| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.998769987699877, | |
| "eval_steps": 500, | |
| "global_step": 6500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15375153751537515, | |
| "grad_norm": 1.2622125148773193, | |
| "learning_rate": 1.8471709717097174e-05, | |
| "loss": 0.909, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3075030750307503, | |
| "grad_norm": 0.7884178161621094, | |
| "learning_rate": 1.693419434194342e-05, | |
| "loss": 0.2141, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4612546125461255, | |
| "grad_norm": 0.774986743927002, | |
| "learning_rate": 1.5396678966789668e-05, | |
| "loss": 0.1649, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6150061500615006, | |
| "grad_norm": 0.8079761266708374, | |
| "learning_rate": 1.3859163591635918e-05, | |
| "loss": 0.144, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7687576875768758, | |
| "grad_norm": 0.4618232846260071, | |
| "learning_rate": 1.2321648216482165e-05, | |
| "loss": 0.1384, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.922509225092251, | |
| "grad_norm": 0.5913366675376892, | |
| "learning_rate": 1.0784132841328414e-05, | |
| "loss": 0.1315, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 62.5775, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.10974862426519394, | |
| "eval_runtime": 129.6407, | |
| "eval_samples_per_second": 100.331, | |
| "eval_steps_per_second": 6.271, | |
| "step": 3252 | |
| }, | |
| { | |
| "epoch": 1.0762607626076262, | |
| "grad_norm": 0.4670741558074951, | |
| "learning_rate": 9.246617466174663e-06, | |
| "loss": 0.126, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2300123001230012, | |
| "grad_norm": 0.44761019945144653, | |
| "learning_rate": 7.709102091020911e-06, | |
| "loss": 0.1264, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.3837638376383765, | |
| "grad_norm": 0.4738340675830841, | |
| "learning_rate": 6.171586715867159e-06, | |
| "loss": 0.124, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.5375153751537516, | |
| "grad_norm": 0.7554705739021301, | |
| "learning_rate": 4.634071340713408e-06, | |
| "loss": 0.1221, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.6912669126691267, | |
| "grad_norm": 0.39538097381591797, | |
| "learning_rate": 3.0965559655596562e-06, | |
| "loss": 0.1238, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.8450184501845017, | |
| "grad_norm": 0.5276034474372864, | |
| "learning_rate": 1.5621156211562116e-06, | |
| "loss": 0.1208, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.998769987699877, | |
| "grad_norm": 0.4468577802181244, | |
| "learning_rate": 2.4600246002460026e-08, | |
| "loss": 0.1227, | |
| "step": 6500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6504, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3518616154669056.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |