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:f6f1bef8c07cc222a092b0f5a1871431eab788ec7e2f37b2fd32870591f9f174
+oid sha256:1647959ca63d402add485521cc6986efad5952124dd00881270ead080e175eb7
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8e998732b81666d3775792ac52a7376c9d2b0e7809b282ee36dc97e3d20acf
+oid sha256:e9b96b7b2072d00f9528a52c49c83c470977fcfc82e5f66bfddfca5c8ea0ebf9
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af799fe3211e3e40d8b9706f8c3b206167d5ffb2362156a8c722bc7264a1502
+oid sha256:5247671bb3b43724099e7efbdd6940c1e957ecc51dac33725148b06733cd4ffc
 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": 0.5067567567567568,
+  "epoch": 0.6756756756756757,
   "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": 1.8021,
       "step": 75
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.9077301025390625,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6427,
+      "step": 76
+    },
+    {
+      "epoch": 0.5202702702702703,
+      "grad_norm": 0.9042626023292542,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.8777,
+      "step": 77
+    },
+    {
+      "epoch": 0.527027027027027,
+      "grad_norm": 0.9056885242462158,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.6057,
+      "step": 78
+    },
+    {
+      "epoch": 0.5337837837837838,
+      "grad_norm": 0.9446090459823608,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.9255,
+      "step": 79
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8837075233459473,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8139,
+      "step": 80
+    },
+    {
+      "epoch": 0.5472972972972973,
+      "grad_norm": 0.9778048992156982,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.8501,
+      "step": 81
+    },
+    {
+      "epoch": 0.5472972972972973,
+      "eval_loss": 1.7122490406036377,
+      "eval_runtime": 3.5137,
+      "eval_samples_per_second": 35.575,
+      "eval_steps_per_second": 4.554,
+      "step": 81
+    },
+    {
+      "epoch": 0.5540540540540541,
+      "grad_norm": 0.833020806312561,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7767,
+      "step": 82
+    },
+    {
+      "epoch": 0.5608108108108109,
+      "grad_norm": 0.9481951594352722,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.8747,
+      "step": 83
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 1.0012850761413574,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7838,
+      "step": 84
+    },
+    {
+      "epoch": 0.5743243243243243,
+      "grad_norm": 0.9208377599716187,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6287,
+      "step": 85
+    },
+    {
+      "epoch": 0.581081081081081,
+      "grad_norm": 0.918109655380249,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.6938,
+      "step": 86
+    },
+    {
+      "epoch": 0.5878378378378378,
+      "grad_norm": 0.8909979462623596,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.579,
+      "step": 87
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.930311918258667,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4217,
+      "step": 88
+    },
+    {
+      "epoch": 0.6013513513513513,
+      "grad_norm": 0.9225730895996094,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.5438,
+      "step": 89
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 0.8918566703796387,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6462,
+      "step": 90
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "eval_loss": 1.7096608877182007,
+      "eval_runtime": 3.5101,
+      "eval_samples_per_second": 35.611,
+      "eval_steps_per_second": 4.558,
+      "step": 90
+    },
+    {
+      "epoch": 0.6148648648648649,
+      "grad_norm": 1.0896010398864746,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5569,
+      "step": 91
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 1.0252374410629272,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.6083,
+      "step": 92
+    },
+    {
+      "epoch": 0.6283783783783784,
+      "grad_norm": 0.8842511773109436,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.8988,
+      "step": 93
+    },
+    {
+      "epoch": 0.6351351351351351,
+      "grad_norm": 0.8410938382148743,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6884,
+      "step": 94
+    },
+    {
+      "epoch": 0.6418918918918919,
+      "grad_norm": 0.9215858578681946,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7606,
+      "step": 95
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.8484981656074524,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.6887,
+      "step": 96
+    },
+    {
+      "epoch": 0.6554054054054054,
+      "grad_norm": 0.8972308039665222,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.7588,
+      "step": 97
+    },
+    {
+      "epoch": 0.6621621621621622,
+      "grad_norm": 1.0166327953338623,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0303,
+      "step": 98
+    },
+    {
+      "epoch": 0.668918918918919,
+      "grad_norm": 0.9183834791183472,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.7025,
+      "step": 99
+    },
+    {
+      "epoch": 0.668918918918919,
+      "eval_loss": 1.7084344625473022,
+      "eval_runtime": 3.5099,
+      "eval_samples_per_second": 35.614,
+      "eval_steps_per_second": 4.559,
+      "step": 99
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.8599016070365906,
+      "learning_rate": 0.0,
+      "loss": 1.4669,
+      "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": 7771734228860928.0,
+  "total_flos": 1.0345156158947328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null