| { |
| "best_global_step": 350, |
| "best_metric": 0.4290083050727844, |
| "best_model_checkpoint": "./SFT-Bakti-8B-Base-MultiTurn-Chatbot/checkpoint-350", |
| "epoch": 0.8009153318077803, |
| "eval_steps": 50, |
| "global_step": 350, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.057208237986270026, |
| "grad_norm": 1.0668201446533203, |
| "learning_rate": 1.0909090909090909e-05, |
| "loss": 1.218, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.11441647597254005, |
| "grad_norm": 0.31702354550361633, |
| "learning_rate": 1.987951807228916e-05, |
| "loss": 0.9375, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.11441647597254005, |
| "eval_loss": 0.7834538817405701, |
| "eval_runtime": 142.9037, |
| "eval_samples_per_second": 10.874, |
| "eval_steps_per_second": 1.365, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.17162471395881007, |
| "grad_norm": 0.2436097115278244, |
| "learning_rate": 1.927710843373494e-05, |
| "loss": 0.6942, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.2288329519450801, |
| "grad_norm": 0.2535153329372406, |
| "learning_rate": 1.8674698795180725e-05, |
| "loss": 0.5775, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2288329519450801, |
| "eval_loss": 0.535061776638031, |
| "eval_runtime": 142.327, |
| "eval_samples_per_second": 10.919, |
| "eval_steps_per_second": 1.37, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28604118993135014, |
| "grad_norm": 0.22549062967300415, |
| "learning_rate": 1.807228915662651e-05, |
| "loss": 0.5213, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.34324942791762014, |
| "grad_norm": 0.253602534532547, |
| "learning_rate": 1.746987951807229e-05, |
| "loss": 0.5074, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.34324942791762014, |
| "eval_loss": 0.4855903685092926, |
| "eval_runtime": 142.6506, |
| "eval_samples_per_second": 10.894, |
| "eval_steps_per_second": 1.367, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.40045766590389015, |
| "grad_norm": 0.2599852979183197, |
| "learning_rate": 1.6867469879518076e-05, |
| "loss": 0.491, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.4576659038901602, |
| "grad_norm": 0.2638922929763794, |
| "learning_rate": 1.6265060240963857e-05, |
| "loss": 0.4755, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4576659038901602, |
| "eval_loss": 0.4620622992515564, |
| "eval_runtime": 142.2944, |
| "eval_samples_per_second": 10.921, |
| "eval_steps_per_second": 1.37, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5148741418764302, |
| "grad_norm": 0.28857553005218506, |
| "learning_rate": 1.566265060240964e-05, |
| "loss": 0.4639, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.5720823798627003, |
| "grad_norm": 0.3098597228527069, |
| "learning_rate": 1.5060240963855424e-05, |
| "loss": 0.4617, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5720823798627003, |
| "eval_loss": 0.44807058572769165, |
| "eval_runtime": 142.2435, |
| "eval_samples_per_second": 10.925, |
| "eval_steps_per_second": 1.371, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6292906178489702, |
| "grad_norm": 0.321586549282074, |
| "learning_rate": 1.4457831325301207e-05, |
| "loss": 0.455, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.6864988558352403, |
| "grad_norm": 0.31933411955833435, |
| "learning_rate": 1.3855421686746989e-05, |
| "loss": 0.4464, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6864988558352403, |
| "eval_loss": 0.43681567907333374, |
| "eval_runtime": 142.6271, |
| "eval_samples_per_second": 10.896, |
| "eval_steps_per_second": 1.367, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7437070938215103, |
| "grad_norm": 0.3048318326473236, |
| "learning_rate": 1.3253012048192772e-05, |
| "loss": 0.4384, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.8009153318077803, |
| "grad_norm": 0.336558073759079, |
| "learning_rate": 1.2650602409638555e-05, |
| "loss": 0.4332, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8009153318077803, |
| "eval_loss": 0.4290083050727844, |
| "eval_runtime": 142.2181, |
| "eval_samples_per_second": 10.927, |
| "eval_steps_per_second": 1.371, |
| "step": 350 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 874, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "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": 5.23806644895744e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
