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:b0222d517298b910843485af096d0a1f9aac5776ef712da093fdaf62d6cc7fbb
+oid sha256:2883a38093ea20640379187a393117bcfb37f17fbbf8fe58c89a1717543aa091
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ab9af3e9a83ee75da2dcc98945b7600d1656410fd49235710bdf27dd741bbe
+oid sha256:80fe3c24ecda95ee232d015800b7513b1afb055fc5c8a2059fc7284a545bc3e3
 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": 0.05813953488372093,
+  "epoch": 0.07751937984496124,
   "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": 0.5731,
       "step": 75
+    },
+    {
+      "epoch": 0.05891472868217054,
+      "grad_norm": 16.920230865478516,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8086,
+      "step": 76
+    },
+    {
+      "epoch": 0.059689922480620154,
+      "grad_norm": 17.397293090820312,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8585,
+      "step": 77
+    },
+    {
+      "epoch": 0.06046511627906977,
+      "grad_norm": 11.810914039611816,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9178,
+      "step": 78
+    },
+    {
+      "epoch": 0.06124031007751938,
+      "grad_norm": 14.582168579101562,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1458,
+      "step": 79
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 9.802223205566406,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6749,
+      "step": 80
+    },
+    {
+      "epoch": 0.06279069767441861,
+      "grad_norm": 22.057186126708984,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.9713,
+      "step": 81
+    },
+    {
+      "epoch": 0.06279069767441861,
+      "eval_loss": 0.8691883683204651,
+      "eval_runtime": 118.3033,
+      "eval_samples_per_second": 9.18,
+      "eval_steps_per_second": 1.15,
+      "step": 81
+    },
+    {
+      "epoch": 0.06356589147286822,
+      "grad_norm": 15.885632514953613,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0604,
+      "step": 82
+    },
+    {
+      "epoch": 0.06434108527131784,
+      "grad_norm": 14.095142364501953,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.4269,
+      "step": 83
+    },
+    {
+      "epoch": 0.06511627906976744,
+      "grad_norm": 11.631954193115234,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3714,
+      "step": 84
+    },
+    {
+      "epoch": 0.06589147286821706,
+      "grad_norm": 11.832831382751465,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7737,
+      "step": 85
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 14.319507598876953,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.2051,
+      "step": 86
+    },
+    {
+      "epoch": 0.06744186046511629,
+      "grad_norm": 16.631603240966797,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.1872,
+      "step": 87
+    },
+    {
+      "epoch": 0.06821705426356589,
+      "grad_norm": 7.372907638549805,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4726,
+      "step": 88
+    },
+    {
+      "epoch": 0.06899224806201551,
+      "grad_norm": 17.025836944580078,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0284,
+      "step": 89
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 10.32677173614502,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2095,
+      "step": 90
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "eval_loss": 0.8616081476211548,
+      "eval_runtime": 118.189,
+      "eval_samples_per_second": 9.189,
+      "eval_steps_per_second": 1.151,
+      "step": 90
+    },
+    {
+      "epoch": 0.07054263565891473,
+      "grad_norm": 5.949835777282715,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6475,
+      "step": 91
+    },
+    {
+      "epoch": 0.07131782945736434,
+      "grad_norm": 19.60506248474121,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0418,
+      "step": 92
+    },
+    {
+      "epoch": 0.07209302325581396,
+      "grad_norm": 12.335699081420898,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.684,
+      "step": 93
+    },
+    {
+      "epoch": 0.07286821705426356,
+      "grad_norm": 14.82921314239502,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8848,
+      "step": 94
+    },
+    {
+      "epoch": 0.07364341085271318,
+      "grad_norm": 11.518810272216797,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5252,
+      "step": 95
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 9.791691780090332,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7503,
+      "step": 96
+    },
+    {
+      "epoch": 0.07519379844961241,
+      "grad_norm": 24.59143829345703,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.9212,
+      "step": 97
+    },
+    {
+      "epoch": 0.07596899224806201,
+      "grad_norm": 10.274015426635742,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.5327,
+      "step": 98
+    },
+    {
+      "epoch": 0.07674418604651163,
+      "grad_norm": 8.858074188232422,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5188,
+      "step": 99
+    },
+    {
+      "epoch": 0.07674418604651163,
+      "eval_loss": 0.8598546385765076,
+      "eval_runtime": 118.2872,
+      "eval_samples_per_second": 9.181,
+      "eval_steps_per_second": 1.15,
+      "step": 99
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 6.341395854949951,
+      "learning_rate": 0.0,
+      "loss": 0.6626,
+      "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