Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75705faea2b2e330bdf948ed61e124e0c8595b61416079dfc45005f15af84f05
+oid sha256:a89dc717a33e3e4c2b0c598bc5acad61024487e8ecd8db6c583bdd0ea0b38156
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3f98de3c28571fb3e2a7f909055e50a2364d2773e19547a4618f6791b013c0
+oid sha256:b11863ab52853f37cf7e298e5c39b312047ec99bec31d1b6fae7004f77c84a0c
 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": 0.00635862653666808,
+  "epoch": 0.00847816871555744,
   "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": 1.5489,
       "step": 75
+    },
+    {
+      "epoch": 0.006443408223823654,
+      "grad_norm": 6.734039306640625,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0344,
+      "step": 76
+    },
+    {
+      "epoch": 0.006528189910979229,
+      "grad_norm": 6.099946975708008,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6265,
+      "step": 77
+    },
+    {
+      "epoch": 0.006612971598134803,
+      "grad_norm": 10.360422134399414,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5251,
+      "step": 78
+    },
+    {
+      "epoch": 0.006697753285290377,
+      "grad_norm": 6.372679710388184,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.187,
+      "step": 79
+    },
+    {
+      "epoch": 0.006782534972445952,
+      "grad_norm": 10.696057319641113,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2026,
+      "step": 80
+    },
+    {
+      "epoch": 0.006867316659601526,
+      "grad_norm": 6.109935283660889,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0836,
+      "step": 81
+    },
+    {
+      "epoch": 0.006867316659601526,
+      "eval_loss": 1.1527385711669922,
+      "eval_runtime": 1092.1652,
+      "eval_samples_per_second": 9.095,
+      "eval_steps_per_second": 1.137,
+      "step": 81
+    },
+    {
+      "epoch": 0.006952098346757101,
+      "grad_norm": 7.8638153076171875,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.964,
+      "step": 82
+    },
+    {
+      "epoch": 0.0070368800339126744,
+      "grad_norm": 6.4917073249816895,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.9489,
+      "step": 83
+    },
+    {
+      "epoch": 0.007121661721068249,
+      "grad_norm": 8.929377555847168,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1023,
+      "step": 84
+    },
+    {
+      "epoch": 0.0072064434082238235,
+      "grad_norm": 7.891057014465332,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9056,
+      "step": 85
+    },
+    {
+      "epoch": 0.007291225095379398,
+      "grad_norm": 6.32158899307251,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.537,
+      "step": 86
+    },
+    {
+      "epoch": 0.007376006782534973,
+      "grad_norm": 8.249305725097656,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5525,
+      "step": 87
+    },
+    {
+      "epoch": 0.007460788469690547,
+      "grad_norm": 7.551522731781006,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.2756,
+      "step": 88
+    },
+    {
+      "epoch": 0.007545570156846121,
+      "grad_norm": 7.788208961486816,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.1809,
+      "step": 89
+    },
+    {
+      "epoch": 0.007630351844001695,
+      "grad_norm": 7.2590742111206055,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7865,
+      "step": 90
+    },
+    {
+      "epoch": 0.007630351844001695,
+      "eval_loss": 1.142938494682312,
+      "eval_runtime": 1092.1983,
+      "eval_samples_per_second": 9.095,
+      "eval_steps_per_second": 1.137,
+      "step": 90
+    },
+    {
+      "epoch": 0.00771513353115727,
+      "grad_norm": 9.461429595947266,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3978,
+      "step": 91
+    },
+    {
+      "epoch": 0.0077999152183128445,
+      "grad_norm": 5.229576110839844,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9493,
+      "step": 92
+    },
+    {
+      "epoch": 0.007884696905468419,
+      "grad_norm": 6.617914199829102,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.9974,
+      "step": 93
+    },
+    {
+      "epoch": 0.007969478592623994,
+      "grad_norm": 6.198403835296631,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9369,
+      "step": 94
+    },
+    {
+      "epoch": 0.008054260279779568,
+      "grad_norm": 6.742490768432617,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.3305,
+      "step": 95
+    },
+    {
+      "epoch": 0.008139041966935143,
+      "grad_norm": 7.071584701538086,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9312,
+      "step": 96
+    },
+    {
+      "epoch": 0.008223823654090717,
+      "grad_norm": 5.995955467224121,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.7436,
+      "step": 97
+    },
+    {
+      "epoch": 0.00830860534124629,
+      "grad_norm": 7.11261510848999,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1321,
+      "step": 98
+    },
+    {
+      "epoch": 0.008393387028401865,
+      "grad_norm": 8.315668106079102,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.9591,
+      "step": 99
+    },
+    {
+      "epoch": 0.008393387028401865,
+      "eval_loss": 1.1404645442962646,
+      "eval_runtime": 1091.0994,
+      "eval_samples_per_second": 9.104,
+      "eval_steps_per_second": 1.138,
+      "step": 99
+    },
+    {
+      "epoch": 0.00847816871555744,
+      "grad_norm": 5.73974609375,
+      "learning_rate": 0.0,
+      "loss": 1.0922,
+      "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": 5.56425126346752e+16,
+  "total_flos": 7.41900168462336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null