| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009008603216071348, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0028677386904494e-05, | |
| "eval_loss": 1.0328869819641113, | |
| "eval_runtime": 1647.6581, | |
| "eval_samples_per_second": 8.51, | |
| "eval_steps_per_second": 4.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.008603216071348e-05, | |
| "grad_norm": 0.25066274404525757, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018017206432142696, | |
| "grad_norm": 0.49407339096069336, | |
| "learning_rate": 0.00012, | |
| "loss": 0.955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024022941909523595, | |
| "eval_loss": 0.8399771451950073, | |
| "eval_runtime": 1655.5258, | |
| "eval_samples_per_second": 8.47, | |
| "eval_steps_per_second": 4.235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002702580964821404, | |
| "grad_norm": 0.5673564672470093, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8769, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00036034412864285393, | |
| "grad_norm": 0.27589112520217896, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.7145, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004504301608035674, | |
| "grad_norm": 0.3418157696723938, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6903, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004804588381904719, | |
| "eval_loss": 0.6653794646263123, | |
| "eval_runtime": 1652.2191, | |
| "eval_samples_per_second": 8.487, | |
| "eval_steps_per_second": 4.243, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005405161929642808, | |
| "grad_norm": 0.2595500349998474, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6711, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006306022251249943, | |
| "grad_norm": 0.2987304925918579, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6307, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007206882572857079, | |
| "grad_norm": 0.24557766318321228, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6283, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007206882572857079, | |
| "eval_loss": 0.6251760125160217, | |
| "eval_runtime": 1652.0384, | |
| "eval_samples_per_second": 8.488, | |
| "eval_steps_per_second": 4.244, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008107742894464214, | |
| "grad_norm": 0.21351483464241028, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.6718, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009008603216071348, | |
| "grad_norm": 0.2256997674703598, | |
| "learning_rate": 0.0, | |
| "loss": 0.6141, | |
| "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": 2.47563798183936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |