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:bc6be646f75e52d433d1eaa9ab9fb47a06ab36db6d03b331a64a36d223bb9a00
+oid sha256:b17865dffaa128d7342c6050853b741e166d439b298cdce40e6154de90c3c037
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b3e536f2055e9bb35676d2b4d438fc49edd6e466f6341bbdb2f5d4fcd405e5
+oid sha256:9083e8d590d6d9d1dbf8e89d55e8327be781f07d22e33908bd872d86e3279ef4
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
+oid sha256:c659e4505005131eab7ea0ee74ff9e2fee448c1f7e5a9dc766af93a6f64c72a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26501766784452296,
+  "epoch": 0.35335689045936397,
   "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": 3.5721239031346067e-06,
       "loss": 3.1231,
       "step": 75
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 3.529139757156372,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 3.1566,
+      "step": 76
+    },
+    {
+      "epoch": 0.27208480565371024,
+      "grad_norm": 3.4794118404388428,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 3.4272,
+      "step": 77
+    },
+    {
+      "epoch": 0.2756183745583039,
+      "grad_norm": 3.51943039894104,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 3.1396,
+      "step": 78
+    },
+    {
+      "epoch": 0.2791519434628975,
+      "grad_norm": 3.0890696048736572,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 2.9279,
+      "step": 79
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 3.705535888671875,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 3.3905,
+      "step": 80
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "grad_norm": 3.2892282009124756,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 2.9052,
+      "step": 81
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "eval_loss": 3.1131207942962646,
+      "eval_runtime": 7.1679,
+      "eval_samples_per_second": 33.343,
+      "eval_steps_per_second": 4.185,
+      "step": 81
+    },
+    {
+      "epoch": 0.28975265017667845,
+      "grad_norm": 3.7099380493164062,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 3.3264,
+      "step": 82
+    },
+    {
+      "epoch": 0.29328621908127206,
+      "grad_norm": 3.6428582668304443,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 3.3048,
+      "step": 83
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 3.505910873413086,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 3.1878,
+      "step": 84
+    },
+    {
+      "epoch": 0.3003533568904594,
+      "grad_norm": 3.2558436393737793,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 3.1286,
+      "step": 85
+    },
+    {
+      "epoch": 0.303886925795053,
+      "grad_norm": 3.377671241760254,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 3.297,
+      "step": 86
+    },
+    {
+      "epoch": 0.30742049469964666,
+      "grad_norm": 3.550931215286255,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 3.0584,
+      "step": 87
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 3.6695592403411865,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 3.1337,
+      "step": 88
+    },
+    {
+      "epoch": 0.31448763250883394,
+      "grad_norm": 3.8914008140563965,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 3.04,
+      "step": 89
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "grad_norm": 3.7432496547698975,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 3.2667,
+      "step": 90
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "eval_loss": 3.1055989265441895,
+      "eval_runtime": 7.176,
+      "eval_samples_per_second": 33.306,
+      "eval_steps_per_second": 4.181,
+      "step": 90
+    },
+    {
+      "epoch": 0.3215547703180212,
+      "grad_norm": 3.9864752292633057,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 3.2459,
+      "step": 91
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 3.2838871479034424,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 3.2282,
+      "step": 92
+    },
+    {
+      "epoch": 0.3286219081272085,
+      "grad_norm": 3.8689634799957275,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 3.3922,
+      "step": 93
+    },
+    {
+      "epoch": 0.3321554770318021,
+      "grad_norm": 3.352163076400757,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 3.1316,
+      "step": 94
+    },
+    {
+      "epoch": 0.33568904593639576,
+      "grad_norm": 2.9623937606811523,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 2.8593,
+      "step": 95
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 3.628258228302002,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 3.0653,
+      "step": 96
+    },
+    {
+      "epoch": 0.34275618374558303,
+      "grad_norm": 3.236924409866333,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 3.151,
+      "step": 97
+    },
+    {
+      "epoch": 0.3462897526501767,
+      "grad_norm": 3.264038324356079,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 2.9987,
+      "step": 98
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "grad_norm": 3.5730013847351074,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 3.0237,
+      "step": 99
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "eval_loss": 3.10420298576355,
+      "eval_runtime": 7.1746,
+      "eval_samples_per_second": 33.312,
+      "eval_steps_per_second": 4.181,
+      "step": 99
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 3.5553343296051025,
+      "learning_rate": 0.0,
+      "loss": 3.1938,
+      "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": 7257919271731200.0,
+  "total_flos": 9677225695641600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null