| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011013215859030838, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011013215859030838, | |
| "grad_norm": 0.8156202435493469, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011013215859030838, | |
| "eval_loss": 0.8059872984886169, | |
| "eval_runtime": 23.4204, | |
| "eval_samples_per_second": 16.353, | |
| "eval_steps_per_second": 8.198, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022026431718061676, | |
| "grad_norm": 0.8691166639328003, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8264, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003303964757709251, | |
| "grad_norm": 0.8915963768959045, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003303964757709251, | |
| "eval_loss": 0.7925938367843628, | |
| "eval_runtime": 22.2371, | |
| "eval_samples_per_second": 17.224, | |
| "eval_steps_per_second": 8.634, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004405286343612335, | |
| "grad_norm": 0.7829200625419617, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005506607929515419, | |
| "grad_norm": 1.2445497512817383, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9861, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006607929515418502, | |
| "grad_norm": 0.7674492597579956, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6552, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006607929515418502, | |
| "eval_loss": 0.6461026072502136, | |
| "eval_runtime": 22.2531, | |
| "eval_samples_per_second": 17.211, | |
| "eval_steps_per_second": 8.628, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007709251101321586, | |
| "grad_norm": 0.6054182052612305, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4957, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00881057268722467, | |
| "grad_norm": 0.5956518054008484, | |
| "learning_rate": 0.00016, | |
| "loss": 0.521, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009911894273127754, | |
| "grad_norm": 0.7739569544792175, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5585, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009911894273127754, | |
| "eval_loss": 0.5488515496253967, | |
| "eval_runtime": 22.2491, | |
| "eval_samples_per_second": 17.214, | |
| "eval_steps_per_second": 8.63, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011013215859030838, | |
| "grad_norm": 0.6800111532211304, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5458, | |
| "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": 3699192920801280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |