| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05319148936170213, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002127659574468085, | |
| "grad_norm": 0.10300079733133316, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002127659574468085, | |
| "eval_loss": 0.28012359142303467, | |
| "eval_runtime": 136.1969, | |
| "eval_samples_per_second": 2.908, | |
| "eval_steps_per_second": 0.367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00425531914893617, | |
| "grad_norm": 0.10144907981157303, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006382978723404255, | |
| "grad_norm": 0.08996520936489105, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4374, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00851063829787234, | |
| "grad_norm": 0.09395291656255722, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5495, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010638297872340425, | |
| "grad_norm": 0.10324636846780777, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6145, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01276595744680851, | |
| "grad_norm": 0.08707210421562195, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3558, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014893617021276596, | |
| "grad_norm": 0.11621297895908356, | |
| "learning_rate": 7e-05, | |
| "loss": 0.5514, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01702127659574468, | |
| "grad_norm": 0.10932344943284988, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019148936170212766, | |
| "grad_norm": 0.1405569314956665, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4737, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019148936170212766, | |
| "eval_loss": 0.2623712122440338, | |
| "eval_runtime": 137.2425, | |
| "eval_samples_per_second": 2.885, | |
| "eval_steps_per_second": 0.364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 0.14397543668746948, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5168, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023404255319148935, | |
| "grad_norm": 0.1323714256286621, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.4371, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02553191489361702, | |
| "grad_norm": 0.13116616010665894, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.4262, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.027659574468085105, | |
| "grad_norm": 0.13853837549686432, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.5099, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.029787234042553193, | |
| "grad_norm": 0.1474577784538269, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.3021, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031914893617021274, | |
| "grad_norm": 0.1504347324371338, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.4131, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03404255319148936, | |
| "grad_norm": 0.1708698570728302, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.4761, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.036170212765957444, | |
| "grad_norm": 0.17005902528762817, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.3081, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03829787234042553, | |
| "grad_norm": 0.21712253987789154, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.4314, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03829787234042553, | |
| "eval_loss": 0.18715143203735352, | |
| "eval_runtime": 137.3301, | |
| "eval_samples_per_second": 2.884, | |
| "eval_steps_per_second": 0.364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04042553191489362, | |
| "grad_norm": 0.23651768267154694, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.3969, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 0.1859365850687027, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.435, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04468085106382979, | |
| "grad_norm": 0.20384368300437927, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.3033, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04680851063829787, | |
| "grad_norm": 0.2507339417934418, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.3752, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04893617021276596, | |
| "grad_norm": 0.23452381789684296, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.2799, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05106382978723404, | |
| "grad_norm": 0.22419746220111847, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.334, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05319148936170213, | |
| "grad_norm": 0.19811676442623138, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2044, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.26732322177024e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |