| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.477832512315271, | |
| "eval_steps": 100, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.3109243697478994e-05, | |
| "loss": 1.0832, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.100840336134454e-05, | |
| "loss": 0.4234, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.36679086089134216, | |
| "eval_runtime": 111.544, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.8907563025210083e-05, | |
| "loss": 0.3757, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.6806722689075634e-05, | |
| "loss": 0.3644, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.32610517740249634, | |
| "eval_runtime": 111.5555, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 0.3444, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.2605042016806723e-05, | |
| "loss": 0.3289, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.3098466098308563, | |
| "eval_runtime": 111.5402, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.050420168067227e-05, | |
| "loss": 0.3027, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 8.403361344537817e-06, | |
| "loss": 0.2973, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.2937043309211731, | |
| "eval_runtime": 111.5631, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.3025210084033615e-06, | |
| "loss": 0.3113, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.2016806722689085e-06, | |
| "loss": 0.2787, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.28651753067970276, | |
| "eval_runtime": 111.552, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.1008403361344543e-06, | |
| "loss": 0.2982, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0, | |
| "loss": 0.3138, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.28348788619041443, | |
| "eval_runtime": 111.5723, | |
| "eval_samples_per_second": 1.219, | |
| "eval_steps_per_second": 0.152, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 6.9835844772864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |