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:f9160af0804bec34475815f42631e27b800fd19c04242c2ce15c1095a6d9ec56
+oid sha256:fc57e8875a69fda874934cd0cf8c7fe69161f91a339802d4542857a55b7394e3
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bade7744e6e97a7b031f341c33d2a22efb3f987ca31119f9677db3af1ca5d1a
+oid sha256:37c800931fabb301d5c07ea0f5bbede41be1396d8e7e44a39b46f1422b41c42d
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc53caa9ee29aa5549541f2de9dd6caf73aa7da168afdee6aa75fb8a93119dd
+oid sha256:683c5b74f6d2e341e31ce2acd3fc89f1cec37c36c36cefa6a5866c5a57186851
 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": 0.11914217633042097,
+  "epoch": 0.15885623510722796,
   "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": 0.8645,
       "step": 75
+    },
+    {
+      "epoch": 0.12073073868149325,
+      "grad_norm": 1.0505174398422241,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4891,
+      "step": 76
+    },
+    {
+      "epoch": 0.12231930103256553,
+      "grad_norm": 2.664303779602051,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8714,
+      "step": 77
+    },
+    {
+      "epoch": 0.12390786338363781,
+      "grad_norm": 6.456088066101074,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4106,
+      "step": 78
+    },
+    {
+      "epoch": 0.1254964257347101,
+      "grad_norm": 5.035181045532227,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1116,
+      "step": 79
+    },
+    {
+      "epoch": 0.12708498808578236,
+      "grad_norm": 1.2827062606811523,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6038,
+      "step": 80
+    },
+    {
+      "epoch": 0.12867355043685463,
+      "grad_norm": 1.571867823600769,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0119,
+      "step": 81
+    },
+    {
+      "epoch": 0.12867355043685463,
+      "eval_loss": 0.5474610328674316,
+      "eval_runtime": 25.0332,
+      "eval_samples_per_second": 21.172,
+      "eval_steps_per_second": 2.676,
+      "step": 81
+    },
+    {
+      "epoch": 0.13026211278792693,
+      "grad_norm": 2.406301736831665,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4819,
+      "step": 82
+    },
+    {
+      "epoch": 0.1318506751389992,
+      "grad_norm": 1.4583051204681396,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.7409,
+      "step": 83
+    },
+    {
+      "epoch": 0.13343923749007147,
+      "grad_norm": 1.6111057996749878,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6727,
+      "step": 84
+    },
+    {
+      "epoch": 0.13502779984114377,
+      "grad_norm": 1.4775164127349854,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4757,
+      "step": 85
+    },
+    {
+      "epoch": 0.13661636219221604,
+      "grad_norm": 2.2460825443267822,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.8622,
+      "step": 86
+    },
+    {
+      "epoch": 0.13820492454328834,
+      "grad_norm": 2.399625778198242,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.9663,
+      "step": 87
+    },
+    {
+      "epoch": 0.1397934868943606,
+      "grad_norm": 1.7391408681869507,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8286,
+      "step": 88
+    },
+    {
+      "epoch": 0.14138204924543288,
+      "grad_norm": 1.061781406402588,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.3296,
+      "step": 89
+    },
+    {
+      "epoch": 0.14297061159650518,
+      "grad_norm": 0.9983460903167725,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2936,
+      "step": 90
+    },
+    {
+      "epoch": 0.14297061159650518,
+      "eval_loss": 0.5319394469261169,
+      "eval_runtime": 24.9759,
+      "eval_samples_per_second": 21.22,
+      "eval_steps_per_second": 2.683,
+      "step": 90
+    },
+    {
+      "epoch": 0.14455917394757745,
+      "grad_norm": 1.3195279836654663,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4158,
+      "step": 91
+    },
+    {
+      "epoch": 0.14614773629864972,
+      "grad_norm": 1.5764867067337036,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9167,
+      "step": 92
+    },
+    {
+      "epoch": 0.14773629864972201,
+      "grad_norm": 1.1892976760864258,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2918,
+      "step": 93
+    },
+    {
+      "epoch": 0.14932486100079428,
+      "grad_norm": 1.2646450996398926,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.5086,
+      "step": 94
+    },
+    {
+      "epoch": 0.15091342335186655,
+      "grad_norm": 0.7004561424255371,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3725,
+      "step": 95
+    },
+    {
+      "epoch": 0.15250198570293885,
+      "grad_norm": 1.6172034740447998,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6218,
+      "step": 96
+    },
+    {
+      "epoch": 0.15409054805401112,
+      "grad_norm": 0.9688251614570618,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.4396,
+      "step": 97
+    },
+    {
+      "epoch": 0.1556791104050834,
+      "grad_norm": 1.4910237789154053,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6491,
+      "step": 98
+    },
+    {
+      "epoch": 0.1572676727561557,
+      "grad_norm": 2.0912060737609863,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.8586,
+      "step": 99
+    },
+    {
+      "epoch": 0.1572676727561557,
+      "eval_loss": 0.5280284881591797,
+      "eval_runtime": 24.9771,
+      "eval_samples_per_second": 21.219,
+      "eval_steps_per_second": 2.682,
+      "step": 99
+    },
+    {
+      "epoch": 0.15885623510722796,
+      "grad_norm": 0.985113263130188,
+      "learning_rate": 0.0,
+      "loss": 0.4754,
+      "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": 1.0306245365858304e+16,
+  "total_flos": 1.3499729845420032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null