| { | |
| "best_metric": 1.8785371780395508, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.07072135785007072, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002828854314002829, | |
| "grad_norm": 4.835982322692871, | |
| "learning_rate": 5e-06, | |
| "loss": 2.7483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002828854314002829, | |
| "eval_loss": 2.652212142944336, | |
| "eval_runtime": 28.5954, | |
| "eval_samples_per_second": 20.843, | |
| "eval_steps_per_second": 2.623, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005657708628005658, | |
| "grad_norm": 5.14434289932251, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6398, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008486562942008486, | |
| "grad_norm": 4.789090156555176, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.7924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011315417256011316, | |
| "grad_norm": 4.524115562438965, | |
| "learning_rate": 2e-05, | |
| "loss": 2.787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014144271570014143, | |
| "grad_norm": 4.898167133331299, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.6675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016973125884016973, | |
| "grad_norm": 4.676875114440918, | |
| "learning_rate": 3e-05, | |
| "loss": 2.68, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 5.323249340057373, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.6687, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02263083451202263, | |
| "grad_norm": 5.85331392288208, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6787, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02545968882602546, | |
| "grad_norm": 4.22189474105835, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.5529, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.028288543140028287, | |
| "grad_norm": 4.426727771759033, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031117397454031116, | |
| "grad_norm": 4.649036884307861, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.5902, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.033946251768033946, | |
| "grad_norm": 5.093221664428711, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5167, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.036775106082036775, | |
| "grad_norm": 4.573429584503174, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 2.409, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": 4.811120986938477, | |
| "learning_rate": 7e-05, | |
| "loss": 2.5057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.042432814710042434, | |
| "grad_norm": 4.52741003036499, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.2795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04526166902404526, | |
| "grad_norm": 4.902586936950684, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04809052333804809, | |
| "grad_norm": 4.699262619018555, | |
| "learning_rate": 8.5e-05, | |
| "loss": 2.2644, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05091937765205092, | |
| "grad_norm": 4.109030246734619, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3355, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05374823196605375, | |
| "grad_norm": 4.7285943031311035, | |
| "learning_rate": 9.5e-05, | |
| "loss": 2.1301, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.056577086280056574, | |
| "grad_norm": 3.8704135417938232, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": 4.164304733276367, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.0421, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06223479490806223, | |
| "grad_norm": 4.296514987945557, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.0358, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06506364922206506, | |
| "grad_norm": 4.264124393463135, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06789250353606789, | |
| "grad_norm": 4.8569016456604, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.0011, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07072135785007072, | |
| "grad_norm": 4.313958168029785, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8973, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07072135785007072, | |
| "eval_loss": 1.8785371780395508, | |
| "eval_runtime": 28.6135, | |
| "eval_samples_per_second": 20.829, | |
| "eval_steps_per_second": 2.621, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3482313383936e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |