| { | |
| "best_metric": 2.0400946140289307, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.6229508196721314, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05245901639344262, | |
| "grad_norm": 28.040943145751953, | |
| "learning_rate": 5e-05, | |
| "loss": 34.5942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05245901639344262, | |
| "eval_loss": 2.3756308555603027, | |
| "eval_runtime": 4.6778, | |
| "eval_samples_per_second": 10.689, | |
| "eval_steps_per_second": 2.779, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10491803278688525, | |
| "grad_norm": 32.83949661254883, | |
| "learning_rate": 0.0001, | |
| "loss": 36.1517, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15737704918032788, | |
| "grad_norm": 19.23084831237793, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 35.2352, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2098360655737705, | |
| "grad_norm": 25.612417221069336, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 36.0173, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 31.208818435668945, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 36.4542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31475409836065577, | |
| "grad_norm": 18.078365325927734, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 33.7462, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36721311475409835, | |
| "grad_norm": 12.693277359008789, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 33.5992, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.419672131147541, | |
| "grad_norm": 13.131746292114258, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 34.7373, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4721311475409836, | |
| "grad_norm": 15.925198554992676, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 35.3066, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 26.936176300048828, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 34.8721, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5770491803278689, | |
| "grad_norm": 9.179637908935547, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 33.0316, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6295081967213115, | |
| "grad_norm": 9.933494567871094, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 34.1036, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6819672131147541, | |
| "grad_norm": 8.703592300415039, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 34.0136, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7344262295081967, | |
| "grad_norm": 9.874922752380371, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 34.5527, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 12.227039337158203, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 32.3872, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.839344262295082, | |
| "grad_norm": 8.206033706665039, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 33.3664, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8918032786885246, | |
| "grad_norm": 7.768029689788818, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 33.6671, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9442622950819672, | |
| "grad_norm": 8.540914535522461, | |
| "learning_rate": 7.75e-05, | |
| "loss": 33.2975, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9967213114754099, | |
| "grad_norm": 11.925562858581543, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 34.973, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 7.6253767013549805, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 31.5295, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1016393442622952, | |
| "grad_norm": 10.110396385192871, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 31.8094, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1540983606557378, | |
| "grad_norm": 8.087203979492188, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 31.5272, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2065573770491804, | |
| "grad_norm": 8.519153594970703, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 32.3371, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2590163934426228, | |
| "grad_norm": 13.146418571472168, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 32.0866, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 8.602477073669434, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 31.1782, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "eval_loss": 2.044109582901001, | |
| "eval_runtime": 4.7369, | |
| "eval_samples_per_second": 10.556, | |
| "eval_steps_per_second": 2.744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3639344262295081, | |
| "grad_norm": 7.692803859710693, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 30.9557, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4163934426229507, | |
| "grad_norm": 7.772709369659424, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 31.432, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.4688524590163934, | |
| "grad_norm": 9.130861282348633, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 32.0877, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.521311475409836, | |
| "grad_norm": 10.832189559936523, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 31.0261, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 8.154661178588867, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 30.5008, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6262295081967213, | |
| "grad_norm": 8.400430679321289, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 31.3353, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.678688524590164, | |
| "grad_norm": 8.89877700805664, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 30.9697, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7311475409836066, | |
| "grad_norm": 9.605426788330078, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 32.3451, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7836065573770492, | |
| "grad_norm": 12.887454986572266, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 30.6939, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8360655737704918, | |
| "grad_norm": 8.313308715820312, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 30.9625, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8885245901639345, | |
| "grad_norm": 9.007829666137695, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 31.2103, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.940983606557377, | |
| "grad_norm": 8.962111473083496, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 31.4604, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.9934426229508198, | |
| "grad_norm": 11.267090797424316, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 32.3345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.045901639344262, | |
| "grad_norm": 9.0362548828125, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 29.2781, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 7.795830249786377, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 29.9757, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1508196721311474, | |
| "grad_norm": 8.447335243225098, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 30.0933, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2032786885245903, | |
| "grad_norm": 9.279709815979004, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 29.6093, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.2557377049180327, | |
| "grad_norm": 11.038886070251465, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 30.4997, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.3081967213114756, | |
| "grad_norm": 8.14568042755127, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 29.6179, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.360655737704918, | |
| "grad_norm": 8.41407299041748, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 29.772, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.413114754098361, | |
| "grad_norm": 9.197470664978027, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 29.093, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.4655737704918033, | |
| "grad_norm": 10.19188404083252, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 30.6495, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.5180327868852457, | |
| "grad_norm": 13.069672584533691, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 30.3433, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.5704918032786885, | |
| "grad_norm": 8.42982006072998, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 29.7666, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 9.083083152770996, | |
| "learning_rate": 1e-05, | |
| "loss": 30.3737, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "eval_loss": 2.0400946140289307, | |
| "eval_runtime": 4.7581, | |
| "eval_samples_per_second": 10.508, | |
| "eval_steps_per_second": 2.732, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |