| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09250693802035152, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "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": 14.6466, | |
| "eval_samples_per_second": 15.567, | |
| "eval_steps_per_second": 7.783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009250693802035153, | |
| "grad_norm": 3.147674798965454, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5633, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "grad_norm": 4.135693550109863, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0784, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "eval_loss": 2.5756938457489014, | |
| "eval_runtime": 14.7893, | |
| "eval_samples_per_second": 15.417, | |
| "eval_steps_per_second": 7.708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027752081406105456, | |
| "grad_norm": 2.7247848510742188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1231, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03700277520814061, | |
| "grad_norm": 2.6493232250213623, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6803, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03700277520814061, | |
| "eval_loss": 1.6247913837432861, | |
| "eval_runtime": 14.9738, | |
| "eval_samples_per_second": 15.227, | |
| "eval_steps_per_second": 7.613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04625346901017576, | |
| "grad_norm": 2.0250251293182373, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6013, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05550416281221091, | |
| "grad_norm": 2.2003724575042725, | |
| "learning_rate": 5e-05, | |
| "loss": 1.415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05550416281221091, | |
| "eval_loss": 1.2630630731582642, | |
| "eval_runtime": 15.013, | |
| "eval_samples_per_second": 15.187, | |
| "eval_steps_per_second": 7.593, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06475485661424607, | |
| "grad_norm": 2.0022053718566895, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0455, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07400555041628122, | |
| "grad_norm": 2.3407399654388428, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07400555041628122, | |
| "eval_loss": 1.1422836780548096, | |
| "eval_runtime": 15.0272, | |
| "eval_samples_per_second": 15.172, | |
| "eval_steps_per_second": 7.586, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08325624421831637, | |
| "grad_norm": 1.9095128774642944, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0084, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09250693802035152, | |
| "grad_norm": 2.2135424613952637, | |
| "learning_rate": 0.0, | |
| "loss": 1.2982, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09250693802035152, | |
| "eval_loss": 1.123547077178955, | |
| "eval_runtime": 14.9935, | |
| "eval_samples_per_second": 15.207, | |
| "eval_steps_per_second": 7.603, | |
| "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": 8200486649856000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |