| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4050222762251924, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04050222762251924, | |
| "eval_accuracy": 0.07313909615825066, | |
| "eval_loss": 5.535554885864258, | |
| "eval_runtime": 288.6011, | |
| "eval_samples_per_second": 14.075, | |
| "eval_steps_per_second": 0.44, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08100445524503848, | |
| "eval_accuracy": 0.09321176989128148, | |
| "eval_loss": 5.312517166137695, | |
| "eval_runtime": 289.0997, | |
| "eval_samples_per_second": 14.051, | |
| "eval_steps_per_second": 0.439, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12150668286755771, | |
| "eval_accuracy": 0.1025266924717497, | |
| "eval_loss": 5.209850788116455, | |
| "eval_runtime": 288.9641, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 0.44, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16200891049007696, | |
| "eval_accuracy": 0.10690876214872297, | |
| "eval_loss": 5.157820224761963, | |
| "eval_runtime": 288.9416, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 0.44, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2025111381125962, | |
| "grad_norm": 4.206667900085449, | |
| "learning_rate": 4.6624814364790066e-05, | |
| "loss": 5.3676, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2025111381125962, | |
| "eval_accuracy": 0.11018071094865264, | |
| "eval_loss": 5.133289337158203, | |
| "eval_runtime": 288.702, | |
| "eval_samples_per_second": 14.07, | |
| "eval_steps_per_second": 0.44, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24301336573511542, | |
| "eval_accuracy": 0.1130116481766369, | |
| "eval_loss": 5.102772235870361, | |
| "eval_runtime": 288.9586, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 0.44, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28351559335763465, | |
| "eval_accuracy": 0.11700033155499291, | |
| "eval_loss": 5.068767070770264, | |
| "eval_runtime": 288.67, | |
| "eval_samples_per_second": 14.071, | |
| "eval_steps_per_second": 0.44, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3240178209801539, | |
| "eval_accuracy": 0.1189196062267089, | |
| "eval_loss": 5.049363136291504, | |
| "eval_runtime": 288.7628, | |
| "eval_samples_per_second": 14.067, | |
| "eval_steps_per_second": 0.44, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3645200486026732, | |
| "eval_accuracy": 0.12067047317065237, | |
| "eval_loss": 5.0373969078063965, | |
| "eval_runtime": 288.4915, | |
| "eval_samples_per_second": 14.08, | |
| "eval_steps_per_second": 0.44, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4050222762251924, | |
| "grad_norm": 2.745899200439453, | |
| "learning_rate": 4.324962872958013e-05, | |
| "loss": 5.0801, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4050222762251924, | |
| "eval_accuracy": 0.12251942264285288, | |
| "eval_loss": 5.018136024475098, | |
| "eval_runtime": 288.8733, | |
| "eval_samples_per_second": 14.062, | |
| "eval_steps_per_second": 0.44, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4050222762251924, | |
| "step": 1000, | |
| "total_flos": 7.03593355149312e+17, | |
| "train_loss": 5.223868896484375, | |
| "train_runtime": 10418.308, | |
| "train_samples_per_second": 22.746, | |
| "train_steps_per_second": 0.711 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7407, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 7.03593355149312e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |