Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a25671b36f77a5478bc847a4d3439e84619ce6f79235223b9521709f9e8b5f8
+oid sha256:ad48eaa977a009bfeaa4a4d759a03a4a6fbd002e4a3d8a91c4ca3ea5db7e61b9
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50619a4c603731329e81f1631b6a6ce09e99c32938310c360d1d8cbdf29fb90
+oid sha256:0145a333d4f2f729910d1819cba6bd9f73308b39a32214bc30f3cb78e3091965
 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": 10.3749,
       "step": 50
+    },
+    {
+      "epoch": 0.7132867132867133,
+      "grad_norm": 0.031059524044394493,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3751,
+      "step": 51
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.037967417389154434,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3764,
+      "step": 52
+    },
+    {
+      "epoch": 0.7412587412587412,
+      "grad_norm": 0.03357519581913948,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3734,
+      "step": 53
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "grad_norm": 0.03755338490009308,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3767,
+      "step": 54
+    },
+    {
+      "epoch": 0.7552447552447552,
+      "eval_loss": 10.375212669372559,
+      "eval_runtime": 0.2375,
+      "eval_samples_per_second": 1010.492,
+      "eval_steps_per_second": 33.683,
+      "step": 54
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.036303672939538956,
+      "learning_rate": 5e-05,
+      "loss": 10.3755,
+      "step": 55
+    },
+    {
+      "epoch": 0.7832167832167832,
+      "grad_norm": 0.035945743322372437,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3737,
+      "step": 56
+    },
+    {
+      "epoch": 0.7972027972027972,
+      "grad_norm": 0.03665671497583389,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3742,
+      "step": 57
+    },
+    {
+      "epoch": 0.8111888111888111,
+      "grad_norm": 0.03903292864561081,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3754,
+      "step": 58
+    },
+    {
+      "epoch": 0.8251748251748252,
+      "grad_norm": 0.037477292120456696,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3737,
+      "step": 59
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.03761836886405945,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3753,
+      "step": 60
+    },
+    {
+      "epoch": 0.8531468531468531,
+      "grad_norm": 0.03947959467768669,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.375,
+      "step": 61
+    },
+    {
+      "epoch": 0.8671328671328671,
+      "grad_norm": 0.04931560531258583,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3738,
+      "step": 62
+    },
+    {
+      "epoch": 0.8811188811188811,
+      "grad_norm": 0.04289368912577629,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3736,
+      "step": 63
+    },
+    {
+      "epoch": 0.8811188811188811,
+      "eval_loss": 10.374542236328125,
+      "eval_runtime": 0.2332,
+      "eval_samples_per_second": 1029.334,
+      "eval_steps_per_second": 34.311,
+      "step": 63
+    },
+    {
+      "epoch": 0.8951048951048951,
+      "grad_norm": 0.04646448791027069,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.374,
+      "step": 64
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.041442107409238815,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3741,
+      "step": 65
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.0464664064347744,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3735,
+      "step": 66
+    },
+    {
+      "epoch": 0.9370629370629371,
+      "grad_norm": 0.045736297965049744,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3745,
+      "step": 67
+    },
+    {
+      "epoch": 0.951048951048951,
+      "grad_norm": 0.04584592953324318,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3769,
+      "step": 68
+    },
+    {
+      "epoch": 0.965034965034965,
+      "grad_norm": 0.04951049014925957,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3726,
+      "step": 69
+    },
+    {
+      "epoch": 0.9790209790209791,
+      "grad_norm": 0.04482301324605942,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3733,
+      "step": 70
+    },
+    {
+      "epoch": 0.993006993006993,
+      "grad_norm": 0.035766538232564926,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3749,
+      "step": 71
+    },
+    {
+      "epoch": 1.006993006993007,
+      "grad_norm": 0.0610295832157135,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 15.5208,
+      "step": 72
+    },
+    {
+      "epoch": 1.006993006993007,
+      "eval_loss": 10.374032020568848,
+      "eval_runtime": 0.2214,
+      "eval_samples_per_second": 1083.829,
+      "eval_steps_per_second": 36.128,
+      "step": 72
+    },
+    {
+      "epoch": 1.020979020979021,
+      "grad_norm": 0.05227012559771538,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.218,
+      "step": 73
+    },
+    {
+      "epoch": 1.034965034965035,
+      "grad_norm": 0.050558362156152725,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.4773,
+      "step": 74
+    },
+    {
+      "epoch": 1.048951048951049,
+      "grad_norm": 0.04764160141348839,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.0928,
+      "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