Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57da73fcb926bc41354030a4024c2ef5fa26db0c9174de1527771efe0bb9cd4
+oid sha256:e1c9e6ceb931b4e55f295e71c5724e65ea2f89efabf0c9d83831f42dc5b7dd7f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c490c498edf269e89494e914152dc603d32ec0f3ff191f59926b37947bb6ef
+oid sha256:a2e8b34fb486963446df0b66ca051799552df8ccc3f737406c2ab14aca048405
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:1e431f0168bd1d0fab8fca2ae27b597582b62bae74e8a5d014095cbf1c857c15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.31982942430703626,
+  "epoch": 0.42643923240938164,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.3385,
       "step": 75
+    },
+    {
+      "epoch": 0.32409381663113007,
+      "grad_norm": 1.9991743564605713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4137,
+      "step": 76
+    },
+    {
+      "epoch": 0.3283582089552239,
+      "grad_norm": 1.8879848718643188,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2795,
+      "step": 77
+    },
+    {
+      "epoch": 0.3326226012793177,
+      "grad_norm": 2.1605823040008545,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3742,
+      "step": 78
+    },
+    {
+      "epoch": 0.3368869936034115,
+      "grad_norm": 1.3594540357589722,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3981,
+      "step": 79
+    },
+    {
+      "epoch": 0.3411513859275053,
+      "grad_norm": 2.6950554847717285,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4524,
+      "step": 80
+    },
+    {
+      "epoch": 0.34541577825159914,
+      "grad_norm": 2.7667741775512695,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.4817,
+      "step": 81
+    },
+    {
+      "epoch": 0.34541577825159914,
+      "eval_loss": 0.3979479968547821,
+      "eval_runtime": 21.5996,
+      "eval_samples_per_second": 9.167,
+      "eval_steps_per_second": 1.157,
+      "step": 81
+    },
+    {
+      "epoch": 0.34968017057569295,
+      "grad_norm": 2.7610809803009033,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3045,
+      "step": 82
+    },
+    {
+      "epoch": 0.35394456289978676,
+      "grad_norm": 1.6721285581588745,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3334,
+      "step": 83
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 1.8439525365829468,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5136,
+      "step": 84
+    },
+    {
+      "epoch": 0.3624733475479744,
+      "grad_norm": 2.430210828781128,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5547,
+      "step": 85
+    },
+    {
+      "epoch": 0.36673773987206826,
+      "grad_norm": 2.2612948417663574,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6242,
+      "step": 86
+    },
+    {
+      "epoch": 0.37100213219616207,
+      "grad_norm": 2.322953701019287,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3534,
+      "step": 87
+    },
+    {
+      "epoch": 0.3752665245202559,
+      "grad_norm": 2.0307810306549072,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5046,
+      "step": 88
+    },
+    {
+      "epoch": 0.3795309168443497,
+      "grad_norm": 1.8660930395126343,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.3192,
+      "step": 89
+    },
+    {
+      "epoch": 0.3837953091684435,
+      "grad_norm": 5.239176273345947,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2554,
+      "step": 90
+    },
+    {
+      "epoch": 0.3837953091684435,
+      "eval_loss": 0.39385977387428284,
+      "eval_runtime": 21.5643,
+      "eval_samples_per_second": 9.182,
+      "eval_steps_per_second": 1.159,
+      "step": 90
+    },
+    {
+      "epoch": 0.3880597014925373,
+      "grad_norm": 1.2835588455200195,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2739,
+      "step": 91
+    },
+    {
+      "epoch": 0.39232409381663114,
+      "grad_norm": 1.4618430137634277,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3976,
+      "step": 92
+    },
+    {
+      "epoch": 0.39658848614072495,
+      "grad_norm": 1.5838537216186523,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3197,
+      "step": 93
+    },
+    {
+      "epoch": 0.40085287846481876,
+      "grad_norm": 1.7100536823272705,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3564,
+      "step": 94
+    },
+    {
+      "epoch": 0.4051172707889126,
+      "grad_norm": 1.662548542022705,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3093,
+      "step": 95
+    },
+    {
+      "epoch": 0.4093816631130064,
+      "grad_norm": 1.4733221530914307,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4386,
+      "step": 96
+    },
+    {
+      "epoch": 0.4136460554371002,
+      "grad_norm": 5.1062541007995605,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.6305,
+      "step": 97
+    },
+    {
+      "epoch": 0.417910447761194,
+      "grad_norm": 2.9255800247192383,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3684,
+      "step": 98
+    },
+    {
+      "epoch": 0.42217484008528783,
+      "grad_norm": 2.279921770095825,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4791,
+      "step": 99
+    },
+    {
+      "epoch": 0.42217484008528783,
+      "eval_loss": 0.39348170161247253,
+      "eval_runtime": 21.5528,
+      "eval_samples_per_second": 9.187,
+      "eval_steps_per_second": 1.16,
+      "step": 99
+    },
+    {
+      "epoch": 0.42643923240938164,
+      "grad_norm": 2.6319727897644043,
+      "learning_rate": 0.0,
+      "loss": 0.5731,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.56415462670336e+16,
+  "total_flos": 7.455967199782502e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null