| { | |
| "best_metric": 0.7776047587394714, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.051282051282051, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05860805860805861, | |
| "grad_norm": 41.95743179321289, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05860805860805861, | |
| "eval_loss": 11.64078426361084, | |
| "eval_runtime": 11.7698, | |
| "eval_samples_per_second": 19.542, | |
| "eval_steps_per_second": 1.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11721611721611722, | |
| "grad_norm": 42.654151916503906, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17582417582417584, | |
| "grad_norm": 30.422691345214844, | |
| "learning_rate": 9.977359612865423e-05, | |
| "loss": 8.9994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23443223443223443, | |
| "grad_norm": 17.667789459228516, | |
| "learning_rate": 9.909643486313533e-05, | |
| "loss": 4.2615, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 9.984042167663574, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 1.9114, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3516483516483517, | |
| "grad_norm": 3.775686740875244, | |
| "learning_rate": 9.641839665080363e-05, | |
| "loss": 1.1071, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 2.311100721359253, | |
| "learning_rate": 9.444177243274618e-05, | |
| "loss": 0.9249, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.46886446886446886, | |
| "grad_norm": 2.155744791030884, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.9448, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "grad_norm": 1.0787104368209839, | |
| "learning_rate": 8.930265473713938e-05, | |
| "loss": 0.8014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.8048316836357117, | |
| "learning_rate": 8.618670190525352e-05, | |
| "loss": 0.7563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6446886446886447, | |
| "grad_norm": 1.2824442386627197, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.8288, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7032967032967034, | |
| "grad_norm": 0.678689181804657, | |
| "learning_rate": 7.900284547855991e-05, | |
| "loss": 0.8168, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.908683717250824, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8063, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.9696321487426758, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.728, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.7471110224723816, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 0.7831, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9377289377289377, | |
| "grad_norm": 1.1943230628967285, | |
| "learning_rate": 6.178794677547137e-05, | |
| "loss": 0.828, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9963369963369964, | |
| "grad_norm": 1.1461800336837769, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.8597, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.054945054945055, | |
| "grad_norm": 1.492602825164795, | |
| "learning_rate": 5.2379095791187124e-05, | |
| "loss": 1.5238, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1135531135531136, | |
| "grad_norm": 1.4935457706451416, | |
| "learning_rate": 4.762090420881289e-05, | |
| "loss": 0.7688, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1721611721611722, | |
| "grad_norm": 1.063358187675476, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.8187, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.6111706495285034, | |
| "learning_rate": 3.821205322452863e-05, | |
| "loss": 0.8065, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2893772893772895, | |
| "grad_norm": 0.592510998249054, | |
| "learning_rate": 3.364660183412892e-05, | |
| "loss": 0.7727, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.347985347985348, | |
| "grad_norm": 0.515056312084198, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.7482, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4065934065934065, | |
| "grad_norm": 0.6317391395568848, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7803, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "grad_norm": 1.648141860961914, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 0.8176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "eval_loss": 0.7776047587394714, | |
| "eval_runtime": 11.7656, | |
| "eval_samples_per_second": 19.549, | |
| "eval_steps_per_second": 1.275, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.7313464879989624, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.7806, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5824175824175826, | |
| "grad_norm": 0.6874339580535889, | |
| "learning_rate": 1.3813298094746491e-05, | |
| "loss": 0.744, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.6659790277481079, | |
| "learning_rate": 1.0697345262860636e-05, | |
| "loss": 0.8011, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6996336996336996, | |
| "grad_norm": 0.8043178915977478, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.8361, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 0.5227417349815369, | |
| "learning_rate": 5.558227567253832e-06, | |
| "loss": 0.7979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8168498168498168, | |
| "grad_norm": 0.5979397892951965, | |
| "learning_rate": 3.581603349196372e-06, | |
| "loss": 0.7131, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8754578754578755, | |
| "grad_norm": 0.43952739238739014, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.7307, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.934065934065934, | |
| "grad_norm": 0.8428590297698975, | |
| "learning_rate": 9.035651368646648e-07, | |
| "loss": 0.7661, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9926739926739927, | |
| "grad_norm": 0.6554544568061829, | |
| "learning_rate": 2.2640387134577058e-07, | |
| "loss": 0.8265, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 2.641814708709717, | |
| "learning_rate": 0.0, | |
| "loss": 1.6606, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "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": 9.283934412917965e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |