| { | |
| "best_metric": 2.4627528190612793, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02857959416976279, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011431837667905116, | |
| "grad_norm": 4.984986782073975, | |
| "learning_rate": 2e-05, | |
| "loss": 16.5546, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011431837667905116, | |
| "eval_loss": 4.0086774826049805, | |
| "eval_runtime": 69.5577, | |
| "eval_samples_per_second": 5.305, | |
| "eval_steps_per_second": 2.66, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002286367533581023, | |
| "grad_norm": 4.664716720581055, | |
| "learning_rate": 4e-05, | |
| "loss": 14.4938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003429551300371535, | |
| "grad_norm": 3.985492706298828, | |
| "learning_rate": 6e-05, | |
| "loss": 15.3814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004572735067162046, | |
| "grad_norm": 5.596559524536133, | |
| "learning_rate": 8e-05, | |
| "loss": 14.7979, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005715918833952558, | |
| "grad_norm": 3.7223613262176514, | |
| "learning_rate": 0.0001, | |
| "loss": 14.6139, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005715918833952558, | |
| "eval_loss": 3.9355335235595703, | |
| "eval_runtime": 68.1578, | |
| "eval_samples_per_second": 5.414, | |
| "eval_steps_per_second": 2.714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00685910260074307, | |
| "grad_norm": 6.831216335296631, | |
| "learning_rate": 0.00012, | |
| "loss": 17.7024, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00800228636753358, | |
| "grad_norm": 9.130233764648438, | |
| "learning_rate": 0.00014, | |
| "loss": 17.1566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009145470134324093, | |
| "grad_norm": 9.352496147155762, | |
| "learning_rate": 0.00016, | |
| "loss": 14.3919, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010288653901114605, | |
| "grad_norm": 6.8752617835998535, | |
| "learning_rate": 0.00018, | |
| "loss": 11.42, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011431837667905115, | |
| "grad_norm": 8.414678573608398, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5911, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011431837667905115, | |
| "eval_loss": 2.95451283454895, | |
| "eval_runtime": 68.9337, | |
| "eval_samples_per_second": 5.353, | |
| "eval_steps_per_second": 2.684, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012575021434695627, | |
| "grad_norm": 9.174803733825684, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 11.5496, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01371820520148614, | |
| "grad_norm": 10.449328422546387, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 11.4081, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014861388968276651, | |
| "grad_norm": 9.23154354095459, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 12.0689, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01600457273506716, | |
| "grad_norm": 8.31028938293457, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 11.5999, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017147756501857674, | |
| "grad_norm": 6.680941581726074, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.2596, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017147756501857674, | |
| "eval_loss": 2.5652663707733154, | |
| "eval_runtime": 69.4645, | |
| "eval_samples_per_second": 5.312, | |
| "eval_steps_per_second": 2.663, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018290940268648186, | |
| "grad_norm": 6.815301895141602, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.2358, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019434124035438698, | |
| "grad_norm": 9.210680961608887, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 11.0398, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02057730780222921, | |
| "grad_norm": 11.145197868347168, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 10.5009, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021720491569019718, | |
| "grad_norm": 10.375300407409668, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 12.2334, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02286367533581023, | |
| "grad_norm": 10.878546714782715, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 9.7952, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02286367533581023, | |
| "eval_loss": 2.4870645999908447, | |
| "eval_runtime": 68.3821, | |
| "eval_samples_per_second": 5.396, | |
| "eval_steps_per_second": 2.705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024006859102600742, | |
| "grad_norm": 7.396235466003418, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 8.5751, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025150042869391254, | |
| "grad_norm": 7.178986072540283, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 9.0461, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026293226636181766, | |
| "grad_norm": 8.065658569335938, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 9.4133, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02743641040297228, | |
| "grad_norm": 10.194811820983887, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 8.1633, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02857959416976279, | |
| "grad_norm": 7.041247844696045, | |
| "learning_rate": 0.0, | |
| "loss": 8.6386, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02857959416976279, | |
| "eval_loss": 2.4627528190612793, | |
| "eval_runtime": 68.7471, | |
| "eval_samples_per_second": 5.368, | |
| "eval_steps_per_second": 2.691, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 7915560763392000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |