| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0035836513823935207, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.167302764787042e-05, | |
| "eval_loss": 2.5433077812194824, | |
| "eval_runtime": 177.8371, | |
| "eval_samples_per_second": 33.036, | |
| "eval_steps_per_second": 16.521, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035836513823935207, | |
| "grad_norm": 2.391714572906494, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007167302764787041, | |
| "grad_norm": 2.358987808227539, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4191, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007167302764787041, | |
| "eval_loss": 2.255765676498413, | |
| "eval_runtime": 177.5269, | |
| "eval_samples_per_second": 33.094, | |
| "eval_steps_per_second": 16.55, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010750954147180562, | |
| "grad_norm": 2.2335422039031982, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0313, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014334605529574083, | |
| "grad_norm": 2.0591068267822266, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6829, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014334605529574083, | |
| "eval_loss": 1.4891319274902344, | |
| "eval_runtime": 177.2979, | |
| "eval_samples_per_second": 33.136, | |
| "eval_steps_per_second": 16.571, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017918256911967603, | |
| "grad_norm": 2.6264262199401855, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2995, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021501908294361124, | |
| "grad_norm": 2.1978797912597656, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0021501908294361124, | |
| "eval_loss": 1.3642194271087646, | |
| "eval_runtime": 177.9365, | |
| "eval_samples_per_second": 33.017, | |
| "eval_steps_per_second": 16.512, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025085559676754645, | |
| "grad_norm": 2.451869249343872, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028669211059148166, | |
| "grad_norm": 2.7362568378448486, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2605, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028669211059148166, | |
| "eval_loss": 1.339518666267395, | |
| "eval_runtime": 177.3424, | |
| "eval_samples_per_second": 33.128, | |
| "eval_steps_per_second": 16.567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032252862441541686, | |
| "grad_norm": 2.2676689624786377, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4433, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0035836513823935207, | |
| "grad_norm": 1.9010828733444214, | |
| "learning_rate": 0.0, | |
| "loss": 1.369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035836513823935207, | |
| "eval_loss": 1.3369534015655518, | |
| "eval_runtime": 177.2715, | |
| "eval_samples_per_second": 33.141, | |
| "eval_steps_per_second": 16.573, | |
| "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": 1291749490163712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |