| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00852969399722785, | |
| "eval_steps": 2, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042648469986139245, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042648469986139245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 50.2131, | |
| "eval_samples_per_second": 19.676, | |
| "eval_steps_per_second": 9.838, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008529693997227849, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008529693997227849, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5511, | |
| "eval_samples_per_second": 19.939, | |
| "eval_steps_per_second": 9.97, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012794540995841775, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017059387994455698, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017059387994455698, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.4976, | |
| "eval_samples_per_second": 19.961, | |
| "eval_steps_per_second": 9.98, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021324234993069626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002558908199168355, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002558908199168355, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5029, | |
| "eval_samples_per_second": 19.958, | |
| "eval_steps_per_second": 9.979, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029853928990297473, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034118775988911396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034118775988911396, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5049, | |
| "eval_samples_per_second": 19.958, | |
| "eval_steps_per_second": 9.979, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0038383622987525324, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5265, | |
| "eval_samples_per_second": 19.949, | |
| "eval_steps_per_second": 9.974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0046913316984753175, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00511781639833671, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00511781639833671, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5221, | |
| "eval_samples_per_second": 19.951, | |
| "eval_steps_per_second": 9.975, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005544301098198102, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0059707857980594945, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0059707857980594945, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.531, | |
| "eval_samples_per_second": 19.947, | |
| "eval_steps_per_second": 9.974, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006397270497920887, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006823755197782279, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006823755197782279, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5109, | |
| "eval_samples_per_second": 19.955, | |
| "eval_steps_per_second": 9.978, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007250239897643672, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007676724597505065, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007676724597505065, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5165, | |
| "eval_samples_per_second": 19.953, | |
| "eval_steps_per_second": 9.976, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008103209297366456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "eval_loss": NaN, | |
| "eval_runtime": 49.5454, | |
| "eval_samples_per_second": 19.941, | |
| "eval_steps_per_second": 9.971, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2531098047283200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |