Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fb1764774c09f4c1d37be5c498abbf4ade5b4b30519072b0453b66964c9f86
+oid sha256:f7730681e2b4047ab2e932bab443e584d478ba9e88ba17f3fb4637167b785394
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f5e63043d481334ab81e206012a484b9aeba3a5767f0978687a66320186803
+oid sha256:84ab9939bc69e88d91aa210f169813f6cf958fc07767ae321a8943810079a868
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
+oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
 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": 0.001110814893806096,
+  "epoch": 0.002221629787612192,
   "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": 1.2685,
       "step": 25
+    },
+    {
+      "epoch": 0.00115524748955834,
+      "grad_norm": 4.6381072998046875,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.0216,
+      "step": 26
+    },
+    {
+      "epoch": 0.0011996800853105837,
+      "grad_norm": 3.818336248397827,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.2808,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011996800853105837,
+      "eval_loss": 1.0154649019241333,
+      "eval_runtime": 2090.5291,
+      "eval_samples_per_second": 9.066,
+      "eval_steps_per_second": 1.134,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012441126810628278,
+      "grad_norm": 4.990555286407471,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2793,
+      "step": 28
+    },
+    {
+      "epoch": 0.0012885452768150716,
+      "grad_norm": 3.8898091316223145,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.0337,
+      "step": 29
+    },
+    {
+      "epoch": 0.0013329778725673154,
+      "grad_norm": 4.613339424133301,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.2245,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013774104683195593,
+      "grad_norm": 4.101949691772461,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.9874,
+      "step": 31
+    },
+    {
+      "epoch": 0.001421843064071803,
+      "grad_norm": 3.4817678928375244,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.8011,
+      "step": 32
+    },
+    {
+      "epoch": 0.001466275659824047,
+      "grad_norm": 4.340565204620361,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9708,
+      "step": 33
+    },
+    {
+      "epoch": 0.0015107082555762907,
+      "grad_norm": 4.810932159423828,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0238,
+      "step": 34
+    },
+    {
+      "epoch": 0.0015551408513285346,
+      "grad_norm": 3.2785961627960205,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.0832,
+      "step": 35
+    },
+    {
+      "epoch": 0.0015995734470807784,
+      "grad_norm": 3.1490390300750732,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6921,
+      "step": 36
+    },
+    {
+      "epoch": 0.0015995734470807784,
+      "eval_loss": 0.938591718673706,
+      "eval_runtime": 2088.9887,
+      "eval_samples_per_second": 9.073,
+      "eval_steps_per_second": 1.135,
+      "step": 36
+    },
+    {
+      "epoch": 0.0016440060428330222,
+      "grad_norm": 3.129164934158325,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7297,
+      "step": 37
+    },
+    {
+      "epoch": 0.001688438638585266,
+      "grad_norm": 3.497979164123535,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6793,
+      "step": 38
+    },
+    {
+      "epoch": 0.00173287123433751,
+      "grad_norm": 3.4145689010620117,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.9505,
+      "step": 39
+    },
+    {
+      "epoch": 0.001777303830089754,
+      "grad_norm": 4.804287910461426,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9092,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018217364258419977,
+      "grad_norm": 3.785067081451416,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.7816,
+      "step": 41
+    },
+    {
+      "epoch": 0.0018661690215942416,
+      "grad_norm": 3.534381628036499,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.0754,
+      "step": 42
+    },
+    {
+      "epoch": 0.0019106016173464854,
+      "grad_norm": 5.234914302825928,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.9232,
+      "step": 43
+    },
+    {
+      "epoch": 0.0019550342130987292,
+      "grad_norm": 6.870372295379639,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.3589,
+      "step": 44
+    },
+    {
+      "epoch": 0.0019994668088509733,
+      "grad_norm": 2.744567394256592,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.6761,
+      "step": 45
+    },
+    {
+      "epoch": 0.0019994668088509733,
+      "eval_loss": 0.899674654006958,
+      "eval_runtime": 2090.0954,
+      "eval_samples_per_second": 9.068,
+      "eval_steps_per_second": 1.134,
+      "step": 45
+    },
+    {
+      "epoch": 0.002043899404603217,
+      "grad_norm": 3.99665904045105,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9011,
+      "step": 46
+    },
+    {
+      "epoch": 0.002088332000355461,
+      "grad_norm": 3.316638231277466,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.9587,
+      "step": 47
+    },
+    {
+      "epoch": 0.0021327645961077045,
+      "grad_norm": 3.783149480819702,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.0353,
+      "step": 48
+    },
+    {
+      "epoch": 0.0021771971918599486,
+      "grad_norm": 3.442662000656128,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.6331,
+      "step": 49
+    },
+    {
+      "epoch": 0.002221629787612192,
+      "grad_norm": 3.411076545715332,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.1829,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null