| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007647452442405124, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.647452442405124e-05, | |
| "grad_norm": 2.78946852684021, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.647452442405124e-05, | |
| "eval_loss": 1.946945309638977, | |
| "eval_runtime": 360.742, | |
| "eval_samples_per_second": 15.263, | |
| "eval_steps_per_second": 7.631, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015294904884810247, | |
| "grad_norm": 1.5727864503860474, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5713, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002294235732721537, | |
| "grad_norm": 1.5884180068969727, | |
| "learning_rate": 6e-05, | |
| "loss": 8.1727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002294235732721537, | |
| "eval_loss": 1.9464224576950073, | |
| "eval_runtime": 358.8588, | |
| "eval_samples_per_second": 15.343, | |
| "eval_steps_per_second": 7.672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00030589809769620494, | |
| "grad_norm": 1.8929306268692017, | |
| "learning_rate": 8e-05, | |
| "loss": 7.2029, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003823726221202562, | |
| "grad_norm": 1.1344847679138184, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004588471465443074, | |
| "grad_norm": 0.9726885557174683, | |
| "learning_rate": 0.00012, | |
| "loss": 6.7759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004588471465443074, | |
| "eval_loss": 1.9414023160934448, | |
| "eval_runtime": 212.9328, | |
| "eval_samples_per_second": 25.858, | |
| "eval_steps_per_second": 12.929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005353216709683586, | |
| "grad_norm": 2.1057753562927246, | |
| "learning_rate": 0.00014, | |
| "loss": 7.3434, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006117961953924099, | |
| "grad_norm": 1.5885932445526123, | |
| "learning_rate": 0.00016, | |
| "loss": 8.5249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006882707198164612, | |
| "grad_norm": 4.077880382537842, | |
| "learning_rate": 0.00018, | |
| "loss": 6.8275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006882707198164612, | |
| "eval_loss": 1.9185253381729126, | |
| "eval_runtime": 187.0646, | |
| "eval_samples_per_second": 29.434, | |
| "eval_steps_per_second": 14.717, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007647452442405124, | |
| "grad_norm": 4.48407506942749, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9738, | |
| "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": 1669467973091328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |