| { | |
| "best_metric": 0.9073211550712585, | |
| "best_model_checkpoint": "/ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen4B_models/qwen_4B_d0_iter1_model/checkpoint-100", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 1.8514470549546265, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.302, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 0.3635169007023558, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.6423674064129872, | |
| "learning_rate": 4.8187561277552374e-05, | |
| "loss": 0.9886, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 1.7652163975371618, | |
| "learning_rate": 4.301303984001967e-05, | |
| "loss": 1.0972, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 0.8125720365482934, | |
| "learning_rate": 3.5226715929283506e-05, | |
| "loss": 0.9888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.5160887085744938, | |
| "learning_rate": 2.595756834225089e-05, | |
| "loss": 0.9882, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3725490196078431, | |
| "grad_norm": 0.9475974337041686, | |
| "learning_rate": 1.6549578039787436e-05, | |
| "loss": 0.9159, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5686274509803921, | |
| "grad_norm": 0.6992885675683204, | |
| "learning_rate": 8.36685749586087e-06, | |
| "loss": 0.8981, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.6476094908491726, | |
| "learning_rate": 2.595861075973613e-06, | |
| "loss": 0.9455, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "grad_norm": 0.852996571624781, | |
| "learning_rate": 7.335497040648898e-08, | |
| "loss": 0.8416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "eval_loss": 0.9073211550712585, | |
| "eval_runtime": 10.152, | |
| "eval_samples_per_second": 8.865, | |
| "eval_steps_per_second": 1.182, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 102, | |
| "total_flos": 22867310280704.0, | |
| "train_loss": 1.0144876452053295, | |
| "train_runtime": 349.3742, | |
| "train_samples_per_second": 4.631, | |
| "train_steps_per_second": 0.292 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 102, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 22867310280704.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |