| { | |
| "best_metric": 0.13966971635818481, | |
| "best_model_checkpoint": "saves/Gemma-7B/lora/train_1/checkpoint-50", | |
| "epoch": 2.8828828828828827, | |
| "eval_steps": 10, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 12.859936714172363, | |
| "learning_rate": 4.814309923172227e-05, | |
| "loss": 6.4386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "eval_loss": 0.7805296778678894, | |
| "eval_runtime": 58.0357, | |
| "eval_samples_per_second": 25.226, | |
| "eval_steps_per_second": 3.153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 2.831813335418701, | |
| "learning_rate": 4.2848243363947484e-05, | |
| "loss": 0.2931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "eval_loss": 0.14660023152828217, | |
| "eval_runtime": 58.018, | |
| "eval_samples_per_second": 25.234, | |
| "eval_steps_per_second": 3.154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.9679704308509827, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 0.1433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "eval_loss": 0.142491415143013, | |
| "eval_runtime": 58.0956, | |
| "eval_samples_per_second": 25.2, | |
| "eval_steps_per_second": 3.15, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 0.43013083934783936, | |
| "learning_rate": 2.548478329429561e-05, | |
| "loss": 0.1384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "eval_loss": 0.14014391601085663, | |
| "eval_runtime": 58.0161, | |
| "eval_samples_per_second": 25.234, | |
| "eval_steps_per_second": 3.154, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "grad_norm": 0.21392107009887695, | |
| "learning_rate": 1.5995556879882246e-05, | |
| "loss": 0.137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "eval_loss": 0.13966971635818481, | |
| "eval_runtime": 58.0599, | |
| "eval_samples_per_second": 25.215, | |
| "eval_steps_per_second": 3.152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.3341553211212158, | |
| "learning_rate": 7.843959053281663e-06, | |
| "loss": 0.1392, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "eval_loss": 0.14178413152694702, | |
| "eval_runtime": 58.0557, | |
| "eval_samples_per_second": 25.217, | |
| "eval_steps_per_second": 3.152, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "grad_norm": 0.27669599652290344, | |
| "learning_rate": 2.2409264758463363e-06, | |
| "loss": 0.1357, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "eval_loss": 0.14104121923446655, | |
| "eval_runtime": 57.9995, | |
| "eval_samples_per_second": 25.242, | |
| "eval_steps_per_second": 3.155, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "grad_norm": 0.3385619521141052, | |
| "learning_rate": 1.8801187394248965e-08, | |
| "loss": 0.1351, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "eval_loss": 0.1403447389602661, | |
| "eval_runtime": 58.0503, | |
| "eval_samples_per_second": 25.22, | |
| "eval_steps_per_second": 3.152, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "step": 80, | |
| "total_flos": 1.1914609852317696e+17, | |
| "train_loss": 0.945058161020279, | |
| "train_runtime": 2744.9763, | |
| "train_samples_per_second": 7.762, | |
| "train_steps_per_second": 0.03 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 81, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1914609852317696e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |