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:c18e085d42f170073c266faa07cda8666cb8c423042579a66b4662f48decac67
+oid sha256:1fda8ad6c963e48c55a15b1e2c5b61710cdec51cfb24dd8f4420f99b661024bf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175a3b90952e171404f8b1ad4d014934c98041226cdd2e7924bbd646132a68dc
+oid sha256:25d136c505ea4987cdb3d5cc51ad6e01038dd676ca5c45a934216b4cc464d9e3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
+oid sha256:12d5e215f21fbf0d0fadcba9d9404c63f2d389e7deeb200582435d8a294f7182
 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": 0.015981248668229277,
+  "epoch": 0.021308331557639035,
   "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": 2.2417,
       "step": 75
+    },
+    {
+      "epoch": 0.016194331983805668,
+      "grad_norm": 1.606557011604309,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.32,
+      "step": 76
+    },
+    {
+      "epoch": 0.01640741529938206,
+      "grad_norm": 1.6703760623931885,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.5816,
+      "step": 77
+    },
+    {
+      "epoch": 0.01662049861495845,
+      "grad_norm": 1.63593590259552,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.3473,
+      "step": 78
+    },
+    {
+      "epoch": 0.01683358193053484,
+      "grad_norm": 1.9115629196166992,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.2544,
+      "step": 79
+    },
+    {
+      "epoch": 0.01704666524611123,
+      "grad_norm": 1.720870018005371,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1917,
+      "step": 80
+    },
+    {
+      "epoch": 0.01725974856168762,
+      "grad_norm": 1.7113711833953857,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.0777,
+      "step": 81
+    },
+    {
+      "epoch": 0.01725974856168762,
+      "eval_loss": 2.248765468597412,
+      "eval_runtime": 484.7178,
+      "eval_samples_per_second": 8.153,
+      "eval_steps_per_second": 1.019,
+      "step": 81
+    },
+    {
+      "epoch": 0.01747283187726401,
+      "grad_norm": 1.6351940631866455,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3214,
+      "step": 82
+    },
+    {
+      "epoch": 0.0176859151928404,
+      "grad_norm": 1.4796867370605469,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.2755,
+      "step": 83
+    },
+    {
+      "epoch": 0.01789899850841679,
+      "grad_norm": 1.394295334815979,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.4346,
+      "step": 84
+    },
+    {
+      "epoch": 0.01811208182399318,
+      "grad_norm": 1.846497654914856,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1393,
+      "step": 85
+    },
+    {
+      "epoch": 0.018325165139569572,
+      "grad_norm": 1.752183198928833,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4348,
+      "step": 86
+    },
+    {
+      "epoch": 0.018538248455145963,
+      "grad_norm": 1.6644121408462524,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.3184,
+      "step": 87
+    },
+    {
+      "epoch": 0.018751331770722354,
+      "grad_norm": 1.5804589986801147,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.839,
+      "step": 88
+    },
+    {
+      "epoch": 0.018964415086298744,
+      "grad_norm": 1.5491611957550049,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.3984,
+      "step": 89
+    },
+    {
+      "epoch": 0.01917749840187513,
+      "grad_norm": 1.6144686937332153,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0352,
+      "step": 90
+    },
+    {
+      "epoch": 0.01917749840187513,
+      "eval_loss": 2.2463996410369873,
+      "eval_runtime": 484.6085,
+      "eval_samples_per_second": 8.155,
+      "eval_steps_per_second": 1.019,
+      "step": 90
+    },
+    {
+      "epoch": 0.019390581717451522,
+      "grad_norm": 1.871982455253601,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2682,
+      "step": 91
+    },
+    {
+      "epoch": 0.019603665033027913,
+      "grad_norm": 1.5905784368515015,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1101,
+      "step": 92
+    },
+    {
+      "epoch": 0.019816748348604304,
+      "grad_norm": 1.4988384246826172,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.4955,
+      "step": 93
+    },
+    {
+      "epoch": 0.020029831664180694,
+      "grad_norm": 1.6045547723770142,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.488,
+      "step": 94
+    },
+    {
+      "epoch": 0.020242914979757085,
+      "grad_norm": 1.3878628015518188,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.138,
+      "step": 95
+    },
+    {
+      "epoch": 0.020455998295333476,
+      "grad_norm": 1.6201906204223633,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.426,
+      "step": 96
+    },
+    {
+      "epoch": 0.020669081610909867,
+      "grad_norm": 1.7183762788772583,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1243,
+      "step": 97
+    },
+    {
+      "epoch": 0.020882164926486257,
+      "grad_norm": 1.3840333223342896,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3035,
+      "step": 98
+    },
+    {
+      "epoch": 0.021095248242062648,
+      "grad_norm": 1.535163402557373,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.306,
+      "step": 99
+    },
+    {
+      "epoch": 0.021095248242062648,
+      "eval_loss": 2.2457332611083984,
+      "eval_runtime": 484.4586,
+      "eval_samples_per_second": 8.158,
+      "eval_steps_per_second": 1.02,
+      "step": 99
+    },
+    {
+      "epoch": 0.021308331557639035,
+      "grad_norm": 1.3996747732162476,
+      "learning_rate": 0.0,
+      "loss": 2.4191,
+      "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