Training in progress, epoch 1, checkpoint

checkpoint-3599/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ea57b88e77d0ad7464517a3a05f2d59c6197c3a9f78a086e88b01e15b346f4
+oid sha256:e80772e2eadbfaba74c7bd52ee5780fe403361d763193581d8c19cacf6f60f09
 size 541459256

checkpoint-3599/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa303a5c6351d717792656330fd7ca8a3d6f7d5c2dea6d16c3cf1c104ae52c6e
+oid sha256:fda060a95f49b34613c5aca089766930ecff14dd3ff6e9c13192aed0351b0022
 size 33662074

checkpoint-3599/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8409cfd85ce846fced25a9d710751277f8eb105ecd9b11986a85acca247b7f5d
+oid sha256:ed9788f623dbedcffdd08e10e7e7c688263bd7e046f284da03c20e238150c564
 size 15024

checkpoint-3599/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864dbefa7c8251ca68d1d3b4700787ea5586f8e149337d67d4a16769235cdfc0
+oid sha256:e90539e2e1f01024a2fc0f2b33e6699e8fab3c3f42a8d71f4cd892272a95f29f
 size 15024

checkpoint-3599/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab4464c17dd70ab055e558bb33f713fce0403d324bcb68cbf0b9ade488e1e4f
+oid sha256:1ad8910a4ffa0dc7251ac9e854005ca1e2bfaecbe884141af2869975e76d80c0
 size 15024

checkpoint-3599/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d158a9696b46d55b7fe4fd85e5e44cc5b5c857659799d699bf3d2b08ee524153
+oid sha256:5c1dd7389977a275bf118f5a82bc34870d5f7ffbe5bc19671403b0f80601a782
 size 15024

checkpoint-3599/trainer_state.json

@@ -10,83 +10,83 @@
   "log_history": [
     {
       "epoch": 0.13892747985551543,
-      "grad_norm": 0.6994414925575256,
-      "learning_rate": 0.00039537834583680656,
-      "loss": 0.2943,
+      "grad_norm": 0.4299773573875427,
+      "learning_rate": 0.0003953968695007873,
+      "loss": 0.2967,
       "step": 500
     },
     {
       "epoch": 0.2000555709919422,
-      "eval_loss": 0.21401312947273254,
-      "eval_runtime": 16.5317,
-      "eval_samples_per_second": 30.245,
-      "eval_steps_per_second": 3.811,
+      "eval_loss": 0.1983761489391327,
+      "eval_runtime": 16.4512,
+      "eval_samples_per_second": 30.393,
+      "eval_steps_per_second": 3.83,
       "step": 720
     },
     {
       "epoch": 0.27785495971103086,
-      "grad_norm": 0.5945971608161926,
-      "learning_rate": 0.00039075669167361305,
-      "loss": 0.1986,
+      "grad_norm": 0.5706949830055237,
+      "learning_rate": 0.0003907659535056034,
+      "loss": 0.1959,
       "step": 1000
     },
     {
       "epoch": 0.4001111419838844,
-      "eval_loss": 0.17625106871128082,
-      "eval_runtime": 16.4823,
-      "eval_samples_per_second": 30.336,
+      "eval_loss": 0.17383727431297302,
+      "eval_runtime": 16.4842,
+      "eval_samples_per_second": 30.332,
       "eval_steps_per_second": 3.822,
       "step": 1440
     },
     {
       "epoch": 0.41678243956654626,
-      "grad_norm": 0.3619824945926666,
-      "learning_rate": 0.0003861257756784292,
-      "loss": 0.1802,
+      "grad_norm": 0.5392869710922241,
+      "learning_rate": 0.0003861350375104196,
+      "loss": 0.1723,
       "step": 1500
     },
     {
       "epoch": 0.5557099194220617,
-      "grad_norm": 0.40362638235092163,
-      "learning_rate": 0.00038149485968324534,
-      "loss": 0.1686,
+      "grad_norm": 0.5005412697792053,
+      "learning_rate": 0.0003815041215152357,
+      "loss": 0.1636,
       "step": 2000
     },
     {
       "epoch": 0.6001667129758266,
-      "eval_loss": 0.16156445443630219,
-      "eval_runtime": 16.3535,
-      "eval_samples_per_second": 30.575,
-      "eval_steps_per_second": 3.852,
+      "eval_loss": 0.16229495406150818,
+      "eval_runtime": 16.4963,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 3.819,
       "step": 2160
     },
     {
       "epoch": 0.6946373992775771,
-      "grad_norm": 0.4962793290615082,
-      "learning_rate": 0.0003768639436880615,
-      "loss": 0.1577,
+      "grad_norm": 0.370914489030838,
+      "learning_rate": 0.0003768732055200519,
+      "loss": 0.1539,
       "step": 2500
     },
     {
       "epoch": 0.8002222839677688,
-      "eval_loss": 0.15043224394321442,
-      "eval_runtime": 16.3325,
-      "eval_samples_per_second": 30.614,
-      "eval_steps_per_second": 3.857,
+      "eval_loss": 0.1537286937236786,
+      "eval_runtime": 16.4662,
+      "eval_samples_per_second": 30.365,
+      "eval_steps_per_second": 3.826,
       "step": 2880
     },
     {
       "epoch": 0.8335648791330925,
-      "grad_norm": 0.41315382719039917,
-      "learning_rate": 0.0003722330276928777,
-      "loss": 0.1493,
+      "grad_norm": 0.41378697752952576,
+      "learning_rate": 0.000372242289524868,
+      "loss": 0.1445,
       "step": 3000
     },
     {
       "epoch": 0.972492358988608,
-      "grad_norm": 0.37953054904937744,
+      "grad_norm": 0.4000154137611389,
       "learning_rate": 0.0003676113735296842,
-      "loss": 0.1477,
+      "loss": 0.1384,
       "step": 3500
     }
   ],
@@ -107,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.733879185296589e+17,
+  "total_flos": 6.778569565551985e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-3599/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58052fbf3a2b07f2a6024b5cc28db88f1f0e48109a11483aa716d00657e9906e
+oid sha256:b2784cc9ebb113293b9d7c5af564dbf5463d67b520bf149c8840105fec4706ec
 size 5496