16,66 @@
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6424810886383057,
-      "eval_runtime": 206.4108,
-      "eval_samples_per_second": 30.396,
-      "eval_steps_per_second": 3.803,
+      "eval_loss": 2.6424834728240967,
+      "eval_runtime": 206.3704,
+      "eval_samples_per_second": 30.402,
+      "eval_steps_per_second": 3.804,
       "step": 100
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.6061,
+      "loss": 2.6053,
       "step": 200
     },
     {
       "epoch": 0.15,
-      "eval_loss": 2.5929574966430664,
-      "eval_runtime": 206.2177,
-      "eval_samples_per_second": 30.424,
-      "eval_steps_per_second": 3.807,
+      "eval_loss": 2.592982053756714,
+      "eval_runtime": 206.2608,
+      "eval_samples_per_second": 30.418,
+      "eval_steps_per_second": 3.806,
       "step": 200
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.5643,
+      "loss": 2.5637,
       "step": 300
     },
     {
       "epoch": 0.22,
-      "eval_loss": 2.5578970909118652,
-      "eval_runtime": 206.509,
-      "eval_samples_per_second": 30.381,
-      "eval_steps_per_second": 3.801,
+      "eval_loss": 2.558687448501587,
+      "eval_runtime": 206.6302,
+      "eval_samples_per_second": 30.363,
+      "eval_steps_per_second": 3.799,
       "step": 300
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.5383,
+      "loss": 2.5384,
       "step": 400
     },
     {
       "epoch": 0.29,
-      "eval_loss": 2.5257716178894043,
-      "eval_runtime": 206.1349,
-      "eval_samples_per_second": 30.436,
-      "eval_steps_per_second": 3.808,
+      "eval_loss": 2.5261261463165283,
+      "eval_runtime": 206.3988,
+      "eval_samples_per_second": 30.397,
+      "eval_steps_per_second": 3.803,
       "step": 400
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 2.4959,
+      "loss": 2.4965,
       "step": 500
     },
     {
       "epoch": 0.36,
-      "eval_loss": 2.5014102458953857,
-      "eval_runtime": 282.6461,
-      "eval_samples_per_second": 22.197,
-      "eval_steps_per_second": 2.777,
+      "eval_loss": 2.5020904541015625,
+      "eval_runtime": 273.7006,
+      "eval_samples_per_second": 22.923,
+      "eval_steps_per_second": 2.868,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
+oid sha256:3618b713e8d14cca4d31f18e13bbc5304b540d431ee441c88df694b97c28653e
 size 4219