| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023798191337458353, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "eval_loss": 3.89152193069458, | |
| "eval_runtime": 22.7832, | |
| "eval_samples_per_second": 38.844, | |
| "eval_steps_per_second": 19.444, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002379819133745835, | |
| "grad_norm": 2.0327930450439453, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00475963826749167, | |
| "grad_norm": 2.0710887908935547, | |
| "learning_rate": 0.0001, | |
| "loss": 3.735, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00475963826749167, | |
| "eval_loss": 3.669828176498413, | |
| "eval_runtime": 22.6353, | |
| "eval_samples_per_second": 39.098, | |
| "eval_steps_per_second": 19.571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007139457401237506, | |
| "grad_norm": 2.214755058288574, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00951927653498334, | |
| "grad_norm": 2.7612407207489014, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00951927653498334, | |
| "eval_loss": 3.165354013442993, | |
| "eval_runtime": 22.7252, | |
| "eval_samples_per_second": 38.944, | |
| "eval_steps_per_second": 19.494, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011899095668729176, | |
| "grad_norm": 2.89294171333313, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1063, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014278914802475012, | |
| "grad_norm": 2.7005653381347656, | |
| "learning_rate": 5e-05, | |
| "loss": 2.879, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014278914802475012, | |
| "eval_loss": 2.9647376537323, | |
| "eval_runtime": 22.4659, | |
| "eval_samples_per_second": 39.393, | |
| "eval_steps_per_second": 19.719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016658733936220846, | |
| "grad_norm": 2.840834140777588, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.9493, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01903855306996668, | |
| "grad_norm": 3.0013303756713867, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.946, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01903855306996668, | |
| "eval_loss": 2.8999171257019043, | |
| "eval_runtime": 23.0559, | |
| "eval_samples_per_second": 38.385, | |
| "eval_steps_per_second": 19.214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021418372203712517, | |
| "grad_norm": 2.9253106117248535, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8646, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.023798191337458353, | |
| "grad_norm": 2.795085906982422, | |
| "learning_rate": 0.0, | |
| "loss": 2.7996, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023798191337458353, | |
| "eval_loss": 2.8892688751220703, | |
| "eval_runtime": 22.4508, | |
| "eval_samples_per_second": 39.42, | |
| "eval_steps_per_second": 19.732, | |
| "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": 1202727577190400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |