Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989b3be0fa9dd04c654fa5566e768b36c127d5d8771555e995520108d84b6eac
+oid sha256:744870531d769cba5ca88d68b136a912d45731231da2da03995f217495b85e27
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23eb43208a84478f10635cebef2ff2d72a4eb1bed515ad8c394c9e62539ae9d
+oid sha256:e1f6fd58d367c0e76dad72e6ab90414ed8934869541d13d3246e9c066db4fe21
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69131f6b6342ada4bf81d1c901fca524b6be5006a429bb6ee830fc7dde3b4a9
+oid sha256:8e7be9add4fd70e35b944858b1783354a7587e3ae43652236bdd5b1fe3daade7
 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": 0.06134969325153374,
+  "epoch": 0.12269938650306748,
   "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": 0.1511,
       "step": 25
+    },
+    {
+      "epoch": 0.0638036809815951,
+      "grad_norm": 0.15573786199092865,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0681,
+      "step": 26
+    },
+    {
+      "epoch": 0.06625766871165645,
+      "grad_norm": 0.26487231254577637,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.1362,
+      "step": 27
+    },
+    {
+      "epoch": 0.06625766871165645,
+      "eval_loss": 0.09782156348228455,
+      "eval_runtime": 72.5753,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 0.592,
+      "step": 27
+    },
+    {
+      "epoch": 0.0687116564417178,
+      "grad_norm": 0.30442625284194946,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.078,
+      "step": 28
+    },
+    {
+      "epoch": 0.07116564417177915,
+      "grad_norm": 0.17983438074588776,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.1232,
+      "step": 29
+    },
+    {
+      "epoch": 0.0736196319018405,
+      "grad_norm": 0.18753987550735474,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.1154,
+      "step": 30
+    },
+    {
+      "epoch": 0.07607361963190185,
+      "grad_norm": 0.14537593722343445,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0899,
+      "step": 31
+    },
+    {
+      "epoch": 0.0785276073619632,
+      "grad_norm": 0.180735781788826,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0981,
+      "step": 32
+    },
+    {
+      "epoch": 0.08098159509202454,
+      "grad_norm": 0.15630754828453064,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.1026,
+      "step": 33
+    },
+    {
+      "epoch": 0.0834355828220859,
+      "grad_norm": 0.2722282111644745,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.1142,
+      "step": 34
+    },
+    {
+      "epoch": 0.08588957055214724,
+      "grad_norm": 0.1411922425031662,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0742,
+      "step": 35
+    },
+    {
+      "epoch": 0.08834355828220859,
+      "grad_norm": 0.17076779901981354,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1097,
+      "step": 36
+    },
+    {
+      "epoch": 0.08834355828220859,
+      "eval_loss": 0.09277616441249847,
+      "eval_runtime": 72.5864,
+      "eval_samples_per_second": 4.725,
+      "eval_steps_per_second": 0.592,
+      "step": 36
+    },
+    {
+      "epoch": 0.09079754601226994,
+      "grad_norm": 0.17781254649162292,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.1031,
+      "step": 37
+    },
+    {
+      "epoch": 0.09325153374233129,
+      "grad_norm": 0.11563621461391449,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0678,
+      "step": 38
+    },
+    {
+      "epoch": 0.09570552147239264,
+      "grad_norm": 0.18766151368618011,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.1294,
+      "step": 39
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "grad_norm": 0.20950351655483246,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1023,
+      "step": 40
+    },
+    {
+      "epoch": 0.10061349693251534,
+      "grad_norm": 0.13120564818382263,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.083,
+      "step": 41
+    },
+    {
+      "epoch": 0.10306748466257669,
+      "grad_norm": 0.16755475103855133,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0912,
+      "step": 42
+    },
+    {
+      "epoch": 0.10552147239263804,
+      "grad_norm": 0.12863048911094666,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.092,
+      "step": 43
+    },
+    {
+      "epoch": 0.10797546012269939,
+      "grad_norm": 0.14830118417739868,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0955,
+      "step": 44
+    },
+    {
+      "epoch": 0.11042944785276074,
+      "grad_norm": 0.2248990535736084,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.093,
+      "step": 45
+    },
+    {
+      "epoch": 0.11042944785276074,
+      "eval_loss": 0.08893309533596039,
+      "eval_runtime": 72.552,
+      "eval_samples_per_second": 4.728,
+      "eval_steps_per_second": 0.593,
+      "step": 45
+    },
+    {
+      "epoch": 0.11288343558282209,
+      "grad_norm": 0.1789003610610962,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0969,
+      "step": 46
+    },
+    {
+      "epoch": 0.11533742331288344,
+      "grad_norm": 0.29910632967948914,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.1165,
+      "step": 47
+    },
+    {
+      "epoch": 0.11779141104294479,
+      "grad_norm": 0.16039490699768066,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0858,
+      "step": 48
+    },
+    {
+      "epoch": 0.12024539877300613,
+      "grad_norm": 0.1589939296245575,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0924,
+      "step": 49
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.17117133736610413,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0931,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.264304047665971e+16,
+  "total_flos": 6.34313627444183e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null