Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24aa8fe98f15c1c7f71131fe55d2e56dcae4e611ca7851c2c74bf457de2ba2ec
+oid sha256:d5f259f275f482ac805d5ede01bf2d2eb77320233d4e6dea0deb167f7b6aee4b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d6a2f3f6d5058b6429598ed7ea42e1b050fa2afb952d2e21818a1d82d58be5
+oid sha256:f35beaec7b611d754b03a01dd4ddc46b9a536016a2f2c4964a9591e7d4fde1bc
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
+oid sha256:3a2938b827d7faa6c9d8f750cf3ec2800eb55262cf6e2b002f8dc231a945f215
 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:e065eb1df69232f27b2d6dee4b867fd634a18790e0a17aa825c7410bd9375464
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
+oid sha256:67b640f4f5c64f317409bfc71b559a9a115df0faf4a8c53e2bd4a99f3d4e7cab
 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:f0c49bbf34da6895a83a15832e3ad8bf7a6bde93994ac74a6ed64bcd326286c8
 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": 0.6993006993006993,
+  "epoch": 1.048951048951049,
   "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": 10.3751,
       "step": 50
+    },
+    {
+      "epoch": 0.7132867132867133,
+      "grad_norm": 0.025323813781142235,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3755,
+      "step": 51
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.030344007536768913,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3769,
+      "step": 52
+    },
+    {
+      "epoch": 0.7412587412587412,
+      "grad_norm": 0.026691097766160965,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3738,
+      "step": 53
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "grad_norm": 0.030549872666597366,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3772,
+      "step": 54
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "eval_loss": 10.375645637512207,
+      "eval_runtime": 0.2681,
+      "eval_samples_per_second": 895.207,
+      "eval_steps_per_second": 29.84,
+      "step": 54
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.028555618599057198,
+      "learning_rate": 5e-05,
+      "loss": 10.376,
+      "step": 55
+    },
+    {
+      "epoch": 0.7832167832167832,
+      "grad_norm": 0.029428837820887566,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3741,
+      "step": 56
+    },
+    {
+      "epoch": 0.7972027972027972,
+      "grad_norm": 0.029308155179023743,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3746,
+      "step": 57
+    },
+    {
+      "epoch": 0.8111888111888111,
+      "grad_norm": 0.032606493681669235,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3758,
+      "step": 58
+    },
+    {
+      "epoch": 0.8251748251748252,
+      "grad_norm": 0.02967746928334236,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3742,
+      "step": 59
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.03057865984737873,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3758,
+      "step": 60
+    },
+    {
+      "epoch": 0.8531468531468531,
+      "grad_norm": 0.032224319875240326,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3755,
+      "step": 61
+    },
+    {
+      "epoch": 0.8671328671328671,
+      "grad_norm": 0.040901295840740204,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3744,
+      "step": 62
+    },
+    {
+      "epoch": 0.8811188811188811,
+      "grad_norm": 0.03291678801178932,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3743,
+      "step": 63
+    },
+    {
+      "epoch": 0.8811188811188811,
+      "eval_loss": 10.37505054473877,
+      "eval_runtime": 0.2661,
+      "eval_samples_per_second": 901.766,
+      "eval_steps_per_second": 30.059,
+      "step": 63
+    },
+    {
+      "epoch": 0.8951048951048951,
+      "grad_norm": 0.038531407713890076,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3745,
+      "step": 64
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.03420910984277725,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3745,
+      "step": 65
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.03833569958806038,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.374,
+      "step": 66
+    },
+    {
+      "epoch": 0.9370629370629371,
+      "grad_norm": 0.03805769979953766,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.375,
+      "step": 67
+    },
+    {
+      "epoch": 0.951048951048951,
+      "grad_norm": 0.0376318022608757,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3774,
+      "step": 68
+    },
+    {
+      "epoch": 0.965034965034965,
+      "grad_norm": 0.03903169184923172,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3733,
+      "step": 69
+    },
+    {
+      "epoch": 0.9790209790209791,
+      "grad_norm": 0.03841084614396095,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3736,
+      "step": 70
+    },
+    {
+      "epoch": 0.993006993006993,
+      "grad_norm": 0.02962353080511093,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3753,
+      "step": 71
+    },
+    {
+      "epoch": 1.006993006993007,
+      "grad_norm": 0.04900306835770607,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 15.5217,
+      "step": 72
+    },
+    {
+      "epoch": 1.006993006993007,
+      "eval_loss": 10.374591827392578,
+      "eval_runtime": 0.2844,
+      "eval_samples_per_second": 843.76,
+      "eval_steps_per_second": 28.125,
+      "step": 72
+    },
+    {
+      "epoch": 1.020979020979021,
+      "grad_norm": 0.04284500703215599,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.2186,
+      "step": 73
+    },
+    {
+      "epoch": 1.034965034965035,
+      "grad_norm": 0.041206490248441696,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.4779,
+      "step": 74
+    },
+    {
+      "epoch": 1.048951048951049,
+      "grad_norm": 0.03888395428657532,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.0933,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 15690733977600.0,
+  "total_flos": 23457647296512.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null