| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004333850987756871, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001444616995918957, | |
| "eval_loss": 3.8790087699890137, | |
| "eval_runtime": 274.6005, | |
| "eval_samples_per_second": 10.615, | |
| "eval_steps_per_second": 5.31, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004333850987756871, | |
| "grad_norm": 3.4701120853424072, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8051, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008667701975513742, | |
| "grad_norm": 2.1412949562072754, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2291, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011556935967351656, | |
| "eval_loss": 2.4242637157440186, | |
| "eval_runtime": 274.9091, | |
| "eval_samples_per_second": 10.604, | |
| "eval_steps_per_second": 5.304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013001552963270613, | |
| "grad_norm": 1.9423857927322388, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6326, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017335403951027485, | |
| "grad_norm": 2.159100294113159, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1715, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021669254938784356, | |
| "grad_norm": 1.5146921873092651, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002311387193470331, | |
| "eval_loss": 1.8640267848968506, | |
| "eval_runtime": 274.814, | |
| "eval_samples_per_second": 10.607, | |
| "eval_steps_per_second": 5.305, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026003105926541226, | |
| "grad_norm": 1.5231510400772095, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030336956914298096, | |
| "grad_norm": 1.4836976528167725, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.8248, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003467080790205497, | |
| "grad_norm": 1.4981125593185425, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.7242, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003467080790205497, | |
| "eval_loss": 1.7098380327224731, | |
| "eval_runtime": 274.9047, | |
| "eval_samples_per_second": 10.604, | |
| "eval_steps_per_second": 5.304, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003900465888981184, | |
| "grad_norm": 1.5191102027893066, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8248, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004333850987756871, | |
| "grad_norm": 1.53097403049469, | |
| "learning_rate": 0.0, | |
| "loss": 1.7329, | |
| "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 | |
| } | |