Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3e02e5130c16a502b24d52a2e0dbd62ef0b74949f1907f03ddc3917e021df7
+oid sha256:d97cd09c5fa9a41cc69b4b5e62ea08b060b8819aa25b791a33051ed587196fdd
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc6ba7c38fd7bdb7a45620895016f085b752a6a6cd34f4b667eeec88d4f06e2a
+oid sha256:7b7eacbd4851b539aff719364eca3392c892fb41d9e18146d42dddfe8168231f
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e42707bff3a01dd441022647b82d0d244a8f2409373d258e9184fc37cc91af
+oid sha256:71fc6bba3f242e88b85f33651f56380c544ca14fb09dd639b0ec5276ac7956e5
 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": 10.3526,
       "step": 75
+    },
+    {
+      "epoch": 0.5352112676056338,
+      "grad_norm": 0.48135364055633545,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3316,
+      "step": 76
+    },
+    {
+      "epoch": 0.5422535211267606,
+      "grad_norm": 0.44966384768486023,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3226,
+      "step": 77
+    },
+    {
+      "epoch": 0.5492957746478874,
+      "grad_norm": 0.4600827395915985,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3408,
+      "step": 78
+    },
+    {
+      "epoch": 0.5563380281690141,
+      "grad_norm": 0.4820798635482788,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3488,
+      "step": 79
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 0.45883482694625854,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3127,
+      "step": 80
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "grad_norm": 0.4635918140411377,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3243,
+      "step": 81
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "eval_loss": 10.342907905578613,
+      "eval_runtime": 0.5248,
+      "eval_samples_per_second": 228.655,
+      "eval_steps_per_second": 28.582,
+      "step": 81
+    },
+    {
+      "epoch": 0.5774647887323944,
+      "grad_norm": 0.5020090937614441,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3671,
+      "step": 82
+    },
+    {
+      "epoch": 0.5845070422535211,
+      "grad_norm": 0.571985125541687,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3296,
+      "step": 83
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": 0.41995105147361755,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3415,
+      "step": 84
+    },
+    {
+      "epoch": 0.5985915492957746,
+      "grad_norm": 0.475591778755188,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3001,
+      "step": 85
+    },
+    {
+      "epoch": 0.6056338028169014,
+      "grad_norm": 0.4260372221469879,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3346,
+      "step": 86
+    },
+    {
+      "epoch": 0.6126760563380281,
+      "grad_norm": 0.48487669229507446,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3202,
+      "step": 87
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 0.5162070393562317,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3107,
+      "step": 88
+    },
+    {
+      "epoch": 0.6267605633802817,
+      "grad_norm": 0.5247275233268738,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3445,
+      "step": 89
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "grad_norm": 0.4642081558704376,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3393,
+      "step": 90
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "eval_loss": 10.34151554107666,
+      "eval_runtime": 0.5021,
+      "eval_samples_per_second": 239.0,
+      "eval_steps_per_second": 29.875,
+      "step": 90
+    },
+    {
+      "epoch": 0.6408450704225352,
+      "grad_norm": 0.452671080827713,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3266,
+      "step": 91
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": 0.41254308819770813,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3512,
+      "step": 92
+    },
+    {
+      "epoch": 0.6549295774647887,
+      "grad_norm": 0.3993806838989258,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3397,
+      "step": 93
+    },
+    {
+      "epoch": 0.6619718309859155,
+      "grad_norm": 0.46821779012680054,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3482,
+      "step": 94
+    },
+    {
+      "epoch": 0.6690140845070423,
+      "grad_norm": 0.5118176937103271,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3231,
+      "step": 95
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.46694812178611755,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3398,
+      "step": 96
+    },
+    {
+      "epoch": 0.6830985915492958,
+      "grad_norm": 0.44762948155403137,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3289,
+      "step": 97
+    },
+    {
+      "epoch": 0.6901408450704225,
+      "grad_norm": 0.49409934878349304,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3326,
+      "step": 98
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "grad_norm": 0.3911196291446686,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3373,
+      "step": 99
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "eval_loss": 10.341242790222168,
+      "eval_runtime": 0.4937,
+      "eval_samples_per_second": 243.083,
+      "eval_steps_per_second": 30.385,
+      "step": 99
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 0.4704214632511139,
+      "learning_rate": 0.0,
+      "loss": 10.3267,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null