| { | |
| "best_metric": 1.0208630561828613, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.16035277610743637, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006414111044297455, | |
| "grad_norm": 10.31315803527832, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.8656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006414111044297455, | |
| "eval_loss": 2.4902782440185547, | |
| "eval_runtime": 1.0287, | |
| "eval_samples_per_second": 48.606, | |
| "eval_steps_per_second": 12.637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01282822208859491, | |
| "grad_norm": 12.256026268005371, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.0725, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019242333132892364, | |
| "grad_norm": 10.072068214416504, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02565644417718982, | |
| "grad_norm": 3.304625988006592, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.1228, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032070555221487274, | |
| "grad_norm": 3.110682487487793, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.1082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03848466626578473, | |
| "grad_norm": 3.0085599422454834, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9762, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04489877731008218, | |
| "grad_norm": 2.9738759994506836, | |
| "learning_rate": 9.998929121859592e-05, | |
| "loss": 1.8855, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05131288835437964, | |
| "grad_norm": 2.297053813934326, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 1.7019, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05772699939867709, | |
| "grad_norm": 1.9924105405807495, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5766, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06414111044297455, | |
| "grad_norm": 2.017209529876709, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 1.5321, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.070555221487272, | |
| "grad_norm": 2.017620086669922, | |
| "learning_rate": 9.973253522000438e-05, | |
| "loss": 1.4972, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07696933253156946, | |
| "grad_norm": 2.0020158290863037, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.447, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08338344357586691, | |
| "grad_norm": 1.0016213655471802, | |
| "learning_rate": 9.947626797104925e-05, | |
| "loss": 1.2698, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08979755462016437, | |
| "grad_norm": 1.1300530433654785, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.2114, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09621166566446182, | |
| "grad_norm": 0.8754634261131287, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.1015, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10262577670875928, | |
| "grad_norm": 0.9171552658081055, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 1.1322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10903988775305673, | |
| "grad_norm": 0.8763850927352905, | |
| "learning_rate": 9.871039314159677e-05, | |
| "loss": 1.0756, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11545399879735418, | |
| "grad_norm": 0.8467594385147095, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0607, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12186810984165164, | |
| "grad_norm": 0.9706906676292419, | |
| "learning_rate": 9.82022434473668e-05, | |
| "loss": 1.039, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1282822208859491, | |
| "grad_norm": 0.7961729168891907, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 1.0063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13469633193024655, | |
| "grad_norm": 0.889162540435791, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.0522, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.141110442974544, | |
| "grad_norm": 0.7932081818580627, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.9918, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14752455401884146, | |
| "grad_norm": 0.8014475703239441, | |
| "learning_rate": 9.694035411772594e-05, | |
| "loss": 1.0652, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1539386650631389, | |
| "grad_norm": 1.1154183149337769, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0376, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16035277610743637, | |
| "grad_norm": 1.1352952718734741, | |
| "learning_rate": 9.618901656037514e-05, | |
| "loss": 1.1077, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16035277610743637, | |
| "eval_loss": 1.0208630561828613, | |
| "eval_runtime": 1.0294, | |
| "eval_samples_per_second": 48.573, | |
| "eval_steps_per_second": 12.629, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.168384167647642e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |