| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02622950819672131, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002622950819672131, | |
| "grad_norm": 0.031223058700561523, | |
| "learning_rate": 2e-05, | |
| "loss": 11.756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002622950819672131, | |
| "eval_loss": 11.759812355041504, | |
| "eval_runtime": 5.877, | |
| "eval_samples_per_second": 27.395, | |
| "eval_steps_per_second": 13.782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005245901639344262, | |
| "grad_norm": 0.03421200439333916, | |
| "learning_rate": 4e-05, | |
| "loss": 11.756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007868852459016393, | |
| "grad_norm": 0.04382362961769104, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7597, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007868852459016393, | |
| "eval_loss": 11.759759902954102, | |
| "eval_runtime": 6.9009, | |
| "eval_samples_per_second": 23.33, | |
| "eval_steps_per_second": 11.738, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010491803278688525, | |
| "grad_norm": 0.02897525578737259, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7588, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013114754098360656, | |
| "grad_norm": 0.04384247586131096, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7601, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015737704918032787, | |
| "grad_norm": 0.04108477011322975, | |
| "learning_rate": 0.00012, | |
| "loss": 11.7592, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015737704918032787, | |
| "eval_loss": 11.75953197479248, | |
| "eval_runtime": 6.1771, | |
| "eval_samples_per_second": 26.064, | |
| "eval_steps_per_second": 13.113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018360655737704918, | |
| "grad_norm": 0.03210461512207985, | |
| "learning_rate": 0.00014, | |
| "loss": 11.7568, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02098360655737705, | |
| "grad_norm": 0.042795587331056595, | |
| "learning_rate": 0.00016, | |
| "loss": 11.7597, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02360655737704918, | |
| "grad_norm": 0.03623143583536148, | |
| "learning_rate": 0.00018, | |
| "loss": 11.7611, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02360655737704918, | |
| "eval_loss": 11.759139060974121, | |
| "eval_runtime": 6.1857, | |
| "eval_samples_per_second": 26.028, | |
| "eval_steps_per_second": 13.095, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02622950819672131, | |
| "grad_norm": 0.03370063751935959, | |
| "learning_rate": 0.0002, | |
| "loss": 11.7614, | |
| "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": 4074000875520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |