| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04156275976724855, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016625103906899418, | |
| "grad_norm": 0.04670165851712227, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016625103906899418, | |
| "eval_loss": 11.760279655456543, | |
| "eval_runtime": 10.8414, | |
| "eval_samples_per_second": 46.765, | |
| "eval_steps_per_second": 5.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033250207813798837, | |
| "grad_norm": 0.04368332028388977, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004987531172069825, | |
| "grad_norm": 0.044506169855594635, | |
| "learning_rate": 3e-05, | |
| "loss": 11.7567, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006650041562759767, | |
| "grad_norm": 0.0508490614593029, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00831255195344971, | |
| "grad_norm": 0.044127244502305984, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7587, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00997506234413965, | |
| "grad_norm": 0.05494147166609764, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7636, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011637572734829594, | |
| "grad_norm": 0.044881321489810944, | |
| "learning_rate": 7e-05, | |
| "loss": 11.7567, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013300083125519535, | |
| "grad_norm": 0.05256935581564903, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7558, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014962593516209476, | |
| "grad_norm": 0.05547723546624184, | |
| "learning_rate": 9e-05, | |
| "loss": 11.7578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014962593516209476, | |
| "eval_loss": 11.760008811950684, | |
| "eval_runtime": 10.8532, | |
| "eval_samples_per_second": 46.714, | |
| "eval_steps_per_second": 5.897, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01662510390689942, | |
| "grad_norm": 0.050355251878499985, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7521, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01828761429758936, | |
| "grad_norm": 0.05273785442113876, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 11.7576, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0199501246882793, | |
| "grad_norm": 0.047757700085639954, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 11.7637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021612635078969242, | |
| "grad_norm": 0.04381760209798813, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 11.7615, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023275145469659187, | |
| "grad_norm": 0.05205358564853668, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 11.7624, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02493765586034913, | |
| "grad_norm": 0.05228843539953232, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 11.7613, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02660016625103907, | |
| "grad_norm": 0.04606500267982483, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 11.7586, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02826267664172901, | |
| "grad_norm": 0.05653437227010727, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 11.7601, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "grad_norm": 0.049704670906066895, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 11.7634, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "eval_loss": 11.759297370910645, | |
| "eval_runtime": 10.8593, | |
| "eval_samples_per_second": 46.688, | |
| "eval_steps_per_second": 5.894, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03158769742310889, | |
| "grad_norm": 0.06516430526971817, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.7569, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03325020781379884, | |
| "grad_norm": 0.05210546776652336, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 11.7583, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.034912718204488775, | |
| "grad_norm": 0.05196945369243622, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 11.7641, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03657522859517872, | |
| "grad_norm": 0.052862655371427536, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 11.7536, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.038237738985868665, | |
| "grad_norm": 0.05532236397266388, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 11.756, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0399002493765586, | |
| "grad_norm": 0.05812180042266846, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 11.7572, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04156275976724855, | |
| "grad_norm": 0.06880798190832138, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.7558, | |
| "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": 5092501094400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |