| { | |
| "best_metric": 2.468625068664551, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.017844396859386154, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007137758743754461, | |
| "grad_norm": 2.5754621028900146, | |
| "learning_rate": 2e-05, | |
| "loss": 4.3565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007137758743754461, | |
| "eval_loss": 4.792675971984863, | |
| "eval_runtime": 85.6607, | |
| "eval_samples_per_second": 6.888, | |
| "eval_steps_per_second": 3.444, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014275517487508922, | |
| "grad_norm": 3.142717123031616, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2192, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021413276231263384, | |
| "grad_norm": 2.8496334552764893, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5054, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028551034975017845, | |
| "grad_norm": 2.690779209136963, | |
| "learning_rate": 8e-05, | |
| "loss": 4.9208, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0035688793718772305, | |
| "grad_norm": 3.2031099796295166, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035688793718772305, | |
| "eval_loss": 4.685855388641357, | |
| "eval_runtime": 85.2077, | |
| "eval_samples_per_second": 6.924, | |
| "eval_steps_per_second": 3.462, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004282655246252677, | |
| "grad_norm": 3.475053310394287, | |
| "learning_rate": 0.00012, | |
| "loss": 4.4628, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004996431120628123, | |
| "grad_norm": 4.0881500244140625, | |
| "learning_rate": 0.00014, | |
| "loss": 4.0751, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005710206995003569, | |
| "grad_norm": 4.9304118156433105, | |
| "learning_rate": 0.00016, | |
| "loss": 3.9034, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006423982869379015, | |
| "grad_norm": 4.383515357971191, | |
| "learning_rate": 0.00018, | |
| "loss": 3.7444, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007137758743754461, | |
| "grad_norm": 4.758116245269775, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007137758743754461, | |
| "eval_loss": 3.4135711193084717, | |
| "eval_runtime": 85.1857, | |
| "eval_samples_per_second": 6.926, | |
| "eval_steps_per_second": 3.463, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007851534618129907, | |
| "grad_norm": 5.061439037322998, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.216, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008565310492505354, | |
| "grad_norm": 8.323115348815918, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.5422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009279086366880799, | |
| "grad_norm": 4.150096416473389, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.6907, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009992862241256246, | |
| "grad_norm": 6.372169494628906, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.6909, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010706638115631691, | |
| "grad_norm": 5.622885227203369, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.8453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010706638115631691, | |
| "eval_loss": 2.680262565612793, | |
| "eval_runtime": 85.1254, | |
| "eval_samples_per_second": 6.931, | |
| "eval_steps_per_second": 3.465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011420413990007138, | |
| "grad_norm": 4.390577793121338, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.4404, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012134189864382585, | |
| "grad_norm": 4.550952434539795, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.7048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01284796573875803, | |
| "grad_norm": 4.015772819519043, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.5229, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013561741613133477, | |
| "grad_norm": 4.186005592346191, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.2092, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014275517487508922, | |
| "grad_norm": 4.793872356414795, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.8665, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014275517487508922, | |
| "eval_loss": 2.5100436210632324, | |
| "eval_runtime": 84.757, | |
| "eval_samples_per_second": 6.961, | |
| "eval_steps_per_second": 3.481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014989293361884369, | |
| "grad_norm": 4.453582763671875, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.2294, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015703069236259814, | |
| "grad_norm": 3.8627285957336426, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.0848, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01641684511063526, | |
| "grad_norm": 3.8947551250457764, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.3459, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017130620985010708, | |
| "grad_norm": 4.605079650878906, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.1639, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017844396859386154, | |
| "grad_norm": 4.187133312225342, | |
| "learning_rate": 0.0, | |
| "loss": 2.3788, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017844396859386154, | |
| "eval_loss": 2.468625068664551, | |
| "eval_runtime": 84.8049, | |
| "eval_samples_per_second": 6.957, | |
| "eval_steps_per_second": 3.479, | |
| "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": 4623910620364800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |