Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7349131b1240f46542343dcda04bd0e14a15bd0ca9908d3f916e79bdf7ac6565
+oid sha256:5552a7727c27d82298d933b8b9e6b0a1f1f1820f5a8788d59053e0314e332041
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03cae6548ae4b16304c08e3a15fb4825bcdd59ee2d8f4ac6eec0fb9ac03e598
+oid sha256:e352aa71b9228722ff14c5ed7cb9dbb8b1c12faac03392b7f55a606b306f8fad
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbf52846b0950d1b0204ef5064ad518cb02596007e36540f5b060f1237792f0
+oid sha256:e5e6d6df32af28965e521ce09e49489f0f73a73e437d8780fef6228a2797f791
 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": 0.31982942430703626,
+  "epoch": 0.42643923240938164,
   "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": 0.3384,
       "step": 75
+    },
+    {
+      "epoch": 0.32409381663113007,
+      "grad_norm": 2.230226993560791,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4053,
+      "step": 76
+    },
+    {
+      "epoch": 0.3283582089552239,
+      "grad_norm": 2.071410655975342,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2676,
+      "step": 77
+    },
+    {
+      "epoch": 0.3326226012793177,
+      "grad_norm": 2.1903834342956543,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3557,
+      "step": 78
+    },
+    {
+      "epoch": 0.3368869936034115,
+      "grad_norm": 1.414023518562317,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3895,
+      "step": 79
+    },
+    {
+      "epoch": 0.3411513859275053,
+      "grad_norm": 2.7078359127044678,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4453,
+      "step": 80
+    },
+    {
+      "epoch": 0.34541577825159914,
+      "grad_norm": 3.0554823875427246,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.4786,
+      "step": 81
+    },
+    {
+      "epoch": 0.34541577825159914,
+      "eval_loss": 0.3989747166633606,
+      "eval_runtime": 10.3092,
+      "eval_samples_per_second": 19.206,
+      "eval_steps_per_second": 2.425,
+      "step": 81
+    },
+    {
+      "epoch": 0.34968017057569295,
+      "grad_norm": 2.796588897705078,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3151,
+      "step": 82
+    },
+    {
+      "epoch": 0.35394456289978676,
+      "grad_norm": 2.060140371322632,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3486,
+      "step": 83
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 2.0628552436828613,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5163,
+      "step": 84
+    },
+    {
+      "epoch": 0.3624733475479744,
+      "grad_norm": 2.8777129650115967,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5624,
+      "step": 85
+    },
+    {
+      "epoch": 0.36673773987206826,
+      "grad_norm": 2.5616040229797363,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6318,
+      "step": 86
+    },
+    {
+      "epoch": 0.37100213219616207,
+      "grad_norm": 2.548530340194702,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3601,
+      "step": 87
+    },
+    {
+      "epoch": 0.3752665245202559,
+      "grad_norm": 2.070634126663208,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5104,
+      "step": 88
+    },
+    {
+      "epoch": 0.3795309168443497,
+      "grad_norm": 1.8933154344558716,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.3162,
+      "step": 89
+    },
+    {
+      "epoch": 0.3837953091684435,
+      "grad_norm": 5.129238128662109,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2426,
+      "step": 90
+    },
+    {
+      "epoch": 0.3837953091684435,
+      "eval_loss": 0.39163798093795776,
+      "eval_runtime": 10.2858,
+      "eval_samples_per_second": 19.25,
+      "eval_steps_per_second": 2.431,
+      "step": 90
+    },
+    {
+      "epoch": 0.3880597014925373,
+      "grad_norm": 1.3959840536117554,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2662,
+      "step": 91
+    },
+    {
+      "epoch": 0.39232409381663114,
+      "grad_norm": 1.5999782085418701,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4021,
+      "step": 92
+    },
+    {
+      "epoch": 0.39658848614072495,
+      "grad_norm": 1.681472659111023,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.323,
+      "step": 93
+    },
+    {
+      "epoch": 0.40085287846481876,
+      "grad_norm": 1.872139811515808,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3603,
+      "step": 94
+    },
+    {
+      "epoch": 0.4051172707889126,
+      "grad_norm": 1.6787221431732178,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3002,
+      "step": 95
+    },
+    {
+      "epoch": 0.4093816631130064,
+      "grad_norm": 1.6023163795471191,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4431,
+      "step": 96
+    },
+    {
+      "epoch": 0.4136460554371002,
+      "grad_norm": 5.4748125076293945,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.6219,
+      "step": 97
+    },
+    {
+      "epoch": 0.417910447761194,
+      "grad_norm": 3.0397448539733887,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3617,
+      "step": 98
+    },
+    {
+      "epoch": 0.42217484008528783,
+      "grad_norm": 2.4502100944519043,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4726,
+      "step": 99
+    },
+    {
+      "epoch": 0.42217484008528783,
+      "eval_loss": 0.3900476396083832,
+      "eval_runtime": 10.2861,
+      "eval_samples_per_second": 19.249,
+      "eval_steps_per_second": 2.43,
+      "step": 99
+    },
+    {
+      "epoch": 0.42643923240938164,
+      "grad_norm": 2.7998695373535156,
+      "learning_rate": 0.0,
+      "loss": 0.591,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.455967199782502e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null