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:e3b44435a4703934940c4e3dc3097a041d00878c49c54e413466188efc0df6b4
+oid sha256:cfef193180ecb30f2b563605011b33ace49d374e3299a717116f51b9654e999f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1bf0e52fbd169ce8f1e933af3f6763308d733e6c598c25c63200594e6f41410
+oid sha256:5555067b5330722f06ce2fa89fed6c291202f17e375d7e19be0ce7ee3e0aecaf
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
+oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
 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": 0.033277870216306155,
+  "epoch": 0.04991680532445923,
   "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": 0.5401,
       "step": 50
+    },
+    {
+      "epoch": 0.03394342762063228,
+      "grad_norm": 6.905318737030029,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2936,
+      "step": 51
+    },
+    {
+      "epoch": 0.034608985024958405,
+      "grad_norm": 3.5402543544769287,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2763,
+      "step": 52
+    },
+    {
+      "epoch": 0.035274542429284524,
+      "grad_norm": 5.859736442565918,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.6242,
+      "step": 53
+    },
+    {
+      "epoch": 0.03594009983361065,
+      "grad_norm": 5.486581325531006,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.5799,
+      "step": 54
+    },
+    {
+      "epoch": 0.03594009983361065,
+      "eval_loss": 0.36419036984443665,
+      "eval_runtime": 128.9077,
+      "eval_samples_per_second": 9.813,
+      "eval_steps_per_second": 1.233,
+      "step": 54
+    },
+    {
+      "epoch": 0.036605657237936774,
+      "grad_norm": 4.571095943450928,
+      "learning_rate": 5e-05,
+      "loss": 0.4744,
+      "step": 55
+    },
+    {
+      "epoch": 0.03727121464226289,
+      "grad_norm": 3.6389660835266113,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3371,
+      "step": 56
+    },
+    {
+      "epoch": 0.03793677204658902,
+      "grad_norm": 3.095595598220825,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.279,
+      "step": 57
+    },
+    {
+      "epoch": 0.03860232945091514,
+      "grad_norm": 2.50360107421875,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.2331,
+      "step": 58
+    },
+    {
+      "epoch": 0.03926788685524126,
+      "grad_norm": 3.3427207469940186,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.3408,
+      "step": 59
+    },
+    {
+      "epoch": 0.03993344425956739,
+      "grad_norm": 2.150428056716919,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1876,
+      "step": 60
+    },
+    {
+      "epoch": 0.04059900166389351,
+      "grad_norm": 3.427457809448242,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.2515,
+      "step": 61
+    },
+    {
+      "epoch": 0.04126455906821963,
+      "grad_norm": 6.998630523681641,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.518,
+      "step": 62
+    },
+    {
+      "epoch": 0.041930116472545756,
+      "grad_norm": 4.818533420562744,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1538,
+      "step": 63
+    },
+    {
+      "epoch": 0.041930116472545756,
+      "eval_loss": 0.28987985849380493,
+      "eval_runtime": 128.9461,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 1.233,
+      "step": 63
+    },
+    {
+      "epoch": 0.04259567387687188,
+      "grad_norm": 4.08487606048584,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2289,
+      "step": 64
+    },
+    {
+      "epoch": 0.04326123128119801,
+      "grad_norm": 2.054035186767578,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1527,
+      "step": 65
+    },
+    {
+      "epoch": 0.043926788685524125,
+      "grad_norm": 2.675480604171753,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.1623,
+      "step": 66
+    },
+    {
+      "epoch": 0.04459234608985025,
+      "grad_norm": 7.059667110443115,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.3663,
+      "step": 67
+    },
+    {
+      "epoch": 0.045257903494176376,
+      "grad_norm": 5.064462184906006,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.3349,
+      "step": 68
+    },
+    {
+      "epoch": 0.045923460898502494,
+      "grad_norm": 4.9036359786987305,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.6395,
+      "step": 69
+    },
+    {
+      "epoch": 0.04658901830282862,
+      "grad_norm": 4.005232810974121,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1899,
+      "step": 70
+    },
+    {
+      "epoch": 0.047254575707154745,
+      "grad_norm": 7.462133407592773,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.5265,
+      "step": 71
+    },
+    {
+      "epoch": 0.04792013311148086,
+      "grad_norm": 3.7536137104034424,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.2666,
+      "step": 72
+    },
+    {
+      "epoch": 0.04792013311148086,
+      "eval_loss": 0.23793905973434448,
+      "eval_runtime": 128.9359,
+      "eval_samples_per_second": 9.811,
+      "eval_steps_per_second": 1.233,
+      "step": 72
+    },
+    {
+      "epoch": 0.04858569051580699,
+      "grad_norm": 4.212645053863525,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.2125,
+      "step": 73
+    },
+    {
+      "epoch": 0.049251247920133114,
+      "grad_norm": 3.5476250648498535,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.3124,
+      "step": 74
+    },
+    {
+      "epoch": 0.04991680532445923,
+      "grad_norm": 4.556929588317871,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.274,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3054705844224e+16,
+  "total_flos": 4.9582058766336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null