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:c9c8a205419204f61991b1a0f23b98445f3c4af355e48f1c0d99bd4ea16d5b07
+oid sha256:cc227258e87a1f6ba5f6a6a0ff81ad6aad1648785525827726419eb1cdbba8ea
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9986a31a8f4773996e3706164d2d256de574cc673d442aba9361f615c5f0ad85
+oid sha256:71705c29034cbdc4460a30dd75e38c49bbc40e5cb46ae425d5d7fc9fb2940aec
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be71c9277f6ea813a155d91bacae262bb78b0ddd8958e1530a8e4f0ac1f5bc5d
+oid sha256:c79bf8ebcb249beccd05145daa4ffcfc686ad5a5865005baa6ff3cdad29c138c
 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": 0.0039148136548700285,
+  "epoch": 0.007829627309740057,
   "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": 2.091,
       "step": 25
+    },
+    {
+      "epoch": 0.004071406201064829,
+      "grad_norm": 0.8978224396705627,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.6222,
+      "step": 26
+    },
+    {
+      "epoch": 0.00422799874725963,
+      "grad_norm": 0.910511314868927,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.4146,
+      "step": 27
+    },
+    {
+      "epoch": 0.00422799874725963,
+      "eval_loss": 1.7382819652557373,
+      "eval_runtime": 341.6711,
+      "eval_samples_per_second": 15.74,
+      "eval_steps_per_second": 1.97,
+      "step": 27
+    },
+    {
+      "epoch": 0.004384591293454432,
+      "grad_norm": 1.0003559589385986,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4551,
+      "step": 28
+    },
+    {
+      "epoch": 0.004541183839649233,
+      "grad_norm": 0.9404575824737549,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.5461,
+      "step": 29
+    },
+    {
+      "epoch": 0.004697776385844034,
+      "grad_norm": 0.8040342330932617,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.3199,
+      "step": 30
+    },
+    {
+      "epoch": 0.0048543689320388345,
+      "grad_norm": 0.7769756317138672,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.7402,
+      "step": 31
+    },
+    {
+      "epoch": 0.005010961478233636,
+      "grad_norm": 0.6750996112823486,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.7677,
+      "step": 32
+    },
+    {
+      "epoch": 0.005167554024428437,
+      "grad_norm": 0.8155618906021118,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.2559,
+      "step": 33
+    },
+    {
+      "epoch": 0.005324146570623238,
+      "grad_norm": 0.8737456202507019,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.7302,
+      "step": 34
+    },
+    {
+      "epoch": 0.00548073911681804,
+      "grad_norm": 0.7429255247116089,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.5429,
+      "step": 35
+    },
+    {
+      "epoch": 0.005637331663012841,
+      "grad_norm": 0.787848174571991,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.8001,
+      "step": 36
+    },
+    {
+      "epoch": 0.005637331663012841,
+      "eval_loss": 1.5025882720947266,
+      "eval_runtime": 341.681,
+      "eval_samples_per_second": 15.74,
+      "eval_steps_per_second": 1.97,
+      "step": 36
+    },
+    {
+      "epoch": 0.0057939242092076414,
+      "grad_norm": 0.8274391293525696,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.5021,
+      "step": 37
+    },
+    {
+      "epoch": 0.005950516755402443,
+      "grad_norm": 0.684043824672699,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.6989,
+      "step": 38
+    },
+    {
+      "epoch": 0.006107109301597244,
+      "grad_norm": 0.5877222418785095,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.9083,
+      "step": 39
+    },
+    {
+      "epoch": 0.006263701847792045,
+      "grad_norm": 0.8567363023757935,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.3317,
+      "step": 40
+    },
+    {
+      "epoch": 0.006420294393986847,
+      "grad_norm": 0.789842963218689,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.233,
+      "step": 41
+    },
+    {
+      "epoch": 0.0065768869401816475,
+      "grad_norm": 0.8660836219787598,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.1597,
+      "step": 42
+    },
+    {
+      "epoch": 0.006733479486376448,
+      "grad_norm": 0.7116528153419495,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.2998,
+      "step": 43
+    },
+    {
+      "epoch": 0.006890072032571249,
+      "grad_norm": 0.7719988226890564,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.5096,
+      "step": 44
+    },
+    {
+      "epoch": 0.007046664578766051,
+      "grad_norm": 0.6935805678367615,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.6491,
+      "step": 45
+    },
+    {
+      "epoch": 0.007046664578766051,
+      "eval_loss": 1.310565710067749,
+      "eval_runtime": 341.6735,
+      "eval_samples_per_second": 15.74,
+      "eval_steps_per_second": 1.97,
+      "step": 45
+    },
+    {
+      "epoch": 0.007203257124960852,
+      "grad_norm": 0.6075599789619446,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.4503,
+      "step": 46
+    },
+    {
+      "epoch": 0.007359849671155653,
+      "grad_norm": 0.5467920899391174,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.5001,
+      "step": 47
+    },
+    {
+      "epoch": 0.007516442217350454,
+      "grad_norm": 0.6646414995193481,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.9366,
+      "step": 48
+    },
+    {
+      "epoch": 0.007673034763545255,
+      "grad_norm": 0.6338045597076416,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.3771,
+      "step": 49
+    },
+    {
+      "epoch": 0.007829627309740057,
+      "grad_norm": 0.6069777011871338,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.2211,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null