| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03752697251149264, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018763486255746317, | |
| "eval_loss": 0.9478870630264282, | |
| "eval_runtime": 246.4229, | |
| "eval_samples_per_second": 9.106, | |
| "eval_steps_per_second": 4.553, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018763486255746317, | |
| "grad_norm": 1.1852015256881714, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 3.5285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037526972511492634, | |
| "grad_norm": 1.0713735818862915, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 2.3104, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005629045876723895, | |
| "grad_norm": 1.1629306077957153, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 2.0838, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007505394502298527, | |
| "grad_norm": 0.9892584681510925, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 2.2854, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00938174312787316, | |
| "grad_norm": 6.3884663581848145, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.9859, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00938174312787316, | |
| "eval_loss": 0.5233616232872009, | |
| "eval_runtime": 246.463, | |
| "eval_samples_per_second": 9.105, | |
| "eval_steps_per_second": 4.552, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01125809175344779, | |
| "grad_norm": 0.802453875541687, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 2.1749, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.013134440379022422, | |
| "grad_norm": 1.9824305772781372, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.3033, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.015010789004597054, | |
| "grad_norm": 1.2942346334457397, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 2.1344, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.016887137630171686, | |
| "grad_norm": 0.9966654777526855, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 2.0934, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01876348625574632, | |
| "grad_norm": 0.9738155603408813, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.9877, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01876348625574632, | |
| "eval_loss": 0.5045682787895203, | |
| "eval_runtime": 247.6377, | |
| "eval_samples_per_second": 9.062, | |
| "eval_steps_per_second": 4.531, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02063983488132095, | |
| "grad_norm": 0.9715750217437744, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 2.1053, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02251618350689558, | |
| "grad_norm": 0.8509733080863953, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 1.8666, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.024392532132470213, | |
| "grad_norm": 1.073076844215393, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 1.9373, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.026268880758044844, | |
| "grad_norm": 1.0255498886108398, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.9798, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.028145229383619477, | |
| "grad_norm": 0.932864785194397, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 2.0326, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.028145229383619477, | |
| "eval_loss": 0.4930672347545624, | |
| "eval_runtime": 247.1383, | |
| "eval_samples_per_second": 9.08, | |
| "eval_steps_per_second": 4.54, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.030021578009194107, | |
| "grad_norm": 0.8730648756027222, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 1.9601, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03189792663476874, | |
| "grad_norm": 1.2730159759521484, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 2.2116, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03377427526034337, | |
| "grad_norm": 0.9545321464538574, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.8604, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 0.9635279178619385, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 1.9259, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03752697251149264, | |
| "grad_norm": 1.0731476545333862, | |
| "learning_rate": 0.0, | |
| "loss": 2.2284, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03752697251149264, | |
| "eval_loss": 0.49111470580101013, | |
| "eval_runtime": 247.0242, | |
| "eval_samples_per_second": 9.084, | |
| "eval_steps_per_second": 4.542, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.298643675512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |