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:c695e3601405e549134d7ea49799417e7ed642916c9c8601b702e3818fdc7e5e
+oid sha256:4aaa60a8f41b5a2979f931747d06d79b58a24c1948f08aa6f0497670b53361d7
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6a24fc92a7e6954091a81e1c64741b28f0ade8dd5f33b440729eb3008a865b
+oid sha256:b6ebf2c60a7ecc1a99a30206290a2d98b4d6009197d72b37b8acd9acf7f7cfcb
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.07716049382716049,
+  "epoch": 0.102880658436214,
   "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": 10.3657,
       "step": 75
+    },
+    {
+      "epoch": 0.07818930041152264,
+      "grad_norm": 0.04726821556687355,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3692,
+      "step": 76
+    },
+    {
+      "epoch": 0.07921810699588477,
+      "grad_norm": 0.04689066484570503,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3695,
+      "step": 77
+    },
+    {
+      "epoch": 0.08024691358024691,
+      "grad_norm": 0.05402266979217529,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.37,
+      "step": 78
+    },
+    {
+      "epoch": 0.08127572016460906,
+      "grad_norm": 0.04493223875761032,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3684,
+      "step": 79
+    },
+    {
+      "epoch": 0.0823045267489712,
+      "grad_norm": 0.058183249086141586,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3659,
+      "step": 80
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.04858890920877457,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3681,
+      "step": 81
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "eval_loss": 10.369402885437012,
+      "eval_runtime": 4.4593,
+      "eval_samples_per_second": 183.661,
+      "eval_steps_per_second": 23.098,
+      "step": 81
+    },
+    {
+      "epoch": 0.08436213991769548,
+      "grad_norm": 0.04888492077589035,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3731,
+      "step": 82
+    },
+    {
+      "epoch": 0.08539094650205761,
+      "grad_norm": 0.04856285825371742,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3696,
+      "step": 83
+    },
+    {
+      "epoch": 0.08641975308641975,
+      "grad_norm": 0.053031668066978455,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.371,
+      "step": 84
+    },
+    {
+      "epoch": 0.0874485596707819,
+      "grad_norm": 0.04873763024806976,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3726,
+      "step": 85
+    },
+    {
+      "epoch": 0.08847736625514403,
+      "grad_norm": 0.06068224832415581,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3666,
+      "step": 86
+    },
+    {
+      "epoch": 0.08950617283950617,
+      "grad_norm": 0.05208251252770424,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3692,
+      "step": 87
+    },
+    {
+      "epoch": 0.09053497942386832,
+      "grad_norm": 0.044392600655555725,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.369,
+      "step": 88
+    },
+    {
+      "epoch": 0.09156378600823045,
+      "grad_norm": 0.05065758153796196,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3688,
+      "step": 89
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 0.04816662147641182,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3699,
+      "step": 90
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "eval_loss": 10.36927318572998,
+      "eval_runtime": 4.7104,
+      "eval_samples_per_second": 173.872,
+      "eval_steps_per_second": 21.867,
+      "step": 90
+    },
+    {
+      "epoch": 0.09362139917695474,
+      "grad_norm": 0.040740616619586945,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3726,
+      "step": 91
+    },
+    {
+      "epoch": 0.09465020576131687,
+      "grad_norm": 0.04884503409266472,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3637,
+      "step": 92
+    },
+    {
+      "epoch": 0.09567901234567901,
+      "grad_norm": 0.045312654227018356,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3682,
+      "step": 93
+    },
+    {
+      "epoch": 0.09670781893004116,
+      "grad_norm": 0.03917687013745308,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3687,
+      "step": 94
+    },
+    {
+      "epoch": 0.09773662551440329,
+      "grad_norm": 0.04869252070784569,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3677,
+      "step": 95
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.03939636051654816,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3654,
+      "step": 96
+    },
+    {
+      "epoch": 0.09979423868312758,
+      "grad_norm": 0.04943367838859558,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.366,
+      "step": 97
+    },
+    {
+      "epoch": 0.10082304526748971,
+      "grad_norm": 0.04062531515955925,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3703,
+      "step": 98
+    },
+    {
+      "epoch": 0.10185185185185185,
+      "grad_norm": 0.04285578057169914,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3704,
+      "step": 99
+    },
+    {
+      "epoch": 0.10185185185185185,
+      "eval_loss": 10.369248390197754,
+      "eval_runtime": 4.5585,
+      "eval_samples_per_second": 179.666,
+      "eval_steps_per_second": 22.595,
+      "step": 99
+    },
+    {
+      "epoch": 0.102880658436214,
+      "grad_norm": 0.04049593210220337,
+      "learning_rate": 0.0,
+      "loss": 10.3727,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null