| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007570977917981073, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008412197686645636, | |
| "grad_norm": 15.92228889465332, | |
| "learning_rate": 2e-05, | |
| "loss": 7.8166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008412197686645636, | |
| "eval_loss": 2.1562464237213135, | |
| "eval_runtime": 7.6626, | |
| "eval_samples_per_second": 65.383, | |
| "eval_steps_per_second": 32.757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016824395373291271, | |
| "grad_norm": 10.205143928527832, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5513, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002523659305993691, | |
| "grad_norm": 10.613945007324219, | |
| "learning_rate": 6e-05, | |
| "loss": 5.938, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002523659305993691, | |
| "eval_loss": 2.114485025405884, | |
| "eval_runtime": 7.9261, | |
| "eval_samples_per_second": 63.209, | |
| "eval_steps_per_second": 31.668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033648790746582543, | |
| "grad_norm": 13.422664642333984, | |
| "learning_rate": 8e-05, | |
| "loss": 7.7495, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004206098843322818, | |
| "grad_norm": 16.202129364013672, | |
| "learning_rate": 0.0001, | |
| "loss": 9.2258, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005047318611987382, | |
| "grad_norm": 15.362430572509766, | |
| "learning_rate": 0.00012, | |
| "loss": 8.1297, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005047318611987382, | |
| "eval_loss": 1.5652238130569458, | |
| "eval_runtime": 7.7627, | |
| "eval_samples_per_second": 64.539, | |
| "eval_steps_per_second": 32.334, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005888538380651945, | |
| "grad_norm": 14.385408401489258, | |
| "learning_rate": 0.00014, | |
| "loss": 7.7112, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0067297581493165086, | |
| "grad_norm": 11.384392738342285, | |
| "learning_rate": 0.00016, | |
| "loss": 4.8809, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007570977917981073, | |
| "grad_norm": 9.325665473937988, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1221, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007570977917981073, | |
| "eval_loss": 0.6571796536445618, | |
| "eval_runtime": 7.1751, | |
| "eval_samples_per_second": 69.825, | |
| "eval_steps_per_second": 34.982, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 268715132190720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |