Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1dfb26fb034be068f2fe0774206ad29255d6f02b4b0269b5e8b33b2c511db2
+oid sha256:ab6d2cb14a7ea5d78b71faaa0a19be0812adaa94b821abe192d58b95084cf08a
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ae55fcb672a6d9aba62a89a684c90e87a0430bdafef2569cb9e6a574bdfb0a
+oid sha256:4c3e36ddf2159f9dd2fea07d5cfa0ffca58884eb5759f71a8f072ff84f9200a1
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5984639385e955b7730db79c8d44ebf50a83c75f8e1d452771b84c9f499fee
+oid sha256:ad98dea313f4af8fedd04d99aa5e8a9384c133f275bc1b349d6eadd3081b8462
 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": 0.5154639175257731,
+  "epoch": 1.0309278350515463,
   "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": 2.7697,
       "step": 25
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.8165346384048462,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.6725,
+      "step": 26
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 0.8682026267051697,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.7597,
+      "step": 27
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "eval_loss": 2.6847293376922607,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 98.602,
+      "eval_steps_per_second": 14.43,
+      "step": 27
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 0.9257245659828186,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.6435,
+      "step": 28
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 0.8357184529304504,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.649,
+      "step": 29
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 0.8404372334480286,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.607,
+      "step": 30
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 0.7873509526252747,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.6266,
+      "step": 31
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 0.8580664992332458,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.6335,
+      "step": 32
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 0.7918985486030579,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.5781,
+      "step": 33
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 0.9945449829101562,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.6204,
+      "step": 34
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 0.972023069858551,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.4871,
+      "step": 35
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 0.882148265838623,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.5851,
+      "step": 36
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "eval_loss": 2.549657106399536,
+      "eval_runtime": 0.412,
+      "eval_samples_per_second": 99.523,
+      "eval_steps_per_second": 14.564,
+      "step": 36
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 1.065983533859253,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.5385,
+      "step": 37
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 0.8932860493659973,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.587,
+      "step": 38
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 0.7516025304794312,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.4763,
+      "step": 39
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.1583222150802612,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4846,
+      "step": 40
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 0.797197699546814,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.5684,
+      "step": 41
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 0.8551321625709534,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.4838,
+      "step": 42
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 0.8284348845481873,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.5329,
+      "step": 43
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 0.9195374250411987,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.4583,
+      "step": 44
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 0.8680117130279541,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.4121,
+      "step": 45
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "eval_loss": 2.4568657875061035,
+      "eval_runtime": 0.4143,
+      "eval_samples_per_second": 98.972,
+      "eval_steps_per_second": 14.484,
+      "step": 45
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.8823745250701904,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.4938,
+      "step": 46
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 0.8819367289543152,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.5178,
+      "step": 47
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 0.8066341280937195,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.4225,
+      "step": 48
+    },
+    {
+      "epoch": 1.0103092783505154,
+      "grad_norm": 1.8289326429367065,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 3.7317,
+      "step": 49
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 0.7989461421966553,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.1872,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 347093965209600.0,
+  "total_flos": 689849255854080.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null