| { | |
| "best_metric": 4.010801315307617, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.012053638692180202, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006026819346090101, | |
| "grad_norm": 2.3684256076812744, | |
| "learning_rate": 2e-05, | |
| "loss": 4.8078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006026819346090101, | |
| "eval_loss": 5.086623191833496, | |
| "eval_runtime": 77.0263, | |
| "eval_samples_per_second": 9.075, | |
| "eval_steps_per_second": 4.544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012053638692180201, | |
| "grad_norm": 4.19559907913208, | |
| "learning_rate": 4e-05, | |
| "loss": 4.9181, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018080458038270302, | |
| "grad_norm": 3.932884454727173, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024107277384360403, | |
| "grad_norm": 2.25919246673584, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3582, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030134096730450506, | |
| "grad_norm": 1.8532415628433228, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030134096730450506, | |
| "eval_loss": 5.0003252029418945, | |
| "eval_runtime": 74.9367, | |
| "eval_samples_per_second": 9.328, | |
| "eval_steps_per_second": 4.671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036160916076540604, | |
| "grad_norm": 8.846040725708008, | |
| "learning_rate": 0.00012, | |
| "loss": 4.6917, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004218773542263071, | |
| "grad_norm": 2.1262896060943604, | |
| "learning_rate": 0.00014, | |
| "loss": 4.2713, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0048214554768720806, | |
| "grad_norm": 4.06171989440918, | |
| "learning_rate": 0.00016, | |
| "loss": 4.863, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005424137411481091, | |
| "grad_norm": 5.009016513824463, | |
| "learning_rate": 0.00018, | |
| "loss": 4.6057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006026819346090101, | |
| "grad_norm": 3.979311466217041, | |
| "learning_rate": 0.0002, | |
| "loss": 4.7237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006026819346090101, | |
| "eval_loss": 4.511049270629883, | |
| "eval_runtime": 75.1975, | |
| "eval_samples_per_second": 9.296, | |
| "eval_steps_per_second": 4.654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006629501280699111, | |
| "grad_norm": 3.848144054412842, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.5971, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007232183215308121, | |
| "grad_norm": 4.838451862335205, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.4905, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00783486514991713, | |
| "grad_norm": 3.418919563293457, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.0452, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008437547084526141, | |
| "grad_norm": 5.053792953491211, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.8261, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009040229019135152, | |
| "grad_norm": 5.080602645874023, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.8139, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009040229019135152, | |
| "eval_loss": 4.185687065124512, | |
| "eval_runtime": 75.4289, | |
| "eval_samples_per_second": 9.267, | |
| "eval_steps_per_second": 4.64, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009642910953744161, | |
| "grad_norm": 3.5324654579162598, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.7614, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010245592888353172, | |
| "grad_norm": 4.834116458892822, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.6882, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010848274822962183, | |
| "grad_norm": 3.57612943649292, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.3122, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011450956757571192, | |
| "grad_norm": 3.308840751647949, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.7553, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012053638692180202, | |
| "grad_norm": 3.328306198120117, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.1738, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012053638692180202, | |
| "eval_loss": 4.010801315307617, | |
| "eval_runtime": 81.4236, | |
| "eval_samples_per_second": 8.585, | |
| "eval_steps_per_second": 4.299, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 180302281703424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |