| { | |
| "best_metric": 0.038246795535087585, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0588235294117645, | |
| "eval_steps": 25, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 60.86349868774414, | |
| "learning_rate": 5e-05, | |
| "loss": 87.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "eval_loss": 6.279521465301514, | |
| "eval_runtime": 2.283, | |
| "eval_samples_per_second": 21.901, | |
| "eval_steps_per_second": 5.694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 66.25541687011719, | |
| "learning_rate": 0.0001, | |
| "loss": 92.7498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 83.56111907958984, | |
| "learning_rate": 9.983788698441369e-05, | |
| "loss": 104.2699, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 74.07500457763672, | |
| "learning_rate": 9.935271596564688e-05, | |
| "loss": 73.7409, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 122.21480560302734, | |
| "learning_rate": 9.854798261200746e-05, | |
| "loss": 52.6066, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 216.04931640625, | |
| "learning_rate": 9.74294850457488e-05, | |
| "loss": 24.5554, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5490196078431373, | |
| "grad_norm": 169.465087890625, | |
| "learning_rate": 9.600528206746612e-05, | |
| "loss": 27.2953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 143.66921997070312, | |
| "learning_rate": 9.428563509225347e-05, | |
| "loss": 18.9022, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 105.4874267578125, | |
| "learning_rate": 9.22829342159729e-05, | |
| "loss": 5.5785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 118.35433197021484, | |
| "learning_rate": 9.001160894432978e-05, | |
| "loss": 12.1629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8627450980392157, | |
| "grad_norm": 195.34605407714844, | |
| "learning_rate": 8.74880242279536e-05, | |
| "loss": 9.8084, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 267.8063049316406, | |
| "learning_rate": 8.473036255255366e-05, | |
| "loss": 8.0296, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0196078431372548, | |
| "grad_norm": 39.37614440917969, | |
| "learning_rate": 8.175849293369291e-05, | |
| "loss": 4.7077, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0980392156862746, | |
| "grad_norm": 72.95148468017578, | |
| "learning_rate": 7.859382776007543e-05, | |
| "loss": 6.9191, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 63.84526443481445, | |
| "learning_rate": 7.525916851679529e-05, | |
| "loss": 4.7309, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2549019607843137, | |
| "grad_norm": 77.97026062011719, | |
| "learning_rate": 7.177854150011389e-05, | |
| "loss": 2.3247, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 25.761390686035156, | |
| "learning_rate": 6.817702470744477e-05, | |
| "loss": 1.8443, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 65.09815216064453, | |
| "learning_rate": 6.448056714980767e-05, | |
| "loss": 3.2645, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4901960784313726, | |
| "grad_norm": 42.31401824951172, | |
| "learning_rate": 6.071580188860955e-05, | |
| "loss": 1.0521, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5686274509803921, | |
| "grad_norm": 33.89790725708008, | |
| "learning_rate": 5.690985414382668e-05, | |
| "loss": 1.5936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 29.281991958618164, | |
| "learning_rate": 5.3090145856173346e-05, | |
| "loss": 1.6774, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.7254901960784315, | |
| "grad_norm": 10.227999687194824, | |
| "learning_rate": 4.9284198111390456e-05, | |
| "loss": 0.2475, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.803921568627451, | |
| "grad_norm": 40.34574890136719, | |
| "learning_rate": 4.551943285019234e-05, | |
| "loss": 1.5025, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 21.78724479675293, | |
| "learning_rate": 4.182297529255525e-05, | |
| "loss": 1.3656, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "grad_norm": 6.2362823486328125, | |
| "learning_rate": 3.822145849988612e-05, | |
| "loss": 0.3406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "eval_loss": 0.038246795535087585, | |
| "eval_runtime": 1.8295, | |
| "eval_samples_per_second": 27.331, | |
| "eval_steps_per_second": 7.106, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0392156862745097, | |
| "grad_norm": 3.510915994644165, | |
| "learning_rate": 3.474083148320469e-05, | |
| "loss": 0.4248, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 8.030313491821289, | |
| "learning_rate": 3.1406172239924584e-05, | |
| "loss": 0.8069, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.196078431372549, | |
| "grad_norm": 26.57486915588379, | |
| "learning_rate": 2.8241507066307104e-05, | |
| "loss": 1.1415, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.2745098039215685, | |
| "grad_norm": 6.342585563659668, | |
| "learning_rate": 2.5269637447446348e-05, | |
| "loss": 0.0675, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 20.42534065246582, | |
| "learning_rate": 2.2511975772046403e-05, | |
| "loss": 1.1795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.431372549019608, | |
| "grad_norm": 71.26493835449219, | |
| "learning_rate": 1.9988391055670233e-05, | |
| "loss": 1.4359, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.5098039215686274, | |
| "grad_norm": 4.1655449867248535, | |
| "learning_rate": 1.771706578402711e-05, | |
| "loss": 0.0568, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 12.102375030517578, | |
| "learning_rate": 1.5714364907746536e-05, | |
| "loss": 0.9678, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 25.678956985473633, | |
| "learning_rate": 1.3994717932533891e-05, | |
| "loss": 1.2355, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.7450980392156863, | |
| "grad_norm": 1.5909215211868286, | |
| "learning_rate": 1.257051495425121e-05, | |
| "loss": 0.0221, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 33.322696685791016, | |
| "learning_rate": 1.1452017387992552e-05, | |
| "loss": 1.1316, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.9019607843137254, | |
| "grad_norm": 23.584259033203125, | |
| "learning_rate": 1.064728403435312e-05, | |
| "loss": 0.9945, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.980392156862745, | |
| "grad_norm": 6.629971981048584, | |
| "learning_rate": 1.0162113015586309e-05, | |
| "loss": 0.3805, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 8.110614776611328, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5328, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "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": 4.104695101563863e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |