| { | |
| "best_metric": 0.6539015173912048, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0294117647058822, | |
| "eval_steps": 25, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.19458436965942383, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5895, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "eval_loss": 0.8424332737922668, | |
| "eval_runtime": 2.7238, | |
| "eval_samples_per_second": 26.433, | |
| "eval_steps_per_second": 3.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.32966628670692444, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7361, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.2454020082950592, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.6603, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.22934691607952118, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.5838, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.2963561415672302, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7057, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.16340835392475128, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.5048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.19918110966682434, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5926, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.16093185544013977, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.5631, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.15876661241054535, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.4976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.19718866050243378, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.617, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0411764705882354, | |
| "grad_norm": 0.18958346545696259, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.707, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1352941176470588, | |
| "grad_norm": 0.12120410054922104, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4555, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2294117647058824, | |
| "grad_norm": 0.14071109890937805, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.4602, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3235294117647058, | |
| "grad_norm": 0.1380264014005661, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5816, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4176470588235295, | |
| "grad_norm": 0.16174176335334778, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.5396, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.511764705882353, | |
| "grad_norm": 0.12782365083694458, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.5236, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6058823529411765, | |
| "grad_norm": 0.125085711479187, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4575, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.12307789921760559, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.4047, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7941176470588234, | |
| "grad_norm": 0.10940416157245636, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.5674, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.888235294117647, | |
| "grad_norm": 0.12826353311538696, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.4867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9823529411764707, | |
| "grad_norm": 0.18988151848316193, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.6496, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0823529411764707, | |
| "grad_norm": 0.11396374553442001, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4821, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.176470588235294, | |
| "grad_norm": 0.11782456934452057, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.4709, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.2705882352941176, | |
| "grad_norm": 0.1059720441699028, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.5363, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.364705882352941, | |
| "grad_norm": 0.1112937182188034, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.4354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.364705882352941, | |
| "eval_loss": 0.6539015173912048, | |
| "eval_runtime": 1.2437, | |
| "eval_samples_per_second": 57.894, | |
| "eval_steps_per_second": 7.237, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.458823529411765, | |
| "grad_norm": 0.14100024104118347, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.5238, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.552941176470588, | |
| "grad_norm": 0.09745590388774872, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4364, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6470588235294117, | |
| "grad_norm": 0.12731899321079254, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.4703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.7411764705882353, | |
| "grad_norm": 0.10433598607778549, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.3853, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.835294117647059, | |
| "grad_norm": 0.11452948302030563, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.5038, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.9294117647058826, | |
| "grad_norm": 0.13775578141212463, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.5232, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.0294117647058822, | |
| "grad_norm": 0.14986667037010193, | |
| "learning_rate": 0.0, | |
| "loss": 0.6791, | |
| "step": 32 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 32, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4336879040554598e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |