Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0734d52f0ecec551bbc713c3ff805c55bf6b563c1f47a161d0daace08b384812
+oid sha256:bed84625353f1b7d491849a09b312dad10e5bc2c0d8ef559f492c66e60f6f7dc
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7873bf68d3434babf3e8e3bd6882bc679e3c1848c8fd04147bc888b856a099e1
+oid sha256:b8cb6e374247aea62cc18c8edabd2db728f10147c9d6599d6bd41f098665c117
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a985de432d6a2a4144c941972e5a14ec04f02b9ead518ec9c9fe3de4648cfc2d
+oid sha256:89a341144ccc53065c7e3e5d12c13a44295b4c7edcd0822a258c5756752fddf2
 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": 0.2148997134670487,
+  "epoch": 0.28653295128939826,
   "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": 10.3128,
       "step": 75
+    },
+    {
+      "epoch": 0.2177650429799427,
+      "grad_norm": 0.3165194094181061,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3204,
+      "step": 76
+    },
+    {
+      "epoch": 0.22063037249283668,
+      "grad_norm": 0.3308541476726532,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3179,
+      "step": 77
+    },
+    {
+      "epoch": 0.22349570200573066,
+      "grad_norm": 0.3327239453792572,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.312,
+      "step": 78
+    },
+    {
+      "epoch": 0.22636103151862463,
+      "grad_norm": 0.3000035583972931,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3087,
+      "step": 79
+    },
+    {
+      "epoch": 0.22922636103151864,
+      "grad_norm": 0.32877233624458313,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3161,
+      "step": 80
+    },
+    {
+      "epoch": 0.23209169054441262,
+      "grad_norm": 0.3862011730670929,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3023,
+      "step": 81
+    },
+    {
+      "epoch": 0.23209169054441262,
+      "eval_loss": 10.311718940734863,
+      "eval_runtime": 1.0872,
+      "eval_samples_per_second": 270.408,
+      "eval_steps_per_second": 34.031,
+      "step": 81
+    },
+    {
+      "epoch": 0.2349570200573066,
+      "grad_norm": 0.33126261830329895,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3185,
+      "step": 82
+    },
+    {
+      "epoch": 0.23782234957020057,
+      "grad_norm": 0.29596734046936035,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3169,
+      "step": 83
+    },
+    {
+      "epoch": 0.24068767908309455,
+      "grad_norm": 0.32354721426963806,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3139,
+      "step": 84
+    },
+    {
+      "epoch": 0.24355300859598855,
+      "grad_norm": 0.32435595989227295,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3234,
+      "step": 85
+    },
+    {
+      "epoch": 0.24641833810888253,
+      "grad_norm": 0.3075031340122223,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3194,
+      "step": 86
+    },
+    {
+      "epoch": 0.2492836676217765,
+      "grad_norm": 0.38141223788261414,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3027,
+      "step": 87
+    },
+    {
+      "epoch": 0.2521489971346705,
+      "grad_norm": 0.3392947018146515,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3089,
+      "step": 88
+    },
+    {
+      "epoch": 0.25501432664756446,
+      "grad_norm": 0.3004538118839264,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3138,
+      "step": 89
+    },
+    {
+      "epoch": 0.25787965616045844,
+      "grad_norm": 0.3904876410961151,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3068,
+      "step": 90
+    },
+    {
+      "epoch": 0.25787965616045844,
+      "eval_loss": 10.310718536376953,
+      "eval_runtime": 1.0615,
+      "eval_samples_per_second": 276.979,
+      "eval_steps_per_second": 34.858,
+      "step": 90
+    },
+    {
+      "epoch": 0.2607449856733524,
+      "grad_norm": 0.3297453224658966,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3213,
+      "step": 91
+    },
+    {
+      "epoch": 0.2636103151862464,
+      "grad_norm": 0.35301482677459717,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3242,
+      "step": 92
+    },
+    {
+      "epoch": 0.2664756446991404,
+      "grad_norm": 0.37583693861961365,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3206,
+      "step": 93
+    },
+    {
+      "epoch": 0.2693409742120344,
+      "grad_norm": 0.4035826623439789,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.2922,
+      "step": 94
+    },
+    {
+      "epoch": 0.2722063037249284,
+      "grad_norm": 0.33306726813316345,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.314,
+      "step": 95
+    },
+    {
+      "epoch": 0.27507163323782235,
+      "grad_norm": 0.38546448945999146,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3188,
+      "step": 96
+    },
+    {
+      "epoch": 0.27793696275071633,
+      "grad_norm": 0.3463270962238312,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3203,
+      "step": 97
+    },
+    {
+      "epoch": 0.2808022922636103,
+      "grad_norm": 0.33884936571121216,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3175,
+      "step": 98
+    },
+    {
+      "epoch": 0.2836676217765043,
+      "grad_norm": 0.34364816546440125,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3123,
+      "step": 99
+    },
+    {
+      "epoch": 0.2836676217765043,
+      "eval_loss": 10.31053352355957,
+      "eval_runtime": 1.029,
+      "eval_samples_per_second": 285.719,
+      "eval_steps_per_second": 35.958,
+      "step": 99
+    },
+    {
+      "epoch": 0.28653295128939826,
+      "grad_norm": 0.3673644959926605,
+      "learning_rate": 0.0,
+      "loss": 10.3042,
+      "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": 3948834717696.0,
+  "total_flos": 5256395882496.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null