Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd9718755560c308aecac276c9ee7fb044ae0ee5591d2e97ce7e9594e64a086
+oid sha256:3db4cec11cb96d0460bb12cee61072ce85dc9c15b08ea79ff3189ee41f96257a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562579292a75da3c16d1f208cfaf0a4b519d23fdbd9b53b4ed5d04e1d8e2d858
+oid sha256:c60385e8608bfc28d3eff1f686b5250b2f977ce329db2291a75b9c71be23b73f
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911058565dc868849673710656c32933e9a5c0c739dc26b6d67dce13bb3e41c3
+oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8615f1aeccd0f9873fc0cf2c0322fde20ac202421c015654a471730a5fa755
+oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20080321285140562,
+  "epoch": 0.30120481927710846,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 1.1736481776669307e-05,
       "loss": 1.3032,
       "step": 50
+    },
+    {
+      "epoch": 0.20481927710843373,
+      "grad_norm": 1.0638103485107422,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 1.3361,
+      "step": 51
+    },
+    {
+      "epoch": 0.20883534136546184,
+      "grad_norm": 1.422438144683838,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 1.4487,
+      "step": 52
+    },
+    {
+      "epoch": 0.21285140562248997,
+      "grad_norm": 1.2671741247177124,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 1.3626,
+      "step": 53
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 1.0545305013656616,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 1.3192,
+      "step": 54
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "eval_loss": 0.67100989818573,
+      "eval_runtime": 32.6003,
+      "eval_samples_per_second": 6.442,
+      "eval_steps_per_second": 0.828,
+      "step": 54
+    },
+    {
+      "epoch": 0.22088353413654618,
+      "grad_norm": 1.1217244863510132,
+      "learning_rate": 1e-05,
+      "loss": 1.0894,
+      "step": 55
+    },
+    {
+      "epoch": 0.2248995983935743,
+      "grad_norm": 1.5441569089889526,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 1.5076,
+      "step": 56
+    },
+    {
+      "epoch": 0.2289156626506024,
+      "grad_norm": 1.2194684743881226,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 1.3286,
+      "step": 57
+    },
+    {
+      "epoch": 0.23293172690763053,
+      "grad_norm": 1.2157171964645386,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 1.1355,
+      "step": 58
+    },
+    {
+      "epoch": 0.23694779116465864,
+      "grad_norm": 1.2383450269699097,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 1.3349,
+      "step": 59
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 1.0101817846298218,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.992,
+      "step": 60
+    },
+    {
+      "epoch": 0.24497991967871485,
+      "grad_norm": 1.3267630338668823,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 1.4941,
+      "step": 61
+    },
+    {
+      "epoch": 0.24899598393574296,
+      "grad_norm": 1.0341275930404663,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.8775,
+      "step": 62
+    },
+    {
+      "epoch": 0.25301204819277107,
+      "grad_norm": 1.5267117023468018,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.9736,
+      "step": 63
+    },
+    {
+      "epoch": 0.25301204819277107,
+      "eval_loss": 0.6493720412254333,
+      "eval_runtime": 32.5813,
+      "eval_samples_per_second": 6.445,
+      "eval_steps_per_second": 0.829,
+      "step": 63
+    },
+    {
+      "epoch": 0.2570281124497992,
+      "grad_norm": 1.3753007650375366,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.4487,
+      "step": 64
+    },
+    {
+      "epoch": 0.26104417670682734,
+      "grad_norm": 1.2772159576416016,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 1.0686,
+      "step": 65
+    },
+    {
+      "epoch": 0.26506024096385544,
+      "grad_norm": 1.349326491355896,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 1.209,
+      "step": 66
+    },
+    {
+      "epoch": 0.26907630522088355,
+      "grad_norm": 1.2562471628189087,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 1.3394,
+      "step": 67
+    },
+    {
+      "epoch": 0.27309236947791166,
+      "grad_norm": 1.4296122789382935,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 1.3279,
+      "step": 68
+    },
+    {
+      "epoch": 0.27710843373493976,
+      "grad_norm": 1.0856250524520874,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.6899,
+      "step": 69
+    },
+    {
+      "epoch": 0.28112449799196787,
+      "grad_norm": 1.3272840976715088,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.2571,
+      "step": 70
+    },
+    {
+      "epoch": 0.285140562248996,
+      "grad_norm": 1.5904431343078613,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 1.2008,
+      "step": 71
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 1.8825539350509644,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 1.9554,
+      "step": 72
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "eval_loss": 0.6365012526512146,
+      "eval_runtime": 32.5792,
+      "eval_samples_per_second": 6.446,
+      "eval_steps_per_second": 0.829,
+      "step": 72
+    },
+    {
+      "epoch": 0.2931726907630522,
+      "grad_norm": 1.4897550344467163,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 1.395,
+      "step": 73
+    },
+    {
+      "epoch": 0.2971887550200803,
+      "grad_norm": 1.3629871606826782,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 1.3097,
+      "step": 74
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "grad_norm": 1.578955888748169,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 1.3274,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 9.521684545536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null