Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276a6d7f86d22c2b0c0336a5763ec4bb234ca78b3de4d34bda482c1864bea0f9
+oid sha256:638d4e6ee654cc01449833eacc7cff29c40761e25395ab03441e4aa89341c18d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e2391a6305b3e29866f3872b4a667db148a7493a2506e4705154cd0e97722c1
+oid sha256:f7345feecac021092d9ef22fb64e2741bff4718ff241369f476f80eee66f37ee
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb9ef2265dcea400f3cd5547b7a7062cbfb845056640507022af41494f5666d
+oid sha256:db37e9ba5d67b2d9cdd5da3b994e82414b34dc0739ad1f1b22e6585f852877f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002140033063510831,
+  "epoch": 0.003210049595266247,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.978,
       "eval_steps_per_second": 1.989,
       "step": 50
+    },
+    {
+      "epoch": 0.002182833724781048,
+      "grad_norm": 2.7450528144836426,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2259,
+      "step": 51
+    },
+    {
+      "epoch": 0.0022256343860512645,
+      "grad_norm": 2.8521487712860107,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.1781,
+      "step": 52
+    },
+    {
+      "epoch": 0.002268435047321481,
+      "grad_norm": 2.500920534133911,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.1848,
+      "step": 53
+    },
+    {
+      "epoch": 0.002311235708591698,
+      "grad_norm": 2.4444034099578857,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1917,
+      "step": 54
+    },
+    {
+      "epoch": 0.0023540363698619144,
+      "grad_norm": 2.5305259227752686,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1816,
+      "step": 55
+    },
+    {
+      "epoch": 0.002396837031132131,
+      "grad_norm": 2.042140007019043,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.1032,
+      "step": 56
+    },
+    {
+      "epoch": 0.0024396376924023474,
+      "grad_norm": 1.2077791690826416,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0627,
+      "step": 57
+    },
+    {
+      "epoch": 0.0024824383536725643,
+      "grad_norm": 0.5527344346046448,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0343,
+      "step": 58
+    },
+    {
+      "epoch": 0.002525239014942781,
+      "grad_norm": 1.0725934505462646,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0795,
+      "step": 59
+    },
+    {
+      "epoch": 0.0025680396762129973,
+      "grad_norm": 1.7582429647445679,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0996,
+      "step": 60
+    },
+    {
+      "epoch": 0.0026108403374832142,
+      "grad_norm": 1.7188550233840942,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0881,
+      "step": 61
+    },
+    {
+      "epoch": 0.0026536409987534307,
+      "grad_norm": 0.7734795212745667,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0452,
+      "step": 62
+    },
+    {
+      "epoch": 0.0026964416600236472,
+      "grad_norm": 2.1274631023406982,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0967,
+      "step": 63
+    },
+    {
+      "epoch": 0.002739242321293864,
+      "grad_norm": 0.8547139763832092,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0528,
+      "step": 64
+    },
+    {
+      "epoch": 0.0027820429825640806,
+      "grad_norm": 1.9717649221420288,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0956,
+      "step": 65
+    },
+    {
+      "epoch": 0.002824843643834297,
+      "grad_norm": 1.0732667446136475,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0824,
+      "step": 66
+    },
+    {
+      "epoch": 0.002867644305104514,
+      "grad_norm": 1.1208678483963013,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0608,
+      "step": 67
+    },
+    {
+      "epoch": 0.0029104449663747306,
+      "grad_norm": 1.1556836366653442,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0524,
+      "step": 68
+    },
+    {
+      "epoch": 0.002953245627644947,
+      "grad_norm": 1.502225637435913,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0752,
+      "step": 69
+    },
+    {
+      "epoch": 0.0029960462889151635,
+      "grad_norm": 1.142922282218933,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0598,
+      "step": 70
+    },
+    {
+      "epoch": 0.0030388469501853805,
+      "grad_norm": 0.8057124018669128,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0576,
+      "step": 71
+    },
+    {
+      "epoch": 0.003081647611455597,
+      "grad_norm": 0.6891778111457825,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0509,
+      "step": 72
+    },
+    {
+      "epoch": 0.0031244482727258134,
+      "grad_norm": 1.7224620580673218,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0568,
+      "step": 73
+    },
+    {
+      "epoch": 0.0031672489339960304,
+      "grad_norm": 1.9783501625061035,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0893,
+      "step": 74
+    },
+    {
+      "epoch": 0.003210049595266247,
+      "grad_norm": 0.829711377620697,
+      "learning_rate": 0.0,
+      "loss": 0.0608,
+      "step": 75
+    },
+    {
+      "epoch": 0.003210049595266247,
+      "eval_loss": 0.0819869264960289,
+      "eval_runtime": 4946.3978,
+      "eval_samples_per_second": 3.978,
+      "eval_steps_per_second": 1.989,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.46023337066496e+16,
+  "total_flos": 1.119035005599744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null