| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.7094017094017095, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.1257, | |
| "eval_samples_per_second": 44.415, | |
| "eval_steps_per_second": 11.548, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996926770643604e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987711280236048e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972366116028733e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.950912237670159e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.889803855911966e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.850232819211343e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.804719887751984e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.753327226723689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.633191435856655e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.56461239705758e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.490481586640278e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.410900258374877e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.235828138669979e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.040352221150675e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.935292272334964e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.711245694852886e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.592565086861683e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.1338, | |
| "eval_samples_per_second": 44.101, | |
| "eval_steps_per_second": 11.466, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.469660406954253e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.342699528139629e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.077308130362274e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.939240104126023e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0598290598290598, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.797840369314081e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0940170940170941, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.653302060955789e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1282051282051282, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1623931623931625, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.355603428632566e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1965811965811965, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.202849725190397e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.047770133852677e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.264957264957265, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2991452991452992, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.570708377691784e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3675213675213675, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.408470841206546e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4017094017094016, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.244992442828586e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0804964743859164e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4700854700854702, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9152076175848594e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5042735042735043, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.749351637121866e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5831550723160856e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5726495726495726, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.416844927683916e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.606837606837607, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.250648362878135e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0847923824151424e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6752136752136753, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.919503525614087e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7550075571714146e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.1173, | |
| "eval_samples_per_second": 44.749, | |
| "eval_steps_per_second": 11.635, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 88, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |