| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.547169811320755, |
| "eval_steps": 200, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.018867924528301886, |
| "eval_loss": 2.017465591430664, |
| "eval_runtime": 24.849, |
| "eval_samples_per_second": 60.405, |
| "eval_steps_per_second": 3.783, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.18867924528301888, |
| "grad_norm": 1.640625, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.729, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.37735849056603776, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 1.6468, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5660377358490566, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0002, |
| "loss": 1.7455, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.8359375, |
| "learning_rate": 0.00019984815164333163, |
| "loss": 1.7135, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9433962264150944, |
| "grad_norm": 0.85546875, |
| "learning_rate": 0.00019939306773179497, |
| "loss": 1.7049, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1320754716981132, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 1.2839, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.320754716981132, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00019757963826274357, |
| "loss": 1.2625, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.509433962264151, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.00019622680003092503, |
| "loss": 1.0337, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.6981132075471699, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 1.038, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8867924528301887, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.00019264940672148018, |
| "loss": 1.1882, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0754716981132075, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.00019043571606975777, |
| "loss": 0.8319, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.2641509433962264, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 0.4283, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.452830188679245, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.00018519194088383273, |
| "loss": 0.4301, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.641509433962264, |
| "grad_norm": 0.84375, |
| "learning_rate": 0.0001821777815225245, |
| "loss": 0.4305, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.830188679245283, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 0.7161, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.018867924528302, |
| "grad_norm": 0.63671875, |
| "learning_rate": 0.00017541066097768963, |
| "loss": 0.4131, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.207547169811321, |
| "grad_norm": 0.71875, |
| "learning_rate": 0.00017167825131684513, |
| "loss": 0.3015, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.3962264150943398, |
| "grad_norm": 0.57421875, |
| "learning_rate": 0.00016772815716257412, |
| "loss": 0.1438, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.5849056603773586, |
| "grad_norm": 0.5546875, |
| "learning_rate": 0.00016357237482099684, |
| "loss": 0.2742, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.7735849056603774, |
| "grad_norm": 0.6953125, |
| "learning_rate": 0.00015922352526649803, |
| "loss": 0.1363, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.7735849056603774, |
| "eval_loss": 2.5724847316741943, |
| "eval_runtime": 18.9982, |
| "eval_samples_per_second": 79.007, |
| "eval_steps_per_second": 4.948, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.9622641509433962, |
| "grad_norm": 0.58984375, |
| "learning_rate": 0.00015469481581224272, |
| "loss": 0.1385, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.150943396226415, |
| "grad_norm": 0.294921875, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.0523, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.339622641509434, |
| "grad_norm": 0.3515625, |
| "learning_rate": 0.00014515333583108896, |
| "loss": 0.0338, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.528301886792453, |
| "grad_norm": 0.337890625, |
| "learning_rate": 0.00014016954246529696, |
| "loss": 0.2872, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.716981132075472, |
| "grad_norm": 0.3828125, |
| "learning_rate": 0.00013506375551927547, |
| "loss": 0.0379, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.90566037735849, |
| "grad_norm": 0.33984375, |
| "learning_rate": 0.00012985148110016947, |
| "loss": 0.153, |
| "step": 260 |
| }, |
| { |
| "epoch": 5.09433962264151, |
| "grad_norm": 0.12451171875, |
| "learning_rate": 0.00012454854871407994, |
| "loss": 0.0279, |
| "step": 270 |
| }, |
| { |
| "epoch": 5.283018867924528, |
| "grad_norm": 0.1083984375, |
| "learning_rate": 0.00011917106319237386, |
| "loss": 0.0072, |
| "step": 280 |
| }, |
| { |
| "epoch": 5.471698113207547, |
| "grad_norm": 0.1318359375, |
| "learning_rate": 0.00011373535578184082, |
| "loss": 0.0076, |
| "step": 290 |
| }, |
| { |
| "epoch": 5.660377358490566, |
| "grad_norm": 0.142578125, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 0.0072, |
| "step": 300 |
| }, |
| { |
| "epoch": 5.849056603773585, |
| "grad_norm": 0.1396484375, |
| "learning_rate": 0.00010275543423681621, |
| "loss": 0.0078, |
| "step": 310 |
| }, |
| { |
| "epoch": 6.037735849056604, |
| "grad_norm": 0.138671875, |
| "learning_rate": 9.724456576318381e-05, |
| "loss": 0.0061, |
| "step": 320 |
| }, |
| { |
| "epoch": 6.226415094339623, |
| "grad_norm": 0.78515625, |
| "learning_rate": 9.174206545276677e-05, |
| "loss": 0.1177, |
| "step": 330 |
| }, |
| { |
| "epoch": 6.415094339622642, |
| "grad_norm": 0.11962890625, |
| "learning_rate": 8.626464421815919e-05, |
| "loss": 0.0031, |
| "step": 340 |
| }, |
| { |
| "epoch": 6.60377358490566, |
| "grad_norm": 0.035400390625, |
| "learning_rate": 8.082893680762619e-05, |
| "loss": 0.0028, |
| "step": 350 |
| }, |
| { |
| "epoch": 6.7924528301886795, |
| "grad_norm": 0.04541015625, |
| "learning_rate": 7.54514512859201e-05, |
| "loss": 0.0026, |
| "step": 360 |
| }, |
| { |
| "epoch": 6.981132075471698, |
| "grad_norm": 0.0400390625, |
| "learning_rate": 7.014851889983057e-05, |
| "loss": 0.0034, |
| "step": 370 |
| }, |
| { |
| "epoch": 7.169811320754717, |
| "grad_norm": 0.0225830078125, |
| "learning_rate": 6.493624448072457e-05, |
| "loss": 0.1195, |
| "step": 380 |
| }, |
| { |
| "epoch": 7.3584905660377355, |
| "grad_norm": 0.034423828125, |
| "learning_rate": 5.983045753470308e-05, |
| "loss": 0.0019, |
| "step": 390 |
| }, |
| { |
| "epoch": 7.547169811320755, |
| "grad_norm": 0.0263671875, |
| "learning_rate": 5.484666416891109e-05, |
| "loss": 0.0019, |
| "step": 400 |
| }, |
| { |
| "epoch": 7.547169811320755, |
| "eval_loss": 3.409816265106201, |
| "eval_runtime": 19.0169, |
| "eval_samples_per_second": 78.93, |
| "eval_steps_per_second": 4.943, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 12, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.9246827031166976e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
