Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ba9fb94daf8aa5beafd7f427085b91723093ea524e55246a2b86e392c2dc44
+oid sha256:05f5749d350049ec9b5a63a1a8775eb8ce8bff49a225f809f56ebe1bbc66ed7e
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a463259fbe4991d2d30c28b1240a8f0cfa1bdeefe7bd8f2dd7c893283fd8718d
+oid sha256:585161e71fe20c2f2c44d16e0523cd55fc7a79468697cd65434b8f863b671533
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0715d178292561e517983403ac638349e71a6ce55d82d47c6ac169dc25cd07ab
+oid sha256:870ade4a4e3d55877d26589aaae85a5d2c1b1111fc0b69288c21885a3e103062
 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": 0.0016469038208168643,
+  "epoch": 0.0032938076416337285,
   "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": 6.8355,
       "step": 25
+    },
+    {
+      "epoch": 0.0017127799736495388,
+      "grad_norm": 6.512882709503174,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 5.8496,
+      "step": 26
+    },
+    {
+      "epoch": 0.0017786561264822134,
+      "grad_norm": 6.7052001953125,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 5.7517,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017786561264822134,
+      "eval_loss": 5.528936862945557,
+      "eval_runtime": 184.5038,
+      "eval_samples_per_second": 69.289,
+      "eval_steps_per_second": 8.661,
+      "step": 27
+    },
+    {
+      "epoch": 0.001844532279314888,
+      "grad_norm": 6.696857929229736,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 5.744,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019104084321475627,
+      "grad_norm": 6.88131046295166,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 5.3715,
+      "step": 29
+    },
+    {
+      "epoch": 0.001976284584980237,
+      "grad_norm": 7.05979061126709,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 4.748,
+      "step": 30
+    },
+    {
+      "epoch": 0.002042160737812912,
+      "grad_norm": 7.165943145751953,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 4.3262,
+      "step": 31
+    },
+    {
+      "epoch": 0.002108036890645586,
+      "grad_norm": 6.821268081665039,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 4.4215,
+      "step": 32
+    },
+    {
+      "epoch": 0.002173913043478261,
+      "grad_norm": 5.98926305770874,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.6921,
+      "step": 33
+    },
+    {
+      "epoch": 0.0022397891963109352,
+      "grad_norm": 5.945371150970459,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 3.7048,
+      "step": 34
+    },
+    {
+      "epoch": 0.00230566534914361,
+      "grad_norm": 4.138054847717285,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 3.308,
+      "step": 35
+    },
+    {
+      "epoch": 0.0023715415019762848,
+      "grad_norm": 4.569094181060791,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.4081,
+      "step": 36
+    },
+    {
+      "epoch": 0.0023715415019762848,
+      "eval_loss": 3.0261588096618652,
+      "eval_runtime": 184.3164,
+      "eval_samples_per_second": 69.359,
+      "eval_steps_per_second": 8.67,
+      "step": 36
+    },
+    {
+      "epoch": 0.002437417654808959,
+      "grad_norm": 3.269929885864258,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.8406,
+      "step": 37
+    },
+    {
+      "epoch": 0.002503293807641634,
+      "grad_norm": 3.704793930053711,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.7271,
+      "step": 38
+    },
+    {
+      "epoch": 0.002569169960474308,
+      "grad_norm": 5.287662029266357,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.0801,
+      "step": 39
+    },
+    {
+      "epoch": 0.002635046113306983,
+      "grad_norm": 3.6738574504852295,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5241,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027009222661396573,
+      "grad_norm": 3.433509111404419,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.4624,
+      "step": 41
+    },
+    {
+      "epoch": 0.002766798418972332,
+      "grad_norm": 3.7118277549743652,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.7331,
+      "step": 42
+    },
+    {
+      "epoch": 0.0028326745718050064,
+      "grad_norm": 4.565731525421143,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.8115,
+      "step": 43
+    },
+    {
+      "epoch": 0.002898550724637681,
+      "grad_norm": 2.9661378860473633,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.0928,
+      "step": 44
+    },
+    {
+      "epoch": 0.0029644268774703555,
+      "grad_norm": 3.1142585277557373,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.0762,
+      "step": 45
+    },
+    {
+      "epoch": 0.0029644268774703555,
+      "eval_loss": 2.1579360961914062,
+      "eval_runtime": 184.323,
+      "eval_samples_per_second": 69.356,
+      "eval_steps_per_second": 8.67,
+      "step": 45
+    },
+    {
+      "epoch": 0.0030303030303030303,
+      "grad_norm": 5.064971446990967,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2238,
+      "step": 46
+    },
+    {
+      "epoch": 0.003096179183135705,
+      "grad_norm": 4.904120922088623,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.1618,
+      "step": 47
+    },
+    {
+      "epoch": 0.0031620553359683794,
+      "grad_norm": 3.264500141143799,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.8662,
+      "step": 48
+    },
+    {
+      "epoch": 0.003227931488801054,
+      "grad_norm": 3.768419027328491,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.7912,
+      "step": 49
+    },
+    {
+      "epoch": 0.0032938076416337285,
+      "grad_norm": 3.241663694381714,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.68,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 527582827118592.0,
+  "total_flos": 1055165654237184.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null