Training in progress, epoch 1, checkpoint

checkpoint-3599/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a3afb1c763321f2bd1d2aa3dc8be35c653bc68a032d5c9c5a31c51aa69c8cd
+oid sha256:98ea57b88e77d0ad7464517a3a05f2d59c6197c3a9f78a086e88b01e15b346f4
 size 541459256

checkpoint-3599/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:273b67275a36afa8e4405688881b549139cd12a48039f2387ca7423b583c5dd5
+oid sha256:aa303a5c6351d717792656330fd7ca8a3d6f7d5c2dea6d16c3cf1c104ae52c6e
 size 33662074

checkpoint-3599/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6f3a43117e640912628a4fa4cf4d3868955758ec9f5c569a5f9ddc813cc496
+oid sha256:8409cfd85ce846fced25a9d710751277f8eb105ecd9b11986a85acca247b7f5d
 size 15024

checkpoint-3599/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20eaeb45144578cb5b9cac909f725cca209d8046f816821ee5fa320072bfa0c4
+oid sha256:864dbefa7c8251ca68d1d3b4700787ea5586f8e149337d67d4a16769235cdfc0
 size 15024

checkpoint-3599/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc3405c7ff444273126451475ce6adef44e68cdf092c001101aaedacf98dc13
+oid sha256:1ab4464c17dd70ab055e558bb33f713fce0403d324bcb68cbf0b9ade488e1e4f
 size 15024

checkpoint-3599/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28662739cfee2378fd37c7993d6ef747e967040c35a8946319d697abfaa37a83
+oid sha256:d158a9696b46d55b7fe4fd85e5e44cc5b5c857659799d699bf3d2b08ee524153
 size 15024

checkpoint-3599/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f85ef4c683e2cabdc66d89807722acfb285fba408982cc4dcce4c0a319b1d1
+oid sha256:389dc0455bfde9e5bd7f663cc1299e3355b7c51181720b0bb246350e7f42f84d
 size 1064

checkpoint-3599/trainer_state.json

@@ -10,83 +10,83 @@
   "log_history": [
     {
       "epoch": 0.13892747985551543,
-      "grad_norm": 0.5752785205841064,
-      "learning_rate": 0.00039538760766879693,
-      "loss": 0.2947,
+      "grad_norm": 0.6994414925575256,
+      "learning_rate": 0.00039537834583680656,
+      "loss": 0.2943,
       "step": 500
     },
     {
       "epoch": 0.2000555709919422,
-      "eval_loss": 0.19290830194950104,
-      "eval_runtime": 6.2591,
-      "eval_samples_per_second": 79.884,
-      "eval_steps_per_second": 10.065,
+      "eval_loss": 0.21401312947273254,
+      "eval_runtime": 16.5317,
+      "eval_samples_per_second": 30.245,
+      "eval_steps_per_second": 3.811,
       "step": 720
     },
     {
       "epoch": 0.27785495971103086,
-      "grad_norm": 0.4608103632926941,
+      "grad_norm": 0.5945971608161926,
       "learning_rate": 0.00039075669167361305,
-      "loss": 0.1972,
+      "loss": 0.1986,
       "step": 1000
     },
     {
       "epoch": 0.4001111419838844,
-      "eval_loss": 0.17835241556167603,
-      "eval_runtime": 6.2534,
-      "eval_samples_per_second": 79.957,
-      "eval_steps_per_second": 10.075,
+      "eval_loss": 0.17625106871128082,
+      "eval_runtime": 16.4823,
+      "eval_samples_per_second": 30.336,
+      "eval_steps_per_second": 3.822,
       "step": 1440
     },
     {
       "epoch": 0.41678243956654626,
-      "grad_norm": 0.44341567158699036,
+      "grad_norm": 0.3619824945926666,
       "learning_rate": 0.0003861257756784292,
-      "loss": 0.1817,
+      "loss": 0.1802,
       "step": 1500
     },
     {
       "epoch": 0.5557099194220617,
-      "grad_norm": 0.3840184509754181,
+      "grad_norm": 0.40362638235092163,
       "learning_rate": 0.00038149485968324534,
-      "loss": 0.1679,
+      "loss": 0.1686,
       "step": 2000
     },
     {
       "epoch": 0.6001667129758266,
-      "eval_loss": 0.16081829369068146,
-      "eval_runtime": 6.259,
-      "eval_samples_per_second": 79.885,
-      "eval_steps_per_second": 10.065,
+      "eval_loss": 0.16156445443630219,
+      "eval_runtime": 16.3535,
+      "eval_samples_per_second": 30.575,
+      "eval_steps_per_second": 3.852,
       "step": 2160
     },
     {
       "epoch": 0.6946373992775771,
-      "grad_norm": 0.4211641848087311,
+      "grad_norm": 0.4962793290615082,
       "learning_rate": 0.0003768639436880615,
-      "loss": 0.1584,
+      "loss": 0.1577,
       "step": 2500
     },
     {
       "epoch": 0.8002222839677688,
-      "eval_loss": 0.15788592398166656,
-      "eval_runtime": 6.2616,
-      "eval_samples_per_second": 79.852,
-      "eval_steps_per_second": 10.061,
+      "eval_loss": 0.15043224394321442,
+      "eval_runtime": 16.3325,
+      "eval_samples_per_second": 30.614,
+      "eval_steps_per_second": 3.857,
       "step": 2880
     },
     {
       "epoch": 0.8335648791330925,
-      "grad_norm": 0.3697059750556946,
-      "learning_rate": 0.0003722515513568584,
-      "loss": 0.1501,
+      "grad_norm": 0.41315382719039917,
+      "learning_rate": 0.0003722330276928777,
+      "loss": 0.1493,
       "step": 3000
     },
     {
       "epoch": 0.972492358988608,
-      "grad_norm": 0.420885294675827,
-      "learning_rate": 0.00036762063536167455,
-      "loss": 0.1478,
+      "grad_norm": 0.37953054904937744,
+      "learning_rate": 0.0003676113735296842,
+      "loss": 0.1477,
       "step": 3500
     }
   ],

checkpoint-3599/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfac93b9b3b40952529bd84fbff166d6257cf3d6fa4cc937269a037e37d853d5
+oid sha256:58052fbf3a2b07f2a6024b5cc28db88f1f0e48109a11483aa716d00657e9906e
 size 5496