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:c650d3f9fb380ab4d4255dcf9d76cf4c7cd8fb2b5867e22a35cb4ff4117b0ae3
+oid sha256:2d4bad51f01fbb8af14a6fa1353839050dac28485445f35d86f8288b7b3ecd3b
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081b9dc8bf4ab091b90f9b4715602f915d877f1cb71479341882a2845a4858e4
+oid sha256:1210cec36a4ba03876b2a3616d89a451294dfc6ea0c5b0a1d98446752bf43d0d
 size 101184122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24e3a0867bbf92caf301a1a20f0c479bf5c2ee6a8517aa42c8c178899c99e09
+oid sha256:1dd99024d71f36350cbca2375c975db5253f1d1d80766e6eb1cf2b9bbed532df
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bf25ccae0a235b7172a6f610240e23300cd6029de801e81c7a5b125f2c4141
+oid sha256:be584329eaa42c4d42bce34fa9a6b6bb8bacdd00159010cce1cacdd4c57d6228
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084c7b5235ce94c3a9317566f0b85e771c642e908ed595c6c85e016ecbd54cbe
+oid sha256:46e26e6e12385670e316b4019cb9b7eadb06712cabd708ed2a0aac2a55822615
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f1b7fec83cfa2275e83b573eeec59b026efef3468e1637ebb2892b10515187
+oid sha256:9f075fae3899370ff48d5b512a1ca2ab8c7253583bb08887b2c80db9aa5efef7
 size 15024

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": 0.09797517962116264,
+  "epoch": 0.13063357282821686,
   "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": 0.9716,
       "step": 75
+    },
+    {
+      "epoch": 0.09928151534944481,
+      "grad_norm": 0.31112876534461975,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9679,
+      "step": 76
+    },
+    {
+      "epoch": 0.10058785107772697,
+      "grad_norm": 0.2868760824203491,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.9714,
+      "step": 77
+    },
+    {
+      "epoch": 0.10189418680600915,
+      "grad_norm": 0.2732284963130951,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0294,
+      "step": 78
+    },
+    {
+      "epoch": 0.10320052253429131,
+      "grad_norm": 0.3132527768611908,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.9823,
+      "step": 79
+    },
+    {
+      "epoch": 0.10450685826257348,
+      "grad_norm": 0.34114107489585876,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0015,
+      "step": 80
+    },
+    {
+      "epoch": 0.10581319399085565,
+      "grad_norm": 0.3598445653915405,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0128,
+      "step": 81
+    },
+    {
+      "epoch": 0.10581319399085565,
+      "eval_loss": 0.9954747557640076,
+      "eval_runtime": 9.4558,
+      "eval_samples_per_second": 272.636,
+      "eval_steps_per_second": 8.566,
+      "step": 81
+    },
+    {
+      "epoch": 0.10711952971913782,
+      "grad_norm": 0.286565899848938,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9809,
+      "step": 82
+    },
+    {
+      "epoch": 0.10842586544741999,
+      "grad_norm": 0.3290863037109375,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0103,
+      "step": 83
+    },
+    {
+      "epoch": 0.10973220117570215,
+      "grad_norm": 0.29899007081985474,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9652,
+      "step": 84
+    },
+    {
+      "epoch": 0.11103853690398433,
+      "grad_norm": 0.3017849922180176,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0355,
+      "step": 85
+    },
+    {
+      "epoch": 0.11234487263226649,
+      "grad_norm": 0.30627602338790894,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0068,
+      "step": 86
+    },
+    {
+      "epoch": 0.11365120836054866,
+      "grad_norm": 0.29219281673431396,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0003,
+      "step": 87
+    },
+    {
+      "epoch": 0.11495754408883083,
+      "grad_norm": 0.29773980379104614,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0151,
+      "step": 88
+    },
+    {
+      "epoch": 0.116263879817113,
+      "grad_norm": 0.276870995759964,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.9312,
+      "step": 89
+    },
+    {
+      "epoch": 0.11757021554539517,
+      "grad_norm": 0.2851667106151581,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0124,
+      "step": 90
+    },
+    {
+      "epoch": 0.11757021554539517,
+      "eval_loss": 0.9941932559013367,
+      "eval_runtime": 9.4226,
+      "eval_samples_per_second": 273.599,
+      "eval_steps_per_second": 8.596,
+      "step": 90
+    },
+    {
+      "epoch": 0.11887655127367734,
+      "grad_norm": 0.2754754424095154,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9848,
+      "step": 91
+    },
+    {
+      "epoch": 0.1201828870019595,
+      "grad_norm": 0.30135542154312134,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9696,
+      "step": 92
+    },
+    {
+      "epoch": 0.12148922273024167,
+      "grad_norm": 0.36859849095344543,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0371,
+      "step": 93
+    },
+    {
+      "epoch": 0.12279555845852384,
+      "grad_norm": 0.28066200017929077,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9595,
+      "step": 94
+    },
+    {
+      "epoch": 0.124101894186806,
+      "grad_norm": 0.28233689069747925,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.0157,
+      "step": 95
+    },
+    {
+      "epoch": 0.12540822991508818,
+      "grad_norm": 0.27524614334106445,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0362,
+      "step": 96
+    },
+    {
+      "epoch": 0.12671456564337036,
+      "grad_norm": 0.3097120523452759,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.995,
+      "step": 97
+    },
+    {
+      "epoch": 0.1280209013716525,
+      "grad_norm": 0.2737129330635071,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.9566,
+      "step": 98
+    },
+    {
+      "epoch": 0.12932723709993468,
+      "grad_norm": 0.3093501925468445,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0087,
+      "step": 99
+    },
+    {
+      "epoch": 0.12932723709993468,
+      "eval_loss": 0.9940328598022461,
+      "eval_runtime": 9.4334,
+      "eval_samples_per_second": 273.283,
+      "eval_steps_per_second": 8.586,
+      "step": 99
+    },
+    {
+      "epoch": 0.13063357282821686,
+      "grad_norm": 0.3667088449001312,
+      "learning_rate": 0.0,
+      "loss": 1.0538,
+      "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": 3.08810631610368e+16,
+  "total_flos": 4.11747508813824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null