| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028421202216853774, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": 2.1607179641723633, | |
| "eval_runtime": 16.5482, | |
| "eval_samples_per_second": 44.778, | |
| "eval_steps_per_second": 22.419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "grad_norm": 5.809887886047363, | |
| "learning_rate": 5e-05, | |
| "loss": 9.2478, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 3.9705562591552734, | |
| "learning_rate": 0.0001, | |
| "loss": 9.3405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "eval_loss": 2.0316154956817627, | |
| "eval_runtime": 16.5476, | |
| "eval_samples_per_second": 44.78, | |
| "eval_steps_per_second": 22.42, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "grad_norm": 4.812692642211914, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.7379, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 3.422988176345825, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.7537, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "eval_loss": 1.8818048238754272, | |
| "eval_runtime": 16.6029, | |
| "eval_samples_per_second": 44.631, | |
| "eval_steps_per_second": 22.346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014210601108426887, | |
| "grad_norm": 4.315964698791504, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.5853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 4.046550273895264, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2024, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "eval_loss": 1.8423748016357422, | |
| "eval_runtime": 16.5476, | |
| "eval_samples_per_second": 44.78, | |
| "eval_steps_per_second": 22.42, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019894841551797642, | |
| "grad_norm": 3.8385205268859863, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.1574, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 3.864719867706299, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.5536, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "eval_loss": 1.8288508653640747, | |
| "eval_runtime": 16.7175, | |
| "eval_samples_per_second": 44.325, | |
| "eval_steps_per_second": 22.192, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025579081995168396, | |
| "grad_norm": 4.516152381896973, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.2153, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 4.5708909034729, | |
| "learning_rate": 0.0, | |
| "loss": 8.1108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 1.8269723653793335, | |
| "eval_runtime": 16.8937, | |
| "eval_samples_per_second": 43.862, | |
| "eval_steps_per_second": 21.961, | |
| "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": 429773763379200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |