Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa91a5c7c895a1edf268b92ddf69cfe9a312ec282ab3dd161bf2035f3691779
+oid sha256:ce4af7a85f81eddebfd61247d3005446d1a1dc704565ff25800017436a77c518
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a6d8cc56f099d0c89803df4141df9e19d34c394d7a6d3f72a922f01bb144e3
+oid sha256:e9efff3c64a4e3205e3781def76b580a1382c230a6c26d77e33668dc1e0b6b59
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51835fedd600a13be493cd65243a4b1bbb70fe38246f07acaa55d78ff0549496
+oid sha256:7404f1d49ef0a025828ba42224e33ca3657874e341d0cdde3bb1fed2d6facb0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000811187903565982,
+  "epoch": 0.001622375807131964,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 1.0345,
       "step": 25
+    },
+    {
+      "epoch": 0.0008436354197086213,
+      "grad_norm": 0.6223241090774536,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.0311,
+      "step": 26
+    },
+    {
+      "epoch": 0.0008760829358512606,
+      "grad_norm": 0.7213761806488037,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.0735,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008760829358512606,
+      "eval_loss": 1.129144310951233,
+      "eval_runtime": 409.5892,
+      "eval_samples_per_second": 63.363,
+      "eval_steps_per_second": 7.923,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009085304519938998,
+      "grad_norm": 0.7402194142341614,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0728,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009409779681365391,
+      "grad_norm": 0.7021007537841797,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1606,
+      "step": 29
+    },
+    {
+      "epoch": 0.0009734254842791784,
+      "grad_norm": 0.7063369750976562,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.1922,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010058730004218178,
+      "grad_norm": 0.7353460192680359,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.266,
+      "step": 31
+    },
+    {
+      "epoch": 0.001038320516564457,
+      "grad_norm": 0.6535232067108154,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.1358,
+      "step": 32
+    },
+    {
+      "epoch": 0.0010707680327070963,
+      "grad_norm": 0.7119964957237244,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.193,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011032155488497355,
+      "grad_norm": 0.7616000175476074,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.225,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011356630649923748,
+      "grad_norm": 0.6312659382820129,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.0475,
+      "step": 35
+    },
+    {
+      "epoch": 0.001168110581135014,
+      "grad_norm": 0.9175184369087219,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.0903,
+      "step": 36
+    },
+    {
+      "epoch": 0.001168110581135014,
+      "eval_loss": 1.1155873537063599,
+      "eval_runtime": 410.7403,
+      "eval_samples_per_second": 63.186,
+      "eval_steps_per_second": 7.9,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012005580972776534,
+      "grad_norm": 0.41725394129753113,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.0517,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012330056134202928,
+      "grad_norm": 0.6825345158576965,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.134,
+      "step": 38
+    },
+    {
+      "epoch": 0.001265453129562932,
+      "grad_norm": 0.641930878162384,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.4195,
+      "step": 39
+    },
+    {
+      "epoch": 0.0012979006457055713,
+      "grad_norm": 0.7435463070869446,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.195,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013303481618482105,
+      "grad_norm": 0.5704800486564636,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.0218,
+      "step": 41
+    },
+    {
+      "epoch": 0.0013627956779908499,
+      "grad_norm": 0.6911413669586182,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.2863,
+      "step": 42
+    },
+    {
+      "epoch": 0.001395243194133489,
+      "grad_norm": 0.9549648761749268,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.2395,
+      "step": 43
+    },
+    {
+      "epoch": 0.0014276907102761284,
+      "grad_norm": 0.8420898914337158,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.0508,
+      "step": 44
+    },
+    {
+      "epoch": 0.0014601382264187676,
+      "grad_norm": 0.8447883129119873,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.0626,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014601382264187676,
+      "eval_loss": 1.1072334051132202,
+      "eval_runtime": 410.1574,
+      "eval_samples_per_second": 63.276,
+      "eval_steps_per_second": 7.912,
+      "step": 45
+    },
+    {
+      "epoch": 0.001492585742561407,
+      "grad_norm": 0.7884063124656677,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1144,
+      "step": 46
+    },
+    {
+      "epoch": 0.001525033258704046,
+      "grad_norm": 0.6031967401504517,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.2737,
+      "step": 47
+    },
+    {
+      "epoch": 0.0015574807748466855,
+      "grad_norm": 1.1018924713134766,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.0928,
+      "step": 48
+    },
+    {
+      "epoch": 0.0015899282909893249,
+      "grad_norm": 0.6400368213653564,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.0312,
+      "step": 49
+    },
+    {
+      "epoch": 0.001622375807131964,
+      "grad_norm": 0.5094920992851257,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.951,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2727827245891584.0,
+  "total_flos": 5301249175977984.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null