Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113f706992506cea8c8e085086b48f49b7d342c64975086f3f07e6a7b37dac48
+oid sha256:923e092b04b7993c38e5965ba3a9daa9a9106f64cf13ef8f5624c961d41f2819
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d5645ae36a260b67156dffdc78186e268372589eef63e2892a62eb1f7a75b8
+oid sha256:b6d53e2215151a779b3510d02929cc59f83098dd407fe0df8076ecc025d7aa6a
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
+oid sha256:e0c7f44ec6860003f13de57bd2ad679abc76372e696f0ba64dcb096ad8c2d194
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
+oid sha256:bd6efc3cf2283ba2318df09b4fccd81fc2c7c92f336f9b8fbed31252acffe51a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
+oid sha256:8ec5a5fa365a025d7b72e73ba5ae61435c717d5192c0a548efd67efffa7d01f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
+oid sha256:4ef8374d5b4a7b565c654f01afc3676c24946d4955ee4d27506c6d5576f109d2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4065040650406504,
+  "epoch": 0.6097560975609756,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 10.3728,
       "step": 50
+    },
+    {
+      "epoch": 0.4146341463414634,
+      "grad_norm": 0.1587628722190857,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3699,
+      "step": 51
+    },
+    {
+      "epoch": 0.42276422764227645,
+      "grad_norm": 0.14911603927612305,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3695,
+      "step": 52
+    },
+    {
+      "epoch": 0.43089430894308944,
+      "grad_norm": 0.1736917495727539,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3702,
+      "step": 53
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.1670113503932953,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3715,
+      "step": 54
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "eval_loss": 10.371479988098145,
+      "eval_runtime": 0.4801,
+      "eval_samples_per_second": 864.389,
+      "eval_steps_per_second": 27.077,
+      "step": 54
+    },
+    {
+      "epoch": 0.44715447154471544,
+      "grad_norm": 0.14659471809864044,
+      "learning_rate": 5e-05,
+      "loss": 10.3694,
+      "step": 55
+    },
+    {
+      "epoch": 0.45528455284552843,
+      "grad_norm": 0.1813124120235443,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3698,
+      "step": 56
+    },
+    {
+      "epoch": 0.4634146341463415,
+      "grad_norm": 0.15320055186748505,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.371,
+      "step": 57
+    },
+    {
+      "epoch": 0.4715447154471545,
+      "grad_norm": 0.16380159556865692,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3684,
+      "step": 58
+    },
+    {
+      "epoch": 0.4796747967479675,
+      "grad_norm": 0.14014634490013123,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3664,
+      "step": 59
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.16128551959991455,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3691,
+      "step": 60
+    },
+    {
+      "epoch": 0.4959349593495935,
+      "grad_norm": 0.179128959774971,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3663,
+      "step": 61
+    },
+    {
+      "epoch": 0.5040650406504065,
+      "grad_norm": 0.1816730499267578,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3667,
+      "step": 62
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "grad_norm": 0.183024063706398,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3674,
+      "step": 63
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "eval_loss": 10.36843204498291,
+      "eval_runtime": 0.4818,
+      "eval_samples_per_second": 861.292,
+      "eval_steps_per_second": 26.98,
+      "step": 63
+    },
+    {
+      "epoch": 0.5203252032520326,
+      "grad_norm": 0.16616392135620117,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3696,
+      "step": 64
+    },
+    {
+      "epoch": 0.5284552845528455,
+      "grad_norm": 0.18292267620563507,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3652,
+      "step": 65
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.1613316386938095,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3676,
+      "step": 66
+    },
+    {
+      "epoch": 0.5447154471544715,
+      "grad_norm": 0.17998585104942322,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3678,
+      "step": 67
+    },
+    {
+      "epoch": 0.5528455284552846,
+      "grad_norm": 0.1902780830860138,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.365,
+      "step": 68
+    },
+    {
+      "epoch": 0.5609756097560976,
+      "grad_norm": 0.1761104017496109,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.368,
+      "step": 69
+    },
+    {
+      "epoch": 0.5691056910569106,
+      "grad_norm": 0.17624002695083618,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3665,
+      "step": 70
+    },
+    {
+      "epoch": 0.5772357723577236,
+      "grad_norm": 0.18516290187835693,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3661,
+      "step": 71
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.18870964646339417,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3665,
+      "step": 72
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "eval_loss": 10.366302490234375,
+      "eval_runtime": 0.4628,
+      "eval_samples_per_second": 896.775,
+      "eval_steps_per_second": 28.092,
+      "step": 72
+    },
+    {
+      "epoch": 0.5934959349593496,
+      "grad_norm": 0.2053869515657425,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3662,
+      "step": 73
+    },
+    {
+      "epoch": 0.6016260162601627,
+      "grad_norm": 0.18971996009349823,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3648,
+      "step": 74
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 0.17851522564888,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3638,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20790222520320.0,
+  "total_flos": 31119955722240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null