| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 134, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007462686567164179, | |
| "grad_norm": 1.777404546737671, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.2363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 1.1628299951553345, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.1427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 0.5306259989738464, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.8518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 0.36661896109580994, | |
| "learning_rate": 0.00019996573249755572, | |
| "loss": 0.6968, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.22499878704547882, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.6287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 0.23837368190288544, | |
| "learning_rate": 0.0001958819734868193, | |
| "loss": 0.5985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.20461460947990417, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.5683, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 0.1855892837047577, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 0.555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.22351227700710297, | |
| "learning_rate": 0.0001777145961456971, | |
| "loss": 0.5436, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 0.2045900523662567, | |
| "learning_rate": 0.0001688354575693754, | |
| "loss": 0.531, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.20202215015888214, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.5251, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.20512989163398743, | |
| "learning_rate": 0.00014771587602596084, | |
| "loss": 0.519, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.21831591427326202, | |
| "learning_rate": 0.00013583679495453, | |
| "loss": 0.5138, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 0.20354878902435303, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 0.5104, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.1882062703371048, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.5059, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 0.21688711643218994, | |
| "learning_rate": 9.73823051692127e-05, | |
| "loss": 0.4992, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.2021055668592453, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.4936, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 0.18059054017066956, | |
| "learning_rate": 7.159846552960774e-05, | |
| "loss": 0.5016, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.19665920734405518, | |
| "learning_rate": 5.9326335692419995e-05, | |
| "loss": 0.4983, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 0.20969931781291962, | |
| "learning_rate": 4.7750143528405126e-05, | |
| "loss": 0.4911, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.19205212593078613, | |
| "learning_rate": 3.7067960895016275e-05, | |
| "loss": 0.4964, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 0.17200438678264618, | |
| "learning_rate": 2.746256289877126e-05, | |
| "loss": 0.4879, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.17229676246643066, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.4915, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.17735055088996887, | |
| "learning_rate": 1.2118288733803473e-05, | |
| "loss": 0.4883, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.17195551097393036, | |
| "learning_rate": 6.6419573502798374e-06, | |
| "loss": 0.4912, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.17827412486076355, | |
| "learning_rate": 2.7630079602323442e-06, | |
| "loss": 0.4861, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.17053547501564026, | |
| "learning_rate": 5.478104631726711e-07, | |
| "loss": 0.4852, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.1658700853586197, | |
| "eval_runtime": 9.0857, | |
| "eval_samples_per_second": 9.685, | |
| "eval_steps_per_second": 0.33, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 134, | |
| "total_flos": 3.768774247149732e+17, | |
| "train_loss": 0.5603564016854585, | |
| "train_runtime": 1424.9095, | |
| "train_samples_per_second": 3.001, | |
| "train_steps_per_second": 0.094 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 134, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.768774247149732e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |