| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007106057914372002, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002368685971457334, | |
| "eval_loss": 3.4545469284057617, | |
| "eval_runtime": 151.9754, | |
| "eval_samples_per_second": 11.699, | |
| "eval_steps_per_second": 5.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007106057914372002, | |
| "grad_norm": 2.541372060775757, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4071, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001184342985728667, | |
| "eval_loss": 3.3429229259490967, | |
| "eval_runtime": 152.92, | |
| "eval_samples_per_second": 11.627, | |
| "eval_steps_per_second": 5.813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014212115828744004, | |
| "grad_norm": 2.6924803256988525, | |
| "learning_rate": 8e-05, | |
| "loss": 3.2775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021318173743116006, | |
| "grad_norm": 3.636328935623169, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9305, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002368685971457334, | |
| "eval_loss": 2.5160555839538574, | |
| "eval_runtime": 152.8536, | |
| "eval_samples_per_second": 11.632, | |
| "eval_steps_per_second": 5.816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028424231657488007, | |
| "grad_norm": 2.70186185836792, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5495, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003553028957186001, | |
| "grad_norm": 3.717397928237915, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1051, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003553028957186001, | |
| "eval_loss": 1.9074734449386597, | |
| "eval_runtime": 152.8264, | |
| "eval_samples_per_second": 11.634, | |
| "eval_steps_per_second": 5.817, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004263634748623201, | |
| "grad_norm": 3.084251880645752, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.4886, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004737371942914668, | |
| "eval_loss": 1.5163520574569702, | |
| "eval_runtime": 152.8342, | |
| "eval_samples_per_second": 11.634, | |
| "eval_steps_per_second": 5.817, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004974240540060401, | |
| "grad_norm": 2.9578020572662354, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5724, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005684846331497601, | |
| "grad_norm": 2.541783094406128, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.3204, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005921714928643335, | |
| "eval_loss": 1.361017107963562, | |
| "eval_runtime": 152.84, | |
| "eval_samples_per_second": 11.633, | |
| "eval_steps_per_second": 5.817, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006395452122934802, | |
| "grad_norm": 2.4790844917297363, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.3091, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007106057914372002, | |
| "grad_norm": 2.3881053924560547, | |
| "learning_rate": 0.0, | |
| "loss": 1.448, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007106057914372002, | |
| "eval_loss": 1.3135907649993896, | |
| "eval_runtime": 152.8429, | |
| "eval_samples_per_second": 11.633, | |
| "eval_steps_per_second": 5.816, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |