| { | |
| "best_metric": 1.4073567390441895, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.004402135035492214, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "grad_norm": 1.335319995880127, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.4477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "eval_loss": 1.583249568939209, | |
| "eval_runtime": 375.2608, | |
| "eval_samples_per_second": 5.098, | |
| "eval_steps_per_second": 2.55, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044021350354922137, | |
| "grad_norm": 0.7646092772483826, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2837, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006603202553238321, | |
| "grad_norm": 0.984878659248352, | |
| "learning_rate": 6e-06, | |
| "loss": 1.4308, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008804270070984427, | |
| "grad_norm": 1.3296175003051758, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.2962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011005337588730535, | |
| "grad_norm": 1.7959861755371094, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3243, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011005337588730535, | |
| "eval_loss": 1.580323338508606, | |
| "eval_runtime": 238.4962, | |
| "eval_samples_per_second": 8.021, | |
| "eval_steps_per_second": 4.013, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013206405106476642, | |
| "grad_norm": 1.0089523792266846, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.5139, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015407472624222747, | |
| "grad_norm": 1.0647411346435547, | |
| "learning_rate": 1.4e-05, | |
| "loss": 1.23, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017608540141968855, | |
| "grad_norm": 0.8876328468322754, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.2597, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019809607659714962, | |
| "grad_norm": 3.455842971801758, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.5887, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002201067517746107, | |
| "grad_norm": 1.0496996641159058, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002201067517746107, | |
| "eval_loss": 1.556506872177124, | |
| "eval_runtime": 238.5187, | |
| "eval_samples_per_second": 8.02, | |
| "eval_steps_per_second": 4.012, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024211742695207177, | |
| "grad_norm": 2.3803887367248535, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 1.5437, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026412810212953284, | |
| "grad_norm": 1.5120227336883545, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.5937, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0028613877730699388, | |
| "grad_norm": 1.4125422239303589, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.4758, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030814945248445495, | |
| "grad_norm": 1.1811188459396362, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 1.404, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0033016012766191602, | |
| "grad_norm": 1.0221134424209595, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.2909, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033016012766191602, | |
| "eval_loss": 1.476494550704956, | |
| "eval_runtime": 238.2339, | |
| "eval_samples_per_second": 8.03, | |
| "eval_steps_per_second": 4.017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003521708028393771, | |
| "grad_norm": 1.1143208742141724, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.187, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0037418147801683817, | |
| "grad_norm": 1.5501571893692017, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 1.6458, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0039619215319429925, | |
| "grad_norm": 4.555670261383057, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 1.2275, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004182028283717603, | |
| "grad_norm": 1.250296711921692, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.2713, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004402135035492214, | |
| "grad_norm": 1.27157723903656, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.2806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004402135035492214, | |
| "eval_loss": 1.4073567390441895, | |
| "eval_runtime": 238.2087, | |
| "eval_samples_per_second": 8.031, | |
| "eval_steps_per_second": 4.017, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |