| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011467889908256881, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011467889908256881, | |
| "grad_norm": 0.6337073445320129, | |
| "learning_rate": 2e-05, | |
| "loss": 7.6449, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011467889908256881, | |
| "eval_loss": 1.7937849760055542, | |
| "eval_runtime": 27.7995, | |
| "eval_samples_per_second": 13.238, | |
| "eval_steps_per_second": 6.619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022935779816513763, | |
| "grad_norm": 0.3841286301612854, | |
| "learning_rate": 4e-05, | |
| "loss": 5.9666, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034403669724770644, | |
| "grad_norm": 0.45325732231140137, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8753, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034403669724770644, | |
| "eval_loss": 1.7932604551315308, | |
| "eval_runtime": 26.6785, | |
| "eval_samples_per_second": 13.794, | |
| "eval_steps_per_second": 6.897, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0045871559633027525, | |
| "grad_norm": 1.2741070985794067, | |
| "learning_rate": 8e-05, | |
| "loss": 9.1738, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005733944954128441, | |
| "grad_norm": 0.6461805105209351, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9995, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006880733944954129, | |
| "grad_norm": 0.6756094694137573, | |
| "learning_rate": 0.00012, | |
| "loss": 7.2973, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006880733944954129, | |
| "eval_loss": 1.7852340936660767, | |
| "eval_runtime": 26.7166, | |
| "eval_samples_per_second": 13.774, | |
| "eval_steps_per_second": 6.887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008027522935779817, | |
| "grad_norm": 0.4998139441013336, | |
| "learning_rate": 0.00014, | |
| "loss": 7.1038, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009174311926605505, | |
| "grad_norm": 0.8987786173820496, | |
| "learning_rate": 0.00016, | |
| "loss": 6.2242, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010321100917431193, | |
| "grad_norm": 1.180274248123169, | |
| "learning_rate": 0.00018, | |
| "loss": 7.2237, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010321100917431193, | |
| "eval_loss": 1.7290107011795044, | |
| "eval_runtime": 26.7285, | |
| "eval_samples_per_second": 13.768, | |
| "eval_steps_per_second": 6.884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011467889908256881, | |
| "grad_norm": 0.8208650946617126, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2877, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6274650262732800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |