| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017552242298953691, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.850747432984564e-05, | |
| "eval_loss": 4.441978931427002, | |
| "eval_runtime": 532.0384, | |
| "eval_samples_per_second": 40.58, | |
| "eval_steps_per_second": 10.146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001755224229895369, | |
| "grad_norm": 12.403585433959961, | |
| "learning_rate": 6e-05, | |
| "loss": 27.0048, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003510448459790738, | |
| "grad_norm": 9.272995948791504, | |
| "learning_rate": 0.00012, | |
| "loss": 26.0278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004680597946387651, | |
| "eval_loss": 4.086904525756836, | |
| "eval_runtime": 532.2184, | |
| "eval_samples_per_second": 40.566, | |
| "eval_steps_per_second": 10.142, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005265672689686108, | |
| "grad_norm": 8.849642753601074, | |
| "learning_rate": 0.00018, | |
| "loss": 24.872, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007020896919581476, | |
| "grad_norm": 8.354921340942383, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 23.5208, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008776121149476846, | |
| "grad_norm": 8.811142921447754, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 22.7527, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009361195892775302, | |
| "eval_loss": 3.8560914993286133, | |
| "eval_runtime": 531.7153, | |
| "eval_samples_per_second": 40.604, | |
| "eval_steps_per_second": 10.152, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010531345379372215, | |
| "grad_norm": 7.890682697296143, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 22.7001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012286569609267584, | |
| "grad_norm": 11.67773723602295, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 24.0305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014041793839162952, | |
| "grad_norm": 9.549829483032227, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 22.462, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014041793839162952, | |
| "eval_loss": 3.7929909229278564, | |
| "eval_runtime": 531.5397, | |
| "eval_samples_per_second": 40.618, | |
| "eval_steps_per_second": 10.155, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015797018069058323, | |
| "grad_norm": 7.023437976837158, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 23.2863, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0017552242298953691, | |
| "grad_norm": 7.868184566497803, | |
| "learning_rate": 0.0, | |
| "loss": 22.6354, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 1365169447895040.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |