| { | |
| "best_metric": 0.26085758209228516, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.010752688172043, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 1.8886111974716187, | |
| "learning_rate": 5e-05, | |
| "loss": 0.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "eval_loss": 0.7152150869369507, | |
| "eval_runtime": 3.5362, | |
| "eval_samples_per_second": 22.34, | |
| "eval_steps_per_second": 2.828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 2.1663036346435547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6948, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.239184021949768, | |
| "learning_rate": 9.977359612865423e-05, | |
| "loss": 0.694, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 0.6597561836242676, | |
| "learning_rate": 9.909643486313533e-05, | |
| "loss": 0.4295, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.7343956828117371, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.4282, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.6272724866867065, | |
| "learning_rate": 9.641839665080363e-05, | |
| "loss": 0.409, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 0.4894818961620331, | |
| "learning_rate": 9.444177243274618e-05, | |
| "loss": 0.3302, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 0.49684205651283264, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.3077, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.36764946579933167, | |
| "learning_rate": 8.930265473713938e-05, | |
| "loss": 0.3224, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 0.31620141863822937, | |
| "learning_rate": 8.618670190525352e-05, | |
| "loss": 0.3121, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "grad_norm": 0.37370702624320984, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.3347, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 0.5700744390487671, | |
| "learning_rate": 7.900284547855991e-05, | |
| "loss": 0.4621, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.118279569892473, | |
| "grad_norm": 0.43438950181007385, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2736, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2043010752688172, | |
| "grad_norm": 0.39586031436920166, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.2847, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.4413219094276428, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 0.3298, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3763440860215055, | |
| "grad_norm": 0.3812790811061859, | |
| "learning_rate": 6.178794677547137e-05, | |
| "loss": 0.2532, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4623655913978495, | |
| "grad_norm": 0.3373176157474518, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.2443, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 0.31114816665649414, | |
| "learning_rate": 5.2379095791187124e-05, | |
| "loss": 0.3003, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6344086021505375, | |
| "grad_norm": 0.32430943846702576, | |
| "learning_rate": 4.762090420881289e-05, | |
| "loss": 0.2514, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 0.3630256950855255, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.2745, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 0.27914172410964966, | |
| "learning_rate": 3.821205322452863e-05, | |
| "loss": 0.242, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.89247311827957, | |
| "grad_norm": 0.37263160943984985, | |
| "learning_rate": 3.364660183412892e-05, | |
| "loss": 0.2772, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.978494623655914, | |
| "grad_norm": 0.46930578351020813, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.3409, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 0.40534141659736633, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 0.34685373306274414, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 0.2348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "eval_loss": 0.26085758209228516, | |
| "eval_runtime": 3.5429, | |
| "eval_samples_per_second": 22.298, | |
| "eval_steps_per_second": 2.823, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.236559139784946, | |
| "grad_norm": 0.350571870803833, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.2556, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3225806451612905, | |
| "grad_norm": 0.33824387192726135, | |
| "learning_rate": 1.3813298094746491e-05, | |
| "loss": 0.2453, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4086021505376345, | |
| "grad_norm": 0.33050841093063354, | |
| "learning_rate": 1.0697345262860636e-05, | |
| "loss": 0.2701, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4946236559139785, | |
| "grad_norm": 0.4018042981624603, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.2571, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 0.3769586384296417, | |
| "learning_rate": 5.558227567253832e-06, | |
| "loss": 0.265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.3363115191459656, | |
| "learning_rate": 3.581603349196372e-06, | |
| "loss": 0.2491, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.752688172043011, | |
| "grad_norm": 0.3187609612941742, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.2414, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.838709677419355, | |
| "grad_norm": 0.29826077818870544, | |
| "learning_rate": 9.035651368646648e-07, | |
| "loss": 0.2394, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.924731182795699, | |
| "grad_norm": 0.4264858663082123, | |
| "learning_rate": 2.2640387134577058e-07, | |
| "loss": 0.2775, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.010752688172043, | |
| "grad_norm": 0.34414350986480713, | |
| "learning_rate": 0.0, | |
| "loss": 0.3759, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.595424428283658e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |