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:daa6543a8a6b6457f5405e642e5fa93cd9ada1593e4c72cb8c1624b6ba1f8cb1
+oid sha256:65754f15f928ca9bf54880dc50c8c40a4b868c145ba0f8376aa8562226a1e6b6
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f752e65b871adaca6aa3bd5c9e98c2feef4fcf931cf9d240aa2603767ae71e
+oid sha256:4d0a6e2a0b50cfcc264e31227029fd26f5f0f0ef92c1f310478cb3fde49bcf5e
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08b5e52b0fa4353f52e15f0ed12a3218a82410f3a186af6d5309b9f733aa130
+oid sha256:11514b197853b462348465f3dc339beef02f4f254b0c41ac5a64915cdbed9ea0
 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": 0.021204410517387615,
+  "epoch": 0.04240882103477523,
   "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": 0.5523,
       "step": 25
+    },
+    {
+      "epoch": 0.02205258693808312,
+      "grad_norm": 2.9645886421203613,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.5708,
+      "step": 26
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "grad_norm": 2.077575922012329,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.4646,
+      "step": 27
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "eval_loss": 0.48650485277175903,
+      "eval_runtime": 28.9407,
+      "eval_samples_per_second": 34.312,
+      "eval_steps_per_second": 4.319,
+      "step": 27
+    },
+    {
+      "epoch": 0.02374893977947413,
+      "grad_norm": 1.3554171323776245,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.4826,
+      "step": 28
+    },
+    {
+      "epoch": 0.024597116200169637,
+      "grad_norm": 1.6642234325408936,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.4937,
+      "step": 29
+    },
+    {
+      "epoch": 0.02544529262086514,
+      "grad_norm": 1.637468934059143,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.5004,
+      "step": 30
+    },
+    {
+      "epoch": 0.026293469041560644,
+      "grad_norm": 2.1573736667633057,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.456,
+      "step": 31
+    },
+    {
+      "epoch": 0.02714164546225615,
+      "grad_norm": 1.3219460248947144,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.428,
+      "step": 32
+    },
+    {
+      "epoch": 0.027989821882951654,
+      "grad_norm": 1.4489333629608154,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.5236,
+      "step": 33
+    },
+    {
+      "epoch": 0.02883799830364716,
+      "grad_norm": 0.9528306126594543,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.4771,
+      "step": 34
+    },
+    {
+      "epoch": 0.029686174724342665,
+      "grad_norm": 0.9525566697120667,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.4884,
+      "step": 35
+    },
+    {
+      "epoch": 0.030534351145038167,
+      "grad_norm": 5.734241962432861,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.5496,
+      "step": 36
+    },
+    {
+      "epoch": 0.030534351145038167,
+      "eval_loss": 0.4875996708869934,
+      "eval_runtime": 28.8306,
+      "eval_samples_per_second": 34.443,
+      "eval_steps_per_second": 4.336,
+      "step": 36
+    },
+    {
+      "epoch": 0.031382527565733676,
+      "grad_norm": 1.5124987363815308,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.5263,
+      "step": 37
+    },
+    {
+      "epoch": 0.032230703986429174,
+      "grad_norm": 1.2907754182815552,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.4894,
+      "step": 38
+    },
+    {
+      "epoch": 0.03307888040712468,
+      "grad_norm": 0.8150112628936768,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.47,
+      "step": 39
+    },
+    {
+      "epoch": 0.033927056827820185,
+      "grad_norm": 1.1699497699737549,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4706,
+      "step": 40
+    },
+    {
+      "epoch": 0.03477523324851569,
+      "grad_norm": 1.4197578430175781,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.4537,
+      "step": 41
+    },
+    {
+      "epoch": 0.035623409669211195,
+      "grad_norm": 0.6217430233955383,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.4533,
+      "step": 42
+    },
+    {
+      "epoch": 0.0364715860899067,
+      "grad_norm": 1.0930975675582886,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.4813,
+      "step": 43
+    },
+    {
+      "epoch": 0.037319762510602206,
+      "grad_norm": 1.2884628772735596,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.5025,
+      "step": 44
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "grad_norm": 2.1661903858184814,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5309,
+      "step": 45
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "eval_loss": 0.48306483030319214,
+      "eval_runtime": 28.8269,
+      "eval_samples_per_second": 34.447,
+      "eval_steps_per_second": 4.336,
+      "step": 45
+    },
+    {
+      "epoch": 0.039016115351993216,
+      "grad_norm": 3.116976022720337,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5825,
+      "step": 46
+    },
+    {
+      "epoch": 0.03986429177268872,
+      "grad_norm": 1.477339744567871,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.4475,
+      "step": 47
+    },
+    {
+      "epoch": 0.04071246819338423,
+      "grad_norm": 1.4223567247390747,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.4632,
+      "step": 48
+    },
+    {
+      "epoch": 0.041560644614079725,
+      "grad_norm": 1.7375524044036865,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.515,
+      "step": 49
+    },
+    {
+      "epoch": 0.04240882103477523,
+      "grad_norm": 2.708205223083496,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.5253,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2573421930086400.0,
+  "total_flos": 5146843860172800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null