| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01231830500123183, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002463661000246366, | |
| "eval_loss": 0.8827053308486938, | |
| "eval_runtime": 185.0064, | |
| "eval_samples_per_second": 9.238, | |
| "eval_steps_per_second": 4.621, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001231830500123183, | |
| "grad_norm": 0.343232125043869, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6546, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002463661000246366, | |
| "grad_norm": 0.4824935495853424, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7633, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002463661000246366, | |
| "eval_loss": 0.7920751571655273, | |
| "eval_runtime": 186.2524, | |
| "eval_samples_per_second": 9.176, | |
| "eval_steps_per_second": 4.591, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003695491500369549, | |
| "grad_norm": 0.49396812915802, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.564, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004927322000492732, | |
| "grad_norm": 0.4514356255531311, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5986, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004927322000492732, | |
| "eval_loss": 0.6488857269287109, | |
| "eval_runtime": 186.4078, | |
| "eval_samples_per_second": 9.168, | |
| "eval_steps_per_second": 4.587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006159152500615915, | |
| "grad_norm": 0.4030328392982483, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7381, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007390983000739098, | |
| "grad_norm": 0.4189673662185669, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5604, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007390983000739098, | |
| "eval_loss": 0.6136700510978699, | |
| "eval_runtime": 186.5457, | |
| "eval_samples_per_second": 9.161, | |
| "eval_steps_per_second": 4.583, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008622813500862282, | |
| "grad_norm": 0.31886205077171326, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7209, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009854644000985464, | |
| "grad_norm": 0.4157666862010956, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6725, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009854644000985464, | |
| "eval_loss": 0.6030021905899048, | |
| "eval_runtime": 187.4873, | |
| "eval_samples_per_second": 9.115, | |
| "eval_steps_per_second": 4.56, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011086474501108648, | |
| "grad_norm": 0.3123442232608795, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4155, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01231830500123183, | |
| "grad_norm": 0.26258960366249084, | |
| "learning_rate": 0.0, | |
| "loss": 0.6081, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01231830500123183, | |
| "eval_loss": 0.6012914180755615, | |
| "eval_runtime": 186.2751, | |
| "eval_samples_per_second": 9.175, | |
| "eval_steps_per_second": 4.59, | |
| "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": 1.5813774321647616e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |