| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029331964508322946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "grad_norm": 1.087234616279602, | |
| "learning_rate": 2e-05, | |
| "loss": 1.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "eval_loss": 1.4804340600967407, | |
| "eval_runtime": 36.127, | |
| "eval_samples_per_second": 39.749, | |
| "eval_steps_per_second": 19.874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005866392901664589, | |
| "grad_norm": 0.8038930296897888, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3127, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "grad_norm": 0.9076142311096191, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3753, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008799589352496884, | |
| "eval_loss": 1.4741162061691284, | |
| "eval_runtime": 36.0889, | |
| "eval_samples_per_second": 39.791, | |
| "eval_steps_per_second": 19.895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011732785803329178, | |
| "grad_norm": 1.0265518426895142, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5025, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014665982254161473, | |
| "grad_norm": 0.9377641081809998, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4362, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "grad_norm": 0.8098152279853821, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017599178704993767, | |
| "eval_loss": 1.4094159603118896, | |
| "eval_runtime": 36.0993, | |
| "eval_samples_per_second": 39.779, | |
| "eval_steps_per_second": 19.89, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002053237515582606, | |
| "grad_norm": 0.8570644855499268, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4943, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023465571606658357, | |
| "grad_norm": 1.0614972114562988, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3981, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "grad_norm": 0.7946088314056396, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3035, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002639876805749065, | |
| "eval_loss": 1.3043134212493896, | |
| "eval_runtime": 35.9797, | |
| "eval_samples_per_second": 39.911, | |
| "eval_steps_per_second": 19.956, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029331964508322946, | |
| "grad_norm": 0.7848902940750122, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3551, | |
| "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": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |