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:e77badc499f4ac13721ce0904abad8ea9447eefae5d159acc171bd0ab1702980
+oid sha256:66c47a636952d4d117df27da8ed3200397b85fd4511b3e0cde7da6f4343319aa
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3252ff189c952572ff07e6421b11f704323aff3e5d87b7bb4619ae02a476ec1
+oid sha256:a42eb0f14fdc3bcd63411d735859b60d74635a1c1a63f9b277e34662af0e9ad7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58b155e5123c7f1976665fc15d0993b62f2994fac0848287641211bae5ae5bc
+oid sha256:d665228d5c674a5322354b2cbabcdb77447213d0273363aa47e9189b164a4bf9
 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": 0.12886597938144329,
+  "epoch": 0.1718213058419244,
   "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": 1.0416,
       "step": 75
+    },
+    {
+      "epoch": 0.13058419243986255,
+      "grad_norm": 0.6408966779708862,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1461,
+      "step": 76
+    },
+    {
+      "epoch": 0.1323024054982818,
+      "grad_norm": 0.7367373704910278,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.2142,
+      "step": 77
+    },
+    {
+      "epoch": 0.13402061855670103,
+      "grad_norm": 0.6621880531311035,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.1731,
+      "step": 78
+    },
+    {
+      "epoch": 0.13573883161512026,
+      "grad_norm": 0.6764753460884094,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0846,
+      "step": 79
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 0.6529674530029297,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0734,
+      "step": 80
+    },
+    {
+      "epoch": 0.13917525773195877,
+      "grad_norm": 0.6741594076156616,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0207,
+      "step": 81
+    },
+    {
+      "epoch": 0.13917525773195877,
+      "eval_loss": 0.5421542525291443,
+      "eval_runtime": 89.6291,
+      "eval_samples_per_second": 5.467,
+      "eval_steps_per_second": 0.692,
+      "step": 81
+    },
+    {
+      "epoch": 0.140893470790378,
+      "grad_norm": 0.7340226769447327,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1102,
+      "step": 82
+    },
+    {
+      "epoch": 0.14261168384879724,
+      "grad_norm": 0.6878682971000671,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.2112,
+      "step": 83
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.6366817355155945,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0678,
+      "step": 84
+    },
+    {
+      "epoch": 0.14604810996563575,
+      "grad_norm": 0.6893492937088013,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0762,
+      "step": 85
+    },
+    {
+      "epoch": 0.14776632302405499,
+      "grad_norm": 0.6605353951454163,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0357,
+      "step": 86
+    },
+    {
+      "epoch": 0.14948453608247422,
+      "grad_norm": 0.7407884001731873,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.1237,
+      "step": 87
+    },
+    {
+      "epoch": 0.15120274914089346,
+      "grad_norm": 0.6551597714424133,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.018,
+      "step": 88
+    },
+    {
+      "epoch": 0.15292096219931273,
+      "grad_norm": 0.7414847016334534,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0993,
+      "step": 89
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 0.693731963634491,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0952,
+      "step": 90
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "eval_loss": 0.5406250953674316,
+      "eval_runtime": 89.7971,
+      "eval_samples_per_second": 5.457,
+      "eval_steps_per_second": 0.69,
+      "step": 90
+    },
+    {
+      "epoch": 0.1563573883161512,
+      "grad_norm": 0.65057373046875,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0264,
+      "step": 91
+    },
+    {
+      "epoch": 0.15807560137457044,
+      "grad_norm": 0.6754416227340698,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.084,
+      "step": 92
+    },
+    {
+      "epoch": 0.15979381443298968,
+      "grad_norm": 0.6395115256309509,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.089,
+      "step": 93
+    },
+    {
+      "epoch": 0.16151202749140894,
+      "grad_norm": 0.6276084780693054,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9808,
+      "step": 94
+    },
+    {
+      "epoch": 0.16323024054982818,
+      "grad_norm": 0.6917354464530945,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1236,
+      "step": 95
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.7183430194854736,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0612,
+      "step": 96
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.6331589221954346,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.0061,
+      "step": 97
+    },
+    {
+      "epoch": 0.16838487972508592,
+      "grad_norm": 0.7188170552253723,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0711,
+      "step": 98
+    },
+    {
+      "epoch": 0.17010309278350516,
+      "grad_norm": 0.6708242893218994,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0865,
+      "step": 99
+    },
+    {
+      "epoch": 0.17010309278350516,
+      "eval_loss": 0.5401706695556641,
+      "eval_runtime": 89.7161,
+      "eval_samples_per_second": 5.462,
+      "eval_steps_per_second": 0.691,
+      "step": 99
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "grad_norm": 0.6491491198539734,
+      "learning_rate": 0.0,
+      "loss": 1.0956,
+      "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": 9.80187302854656e+16,
+  "total_flos": 1.306916403806208e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null