Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a514cdeb120aed303b662a0bff1bc37714c1a3e8e4bf959710348c79303228
+oid sha256:09e2f1ea997442a3cb912a93b2835ef9b9bf0bdf67ef7c58d7b6caca0a7507e3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90579d74ab72c7f1650e62c917414eead63bba958fa246f22c20aa4d2687c83e
+oid sha256:5752bc5eb036f44e0ce31233d71b4528667b34c2296aaba2ab77aa8306c2a8d1
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.003876369650609882,
+  "epoch": 0.0051684928674798425,
   "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": 0.0658,
       "step": 75
+    },
+    {
+      "epoch": 0.00392805457928468,
+      "grad_norm": 0.5122618079185486,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0615,
+      "step": 76
+    },
+    {
+      "epoch": 0.003979739507959479,
+      "grad_norm": 0.40899038314819336,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.042,
+      "step": 77
+    },
+    {
+      "epoch": 0.004031424436634278,
+      "grad_norm": 0.3847385048866272,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0492,
+      "step": 78
+    },
+    {
+      "epoch": 0.004083109365309076,
+      "grad_norm": 0.8799728155136108,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0751,
+      "step": 79
+    },
+    {
+      "epoch": 0.004134794293983874,
+      "grad_norm": 0.4237743020057678,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0538,
+      "step": 80
+    },
+    {
+      "epoch": 0.004186479222658673,
+      "grad_norm": 0.4771229922771454,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0585,
+      "step": 81
+    },
+    {
+      "epoch": 0.004186479222658673,
+      "eval_loss": 0.0616205632686615,
+      "eval_runtime": 2002.2154,
+      "eval_samples_per_second": 8.137,
+      "eval_steps_per_second": 1.017,
+      "step": 81
+    },
+    {
+      "epoch": 0.004238164151333471,
+      "grad_norm": 0.420214980840683,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0467,
+      "step": 82
+    },
+    {
+      "epoch": 0.004289849080008269,
+      "grad_norm": 0.3315078020095825,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0405,
+      "step": 83
+    },
+    {
+      "epoch": 0.004341534008683068,
+      "grad_norm": 0.4422627389431,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0556,
+      "step": 84
+    },
+    {
+      "epoch": 0.004393218937357867,
+      "grad_norm": 0.664663553237915,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0848,
+      "step": 85
+    },
+    {
+      "epoch": 0.004444903866032665,
+      "grad_norm": 0.9881814122200012,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1188,
+      "step": 86
+    },
+    {
+      "epoch": 0.004496588794707463,
+      "grad_norm": 0.768933892250061,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0472,
+      "step": 87
+    },
+    {
+      "epoch": 0.0045482737233822615,
+      "grad_norm": 0.545575737953186,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0406,
+      "step": 88
+    },
+    {
+      "epoch": 0.00459995865205706,
+      "grad_norm": 0.3007638454437256,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0406,
+      "step": 89
+    },
+    {
+      "epoch": 0.004651643580731859,
+      "grad_norm": 0.4055767059326172,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0426,
+      "step": 90
+    },
+    {
+      "epoch": 0.004651643580731859,
+      "eval_loss": 0.06025952845811844,
+      "eval_runtime": 2002.5397,
+      "eval_samples_per_second": 8.136,
+      "eval_steps_per_second": 1.017,
+      "step": 90
+    },
+    {
+      "epoch": 0.004703328509406657,
+      "grad_norm": 0.42823222279548645,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0523,
+      "step": 91
+    },
+    {
+      "epoch": 0.0047550134380814554,
+      "grad_norm": 0.317855566740036,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0418,
+      "step": 92
+    },
+    {
+      "epoch": 0.004806698366756254,
+      "grad_norm": 0.5230840444564819,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0538,
+      "step": 93
+    },
+    {
+      "epoch": 0.004858383295431052,
+      "grad_norm": 1.009881854057312,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0426,
+      "step": 94
+    },
+    {
+      "epoch": 0.004910068224105851,
+      "grad_norm": 0.34990185499191284,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0524,
+      "step": 95
+    },
+    {
+      "epoch": 0.004961753152780649,
+      "grad_norm": 0.5936976075172424,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0695,
+      "step": 96
+    },
+    {
+      "epoch": 0.005013438081455448,
+      "grad_norm": 0.526382565498352,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0483,
+      "step": 97
+    },
+    {
+      "epoch": 0.005065123010130246,
+      "grad_norm": 0.47215914726257324,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0522,
+      "step": 98
+    },
+    {
+      "epoch": 0.005116807938805044,
+      "grad_norm": 0.5641908645629883,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0694,
+      "step": 99
+    },
+    {
+      "epoch": 0.005116807938805044,
+      "eval_loss": 0.06006684526801109,
+      "eval_runtime": 2001.6946,
+      "eval_samples_per_second": 8.14,
+      "eval_steps_per_second": 1.018,
+      "step": 99
+    },
+    {
+      "epoch": 0.0051684928674798425,
+      "grad_norm": 0.560275137424469,
+      "learning_rate": 0.0,
+      "loss": 0.054,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null