| { | |
| "best_global_step": 600, | |
| "best_metric": 0.5126457214355469, | |
| "best_model_checkpoint": "./opencoder8b_finetuned/checkpoint-400", | |
| "epoch": 3.0, | |
| "eval_steps": 200, | |
| "global_step": 732, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4098360655737705, | |
| "grad_norm": 0.2757495045661926, | |
| "learning_rate": 8.114754098360657e-06, | |
| "loss": 1.269, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.3459929823875427, | |
| "learning_rate": 9.879146512908832e-06, | |
| "loss": 1.041, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_loss": 0.8448625802993774, | |
| "eval_runtime": 200.4789, | |
| "eval_samples_per_second": 4.33, | |
| "eval_steps_per_second": 0.544, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2295081967213115, | |
| "grad_norm": 0.16594329476356506, | |
| "learning_rate": 9.372404789155199e-06, | |
| "loss": 0.708, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 0.17427127063274384, | |
| "learning_rate": 8.510154039531063e-06, | |
| "loss": 0.5883, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "eval_loss": 0.5587947964668274, | |
| "eval_runtime": 200.5362, | |
| "eval_samples_per_second": 4.328, | |
| "eval_steps_per_second": 0.544, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0491803278688523, | |
| "grad_norm": 0.17177526652812958, | |
| "learning_rate": 7.3625016623302155e-06, | |
| "loss": 0.5556, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 0.26423564553260803, | |
| "learning_rate": 6.022760330631006e-06, | |
| "loss": 0.5291, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "eval_loss": 0.5126457214355469, | |
| "eval_runtime": 199.6781, | |
| "eval_samples_per_second": 4.347, | |
| "eval_steps_per_second": 0.546, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.8688524590163933, | |
| "grad_norm": 0.23801229894161224, | |
| "learning_rate": 4.599860978031383e-06, | |
| "loss": 0.5239, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.34827040065536e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |