| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009422850412249705, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001884570082449941, | |
| "eval_loss": 1.5112230777740479, | |
| "eval_runtime": 182.542, | |
| "eval_samples_per_second": 12.244, | |
| "eval_steps_per_second": 6.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009422850412249705, | |
| "grad_norm": 1.75139319896698, | |
| "learning_rate": 5e-05, | |
| "loss": 6.2235, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001884570082449941, | |
| "grad_norm": 2.5495612621307373, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8626, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001884570082449941, | |
| "eval_loss": 1.3714823722839355, | |
| "eval_runtime": 181.8701, | |
| "eval_samples_per_second": 12.289, | |
| "eval_steps_per_second": 6.147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028268551236749115, | |
| "grad_norm": 1.9742214679718018, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.3061, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003769140164899882, | |
| "grad_norm": 2.3247272968292236, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.9027, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003769140164899882, | |
| "eval_loss": 1.1116677522659302, | |
| "eval_runtime": 181.9622, | |
| "eval_samples_per_second": 12.283, | |
| "eval_steps_per_second": 6.144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004711425206124852, | |
| "grad_norm": 2.0242345333099365, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2314, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005653710247349823, | |
| "grad_norm": 2.380277156829834, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0214, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005653710247349823, | |
| "eval_loss": 0.9938903450965881, | |
| "eval_runtime": 183.1215, | |
| "eval_samples_per_second": 12.205, | |
| "eval_steps_per_second": 6.105, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006595995288574794, | |
| "grad_norm": 2.80549693107605, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.1496, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007538280329799764, | |
| "grad_norm": 2.438131332397461, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.7781, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007538280329799764, | |
| "eval_loss": 0.9509055614471436, | |
| "eval_runtime": 182.1245, | |
| "eval_samples_per_second": 12.272, | |
| "eval_steps_per_second": 6.139, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008480565371024734, | |
| "grad_norm": 2.420114755630493, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.8176, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009422850412249705, | |
| "grad_norm": 2.2501401901245117, | |
| "learning_rate": 0.0, | |
| "loss": 3.541, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009422850412249705, | |
| "eval_loss": 0.9434703588485718, | |
| "eval_runtime": 182.0373, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 6.142, | |
| "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": 1.4264026791936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |