| { | |
| "best_metric": 0.5347398519515991, | |
| "best_model_checkpoint": "saves/Mistral-7B/lora/train_1/checkpoint-120", | |
| "epoch": 0.3500136724090785, | |
| "eval_steps": 40, | |
| "global_step": 320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04375170905113481, | |
| "grad_norm": 0.8040962219238281, | |
| "learning_rate": 0.00014457831325301204, | |
| "loss": 0.9535, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04375170905113481, | |
| "eval_loss": 0.5372358560562134, | |
| "eval_runtime": 232.3992, | |
| "eval_samples_per_second": 20.275, | |
| "eval_steps_per_second": 0.637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "grad_norm": 0.5753062963485718, | |
| "learning_rate": 0.0002891566265060241, | |
| "loss": 0.3461, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "eval_loss": 0.5532671213150024, | |
| "eval_runtime": 232.5653, | |
| "eval_samples_per_second": 20.261, | |
| "eval_steps_per_second": 0.636, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "grad_norm": 0.6130059957504272, | |
| "learning_rate": 0.00029985669589905196, | |
| "loss": 0.3181, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "eval_loss": 0.5347398519515991, | |
| "eval_runtime": 232.5299, | |
| "eval_samples_per_second": 20.264, | |
| "eval_steps_per_second": 0.636, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "grad_norm": 0.4800422787666321, | |
| "learning_rate": 0.0002993796936474492, | |
| "loss": 0.3057, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "eval_loss": 0.5564690828323364, | |
| "eval_runtime": 232.384, | |
| "eval_samples_per_second": 20.277, | |
| "eval_steps_per_second": 0.637, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "grad_norm": 0.38192033767700195, | |
| "learning_rate": 0.00029856911617379416, | |
| "loss": 0.297, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "eval_loss": 0.5358652472496033, | |
| "eval_runtime": 232.6578, | |
| "eval_samples_per_second": 20.253, | |
| "eval_steps_per_second": 0.636, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "grad_norm": 0.42881786823272705, | |
| "learning_rate": 0.00029742677355383513, | |
| "loss": 0.277, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "eval_loss": 0.5426477789878845, | |
| "eval_runtime": 232.3465, | |
| "eval_samples_per_second": 20.28, | |
| "eval_steps_per_second": 0.637, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "grad_norm": 0.4693865180015564, | |
| "learning_rate": 0.0002959552167179149, | |
| "loss": 0.2707, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "eval_loss": 0.5676203370094299, | |
| "eval_runtime": 232.3212, | |
| "eval_samples_per_second": 20.282, | |
| "eval_steps_per_second": 0.637, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "grad_norm": 0.5723518133163452, | |
| "learning_rate": 0.00029415773175456614, | |
| "loss": 0.2563, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "eval_loss": 0.566847562789917, | |
| "eval_runtime": 232.4745, | |
| "eval_samples_per_second": 20.269, | |
| "eval_steps_per_second": 0.637, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "step": 320, | |
| "total_flos": 6.133543194454917e+17, | |
| "train_loss": 0.37804515957832335, | |
| "train_runtime": 17123.6385, | |
| "train_samples_per_second": 41.003, | |
| "train_steps_per_second": 0.16 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 2742, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.133543194454917e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |