| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028434132332451874, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.686826466490375e-05, | |
| "eval_loss": 3.088820457458496, | |
| "eval_runtime": 89.6283, | |
| "eval_samples_per_second": 82.608, | |
| "eval_steps_per_second": 41.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005686826466490375, | |
| "grad_norm": 27.399972915649414, | |
| "learning_rate": 0.0002, | |
| "loss": 12.1566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007392874406437487, | |
| "eval_loss": 3.0549521446228027, | |
| "eval_runtime": 89.163, | |
| "eval_samples_per_second": 83.039, | |
| "eval_steps_per_second": 41.519, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001137365293298075, | |
| "grad_norm": 31.398826599121094, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.3425, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014785748812874975, | |
| "eval_loss": 3.0265064239501953, | |
| "eval_runtime": 89.1443, | |
| "eval_samples_per_second": 83.056, | |
| "eval_steps_per_second": 41.528, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0017060479399471126, | |
| "grad_norm": 43.454498291015625, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002217862321931246, | |
| "eval_loss": 3.01473331451416, | |
| "eval_runtime": 89.5926, | |
| "eval_samples_per_second": 82.641, | |
| "eval_steps_per_second": 41.32, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00227473058659615, | |
| "grad_norm": 44.27926254272461, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 12.3463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028434132332451874, | |
| "grad_norm": 41.68784713745117, | |
| "learning_rate": 0.0, | |
| "loss": 11.8272, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 589974604873728.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |