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:e9208ec33273f291a92a7e5187a418113884ea04afdd9b606a1e4283ba30b04c
+oid sha256:e336a19695e7c95ab4d444c76b90384ca1d7030d3a13c1af1caf49bf5a3f4266
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a98e4cd8c25485cf6062731bd7abf44bb9bbc2ae90345c252cb7c1a43c32d4
+oid sha256:c248e74721ed477079bc3ea5c85edd96348c0e6b244ae126bd515f6ce0001ae0
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
+oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
 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": 0.4240570846075433,
+  "epoch": 0.636085626911315,
   "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": 10.722,
       "eval_steps_per_second": 2.7,
       "step": 26
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.4302608072757721,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7152,
+      "step": 27
+    },
+    {
+      "epoch": 0.4566768603465851,
+      "grad_norm": 0.3711889386177063,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7525,
+      "step": 28
+    },
+    {
+      "epoch": 0.47298674821610603,
+      "grad_norm": 0.47885867953300476,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7355,
+      "step": 29
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 0.4034803807735443,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8054,
+      "step": 30
+    },
+    {
+      "epoch": 0.5056065239551478,
+      "grad_norm": 0.455782026052475,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7633,
+      "step": 31
+    },
+    {
+      "epoch": 0.5219164118246687,
+      "grad_norm": 0.5047242045402527,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.796,
+      "step": 32
+    },
+    {
+      "epoch": 0.5382262996941896,
+      "grad_norm": 0.3796207010746002,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7821,
+      "step": 33
+    },
+    {
+      "epoch": 0.5545361875637105,
+      "grad_norm": 0.41559967398643494,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7876,
+      "step": 34
+    },
+    {
+      "epoch": 0.5708460754332314,
+      "grad_norm": 0.44059449434280396,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7923,
+      "step": 35
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.44257858395576477,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7218,
+      "step": 36
+    },
+    {
+      "epoch": 0.6034658511722731,
+      "grad_norm": 0.36089643836021423,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7391,
+      "step": 37
+    },
+    {
+      "epoch": 0.6197757390417941,
+      "grad_norm": 0.41137370467185974,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8426,
+      "step": 38
+    },
+    {
+      "epoch": 0.636085626911315,
+      "grad_norm": 0.4219225347042084,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7719,
+      "step": 39
+    },
+    {
+      "epoch": 0.636085626911315,
+      "eval_loss": 0.7565998435020447,
+      "eval_runtime": 38.0072,
+      "eval_samples_per_second": 10.866,
+      "eval_steps_per_second": 2.736,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.850040779103273e+17,
+  "total_flos": 8.77506116865491e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null