| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8671957054498773, | |
| "eval_steps": 250, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 1.2788289785385132, | |
| "learning_rate": 9.992757124875143e-05, | |
| "loss": 0.3573, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.18718622624874115, | |
| "eval_runtime": 18.4863, | |
| "eval_samples_per_second": 4.706, | |
| "eval_steps_per_second": 4.706, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 1.7301123142242432, | |
| "learning_rate": 9.895259863857224e-05, | |
| "loss": 0.1155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.11222057044506073, | |
| "eval_runtime": 18.4689, | |
| "eval_samples_per_second": 4.711, | |
| "eval_steps_per_second": 4.711, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 0.40849488973617554, | |
| "learning_rate": 9.686044398977847e-05, | |
| "loss": 0.079, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.0827888771891594, | |
| "eval_runtime": 18.4255, | |
| "eval_samples_per_second": 4.722, | |
| "eval_steps_per_second": 4.722, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 0.27379560470581055, | |
| "learning_rate": 9.369885385026829e-05, | |
| "loss": 0.0672, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.07405883818864822, | |
| "eval_runtime": 18.0866, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 4.81, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1669973159061735, | |
| "grad_norm": 0.15424582362174988, | |
| "learning_rate": 8.953998111520053e-05, | |
| "loss": 0.0555, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.1669973159061735, | |
| "eval_loss": 0.07201890647411346, | |
| "eval_runtime": 18.1777, | |
| "eval_samples_per_second": 4.786, | |
| "eval_steps_per_second": 4.786, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.4003967790874081, | |
| "grad_norm": 0.1671038419008255, | |
| "learning_rate": 8.447873837450339e-05, | |
| "loss": 0.055, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4003967790874081, | |
| "eval_loss": 0.07005530595779419, | |
| "eval_runtime": 18.0977, | |
| "eval_samples_per_second": 4.807, | |
| "eval_steps_per_second": 4.807, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.6337962422686427, | |
| "grad_norm": 0.12481052428483963, | |
| "learning_rate": 7.863063184521596e-05, | |
| "loss": 0.053, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.6337962422686427, | |
| "eval_loss": 0.06806331127882004, | |
| "eval_runtime": 18.1718, | |
| "eval_samples_per_second": 4.788, | |
| "eval_steps_per_second": 4.788, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.8671957054498773, | |
| "grad_norm": 0.14744804799556732, | |
| "learning_rate": 7.212912532203201e-05, | |
| "loss": 0.0526, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8671957054498773, | |
| "eval_loss": 0.06636130809783936, | |
| "eval_runtime": 18.0865, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 4.81, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 5355, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.255216151731814e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |