Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3710f0f60bd7cb6d058599a45e570639c4865376c83b083bbf0de2dee1fece99
+oid sha256:ab050c705f31c7f6e7b2e4ce0d4092b71c527c8e48382465f0e7532772153134
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ea9811620bc91214637c7826f5264ae6c0b2007b883076f881753ba290959f
+oid sha256:400bed4bf1e4accbeb1451761e6b1d11cec0733ca35952d75ee017a66c0ee3da
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94a20eee85d5c75b63ebc4d8909f64f2d180c1f85b77b7d16b1c4617b766e1e
+oid sha256:7abb8be9b7e34b0517b1cfde1b5ad52c427b185651234e90b51dab71914b7ad3
 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": 0.11303692539562923,
+  "epoch": 0.15071590052750566,
   "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": 0.1735,
       "step": 75
+    },
+    {
+      "epoch": 0.1145440844009043,
+      "grad_norm": 0.364891916513443,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.07,
+      "step": 76
+    },
+    {
+      "epoch": 0.11605124340617935,
+      "grad_norm": 0.5485689640045166,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.23,
+      "step": 77
+    },
+    {
+      "epoch": 0.1175584024114544,
+      "grad_norm": 0.6924117803573608,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0649,
+      "step": 78
+    },
+    {
+      "epoch": 0.11906556141672947,
+      "grad_norm": 0.40422847867012024,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1353,
+      "step": 79
+    },
+    {
+      "epoch": 0.12057272042200452,
+      "grad_norm": 0.3907949924468994,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12207987942727958,
+      "grad_norm": 0.4222213327884674,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0848,
+      "step": 81
+    },
+    {
+      "epoch": 0.12207987942727958,
+      "eval_loss": 0.14018893241882324,
+      "eval_runtime": 123.5822,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.566,
+      "step": 81
+    },
+    {
+      "epoch": 0.12358703843255464,
+      "grad_norm": 0.6123594045639038,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1254,
+      "step": 82
+    },
+    {
+      "epoch": 0.12509419743782968,
+      "grad_norm": 0.3415692448616028,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0581,
+      "step": 83
+    },
+    {
+      "epoch": 0.12660135644310475,
+      "grad_norm": 0.6530345678329468,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1209,
+      "step": 84
+    },
+    {
+      "epoch": 0.1281085154483798,
+      "grad_norm": 1.1032772064208984,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2231,
+      "step": 85
+    },
+    {
+      "epoch": 0.12961567445365485,
+      "grad_norm": 0.5108954310417175,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0894,
+      "step": 86
+    },
+    {
+      "epoch": 0.13112283345892992,
+      "grad_norm": 2.216198444366455,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0951,
+      "step": 87
+    },
+    {
+      "epoch": 0.13262999246420498,
+      "grad_norm": 0.738016664981842,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2348,
+      "step": 88
+    },
+    {
+      "epoch": 0.13413715146948002,
+      "grad_norm": 0.3426017761230469,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1023,
+      "step": 89
+    },
+    {
+      "epoch": 0.1356443104747551,
+      "grad_norm": 0.5057233572006226,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1386,
+      "step": 90
+    },
+    {
+      "epoch": 0.1356443104747551,
+      "eval_loss": 0.140176922082901,
+      "eval_runtime": 123.5635,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.567,
+      "step": 90
+    },
+    {
+      "epoch": 0.13715146948003015,
+      "grad_norm": 0.47616341710090637,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1072,
+      "step": 91
+    },
+    {
+      "epoch": 0.1386586284853052,
+      "grad_norm": 3.395482063293457,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2067,
+      "step": 92
+    },
+    {
+      "epoch": 0.14016578749058026,
+      "grad_norm": 0.8365815281867981,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1928,
+      "step": 93
+    },
+    {
+      "epoch": 0.14167294649585532,
+      "grad_norm": 0.963044285774231,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1393,
+      "step": 94
+    },
+    {
+      "epoch": 0.14318010550113036,
+      "grad_norm": 0.3439726233482361,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0857,
+      "step": 95
+    },
+    {
+      "epoch": 0.14468726450640543,
+      "grad_norm": 0.44376206398010254,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1651,
+      "step": 96
+    },
+    {
+      "epoch": 0.1461944235116805,
+      "grad_norm": 0.4902697801589966,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0953,
+      "step": 97
+    },
+    {
+      "epoch": 0.14770158251695553,
+      "grad_norm": 0.3958795666694641,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0834,
+      "step": 98
+    },
+    {
+      "epoch": 0.1492087415222306,
+      "grad_norm": 2.75736141204834,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4029,
+      "step": 99
+    },
+    {
+      "epoch": 0.1492087415222306,
+      "eval_loss": 0.13978636264801025,
+      "eval_runtime": 123.6077,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 0.566,
+      "step": 99
+    },
+    {
+      "epoch": 0.15071590052750566,
+      "grad_norm": 0.4361518323421478,
+      "learning_rate": 0.0,
+      "loss": 0.1838,
+      "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": 1.1091214889228698e+17,
+  "total_flos": 1.4800651307030938e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null