| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017028522775649212, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00034057045551298427, | |
| "eval_loss": 1.7009656429290771, | |
| "eval_runtime": 99.2017, | |
| "eval_samples_per_second": 12.47, | |
| "eval_steps_per_second": 6.24, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017028522775649213, | |
| "grad_norm": 0.27365946769714355, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034057045551298426, | |
| "grad_norm": 0.5234311819076538, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0425, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034057045551298426, | |
| "eval_loss": 1.6530998945236206, | |
| "eval_runtime": 99.8257, | |
| "eval_samples_per_second": 12.392, | |
| "eval_steps_per_second": 6.201, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005108556832694764, | |
| "grad_norm": 0.6932932138442993, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1643, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006811409110259685, | |
| "grad_norm": 0.40464410185813904, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9458, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006811409110259685, | |
| "eval_loss": 1.4234973192214966, | |
| "eval_runtime": 99.937, | |
| "eval_samples_per_second": 12.378, | |
| "eval_steps_per_second": 6.194, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008514261387824606, | |
| "grad_norm": 0.7656698226928711, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7984, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010217113665389528, | |
| "grad_norm": 0.4315115213394165, | |
| "learning_rate": 5e-05, | |
| "loss": 0.878, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010217113665389528, | |
| "eval_loss": 1.3054722547531128, | |
| "eval_runtime": 99.9945, | |
| "eval_samples_per_second": 12.371, | |
| "eval_steps_per_second": 6.19, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011919965942954448, | |
| "grad_norm": 0.5621501803398132, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.98, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01362281822051937, | |
| "grad_norm": 0.5246570110321045, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01362281822051937, | |
| "eval_loss": 1.2319979667663574, | |
| "eval_runtime": 100.1281, | |
| "eval_samples_per_second": 12.354, | |
| "eval_steps_per_second": 6.182, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01532567049808429, | |
| "grad_norm": 0.6063374876976013, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9623, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017028522775649212, | |
| "grad_norm": 0.4231788218021393, | |
| "learning_rate": 0.0, | |
| "loss": 0.8506, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017028522775649212, | |
| "eval_loss": 1.2166956663131714, | |
| "eval_runtime": 99.9676, | |
| "eval_samples_per_second": 12.374, | |
| "eval_steps_per_second": 6.192, | |
| "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": 1.202910734057472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |