| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2074688796680498, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 0.5584869980812073, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "eval_loss": 0.525488555431366, | |
| "eval_runtime": 21.6583, | |
| "eval_samples_per_second": 4.71, | |
| "eval_steps_per_second": 0.6, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.574292778968811, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4623, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 0.5636454224586487, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 0.464995801448822, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3894, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04149377593360996, | |
| "grad_norm": 0.48257189989089966, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3823, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04979253112033195, | |
| "grad_norm": 0.43475595116615295, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.058091286307053944, | |
| "grad_norm": 0.5338840484619141, | |
| "learning_rate": 7e-05, | |
| "loss": 0.374, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 0.4116763472557068, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3165, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07468879668049792, | |
| "grad_norm": 0.44430240988731384, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3308, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07468879668049792, | |
| "eval_loss": 0.36139607429504395, | |
| "eval_runtime": 20.832, | |
| "eval_samples_per_second": 4.896, | |
| "eval_steps_per_second": 0.624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "grad_norm": 0.43339839577674866, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0912863070539419, | |
| "grad_norm": 0.41347187757492065, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.4802, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 0.39249882102012634, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.2027, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1078838174273859, | |
| "grad_norm": 0.3496515452861786, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.1702, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11618257261410789, | |
| "grad_norm": 0.3440171480178833, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.1495, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12448132780082988, | |
| "grad_norm": 0.40277042984962463, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.3027, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 0.45786339044570923, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.156, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14107883817427386, | |
| "grad_norm": 0.3107019066810608, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.1383, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "grad_norm": 0.2789028286933899, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.1316, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14937759336099585, | |
| "eval_loss": 0.2620299756526947, | |
| "eval_runtime": 20.8181, | |
| "eval_samples_per_second": 4.9, | |
| "eval_steps_per_second": 0.624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15767634854771784, | |
| "grad_norm": 0.3484548032283783, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.152, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 0.3380146324634552, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17427385892116182, | |
| "grad_norm": 0.47338756918907166, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.1325, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1825726141078838, | |
| "grad_norm": 0.2783995568752289, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.1535, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1908713692946058, | |
| "grad_norm": 0.4390009641647339, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.1582, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 0.2531968951225281, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.129, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2074688796680498, | |
| "grad_norm": 0.21148426830768585, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1381, | |
| "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": 3.3013984118439936e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |