| { | |
| "best_metric": 0.6170168519020081, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05037783375314862, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020151133501259445, | |
| "grad_norm": 0.3594292998313904, | |
| "learning_rate": 2e-05, | |
| "loss": 2.286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020151133501259445, | |
| "eval_loss": 0.6638228893280029, | |
| "eval_runtime": 55.2182, | |
| "eval_samples_per_second": 3.785, | |
| "eval_steps_per_second": 1.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004030226700251889, | |
| "grad_norm": 0.39827266335487366, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006045340050377834, | |
| "grad_norm": 0.25862371921539307, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2722, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008060453400503778, | |
| "grad_norm": 0.5083067417144775, | |
| "learning_rate": 8e-05, | |
| "loss": 3.3879, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010075566750629723, | |
| "grad_norm": 0.40554600954055786, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010075566750629723, | |
| "eval_loss": 0.6636737585067749, | |
| "eval_runtime": 55.176, | |
| "eval_samples_per_second": 3.788, | |
| "eval_steps_per_second": 1.903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012090680100755667, | |
| "grad_norm": 0.37122878432273865, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9988, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014105793450881612, | |
| "grad_norm": 0.33736562728881836, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5039, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016120906801007556, | |
| "grad_norm": 0.5041938424110413, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7734, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0181360201511335, | |
| "grad_norm": 0.46313270926475525, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3923, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020151133501259445, | |
| "grad_norm": 0.43415185809135437, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2073, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020151133501259445, | |
| "eval_loss": 0.6502737402915955, | |
| "eval_runtime": 55.0477, | |
| "eval_samples_per_second": 3.797, | |
| "eval_steps_per_second": 1.907, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02216624685138539, | |
| "grad_norm": 0.7167869210243225, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.6288, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024181360201511334, | |
| "grad_norm": 0.48966965079307556, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.0753, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02619647355163728, | |
| "grad_norm": 0.4106284976005554, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.1925, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028211586901763223, | |
| "grad_norm": 0.46533626317977905, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.0292, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030226700251889168, | |
| "grad_norm": 1.0065481662750244, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.4329, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030226700251889168, | |
| "eval_loss": 0.629341721534729, | |
| "eval_runtime": 55.0242, | |
| "eval_samples_per_second": 3.798, | |
| "eval_steps_per_second": 1.908, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03224181360201511, | |
| "grad_norm": 0.5595883131027222, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.9854, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03425692695214106, | |
| "grad_norm": 0.4277346432209015, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.743, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.036272040302267, | |
| "grad_norm": 0.506736159324646, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.2698, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03828715365239295, | |
| "grad_norm": 0.5150989890098572, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.8678, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04030226700251889, | |
| "grad_norm": 0.3571804165840149, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.1466, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04030226700251889, | |
| "eval_loss": 0.6193917989730835, | |
| "eval_runtime": 55.0702, | |
| "eval_samples_per_second": 3.795, | |
| "eval_steps_per_second": 1.907, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04231738035264484, | |
| "grad_norm": 0.5522847771644592, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.0133, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04433249370277078, | |
| "grad_norm": 0.385016530752182, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.3122, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04634760705289673, | |
| "grad_norm": 0.4866712689399719, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.1991, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04836272040302267, | |
| "grad_norm": 0.6545142531394958, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0803, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05037783375314862, | |
| "grad_norm": 0.6084586381912231, | |
| "learning_rate": 0.0, | |
| "loss": 2.8759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05037783375314862, | |
| "eval_loss": 0.6170168519020081, | |
| "eval_runtime": 55.1544, | |
| "eval_samples_per_second": 3.789, | |
| "eval_steps_per_second": 1.904, | |
| "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": 1.698683682816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |