| { | |
| "best_metric": 2.0446817874908447, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.3114754098360657, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05245901639344262, | |
| "grad_norm": 59.75578308105469, | |
| "learning_rate": 5e-05, | |
| "loss": 69.1845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05245901639344262, | |
| "eval_loss": 2.3756308555603027, | |
| "eval_runtime": 4.6962, | |
| "eval_samples_per_second": 10.647, | |
| "eval_steps_per_second": 2.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10491803278688525, | |
| "grad_norm": 70.11760711669922, | |
| "learning_rate": 0.0001, | |
| "loss": 72.285, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15737704918032788, | |
| "grad_norm": 40.28403091430664, | |
| "learning_rate": 9.992920667580176e-05, | |
| "loss": 70.4757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2098360655737705, | |
| "grad_norm": 50.93065643310547, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 72.0046, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 67.84244537353516, | |
| "learning_rate": 9.936419583332062e-05, | |
| "loss": 72.9162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31475409836065577, | |
| "grad_norm": 39.244895935058594, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 67.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36721311475409835, | |
| "grad_norm": 24.89311408996582, | |
| "learning_rate": 9.82412794875295e-05, | |
| "loss": 67.2244, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.419672131147541, | |
| "grad_norm": 27.440900802612305, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 69.4707, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4721311475409836, | |
| "grad_norm": 32.1877326965332, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 70.6535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 54.610347747802734, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 69.8398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5770491803278689, | |
| "grad_norm": 19.549211502075195, | |
| "learning_rate": 9.438505398589392e-05, | |
| "loss": 66.0735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6295081967213115, | |
| "grad_norm": 21.11090850830078, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 68.2764, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6819672131147541, | |
| "grad_norm": 19.177579879760742, | |
| "learning_rate": 9.17002391031667e-05, | |
| "loss": 68.0621, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7344262295081967, | |
| "grad_norm": 21.684904098510742, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 69.1158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 25.838293075561523, | |
| "learning_rate": 8.855389741974244e-05, | |
| "loss": 64.8987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.839344262295082, | |
| "grad_norm": 16.683151245117188, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 66.7402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8918032786885246, | |
| "grad_norm": 16.149255752563477, | |
| "learning_rate": 8.498559600784018e-05, | |
| "loss": 67.3468, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9442622950819672, | |
| "grad_norm": 17.375782012939453, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 66.6194, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9967213114754099, | |
| "grad_norm": 26.16300392150879, | |
| "learning_rate": 8.104020832809127e-05, | |
| "loss": 69.7571, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 15.187979698181152, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 63.0399, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1016393442622952, | |
| "grad_norm": 15.76618480682373, | |
| "learning_rate": 7.67673499197358e-05, | |
| "loss": 63.5516, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1540983606557378, | |
| "grad_norm": 15.865626335144043, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 63.0109, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2065573770491804, | |
| "grad_norm": 19.105836868286133, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 64.563, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2590163934426228, | |
| "grad_norm": 27.65399932861328, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 63.8715, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 17.719682693481445, | |
| "learning_rate": 6.745759801411822e-05, | |
| "loss": 62.3019, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "eval_loss": 2.0446817874908447, | |
| "eval_runtime": 4.7446, | |
| "eval_samples_per_second": 10.538, | |
| "eval_steps_per_second": 2.74, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 58, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.829010669142016e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |