| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013021237017516665, | |
| "eval_steps": 3, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006200589055960316, | |
| "grad_norm": 0.39027148485183716, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.1401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012401178111920632, | |
| "grad_norm": 0.1772935390472412, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.9133, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018601767167880949, | |
| "grad_norm": 0.192855104804039, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.8036, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018601767167880949, | |
| "eval_loss": 0.993510365486145, | |
| "eval_runtime": 46.5106, | |
| "eval_samples_per_second": 2.15, | |
| "eval_steps_per_second": 2.15, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024802356223841263, | |
| "grad_norm": 0.23705194890499115, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.9389, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031002945279801583, | |
| "grad_norm": 0.22702816128730774, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7836, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037203534335761897, | |
| "grad_norm": 0.22573529183864594, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.8874, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037203534335761897, | |
| "eval_loss": 0.9887735843658447, | |
| "eval_runtime": 47.2769, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 2.115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004340412339172222, | |
| "grad_norm": 0.231398344039917, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.8755, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004960471244768253, | |
| "grad_norm": 0.28229379653930664, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.971, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005580530150364285, | |
| "grad_norm": 0.21991951763629913, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.8546, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005580530150364285, | |
| "eval_loss": 0.9774181842803955, | |
| "eval_runtime": 47.3982, | |
| "eval_samples_per_second": 2.11, | |
| "eval_steps_per_second": 2.11, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0062005890559603165, | |
| "grad_norm": 0.26028916239738464, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.0344, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0068206479615563476, | |
| "grad_norm": 0.23867206275463104, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.8132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0074407068671523795, | |
| "grad_norm": 0.30641764402389526, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 1.1168, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0074407068671523795, | |
| "eval_loss": 0.963714599609375, | |
| "eval_runtime": 47.188, | |
| "eval_samples_per_second": 2.119, | |
| "eval_steps_per_second": 2.119, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008060765772748411, | |
| "grad_norm": 0.25963348150253296, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.9735, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008680824678344443, | |
| "grad_norm": 0.2063651829957962, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.7957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009300883583940475, | |
| "grad_norm": 0.2287115454673767, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.8343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009300883583940475, | |
| "eval_loss": 0.9510444402694702, | |
| "eval_runtime": 47.3972, | |
| "eval_samples_per_second": 2.11, | |
| "eval_steps_per_second": 2.11, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009920942489536505, | |
| "grad_norm": 0.2136881947517395, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.7861, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010541001395132537, | |
| "grad_norm": 0.16134004294872284, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.8375, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01116106030072857, | |
| "grad_norm": 0.20020240545272827, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.8086, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01116106030072857, | |
| "eval_loss": 0.9415214657783508, | |
| "eval_runtime": 47.2291, | |
| "eval_samples_per_second": 2.117, | |
| "eval_steps_per_second": 2.117, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011781119206324601, | |
| "grad_norm": 0.2330344021320343, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.7858, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012401178111920633, | |
| "grad_norm": 0.175759956240654, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013021237017516665, | |
| "grad_norm": 0.21558189392089844, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.8966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013021237017516665, | |
| "eval_loss": 0.9336352348327637, | |
| "eval_runtime": 47.0196, | |
| "eval_samples_per_second": 2.127, | |
| "eval_steps_per_second": 2.127, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.495772591437824e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |