| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018597731076808628, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003719546215361726, | |
| "eval_loss": 2.958796739578247, | |
| "eval_runtime": 101.9058, | |
| "eval_samples_per_second": 11.108, | |
| "eval_steps_per_second": 5.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001859773107680863, | |
| "grad_norm": 60.900169372558594, | |
| "learning_rate": 5e-05, | |
| "loss": 11.3994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003719546215361726, | |
| "grad_norm": 40.15205001831055, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003719546215361726, | |
| "eval_loss": 1.8373997211456299, | |
| "eval_runtime": 107.9048, | |
| "eval_samples_per_second": 10.491, | |
| "eval_steps_per_second": 5.245, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0055793193230425885, | |
| "grad_norm": 30.710779190063477, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.0517, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007439092430723452, | |
| "grad_norm": 49.18103790283203, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9371, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007439092430723452, | |
| "eval_loss": 1.749384880065918, | |
| "eval_runtime": 108.0029, | |
| "eval_samples_per_second": 10.481, | |
| "eval_steps_per_second": 5.241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009298865538404314, | |
| "grad_norm": 44.902671813964844, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.5632, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011158638646085177, | |
| "grad_norm": 21.01249122619629, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011158638646085177, | |
| "eval_loss": 1.7419497966766357, | |
| "eval_runtime": 108.0936, | |
| "eval_samples_per_second": 10.472, | |
| "eval_steps_per_second": 5.236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01301841175376604, | |
| "grad_norm": 31.042816162109375, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.7182, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014878184861446904, | |
| "grad_norm": 32.54092025756836, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.8618, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014878184861446904, | |
| "eval_loss": 1.6697747707366943, | |
| "eval_runtime": 108.181, | |
| "eval_samples_per_second": 10.464, | |
| "eval_steps_per_second": 5.232, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016737957969127765, | |
| "grad_norm": 23.594846725463867, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.3459, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018597731076808628, | |
| "grad_norm": 24.871923446655273, | |
| "learning_rate": 0.0, | |
| "loss": 6.6075, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018597731076808628, | |
| "eval_loss": 1.6488146781921387, | |
| "eval_runtime": 108.2346, | |
| "eval_samples_per_second": 10.459, | |
| "eval_steps_per_second": 5.229, | |
| "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": 9376794125795328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |