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:e39c0deda4d7900db2e2c45645b551e017366c3e45b9ad62dde227de59131164
+oid sha256:bc397999a87eef61c9dd345daf7b60f8137b677c0670598deea5bbae5b13cee4
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156cf2f400275f373f894791612456ae73decd6e116cd49f9af17f92a20a60a8
+oid sha256:89736d39e9d0b0b09e23c9200fc29b52c2005653a2011956648adecb67c72d28
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbff9e443dec67e04f43734b7efee6a4af31572f74dcdacefd50f76ca714b84
+oid sha256:81ba04fca225e9cbe01736e1aa1547ca5dd2df5ba1bfea9e32d46bf48c9d6912
 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": 0.3105590062111801,
+  "epoch": 0.4140786749482402,
   "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": 1.8442,
       "step": 75
+    },
+    {
+      "epoch": 0.3146997929606625,
+      "grad_norm": 1.361826777458191,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8078,
+      "step": 76
+    },
+    {
+      "epoch": 0.3188405797101449,
+      "grad_norm": 1.30433189868927,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6288,
+      "step": 77
+    },
+    {
+      "epoch": 0.32298136645962733,
+      "grad_norm": 1.61412513256073,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8112,
+      "step": 78
+    },
+    {
+      "epoch": 0.32712215320910976,
+      "grad_norm": 1.463856816291809,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.0371,
+      "step": 79
+    },
+    {
+      "epoch": 0.33126293995859213,
+      "grad_norm": 1.370507836341858,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7918,
+      "step": 80
+    },
+    {
+      "epoch": 0.33540372670807456,
+      "grad_norm": 1.5622191429138184,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1189,
+      "step": 81
+    },
+    {
+      "epoch": 0.33540372670807456,
+      "eval_loss": 0.8779899477958679,
+      "eval_runtime": 86.6409,
+      "eval_samples_per_second": 2.355,
+      "eval_steps_per_second": 0.3,
+      "step": 81
+    },
+    {
+      "epoch": 0.33954451345755693,
+      "grad_norm": 1.1751959323883057,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7123,
+      "step": 82
+    },
+    {
+      "epoch": 0.34368530020703936,
+      "grad_norm": 1.3203461170196533,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.9642,
+      "step": 83
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 1.4285207986831665,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0058,
+      "step": 84
+    },
+    {
+      "epoch": 0.35196687370600416,
+      "grad_norm": 1.5354092121124268,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2293,
+      "step": 85
+    },
+    {
+      "epoch": 0.35610766045548653,
+      "grad_norm": 1.2501472234725952,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.6873,
+      "step": 86
+    },
+    {
+      "epoch": 0.36024844720496896,
+      "grad_norm": 1.2382432222366333,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.6576,
+      "step": 87
+    },
+    {
+      "epoch": 0.36438923395445133,
+      "grad_norm": 1.519044041633606,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9783,
+      "step": 88
+    },
+    {
+      "epoch": 0.36853002070393376,
+      "grad_norm": 1.3468337059020996,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.7055,
+      "step": 89
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "grad_norm": 1.450764775276184,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.2036,
+      "step": 90
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "eval_loss": 0.8755683302879333,
+      "eval_runtime": 86.6141,
+      "eval_samples_per_second": 2.355,
+      "eval_steps_per_second": 0.3,
+      "step": 90
+    },
+    {
+      "epoch": 0.37681159420289856,
+      "grad_norm": 1.2986805438995361,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5392,
+      "step": 91
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.204742431640625,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8787,
+      "step": 92
+    },
+    {
+      "epoch": 0.38509316770186336,
+      "grad_norm": 1.4381076097488403,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.0241,
+      "step": 93
+    },
+    {
+      "epoch": 0.38923395445134573,
+      "grad_norm": 1.3065365552902222,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.8894,
+      "step": 94
+    },
+    {
+      "epoch": 0.39337474120082816,
+      "grad_norm": 1.4354333877563477,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.9965,
+      "step": 95
+    },
+    {
+      "epoch": 0.39751552795031053,
+      "grad_norm": 1.419108510017395,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7321,
+      "step": 96
+    },
+    {
+      "epoch": 0.40165631469979296,
+      "grad_norm": 1.3358365297317505,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.7262,
+      "step": 97
+    },
+    {
+      "epoch": 0.4057971014492754,
+      "grad_norm": 1.2788820266723633,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.9486,
+      "step": 98
+    },
+    {
+      "epoch": 0.40993788819875776,
+      "grad_norm": 1.3755329847335815,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.8636,
+      "step": 99
+    },
+    {
+      "epoch": 0.40993788819875776,
+      "eval_loss": 0.874519944190979,
+      "eval_runtime": 86.6203,
+      "eval_samples_per_second": 2.355,
+      "eval_steps_per_second": 0.3,
+      "step": 99
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "grad_norm": 1.3155301809310913,
+      "learning_rate": 0.0,
+      "loss": 1.6806,
+      "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": 1.6694792800960512e+17,
+  "total_flos": 2.2344361467445248e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null