Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1959b3335278ace412114b0114f6ddf6de6380d7c0d01aa0aa3b8ef871e14d48
+oid sha256:b7ffd8ab716d666fbe9743a18f54ee7eb4d8481d6b45cd6b685ccc796b00ee1e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bad131895d8e088d7d1867cde7fed1f1b3144796be3221fc32f6dca85a74aaa
+oid sha256:e914df3af04755314868059334ffd3ed6ffd9a128c8cf38d2d3af1aceec7c882
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362e47b9c7f4c81a932ce61c95e2004dd7905ca651b0db7df255ead2a22b60ed
+oid sha256:10f7d606fa6c707d17d9396c90838ec833ccc163b2d1c549e4a4e253a2de833f
 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": 0.004655637977590862,
+  "epoch": 0.006207517303454483,
   "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": 0.1884,
       "step": 75
+    },
+    {
+      "epoch": 0.004717713150625407,
+      "grad_norm": 0.5349669456481934,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1454,
+      "step": 76
+    },
+    {
+      "epoch": 0.004779788323659952,
+      "grad_norm": 0.8816052079200745,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1014,
+      "step": 77
+    },
+    {
+      "epoch": 0.004841863496694497,
+      "grad_norm": 1.5665334463119507,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1759,
+      "step": 78
+    },
+    {
+      "epoch": 0.004903938669729042,
+      "grad_norm": 1.1516512632369995,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2133,
+      "step": 79
+    },
+    {
+      "epoch": 0.004966013842763586,
+      "grad_norm": 0.9246344566345215,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1827,
+      "step": 80
+    },
+    {
+      "epoch": 0.005028089015798131,
+      "grad_norm": 0.7256326675415039,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0897,
+      "step": 81
+    },
+    {
+      "epoch": 0.005028089015798131,
+      "eval_loss": 0.17462599277496338,
+      "eval_runtime": 2236.3863,
+      "eval_samples_per_second": 6.066,
+      "eval_steps_per_second": 0.758,
+      "step": 81
+    },
+    {
+      "epoch": 0.005090164188832676,
+      "grad_norm": 1.1471014022827148,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1784,
+      "step": 82
+    },
+    {
+      "epoch": 0.005152239361867221,
+      "grad_norm": 0.6445525288581848,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1625,
+      "step": 83
+    },
+    {
+      "epoch": 0.005214314534901766,
+      "grad_norm": 0.9093417525291443,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1404,
+      "step": 84
+    },
+    {
+      "epoch": 0.0052763897079363105,
+      "grad_norm": 0.9778578281402588,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1453,
+      "step": 85
+    },
+    {
+      "epoch": 0.0053384648809708555,
+      "grad_norm": 1.2823891639709473,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2318,
+      "step": 86
+    },
+    {
+      "epoch": 0.0054005400540054005,
+      "grad_norm": 0.6436693668365479,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1107,
+      "step": 87
+    },
+    {
+      "epoch": 0.0054626152270399455,
+      "grad_norm": 1.4560965299606323,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2796,
+      "step": 88
+    },
+    {
+      "epoch": 0.0055246904000744905,
+      "grad_norm": 0.8489173054695129,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1177,
+      "step": 89
+    },
+    {
+      "epoch": 0.005586765573109035,
+      "grad_norm": 0.9858618974685669,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1779,
+      "step": 90
+    },
+    {
+      "epoch": 0.005586765573109035,
+      "eval_loss": 0.17215199768543243,
+      "eval_runtime": 2237.2776,
+      "eval_samples_per_second": 6.064,
+      "eval_steps_per_second": 0.758,
+      "step": 90
+    },
+    {
+      "epoch": 0.00564884074614358,
+      "grad_norm": 1.120463490486145,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2531,
+      "step": 91
+    },
+    {
+      "epoch": 0.005710915919178125,
+      "grad_norm": 1.1673436164855957,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1362,
+      "step": 92
+    },
+    {
+      "epoch": 0.00577299109221267,
+      "grad_norm": 1.2356417179107666,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2066,
+      "step": 93
+    },
+    {
+      "epoch": 0.005835066265247215,
+      "grad_norm": 0.9142425656318665,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1632,
+      "step": 94
+    },
+    {
+      "epoch": 0.005897141438281759,
+      "grad_norm": 0.9412080645561218,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1884,
+      "step": 95
+    },
+    {
+      "epoch": 0.005959216611316304,
+      "grad_norm": 1.1272531747817993,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1681,
+      "step": 96
+    },
+    {
+      "epoch": 0.006021291784350849,
+      "grad_norm": 1.020373821258545,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2634,
+      "step": 97
+    },
+    {
+      "epoch": 0.006083366957385394,
+      "grad_norm": 0.8609936833381653,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1496,
+      "step": 98
+    },
+    {
+      "epoch": 0.006145442130419939,
+      "grad_norm": 0.7480646967887878,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2058,
+      "step": 99
+    },
+    {
+      "epoch": 0.006145442130419939,
+      "eval_loss": 0.17152301967144012,
+      "eval_runtime": 2237.397,
+      "eval_samples_per_second": 6.063,
+      "eval_steps_per_second": 0.758,
+      "step": 99
+    },
+    {
+      "epoch": 0.006207517303454483,
+      "grad_norm": 0.8420364260673523,
+      "learning_rate": 0.0,
+      "loss": 0.173,
+      "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": 8.160760119164928e+16,
+  "total_flos": 1.1091214889228698e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null