| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028511960767541983, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.7023921535083966e-05, | |
| "eval_loss": 1.8270176649093628, | |
| "eval_runtime": 507.1676, | |
| "eval_samples_per_second": 14.559, | |
| "eval_steps_per_second": 7.28, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002851196076754198, | |
| "grad_norm": 3.7387678623199463, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9126, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005702392153508396, | |
| "grad_norm": 3.420994281768799, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3458, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005702392153508396, | |
| "eval_loss": 0.9002563953399658, | |
| "eval_runtime": 508.8946, | |
| "eval_samples_per_second": 14.51, | |
| "eval_steps_per_second": 7.255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008553588230262595, | |
| "grad_norm": 1.8369693756103516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011404784307016793, | |
| "grad_norm": 2.777296543121338, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7426, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011404784307016793, | |
| "eval_loss": 0.7809138298034668, | |
| "eval_runtime": 507.5612, | |
| "eval_samples_per_second": 14.548, | |
| "eval_steps_per_second": 7.274, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014255980383770992, | |
| "grad_norm": 2.5196776390075684, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8516, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001710717646052519, | |
| "grad_norm": 3.652996301651001, | |
| "learning_rate": 5e-05, | |
| "loss": 0.879, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001710717646052519, | |
| "eval_loss": 0.7591553330421448, | |
| "eval_runtime": 508.8487, | |
| "eval_samples_per_second": 14.511, | |
| "eval_steps_per_second": 7.256, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019958372537279387, | |
| "grad_norm": 3.154165744781494, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9053, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0022809568614033586, | |
| "grad_norm": 3.6070640087127686, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7842, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022809568614033586, | |
| "eval_loss": 0.7511836886405945, | |
| "eval_runtime": 507.7701, | |
| "eval_samples_per_second": 14.542, | |
| "eval_steps_per_second": 7.271, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0025660764690787785, | |
| "grad_norm": 3.1344847679138184, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.669, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0028511960767541983, | |
| "grad_norm": 2.971832275390625, | |
| "learning_rate": 0.0, | |
| "loss": 0.7693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0028511960767541983, | |
| "eval_loss": 0.7486355304718018, | |
| "eval_runtime": 506.8033, | |
| "eval_samples_per_second": 14.57, | |
| "eval_steps_per_second": 7.285, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |