| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031413612565445025, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010471204188481676, | |
| "eval_loss": 1.769338607788086, | |
| "eval_runtime": 56.7426, | |
| "eval_samples_per_second": 7.102, | |
| "eval_steps_per_second": 3.56, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031413612565445027, | |
| "grad_norm": 1.1814874410629272, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0062827225130890054, | |
| "grad_norm": 2.5954596996307373, | |
| "learning_rate": 0.00012, | |
| "loss": 7.3216, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "eval_loss": 1.6977342367172241, | |
| "eval_runtime": 57.2348, | |
| "eval_samples_per_second": 7.041, | |
| "eval_steps_per_second": 3.529, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009424083769633508, | |
| "grad_norm": 1.755470633506775, | |
| "learning_rate": 0.00018, | |
| "loss": 7.0334, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012565445026178011, | |
| "grad_norm": 1.8192013502120972, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.6012, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015706806282722512, | |
| "grad_norm": 1.5765700340270996, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.1287, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016753926701570682, | |
| "eval_loss": 1.506831407546997, | |
| "eval_runtime": 57.3962, | |
| "eval_samples_per_second": 7.021, | |
| "eval_steps_per_second": 3.519, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018848167539267015, | |
| "grad_norm": 2.498102903366089, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.9627, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02198952879581152, | |
| "grad_norm": 1.5644875764846802, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 5.6048, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "grad_norm": 1.8153458833694458, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.8111, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "eval_loss": 1.4594814777374268, | |
| "eval_runtime": 57.4463, | |
| "eval_samples_per_second": 7.015, | |
| "eval_steps_per_second": 3.516, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028272251308900525, | |
| "grad_norm": 1.5302882194519043, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.9313, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031413612565445025, | |
| "grad_norm": 1.3925120830535889, | |
| "learning_rate": 0.0, | |
| "loss": 5.9116, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801969665310720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |