Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c80954338859951571ce2266d837c1e20e2c911ea77eda513af6cf84da24478
+oid sha256:3c3a568739fc55d0be5b572e0788d397d57715e1fade555e20f22eb47dbfe499
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2c2f5fde31ceb864f4b134d23daf5d802d182c3da9b7ead96652398e60e6e2
+oid sha256:430be9308fd239d109553062c08c390051d4a60bef1b01772a2ace87bca659e5
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c88366e4cedd829c09c5fe7059b8e2e98aca6c5ecd80e83fa5290e51d4813d6
+oid sha256:b1eda10e338bda450401b94e9d71edd0e8030fa85df4e15faff7fc1927b372d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37fdc46c9ceacc4f09fb079980eedde483f3261a807a717ac38bb84282cfbc0
+oid sha256:e923d788d0e5bb4670f18c29c587368ad515daf2cbd573de4c8c9532822815ae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7531acfa0ec9fa2b40b0cd20bab3f5a106f4cba2bace97e330dcfa83316c6148
+oid sha256:3d85c2cd236cf7baed4921357ca31c0c601ce7ac6af9160fe04f16a8f52b2067
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9f53c748ab56977e5d0b2dabfb603fcb816a36a8711e81b4f65d5a8fb7d27c
+oid sha256:610c9f310ffd54fd8cf1375ce3733a85b79590ac8039610a2dbe77dd26d9688b
 size 15024

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": 0.04278379920136908,
+  "epoch": 0.05704506560182544,
   "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": 2.0327,
       "step": 75
+    },
+    {
+      "epoch": 0.04335424985738734,
+      "grad_norm": 0.7012278437614441,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1783,
+      "step": 76
+    },
+    {
+      "epoch": 0.04392470051340559,
+      "grad_norm": 0.6532755494117737,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.2421,
+      "step": 77
+    },
+    {
+      "epoch": 0.04449515116942385,
+      "grad_norm": 0.6290297508239746,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.2709,
+      "step": 78
+    },
+    {
+      "epoch": 0.0450656018254421,
+      "grad_norm": 0.6654998660087585,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.1185,
+      "step": 79
+    },
+    {
+      "epoch": 0.045636052481460354,
+      "grad_norm": 0.655230700969696,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1068,
+      "step": 80
+    },
+    {
+      "epoch": 0.04620650313747861,
+      "grad_norm": 0.6342410445213318,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1451,
+      "step": 81
+    },
+    {
+      "epoch": 0.04620650313747861,
+      "eval_loss": 2.1941704750061035,
+      "eval_runtime": 8.0936,
+      "eval_samples_per_second": 729.465,
+      "eval_steps_per_second": 22.858,
+      "step": 81
+    },
+    {
+      "epoch": 0.04677695379349686,
+      "grad_norm": 0.6823005676269531,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.136,
+      "step": 82
+    },
+    {
+      "epoch": 0.047347404449515115,
+      "grad_norm": 0.6718752384185791,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.1136,
+      "step": 83
+    },
+    {
+      "epoch": 0.04791785510553337,
+      "grad_norm": 0.5885657072067261,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.113,
+      "step": 84
+    },
+    {
+      "epoch": 0.04848830576155162,
+      "grad_norm": 0.6037890911102295,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2544,
+      "step": 85
+    },
+    {
+      "epoch": 0.04905875641756988,
+      "grad_norm": 0.7228572964668274,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.2411,
+      "step": 86
+    },
+    {
+      "epoch": 0.04962920707358814,
+      "grad_norm": 0.6061410903930664,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1195,
+      "step": 87
+    },
+    {
+      "epoch": 0.05019965772960639,
+      "grad_norm": 0.6911734938621521,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.2307,
+      "step": 88
+    },
+    {
+      "epoch": 0.050770108385624645,
+      "grad_norm": 0.6571145057678223,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.1619,
+      "step": 89
+    },
+    {
+      "epoch": 0.0513405590416429,
+      "grad_norm": 0.647502601146698,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0679,
+      "step": 90
+    },
+    {
+      "epoch": 0.0513405590416429,
+      "eval_loss": 2.1808366775512695,
+      "eval_runtime": 8.097,
+      "eval_samples_per_second": 729.16,
+      "eval_steps_per_second": 22.848,
+      "step": 90
+    },
+    {
+      "epoch": 0.05191100969766115,
+      "grad_norm": 0.6742761135101318,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2615,
+      "step": 91
+    },
+    {
+      "epoch": 0.052481460353679406,
+      "grad_norm": 1.099161982536316,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3373,
+      "step": 92
+    },
+    {
+      "epoch": 0.05305191100969766,
+      "grad_norm": 0.6479924917221069,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.0586,
+      "step": 93
+    },
+    {
+      "epoch": 0.05362236166571591,
+      "grad_norm": 0.6708055734634399,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1678,
+      "step": 94
+    },
+    {
+      "epoch": 0.05419281232173417,
+      "grad_norm": 0.6822814345359802,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.1989,
+      "step": 95
+    },
+    {
+      "epoch": 0.05476326297775243,
+      "grad_norm": 0.6907012462615967,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2352,
+      "step": 96
+    },
+    {
+      "epoch": 0.05533371363377068,
+      "grad_norm": 0.6413537859916687,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1822,
+      "step": 97
+    },
+    {
+      "epoch": 0.055904164289788935,
+      "grad_norm": 0.6916749477386475,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.141,
+      "step": 98
+    },
+    {
+      "epoch": 0.05647461494580719,
+      "grad_norm": 0.639250636100769,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.1036,
+      "step": 99
+    },
+    {
+      "epoch": 0.05647461494580719,
+      "eval_loss": 2.1780879497528076,
+      "eval_runtime": 8.0554,
+      "eval_samples_per_second": 732.925,
+      "eval_steps_per_second": 22.966,
+      "step": 99
+    },
+    {
+      "epoch": 0.05704506560182544,
+      "grad_norm": 0.6759567260742188,
+      "learning_rate": 0.0,
+      "loss": 2.093,
+      "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": 4172069461819392.0,
+  "total_flos": 5567387201961984.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null