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:df840475719527cf94dccd6a9a8f7a54b0e08abe72d2ea5093e896d62f313711
+oid sha256:51c1d872ee0e73b56261a5b42924028441efab7d71430ad19112f115846c8abf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b58367e69d9cf759a4294d7265bb51f8be26e88dd2d84c89499a3a7578e0d0
+oid sha256:454db3c9266af77fe6553f2ef55ec2842749109247fdb109c41a236ba12bfd28
 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": 0.019648938957296306,
+  "epoch": 0.026198585276395073,
   "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": 0.4874,
       "step": 75
+    },
+    {
+      "epoch": 0.01991092481006026,
+      "grad_norm": 2.372506618499756,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.3445,
+      "step": 76
+    },
+    {
+      "epoch": 0.020172910662824207,
+      "grad_norm": 2.43218731880188,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4993,
+      "step": 77
+    },
+    {
+      "epoch": 0.020434896515588157,
+      "grad_norm": 3.570556402206421,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4182,
+      "step": 78
+    },
+    {
+      "epoch": 0.02069688236835211,
+      "grad_norm": 2.0982840061187744,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3876,
+      "step": 79
+    },
+    {
+      "epoch": 0.020958868221116058,
+      "grad_norm": 3.4213650226593018,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4339,
+      "step": 80
+    },
+    {
+      "epoch": 0.02122085407388001,
+      "grad_norm": 2.9391672611236572,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.4891,
+      "step": 81
+    },
+    {
+      "epoch": 0.02122085407388001,
+      "eval_loss": 0.38018786907196045,
+      "eval_runtime": 350.8665,
+      "eval_samples_per_second": 9.163,
+      "eval_steps_per_second": 1.146,
+      "step": 81
+    },
+    {
+      "epoch": 0.02148283992664396,
+      "grad_norm": 2.111271858215332,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.308,
+      "step": 82
+    },
+    {
+      "epoch": 0.021744825779407912,
+      "grad_norm": 2.7002289295196533,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3516,
+      "step": 83
+    },
+    {
+      "epoch": 0.02200681163217186,
+      "grad_norm": 3.543984889984131,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3705,
+      "step": 84
+    },
+    {
+      "epoch": 0.022268797484935814,
+      "grad_norm": 3.271446704864502,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4343,
+      "step": 85
+    },
+    {
+      "epoch": 0.022530783337699763,
+      "grad_norm": 2.3411824703216553,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2703,
+      "step": 86
+    },
+    {
+      "epoch": 0.022792769190463715,
+      "grad_norm": 2.335960626602173,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3429,
+      "step": 87
+    },
+    {
+      "epoch": 0.023054755043227664,
+      "grad_norm": 2.6089084148406982,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3557,
+      "step": 88
+    },
+    {
+      "epoch": 0.023316740895991617,
+      "grad_norm": 2.5421576499938965,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.3301,
+      "step": 89
+    },
+    {
+      "epoch": 0.023578726748755566,
+      "grad_norm": 6.247707843780518,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.463,
+      "step": 90
+    },
+    {
+      "epoch": 0.023578726748755566,
+      "eval_loss": 0.37040483951568604,
+      "eval_runtime": 350.7285,
+      "eval_samples_per_second": 9.167,
+      "eval_steps_per_second": 1.146,
+      "step": 90
+    },
+    {
+      "epoch": 0.023840712601519518,
+      "grad_norm": 2.291449785232544,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3571,
+      "step": 91
+    },
+    {
+      "epoch": 0.024102698454283467,
+      "grad_norm": 2.9508891105651855,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2984,
+      "step": 92
+    },
+    {
+      "epoch": 0.02436468430704742,
+      "grad_norm": 2.008525848388672,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2997,
+      "step": 93
+    },
+    {
+      "epoch": 0.02462667015981137,
+      "grad_norm": 2.602073907852173,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4047,
+      "step": 94
+    },
+    {
+      "epoch": 0.02488865601257532,
+      "grad_norm": 2.8246009349823,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3206,
+      "step": 95
+    },
+    {
+      "epoch": 0.02515064186533927,
+      "grad_norm": 2.744372844696045,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.345,
+      "step": 96
+    },
+    {
+      "epoch": 0.025412627718103223,
+      "grad_norm": 3.140364408493042,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3394,
+      "step": 97
+    },
+    {
+      "epoch": 0.025674613570867172,
+      "grad_norm": 2.9101879596710205,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4638,
+      "step": 98
+    },
+    {
+      "epoch": 0.025936599423631124,
+      "grad_norm": 2.878218412399292,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.451,
+      "step": 99
+    },
+    {
+      "epoch": 0.025936599423631124,
+      "eval_loss": 0.368945449590683,
+      "eval_runtime": 351.2889,
+      "eval_samples_per_second": 9.152,
+      "eval_steps_per_second": 1.144,
+      "step": 99
+    },
+    {
+      "epoch": 0.026198585276395073,
+      "grad_norm": 2.6435189247131348,
+      "learning_rate": 0.0,
+      "loss": 0.3995,
+      "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