| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00947193937958797, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "eval_loss": 2.0692930221557617, | |
| "eval_runtime": 245.433, | |
| "eval_samples_per_second": 5.435, | |
| "eval_steps_per_second": 2.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000947193937958797, | |
| "grad_norm": 1.692325234413147, | |
| "learning_rate": 6e-05, | |
| "loss": 7.9621, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015786565632646618, | |
| "eval_loss": 2.026681900024414, | |
| "eval_runtime": 247.2335, | |
| "eval_samples_per_second": 5.396, | |
| "eval_steps_per_second": 2.698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001894387875917594, | |
| "grad_norm": 2.0406484603881836, | |
| "learning_rate": 0.00012, | |
| "loss": 7.7044, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028415818138763913, | |
| "grad_norm": 2.049513101577759, | |
| "learning_rate": 0.00018, | |
| "loss": 7.7549, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031573131265293236, | |
| "eval_loss": 1.6765570640563965, | |
| "eval_runtime": 247.086, | |
| "eval_samples_per_second": 5.399, | |
| "eval_steps_per_second": 2.699, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003788775751835188, | |
| "grad_norm": 1.6175545454025269, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.7124, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004735969689793985, | |
| "grad_norm": 2.217756986618042, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.0008, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004735969689793985, | |
| "eval_loss": 1.4084513187408447, | |
| "eval_runtime": 247.059, | |
| "eval_samples_per_second": 5.4, | |
| "eval_steps_per_second": 2.7, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005683163627752783, | |
| "grad_norm": 2.475426435470581, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.6367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006314626253058647, | |
| "eval_loss": 1.2930963039398193, | |
| "eval_runtime": 246.796, | |
| "eval_samples_per_second": 5.405, | |
| "eval_steps_per_second": 2.703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006630357565711579, | |
| "grad_norm": 2.1834053993225098, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 5.4897, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007577551503670376, | |
| "grad_norm": 2.090245246887207, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 4.7943, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007893282816323309, | |
| "eval_loss": 1.2484618425369263, | |
| "eval_runtime": 247.1722, | |
| "eval_samples_per_second": 5.397, | |
| "eval_steps_per_second": 2.699, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008524745441629173, | |
| "grad_norm": 2.3083226680755615, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 4.8183, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00947193937958797, | |
| "grad_norm": 2.6077980995178223, | |
| "learning_rate": 0.0, | |
| "loss": 5.0171, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00947193937958797, | |
| "eval_loss": 1.2385700941085815, | |
| "eval_runtime": 247.1144, | |
| "eval_samples_per_second": 5.398, | |
| "eval_steps_per_second": 2.699, | |
| "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": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |