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:e41d5b25d1f36ffbdea09b38462e006ce7c5ed26575f862915901dbd7526ceab
+oid sha256:e4e5270788056c5b59587f78695f0000cf804736c535c3f8c8caf1bd0d890dab
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3643d9c4c1a11119b58d60b076147de885b538737cf28c787bc0d1f8e2d4ee3
+oid sha256:366b93fbf1b49b5014ebb3f7041e1f0359853f9b93235018de492014dae95017
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074e8690a8d61dba7a66649463fc8a03dc8e3c47ce5a5c77b759d178ed3f5ec7
+oid sha256:8a9386662c626731526f1abdeed2bdc3abd9cd0423f5b4ce3bfa3fae95d59602
 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": 1.4053,
       "step": 75
+    },
+    {
+      "epoch": 0.5352112676056338,
+      "grad_norm": 1.6777218580245972,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5162,
+      "step": 76
+    },
+    {
+      "epoch": 0.5422535211267606,
+      "grad_norm": 2.207165479660034,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4367,
+      "step": 77
+    },
+    {
+      "epoch": 0.5492957746478874,
+      "grad_norm": 2.791753053665161,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5284,
+      "step": 78
+    },
+    {
+      "epoch": 0.5563380281690141,
+      "grad_norm": 2.0597660541534424,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4983,
+      "step": 79
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 2.1963610649108887,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.469,
+      "step": 80
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "grad_norm": 1.8355844020843506,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.6337,
+      "step": 81
+    },
+    {
+      "epoch": 0.5704225352112676,
+      "eval_loss": 0.7295297980308533,
+      "eval_runtime": 5.2947,
+      "eval_samples_per_second": 22.664,
+      "eval_steps_per_second": 2.833,
+      "step": 81
+    },
+    {
+      "epoch": 0.5774647887323944,
+      "grad_norm": 2.3852171897888184,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3641,
+      "step": 82
+    },
+    {
+      "epoch": 0.5845070422535211,
+      "grad_norm": 2.421605110168457,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4797,
+      "step": 83
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": 1.8228073120117188,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.5467,
+      "step": 84
+    },
+    {
+      "epoch": 0.5985915492957746,
+      "grad_norm": 3.43153977394104,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4331,
+      "step": 85
+    },
+    {
+      "epoch": 0.6056338028169014,
+      "grad_norm": 1.7456953525543213,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.341,
+      "step": 86
+    },
+    {
+      "epoch": 0.6126760563380281,
+      "grad_norm": 1.962058663368225,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5015,
+      "step": 87
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 4.884045600891113,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6106,
+      "step": 88
+    },
+    {
+      "epoch": 0.6267605633802817,
+      "grad_norm": 1.6915897130966187,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4477,
+      "step": 89
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "grad_norm": 1.18873131275177,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3877,
+      "step": 90
+    },
+    {
+      "epoch": 0.6338028169014085,
+      "eval_loss": 0.7244928479194641,
+      "eval_runtime": 5.2601,
+      "eval_samples_per_second": 22.813,
+      "eval_steps_per_second": 2.852,
+      "step": 90
+    },
+    {
+      "epoch": 0.6408450704225352,
+      "grad_norm": 2.745110273361206,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3234,
+      "step": 91
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": 1.5612205266952515,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3812,
+      "step": 92
+    },
+    {
+      "epoch": 0.6549295774647887,
+      "grad_norm": 1.651207447052002,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6955,
+      "step": 93
+    },
+    {
+      "epoch": 0.6619718309859155,
+      "grad_norm": 1.4542431831359863,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4568,
+      "step": 94
+    },
+    {
+      "epoch": 0.6690140845070423,
+      "grad_norm": 2.2859489917755127,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4368,
+      "step": 95
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 2.264481544494629,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7259,
+      "step": 96
+    },
+    {
+      "epoch": 0.6830985915492958,
+      "grad_norm": 3.839521646499634,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.663,
+      "step": 97
+    },
+    {
+      "epoch": 0.6901408450704225,
+      "grad_norm": 1.972511649131775,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4722,
+      "step": 98
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "grad_norm": 1.8594896793365479,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.6764,
+      "step": 99
+    },
+    {
+      "epoch": 0.6971830985915493,
+      "eval_loss": 0.7270611524581909,
+      "eval_runtime": 5.2604,
+      "eval_samples_per_second": 22.812,
+      "eval_steps_per_second": 2.851,
+      "step": 99
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 1.3822779655456543,
+      "learning_rate": 0.0,
+      "loss": 1.4299,
+      "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": 4.90098483265536e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null