Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3769b1b520e548fcc2e49e3526ba53c969f995ed31d16a17f83c9bcde08426b0
+oid sha256:ce6b48b659d6f7a0560c6a5579bb6e83eeff25eec40cff02a9558278f859c1a3
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa17e2bd5a2d2407570244f5a7dff423f5d4bf277ba2cfe5f11d7070d6f605ac
+oid sha256:93b48fffcb0aab870add57635818554129d2e5e6796da983ba9faef8a8bc5a54
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
+oid sha256:7390d69c035960909a3614dd1bb0738527d72c78eaafed1ea04f6c83d7885b4d
 size 14244

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": 0.0683526999316473,
+  "epoch": 0.10252904989747096,
   "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": 10.3755,
       "step": 50
+    },
+    {
+      "epoch": 0.06971975393028025,
+      "grad_norm": 0.049810998141765594,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3735,
+      "step": 51
+    },
+    {
+      "epoch": 0.0710868079289132,
+      "grad_norm": 0.043195340782403946,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.375,
+      "step": 52
+    },
+    {
+      "epoch": 0.07245386192754613,
+      "grad_norm": 0.047868385910987854,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3728,
+      "step": 53
+    },
+    {
+      "epoch": 0.07382091592617908,
+      "grad_norm": 0.03871385008096695,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3749,
+      "step": 54
+    },
+    {
+      "epoch": 0.07382091592617908,
+      "eval_loss": 10.37525463104248,
+      "eval_runtime": 7.4518,
+      "eval_samples_per_second": 82.665,
+      "eval_steps_per_second": 10.333,
+      "step": 54
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "grad_norm": 0.046165093779563904,
+      "learning_rate": 5e-05,
+      "loss": 10.3771,
+      "step": 55
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 0.04805214703083038,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3757,
+      "step": 56
+    },
+    {
+      "epoch": 0.07792207792207792,
+      "grad_norm": 0.04241994395852089,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3731,
+      "step": 57
+    },
+    {
+      "epoch": 0.07928913192071087,
+      "grad_norm": 0.05413554608821869,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3751,
+      "step": 58
+    },
+    {
+      "epoch": 0.08065618591934381,
+      "grad_norm": 0.05318213999271393,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3759,
+      "step": 59
+    },
+    {
+      "epoch": 0.08202323991797676,
+      "grad_norm": 0.04020492359995842,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3745,
+      "step": 60
+    },
+    {
+      "epoch": 0.08339029391660971,
+      "grad_norm": 0.05230384320020676,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3756,
+      "step": 61
+    },
+    {
+      "epoch": 0.08475734791524266,
+      "grad_norm": 0.05986716225743294,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3746,
+      "step": 62
+    },
+    {
+      "epoch": 0.0861244019138756,
+      "grad_norm": 0.05598291754722595,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3747,
+      "step": 63
+    },
+    {
+      "epoch": 0.0861244019138756,
+      "eval_loss": 10.374478340148926,
+      "eval_runtime": 7.5341,
+      "eval_samples_per_second": 81.762,
+      "eval_steps_per_second": 10.22,
+      "step": 63
+    },
+    {
+      "epoch": 0.08749145591250855,
+      "grad_norm": 0.048764973878860474,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.374,
+      "step": 64
+    },
+    {
+      "epoch": 0.08885850991114148,
+      "grad_norm": 0.05037747696042061,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.375,
+      "step": 65
+    },
+    {
+      "epoch": 0.09022556390977443,
+      "grad_norm": 0.05323159694671631,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3725,
+      "step": 66
+    },
+    {
+      "epoch": 0.09159261790840738,
+      "grad_norm": 0.05076790973544121,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3727,
+      "step": 67
+    },
+    {
+      "epoch": 0.09295967190704033,
+      "grad_norm": 0.05909010395407677,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.373,
+      "step": 68
+    },
+    {
+      "epoch": 0.09432672590567327,
+      "grad_norm": 0.05870535224676132,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.373,
+      "step": 69
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 0.05204598605632782,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3745,
+      "step": 70
+    },
+    {
+      "epoch": 0.09706083390293917,
+      "grad_norm": 0.05706306919455528,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3738,
+      "step": 71
+    },
+    {
+      "epoch": 0.09842788790157211,
+      "grad_norm": 0.052603580057621,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3744,
+      "step": 72
+    },
+    {
+      "epoch": 0.09842788790157211,
+      "eval_loss": 10.373908996582031,
+      "eval_runtime": 7.5206,
+      "eval_samples_per_second": 81.909,
+      "eval_steps_per_second": 10.239,
+      "step": 72
+    },
+    {
+      "epoch": 0.09979494190020506,
+      "grad_norm": 0.05649203807115555,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3732,
+      "step": 73
+    },
+    {
+      "epoch": 0.10116199589883801,
+      "grad_norm": 0.052477333694696426,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.373,
+      "step": 74
+    },
+    {
+      "epoch": 0.10252904989747096,
+      "grad_norm": 0.053809039294719696,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3712,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5230244659200.0,
+  "total_flos": 7845366988800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null