| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006846970215679562, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022823234052265205, | |
| "eval_loss": 2.2855961322784424, | |
| "eval_runtime": 257.8182, | |
| "eval_samples_per_second": 7.156, | |
| "eval_steps_per_second": 3.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006846970215679561, | |
| "grad_norm": 0.9269846081733704, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013693940431359123, | |
| "grad_norm": 0.9510827660560608, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018258587241812164, | |
| "eval_loss": 2.153048276901245, | |
| "eval_runtime": 258.3426, | |
| "eval_samples_per_second": 7.142, | |
| "eval_steps_per_second": 3.573, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020540910647038686, | |
| "grad_norm": 0.6708703637123108, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2041, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027387880862718246, | |
| "grad_norm": 1.3607641458511353, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.2227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003423485107839781, | |
| "grad_norm": 0.737883448600769, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.1457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036517174483624328, | |
| "eval_loss": 2.0498392581939697, | |
| "eval_runtime": 258.2323, | |
| "eval_samples_per_second": 7.145, | |
| "eval_steps_per_second": 3.574, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004108182129407737, | |
| "grad_norm": 0.6803624033927917, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0524, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004792879150975694, | |
| "grad_norm": 0.5455082058906555, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.0345, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005477576172543649, | |
| "grad_norm": 1.0996414422988892, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.0625, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005477576172543649, | |
| "eval_loss": 2.0255534648895264, | |
| "eval_runtime": 258.4482, | |
| "eval_samples_per_second": 7.139, | |
| "eval_steps_per_second": 3.571, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0061622731941116055, | |
| "grad_norm": 0.6625553965568542, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0498, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006846970215679562, | |
| "grad_norm": 0.5361489057540894, | |
| "learning_rate": 0.0, | |
| "loss": 2.124, | |
| "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": 1.2148404268302336e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |