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:fdf3e944f41ec39c8768ba561bcb4da1231a8c4535ac082addfd25bd205b4a43
+oid sha256:a2613e9047f95991346f3a61b359828a57186fcba00deea17030183b1d256333
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171981e9b45c27ddd4b1b638c14a8e3cdb3fdb2734cb82d154ac1b748c0c3de5
+oid sha256:d21c72d53e4b00ced2271699bca1ad3a05ca66d4e688f7f65ea735372454eeac
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.005583265093426636,
+  "epoch": 0.007444353457902181,
   "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": 4.6476,
       "step": 75
+    },
+    {
+      "epoch": 0.005657708628005658,
+      "grad_norm": 3.482083797454834,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 5.0748,
+      "step": 76
+    },
+    {
+      "epoch": 0.005732152162584679,
+      "grad_norm": 3.336946964263916,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 4.3167,
+      "step": 77
+    },
+    {
+      "epoch": 0.005806595697163701,
+      "grad_norm": 2.958566427230835,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.8344,
+      "step": 78
+    },
+    {
+      "epoch": 0.005881039231742723,
+      "grad_norm": 2.784067392349243,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 4.1894,
+      "step": 79
+    },
+    {
+      "epoch": 0.0059554827663217446,
+      "grad_norm": 3.0680527687072754,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.7619,
+      "step": 80
+    },
+    {
+      "epoch": 0.006029926300900767,
+      "grad_norm": 2.970621347427368,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 4.1997,
+      "step": 81
+    },
+    {
+      "epoch": 0.006029926300900767,
+      "eval_loss": 2.1963963508605957,
+      "eval_runtime": 1768.5617,
+      "eval_samples_per_second": 6.396,
+      "eval_steps_per_second": 0.8,
+      "step": 81
+    },
+    {
+      "epoch": 0.006104369835479789,
+      "grad_norm": 3.0712950229644775,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.5019,
+      "step": 82
+    },
+    {
+      "epoch": 0.00617881337005881,
+      "grad_norm": 2.5973801612854004,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 4.2906,
+      "step": 83
+    },
+    {
+      "epoch": 0.006253256904637832,
+      "grad_norm": 2.581934928894043,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.8983,
+      "step": 84
+    },
+    {
+      "epoch": 0.006327700439216854,
+      "grad_norm": 2.9472391605377197,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.1401,
+      "step": 85
+    },
+    {
+      "epoch": 0.006402143973795875,
+      "grad_norm": 2.82492733001709,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.1082,
+      "step": 86
+    },
+    {
+      "epoch": 0.0064765875083748975,
+      "grad_norm": 3.395123243331909,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 4.2731,
+      "step": 87
+    },
+    {
+      "epoch": 0.00655103104295392,
+      "grad_norm": 3.4191434383392334,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.5354,
+      "step": 88
+    },
+    {
+      "epoch": 0.006625474577532941,
+      "grad_norm": 3.413599967956543,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 4.7829,
+      "step": 89
+    },
+    {
+      "epoch": 0.006699918112111963,
+      "grad_norm": 3.189854383468628,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.4412,
+      "step": 90
+    },
+    {
+      "epoch": 0.006699918112111963,
+      "eval_loss": 2.1938297748565674,
+      "eval_runtime": 1767.8921,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.8,
+      "step": 90
+    },
+    {
+      "epoch": 0.006774361646690985,
+      "grad_norm": 4.145727157592773,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.099,
+      "step": 91
+    },
+    {
+      "epoch": 0.006848805181270006,
+      "grad_norm": 2.8019332885742188,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.6641,
+      "step": 92
+    },
+    {
+      "epoch": 0.006923248715849028,
+      "grad_norm": 2.8234806060791016,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 4.2909,
+      "step": 93
+    },
+    {
+      "epoch": 0.0069976922504280505,
+      "grad_norm": 2.6929306983947754,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 4.3875,
+      "step": 94
+    },
+    {
+      "epoch": 0.007072135785007072,
+      "grad_norm": 3.3331360816955566,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.9137,
+      "step": 95
+    },
+    {
+      "epoch": 0.007146579319586094,
+      "grad_norm": 3.2792673110961914,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.3802,
+      "step": 96
+    },
+    {
+      "epoch": 0.007221022854165116,
+      "grad_norm": 3.153491497039795,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 4.3517,
+      "step": 97
+    },
+    {
+      "epoch": 0.007295466388744137,
+      "grad_norm": 2.901925802230835,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.2306,
+      "step": 98
+    },
+    {
+      "epoch": 0.007369909923323159,
+      "grad_norm": 2.977510690689087,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 4.3099,
+      "step": 99
+    },
+    {
+      "epoch": 0.007369909923323159,
+      "eval_loss": 2.1932551860809326,
+      "eval_runtime": 1767.8313,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.8,
+      "step": 99
+    },
+    {
+      "epoch": 0.007444353457902181,
+      "grad_norm": 2.916205883026123,
+      "learning_rate": 0.0,
+      "loss": 4.3172,
+      "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": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null