Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7573f0b16c38a2284f7a0507bcb8cbfefce10088715e95a4a5ae214f7bfa3529
+oid sha256:57f8427d2e1ca644451314fc8e493866c0bea0b3630a277be9ff125ade0866d5
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1db83fef5b49ab9070b8e640f2fb1dc00f00443ce21ceb56ac43711b1300644
+oid sha256:4c160c53c84fb2c85fb087c73890c779a2046e1006408a93af13f2f0b80f825c
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbf67edaa5ce91e9e90c0f79ac4fd893b0ed1f125baec8e73bbae72aec6d24c
+oid sha256:3d53073dd24a1f7ade85d8d7b1628f314544282909c943e52b856be30e5b812b
 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": 0.007510514720608852,
+  "epoch": 0.01001401962747847,
   "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": 0.1194,
       "step": 75
+    },
+    {
+      "epoch": 0.007610654916883637,
+      "grad_norm": 1.875455379486084,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2304,
+      "step": 76
+    },
+    {
+      "epoch": 0.007710795113158422,
+      "grad_norm": 2.2411744594573975,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1815,
+      "step": 77
+    },
+    {
+      "epoch": 0.007810935309433206,
+      "grad_norm": 2.8946216106414795,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2217,
+      "step": 78
+    },
+    {
+      "epoch": 0.007911075505707991,
+      "grad_norm": 1.7799750566482544,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3182,
+      "step": 79
+    },
+    {
+      "epoch": 0.008011215701982776,
+      "grad_norm": 1.9484471082687378,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.299,
+      "step": 80
+    },
+    {
+      "epoch": 0.008111355898257561,
+      "grad_norm": 1.5336110591888428,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1742,
+      "step": 81
+    },
+    {
+      "epoch": 0.008111355898257561,
+      "eval_loss": 0.09696789085865021,
+      "eval_runtime": 474.2628,
+      "eval_samples_per_second": 17.733,
+      "eval_steps_per_second": 2.218,
+      "step": 81
+    },
+    {
+      "epoch": 0.008211496094532346,
+      "grad_norm": 1.6862149238586426,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2586,
+      "step": 82
+    },
+    {
+      "epoch": 0.00831163629080713,
+      "grad_norm": 1.7612273693084717,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2939,
+      "step": 83
+    },
+    {
+      "epoch": 0.008411776487081914,
+      "grad_norm": 1.6957480907440186,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1462,
+      "step": 84
+    },
+    {
+      "epoch": 0.008511916683356699,
+      "grad_norm": 1.4230989217758179,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.144,
+      "step": 85
+    },
+    {
+      "epoch": 0.008612056879631484,
+      "grad_norm": 1.2826586961746216,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1533,
+      "step": 86
+    },
+    {
+      "epoch": 0.008712197075906269,
+      "grad_norm": 1.4179471731185913,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2041,
+      "step": 87
+    },
+    {
+      "epoch": 0.008812337272181054,
+      "grad_norm": 1.0860555171966553,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1134,
+      "step": 88
+    },
+    {
+      "epoch": 0.008912477468455839,
+      "grad_norm": 4.3372626304626465,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.4055,
+      "step": 89
+    },
+    {
+      "epoch": 0.009012617664730624,
+      "grad_norm": 1.6257705688476562,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1494,
+      "step": 90
+    },
+    {
+      "epoch": 0.009012617664730624,
+      "eval_loss": 0.0966808870434761,
+      "eval_runtime": 474.7135,
+      "eval_samples_per_second": 17.716,
+      "eval_steps_per_second": 2.216,
+      "step": 90
+    },
+    {
+      "epoch": 0.009112757861005407,
+      "grad_norm": 2.111048698425293,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2083,
+      "step": 91
+    },
+    {
+      "epoch": 0.009212898057280192,
+      "grad_norm": 1.822697639465332,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1038,
+      "step": 92
+    },
+    {
+      "epoch": 0.009313038253554977,
+      "grad_norm": 0.9412707686424255,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1446,
+      "step": 93
+    },
+    {
+      "epoch": 0.009413178449829761,
+      "grad_norm": 1.0589618682861328,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1955,
+      "step": 94
+    },
+    {
+      "epoch": 0.009513318646104546,
+      "grad_norm": 1.2069085836410522,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0989,
+      "step": 95
+    },
+    {
+      "epoch": 0.009613458842379331,
+      "grad_norm": 0.6846264600753784,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0628,
+      "step": 96
+    },
+    {
+      "epoch": 0.009713599038654116,
+      "grad_norm": 1.4135501384735107,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1567,
+      "step": 97
+    },
+    {
+      "epoch": 0.009813739234928901,
+      "grad_norm": 1.6825953722000122,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2452,
+      "step": 98
+    },
+    {
+      "epoch": 0.009913879431203684,
+      "grad_norm": 1.1096628904342651,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1059,
+      "step": 99
+    },
+    {
+      "epoch": 0.009913879431203684,
+      "eval_loss": 0.09647203981876373,
+      "eval_runtime": 475.1526,
+      "eval_samples_per_second": 17.7,
+      "eval_steps_per_second": 2.214,
+      "step": 99
+    },
+    {
+      "epoch": 0.01001401962747847,
+      "grad_norm": 1.0432554483413696,
+      "learning_rate": 0.0,
+      "loss": 0.0432,
+      "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": 9003556719820800.0,
+  "total_flos": 1.20047422930944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null