| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012766500702157539, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025533001404315077, | |
| "eval_loss": 11.092205047607422, | |
| "eval_runtime": 7.7875, | |
| "eval_samples_per_second": 211.75, | |
| "eval_steps_per_second": 105.939, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012766500702157538, | |
| "grad_norm": 0.5062381029129028, | |
| "learning_rate": 5e-05, | |
| "loss": 44.352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025533001404315077, | |
| "grad_norm": 0.49682265520095825, | |
| "learning_rate": 0.0001, | |
| "loss": 44.336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025533001404315077, | |
| "eval_loss": 11.091653823852539, | |
| "eval_runtime": 6.9243, | |
| "eval_samples_per_second": 238.147, | |
| "eval_steps_per_second": 119.146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0038299502106472617, | |
| "grad_norm": 0.5654242634773254, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.3696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005106600280863015, | |
| "grad_norm": 0.5463382601737976, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.3713, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005106600280863015, | |
| "eval_loss": 11.090264320373535, | |
| "eval_runtime": 7.0519, | |
| "eval_samples_per_second": 233.838, | |
| "eval_steps_per_second": 116.99, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006383250351078769, | |
| "grad_norm": 0.5365641117095947, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.3573, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0076599004212945234, | |
| "grad_norm": 0.6584469079971313, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3663, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0076599004212945234, | |
| "eval_loss": 11.089264869689941, | |
| "eval_runtime": 7.1326, | |
| "eval_samples_per_second": 231.192, | |
| "eval_steps_per_second": 115.666, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008936550491510277, | |
| "grad_norm": 0.5538540482521057, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.3462, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01021320056172603, | |
| "grad_norm": 0.5181305408477783, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.3626, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01021320056172603, | |
| "eval_loss": 11.088730812072754, | |
| "eval_runtime": 7.2009, | |
| "eval_samples_per_second": 228.999, | |
| "eval_steps_per_second": 114.569, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011489850631941785, | |
| "grad_norm": 0.654859721660614, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 44.3393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012766500702157539, | |
| "grad_norm": 0.580810546875, | |
| "learning_rate": 0.0, | |
| "loss": 44.361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012766500702157539, | |
| "eval_loss": 11.088641166687012, | |
| "eval_runtime": 6.9998, | |
| "eval_samples_per_second": 235.577, | |
| "eval_steps_per_second": 117.86, | |
| "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": 37355520000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |