| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029266294009189617, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.8532588018379236e-05, | |
| "eval_loss": 3.375028133392334, | |
| "eval_runtime": 782.6628, | |
| "eval_samples_per_second": 9.192, | |
| "eval_steps_per_second": 4.596, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029266294009189616, | |
| "grad_norm": 2.181471109390259, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005853258801837923, | |
| "grad_norm": 2.263486385345459, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005853258801837923, | |
| "eval_loss": 2.706347703933716, | |
| "eval_runtime": 787.5742, | |
| "eval_samples_per_second": 9.134, | |
| "eval_steps_per_second": 4.567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008779888202756885, | |
| "grad_norm": 2.132351875305176, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6323, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011706517603675846, | |
| "grad_norm": 1.5535396337509155, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011706517603675846, | |
| "eval_loss": 2.518202066421509, | |
| "eval_runtime": 784.5501, | |
| "eval_samples_per_second": 9.17, | |
| "eval_steps_per_second": 4.585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014633147004594808, | |
| "grad_norm": 1.7690931558609009, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5346, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001755977640551377, | |
| "grad_norm": 1.654198169708252, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001755977640551377, | |
| "eval_loss": 2.451936721801758, | |
| "eval_runtime": 782.4367, | |
| "eval_samples_per_second": 9.194, | |
| "eval_steps_per_second": 4.597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002048640580643273, | |
| "grad_norm": 1.418197751045227, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3071, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0023413035207351693, | |
| "grad_norm": 1.4352751970291138, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023413035207351693, | |
| "eval_loss": 2.4152517318725586, | |
| "eval_runtime": 784.6728, | |
| "eval_samples_per_second": 9.168, | |
| "eval_steps_per_second": 4.584, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026339664608270655, | |
| "grad_norm": 1.5534476041793823, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.406, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0029266294009189617, | |
| "grad_norm": 1.7215681076049805, | |
| "learning_rate": 0.0, | |
| "loss": 2.4092, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029266294009189617, | |
| "eval_loss": 2.4109411239624023, | |
| "eval_runtime": 789.4098, | |
| "eval_samples_per_second": 9.113, | |
| "eval_steps_per_second": 4.557, | |
| "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": 1.261320334737408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |