Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c52138cf2c59d45e1831c51de681c4950b03a7a39d40a380c4ada227d37277
+oid sha256:2c19bf47871ecc35279881d3fb13d0f249a9eac6e9ce25d4568cdbc8c9d7ca93
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab4f46ba392e9fd9eedff9b9476dca93994426da8e8e1ae3021c4fb71dcf33c
+oid sha256:251f36a2315d6039ade373bf1d2aba5035cb28a4cbd2c036d5a5b82e05eebb83
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c2aeb48c97bc17fc16027c087a1f2b9b14a3b5da40e726c4c4179d5382c495
+oid sha256:91f22f8f8c0b9795081b2113cdf6c8de9bf9ffc844eac0cced0355cd972f7187
 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": 0.18404907975460122,
+  "epoch": 0.24539877300613497,
   "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": 0.0591,
       "step": 75
+    },
+    {
+      "epoch": 0.18650306748466258,
+      "grad_norm": 0.15801814198493958,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.107,
+      "step": 76
+    },
+    {
+      "epoch": 0.18895705521472392,
+      "grad_norm": 0.14311841130256653,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0723,
+      "step": 77
+    },
+    {
+      "epoch": 0.19141104294478528,
+      "grad_norm": 0.26355618238449097,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1375,
+      "step": 78
+    },
+    {
+      "epoch": 0.19386503067484662,
+      "grad_norm": 0.18676921725273132,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0876,
+      "step": 79
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.15667636692523956,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0802,
+      "step": 80
+    },
+    {
+      "epoch": 0.19877300613496932,
+      "grad_norm": 0.1485484093427658,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.093,
+      "step": 81
+    },
+    {
+      "epoch": 0.19877300613496932,
+      "eval_loss": 0.08068693429231644,
+      "eval_runtime": 72.5605,
+      "eval_samples_per_second": 4.727,
+      "eval_steps_per_second": 0.593,
+      "step": 81
+    },
+    {
+      "epoch": 0.20122699386503068,
+      "grad_norm": 0.17449061572551727,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.081,
+      "step": 82
+    },
+    {
+      "epoch": 0.20368098159509201,
+      "grad_norm": 0.18600428104400635,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0983,
+      "step": 83
+    },
+    {
+      "epoch": 0.20613496932515338,
+      "grad_norm": 0.25841566920280457,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1364,
+      "step": 84
+    },
+    {
+      "epoch": 0.2085889570552147,
+      "grad_norm": 0.15932850539684296,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0906,
+      "step": 85
+    },
+    {
+      "epoch": 0.21104294478527608,
+      "grad_norm": 0.1419418305158615,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0762,
+      "step": 86
+    },
+    {
+      "epoch": 0.2134969325153374,
+      "grad_norm": 0.1434643417596817,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0746,
+      "step": 87
+    },
+    {
+      "epoch": 0.21595092024539878,
+      "grad_norm": 0.1833578497171402,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0677,
+      "step": 88
+    },
+    {
+      "epoch": 0.2184049079754601,
+      "grad_norm": 0.12698689103126526,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0722,
+      "step": 89
+    },
+    {
+      "epoch": 0.22085889570552147,
+      "grad_norm": 0.13668203353881836,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0869,
+      "step": 90
+    },
+    {
+      "epoch": 0.22085889570552147,
+      "eval_loss": 0.07971709966659546,
+      "eval_runtime": 72.5838,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 0.592,
+      "step": 90
+    },
+    {
+      "epoch": 0.2233128834355828,
+      "grad_norm": 0.17934265732765198,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0912,
+      "step": 91
+    },
+    {
+      "epoch": 0.22576687116564417,
+      "grad_norm": 0.2167123705148697,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1007,
+      "step": 92
+    },
+    {
+      "epoch": 0.2282208588957055,
+      "grad_norm": 0.1933976113796234,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0885,
+      "step": 93
+    },
+    {
+      "epoch": 0.23067484662576687,
+      "grad_norm": 0.15569214522838593,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1064,
+      "step": 94
+    },
+    {
+      "epoch": 0.2331288343558282,
+      "grad_norm": 0.10046561807394028,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0589,
+      "step": 95
+    },
+    {
+      "epoch": 0.23558282208588957,
+      "grad_norm": 0.18496468663215637,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0663,
+      "step": 96
+    },
+    {
+      "epoch": 0.23803680981595093,
+      "grad_norm": 0.15307293832302094,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.087,
+      "step": 97
+    },
+    {
+      "epoch": 0.24049079754601227,
+      "grad_norm": 0.703031599521637,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0849,
+      "step": 98
+    },
+    {
+      "epoch": 0.24294478527607363,
+      "grad_norm": 0.12190704792737961,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0673,
+      "step": 99
+    },
+    {
+      "epoch": 0.24294478527607363,
+      "eval_loss": 0.07961469888687134,
+      "eval_runtime": 72.5905,
+      "eval_samples_per_second": 4.725,
+      "eval_steps_per_second": 0.592,
+      "step": 99
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.1318531483411789,
+      "learning_rate": 0.0,
+      "loss": 0.0657,
+      "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": 9.57034595792978e+16,
+  "total_flos": 1.283465000559575e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null