| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 6480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7716049382716049, | |
| "grad_norm": 1.0553990602493286, | |
| "learning_rate": 1.846913580246914e-05, | |
| "loss": 0.9346, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.0959, | |
| "eval_loss": 0.15309424698352814, | |
| "eval_runtime": 7.8759, | |
| "eval_samples_per_second": 154.903, | |
| "eval_steps_per_second": 2.539, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.5432098765432098, | |
| "grad_norm": 0.7297214269638062, | |
| "learning_rate": 1.6925925925925926e-05, | |
| "loss": 0.0763, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.159, | |
| "eval_loss": 0.16104426980018616, | |
| "eval_runtime": 7.6405, | |
| "eval_samples_per_second": 159.674, | |
| "eval_steps_per_second": 2.618, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 2.314814814814815, | |
| "grad_norm": 0.44237253069877625, | |
| "learning_rate": 1.5382716049382717e-05, | |
| "loss": 0.0446, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.0426, | |
| "eval_loss": 0.17489495873451233, | |
| "eval_runtime": 7.8385, | |
| "eval_samples_per_second": 155.642, | |
| "eval_steps_per_second": 2.552, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 3.0864197530864197, | |
| "grad_norm": 0.3801327049732208, | |
| "learning_rate": 1.3839506172839507e-05, | |
| "loss": 0.0275, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.8580246913580245, | |
| "grad_norm": 0.29495081305503845, | |
| "learning_rate": 1.2296296296296298e-05, | |
| "loss": 0.0162, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.1139, | |
| "eval_loss": 0.1843736320734024, | |
| "eval_runtime": 7.7649, | |
| "eval_samples_per_second": 157.118, | |
| "eval_steps_per_second": 2.576, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 4.62962962962963, | |
| "grad_norm": 0.29735738039016724, | |
| "learning_rate": 1.0753086419753086e-05, | |
| "loss": 0.0106, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 9.9508, | |
| "eval_loss": 0.19341909885406494, | |
| "eval_runtime": 7.6995, | |
| "eval_samples_per_second": 158.452, | |
| "eval_steps_per_second": 2.598, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 5.401234567901234, | |
| "grad_norm": 0.07027166336774826, | |
| "learning_rate": 9.209876543209877e-06, | |
| "loss": 0.0076, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 9.9377, | |
| "eval_loss": 0.20017552375793457, | |
| "eval_runtime": 7.6996, | |
| "eval_samples_per_second": 158.45, | |
| "eval_steps_per_second": 2.598, | |
| "step": 3888 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "grad_norm": 0.1504916250705719, | |
| "learning_rate": 7.666666666666667e-06, | |
| "loss": 0.0059, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.944444444444445, | |
| "grad_norm": 0.24264627695083618, | |
| "learning_rate": 6.123456790123458e-06, | |
| "loss": 0.0043, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.0279, | |
| "eval_loss": 0.20386986434459686, | |
| "eval_runtime": 7.7944, | |
| "eval_samples_per_second": 156.523, | |
| "eval_steps_per_second": 2.566, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 7.716049382716049, | |
| "grad_norm": 0.08363181352615356, | |
| "learning_rate": 4.580246913580247e-06, | |
| "loss": 0.0035, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.1566, | |
| "eval_loss": 0.20531675219535828, | |
| "eval_runtime": 7.6989, | |
| "eval_samples_per_second": 158.465, | |
| "eval_steps_per_second": 2.598, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 8.487654320987655, | |
| "grad_norm": 0.13225023448467255, | |
| "learning_rate": 3.0370370370370372e-06, | |
| "loss": 0.0029, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 10.0689, | |
| "eval_loss": 0.20702147483825684, | |
| "eval_runtime": 7.6619, | |
| "eval_samples_per_second": 159.23, | |
| "eval_steps_per_second": 2.61, | |
| "step": 5832 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 0.022540247067809105, | |
| "learning_rate": 1.4938271604938272e-06, | |
| "loss": 0.003, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 4.288315707563704e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |