| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.01860176716788095, |
| "eval_steps": 3, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006200589055960316, |
| "grad_norm": 0.18599237501621246, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.9319, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0012401178111920632, |
| "grad_norm": 0.09086523950099945, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.6463, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "grad_norm": 0.09325356036424637, |
| "learning_rate": 1.2e-05, |
| "loss": 0.575, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "eval_loss": 0.7272388935089111, |
| "eval_runtime": 33.9288, |
| "eval_samples_per_second": 2.947, |
| "eval_steps_per_second": 2.947, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0024802356223841263, |
| "grad_norm": 0.09707680344581604, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.7038, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0031002945279801583, |
| "grad_norm": 0.10810782760381699, |
| "learning_rate": 2e-05, |
| "loss": 0.5471, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "grad_norm": 0.13030411303043365, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 0.6735, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "eval_loss": 0.7256982922554016, |
| "eval_runtime": 33.9528, |
| "eval_samples_per_second": 2.945, |
| "eval_steps_per_second": 2.945, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.004340412339172222, |
| "grad_norm": 0.12336976826190948, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 0.654, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.004960471244768253, |
| "grad_norm": 0.16046489775180817, |
| "learning_rate": 1.76e-05, |
| "loss": 0.6301, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.005580530150364285, |
| "grad_norm": 0.11589628458023071, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 0.5326, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.005580530150364285, |
| "eval_loss": 0.723076343536377, |
| "eval_runtime": 34.5303, |
| "eval_samples_per_second": 2.896, |
| "eval_steps_per_second": 2.896, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0062005890559603165, |
| "grad_norm": 0.12244553864002228, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.8055, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0068206479615563476, |
| "grad_norm": 0.10270956158638, |
| "learning_rate": 1.5200000000000002e-05, |
| "loss": 0.5492, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.0074407068671523795, |
| "grad_norm": 0.14439155161380768, |
| "learning_rate": 1.4400000000000001e-05, |
| "loss": 0.8579, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0074407068671523795, |
| "eval_loss": 0.7205619215965271, |
| "eval_runtime": 33.7297, |
| "eval_samples_per_second": 2.965, |
| "eval_steps_per_second": 2.965, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.008060765772748411, |
| "grad_norm": 0.1271936148405075, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 0.6923, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.008680824678344443, |
| "grad_norm": 0.092640720307827, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 0.5983, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.009300883583940475, |
| "grad_norm": 0.1161455512046814, |
| "learning_rate": 1.2e-05, |
| "loss": 0.6386, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.009300883583940475, |
| "eval_loss": 0.7178443074226379, |
| "eval_runtime": 33.5878, |
| "eval_samples_per_second": 2.977, |
| "eval_steps_per_second": 2.977, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.009920942489536505, |
| "grad_norm": 0.09220079332590103, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 0.4665, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.010541001395132537, |
| "grad_norm": 0.08713295310735703, |
| "learning_rate": 1.04e-05, |
| "loss": 0.6114, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.01116106030072857, |
| "grad_norm": 0.11913106590509415, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 0.5703, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.01116106030072857, |
| "eval_loss": 0.7152560949325562, |
| "eval_runtime": 33.4806, |
| "eval_samples_per_second": 2.987, |
| "eval_steps_per_second": 2.987, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.011781119206324601, |
| "grad_norm": 0.11837327480316162, |
| "learning_rate": 8.8e-06, |
| "loss": 0.6049, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.012401178111920633, |
| "grad_norm": 0.08001928776502609, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.4691, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.013021237017516665, |
| "grad_norm": 0.11291633546352386, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 0.6752, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.013021237017516665, |
| "eval_loss": 0.7128345370292664, |
| "eval_runtime": 34.2622, |
| "eval_samples_per_second": 2.919, |
| "eval_steps_per_second": 2.919, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.013641295923112695, |
| "grad_norm": 0.1115325391292572, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.5874, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.014261354828708727, |
| "grad_norm": 0.1305752545595169, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 0.7733, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.014881413734304759, |
| "grad_norm": 0.10779058188199997, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.6217, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.014881413734304759, |
| "eval_loss": 0.7108609080314636, |
| "eval_runtime": 34.6034, |
| "eval_samples_per_second": 2.89, |
| "eval_steps_per_second": 2.89, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.01550147263990079, |
| "grad_norm": 0.11457020789384842, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.5838, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.016121531545496823, |
| "grad_norm": 0.1093108132481575, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.504, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.016741590451092855, |
| "grad_norm": 0.11828811466693878, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.5179, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.016741590451092855, |
| "eval_loss": 0.7094972133636475, |
| "eval_runtime": 34.2275, |
| "eval_samples_per_second": 2.922, |
| "eval_steps_per_second": 2.922, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.017361649356688887, |
| "grad_norm": 0.09534204006195068, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 0.4988, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.01798170826228492, |
| "grad_norm": 0.12317203730344772, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 0.6945, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.01860176716788095, |
| "grad_norm": 0.13696961104869843, |
| "learning_rate": 0.0, |
| "loss": 0.5378, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.01860176716788095, |
| "eval_loss": 0.7089178562164307, |
| "eval_runtime": 33.3831, |
| "eval_samples_per_second": 2.996, |
| "eval_steps_per_second": 2.996, |
| "step": 30 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.029866007950131e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
