| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011395362087630334, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002279072417526067, | |
| "eval_loss": 2.6313023567199707, | |
| "eval_runtime": 200.9638, | |
| "eval_samples_per_second": 9.196, | |
| "eval_steps_per_second": 4.598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011395362087630334, | |
| "grad_norm": 6.184070587158203, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022790724175260667, | |
| "grad_norm": 4.256957054138184, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022790724175260667, | |
| "eval_loss": 2.4396352767944336, | |
| "eval_runtime": 201.6418, | |
| "eval_samples_per_second": 9.165, | |
| "eval_steps_per_second": 4.582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034186086262891005, | |
| "grad_norm": 5.593558311462402, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.6311, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004558144835052133, | |
| "grad_norm": 3.0657575130462646, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.5522, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004558144835052133, | |
| "eval_loss": 2.3475072383880615, | |
| "eval_runtime": 201.0803, | |
| "eval_samples_per_second": 9.19, | |
| "eval_steps_per_second": 4.595, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005697681043815167, | |
| "grad_norm": 5.7726216316223145, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.3302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006837217252578201, | |
| "grad_norm": 7.50958776473999, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006837217252578201, | |
| "eval_loss": 2.249419927597046, | |
| "eval_runtime": 201.4827, | |
| "eval_samples_per_second": 9.172, | |
| "eval_steps_per_second": 4.586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007976753461341234, | |
| "grad_norm": 11.158656120300293, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.8912, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009116289670104267, | |
| "grad_norm": 15.474498748779297, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.798, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009116289670104267, | |
| "eval_loss": 2.1602330207824707, | |
| "eval_runtime": 201.7772, | |
| "eval_samples_per_second": 9.159, | |
| "eval_steps_per_second": 4.579, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010255825878867302, | |
| "grad_norm": 10.319501876831055, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.617, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011395362087630334, | |
| "grad_norm": 9.459415435791016, | |
| "learning_rate": 0.0, | |
| "loss": 8.4121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011395362087630334, | |
| "eval_loss": 2.1242289543151855, | |
| "eval_runtime": 201.5471, | |
| "eval_samples_per_second": 9.169, | |
| "eval_steps_per_second": 4.585, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3276473628557312e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |