| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00039876471552568267, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.3292157184189422e-05, | |
| "eval_loss": 2.3748350143432617, | |
| "eval_runtime": 2056.8986, | |
| "eval_samples_per_second": 11.55, | |
| "eval_steps_per_second": 5.775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.987647155256827e-05, | |
| "grad_norm": 0.8939356803894043, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1183, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.975294310513654e-05, | |
| "grad_norm": 1.2293646335601807, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5036, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010633725747351538, | |
| "eval_loss": 2.133735418319702, | |
| "eval_runtime": 2065.5153, | |
| "eval_samples_per_second": 11.502, | |
| "eval_steps_per_second": 5.751, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001196294146577048, | |
| "grad_norm": 1.169637680053711, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2538, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00015950588621027308, | |
| "grad_norm": 0.7869271636009216, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9268, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00019938235776284133, | |
| "grad_norm": 1.1890661716461182, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8888, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00021267451494703075, | |
| "eval_loss": 1.7299827337265015, | |
| "eval_runtime": 2067.6299, | |
| "eval_samples_per_second": 11.49, | |
| "eval_steps_per_second": 5.745, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002392588293154096, | |
| "grad_norm": 1.4860124588012695, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7889, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00027913530086797785, | |
| "grad_norm": 0.8257107138633728, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7835, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00031901177242054616, | |
| "grad_norm": 0.6575050950050354, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.5446, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00031901177242054616, | |
| "eval_loss": 1.5880478620529175, | |
| "eval_runtime": 2067.4112, | |
| "eval_samples_per_second": 11.492, | |
| "eval_steps_per_second": 5.746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003588882439731144, | |
| "grad_norm": 0.6337928175926208, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.7106, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00039876471552568267, | |
| "grad_norm": 0.7751510739326477, | |
| "learning_rate": 0.0, | |
| "loss": 1.5877, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7519945579560960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |