| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026006111436187505, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000260061114361875, | |
| "eval_loss": 3.210697650909424, | |
| "eval_runtime": 46.0394, | |
| "eval_samples_per_second": 140.684, | |
| "eval_steps_per_second": 17.594, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001300305571809375, | |
| "grad_norm": 0.1790143996477127, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2141, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00260061114361875, | |
| "grad_norm": 0.20394925773143768, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 0.21119458973407745, | |
| "learning_rate": 9.995944990857849e-05, | |
| "loss": 3.1673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0052012222872375, | |
| "grad_norm": 0.2528775930404663, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 3.1641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "grad_norm": 0.2846454381942749, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 3.0395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 0.2666814625263214, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 2.9841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009102139002665627, | |
| "grad_norm": 0.2622530460357666, | |
| "learning_rate": 9.898953260211338e-05, | |
| "loss": 2.7829, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010402444574475, | |
| "grad_norm": 0.25730785727500916, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 2.911, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 0.23502734303474426, | |
| "learning_rate": 9.802590558156862e-05, | |
| "loss": 2.7205, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "grad_norm": 0.22792138159275055, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 2.7597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014303361289903128, | |
| "grad_norm": 0.22460439801216125, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 2.624, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015603666861712502, | |
| "grad_norm": 0.2262052595615387, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 2.6747, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.016903972433521878, | |
| "grad_norm": 0.21055257320404053, | |
| "learning_rate": 9.517252173051911e-05, | |
| "loss": 2.6395, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018204278005331254, | |
| "grad_norm": 0.20293797552585602, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 2.5635, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01950458357714063, | |
| "grad_norm": 0.19834651052951813, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.6046, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02080488914895, | |
| "grad_norm": 0.2112269252538681, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 2.5376, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022105194720759377, | |
| "grad_norm": 0.1964295357465744, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 2.4841, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.023405500292568753, | |
| "grad_norm": 0.20404809713363647, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 2.451, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02470580586437813, | |
| "grad_norm": 0.2313140332698822, | |
| "learning_rate": 8.873024809138272e-05, | |
| "loss": 2.487, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "grad_norm": 0.23010624945163727, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 2.4241, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "eval_loss": 2.4956908226013184, | |
| "eval_runtime": 45.9142, | |
| "eval_samples_per_second": 141.067, | |
| "eval_steps_per_second": 17.642, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6349734008586240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |