| { | |
| "best_metric": 1.441811203956604, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02960331557134399, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "grad_norm": 1.1009294986724854, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "eval_loss": 1.622971773147583, | |
| "eval_runtime": 56.2178, | |
| "eval_samples_per_second": 6.333, | |
| "eval_steps_per_second": 3.166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002368265245707519, | |
| "grad_norm": 0.73466557264328, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7661, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003552397868561279, | |
| "grad_norm": 0.8278913497924805, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6963, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004736530491415038, | |
| "grad_norm": 1.151739478111267, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7265, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005920663114268798, | |
| "grad_norm": 0.7402674555778503, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5281, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005920663114268798, | |
| "eval_loss": 1.614159107208252, | |
| "eval_runtime": 53.8478, | |
| "eval_samples_per_second": 6.611, | |
| "eval_steps_per_second": 3.306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007104795737122558, | |
| "grad_norm": 1.0584721565246582, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008288928359976317, | |
| "grad_norm": 0.8590249419212341, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8947, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009473060982830076, | |
| "grad_norm": 0.7832806706428528, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8183, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010657193605683837, | |
| "grad_norm": 0.805705189704895, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8028, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011841326228537596, | |
| "grad_norm": 1.0513153076171875, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0219, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011841326228537596, | |
| "eval_loss": 1.5592914819717407, | |
| "eval_runtime": 53.5568, | |
| "eval_samples_per_second": 6.647, | |
| "eval_steps_per_second": 3.324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013025458851391355, | |
| "grad_norm": 0.9684340357780457, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.9317, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014209591474245116, | |
| "grad_norm": 1.5347967147827148, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.2451, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015393724097098875, | |
| "grad_norm": 0.6658350825309753, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.1592, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016577856719952634, | |
| "grad_norm": 0.5862579345703125, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.0437, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.8402700424194336, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "eval_loss": 1.4690113067626953, | |
| "eval_runtime": 58.5466, | |
| "eval_samples_per_second": 6.081, | |
| "eval_steps_per_second": 3.04, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018946121965660152, | |
| "grad_norm": 1.071670413017273, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7594, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020130254588513915, | |
| "grad_norm": 1.167551040649414, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.8349, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021314387211367674, | |
| "grad_norm": 0.730896532535553, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.137, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022498519834221433, | |
| "grad_norm": 0.7160881757736206, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7813, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023682652457075192, | |
| "grad_norm": 0.6176623106002808, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023682652457075192, | |
| "eval_loss": 1.443589687347412, | |
| "eval_runtime": 55.9559, | |
| "eval_samples_per_second": 6.362, | |
| "eval_steps_per_second": 3.181, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02486678507992895, | |
| "grad_norm": 0.8491754531860352, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5677, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02605091770278271, | |
| "grad_norm": 0.9003405570983887, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6864, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027235050325636473, | |
| "grad_norm": 0.6072733402252197, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6922, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028419182948490232, | |
| "grad_norm": 1.0873887538909912, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8884, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02960331557134399, | |
| "grad_norm": 1.862977147102356, | |
| "learning_rate": 0.0, | |
| "loss": 1.9757, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02960331557134399, | |
| "eval_loss": 1.441811203956604, | |
| "eval_runtime": 55.8826, | |
| "eval_samples_per_second": 6.371, | |
| "eval_steps_per_second": 3.185, | |
| "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": 347248838836224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |