Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6619f01f8c8e33288505c13178c9da0d2b7769bda0a441a987eb8d53642a0a9f
+oid sha256:b0510f518d4cde18a11673fee8575461d104d57c94500e2ba60d490704e728f1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a61c57f980e49f18c400b3a32ca26f87061ec3e3bba487979ee0a37d40c5cb
+oid sha256:364ae96986867dfd61d3001e5cbfeda4ccf2e73861e21a8b55b4fbd83f54bdd3
 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": 0.0929944203347799,
+  "epoch": 0.12399256044637322,
   "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": 0.4761,
       "step": 75
+    },
+    {
+      "epoch": 0.09423434593924365,
+      "grad_norm": 2.8234503269195557,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2459,
+      "step": 76
+    },
+    {
+      "epoch": 0.09547427154370738,
+      "grad_norm": 3.906480073928833,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4904,
+      "step": 77
+    },
+    {
+      "epoch": 0.09671419714817112,
+      "grad_norm": 4.214174270629883,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7033,
+      "step": 78
+    },
+    {
+      "epoch": 0.09795412275263485,
+      "grad_norm": 2.5430684089660645,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2709,
+      "step": 79
+    },
+    {
+      "epoch": 0.09919404835709858,
+      "grad_norm": 3.603428363800049,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2043,
+      "step": 80
+    },
+    {
+      "epoch": 0.10043397396156231,
+      "grad_norm": 2.2767882347106934,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1009,
+      "step": 81
+    },
+    {
+      "epoch": 0.10043397396156231,
+      "eval_loss": 0.36546072363853455,
+      "eval_runtime": 74.5654,
+      "eval_samples_per_second": 9.106,
+      "eval_steps_per_second": 1.14,
+      "step": 81
+    },
+    {
+      "epoch": 0.10167389956602604,
+      "grad_norm": 1.9613827466964722,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2421,
+      "step": 82
+    },
+    {
+      "epoch": 0.10291382517048978,
+      "grad_norm": 3.4064152240753174,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6087,
+      "step": 83
+    },
+    {
+      "epoch": 0.10415375077495351,
+      "grad_norm": 3.468510150909424,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3645,
+      "step": 84
+    },
+    {
+      "epoch": 0.10539367637941724,
+      "grad_norm": 2.997673749923706,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2891,
+      "step": 85
+    },
+    {
+      "epoch": 0.10663360198388097,
+      "grad_norm": 3.279283285140991,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3884,
+      "step": 86
+    },
+    {
+      "epoch": 0.1078735275883447,
+      "grad_norm": 3.1893913745880127,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2048,
+      "step": 87
+    },
+    {
+      "epoch": 0.10911345319280844,
+      "grad_norm": 3.0490288734436035,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2788,
+      "step": 88
+    },
+    {
+      "epoch": 0.11035337879727217,
+      "grad_norm": 4.683725833892822,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2737,
+      "step": 89
+    },
+    {
+      "epoch": 0.1115933044017359,
+      "grad_norm": 3.1918933391571045,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4477,
+      "step": 90
+    },
+    {
+      "epoch": 0.1115933044017359,
+      "eval_loss": 0.3621177077293396,
+      "eval_runtime": 74.5607,
+      "eval_samples_per_second": 9.107,
+      "eval_steps_per_second": 1.14,
+      "step": 90
+    },
+    {
+      "epoch": 0.11283323000619963,
+      "grad_norm": 2.881042003631592,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2986,
+      "step": 91
+    },
+    {
+      "epoch": 0.11407315561066336,
+      "grad_norm": 2.159529685974121,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1908,
+      "step": 92
+    },
+    {
+      "epoch": 0.1153130812151271,
+      "grad_norm": 2.5343451499938965,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3447,
+      "step": 93
+    },
+    {
+      "epoch": 0.11655300681959083,
+      "grad_norm": 2.5903573036193848,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3459,
+      "step": 94
+    },
+    {
+      "epoch": 0.11779293242405456,
+      "grad_norm": 1.5675890445709229,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0968,
+      "step": 95
+    },
+    {
+      "epoch": 0.11903285802851829,
+      "grad_norm": 3.2924253940582275,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4554,
+      "step": 96
+    },
+    {
+      "epoch": 0.12027278363298202,
+      "grad_norm": 3.223909378051758,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2568,
+      "step": 97
+    },
+    {
+      "epoch": 0.12151270923744575,
+      "grad_norm": 2.694246292114258,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4494,
+      "step": 98
+    },
+    {
+      "epoch": 0.12275263484190949,
+      "grad_norm": 2.3312549591064453,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.365,
+      "step": 99
+    },
+    {
+      "epoch": 0.12275263484190949,
+      "eval_loss": 0.36193743348121643,
+      "eval_runtime": 74.542,
+      "eval_samples_per_second": 9.109,
+      "eval_steps_per_second": 1.14,
+      "step": 99
+    },
+    {
+      "epoch": 0.12399256044637322,
+      "grad_norm": 2.271353244781494,
+      "learning_rate": 0.0,
+      "loss": 0.2151,
+      "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