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:aedcaf6db9d824cb52ade082dced2012138d613bcb6a61e89e8f1afbffcf23de
+oid sha256:41ba83e9fdbb45dce8be26232c5205204351741c116cb8108f38da336d9ebdb9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca267f984319bc86f753c0055cd6b31c24532e9696a64e21b41248c942a9094
+oid sha256:549dc3b3ea553aa701e9e52e7c03c3d14465115f738e0ffc587c7cebaae2d253
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
+oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
 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": 0.001295840352468576,
+  "epoch": 0.002591680704937152,
   "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": 2.3507,
       "step": 25
+    },
+    {
+      "epoch": 0.001347673966567319,
+      "grad_norm": 2.0271666049957275,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.3528,
+      "step": 26
+    },
+    {
+      "epoch": 0.001399507580666062,
+      "grad_norm": 1.7645819187164307,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.4185,
+      "step": 27
+    },
+    {
+      "epoch": 0.001399507580666062,
+      "eval_loss": 2.4034855365753174,
+      "eval_runtime": 1773.3095,
+      "eval_samples_per_second": 9.162,
+      "eval_steps_per_second": 1.145,
+      "step": 27
+    },
+    {
+      "epoch": 0.001451341194764805,
+      "grad_norm": 1.8423093557357788,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.4298,
+      "step": 28
+    },
+    {
+      "epoch": 0.001503174808863548,
+      "grad_norm": 2.868162155151367,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.3648,
+      "step": 29
+    },
+    {
+      "epoch": 0.0015550084229622911,
+      "grad_norm": 2.26560378074646,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.3836,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016068420370610342,
+      "grad_norm": 1.755423665046692,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.3411,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016586756511597772,
+      "grad_norm": 1.673230528831482,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.5404,
+      "step": 32
+    },
+    {
+      "epoch": 0.0017105092652585203,
+      "grad_norm": 1.7275108098983765,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.492,
+      "step": 33
+    },
+    {
+      "epoch": 0.001762342879357263,
+      "grad_norm": 1.8824987411499023,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.5956,
+      "step": 34
+    },
+    {
+      "epoch": 0.0018141764934560061,
+      "grad_norm": 1.8801908493041992,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.427,
+      "step": 35
+    },
+    {
+      "epoch": 0.0018660101075547492,
+      "grad_norm": 2.096254587173462,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.4255,
+      "step": 36
+    },
+    {
+      "epoch": 0.0018660101075547492,
+      "eval_loss": 2.351825475692749,
+      "eval_runtime": 1774.3205,
+      "eval_samples_per_second": 9.157,
+      "eval_steps_per_second": 1.145,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019178437216534922,
+      "grad_norm": 2.0004048347473145,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.0979,
+      "step": 37
+    },
+    {
+      "epoch": 0.0019696773357522354,
+      "grad_norm": 2.086202621459961,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.2972,
+      "step": 38
+    },
+    {
+      "epoch": 0.0020215109498509785,
+      "grad_norm": 1.5125240087509155,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.3179,
+      "step": 39
+    },
+    {
+      "epoch": 0.0020733445639497215,
+      "grad_norm": 1.5626386404037476,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.2221,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021251781780484646,
+      "grad_norm": 1.8468570709228516,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.436,
+      "step": 41
+    },
+    {
+      "epoch": 0.0021770117921472076,
+      "grad_norm": 1.7203456163406372,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.3326,
+      "step": 42
+    },
+    {
+      "epoch": 0.0022288454062459506,
+      "grad_norm": 1.7609412670135498,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.4079,
+      "step": 43
+    },
+    {
+      "epoch": 0.0022806790203446937,
+      "grad_norm": 1.9543553590774536,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.3076,
+      "step": 44
+    },
+    {
+      "epoch": 0.0023325126344434367,
+      "grad_norm": 1.9948867559432983,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023325126344434367,
+      "eval_loss": 2.3102049827575684,
+      "eval_runtime": 1772.0158,
+      "eval_samples_per_second": 9.169,
+      "eval_steps_per_second": 1.146,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023843462485421798,
+      "grad_norm": 1.8627070188522339,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2056,
+      "step": 46
+    },
+    {
+      "epoch": 0.002436179862640923,
+      "grad_norm": 1.692333459854126,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.2567,
+      "step": 47
+    },
+    {
+      "epoch": 0.002488013476739666,
+      "grad_norm": 1.8308770656585693,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.3291,
+      "step": 48
+    },
+    {
+      "epoch": 0.002539847090838409,
+      "grad_norm": 1.635390281677246,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.4812,
+      "step": 49
+    },
+    {
+      "epoch": 0.002591680704937152,
+      "grad_norm": 1.5308008193969727,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.2056,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null