| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01804402742692169, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036088054853843375, | |
| "eval_loss": 2.0533976554870605, | |
| "eval_runtime": 189.6776, | |
| "eval_samples_per_second": 6.153, | |
| "eval_steps_per_second": 3.079, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001804402742692169, | |
| "grad_norm": 2.8719000816345215, | |
| "learning_rate": 5e-05, | |
| "loss": 7.8798, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003608805485384338, | |
| "grad_norm": 4.422485828399658, | |
| "learning_rate": 0.0001, | |
| "loss": 7.909, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003608805485384338, | |
| "eval_loss": 1.6814217567443848, | |
| "eval_runtime": 189.7908, | |
| "eval_samples_per_second": 6.149, | |
| "eval_steps_per_second": 3.077, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0054132082280765065, | |
| "grad_norm": 4.070103168487549, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.9845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007217610970768676, | |
| "grad_norm": 4.116288661956787, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.6893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007217610970768676, | |
| "eval_loss": 1.0644481182098389, | |
| "eval_runtime": 189.9259, | |
| "eval_samples_per_second": 6.145, | |
| "eval_steps_per_second": 3.075, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009022013713460845, | |
| "grad_norm": 5.424530029296875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.911, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010826416456153013, | |
| "grad_norm": 3.1955983638763428, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010826416456153013, | |
| "eval_loss": 0.9001002311706543, | |
| "eval_runtime": 189.7918, | |
| "eval_samples_per_second": 6.149, | |
| "eval_steps_per_second": 3.077, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012630819198845183, | |
| "grad_norm": 3.5302228927612305, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.404, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014435221941537351, | |
| "grad_norm": 3.5075478553771973, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.4593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014435221941537351, | |
| "eval_loss": 0.8535332083702087, | |
| "eval_runtime": 189.7319, | |
| "eval_samples_per_second": 6.151, | |
| "eval_steps_per_second": 3.078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01623962468422952, | |
| "grad_norm": 4.0576958656311035, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01804402742692169, | |
| "grad_norm": 3.0427911281585693, | |
| "learning_rate": 0.0, | |
| "loss": 3.4048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01804402742692169, | |
| "eval_loss": 0.8458905816078186, | |
| "eval_runtime": 191.182, | |
| "eval_samples_per_second": 6.104, | |
| "eval_steps_per_second": 3.055, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8528053583872e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |