| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023556293652756675, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.711258730551335e-05, | |
| "eval_loss": 2.255336046218872, | |
| "eval_runtime": 666.5702, | |
| "eval_samples_per_second": 13.409, | |
| "eval_steps_per_second": 6.704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023556293652756677, | |
| "grad_norm": 1.0586025714874268, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1781, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00047112587305513353, | |
| "grad_norm": 1.62703537940979, | |
| "learning_rate": 0.0001, | |
| "loss": 2.082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00047112587305513353, | |
| "eval_loss": 2.0847971439361572, | |
| "eval_runtime": 667.4768, | |
| "eval_samples_per_second": 13.391, | |
| "eval_steps_per_second": 6.695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007066888095827003, | |
| "grad_norm": 1.8582125902175903, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0211, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009422517461102671, | |
| "grad_norm": 1.7657477855682373, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9053, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009422517461102671, | |
| "eval_loss": 1.795223593711853, | |
| "eval_runtime": 667.8705, | |
| "eval_samples_per_second": 13.383, | |
| "eval_steps_per_second": 6.691, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011778146826378337, | |
| "grad_norm": 1.6993805170059204, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014133776191654005, | |
| "grad_norm": 1.39825439453125, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7729, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014133776191654005, | |
| "eval_loss": 1.7357591390609741, | |
| "eval_runtime": 668.5358, | |
| "eval_samples_per_second": 13.37, | |
| "eval_steps_per_second": 6.685, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016489405556929673, | |
| "grad_norm": 1.4528638124465942, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7096, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018845034922205341, | |
| "grad_norm": 1.3227989673614502, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6578, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018845034922205341, | |
| "eval_loss": 1.7218973636627197, | |
| "eval_runtime": 668.1754, | |
| "eval_samples_per_second": 13.377, | |
| "eval_steps_per_second": 6.688, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021200664287481007, | |
| "grad_norm": 1.4656140804290771, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6568, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0023556293652756675, | |
| "grad_norm": 1.2751281261444092, | |
| "learning_rate": 0.0, | |
| "loss": 1.6041, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0023556293652756675, | |
| "eval_loss": 1.7157447338104248, | |
| "eval_runtime": 667.6784, | |
| "eval_samples_per_second": 13.387, | |
| "eval_steps_per_second": 6.693, | |
| "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": 1.0218842471006208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |