| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.051546391752577, | |
| "eval_steps": 25, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.1462, | |
| "eval_samples_per_second": 6.997, | |
| "eval_steps_per_second": 1.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.981884322978576e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.927683148693833e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.83783287313134e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.713056917878818e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5773195876288659, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.363019571208397e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7422680412371134, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.88882159701625e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9072164948453608, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.609781920440891e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9896907216494846, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0721649484536082, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.979036416534463e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1546391752577319, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.632408981128494e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2371134020618557, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.268612642442657e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3195876288659794, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.402061855670103, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4845360824742269, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.10404969617945e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.5670103092783505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7018917365773184e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6494845360824741, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2981082634226854e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.731958762886598, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.895950303820552e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.8144329896907216, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.8969072164948453, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.9793814432989691, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7313873575573445e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0618556701030926, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3675910188715066e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0618556701030926, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.2561, | |
| "eval_samples_per_second": 7.992, | |
| "eval_steps_per_second": 2.078, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1443298969072164, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0209635834655392e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.2268041237113403, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.3092783505154637, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3902180795591093e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.3917525773195876, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.111178402983751e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.4742268041237114, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.556701030927835, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6369804287916028e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.6391752577319587, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.7216494845360826, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2869430821211828e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.804123711340206, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1621671268686606e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.88659793814433, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0723168513061666e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.9690721649484537, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0181156770214243e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.051546391752577, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 37, | |
| "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": 5.784250223102525e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |