| { | |
| "best_metric": 0.5904276967048645, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0, | |
| "eval_steps": 25, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 3.9250755310058594, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "eval_loss": 3.2133781909942627, | |
| "eval_runtime": 0.7306, | |
| "eval_samples_per_second": 101.292, | |
| "eval_steps_per_second": 13.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 4.883828163146973, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 4.751261234283447, | |
| "learning_rate": 9.974346616959476e-05, | |
| "loss": 3.082, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 4.260494232177734, | |
| "learning_rate": 9.897649706262473e-05, | |
| "loss": 2.5029, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 5.264866828918457, | |
| "learning_rate": 9.770696282000244e-05, | |
| "loss": 2.5518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 2.550161361694336, | |
| "learning_rate": 9.594789058101153e-05, | |
| "loss": 1.5278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 2.883025646209717, | |
| "learning_rate": 9.371733080722911e-05, | |
| "loss": 1.5295, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 2.446653127670288, | |
| "learning_rate": 9.103817206036382e-05, | |
| "loss": 1.2206, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 2.4879133701324463, | |
| "learning_rate": 8.793790613463955e-05, | |
| "loss": 1.095, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 2.3682610988616943, | |
| "learning_rate": 8.444834595378434e-05, | |
| "loss": 1.1061, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.6341614723205566, | |
| "learning_rate": 8.060529912738315e-05, | |
| "loss": 0.935, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 1.5357123613357544, | |
| "learning_rate": 7.644820051634812e-05, | |
| "loss": 0.7651, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 1.6579945087432861, | |
| "learning_rate": 7.201970757788172e-05, | |
| "loss": 0.7296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 2.005446434020996, | |
| "learning_rate": 6.736526264224101e-05, | |
| "loss": 0.9158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 3.1605615615844727, | |
| "learning_rate": 6.253262661293604e-05, | |
| "loss": 0.8794, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.574661374092102, | |
| "learning_rate": 5.757138887522884e-05, | |
| "loss": 0.7897, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 1.2775368690490723, | |
| "learning_rate": 5.2532458441935636e-05, | |
| "loss": 0.7534, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 1.4721097946166992, | |
| "learning_rate": 4.746754155806437e-05, | |
| "loss": 0.5951, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 1.561679482460022, | |
| "learning_rate": 4.2428611124771184e-05, | |
| "loss": 0.7347, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.2978594303131104, | |
| "learning_rate": 3.746737338706397e-05, | |
| "loss": 0.6884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 1.5109196901321411, | |
| "learning_rate": 3.263473735775899e-05, | |
| "loss": 0.7078, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3557102680206299, | |
| "learning_rate": 2.798029242211828e-05, | |
| "loss": 0.6497, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 1.1088306903839111, | |
| "learning_rate": 2.3551799483651894e-05, | |
| "loss": 0.5894, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.1537069082260132, | |
| "learning_rate": 1.9394700872616855e-05, | |
| "loss": 0.5904, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 1.1084684133529663, | |
| "learning_rate": 1.555165404621567e-05, | |
| "loss": 0.5657, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "eval_loss": 0.5904276967048645, | |
| "eval_runtime": 0.7289, | |
| "eval_samples_per_second": 101.523, | |
| "eval_steps_per_second": 13.719, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 1.1513195037841797, | |
| "learning_rate": 1.2062093865360458e-05, | |
| "loss": 0.6313, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.4545454545454546, | |
| "grad_norm": 1.2628175020217896, | |
| "learning_rate": 8.961827939636196e-06, | |
| "loss": 0.6297, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.271503210067749, | |
| "learning_rate": 6.282669192770896e-06, | |
| "loss": 0.6808, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 1.3215694427490234, | |
| "learning_rate": 4.05210941898847e-06, | |
| "loss": 0.734, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 1.12972891330719, | |
| "learning_rate": 2.2930371799975594e-06, | |
| "loss": 0.5775, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8181818181818183, | |
| "grad_norm": 1.0475295782089233, | |
| "learning_rate": 1.0235029373752758e-06, | |
| "loss": 0.5434, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 1.3993170261383057, | |
| "learning_rate": 2.5653383040524227e-07, | |
| "loss": 0.6718, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.1576110124588013, | |
| "learning_rate": 0.0, | |
| "loss": 0.5754, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.500548187737293e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |