Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9256dc4e2945ea2c6a8568bc8e53cba5fb593c09eca385ce2a3c0fe09fd61081
+oid sha256:574d97e0b8744f49d306a704a289df14b3d697f38ea51f9f11dd9fdbe503fc4f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c493a59cfe4ddfea6f217b524810c6345f037ba038c02ca881252662c4fbe1af
+oid sha256:6bdce0c12765bede17f6034a46aa75936697d8f5f0d5482dc3c5af92309c42fb
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.010141987829614604,
+  "epoch": 0.013522650439486139,
   "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": 10.3613,
       "step": 75
+    },
+    {
+      "epoch": 0.010277214334009466,
+      "grad_norm": 0.342067152261734,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3582,
+      "step": 76
+    },
+    {
+      "epoch": 0.010412440838404327,
+      "grad_norm": 0.3511400818824768,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3546,
+      "step": 77
+    },
+    {
+      "epoch": 0.010547667342799188,
+      "grad_norm": 0.2721881568431854,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3608,
+      "step": 78
+    },
+    {
+      "epoch": 0.01068289384719405,
+      "grad_norm": 0.3455629348754883,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3484,
+      "step": 79
+    },
+    {
+      "epoch": 0.010818120351588911,
+      "grad_norm": 0.327305406332016,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3572,
+      "step": 80
+    },
+    {
+      "epoch": 0.010953346855983773,
+      "grad_norm": 0.18577629327774048,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3567,
+      "step": 81
+    },
+    {
+      "epoch": 0.010953346855983773,
+      "eval_loss": 10.357199668884277,
+      "eval_runtime": 40.778,
+      "eval_samples_per_second": 152.729,
+      "eval_steps_per_second": 19.103,
+      "step": 81
+    },
+    {
+      "epoch": 0.011088573360378634,
+      "grad_norm": 0.11704239249229431,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3635,
+      "step": 82
+    },
+    {
+      "epoch": 0.011223799864773495,
+      "grad_norm": 0.19233828783035278,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3677,
+      "step": 83
+    },
+    {
+      "epoch": 0.011359026369168357,
+      "grad_norm": 0.07823574542999268,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3695,
+      "step": 84
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.13713940978050232,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3596,
+      "step": 85
+    },
+    {
+      "epoch": 0.01162947937795808,
+      "grad_norm": 0.18941013514995575,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3583,
+      "step": 86
+    },
+    {
+      "epoch": 0.011764705882352941,
+      "grad_norm": 0.30075106024742126,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3597,
+      "step": 87
+    },
+    {
+      "epoch": 0.011899932386747802,
+      "grad_norm": 0.10994397848844528,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3648,
+      "step": 88
+    },
+    {
+      "epoch": 0.012035158891142664,
+      "grad_norm": 0.13853776454925537,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3724,
+      "step": 89
+    },
+    {
+      "epoch": 0.012170385395537525,
+      "grad_norm": 0.191994771361351,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3556,
+      "step": 90
+    },
+    {
+      "epoch": 0.012170385395537525,
+      "eval_loss": 10.356754302978516,
+      "eval_runtime": 40.9895,
+      "eval_samples_per_second": 151.941,
+      "eval_steps_per_second": 19.005,
+      "step": 90
+    },
+    {
+      "epoch": 0.012305611899932387,
+      "grad_norm": 0.10114133358001709,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3638,
+      "step": 91
+    },
+    {
+      "epoch": 0.012440838404327248,
+      "grad_norm": 0.22643674910068512,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3453,
+      "step": 92
+    },
+    {
+      "epoch": 0.01257606490872211,
+      "grad_norm": 0.18599919974803925,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3606,
+      "step": 93
+    },
+    {
+      "epoch": 0.01271129141311697,
+      "grad_norm": 0.4384092092514038,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3458,
+      "step": 94
+    },
+    {
+      "epoch": 0.012846517917511832,
+      "grad_norm": 0.1412304788827896,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3518,
+      "step": 95
+    },
+    {
+      "epoch": 0.012981744421906694,
+      "grad_norm": 0.20670315623283386,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3595,
+      "step": 96
+    },
+    {
+      "epoch": 0.013116970926301555,
+      "grad_norm": 0.15490083396434784,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3575,
+      "step": 97
+    },
+    {
+      "epoch": 0.013252197430696416,
+      "grad_norm": 0.19258053600788116,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.349,
+      "step": 98
+    },
+    {
+      "epoch": 0.013387423935091278,
+      "grad_norm": 0.15515723824501038,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3637,
+      "step": 99
+    },
+    {
+      "epoch": 0.013387423935091278,
+      "eval_loss": 10.356693267822266,
+      "eval_runtime": 40.9088,
+      "eval_samples_per_second": 152.241,
+      "eval_steps_per_second": 19.042,
+      "step": 99
+    },
+    {
+      "epoch": 0.013522650439486139,
+      "grad_norm": 0.2686675488948822,
+      "learning_rate": 0.0,
+      "loss": 10.3569,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null