| { | |
| "best_metric": 0.47758275270462036, | |
| "best_model_checkpoint": "Phi-3.5-mini-instruct_text_to_sql_lora\\checkpoint-500", | |
| "epoch": 0.7451564828614009, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07451564828614009, | |
| "grad_norm": 0.09373754262924194, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07451564828614009, | |
| "eval_loss": 0.5543281435966492, | |
| "eval_runtime": 19.9013, | |
| "eval_samples_per_second": 6.231, | |
| "eval_steps_per_second": 0.804, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.04845063388347626, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 0.5243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "eval_loss": 0.5150236487388611, | |
| "eval_runtime": 19.8752, | |
| "eval_samples_per_second": 6.239, | |
| "eval_steps_per_second": 0.805, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "grad_norm": 0.06224009767174721, | |
| "learning_rate": 0.00019872208493487546, | |
| "loss": 0.5046, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "eval_loss": 0.504132091999054, | |
| "eval_runtime": 19.8753, | |
| "eval_samples_per_second": 6.239, | |
| "eval_steps_per_second": 0.805, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.053420498967170715, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 0.4989, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "eval_loss": 0.49748167395591736, | |
| "eval_runtime": 19.873, | |
| "eval_samples_per_second": 6.24, | |
| "eval_steps_per_second": 0.805, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "grad_norm": 0.04381432756781578, | |
| "learning_rate": 0.0001949210010777752, | |
| "loss": 0.4873, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "eval_loss": 0.4926624298095703, | |
| "eval_runtime": 19.9753, | |
| "eval_samples_per_second": 6.208, | |
| "eval_steps_per_second": 0.801, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.05697334185242653, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.4854, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "eval_loss": 0.48829007148742676, | |
| "eval_runtime": 19.8877, | |
| "eval_samples_per_second": 6.235, | |
| "eval_steps_per_second": 0.805, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "grad_norm": 0.07128433138132095, | |
| "learning_rate": 0.0001886938976751951, | |
| "loss": 0.4788, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "eval_loss": 0.48432213068008423, | |
| "eval_runtime": 19.8588, | |
| "eval_samples_per_second": 6.244, | |
| "eval_steps_per_second": 0.806, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.049252185970544815, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.4811, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "eval_loss": 0.4807914197444916, | |
| "eval_runtime": 19.8677, | |
| "eval_samples_per_second": 6.241, | |
| "eval_steps_per_second": 0.805, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "grad_norm": 0.05810828506946564, | |
| "learning_rate": 0.00018019992891214008, | |
| "loss": 0.4796, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "eval_loss": 0.478938490152359, | |
| "eval_runtime": 19.8654, | |
| "eval_samples_per_second": 6.242, | |
| "eval_steps_per_second": 0.805, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.06429937481880188, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.4738, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "eval_loss": 0.47758275270462036, | |
| "eval_runtime": 19.8891, | |
| "eval_samples_per_second": 6.235, | |
| "eval_steps_per_second": 0.804, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2013, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.86675351257088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |