Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4b0fca46c3ded7e0354733843df8d4bf1b9df58dec5886477ec67a8376d162
+oid sha256:5db0b95c8c3a10a91524dea9aacebbfcfbb9dde2761ab991c8022e2fe6df4272
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe2d4f69eb0fec6e19d2d081594a274f18dd48630014acd73fcf4cd64764f7d
+oid sha256:7586701c2e5e163ffc989df0f584bccf4e69f337fc17cdc68d4a10f7bdc4838f
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6829903aaa4143f234b90612cf464d1814d88258a1a614f0e155e2ec01b5e7
+oid sha256:b9177d90829d7463e0eb174ca56deba825ef7d7ca018aa2c22064a61c74ca9ea
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
+oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1922810261150913,
+  "epoch": 0.2884215391726369,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 11.192,
       "eval_steps_per_second": 2.801,
       "step": 26
+    },
+    {
+      "epoch": 0.19967645019644095,
+      "grad_norm": 56.23450469970703,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 85.5899,
+      "step": 27
+    },
+    {
+      "epoch": 0.2070718742777906,
+      "grad_norm": 55.729068756103516,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 84.6372,
+      "step": 28
+    },
+    {
+      "epoch": 0.21446729835914027,
+      "grad_norm": 44.94795608520508,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 81.2659,
+      "step": 29
+    },
+    {
+      "epoch": 0.22186272244048993,
+      "grad_norm": 43.78959274291992,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 84.2274,
+      "step": 30
+    },
+    {
+      "epoch": 0.22925814652183962,
+      "grad_norm": 40.38026809692383,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 80.1799,
+      "step": 31
+    },
+    {
+      "epoch": 0.23665357060318928,
+      "grad_norm": 39.87312698364258,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 80.2665,
+      "step": 32
+    },
+    {
+      "epoch": 0.24404899468453894,
+      "grad_norm": 42.08469772338867,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 81.3834,
+      "step": 33
+    },
+    {
+      "epoch": 0.25144441876588863,
+      "grad_norm": 40.6140251159668,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 80.8223,
+      "step": 34
+    },
+    {
+      "epoch": 0.25883984284723827,
+      "grad_norm": 52.44778823852539,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 85.2504,
+      "step": 35
+    },
+    {
+      "epoch": 0.26623526692858795,
+      "grad_norm": 44.90240478515625,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 80.1232,
+      "step": 36
+    },
+    {
+      "epoch": 0.2736306910099376,
+      "grad_norm": 44.05722427368164,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 85.218,
+      "step": 37
+    },
+    {
+      "epoch": 0.2810261150912873,
+      "grad_norm": 34.475032806396484,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 74.1421,
+      "step": 38
+    },
+    {
+      "epoch": 0.2884215391726369,
+      "grad_norm": 50.83314514160156,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 85.2003,
+      "step": 39
+    },
+    {
+      "epoch": 0.2884215391726369,
+      "eval_loss": 2.658181667327881,
+      "eval_runtime": 81.3831,
+      "eval_samples_per_second": 11.194,
+      "eval_steps_per_second": 2.802,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.850044129177764e+17,
+  "total_flos": 8.775066193766646e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null