| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01238390092879257, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001238390092879257, | |
| "grad_norm": 3.4508397579193115, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001238390092879257, | |
| "eval_loss": 2.4396731853485107, | |
| "eval_runtime": 15.3414, | |
| "eval_samples_per_second": 22.162, | |
| "eval_steps_per_second": 11.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002476780185758514, | |
| "grad_norm": 3.828749895095825, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9901, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037151702786377707, | |
| "grad_norm": 3.8040151596069336, | |
| "learning_rate": 6e-05, | |
| "loss": 2.333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037151702786377707, | |
| "eval_loss": 2.3865134716033936, | |
| "eval_runtime": 14.9594, | |
| "eval_samples_per_second": 22.728, | |
| "eval_steps_per_second": 11.364, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004953560371517028, | |
| "grad_norm": 3.526742696762085, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2862, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006191950464396285, | |
| "grad_norm": 4.159535884857178, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007430340557275541, | |
| "grad_norm": 2.6144652366638184, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007430340557275541, | |
| "eval_loss": 1.816732406616211, | |
| "eval_runtime": 14.9855, | |
| "eval_samples_per_second": 22.689, | |
| "eval_steps_per_second": 11.344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0086687306501548, | |
| "grad_norm": 2.634336471557617, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009907120743034056, | |
| "grad_norm": 2.586655855178833, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3643, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011145510835913313, | |
| "grad_norm": 2.1898770332336426, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3185, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011145510835913313, | |
| "eval_loss": 1.5426946878433228, | |
| "eval_runtime": 15.028, | |
| "eval_samples_per_second": 22.625, | |
| "eval_steps_per_second": 11.312, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 2.10044002532959, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4211, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |