| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020140175622331427, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.028035124466285e-05, | |
| "eval_loss": 0.7639467120170593, | |
| "eval_runtime": 285.9556, | |
| "eval_samples_per_second": 36.558, | |
| "eval_steps_per_second": 18.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020140175622331428, | |
| "grad_norm": 1.4424469470977783, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6932, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040280351244662856, | |
| "grad_norm": 1.5913922786712646, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6406, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00040280351244662856, | |
| "eval_loss": 0.47510087490081787, | |
| "eval_runtime": 286.4783, | |
| "eval_samples_per_second": 36.491, | |
| "eval_steps_per_second": 18.246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006042052686699428, | |
| "grad_norm": 1.1280369758605957, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3627, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008056070248932571, | |
| "grad_norm": 1.5159434080123901, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008056070248932571, | |
| "eval_loss": 0.11229679733514786, | |
| "eval_runtime": 286.7446, | |
| "eval_samples_per_second": 36.458, | |
| "eval_steps_per_second": 18.229, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010070087811165714, | |
| "grad_norm": 1.573866844177246, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1046, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "grad_norm": 1.3068312406539917, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "eval_loss": 0.08075004816055298, | |
| "eval_runtime": 287.6486, | |
| "eval_samples_per_second": 36.343, | |
| "eval_steps_per_second": 18.171, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014098122935631999, | |
| "grad_norm": 1.3475022315979004, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0768, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0016112140497865142, | |
| "grad_norm": 1.0738025903701782, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016112140497865142, | |
| "eval_loss": 0.06289525330066681, | |
| "eval_runtime": 287.6301, | |
| "eval_samples_per_second": 36.345, | |
| "eval_steps_per_second": 18.173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018126158060098284, | |
| "grad_norm": 0.6630128026008606, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0020140175622331427, | |
| "grad_norm": 0.7363331913948059, | |
| "learning_rate": 0.0, | |
| "loss": 0.0592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020140175622331427, | |
| "eval_loss": 0.06008023023605347, | |
| "eval_runtime": 287.1634, | |
| "eval_samples_per_second": 36.404, | |
| "eval_steps_per_second": 18.202, | |
| "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": 1202727577190400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |