| { | |
| "epoch": 0.1048462255358807, | |
| "global_step": 225, | |
| "max_steps": 2146, | |
| "logging_steps": 25, | |
| "eval_steps": 50, | |
| "save_steps": 25, | |
| "train_batch_size": 8, | |
| "num_train_epochs": 1, | |
| "num_input_tokens_seen": 0, | |
| "total_flos": 1.0481533050519552e+17, | |
| "log_history": [ | |
| { | |
| "loss": 3.9545, | |
| "grad_norm": 20.241615295410156, | |
| "learning_rate": 5.8139534883720933e-05, | |
| "epoch": 0.011649580615097856, | |
| "step": 25 | |
| }, | |
| { | |
| "loss": 0.6469, | |
| "grad_norm": 0.6640440821647644, | |
| "learning_rate": 0.00011627906976744187, | |
| "epoch": 0.023299161230195712, | |
| "step": 50 | |
| }, | |
| { | |
| "eval_loss": 0.332077294588089, | |
| "eval_runtime": 1616.9669, | |
| "eval_samples_per_second": 0.558, | |
| "eval_steps_per_second": 0.14, | |
| "epoch": 0.023299161230195712, | |
| "step": 50 | |
| }, | |
| { | |
| "loss": 0.1711, | |
| "grad_norm": 0.0800417810678482, | |
| "learning_rate": 0.0001744186046511628, | |
| "epoch": 0.03494874184529357, | |
| "step": 75 | |
| }, | |
| { | |
| "loss": 0.4039, | |
| "grad_norm": 0.19737310707569122, | |
| "learning_rate": 0.00023255813953488373, | |
| "epoch": 0.046598322460391424, | |
| "step": 100 | |
| }, | |
| { | |
| "eval_loss": 0.6975870728492737, | |
| "eval_runtime": 1615.7283, | |
| "eval_samples_per_second": 0.559, | |
| "eval_steps_per_second": 0.14, | |
| "epoch": 0.046598322460391424, | |
| "step": 100 | |
| }, | |
| { | |
| "loss": 0.2002, | |
| "grad_norm": 0.0352032296359539, | |
| "learning_rate": 0.00029069767441860465, | |
| "epoch": 0.058247903075489285, | |
| "step": 125 | |
| }, | |
| { | |
| "loss": 0.3939, | |
| "grad_norm": 0.17062194645404816, | |
| "learning_rate": 0.0003488372093023256, | |
| "epoch": 0.06989748369058714, | |
| "step": 150 | |
| }, | |
| { | |
| "eval_loss": 0.2825596034526825, | |
| "eval_runtime": 1614.1197, | |
| "eval_samples_per_second": 0.559, | |
| "eval_steps_per_second": 0.14, | |
| "epoch": 0.06989748369058714, | |
| "step": 150 | |
| }, | |
| { | |
| "loss": 0.1607, | |
| "grad_norm": 0.08992636203765869, | |
| "learning_rate": 0.00040697674418604653, | |
| "epoch": 0.081547064305685, | |
| "step": 175 | |
| }, | |
| { | |
| "loss": 0.3829, | |
| "grad_norm": 0.960233747959137, | |
| "learning_rate": 0.00046511627906976747, | |
| "epoch": 0.09319664492078285, | |
| "step": 200 | |
| }, | |
| { | |
| "eval_loss": 0.2506251931190491, | |
| "eval_runtime": 1617.641, | |
| "eval_samples_per_second": 0.558, | |
| "eval_steps_per_second": 0.14, | |
| "epoch": 0.09319664492078285, | |
| "step": 200 | |
| }, | |
| { | |
| "loss": 0.1605, | |
| "grad_norm": 0.04875573888421059, | |
| "learning_rate": 0.0004974106680476438, | |
| "epoch": 0.1048462255358807, | |
| "step": 225 | |
| } | |
| ], | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "is_hyper_param_search": false, | |
| "trial_name": null, | |
| "trial_params": null, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_training_stop": false, | |
| "should_epoch_stop": false, | |
| "should_save": true, | |
| "should_evaluate": false, | |
| "should_log": false | |
| }, | |
| "attributes": {} | |
| } | |
| } | |
| } |