| { | |
| "best_metric": 1.2390294075012207, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.005162356099323731, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020649424397294926, | |
| "grad_norm": 0.11096003651618958, | |
| "learning_rate": 2e-05, | |
| "loss": 1.28, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020649424397294926, | |
| "eval_loss": 1.2963136434555054, | |
| "eval_runtime": 224.1589, | |
| "eval_samples_per_second": 9.101, | |
| "eval_steps_per_second": 4.55, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004129884879458985, | |
| "grad_norm": 0.15150529146194458, | |
| "learning_rate": 4e-05, | |
| "loss": 1.721, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006194827319188478, | |
| "grad_norm": 0.13352718949317932, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4841, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000825976975891797, | |
| "grad_norm": 0.11303545534610748, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3937, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010324712198647463, | |
| "grad_norm": 0.11634062975645065, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010324712198647463, | |
| "eval_loss": 1.2888224124908447, | |
| "eval_runtime": 223.7289, | |
| "eval_samples_per_second": 9.118, | |
| "eval_steps_per_second": 4.559, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012389654638376955, | |
| "grad_norm": 0.12108959257602692, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2703, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014454597078106448, | |
| "grad_norm": 0.1180579885840416, | |
| "learning_rate": 0.00014, | |
| "loss": 1.3096, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001651953951783594, | |
| "grad_norm": 0.12705351412296295, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3474, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018584481957565433, | |
| "grad_norm": 0.12884972989559174, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2564, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020649424397294926, | |
| "grad_norm": 0.1984177976846695, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2577, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020649424397294926, | |
| "eval_loss": 1.2690967321395874, | |
| "eval_runtime": 225.2066, | |
| "eval_samples_per_second": 9.058, | |
| "eval_steps_per_second": 4.529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002271436683702442, | |
| "grad_norm": 0.2093477100133896, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.2525, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002477930927675391, | |
| "grad_norm": 0.19395063817501068, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.2004, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0026844251716483403, | |
| "grad_norm": 0.20893283188343048, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.1796, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0028909194156212896, | |
| "grad_norm": 0.23473279178142548, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.326, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003097413659594239, | |
| "grad_norm": 0.19640016555786133, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0966, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003097413659594239, | |
| "eval_loss": 1.2500059604644775, | |
| "eval_runtime": 224.654, | |
| "eval_samples_per_second": 9.081, | |
| "eval_steps_per_second": 4.54, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003303907903567188, | |
| "grad_norm": 0.20851477980613708, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1577, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0035104021475401374, | |
| "grad_norm": 0.2019023448228836, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.3469, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0037168963915130866, | |
| "grad_norm": 0.20464642345905304, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.1755, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003923390635486036, | |
| "grad_norm": 0.21046672761440277, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.2986, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004129884879458985, | |
| "grad_norm": 0.19917546212673187, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.1211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004129884879458985, | |
| "eval_loss": 1.2417117357254028, | |
| "eval_runtime": 224.3838, | |
| "eval_samples_per_second": 9.092, | |
| "eval_steps_per_second": 4.546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004336379123431934, | |
| "grad_norm": 0.24532422423362732, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.2764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004542873367404884, | |
| "grad_norm": 0.22703120112419128, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.3281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004749367611377833, | |
| "grad_norm": 0.2032739222049713, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.1221, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004955861855350782, | |
| "grad_norm": 0.23146522045135498, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.1992, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005162356099323731, | |
| "grad_norm": 0.23780851066112518, | |
| "learning_rate": 0.0, | |
| "loss": 1.4991, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005162356099323731, | |
| "eval_loss": 1.2390294075012207, | |
| "eval_runtime": 226.8424, | |
| "eval_samples_per_second": 8.993, | |
| "eval_steps_per_second": 4.497, | |
| "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": 1622619350630400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |