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:d85712128bcdf355b6bc9cb128fd6fa9775f7c872da97b1c5a4c4b4fd20f15dc
+oid sha256:64bbf4c2d247ddcac52e24b2d964aacf38851aff4ef091d589d42177d9ccd858
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd6ce742b05b3b4c8f876b79df9baf4dd35009cb41d26eaa4f9a0c51023117c
+oid sha256:61546b21779fb309b167db8ce066874770fb312d4d5403cb0145e64593e78a29
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
+oid sha256:12d5e215f21fbf0d0fadcba9d9404c63f2d389e7deeb200582435d8a294f7182
 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": 0.00759955415948931,
+  "epoch": 0.01013273887931908,
   "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": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.007700881548282501,
+      "grad_norm": 0.0004998171934857965,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.007802208937075692,
+      "grad_norm": 0.0006128872628323734,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.007903536325868883,
+      "grad_norm": 0.0005098230321891606,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.008004863714662074,
+      "grad_norm": 0.0004762745520565659,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.008106191103455264,
+      "grad_norm": 0.0004520942165981978,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.008207518492248454,
+      "grad_norm": 0.0005275892908684909,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.008207518492248454,
+      "eval_loss": 4.220239497954026e-05,
+      "eval_runtime": 910.4375,
+      "eval_samples_per_second": 9.129,
+      "eval_steps_per_second": 1.141,
+      "step": 81
+    },
+    {
+      "epoch": 0.008308845881041646,
+      "grad_norm": 0.00043567438842728734,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.008410173269834837,
+      "grad_norm": 0.0004816035507246852,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.008511500658628027,
+      "grad_norm": 0.0005054061184637249,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.008612828047421217,
+      "grad_norm": 0.00044693483505398035,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.00871415543621441,
+      "grad_norm": 0.000529658398590982,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.0088154828250076,
+      "grad_norm": 0.002676603151485324,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.00891681021380079,
+      "grad_norm": 0.00046323458082042634,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.00901813760259398,
+      "grad_norm": 0.0004469167906790972,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.009119464991387173,
+      "grad_norm": 0.00048288522521033883,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.009119464991387173,
+      "eval_loss": 4.202386844553985e-05,
+      "eval_runtime": 909.1536,
+      "eval_samples_per_second": 9.141,
+      "eval_steps_per_second": 1.143,
+      "step": 90
+    },
+    {
+      "epoch": 0.009220792380180363,
+      "grad_norm": 0.00044704313040710986,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.009322119768973553,
+      "grad_norm": 0.0004466854443307966,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.009423447157766744,
+      "grad_norm": 0.00046623233356513083,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.009524774546559936,
+      "grad_norm": 0.00042636101716198027,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.009626101935353126,
+      "grad_norm": 0.0005625992780551314,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.009727429324146317,
+      "grad_norm": 0.0005262286285869777,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.009828756712939507,
+      "grad_norm": 0.0004594066122081131,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.0099300841017327,
+      "grad_norm": 0.0004715861286967993,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.01003141149052589,
+      "grad_norm": 0.0004536711785476655,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.01003141149052589,
+      "eval_loss": 4.104103209101595e-05,
+      "eval_runtime": 909.6345,
+      "eval_samples_per_second": 9.137,
+      "eval_steps_per_second": 1.142,
+      "step": 99
+    },
+    {
+      "epoch": 0.01013273887931908,
+      "grad_norm": 8.957590103149414,
+      "learning_rate": 0.0,
+      "loss": 0.0842,
+      "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": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null