Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9490910b6fd78968c4bcd67ab15d182fc1be54026baccb7e5753944ff985f88e
+oid sha256:f899ba5f64c5c270df88134371d11639cb0bacf6a2ee096025ec1cb8608dd81d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0195254ee625333bd4bfa98e557e201e1c31437989752250f1d23cc529656f72
+oid sha256:e59218a99b4ba7560731592d320b76d222c10d40e9592fa538a89aced7f7b04b
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b959cb1ce422e3352f7139006f61ea00d94797d8f826a1d0563c117d182549
+oid sha256:d7b0d1dd889d1cacb63e1388e04729ce5594ed9e599ed42094887ad3a398c5f6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb15a5c4a887fb67eec53b267e92476bc5d195a8e876a263ade17c8374535c64
+oid sha256:bfb76b8fc6e352ec1088a1fc9b9c6a6e647aaf1135e78f3073bd00c98d516f34
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09277c658aac53de56a76c737235ffcec56e6d1ada247740097429f79a342cf
+oid sha256:1d304d574d14c6747825125ff28e70014eb966a1308d9d7c840cd4a065b555b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6585539bba2e47261c89e37f54fe8b8331de96f10b73c530b92078fd565040
+oid sha256:c9100b9be46c740e3929c103ad8c46624df47211a48c7fb0edb56f89845804b9
 size 15024

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": 0.24,
+  "epoch": 0.32,
   "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": 2.2913,
       "step": 75
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 3.65971040725708,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1906,
+      "step": 76
+    },
+    {
+      "epoch": 0.2464,
+      "grad_norm": 2.355557441711426,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.0351,
+      "step": 77
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 1.8834080696105957,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.6887,
+      "step": 78
+    },
+    {
+      "epoch": 0.2528,
+      "grad_norm": 2.4096179008483887,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.145,
+      "step": 79
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.10882568359375,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.9101,
+      "step": 80
+    },
+    {
+      "epoch": 0.2592,
+      "grad_norm": 2.360527276992798,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.9097,
+      "step": 81
+    },
+    {
+      "epoch": 0.2592,
+      "eval_loss": 1.9023109674453735,
+      "eval_runtime": 14.7957,
+      "eval_samples_per_second": 71.17,
+      "eval_steps_per_second": 2.23,
+      "step": 81
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 2.4578933715820312,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7014,
+      "step": 82
+    },
+    {
+      "epoch": 0.2656,
+      "grad_norm": 2.11739182472229,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.8754,
+      "step": 83
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 1.8959879875183105,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.8658,
+      "step": 84
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 2.1034061908721924,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1916,
+      "step": 85
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 3.6678836345672607,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0631,
+      "step": 86
+    },
+    {
+      "epoch": 0.2784,
+      "grad_norm": 1.730532169342041,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.842,
+      "step": 87
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 2.7896106243133545,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1777,
+      "step": 88
+    },
+    {
+      "epoch": 0.2848,
+      "grad_norm": 2.0661978721618652,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.1761,
+      "step": 89
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 4.825430870056152,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8883,
+      "step": 90
+    },
+    {
+      "epoch": 0.288,
+      "eval_loss": 1.8964372873306274,
+      "eval_runtime": 14.7933,
+      "eval_samples_per_second": 71.181,
+      "eval_steps_per_second": 2.231,
+      "step": 90
+    },
+    {
+      "epoch": 0.2912,
+      "grad_norm": 1.8670202493667603,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.532,
+      "step": 91
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 2.0198287963867188,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.5803,
+      "step": 92
+    },
+    {
+      "epoch": 0.2976,
+      "grad_norm": 3.088954448699951,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.9913,
+      "step": 93
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 1.8765687942504883,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5786,
+      "step": 94
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 2.057028293609619,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7787,
+      "step": 95
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 2.631533622741699,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.8251,
+      "step": 96
+    },
+    {
+      "epoch": 0.3104,
+      "grad_norm": 2.291435480117798,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.4319,
+      "step": 97
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 6.852570056915283,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1418,
+      "step": 98
+    },
+    {
+      "epoch": 0.3168,
+      "grad_norm": 2.342111349105835,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.6609,
+      "step": 99
+    },
+    {
+      "epoch": 0.3168,
+      "eval_loss": 1.8956471681594849,
+      "eval_runtime": 14.7988,
+      "eval_samples_per_second": 71.155,
+      "eval_steps_per_second": 2.23,
+      "step": 99
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.128903388977051,
+      "learning_rate": 0.0,
+      "loss": 1.7299,
+      "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": 2.225661850681344e+17,
+  "total_flos": 2.967549134241792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null