| { | |
| "best_metric": 0.17924122512340546, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06897740989825832, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027590963959303327, | |
| "grad_norm": 2.8736233711242676, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6531, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027590963959303327, | |
| "eval_loss": 1.0923383235931396, | |
| "eval_runtime": 4.3993, | |
| "eval_samples_per_second": 11.365, | |
| "eval_steps_per_second": 2.955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0055181927918606655, | |
| "grad_norm": 2.5027053356170654, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4551, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008277289187790998, | |
| "grad_norm": 1.5247098207473755, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.1081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011036385583721331, | |
| "grad_norm": 1.0242395401000977, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.8285, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013795481979651664, | |
| "grad_norm": 0.873866856098175, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6806, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016554578375581996, | |
| "grad_norm": 0.7331669926643372, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5174, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01931367477151233, | |
| "grad_norm": 0.6170404553413391, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.4061, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022072771167442662, | |
| "grad_norm": 0.4580063819885254, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.3352, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024831867563372995, | |
| "grad_norm": 0.332847535610199, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.2812, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027590963959303327, | |
| "grad_norm": 0.2888358533382416, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.2477, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03035006035523366, | |
| "grad_norm": 0.29751214385032654, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.2295, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03310915675116399, | |
| "grad_norm": 0.2564615309238434, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.035868253147094326, | |
| "grad_norm": 0.6380288004875183, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2306, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03862734954302466, | |
| "grad_norm": 0.4050877094268799, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1794, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04138644593895499, | |
| "grad_norm": 0.38711509108543396, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1707, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.044145542334885324, | |
| "grad_norm": 0.3676080107688904, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.046904638730815656, | |
| "grad_norm": 0.20531894266605377, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04966373512674599, | |
| "grad_norm": 0.29787468910217285, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1783, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05242283152267632, | |
| "grad_norm": 0.17893420159816742, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1797, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.055181927918606655, | |
| "grad_norm": 0.21105116605758667, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1818, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05794102431453699, | |
| "grad_norm": 0.21834588050842285, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1932, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06070012071046732, | |
| "grad_norm": 0.16078908741474152, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1869, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06345921710639765, | |
| "grad_norm": 0.2289479523897171, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1856, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06621831350232799, | |
| "grad_norm": 0.12230488657951355, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06897740989825832, | |
| "grad_norm": 0.1601058393716812, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06897740989825832, | |
| "eval_loss": 0.17924122512340546, | |
| "eval_runtime": 4.4655, | |
| "eval_samples_per_second": 11.197, | |
| "eval_steps_per_second": 2.911, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 3.030719813879071e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |