| { | |
| "best_metric": 0.8274755477905273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0034168175761096113, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013667270304438446, | |
| "grad_norm": 0.43357425928115845, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013667270304438446, | |
| "eval_loss": 1.2461501359939575, | |
| "eval_runtime": 544.5773, | |
| "eval_samples_per_second": 5.658, | |
| "eval_steps_per_second": 2.83, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027334540608876893, | |
| "grad_norm": 0.36531755328178406, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2405, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041001810913315336, | |
| "grad_norm": 0.43042877316474915, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1044, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005466908121775379, | |
| "grad_norm": 0.46759867668151855, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0786, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006833635152219223, | |
| "grad_norm": 0.4646996855735779, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1697, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006833635152219223, | |
| "eval_loss": 1.2327512502670288, | |
| "eval_runtime": 539.8845, | |
| "eval_samples_per_second": 5.707, | |
| "eval_steps_per_second": 2.854, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008200362182663067, | |
| "grad_norm": 0.5348904132843018, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0867, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009567089213106913, | |
| "grad_norm": 0.28752824664115906, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010933816243550757, | |
| "grad_norm": 0.4235214591026306, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1446, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012300543273994601, | |
| "grad_norm": 0.44647321105003357, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9712, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013667270304438446, | |
| "grad_norm": 0.6285039186477661, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0295, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013667270304438446, | |
| "eval_loss": 1.0453726053237915, | |
| "eval_runtime": 538.7693, | |
| "eval_samples_per_second": 5.719, | |
| "eval_steps_per_second": 2.86, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001503399733488229, | |
| "grad_norm": 0.8284047245979309, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.9237, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016400724365326135, | |
| "grad_norm": 0.6000273823738098, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.0106, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001776745139576998, | |
| "grad_norm": 1.1275712251663208, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8098, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019134178426213825, | |
| "grad_norm": 0.4717814326286316, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.6462, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002050090545665767, | |
| "grad_norm": 0.7204762697219849, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9598, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002050090545665767, | |
| "eval_loss": 0.904741108417511, | |
| "eval_runtime": 541.6221, | |
| "eval_samples_per_second": 5.688, | |
| "eval_steps_per_second": 2.845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021867632487101514, | |
| "grad_norm": 0.5360210537910461, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8431, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002323435951754536, | |
| "grad_norm": 0.6423148512840271, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.7532, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0024601086547989203, | |
| "grad_norm": 0.49850893020629883, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.6763, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0025967813578433047, | |
| "grad_norm": 0.6532036662101746, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.6426, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002733454060887689, | |
| "grad_norm": 0.4738406240940094, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002733454060887689, | |
| "eval_loss": 0.8442187905311584, | |
| "eval_runtime": 541.123, | |
| "eval_samples_per_second": 5.694, | |
| "eval_steps_per_second": 2.848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0028701267639320736, | |
| "grad_norm": 0.7676703929901123, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.9019, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003006799466976458, | |
| "grad_norm": 0.44339215755462646, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.7555, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031434721700208425, | |
| "grad_norm": 0.45984727144241333, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.6824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003280144873065227, | |
| "grad_norm": 0.4886281192302704, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.6757, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0034168175761096113, | |
| "grad_norm": 0.4310750365257263, | |
| "learning_rate": 0.0, | |
| "loss": 0.7122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0034168175761096113, | |
| "eval_loss": 0.8274755477905273, | |
| "eval_runtime": 539.1656, | |
| "eval_samples_per_second": 5.714, | |
| "eval_steps_per_second": 2.858, | |
| "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": 7785963312906240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |