| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00984009840098401, | |
| "eval_steps": 9, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005466721333880005, | |
| "eval_loss": 0.947159469127655, | |
| "eval_runtime": 419.8436, | |
| "eval_samples_per_second": 7.338, | |
| "eval_steps_per_second": 0.919, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016400164001640015, | |
| "grad_norm": 0.40049853920936584, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9586, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003280032800328003, | |
| "grad_norm": 0.5728951096534729, | |
| "learning_rate": 6e-05, | |
| "loss": 0.899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004920049200492005, | |
| "grad_norm": 0.5787760615348816, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9511, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004920049200492005, | |
| "eval_loss": 0.8331949710845947, | |
| "eval_runtime": 422.8511, | |
| "eval_samples_per_second": 7.286, | |
| "eval_steps_per_second": 0.913, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006560065600656006, | |
| "grad_norm": 0.3018288016319275, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8476, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008200082000820008, | |
| "grad_norm": 0.2912035286426544, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6816, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00984009840098401, | |
| "grad_norm": 0.39786526560783386, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7029, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00984009840098401, | |
| "eval_loss": 0.6832850575447083, | |
| "eval_runtime": 422.898, | |
| "eval_samples_per_second": 7.285, | |
| "eval_steps_per_second": 0.913, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.693768229879808e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |