Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800a221cdb032e45a8bd2c9252d45346f8bac88283096ccb64ee19fbedbb2e1f
+oid sha256:94508ac1228afb3d4dae69f869382ccbe0ff82d53faef523521007645dc12e5f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4d541c73b2519c8d4aa5c0b4922d2663184818805a873fe7c1d6e270014d7b
+oid sha256:ac785f8ee69c762f15defd1e38a221314a78f9417ac319d9dbfac9c0daf496a9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a27d6b7e0aba23d28b8905a8d125597ac8cadad29659fb1b9e759bed6a8b6e01
+oid sha256:8beef2f1b537938308fd5e902a63732fe8bcd0d3f9ce197fd2aad02dfb81c554
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06958942240779402,
+  "epoch": 0.13917884481558804,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.07237299930410578,
+      "grad_norm": 0.004986815620213747,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.07515657620041753,
+      "grad_norm": 0.014825048856437206,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0001,
+      "step": 27
+    },
+    {
+      "epoch": 0.0779401530967293,
+      "grad_norm": 0.020950036123394966,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.08072372999304106,
+      "grad_norm": 0.010169435292482376,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.08350730688935282,
+      "grad_norm": 0.005563807673752308,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08629088378566457,
+      "grad_norm": 0.0033290411811321974,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.08907446068197634,
+      "grad_norm": 0.0016648604068905115,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0918580375782881,
+      "grad_norm": 0.0010142697719857097,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.09464161447459986,
+      "grad_norm": 0.00054915965301916,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.09742519137091162,
+      "grad_norm": 0.00043891073437407613,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.10020876826722339,
+      "grad_norm": 0.00028968678088858724,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.10299234516353514,
+      "grad_norm": 0.0002959763223771006,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.1057759220598469,
+      "grad_norm": 0.00021965286578051746,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.10855949895615867,
+      "grad_norm": 0.00015132376574911177,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.11134307585247043,
+      "grad_norm": 0.3647041320800781,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.002,
+      "step": 40
+    },
+    {
+      "epoch": 0.11412665274878218,
+      "grad_norm": 9.909908112604171e-05,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.11691022964509394,
+      "grad_norm": 0.00010844790085684508,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.11969380654140571,
+      "grad_norm": 8.147337939590216e-05,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.12247738343771747,
+      "grad_norm": 2.1904272216488607e-05,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.12526096033402923,
+      "grad_norm": 4.966600681655109e-05,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.12804453723034098,
+      "grad_norm": 9.887644409900531e-05,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.13082811412665274,
+      "grad_norm": 7.535777695011348e-05,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.1336116910229645,
+      "grad_norm": 3.8577378290938213e-05,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.13639526791927628,
+      "grad_norm": 6.952096737222746e-05,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.13917884481558804,
+      "grad_norm": 7.99436165834777e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.820719510336307e+16,
+  "total_flos": 7.56725029231657e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null