| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007435865658693766, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024786218862312553, | |
| "eval_loss": 2.09014892578125, | |
| "eval_runtime": 305.3412, | |
| "eval_samples_per_second": 5.564, | |
| "eval_steps_per_second": 2.784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007435865658693766, | |
| "grad_norm": 1.1143418550491333, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012393109431156277, | |
| "eval_loss": 1.9998418092727661, | |
| "eval_runtime": 304.6612, | |
| "eval_samples_per_second": 5.577, | |
| "eval_steps_per_second": 2.79, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014871731317387532, | |
| "grad_norm": 1.0754435062408447, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5918, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00223075969760813, | |
| "grad_norm": 1.3846229314804077, | |
| "learning_rate": 0.00012, | |
| "loss": 1.893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024786218862312553, | |
| "eval_loss": 1.2593779563903809, | |
| "eval_runtime": 306.6124, | |
| "eval_samples_per_second": 5.541, | |
| "eval_steps_per_second": 2.772, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029743462634775064, | |
| "grad_norm": 1.2388172149658203, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003717932829346883, | |
| "grad_norm": 0.8172288537025452, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8568, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003717932829346883, | |
| "eval_loss": 0.7768763899803162, | |
| "eval_runtime": 304.5869, | |
| "eval_samples_per_second": 5.578, | |
| "eval_steps_per_second": 2.791, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00446151939521626, | |
| "grad_norm": 0.7465487122535706, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.6662, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004957243772462511, | |
| "eval_loss": 0.6128036975860596, | |
| "eval_runtime": 297.1192, | |
| "eval_samples_per_second": 5.718, | |
| "eval_steps_per_second": 2.861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005205105961085636, | |
| "grad_norm": 1.5202752351760864, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6669, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005948692526955013, | |
| "grad_norm": 0.6265591979026794, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5783, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006196554715578138, | |
| "eval_loss": 0.5611212253570557, | |
| "eval_runtime": 146.0056, | |
| "eval_samples_per_second": 11.637, | |
| "eval_steps_per_second": 5.822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006692279092824389, | |
| "grad_norm": 0.6711304783821106, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.5688, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007435865658693766, | |
| "grad_norm": 0.5014675855636597, | |
| "learning_rate": 0.0, | |
| "loss": 0.5148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007435865658693766, | |
| "eval_loss": 0.5482997298240662, | |
| "eval_runtime": 145.7456, | |
| "eval_samples_per_second": 11.657, | |
| "eval_steps_per_second": 5.832, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.016432204709888e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |