Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d94bbe93233ff58e886f27300f54fceb8dc786685e40c5864d3d7d94a4add31
+oid sha256:43d982d500f3616ea814bedcc59c914844cb08ebd810d5907363d36ca015ea06
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b897b6d298be39459a4f201e257ab4cefbd721b08b07e16e5a7cec088ffed66
+oid sha256:93691b7fbbbee9c9dc8a2da6501d9b21899c876ac7448b49a3f2fe91225fd973
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a488ec6d3f5e5a798465f5dc551e4b485f1f571042f5124861158cd9d793a28
+oid sha256:37bc9f091951863adc5f18668a30a9e6aac3f21f8c892b02b33c031686cfb847
 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": 0.03707365299060801,
+  "epoch": 0.049431537320810674,
   "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": 4.5264,
       "step": 75
+    },
+    {
+      "epoch": 0.037567968363816116,
+      "grad_norm": 3.8845295906066895,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.8841,
+      "step": 76
+    },
+    {
+      "epoch": 0.03806228373702422,
+      "grad_norm": 3.018535852432251,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 4.3427,
+      "step": 77
+    },
+    {
+      "epoch": 0.03855659911023233,
+      "grad_norm": 3.39355731010437,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.6911,
+      "step": 78
+    },
+    {
+      "epoch": 0.03905091448344043,
+      "grad_norm": 3.304109573364258,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 4.4204,
+      "step": 79
+    },
+    {
+      "epoch": 0.039545229856648545,
+      "grad_norm": 3.374882936477661,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.485,
+      "step": 80
+    },
+    {
+      "epoch": 0.04003954522985665,
+      "grad_norm": 3.7261548042297363,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 4.2292,
+      "step": 81
+    },
+    {
+      "epoch": 0.04003954522985665,
+      "eval_loss": 4.489640235900879,
+      "eval_runtime": 16.0787,
+      "eval_samples_per_second": 105.979,
+      "eval_steps_per_second": 13.247,
+      "step": 81
+    },
+    {
+      "epoch": 0.040533860603064756,
+      "grad_norm": 3.5689377784729004,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.4952,
+      "step": 82
+    },
+    {
+      "epoch": 0.04102817597627286,
+      "grad_norm": 3.5652458667755127,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 4.2532,
+      "step": 83
+    },
+    {
+      "epoch": 0.04152249134948097,
+      "grad_norm": 3.5636212825775146,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.8038,
+      "step": 84
+    },
+    {
+      "epoch": 0.04201680672268908,
+      "grad_norm": 2.6824896335601807,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.2188,
+      "step": 85
+    },
+    {
+      "epoch": 0.042511122095897184,
+      "grad_norm": 3.0280864238739014,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.6739,
+      "step": 86
+    },
+    {
+      "epoch": 0.04300543746910529,
+      "grad_norm": 3.2650485038757324,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 4.0116,
+      "step": 87
+    },
+    {
+      "epoch": 0.043499752842313395,
+      "grad_norm": 3.5868074893951416,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.4603,
+      "step": 88
+    },
+    {
+      "epoch": 0.0439940682155215,
+      "grad_norm": 2.4912710189819336,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 4.9682,
+      "step": 89
+    },
+    {
+      "epoch": 0.044488383588729606,
+      "grad_norm": 2.7958810329437256,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.45,
+      "step": 90
+    },
+    {
+      "epoch": 0.044488383588729606,
+      "eval_loss": 4.486810207366943,
+      "eval_runtime": 16.024,
+      "eval_samples_per_second": 106.34,
+      "eval_steps_per_second": 13.293,
+      "step": 90
+    },
+    {
+      "epoch": 0.04498269896193772,
+      "grad_norm": 4.003046989440918,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.7876,
+      "step": 91
+    },
+    {
+      "epoch": 0.045477014335145824,
+      "grad_norm": 3.0942835807800293,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 5.1126,
+      "step": 92
+    },
+    {
+      "epoch": 0.04597132970835393,
+      "grad_norm": 2.8093137741088867,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 4.389,
+      "step": 93
+    },
+    {
+      "epoch": 0.046465645081562035,
+      "grad_norm": 3.216890811920166,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 5.2788,
+      "step": 94
+    },
+    {
+      "epoch": 0.04695996045477014,
+      "grad_norm": 3.361987590789795,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.564,
+      "step": 95
+    },
+    {
+      "epoch": 0.04745427582797825,
+      "grad_norm": 2.9318277835845947,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.2455,
+      "step": 96
+    },
+    {
+      "epoch": 0.04794859120118636,
+      "grad_norm": 3.228325605392456,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 4.3779,
+      "step": 97
+    },
+    {
+      "epoch": 0.04844290657439446,
+      "grad_norm": 3.264146327972412,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.5083,
+      "step": 98
+    },
+    {
+      "epoch": 0.04893722194760257,
+      "grad_norm": 3.3395464420318604,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 4.5052,
+      "step": 99
+    },
+    {
+      "epoch": 0.04893722194760257,
+      "eval_loss": 4.485798358917236,
+      "eval_runtime": 16.0193,
+      "eval_samples_per_second": 106.372,
+      "eval_steps_per_second": 13.296,
+      "step": 99
+    },
+    {
+      "epoch": 0.049431537320810674,
+      "grad_norm": 3.2715954780578613,
+      "learning_rate": 0.0,
+      "loss": 4.3831,
+      "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": 20362140057600.0,
+  "total_flos": 27149520076800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null