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:d45fe14428523c371a6bbe4899c6007627ee0f27cf32451bf7809e00accdb265
+oid sha256:4aa9a58e2b153a171249d5583c847f54a99549fdecd5074feb2c81e8c78ee8ab
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc62b813d7d312b3876f460accee483d67d79e8efe14db60d82fbe315e8133be
+oid sha256:41f47d93a3e7469cf96473abf523eb29e0cdcbb9f06adc7da8b12064f3e6cfdf
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38416d88c9d2d10168ce8eb5c0e25ba2e76e46134432cb12986cab3aa7f61db4
+oid sha256:ce8d061d1ee7e6a3b6f169fa8fd229fca644731369322db6930b73e8c6afac9e
 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": 0.01243574863206765,
+  "epoch": 0.0165809981760902,
   "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": 0.6989,
       "step": 75
+    },
+    {
+      "epoch": 0.012601558613828553,
+      "grad_norm": 3.3432273864746094,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.625,
+      "step": 76
+    },
+    {
+      "epoch": 0.012767368595589454,
+      "grad_norm": 3.2553389072418213,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8164,
+      "step": 77
+    },
+    {
+      "epoch": 0.012933178577350357,
+      "grad_norm": 2.3025598526000977,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6151,
+      "step": 78
+    },
+    {
+      "epoch": 0.013098988559111258,
+      "grad_norm": 1.768186330795288,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4743,
+      "step": 79
+    },
+    {
+      "epoch": 0.01326479854087216,
+      "grad_norm": 1.6566768884658813,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3514,
+      "step": 80
+    },
+    {
+      "epoch": 0.013430608522633062,
+      "grad_norm": 2.122018575668335,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.464,
+      "step": 81
+    },
+    {
+      "epoch": 0.013430608522633062,
+      "eval_loss": 0.27632373571395874,
+      "eval_runtime": 1575.8525,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 81
+    },
+    {
+      "epoch": 0.013596418504393965,
+      "grad_norm": 1.748769998550415,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3143,
+      "step": 82
+    },
+    {
+      "epoch": 0.013762228486154866,
+      "grad_norm": 3.251952648162842,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0136,
+      "step": 83
+    },
+    {
+      "epoch": 0.013928038467915769,
+      "grad_norm": 1.9073454141616821,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.4326,
+      "step": 84
+    },
+    {
+      "epoch": 0.01409384844967667,
+      "grad_norm": 1.4053856134414673,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4547,
+      "step": 85
+    },
+    {
+      "epoch": 0.014259658431437573,
+      "grad_norm": 2.472945213317871,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6188,
+      "step": 86
+    },
+    {
+      "epoch": 0.014425468413198474,
+      "grad_norm": 2.9573841094970703,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.6689,
+      "step": 87
+    },
+    {
+      "epoch": 0.014591278394959377,
+      "grad_norm": 1.7082061767578125,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.394,
+      "step": 88
+    },
+    {
+      "epoch": 0.014757088376720278,
+      "grad_norm": 1.5923526287078857,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.4601,
+      "step": 89
+    },
+    {
+      "epoch": 0.014922898358481181,
+      "grad_norm": 1.5400145053863525,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4093,
+      "step": 90
+    },
+    {
+      "epoch": 0.014922898358481181,
+      "eval_loss": 0.26483044028282166,
+      "eval_runtime": 1575.8205,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 90
+    },
+    {
+      "epoch": 0.015088708340242082,
+      "grad_norm": 1.6519761085510254,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3969,
+      "step": 91
+    },
+    {
+      "epoch": 0.015254518322002985,
+      "grad_norm": 2.0877702236175537,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6622,
+      "step": 92
+    },
+    {
+      "epoch": 0.015420328303763886,
+      "grad_norm": 1.6852989196777344,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5761,
+      "step": 93
+    },
+    {
+      "epoch": 0.015586138285524789,
+      "grad_norm": 1.3629008531570435,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3565,
+      "step": 94
+    },
+    {
+      "epoch": 0.015751948267285692,
+      "grad_norm": 1.808484673500061,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.4087,
+      "step": 95
+    },
+    {
+      "epoch": 0.015917758249046593,
+      "grad_norm": 1.5466543436050415,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4395,
+      "step": 96
+    },
+    {
+      "epoch": 0.016083568230807494,
+      "grad_norm": 2.435929298400879,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.6049,
+      "step": 97
+    },
+    {
+      "epoch": 0.016249378212568395,
+      "grad_norm": 1.4214541912078857,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4302,
+      "step": 98
+    },
+    {
+      "epoch": 0.0164151881943293,
+      "grad_norm": 2.556894540786743,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5967,
+      "step": 99
+    },
+    {
+      "epoch": 0.0164151881943293,
+      "eval_loss": 0.26305386424064636,
+      "eval_runtime": 1576.2459,
+      "eval_samples_per_second": 3.222,
+      "eval_steps_per_second": 0.403,
+      "step": 99
+    },
+    {
+      "epoch": 0.0165809981760902,
+      "grad_norm": 1.7079695463180542,
+      "learning_rate": 0.0,
+      "loss": 0.6013,
+      "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": 1.9043369091072e+17,
+  "total_flos": 2.5391158788096e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null