| { | |
| "best_metric": 0.8036689162254333, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004064049418840933, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 0.8780356645584106, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 0.9582918286323547, | |
| "eval_runtime": 365.0083, | |
| "eval_samples_per_second": 7.098, | |
| "eval_steps_per_second": 3.551, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 1.3395466804504395, | |
| "learning_rate": 4e-05, | |
| "loss": 3.727, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 1.3814723491668701, | |
| "learning_rate": 6e-05, | |
| "loss": 3.896, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 1.0956209897994995, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7371, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.1463351249694824, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9716, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "eval_loss": 0.9511369466781616, | |
| "eval_runtime": 362.889, | |
| "eval_samples_per_second": 7.14, | |
| "eval_steps_per_second": 3.571, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.4086196422576904, | |
| "learning_rate": 0.00012, | |
| "loss": 4.0122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 1.3528903722763062, | |
| "learning_rate": 0.00014, | |
| "loss": 3.8003, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 1.3646769523620605, | |
| "learning_rate": 0.00016, | |
| "loss": 3.911, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 3.1598894596099854, | |
| "learning_rate": 0.00018, | |
| "loss": 3.7973, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 1.5187245607376099, | |
| "learning_rate": 0.0002, | |
| "loss": 3.4151, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 0.8704153299331665, | |
| "eval_runtime": 365.8963, | |
| "eval_samples_per_second": 7.081, | |
| "eval_steps_per_second": 3.542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017881817442900105, | |
| "grad_norm": 1.6804190874099731, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.5526, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 1.655336618423462, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.6632, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "grad_norm": 2.5160911083221436, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.5932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 2.3304178714752197, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 2.385143518447876, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.0551, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "eval_loss": 0.8331114649772644, | |
| "eval_runtime": 365.1739, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 3.549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 2.6784660816192627, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.2755, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027635536048118345, | |
| "grad_norm": 1.6437331438064575, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.9725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 1.9800294637680054, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.463, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003088677558319109, | |
| "grad_norm": 1.9015357494354248, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.1569, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 2.7715961933135986, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.6, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 0.8091033101081848, | |
| "eval_runtime": 368.0357, | |
| "eval_samples_per_second": 7.04, | |
| "eval_steps_per_second": 3.521, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 2.1230952739715576, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.4785, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 2.285691976547241, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.4729, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037389254653336585, | |
| "grad_norm": 1.9919122457504272, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.3723, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 1.6255426406860352, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.4557, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 2.079230308532715, | |
| "learning_rate": 0.0, | |
| "loss": 3.5221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "eval_loss": 0.8036689162254333, | |
| "eval_runtime": 374.3428, | |
| "eval_samples_per_second": 6.921, | |
| "eval_steps_per_second": 3.462, | |
| "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": 4153269496578048.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |