| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008128098837681867, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 1.6511867046356201, | |
| "eval_runtime": 74.5602, | |
| "eval_samples_per_second": 34.75, | |
| "eval_steps_per_second": 17.382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 0.17820429801940918, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 0.3048231899738312, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 1.649460792541504, | |
| "eval_runtime": 74.5937, | |
| "eval_samples_per_second": 34.735, | |
| "eval_steps_per_second": 17.374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 0.2008397877216339, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 0.17129330337047577, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6642, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 1.6372413635253906, | |
| "eval_runtime": 74.7542, | |
| "eval_samples_per_second": 34.66, | |
| "eval_steps_per_second": 17.337, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 0.20447033643722534, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5578, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 0.27014607191085815, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "eval_loss": 1.619086503982544, | |
| "eval_runtime": 75.1496, | |
| "eval_samples_per_second": 34.478, | |
| "eval_steps_per_second": 17.246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0056896691863773064, | |
| "grad_norm": 0.23945343494415283, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6408, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006502479070145493, | |
| "grad_norm": 0.21557150781154633, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006502479070145493, | |
| "eval_loss": 1.6094844341278076, | |
| "eval_runtime": 75.0504, | |
| "eval_samples_per_second": 34.523, | |
| "eval_steps_per_second": 17.268, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0073152889539136795, | |
| "grad_norm": 0.25057998299598694, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6054, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "grad_norm": 0.2409868985414505, | |
| "learning_rate": 0.0, | |
| "loss": 1.5964, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "eval_loss": 1.6076915264129639, | |
| "eval_runtime": 74.5511, | |
| "eval_samples_per_second": 34.755, | |
| "eval_steps_per_second": 17.384, | |
| "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": 1624279061889024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |