| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07215541165587419, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "eval_loss": 3.789647102355957, | |
| "eval_runtime": 14.8344, | |
| "eval_samples_per_second": 15.37, | |
| "eval_steps_per_second": 7.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009250693802035153, | |
| "grad_norm": 3.0337514877319336, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "grad_norm": 4.058107852935791, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "eval_loss": 2.5827155113220215, | |
| "eval_runtime": 15.0123, | |
| "eval_samples_per_second": 15.188, | |
| "eval_steps_per_second": 7.594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027752081406105456, | |
| "grad_norm": 2.6269290447235107, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03700277520814061, | |
| "grad_norm": 2.55375075340271, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6842, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03700277520814061, | |
| "eval_loss": 1.6327600479125977, | |
| "eval_runtime": 15.1801, | |
| "eval_samples_per_second": 15.02, | |
| "eval_steps_per_second": 7.51, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04625346901017576, | |
| "grad_norm": 1.9848346710205078, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6157, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05550416281221091, | |
| "grad_norm": 2.131385326385498, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4348, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05550416281221091, | |
| "eval_loss": 1.2888398170471191, | |
| "eval_runtime": 15.2538, | |
| "eval_samples_per_second": 14.947, | |
| "eval_steps_per_second": 7.474, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06475485661424607, | |
| "grad_norm": 1.6838656663894653, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0601, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6396379586887680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |