| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03785011355034065, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001514004542013626, | |
| "grad_norm": 0.6870254278182983, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001514004542013626, | |
| "eval_loss": 0.6710895299911499, | |
| "eval_runtime": 127.6316, | |
| "eval_samples_per_second": 4.356, | |
| "eval_steps_per_second": 0.548, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003028009084027252, | |
| "grad_norm": 1.0985076427459717, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6838, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004542013626040878, | |
| "grad_norm": 0.6782929301261902, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006056018168054504, | |
| "grad_norm": 0.6256589293479919, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7221, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00757002271006813, | |
| "grad_norm": 0.7078294157981873, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6957, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009084027252081756, | |
| "grad_norm": 0.6197799444198608, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7096, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010598031794095382, | |
| "grad_norm": 0.6056140065193176, | |
| "learning_rate": 7e-05, | |
| "loss": 0.65, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012112036336109008, | |
| "grad_norm": 0.9818187952041626, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5974, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013626040878122634, | |
| "grad_norm": 0.7567906379699707, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013626040878122634, | |
| "eval_loss": 0.6097605228424072, | |
| "eval_runtime": 127.5185, | |
| "eval_samples_per_second": 4.36, | |
| "eval_steps_per_second": 0.549, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01514004542013626, | |
| "grad_norm": 0.9188516736030579, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016654049962149888, | |
| "grad_norm": 0.8129972815513611, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.6875, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018168054504163512, | |
| "grad_norm": 0.9102829694747925, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.6385, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01968205904617714, | |
| "grad_norm": 0.9624842405319214, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.667, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021196063588190765, | |
| "grad_norm": 0.7224256992340088, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.6147, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022710068130204392, | |
| "grad_norm": 0.6421948671340942, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.7355, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024224072672218017, | |
| "grad_norm": 0.6296693682670593, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.5936, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025738077214231644, | |
| "grad_norm": 0.529050886631012, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.6936, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02725208175624527, | |
| "grad_norm": 0.6707794070243835, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.5679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02725208175624527, | |
| "eval_loss": 0.5738157033920288, | |
| "eval_runtime": 127.5235, | |
| "eval_samples_per_second": 4.36, | |
| "eval_steps_per_second": 0.549, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028766086298258896, | |
| "grad_norm": 0.6477593779563904, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.5251, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03028009084027252, | |
| "grad_norm": 0.5631066560745239, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.5807, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03179409538228615, | |
| "grad_norm": 0.6563144326210022, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.5969, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.033308099924299776, | |
| "grad_norm": 0.5367952585220337, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7125, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0348221044663134, | |
| "grad_norm": 0.5025123953819275, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.7012, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.036336109008327025, | |
| "grad_norm": 0.5811274647712708, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5697, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03785011355034065, | |
| "grad_norm": 0.5691922903060913, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.674, | |
| "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": 3.4868702327341056e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |