| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.96, | |
| "eval_steps": 500, | |
| "global_step": 111, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 2.969418525695801, | |
| "learning_rate": 4.9005367134442235e-05, | |
| "loss": 0.4778, | |
| "num_input_tokens_seen": 33232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 2.1690313816070557, | |
| "learning_rate": 4.6100612100748765e-05, | |
| "loss": 0.3431, | |
| "num_input_tokens_seen": 65520, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.671631813049316, | |
| "learning_rate": 4.151686808475204e-05, | |
| "loss": 0.318, | |
| "num_input_tokens_seen": 97472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 3.928008794784546, | |
| "learning_rate": 3.56188664821012e-05, | |
| "loss": 0.4028, | |
| "num_input_tokens_seen": 128928, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 11.873285293579102, | |
| "learning_rate": 2.8875914991604948e-05, | |
| "loss": 0.1864, | |
| "num_input_tokens_seen": 161248, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 11.22799301147461, | |
| "learning_rate": 2.182455450632803e-05, | |
| "loss": 0.218, | |
| "num_input_tokens_seen": 193728, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 4.876537799835205, | |
| "learning_rate": 1.5025866217114592e-05, | |
| "loss": 0.2257, | |
| "num_input_tokens_seen": 226048, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 3.1793081760406494, | |
| "learning_rate": 9.020826029175384e-06, | |
| "loss": 0.2099, | |
| "num_input_tokens_seen": 258608, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 4.5291218757629395, | |
| "learning_rate": 4.2872587689039484e-06, | |
| "loss": 0.1456, | |
| "num_input_tokens_seen": 290720, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.929227590560913, | |
| "learning_rate": 1.201817361771837e-06, | |
| "loss": 0.0777, | |
| "num_input_tokens_seen": 323584, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 2.021867036819458, | |
| "learning_rate": 1.0012322041960676e-08, | |
| "loss": 0.0711, | |
| "num_input_tokens_seen": 355456, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "num_input_tokens_seen": 358624, | |
| "step": 111, | |
| "total_flos": 1.5352214341287936e+16, | |
| "train_loss": 0.24338918279957128, | |
| "train_runtime": 8119.2255, | |
| "train_samples_per_second": 0.111, | |
| "train_steps_per_second": 0.014 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 111, | |
| "num_input_tokens_seen": 358624, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5352214341287936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |