| { | |
| "best_metric": 0.8349647521972656, | |
| "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-240", | |
| "epoch": 0.4812687995624829, | |
| "eval_steps": 40, | |
| "global_step": 440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04375170905113481, | |
| "grad_norm": 0.8457286357879639, | |
| "learning_rate": 0.00014457831325301204, | |
| "loss": 1.211, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04375170905113481, | |
| "eval_loss": 0.8552733659744263, | |
| "eval_runtime": 212.5084, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 0.696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "grad_norm": 0.5710806846618652, | |
| "learning_rate": 0.0002891566265060241, | |
| "loss": 0.4676, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08750341810226962, | |
| "eval_loss": 0.8505380153656006, | |
| "eval_runtime": 212.6707, | |
| "eval_samples_per_second": 22.156, | |
| "eval_steps_per_second": 0.696, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "grad_norm": 0.5647861361503601, | |
| "learning_rate": 0.00029985669589905196, | |
| "loss": 0.4316, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13125512715340443, | |
| "eval_loss": 0.8580976128578186, | |
| "eval_runtime": 212.4255, | |
| "eval_samples_per_second": 22.182, | |
| "eval_steps_per_second": 0.697, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "grad_norm": 0.36067792773246765, | |
| "learning_rate": 0.0002993796936474492, | |
| "loss": 0.4109, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17500683620453925, | |
| "eval_loss": 0.8414877653121948, | |
| "eval_runtime": 212.0889, | |
| "eval_samples_per_second": 22.217, | |
| "eval_steps_per_second": 0.698, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "grad_norm": 0.30857041478157043, | |
| "learning_rate": 0.00029856911617379416, | |
| "loss": 0.4033, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "eval_loss": 0.8380470275878906, | |
| "eval_runtime": 212.6628, | |
| "eval_samples_per_second": 22.157, | |
| "eval_steps_per_second": 0.696, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "grad_norm": 0.37047892808914185, | |
| "learning_rate": 0.00029742677355383513, | |
| "loss": 0.3781, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26251025430680885, | |
| "eval_loss": 0.8349647521972656, | |
| "eval_runtime": 212.5015, | |
| "eval_samples_per_second": 22.174, | |
| "eval_steps_per_second": 0.696, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "grad_norm": 0.4294930100440979, | |
| "learning_rate": 0.0002959552167179149, | |
| "loss": 0.3722, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.30626196335794365, | |
| "eval_loss": 0.8508928418159485, | |
| "eval_runtime": 212.9223, | |
| "eval_samples_per_second": 22.13, | |
| "eval_steps_per_second": 0.695, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "grad_norm": 0.39482536911964417, | |
| "learning_rate": 0.00029415773175456614, | |
| "loss": 0.3594, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3500136724090785, | |
| "eval_loss": 0.9025893211364746, | |
| "eval_runtime": 212.0864, | |
| "eval_samples_per_second": 22.217, | |
| "eval_steps_per_second": 0.698, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3937653814602133, | |
| "grad_norm": 0.8047598600387573, | |
| "learning_rate": 0.0002920383325724476, | |
| "loss": 0.357, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3937653814602133, | |
| "eval_loss": 0.9121100902557373, | |
| "eval_runtime": 212.3738, | |
| "eval_samples_per_second": 22.187, | |
| "eval_steps_per_second": 0.697, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "grad_norm": 0.4813142418861389, | |
| "learning_rate": 0.0002896017519370078, | |
| "loss": 0.3297, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "eval_loss": 0.8974694013595581, | |
| "eval_runtime": 212.4785, | |
| "eval_samples_per_second": 22.176, | |
| "eval_steps_per_second": 0.697, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4812687995624829, | |
| "grad_norm": 0.62039715051651, | |
| "learning_rate": 0.000286853430901891, | |
| "loss": 0.3243, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4812687995624829, | |
| "eval_loss": 0.9863638877868652, | |
| "eval_runtime": 212.4156, | |
| "eval_samples_per_second": 22.183, | |
| "eval_steps_per_second": 0.697, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4812687995624829, | |
| "step": 440, | |
| "total_flos": 7.823309976360714e+17, | |
| "train_loss": 0.4586519674821333, | |
| "train_runtime": 21284.6342, | |
| "train_samples_per_second": 32.987, | |
| "train_steps_per_second": 0.129 | |
| } | |
| ], | |
| "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": 7.823309976360714e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |