| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06251220941590155, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012502441883180308, | |
| "grad_norm": 3.901104211807251, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.4001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012502441883180308, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.4591, | |
| "eval_samples_per_second": 11.213, | |
| "eval_steps_per_second": 2.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025004883766360617, | |
| "grad_norm": 4.847945690155029, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.7682, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037507325649540927, | |
| "grad_norm": 4.892094612121582, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005000976753272123, | |
| "grad_norm": 6.0467095375061035, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.4506, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006251220941590154, | |
| "grad_norm": 4.356233596801758, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 3.5468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0075014651299081855, | |
| "grad_norm": 5.469017028808594, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.1005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008751709318226216, | |
| "grad_norm": 2.9598443508148193, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 2.8554, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010001953506544247, | |
| "grad_norm": 4.06898307800293, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 2.4967, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011252197694862277, | |
| "grad_norm": 5.215047836303711, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.5988, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012502441883180308, | |
| "grad_norm": 2.144993782043457, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 2.089, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01375268607149834, | |
| "grad_norm": 1.9372471570968628, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 2.3254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015002930259816371, | |
| "grad_norm": 2.0926334857940674, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8673, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0162531744481344, | |
| "grad_norm": 4.845098495483398, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 2.6344, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017503418636452432, | |
| "grad_norm": 3.6204464435577393, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 2.7293, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018753662824770465, | |
| "grad_norm": 2.1200790405273438, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.5183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020003907013088493, | |
| "grad_norm": 2.0485384464263916, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 2.5504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021254151201406526, | |
| "grad_norm": 1.7548338174819946, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.424, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022504395389724555, | |
| "grad_norm": 1.8181811571121216, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.4019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023754639578042587, | |
| "grad_norm": 2.3223536014556885, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 2.3419, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025004883766360616, | |
| "grad_norm": 1.5470370054244995, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 2.3176, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02625512795467865, | |
| "grad_norm": 1.658192753791809, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.1856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02750537214299668, | |
| "grad_norm": 1.4123740196228027, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.9552, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02875561633131471, | |
| "grad_norm": 1.5405542850494385, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 2.1995, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030005860519632742, | |
| "grad_norm": 1.623979091644287, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7656, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031256104707950774, | |
| "grad_norm": 1.594278335571289, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 1.4945, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031256104707950774, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.4527, | |
| "eval_samples_per_second": 11.229, | |
| "eval_steps_per_second": 2.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0325063488962688, | |
| "grad_norm": 4.290698528289795, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 2.7465, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03375659308458683, | |
| "grad_norm": 3.880889415740967, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.5353, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.035006837272904864, | |
| "grad_norm": 2.8910319805145264, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 2.6292, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0362570814612229, | |
| "grad_norm": 2.103529453277588, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 2.3267, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03750732564954093, | |
| "grad_norm": 2.1339449882507324, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.4088, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038757569837858954, | |
| "grad_norm": 2.083258867263794, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 2.2545, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04000781402617699, | |
| "grad_norm": 1.7957262992858887, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 2.2531, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04125805821449502, | |
| "grad_norm": 1.5465190410614014, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.2347, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04250830240281305, | |
| "grad_norm": 1.6104645729064941, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 2.1565, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04375854659113108, | |
| "grad_norm": 1.7143096923828125, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 2.0586, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04500879077944911, | |
| "grad_norm": 1.9381986856460571, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.9545, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04625903496776714, | |
| "grad_norm": 1.737153172492981, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 1.8466, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.047509279156085174, | |
| "grad_norm": 1.7730242013931274, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 2.2282, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.048759523344403206, | |
| "grad_norm": 1.610041856765747, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.2569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05000976753272123, | |
| "grad_norm": 1.6900049448013306, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 2.3254, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.051260011721039264, | |
| "grad_norm": 1.7346092462539673, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 2.3187, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0525102559093573, | |
| "grad_norm": 1.3713421821594238, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.2042, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05376050009767533, | |
| "grad_norm": 1.1843212842941284, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 2.1743, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05501074428599336, | |
| "grad_norm": 1.167022705078125, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 2.2873, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05626098847431139, | |
| "grad_norm": 1.212775468826294, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2581, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05751123266262942, | |
| "grad_norm": 1.5787919759750366, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 2.0386, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05876147685094745, | |
| "grad_norm": 1.6239919662475586, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 1.9584, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.060011721039265484, | |
| "grad_norm": 1.540845513343811, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9723, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06126196522758351, | |
| "grad_norm": 1.7158163785934448, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 1.8209, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06251220941590155, | |
| "grad_norm": 2.355154275894165, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 1.611, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06251220941590155, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.358, | |
| "eval_samples_per_second": 11.473, | |
| "eval_steps_per_second": 2.983, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |