Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:396942bc6da861f4e92d83a27ffd8bc8c55a5c088339a503c69a5172461270aa
+oid sha256:bc69b9722ccf4c4e2454f0daf0915f11d7ceef6e83d4e2e1bc04df28c8c7cdea
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0afd59f5e062728daa79d148eda51d9bae2aadbcd8c430fe21dce14d591ee44
+oid sha256:13c0b047d19da936b1efeebdb3f8050b5cc1bf93cb745b77d1cfefdf7fd3e24d
 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": 0.0063854242050146864,
+  "epoch": 0.008513898940019582,
   "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": 10.3675,
       "step": 75
+    },
+    {
+      "epoch": 0.006470563194414882,
+      "grad_norm": 0.08556344360113144,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3805,
+      "step": 76
+    },
+    {
+      "epoch": 0.006555702183815078,
+      "grad_norm": 0.10135341435670853,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3807,
+      "step": 77
+    },
+    {
+      "epoch": 0.006640841173215274,
+      "grad_norm": 0.10160138458013535,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3755,
+      "step": 78
+    },
+    {
+      "epoch": 0.00672598016261547,
+      "grad_norm": 0.10789739340543747,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3772,
+      "step": 79
+    },
+    {
+      "epoch": 0.006811119152015666,
+      "grad_norm": 0.09456997364759445,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3725,
+      "step": 80
+    },
+    {
+      "epoch": 0.006896258141415861,
+      "grad_norm": 0.09812531620264053,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.375,
+      "step": 81
+    },
+    {
+      "epoch": 0.006896258141415861,
+      "eval_loss": 10.369479179382324,
+      "eval_runtime": 37.0829,
+      "eval_samples_per_second": 266.726,
+      "eval_steps_per_second": 33.358,
+      "step": 81
+    },
+    {
+      "epoch": 0.006981397130816057,
+      "grad_norm": 0.0770481675863266,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3743,
+      "step": 82
+    },
+    {
+      "epoch": 0.007066536120216253,
+      "grad_norm": 0.1046832948923111,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3652,
+      "step": 83
+    },
+    {
+      "epoch": 0.007151675109616448,
+      "grad_norm": 0.09526332467794418,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3581,
+      "step": 84
+    },
+    {
+      "epoch": 0.007236814099016645,
+      "grad_norm": 0.1255982220172882,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3702,
+      "step": 85
+    },
+    {
+      "epoch": 0.007321953088416841,
+      "grad_norm": 0.07898397743701935,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3798,
+      "step": 86
+    },
+    {
+      "epoch": 0.007407092077817036,
+      "grad_norm": 0.09931027144193649,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3753,
+      "step": 87
+    },
+    {
+      "epoch": 0.007492231067217232,
+      "grad_norm": 0.1049114540219307,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3643,
+      "step": 88
+    },
+    {
+      "epoch": 0.007577370056617428,
+      "grad_norm": 0.10006126761436462,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3656,
+      "step": 89
+    },
+    {
+      "epoch": 0.007662509046017623,
+      "grad_norm": 0.09538846462965012,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3636,
+      "step": 90
+    },
+    {
+      "epoch": 0.007662509046017623,
+      "eval_loss": 10.369254112243652,
+      "eval_runtime": 36.9598,
+      "eval_samples_per_second": 267.615,
+      "eval_steps_per_second": 33.469,
+      "step": 90
+    },
+    {
+      "epoch": 0.00774764803541782,
+      "grad_norm": 0.08441486954689026,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3764,
+      "step": 91
+    },
+    {
+      "epoch": 0.007832787024818015,
+      "grad_norm": 0.11270693689584732,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3591,
+      "step": 92
+    },
+    {
+      "epoch": 0.00791792601421821,
+      "grad_norm": 0.11153753101825714,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.368,
+      "step": 93
+    },
+    {
+      "epoch": 0.008003065003618408,
+      "grad_norm": 0.09465039521455765,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3681,
+      "step": 94
+    },
+    {
+      "epoch": 0.008088203993018604,
+      "grad_norm": 0.09789907187223434,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.362,
+      "step": 95
+    },
+    {
+      "epoch": 0.0081733429824188,
+      "grad_norm": 0.10044945031404495,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3688,
+      "step": 96
+    },
+    {
+      "epoch": 0.008258481971818995,
+      "grad_norm": 0.1057361587882042,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3687,
+      "step": 97
+    },
+    {
+      "epoch": 0.00834362096121919,
+      "grad_norm": 0.10818056762218475,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3696,
+      "step": 98
+    },
+    {
+      "epoch": 0.008428759950619386,
+      "grad_norm": 0.11640747636556625,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3775,
+      "step": 99
+    },
+    {
+      "epoch": 0.008428759950619386,
+      "eval_loss": 10.369211196899414,
+      "eval_runtime": 36.9506,
+      "eval_samples_per_second": 267.682,
+      "eval_steps_per_second": 33.477,
+      "step": 99
+    },
+    {
+      "epoch": 0.008513898940019582,
+      "grad_norm": 0.07348009943962097,
+      "learning_rate": 0.0,
+      "loss": 10.381,
+      "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": 7243888852992.0,
+  "total_flos": 9754406289408.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null