Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7f3a9164960b2e8df28e9002ea252591447f2b023ac09472f56c39cdd15925
+oid sha256:f5fc293e32bb5d806cc549ac8342a24356ce56f3fcd715ff9b0722733dba8b44
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1336ef723de035475e1ad5a637d747db7f6fcef5da0e59af560cf6bdae18ffef
+oid sha256:5027a2e0919d5148b06ee532776f1fd0b9897d8f3b2213d28fad9d960dc1fa2c
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b959cb1ce422e3352f7139006f61ea00d94797d8f826a1d0563c117d182549
+oid sha256:d7b0d1dd889d1cacb63e1388e04729ce5594ed9e599ed42094887ad3a398c5f6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb15a5c4a887fb67eec53b267e92476bc5d195a8e876a263ade17c8374535c64
+oid sha256:bfb76b8fc6e352ec1088a1fc9b9c6a6e647aaf1135e78f3073bd00c98d516f34
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09277c658aac53de56a76c737235ffcec56e6d1ada247740097429f79a342cf
+oid sha256:1d304d574d14c6747825125ff28e70014eb966a1308d9d7c840cd4a065b555b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6585539bba2e47261c89e37f54fe8b8331de96f10b73c530b92078fd565040
+oid sha256:c9100b9be46c740e3929c103ad8c46624df47211a48c7fb0edb56f89845804b9
 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": 0.40540540540540543,
+  "epoch": 0.5405405405405406,
   "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": 0.3474,
       "step": 75
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 1.3155889511108398,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4488,
+      "step": 76
+    },
+    {
+      "epoch": 0.41621621621621624,
+      "grad_norm": 1.0786045789718628,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.3765,
+      "step": 77
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 0.9816880822181702,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3601,
+      "step": 78
+    },
+    {
+      "epoch": 0.42702702702702705,
+      "grad_norm": 0.9960786700248718,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4203,
+      "step": 79
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.9619646668434143,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3425,
+      "step": 80
+    },
+    {
+      "epoch": 0.43783783783783786,
+      "grad_norm": 0.9086030721664429,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.3099,
+      "step": 81
+    },
+    {
+      "epoch": 0.43783783783783786,
+      "eval_loss": 0.3269333839416504,
+      "eval_runtime": 8.9758,
+      "eval_samples_per_second": 69.409,
+      "eval_steps_per_second": 2.228,
+      "step": 81
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 0.9340605735778809,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2895,
+      "step": 82
+    },
+    {
+      "epoch": 0.4486486486486487,
+      "grad_norm": 0.7135784029960632,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2468,
+      "step": 83
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 1.1774721145629883,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3531,
+      "step": 84
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 1.4632771015167236,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4036,
+      "step": 85
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 0.9130470752716064,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3936,
+      "step": 86
+    },
+    {
+      "epoch": 0.4702702702702703,
+      "grad_norm": 0.9564059376716614,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3353,
+      "step": 87
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 1.0288338661193848,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.39,
+      "step": 88
+    },
+    {
+      "epoch": 0.4810810810810811,
+      "grad_norm": 1.2346181869506836,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2855,
+      "step": 89
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.8982526659965515,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3058,
+      "step": 90
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "eval_loss": 0.3246854543685913,
+      "eval_runtime": 8.9751,
+      "eval_samples_per_second": 69.414,
+      "eval_steps_per_second": 2.228,
+      "step": 90
+    },
+    {
+      "epoch": 0.4918918918918919,
+      "grad_norm": 0.9155553579330444,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3339,
+      "step": 91
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 0.945371150970459,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3147,
+      "step": 92
+    },
+    {
+      "epoch": 0.5027027027027027,
+      "grad_norm": 0.8307311534881592,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3373,
+      "step": 93
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 1.0141690969467163,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3083,
+      "step": 94
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.9042853116989136,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3374,
+      "step": 95
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 0.9358722567558289,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.3469,
+      "step": 96
+    },
+    {
+      "epoch": 0.5243243243243243,
+      "grad_norm": 0.968638002872467,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3897,
+      "step": 97
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 0.7917942404747009,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2807,
+      "step": 98
+    },
+    {
+      "epoch": 0.5351351351351351,
+      "grad_norm": 0.8780280351638794,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2534,
+      "step": 99
+    },
+    {
+      "epoch": 0.5351351351351351,
+      "eval_loss": 0.3240814805030823,
+      "eval_runtime": 8.9711,
+      "eval_samples_per_second": 69.445,
+      "eval_steps_per_second": 2.229,
+      "step": 99
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8242177963256836,
+      "learning_rate": 0.0,
+      "loss": 0.3189,
+      "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": 2.225661850681344e+17,
+  "total_flos": 2.967549134241792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null