Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df4dc03270787cea6ae68e19178929d565f66aa1399b1bf7a59d8c0fb221811
+oid sha256:c15cf332314c645caff50138845125fe8e9c82c0d376e60cc93b36a9060fb615
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3ab649e2255739650d31e241d10ecd08d0efde030ec131074c20f423a79e7d
+oid sha256:366192c8b2e6b152e88a0c80bdf9926aff42f7a3da2436349ffa5d6764052160
 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": 0.05154639175257732,
+  "epoch": 0.06872852233676977,
   "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": 0.9151,
       "step": 75
+    },
+    {
+      "epoch": 0.05223367697594502,
+      "grad_norm": 0.9165816903114319,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8993,
+      "step": 76
+    },
+    {
+      "epoch": 0.052920962199312714,
+      "grad_norm": 0.7988548874855042,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.7629,
+      "step": 77
+    },
+    {
+      "epoch": 0.05360824742268041,
+      "grad_norm": 0.8661845922470093,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.8056,
+      "step": 78
+    },
+    {
+      "epoch": 0.05429553264604811,
+      "grad_norm": 0.8931153416633606,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.8286,
+      "step": 79
+    },
+    {
+      "epoch": 0.054982817869415807,
+      "grad_norm": 0.9941338300704956,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.969,
+      "step": 80
+    },
+    {
+      "epoch": 0.05567010309278351,
+      "grad_norm": 0.9468693137168884,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.9096,
+      "step": 81
+    },
+    {
+      "epoch": 0.05567010309278351,
+      "eval_loss": 0.432786762714386,
+      "eval_runtime": 252.8196,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 0.609,
+      "step": 81
+    },
+    {
+      "epoch": 0.056357388316151204,
+      "grad_norm": 0.8518151640892029,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.738,
+      "step": 82
+    },
+    {
+      "epoch": 0.0570446735395189,
+      "grad_norm": 0.8456606268882751,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.8421,
+      "step": 83
+    },
+    {
+      "epoch": 0.0577319587628866,
+      "grad_norm": 0.916377067565918,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.7926,
+      "step": 84
+    },
+    {
+      "epoch": 0.058419243986254296,
+      "grad_norm": 0.8955652713775635,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8337,
+      "step": 85
+    },
+    {
+      "epoch": 0.05910652920962199,
+      "grad_norm": 0.9039252996444702,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.8484,
+      "step": 86
+    },
+    {
+      "epoch": 0.05979381443298969,
+      "grad_norm": 0.9059133529663086,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.8716,
+      "step": 87
+    },
+    {
+      "epoch": 0.06048109965635739,
+      "grad_norm": 0.9183720350265503,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9808,
+      "step": 88
+    },
+    {
+      "epoch": 0.061168384879725084,
+      "grad_norm": 0.9803336262702942,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.8317,
+      "step": 89
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 0.911630392074585,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8261,
+      "step": 90
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "eval_loss": 0.4276270270347595,
+      "eval_runtime": 252.8496,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 0.609,
+      "step": 90
+    },
+    {
+      "epoch": 0.06254295532646048,
+      "grad_norm": 1.0115582942962646,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.8234,
+      "step": 91
+    },
+    {
+      "epoch": 0.06323024054982818,
+      "grad_norm": 0.8366324305534363,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.8316,
+      "step": 92
+    },
+    {
+      "epoch": 0.06391752577319587,
+      "grad_norm": 0.9966782331466675,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.7705,
+      "step": 93
+    },
+    {
+      "epoch": 0.06460481099656358,
+      "grad_norm": 0.9167208075523376,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8403,
+      "step": 94
+    },
+    {
+      "epoch": 0.06529209621993128,
+      "grad_norm": 0.9588520526885986,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.8928,
+      "step": 95
+    },
+    {
+      "epoch": 0.06597938144329897,
+      "grad_norm": 0.9358211159706116,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8543,
+      "step": 96
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.8442792892456055,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.8146,
+      "step": 97
+    },
+    {
+      "epoch": 0.06735395189003436,
+      "grad_norm": 0.8882707357406616,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8587,
+      "step": 98
+    },
+    {
+      "epoch": 0.06804123711340206,
+      "grad_norm": 1.0984888076782227,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.9505,
+      "step": 99
+    },
+    {
+      "epoch": 0.06804123711340206,
+      "eval_loss": 0.42630666494369507,
+      "eval_runtime": 253.3629,
+      "eval_samples_per_second": 4.839,
+      "eval_steps_per_second": 0.608,
+      "step": 99
+    },
+    {
+      "epoch": 0.06872852233676977,
+      "grad_norm": 0.9829119443893433,
+      "learning_rate": 0.0,
+      "loss": 0.9251,
+      "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": 9.5217449435136e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null