| { | |
| "best_metric": 0.08017788827419281, | |
| "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-60", | |
| "epoch": 2.987551867219917, | |
| "eval_steps": 10, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 0.12212196737527847, | |
| "learning_rate": 0.0002909538931178862, | |
| "loss": 0.3319, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "eval_loss": 0.12649552524089813, | |
| "eval_runtime": 54.4218, | |
| "eval_samples_per_second": 15.747, | |
| "eval_steps_per_second": 1.984, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 0.26463553309440613, | |
| "learning_rate": 0.00026490666646784665, | |
| "loss": 0.113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "eval_loss": 0.09510459005832672, | |
| "eval_runtime": 54.4488, | |
| "eval_samples_per_second": 15.74, | |
| "eval_steps_per_second": 1.984, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 0.16762037575244904, | |
| "learning_rate": 0.000225, | |
| "loss": 0.0961, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "eval_loss": 0.0864303931593895, | |
| "eval_runtime": 54.4103, | |
| "eval_samples_per_second": 15.751, | |
| "eval_steps_per_second": 1.985, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "grad_norm": 0.17065662145614624, | |
| "learning_rate": 0.00017604722665003956, | |
| "loss": 0.0908, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "eval_loss": 0.0837957039475441, | |
| "eval_runtime": 54.4476, | |
| "eval_samples_per_second": 15.74, | |
| "eval_steps_per_second": 1.984, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "grad_norm": 0.15821295976638794, | |
| "learning_rate": 0.00012395277334996044, | |
| "loss": 0.0846, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "eval_loss": 0.08163361996412277, | |
| "eval_runtime": 54.4496, | |
| "eval_samples_per_second": 15.739, | |
| "eval_steps_per_second": 1.983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.991701244813278, | |
| "grad_norm": 0.18177442252635956, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 0.0806, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.991701244813278, | |
| "eval_loss": 0.08017788827419281, | |
| "eval_runtime": 54.4696, | |
| "eval_samples_per_second": 15.734, | |
| "eval_steps_per_second": 1.983, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.323651452282158, | |
| "grad_norm": 0.2554187476634979, | |
| "learning_rate": 3.509333353215331e-05, | |
| "loss": 0.0756, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.323651452282158, | |
| "eval_loss": 0.08098582923412323, | |
| "eval_runtime": 54.4479, | |
| "eval_samples_per_second": 15.74, | |
| "eval_steps_per_second": 1.984, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.6556016597510372, | |
| "grad_norm": 0.14397203922271729, | |
| "learning_rate": 9.046106882113751e-06, | |
| "loss": 0.0751, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.6556016597510372, | |
| "eval_loss": 0.08046256750822067, | |
| "eval_runtime": 54.4818, | |
| "eval_samples_per_second": 15.73, | |
| "eval_steps_per_second": 1.982, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.987551867219917, | |
| "grad_norm": 0.17934462428092957, | |
| "learning_rate": 0.0, | |
| "loss": 0.0719, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.987551867219917, | |
| "eval_loss": 0.08062426000833511, | |
| "eval_runtime": 54.5959, | |
| "eval_samples_per_second": 15.697, | |
| "eval_steps_per_second": 1.978, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.987551867219917, | |
| "step": 90, | |
| "total_flos": 1.4599781037991526e+17, | |
| "train_loss": 0.1132976253827413, | |
| "train_runtime": 4057.4795, | |
| "train_samples_per_second": 5.7, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4599781037991526e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |