| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.039473684210526314, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013157894736842105, | |
| "eval_loss": 1.5495436191558838, | |
| "eval_runtime": 63.8211, | |
| "eval_samples_per_second": 5.014, | |
| "eval_steps_per_second": 2.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003947368421052632, | |
| "grad_norm": 1.9250959157943726, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007894736842105263, | |
| "grad_norm": 1.0903421640396118, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3339, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 1.0197498798370361, | |
| "eval_runtime": 64.8541, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 2.467, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011842105263157895, | |
| "grad_norm": 6.691552639007568, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0887, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 1.075379490852356, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9955, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019736842105263157, | |
| "grad_norm": 0.5253409147262573, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.8857, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "eval_loss": 0.7232463955879211, | |
| "eval_runtime": 64.953, | |
| "eval_samples_per_second": 4.927, | |
| "eval_steps_per_second": 2.463, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02368421052631579, | |
| "grad_norm": 0.4655627906322479, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6926, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02763157894736842, | |
| "grad_norm": 0.5387355089187622, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.7123, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "grad_norm": 0.4633444845676422, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.665, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "eval_loss": 0.6380881071090698, | |
| "eval_runtime": 64.9842, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 2.462, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.035526315789473684, | |
| "grad_norm": 0.4371694326400757, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.6613, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 0.4477348327636719, | |
| "learning_rate": 0.0, | |
| "loss": 0.6617, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.235418813038592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |