Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5a164617ca722b42e5e8fde3cd78a5eeb9ffce771943ce6f896040ef2f01ee
+oid sha256:eecee29d9731759bd50a860f7abbaab1f719bb5fa75205cbdbfcd87671c33b25
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4aff18958ef755e9c9a3a6e411d0b54cab17885e9b052cf881802ab6dbafbf
+oid sha256:bb53f1ce3bfcf0f0ed876017265d50aad0be30244a680bc081198af7c636c9a4
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c86b8cb9cf7d4aa12029d2c56f7ad5767a9d9029213bbbd55c9ff2f0cad5bf
+oid sha256:ee835b1b5466b4de2c4ddef4b908a309d122dcf6a40bd09f1f262cba8937c427
 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": 0.023302780798508622,
+  "epoch": 0.031070374398011497,
   "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": 0.0717,
       "step": 75
+    },
+    {
+      "epoch": 0.02361348454248874,
+      "grad_norm": 0.40439170598983765,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1148,
+      "step": 76
+    },
+    {
+      "epoch": 0.02392418828646885,
+      "grad_norm": 0.628427267074585,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0704,
+      "step": 77
+    },
+    {
+      "epoch": 0.024234892030448967,
+      "grad_norm": 0.5532355308532715,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0994,
+      "step": 78
+    },
+    {
+      "epoch": 0.024545595774429083,
+      "grad_norm": 0.18102148175239563,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0508,
+      "step": 79
+    },
+    {
+      "epoch": 0.024856299518409196,
+      "grad_norm": 0.28862491250038147,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0626,
+      "step": 80
+    },
+    {
+      "epoch": 0.025167003262389312,
+      "grad_norm": 0.44811418652534485,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0762,
+      "step": 81
+    },
+    {
+      "epoch": 0.025167003262389312,
+      "eval_loss": 0.09211050719022751,
+      "eval_runtime": 476.7462,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 0.711,
+      "step": 81
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 0.2729843854904175,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0549,
+      "step": 82
+    },
+    {
+      "epoch": 0.02578841075034954,
+      "grad_norm": 0.4627554416656494,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1649,
+      "step": 83
+    },
+    {
+      "epoch": 0.026099114494329657,
+      "grad_norm": 0.2735048234462738,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0503,
+      "step": 84
+    },
+    {
+      "epoch": 0.026409818238309773,
+      "grad_norm": 0.45912477374076843,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0694,
+      "step": 85
+    },
+    {
+      "epoch": 0.026720521982289885,
+      "grad_norm": 0.2504335641860962,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0768,
+      "step": 86
+    },
+    {
+      "epoch": 0.02703122572627,
+      "grad_norm": 0.5822497010231018,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0832,
+      "step": 87
+    },
+    {
+      "epoch": 0.027341929470250118,
+      "grad_norm": 0.4059930443763733,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0662,
+      "step": 88
+    },
+    {
+      "epoch": 0.02765263321423023,
+      "grad_norm": 0.3446873724460602,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0653,
+      "step": 89
+    },
+    {
+      "epoch": 0.027963336958210346,
+      "grad_norm": 0.5446871519088745,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1038,
+      "step": 90
+    },
+    {
+      "epoch": 0.027963336958210346,
+      "eval_loss": 0.0907156765460968,
+      "eval_runtime": 476.7657,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 0.711,
+      "step": 90
+    },
+    {
+      "epoch": 0.028274040702190462,
+      "grad_norm": 0.28611159324645996,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0804,
+      "step": 91
+    },
+    {
+      "epoch": 0.028584744446170575,
+      "grad_norm": 0.526472270488739,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0755,
+      "step": 92
+    },
+    {
+      "epoch": 0.02889544819015069,
+      "grad_norm": 0.2932213842868805,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1271,
+      "step": 93
+    },
+    {
+      "epoch": 0.029206151934130807,
+      "grad_norm": 0.4505036771297455,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0581,
+      "step": 94
+    },
+    {
+      "epoch": 0.02951685567811092,
+      "grad_norm": 0.37807580828666687,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0832,
+      "step": 95
+    },
+    {
+      "epoch": 0.029827559422091036,
+      "grad_norm": 0.41597023606300354,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1158,
+      "step": 96
+    },
+    {
+      "epoch": 0.030138263166071152,
+      "grad_norm": 0.5798332095146179,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3012,
+      "step": 97
+    },
+    {
+      "epoch": 0.030448966910051264,
+      "grad_norm": 0.22657930850982666,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0659,
+      "step": 98
+    },
+    {
+      "epoch": 0.03075967065403138,
+      "grad_norm": 0.23417678475379944,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0867,
+      "step": 99
+    },
+    {
+      "epoch": 0.03075967065403138,
+      "eval_loss": 0.09054123610258102,
+      "eval_runtime": 476.6412,
+      "eval_samples_per_second": 5.688,
+      "eval_steps_per_second": 0.711,
+      "step": 99
+    },
+    {
+      "epoch": 0.031070374398011497,
+      "grad_norm": 0.29348117113113403,
+      "learning_rate": 0.0,
+      "loss": 0.07,
+      "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": 3.407936228425728e+16,
+  "total_flos": 4.5274515111936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null