| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006290495061961376, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012580990123922753, | |
| "eval_loss": 1.046350121498108, | |
| "eval_runtime": 460.9411, | |
| "eval_samples_per_second": 7.261, | |
| "eval_steps_per_second": 3.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006290495061961376, | |
| "grad_norm": 3.190112829208374, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012580990123922753, | |
| "grad_norm": 0.6102684140205383, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012580990123922753, | |
| "eval_loss": 1.001396894454956, | |
| "eval_runtime": 474.1232, | |
| "eval_samples_per_second": 7.059, | |
| "eval_steps_per_second": 3.531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018871485185884128, | |
| "grad_norm": 0.7861143350601196, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8466, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025161980247845506, | |
| "grad_norm": 0.4665175974369049, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7658, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025161980247845506, | |
| "eval_loss": 0.8983107805252075, | |
| "eval_runtime": 473.2366, | |
| "eval_samples_per_second": 7.073, | |
| "eval_steps_per_second": 3.537, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003145247530980688, | |
| "grad_norm": 0.6117036938667297, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0037742970371768257, | |
| "grad_norm": 0.7812676429748535, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037742970371768257, | |
| "eval_loss": 0.8442201018333435, | |
| "eval_runtime": 472.7127, | |
| "eval_samples_per_second": 7.08, | |
| "eval_steps_per_second": 3.541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004403346543372964, | |
| "grad_norm": 0.5659365653991699, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6455, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005032396049569101, | |
| "grad_norm": 0.5611511468887329, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7392, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005032396049569101, | |
| "eval_loss": 0.818490207195282, | |
| "eval_runtime": 472.2539, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 3.545, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005661445555765239, | |
| "grad_norm": 0.5884243249893188, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7173, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006290495061961376, | |
| "grad_norm": 0.6214433312416077, | |
| "learning_rate": 0.0, | |
| "loss": 0.8757, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006290495061961376, | |
| "eval_loss": 0.8147611021995544, | |
| "eval_runtime": 472.5027, | |
| "eval_samples_per_second": 7.084, | |
| "eval_steps_per_second": 3.543, | |
| "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": 1.3917970967298048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |