Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3fbd42722e33a46e81564039f48066ca90a2cbeb14cb0d4cac6c1da737526d
+oid sha256:83ba0a32fc5c864b61e84423197483a72737f7b84cfdb3f57f4d2b90b24d7c34
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf1db9530de8a99649a5161ce4bd9b31eb5a132e9d7651c2aa5c2e86cc76043
+oid sha256:97970cef5619ce89b5b9a8bfce176e7827f6594bbc7fbd8365a86930e5552bfd
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a15a48c2fed1b3ecbaa40dea96f901573434defc9b6253fb93993c6c3a6af1
+oid sha256:33752213e91e5d9daaf41b0e911b3b2623b16a8672150d6b365a88ada68018bd
 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": 0.04156275976724855,
+  "epoch": 0.0831255195344971,
   "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": 11.7558,
       "step": 25
+    },
+    {
+      "epoch": 0.043225270157938485,
+      "grad_norm": 0.06178494170308113,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 11.7574,
+      "step": 26
+    },
+    {
+      "epoch": 0.04488778054862843,
+      "grad_norm": 0.055603306740522385,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 11.7611,
+      "step": 27
+    },
+    {
+      "epoch": 0.04488778054862843,
+      "eval_loss": 11.758519172668457,
+      "eval_runtime": 10.6894,
+      "eval_samples_per_second": 47.43,
+      "eval_steps_per_second": 5.987,
+      "step": 27
+    },
+    {
+      "epoch": 0.046550290939318374,
+      "grad_norm": 0.047771960496902466,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.7565,
+      "step": 28
+    },
+    {
+      "epoch": 0.04821280133000831,
+      "grad_norm": 0.061024993658065796,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 11.7541,
+      "step": 29
+    },
+    {
+      "epoch": 0.04987531172069826,
+      "grad_norm": 0.06483989953994751,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 11.7603,
+      "step": 30
+    },
+    {
+      "epoch": 0.051537822111388194,
+      "grad_norm": 0.05010339245200157,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 11.7539,
+      "step": 31
+    },
+    {
+      "epoch": 0.05320033250207814,
+      "grad_norm": 0.04719735309481621,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 11.7539,
+      "step": 32
+    },
+    {
+      "epoch": 0.05486284289276808,
+      "grad_norm": 0.05507144331932068,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 11.7593,
+      "step": 33
+    },
+    {
+      "epoch": 0.05652535328345802,
+      "grad_norm": 0.0661148950457573,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 11.7532,
+      "step": 34
+    },
+    {
+      "epoch": 0.058187863674147966,
+      "grad_norm": 0.08241010457277298,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 11.756,
+      "step": 35
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "grad_norm": 0.06910108774900436,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 11.7557,
+      "step": 36
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "eval_loss": 11.757696151733398,
+      "eval_runtime": 10.6836,
+      "eval_samples_per_second": 47.456,
+      "eval_steps_per_second": 5.99,
+      "step": 36
+    },
+    {
+      "epoch": 0.06151288445552785,
+      "grad_norm": 0.058035943657159805,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.7563,
+      "step": 37
+    },
+    {
+      "epoch": 0.06317539484621779,
+      "grad_norm": 0.06133880466222763,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 11.757,
+      "step": 38
+    },
+    {
+      "epoch": 0.06483790523690773,
+      "grad_norm": 0.05848357081413269,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 11.752,
+      "step": 39
+    },
+    {
+      "epoch": 0.06650041562759768,
+      "grad_norm": 0.05439987778663635,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 11.7565,
+      "step": 40
+    },
+    {
+      "epoch": 0.06816292601828762,
+      "grad_norm": 0.06417480856180191,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 11.7488,
+      "step": 41
+    },
+    {
+      "epoch": 0.06982543640897755,
+      "grad_norm": 0.061617761850357056,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 11.7599,
+      "step": 42
+    },
+    {
+      "epoch": 0.0714879467996675,
+      "grad_norm": 0.051751330494880676,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 11.7565,
+      "step": 43
+    },
+    {
+      "epoch": 0.07315045719035744,
+      "grad_norm": 0.0564432330429554,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 11.7629,
+      "step": 44
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "grad_norm": 0.05816029757261276,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 11.7613,
+      "step": 45
+    },
+    {
+      "epoch": 0.07481296758104738,
+      "eval_loss": 11.756857872009277,
+      "eval_runtime": 10.9655,
+      "eval_samples_per_second": 46.236,
+      "eval_steps_per_second": 5.836,
+      "step": 45
+    },
+    {
+      "epoch": 0.07647547797173733,
+      "grad_norm": 0.08202195912599564,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.7502,
+      "step": 46
+    },
+    {
+      "epoch": 0.07813798836242726,
+      "grad_norm": 0.06265095621347427,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 11.7583,
+      "step": 47
+    },
+    {
+      "epoch": 0.0798004987531172,
+      "grad_norm": 0.09170009940862656,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 11.7566,
+      "step": 48
+    },
+    {
+      "epoch": 0.08146300914380715,
+      "grad_norm": 0.06977274268865585,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 11.7544,
+      "step": 49
+    },
+    {
+      "epoch": 0.0831255195344971,
+      "grad_norm": 0.060967620462179184,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 11.754,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5092501094400.0,
+  "total_flos": 10185002188800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null