| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08458646616541353, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018796992481203006, | |
| "eval_loss": 2.188689947128296, | |
| "eval_runtime": 15.8759, | |
| "eval_samples_per_second": 28.219, | |
| "eval_steps_per_second": 7.055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005639097744360902, | |
| "grad_norm": 2.3131868839263916, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009398496240601503, | |
| "eval_loss": 2.0904104709625244, | |
| "eval_runtime": 15.9911, | |
| "eval_samples_per_second": 28.016, | |
| "eval_steps_per_second": 7.004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011278195488721804, | |
| "grad_norm": 1.1980903148651123, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016917293233082706, | |
| "grad_norm": 1.9292231798171997, | |
| "learning_rate": 9e-05, | |
| "loss": 2.0794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018796992481203006, | |
| "eval_loss": 1.9134695529937744, | |
| "eval_runtime": 16.0172, | |
| "eval_samples_per_second": 27.97, | |
| "eval_steps_per_second": 6.992, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022556390977443608, | |
| "grad_norm": 1.6164668798446655, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.9332, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02819548872180451, | |
| "grad_norm": 1.1573011875152588, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7655, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02819548872180451, | |
| "eval_loss": 1.7978755235671997, | |
| "eval_runtime": 16.0385, | |
| "eval_samples_per_second": 27.933, | |
| "eval_steps_per_second": 6.983, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03383458646616541, | |
| "grad_norm": 1.463262677192688, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.7978, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03759398496240601, | |
| "eval_loss": 1.7174512147903442, | |
| "eval_runtime": 16.0423, | |
| "eval_samples_per_second": 27.926, | |
| "eval_steps_per_second": 6.982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 1.2767959833145142, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.724, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.045112781954887216, | |
| "grad_norm": 1.445420265197754, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.7438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.046992481203007516, | |
| "eval_loss": 1.6554962396621704, | |
| "eval_runtime": 16.0491, | |
| "eval_samples_per_second": 27.914, | |
| "eval_steps_per_second": 6.979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05075187969924812, | |
| "grad_norm": 1.6344633102416992, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.609, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05639097744360902, | |
| "grad_norm": 1.6545953750610352, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05639097744360902, | |
| "eval_loss": 1.6130125522613525, | |
| "eval_runtime": 16.0529, | |
| "eval_samples_per_second": 27.908, | |
| "eval_steps_per_second": 6.977, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06203007518796992, | |
| "grad_norm": 1.566185712814331, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.5506, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "eval_loss": 1.5798027515411377, | |
| "eval_runtime": 16.0818, | |
| "eval_samples_per_second": 27.858, | |
| "eval_steps_per_second": 6.964, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06766917293233082, | |
| "grad_norm": 1.518865704536438, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.5894, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07330827067669173, | |
| "grad_norm": 1.5283524990081787, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.592, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "eval_loss": 1.5614439249038696, | |
| "eval_runtime": 16.0674, | |
| "eval_samples_per_second": 27.883, | |
| "eval_steps_per_second": 6.971, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 1.3438414335250854, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6063, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08458646616541353, | |
| "grad_norm": 1.4435805082321167, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5254, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08458646616541353, | |
| "eval_loss": 1.552406907081604, | |
| "eval_runtime": 16.0663, | |
| "eval_samples_per_second": 27.885, | |
| "eval_steps_per_second": 6.971, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8940733763420160.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |