| { | |
| "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": 0.27257001399993896, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013364517206815904, | |
| "eval_loss": 10.839484214782715, | |
| "eval_runtime": 2.1844, | |
| "eval_samples_per_second": 144.206, | |
| "eval_steps_per_second": 72.332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026729034413631807, | |
| "grad_norm": 0.21410001814365387, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8211, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "grad_norm": 0.21863418817520142, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "eval_loss": 10.83915901184082, | |
| "eval_runtime": 1.0793, | |
| "eval_samples_per_second": 291.852, | |
| "eval_steps_per_second": 146.389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0053458068827263614, | |
| "grad_norm": 0.23596583306789398, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006682258603407952, | |
| "grad_norm": 0.22535307705402374, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "grad_norm": 0.17757120728492737, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "eval_loss": 10.8368558883667, | |
| "eval_runtime": 1.0942, | |
| "eval_samples_per_second": 287.88, | |
| "eval_steps_per_second": 144.397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009355162044771133, | |
| "grad_norm": 0.23544400930404663, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8397, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010691613765452723, | |
| "grad_norm": 0.218731090426445, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "grad_norm": 0.1904142200946808, | |
| "learning_rate": 0.00018, | |
| "loss": 10.821, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "eval_loss": 10.833208084106445, | |
| "eval_runtime": 1.1379, | |
| "eval_samples_per_second": 276.827, | |
| "eval_steps_per_second": 138.853, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013364517206815904, | |
| "grad_norm": 0.22387710213661194, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8361, | |
| "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 | |
| } | |