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:f9ecb935822deefa465591ce47b7057fe71ccd90a32293e3b0275d3517110f64
+oid sha256:5b4fd96255a4697dd7e0fedbb60c085c8efd13f4e303a4c8eebb484cd2e13ae5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9887b56fbfafc91c0755c86a8c4decf8cff31d3d6504b0da4ebccc2d1bfe5ca
+oid sha256:cda9a878a24800ac5cbfd09ea95fbdb9f40af08e7ce50e4df102506c76097456
 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": 0.36319612590799033,
+  "epoch": 0.48426150121065376,
   "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": 2.9819,
       "step": 75
+    },
+    {
+      "epoch": 0.36803874092009686,
+      "grad_norm": 2.1586506366729736,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.2151,
+      "step": 76
+    },
+    {
+      "epoch": 0.3728813559322034,
+      "grad_norm": 1.8652886152267456,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.8469,
+      "step": 77
+    },
+    {
+      "epoch": 0.37772397094430993,
+      "grad_norm": 1.0568983554840088,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.0914,
+      "step": 78
+    },
+    {
+      "epoch": 0.38256658595641646,
+      "grad_norm": 2.529310941696167,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.9987,
+      "step": 79
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 2.5289180278778076,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.3993,
+      "step": 80
+    },
+    {
+      "epoch": 0.3922518159806295,
+      "grad_norm": 1.687282681465149,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.1609,
+      "step": 81
+    },
+    {
+      "epoch": 0.3922518159806295,
+      "eval_loss": 3.032550573348999,
+      "eval_runtime": 18.9409,
+      "eval_samples_per_second": 9.186,
+      "eval_steps_per_second": 1.162,
+      "step": 81
+    },
+    {
+      "epoch": 0.39709443099273606,
+      "grad_norm": 1.1963615417480469,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.1623,
+      "step": 82
+    },
+    {
+      "epoch": 0.4019370460048426,
+      "grad_norm": 1.187296748161316,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.0359,
+      "step": 83
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 2.5232021808624268,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.042,
+      "step": 84
+    },
+    {
+      "epoch": 0.4116222760290557,
+      "grad_norm": 0.9182229042053223,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8504,
+      "step": 85
+    },
+    {
+      "epoch": 0.41646489104116224,
+      "grad_norm": 1.5995279550552368,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.1284,
+      "step": 86
+    },
+    {
+      "epoch": 0.4213075060532688,
+      "grad_norm": 0.9825161695480347,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.8729,
+      "step": 87
+    },
+    {
+      "epoch": 0.4261501210653753,
+      "grad_norm": 1.644863486289978,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.9239,
+      "step": 88
+    },
+    {
+      "epoch": 0.43099273607748184,
+      "grad_norm": 1.652917742729187,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.978,
+      "step": 89
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 1.7402114868164062,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2838,
+      "step": 90
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "eval_loss": 3.0317323207855225,
+      "eval_runtime": 18.9411,
+      "eval_samples_per_second": 9.186,
+      "eval_steps_per_second": 1.161,
+      "step": 90
+    },
+    {
+      "epoch": 0.4406779661016949,
+      "grad_norm": 0.950768232345581,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.9166,
+      "step": 91
+    },
+    {
+      "epoch": 0.44552058111380144,
+      "grad_norm": 1.404856562614441,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.0537,
+      "step": 92
+    },
+    {
+      "epoch": 0.45036319612590797,
+      "grad_norm": 2.394108772277832,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.1149,
+      "step": 93
+    },
+    {
+      "epoch": 0.4552058111380145,
+      "grad_norm": 0.9558013677597046,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.8942,
+      "step": 94
+    },
+    {
+      "epoch": 0.4600484261501211,
+      "grad_norm": 1.7184518575668335,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.172,
+      "step": 95
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 1.2304576635360718,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.854,
+      "step": 96
+    },
+    {
+      "epoch": 0.46973365617433416,
+      "grad_norm": 0.9844062328338623,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.823,
+      "step": 97
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 1.5699692964553833,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.0896,
+      "step": 98
+    },
+    {
+      "epoch": 0.4794188861985472,
+      "grad_norm": 0.9208653569221497,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.8619,
+      "step": 99
+    },
+    {
+      "epoch": 0.4794188861985472,
+      "eval_loss": 3.029693603515625,
+      "eval_runtime": 18.916,
+      "eval_samples_per_second": 9.199,
+      "eval_steps_per_second": 1.163,
+      "step": 99
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 1.2649552822113037,
+      "learning_rate": 0.0,
+      "loss": 2.9492,
+      "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