Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3aa9733ea59504bf7d1225fcd3af41407b8a427828823f4c1df58f5872bfc1
+oid sha256:d6b8822e8ef13b78beed5989b208438e1a1f33b59ac7dd433ff16bf57cc0d67a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f0ba868fa57d469832f7085872bdcdb7f0b119d97716cfb3a74c9ec59653aa
+oid sha256:5d394331cc8c7eea3ffbfe6d4f1cf19ac151294efb9b345dbccaa20dfa317c02
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf368fb19885ec6c1b991ec870bd32ea0b8b852729c9f654b072c9115ea154e3
+oid sha256:90cdb72911d38e9202f3334751018a6c79ad3b2006b03921a34979cf1abce5c7
 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": 0.12531328320802004,
+  "epoch": 0.2506265664160401,
   "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": 1.5386,
       "step": 25
+    },
+    {
+      "epoch": 0.13032581453634084,
+      "grad_norm": 2.824436664581299,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.4438,
+      "step": 26
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "grad_norm": 3.13669753074646,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.3126,
+      "step": 27
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "eval_loss": 0.7911556959152222,
+      "eval_runtime": 28.3428,
+      "eval_samples_per_second": 5.927,
+      "eval_steps_per_second": 0.741,
+      "step": 27
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 3.12079119682312,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2441,
+      "step": 28
+    },
+    {
+      "epoch": 0.14536340852130325,
+      "grad_norm": 5.930524826049805,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.6673,
+      "step": 29
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 9.300253868103027,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.6697,
+      "step": 30
+    },
+    {
+      "epoch": 0.15538847117794485,
+      "grad_norm": 4.563720226287842,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.6332,
+      "step": 31
+    },
+    {
+      "epoch": 0.16040100250626566,
+      "grad_norm": 2.8544657230377197,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.1952,
+      "step": 32
+    },
+    {
+      "epoch": 0.16541353383458646,
+      "grad_norm": 2.8571174144744873,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.4034,
+      "step": 33
+    },
+    {
+      "epoch": 0.17042606516290726,
+      "grad_norm": 1.2488484382629395,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.3455,
+      "step": 34
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 2.6949751377105713,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.4473,
+      "step": 35
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 2.7027854919433594,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.4684,
+      "step": 36
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "eval_loss": 0.6932310461997986,
+      "eval_runtime": 28.3344,
+      "eval_samples_per_second": 5.929,
+      "eval_steps_per_second": 0.741,
+      "step": 36
+    },
+    {
+      "epoch": 0.18546365914786966,
+      "grad_norm": 2.977766990661621,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.4411,
+      "step": 37
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 4.639328479766846,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.4076,
+      "step": 38
+    },
+    {
+      "epoch": 0.19548872180451127,
+      "grad_norm": 2.0679614543914795,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.3722,
+      "step": 39
+    },
+    {
+      "epoch": 0.20050125313283207,
+      "grad_norm": 3.201908826828003,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.20551378446115287,
+      "grad_norm": 4.107055187225342,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.4506,
+      "step": 41
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.4563536643981934,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.3362,
+      "step": 42
+    },
+    {
+      "epoch": 0.21553884711779447,
+      "grad_norm": 2.039797306060791,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.4047,
+      "step": 43
+    },
+    {
+      "epoch": 0.22055137844611528,
+      "grad_norm": 10.926207542419434,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.7363,
+      "step": 44
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 3.743892192840576,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5538,
+      "step": 45
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "eval_loss": 0.7266060709953308,
+      "eval_runtime": 28.3355,
+      "eval_samples_per_second": 5.929,
+      "eval_steps_per_second": 0.741,
+      "step": 45
+    },
+    {
+      "epoch": 0.23057644110275688,
+      "grad_norm": 3.3518729209899902,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5224,
+      "step": 46
+    },
+    {
+      "epoch": 0.23558897243107768,
+      "grad_norm": 2.9565675258636475,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.4815,
+      "step": 47
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 2.0785973072052,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.382,
+      "step": 48
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 2.082721710205078,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.4032,
+      "step": 49
+    },
+    {
+      "epoch": 0.2506265664160401,
+      "grad_norm": 1.7393074035644531,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.3792,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.940561908563968e+16,
+  "total_flos": 5.946469637318246e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null