Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3391235bf865a8715002f159af43dc8bf427cfed4929750194ec7e058d22ed4f
+oid sha256:5e54fdfa4955e97b07a9e7ad43890417604cd0d8b84d0b72e4720660cea35e19
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77afbd41e41911e3bb53dad2fe1df0497858e7d7c03f56357e3756f577f9a355
+oid sha256:7b239c1d874d99d7a301a536fdd7ebbdc9f6e33e3e42ac3317de2a3fa3588df2
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.528169014084507,
+  "epoch": 0.704225352112676,
   "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": 0.1127,
       "step": 75
+    },
+    {
+      "epoch": 0.5352112676056338,
+      "grad_norm": 7.286668300628662,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6188,
+      "step": 76
+    },
+    {
+      "epoch": 0.5422535211267606,
+      "grad_norm": 11.555882453918457,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8545,
+      "step": 77
+    },
+    {
+      "epoch": 0.5492957746478874,
+      "grad_norm": 3.129523277282715,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1236,
+      "step": 78
+    },
+    {
+      "epoch": 0.5563380281690141,
+      "grad_norm": 2.9682908058166504,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2428,
+      "step": 79
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 4.371545314788818,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1944,
+      "step": 80
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "grad_norm": 6.686436176300049,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2305,
+      "step": 81
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "eval_loss": 0.20365576446056366,
+      "eval_runtime": 13.1791,
+      "eval_samples_per_second": 9.105,
+      "eval_steps_per_second": 1.138,
+      "step": 81
+    },
+    {
+      "epoch": 0.5774647887323944,
+      "grad_norm": 2.3258509635925293,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1026,
+      "step": 82
+    },
+    {
+      "epoch": 0.5845070422535211,
+      "grad_norm": 4.362199783325195,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3257,
+      "step": 83
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": 3.4101643562316895,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1493,
+      "step": 84
+    },
+    {
+      "epoch": 0.5985915492957746,
+      "grad_norm": 4.412539482116699,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3071,
+      "step": 85
+    },
+    {
+      "epoch": 0.6056338028169014,
+      "grad_norm": 3.5476527214050293,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1843,
+      "step": 86
+    },
+    {
+      "epoch": 0.6126760563380281,
+      "grad_norm": 2.7088310718536377,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0625,
+      "step": 87
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 3.1573803424835205,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1934,
+      "step": 88
+    },
+    {
+      "epoch": 0.6267605633802817,
+      "grad_norm": 4.134128093719482,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2589,
+      "step": 89
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "grad_norm": 2.6992673873901367,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.088,
+      "step": 90
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "eval_loss": 0.20047682523727417,
+      "eval_runtime": 13.1753,
+      "eval_samples_per_second": 9.108,
+      "eval_steps_per_second": 1.138,
+      "step": 90
+    },
+    {
+      "epoch": 0.6408450704225352,
+      "grad_norm": 5.939605236053467,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3984,
+      "step": 91
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": 2.5079870223999023,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1128,
+      "step": 92
+    },
+    {
+      "epoch": 0.6549295774647887,
+      "grad_norm": 8.377665519714355,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.233,
+      "step": 93
+    },
+    {
+      "epoch": 0.6619718309859155,
+      "grad_norm": 2.7900145053863525,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1707,
+      "step": 94
+    },
+    {
+      "epoch": 0.6690140845070423,
+      "grad_norm": 4.159727096557617,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2514,
+      "step": 95
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 9.270306587219238,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.245,
+      "step": 96
+    },
+    {
+      "epoch": 0.6830985915492958,
+      "grad_norm": 2.1187515258789062,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1109,
+      "step": 97
+    },
+    {
+      "epoch": 0.6901408450704225,
+      "grad_norm": 6.0606231689453125,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2395,
+      "step": 98
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "grad_norm": 2.87969970703125,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.195,
+      "step": 99
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "eval_loss": 0.19799180328845978,
+      "eval_runtime": 13.1831,
+      "eval_samples_per_second": 9.103,
+      "eval_steps_per_second": 1.138,
+      "step": 99
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 6.620743751525879,
+      "learning_rate": 0.0,
+      "loss": 0.2681,
+      "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