Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcbbf91cf9f2a558802dc46c3138bbfde46c8f828a1af9817191f4302d5db69
+oid sha256:afbd70a44eb27ed70f8734e44786bcc40339c7796a78989e0759b41c613970b8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ea139c7675686d034b25f3beadf395ddcba619d9cf83f1162233cbb370be5b
+oid sha256:3caac4426b10a78ecd6e4e33b78948f1c36f541f73facec8fa6b3588a52a22c5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.14691478942213515,
+  "epoch": 0.1958863858961802,
   "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": 0.5454,
       "step": 75
+    },
+    {
+      "epoch": 0.14887365328109697,
+      "grad_norm": 0.49792057275772095,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.5466,
+      "step": 76
+    },
+    {
+      "epoch": 0.15083251714005877,
+      "grad_norm": 0.5006000399589539,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.5489,
+      "step": 77
+    },
+    {
+      "epoch": 0.15279138099902057,
+      "grad_norm": 0.45990002155303955,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4961,
+      "step": 78
+    },
+    {
+      "epoch": 0.15475024485798236,
+      "grad_norm": 0.6047857403755188,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6423,
+      "step": 79
+    },
+    {
+      "epoch": 0.15670910871694418,
+      "grad_norm": 0.542218029499054,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6736,
+      "step": 80
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "grad_norm": 0.5993568897247314,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.5936,
+      "step": 81
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "eval_loss": 0.5576213002204895,
+      "eval_runtime": 47.2916,
+      "eval_samples_per_second": 9.093,
+      "eval_steps_per_second": 1.142,
+      "step": 81
+    },
+    {
+      "epoch": 0.16062683643486778,
+      "grad_norm": 0.5401186347007751,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.577,
+      "step": 82
+    },
+    {
+      "epoch": 0.16258570029382957,
+      "grad_norm": 0.5273922681808472,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.5519,
+      "step": 83
+    },
+    {
+      "epoch": 0.16454456415279137,
+      "grad_norm": 0.5098137259483337,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5777,
+      "step": 84
+    },
+    {
+      "epoch": 0.1665034280117532,
+      "grad_norm": 0.5234717726707458,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4146,
+      "step": 85
+    },
+    {
+      "epoch": 0.168462291870715,
+      "grad_norm": 0.522405207157135,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.5295,
+      "step": 86
+    },
+    {
+      "epoch": 0.17042115572967678,
+      "grad_norm": 0.5747347474098206,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.5258,
+      "step": 87
+    },
+    {
+      "epoch": 0.17238001958863858,
+      "grad_norm": 0.5367957949638367,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4646,
+      "step": 88
+    },
+    {
+      "epoch": 0.1743388834476004,
+      "grad_norm": 0.6364375948905945,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.6502,
+      "step": 89
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "grad_norm": 0.5091520547866821,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4272,
+      "step": 90
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "eval_loss": 0.5568687915802002,
+      "eval_runtime": 47.2476,
+      "eval_samples_per_second": 9.101,
+      "eval_steps_per_second": 1.143,
+      "step": 90
+    },
+    {
+      "epoch": 0.178256611165524,
+      "grad_norm": 0.5590183734893799,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4774,
+      "step": 91
+    },
+    {
+      "epoch": 0.1802154750244858,
+      "grad_norm": 0.5330744981765747,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5269,
+      "step": 92
+    },
+    {
+      "epoch": 0.1821743388834476,
+      "grad_norm": 0.48939576745033264,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5696,
+      "step": 93
+    },
+    {
+      "epoch": 0.1841332027424094,
+      "grad_norm": 0.5850751996040344,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.672,
+      "step": 94
+    },
+    {
+      "epoch": 0.1860920666013712,
+      "grad_norm": 0.5215665698051453,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6121,
+      "step": 95
+    },
+    {
+      "epoch": 0.188050930460333,
+      "grad_norm": 0.49730828404426575,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.5748,
+      "step": 96
+    },
+    {
+      "epoch": 0.19000979431929482,
+      "grad_norm": 0.5853298306465149,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5077,
+      "step": 97
+    },
+    {
+      "epoch": 0.19196865817825662,
+      "grad_norm": 0.6316199898719788,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7017,
+      "step": 98
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "grad_norm": 0.5572590827941895,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5761,
+      "step": 99
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "eval_loss": 0.5564124584197998,
+      "eval_runtime": 47.2387,
+      "eval_samples_per_second": 9.103,
+      "eval_steps_per_second": 1.143,
+      "step": 99
+    },
+    {
+      "epoch": 0.1958863858961802,
+      "grad_norm": 0.46038520336151123,
+      "learning_rate": 0.0,
+      "loss": 0.524,
+      "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": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null