Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bfb56246525df0b47325f9e84f1455672bf0c8dd230b6491a11296f53120af5
+oid sha256:4df3f68bae1ededa3985817b4450784b98ffb753cbb7093cfda97a53423db5ce
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ba735c9ed21b87786cd08467de21dc026e31695c90e1b1e798333c9959ba27
+oid sha256:67052ed680ed45020e09bf784094153bc49d5812e811c47a95713a9c67957a9d
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f53083d6bf416fa674a4d7654c4dc44772d047f9fd45a1c2d70bd5cf789eb73
+oid sha256:f4c6893fc4a9ed236abb30b22cb769913941a10e57b959801e5127eb964077c8
 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": 0.00799696115476119,
+  "epoch": 0.010662614873014922,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 310.202,
       "eval_steps_per_second": 155.101,
       "step": 75
+    },
+    {
+      "epoch": 0.00810358730349134,
+      "grad_norm": 0.19393402338027954,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.8052,
+      "step": 76
+    },
+    {
+      "epoch": 0.008210213452221489,
+      "grad_norm": 0.17306220531463623,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.8092,
+      "step": 77
+    },
+    {
+      "epoch": 0.008316839600951639,
+      "grad_norm": 0.18071946501731873,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.8096,
+      "step": 78
+    },
+    {
+      "epoch": 0.008423465749681787,
+      "grad_norm": 0.18262875080108643,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.8112,
+      "step": 79
+    },
+    {
+      "epoch": 0.008530091898411937,
+      "grad_norm": 0.18377819657325745,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.8096,
+      "step": 80
+    },
+    {
+      "epoch": 0.008636718047142085,
+      "grad_norm": 0.1848413050174713,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.8044,
+      "step": 81
+    },
+    {
+      "epoch": 0.008743344195872235,
+      "grad_norm": 0.1873786747455597,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.8058,
+      "step": 82
+    },
+    {
+      "epoch": 0.008849970344602385,
+      "grad_norm": 0.20228584110736847,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.8059,
+      "step": 83
+    },
+    {
+      "epoch": 0.008956596493332534,
+      "grad_norm": 0.19265606999397278,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.8088,
+      "step": 84
+    },
+    {
+      "epoch": 0.009063222642062684,
+      "grad_norm": 0.17763932049274445,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.7996,
+      "step": 85
+    },
+    {
+      "epoch": 0.009169848790792832,
+      "grad_norm": 0.17844876646995544,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.802,
+      "step": 86
+    },
+    {
+      "epoch": 0.009276474939522982,
+      "grad_norm": 0.17362311482429504,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.8022,
+      "step": 87
+    },
+    {
+      "epoch": 0.00938310108825313,
+      "grad_norm": 0.18764075636863708,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.8014,
+      "step": 88
+    },
+    {
+      "epoch": 0.00948972723698328,
+      "grad_norm": 0.20152869820594788,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.8044,
+      "step": 89
+    },
+    {
+      "epoch": 0.009596353385713428,
+      "grad_norm": 0.19738389551639557,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.8073,
+      "step": 90
+    },
+    {
+      "epoch": 0.009702979534443578,
+      "grad_norm": 0.19693444669246674,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.7984,
+      "step": 91
+    },
+    {
+      "epoch": 0.009809605683173727,
+      "grad_norm": 0.20395702123641968,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.801,
+      "step": 92
+    },
+    {
+      "epoch": 0.009916231831903877,
+      "grad_norm": 0.1859755963087082,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.8075,
+      "step": 93
+    },
+    {
+      "epoch": 0.010022857980634025,
+      "grad_norm": 0.18670888245105743,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.8028,
+      "step": 94
+    },
+    {
+      "epoch": 0.010129484129364175,
+      "grad_norm": 0.1718273162841797,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.806,
+      "step": 95
+    },
+    {
+      "epoch": 0.010236110278094325,
+      "grad_norm": 0.2033439427614212,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.8003,
+      "step": 96
+    },
+    {
+      "epoch": 0.010342736426824473,
+      "grad_norm": 0.16593502461910248,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.8075,
+      "step": 97
+    },
+    {
+      "epoch": 0.010449362575554623,
+      "grad_norm": 0.1901598572731018,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.8042,
+      "step": 98
+    },
+    {
+      "epoch": 0.010555988724284772,
+      "grad_norm": 0.1914721131324768,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.8042,
+      "step": 99
+    },
+    {
+      "epoch": 0.010662614873014922,
+      "grad_norm": 0.19154879450798035,
+      "learning_rate": 0.0,
+      "loss": 10.8053,
+      "step": 100
+    },
+    {
+      "epoch": 0.010662614873014922,
+      "eval_loss": 10.803692817687988,
+      "eval_runtime": 73.6667,
+      "eval_samples_per_second": 214.425,
+      "eval_steps_per_second": 107.213,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 33262993145856.0,
+  "total_flos": 44295971143680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null