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:a650b7a2c0b774bcc5980af4c8f3130fb8739b857e0f5f3675c9fa1d10c1e8c4
+oid sha256:34813e6bee68f28c6037d5679ef79569ebae928586c561edd791302cc2bf819e
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad9305b5c8ea83cc0e293e60cae3bebec65b9f4122a92e4b528d66baf686f49
+oid sha256:2d597e3efc7b3356079cbcbc038cbcce2f8e3842887f6d3024b95d60850db623
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e775d2e9c67f160055b78e26ced57388d2fc86a0e27f98d9db502631372b98f
+oid sha256:1e098fe567595b3c01ae7f735ecc9b47b6b00984b64d5938ed8f9a8c97d760b2
 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": 0.009579767530974581,
+  "epoch": 0.012773023374632776,
   "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": 0.2381,
       "step": 75
+    },
+    {
+      "epoch": 0.009707497764720909,
+      "grad_norm": 0.2354595959186554,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.243,
+      "step": 76
+    },
+    {
+      "epoch": 0.009835227998467238,
+      "grad_norm": 0.23027749359607697,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2329,
+      "step": 77
+    },
+    {
+      "epoch": 0.009962958232213565,
+      "grad_norm": 0.2699197232723236,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4067,
+      "step": 78
+    },
+    {
+      "epoch": 0.010090688465959893,
+      "grad_norm": 0.21186845004558563,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2092,
+      "step": 79
+    },
+    {
+      "epoch": 0.01021841869970622,
+      "grad_norm": 0.2345714122056961,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2354,
+      "step": 80
+    },
+    {
+      "epoch": 0.010346148933452547,
+      "grad_norm": 0.23713068664073944,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2358,
+      "step": 81
+    },
+    {
+      "epoch": 0.010346148933452547,
+      "eval_loss": 0.2366475909948349,
+      "eval_runtime": 696.6434,
+      "eval_samples_per_second": 9.464,
+      "eval_steps_per_second": 1.184,
+      "step": 81
+    },
+    {
+      "epoch": 0.010473879167198876,
+      "grad_norm": 0.240807443857193,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2159,
+      "step": 82
+    },
+    {
+      "epoch": 0.010601609400945204,
+      "grad_norm": 0.2546962797641754,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2251,
+      "step": 83
+    },
+    {
+      "epoch": 0.010729339634691531,
+      "grad_norm": 0.22596092522144318,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1835,
+      "step": 84
+    },
+    {
+      "epoch": 0.010857069868437859,
+      "grad_norm": 0.2240147888660431,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2367,
+      "step": 85
+    },
+    {
+      "epoch": 0.010984800102184188,
+      "grad_norm": 0.21561257541179657,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2065,
+      "step": 86
+    },
+    {
+      "epoch": 0.011112530335930515,
+      "grad_norm": 0.2575628459453583,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2126,
+      "step": 87
+    },
+    {
+      "epoch": 0.011240260569676842,
+      "grad_norm": 0.22616754472255707,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2175,
+      "step": 88
+    },
+    {
+      "epoch": 0.01136799080342317,
+      "grad_norm": 0.2656971514225006,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.261,
+      "step": 89
+    },
+    {
+      "epoch": 0.011495721037169499,
+      "grad_norm": 0.22394046187400818,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.223,
+      "step": 90
+    },
+    {
+      "epoch": 0.011495721037169499,
+      "eval_loss": 0.23559892177581787,
+      "eval_runtime": 696.0505,
+      "eval_samples_per_second": 9.472,
+      "eval_steps_per_second": 1.185,
+      "step": 90
+    },
+    {
+      "epoch": 0.011623451270915826,
+      "grad_norm": 0.2391272783279419,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2882,
+      "step": 91
+    },
+    {
+      "epoch": 0.011751181504662154,
+      "grad_norm": 0.2529905140399933,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2448,
+      "step": 92
+    },
+    {
+      "epoch": 0.011878911738408481,
+      "grad_norm": 0.22004134953022003,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.215,
+      "step": 93
+    },
+    {
+      "epoch": 0.012006641972154808,
+      "grad_norm": 0.22307589650154114,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2087,
+      "step": 94
+    },
+    {
+      "epoch": 0.012134372205901137,
+      "grad_norm": 0.2611097991466522,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.254,
+      "step": 95
+    },
+    {
+      "epoch": 0.012262102439647465,
+      "grad_norm": 0.22441336512565613,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2229,
+      "step": 96
+    },
+    {
+      "epoch": 0.012389832673393792,
+      "grad_norm": 0.23511357605457306,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.186,
+      "step": 97
+    },
+    {
+      "epoch": 0.01251756290714012,
+      "grad_norm": 0.2311200350522995,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1808,
+      "step": 98
+    },
+    {
+      "epoch": 0.012645293140886448,
+      "grad_norm": 0.2409658282995224,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2209,
+      "step": 99
+    },
+    {
+      "epoch": 0.012645293140886448,
+      "eval_loss": 0.2354019284248352,
+      "eval_runtime": 696.1494,
+      "eval_samples_per_second": 9.471,
+      "eval_steps_per_second": 1.185,
+      "step": 99
+    },
+    {
+      "epoch": 0.012773023374632776,
+      "grad_norm": 0.24480025470256805,
+      "learning_rate": 0.0,
+      "loss": 0.2418,
+      "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": 2.518909386227712e+16,
+  "total_flos": 3.342082388262912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null