| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7936507936507936, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015873015873015872, | |
| "eval_loss": 5.212655544281006, | |
| "eval_runtime": 0.7189, | |
| "eval_samples_per_second": 37.556, | |
| "eval_steps_per_second": 19.474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 4.168554782867432, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 4.182918071746826, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8016, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "eval_loss": 4.441361904144287, | |
| "eval_runtime": 0.7142, | |
| "eval_samples_per_second": 37.805, | |
| "eval_steps_per_second": 19.602, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 4.0556817054748535, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.9843, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 2.6014246940612793, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1812, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "eval_loss": 3.064946413040161, | |
| "eval_runtime": 0.8004, | |
| "eval_samples_per_second": 33.732, | |
| "eval_steps_per_second": 17.491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 2.9831440448760986, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9105, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 3.131338596343994, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "eval_loss": 2.777977228164673, | |
| "eval_runtime": 0.7213, | |
| "eval_samples_per_second": 37.432, | |
| "eval_steps_per_second": 19.409, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 3.399858236312866, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 3.2086362838745117, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9717, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "eval_loss": 2.7027430534362793, | |
| "eval_runtime": 0.7248, | |
| "eval_samples_per_second": 37.252, | |
| "eval_steps_per_second": 19.316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 3.187225103378296, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9323, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 3.1809988021850586, | |
| "learning_rate": 0.0, | |
| "loss": 2.6594, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "eval_loss": 2.692059278488159, | |
| "eval_runtime": 0.7048, | |
| "eval_samples_per_second": 38.309, | |
| "eval_steps_per_second": 19.864, | |
| "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": 1202727577190400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |