| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.088261253309797, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00176522506619594, | |
| "eval_loss": 19.31140899658203, | |
| "eval_runtime": 61.8597, | |
| "eval_samples_per_second": 3.864, | |
| "eval_steps_per_second": 1.94, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0088261253309797, | |
| "grad_norm": 60.404327392578125, | |
| "learning_rate": 5e-05, | |
| "loss": 20.5111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0176522506619594, | |
| "grad_norm": 70.15036010742188, | |
| "learning_rate": 0.0001, | |
| "loss": 13.7811, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0176522506619594, | |
| "eval_loss": 5.2021636962890625, | |
| "eval_runtime": 62.7015, | |
| "eval_samples_per_second": 3.812, | |
| "eval_steps_per_second": 1.914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0264783759929391, | |
| "grad_norm": 11.331101417541504, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0677, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "grad_norm": 16.111406326293945, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "eval_loss": 0.5223247408866882, | |
| "eval_runtime": 62.8674, | |
| "eval_samples_per_second": 3.802, | |
| "eval_steps_per_second": 1.909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0441306266548985, | |
| "grad_norm": 9.063875198364258, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5021, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0529567519858782, | |
| "grad_norm": 4.586399078369141, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0529567519858782, | |
| "eval_loss": 0.47897952795028687, | |
| "eval_runtime": 62.9044, | |
| "eval_samples_per_second": 3.799, | |
| "eval_steps_per_second": 1.908, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0617828773168579, | |
| "grad_norm": 8.578695297241211, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0706090026478376, | |
| "grad_norm": 8.900777816772461, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.36, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0706090026478376, | |
| "eval_loss": 0.3891545236110687, | |
| "eval_runtime": 62.9107, | |
| "eval_samples_per_second": 3.799, | |
| "eval_steps_per_second": 1.907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0794351279788173, | |
| "grad_norm": 6.1990203857421875, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.405, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.088261253309797, | |
| "grad_norm": 2.5258963108062744, | |
| "learning_rate": 0.0, | |
| "loss": 0.4746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.088261253309797, | |
| "eval_loss": 0.3904491364955902, | |
| "eval_runtime": 63.425, | |
| "eval_samples_per_second": 3.768, | |
| "eval_steps_per_second": 1.892, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9110914162688e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |