| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013364517206815904, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013364517206815904, | |
| "grad_norm": 0.23083138465881348, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013364517206815904, | |
| "eval_loss": 10.839484214782715, | |
| "eval_runtime": 2.1213, | |
| "eval_samples_per_second": 148.493, | |
| "eval_steps_per_second": 74.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026729034413631807, | |
| "grad_norm": 0.20339778065681458, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8211, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "grad_norm": 0.17665569484233856, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "eval_loss": 10.839208602905273, | |
| "eval_runtime": 1.0728, | |
| "eval_samples_per_second": 293.616, | |
| "eval_steps_per_second": 147.274, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0053458068827263614, | |
| "grad_norm": 0.19935546815395355, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006682258603407952, | |
| "grad_norm": 0.21560607850551605, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "grad_norm": 0.15446893870830536, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8431, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "eval_loss": 10.837102890014648, | |
| "eval_runtime": 1.1122, | |
| "eval_samples_per_second": 283.219, | |
| "eval_steps_per_second": 142.059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009355162044771133, | |
| "grad_norm": 0.21033413708209991, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8401, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010691613765452723, | |
| "grad_norm": 0.18256831169128418, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8356, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "grad_norm": 0.1905270516872406, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8213, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "eval_loss": 10.833669662475586, | |
| "eval_runtime": 1.1475, | |
| "eval_samples_per_second": 274.511, | |
| "eval_steps_per_second": 137.691, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013364517206815904, | |
| "grad_norm": 0.20988529920578003, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8365, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1620084129792.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |