| { | |
| "best_metric": 0.8432615399360657, | |
| "best_model_checkpoint": "Llama-3.2-1B-sportsqa-V1/checkpoint-150", | |
| "epoch": 6.511041009463723, | |
| "eval_steps": 10, | |
| "global_step": 170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3785488958990536, | |
| "grad_norm": 0.9724205136299133, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4368, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3785488958990536, | |
| "eval_loss": 1.348753809928894, | |
| "eval_runtime": 6.5589, | |
| "eval_samples_per_second": 85.838, | |
| "eval_steps_per_second": 10.825, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "grad_norm": 0.5118973255157471, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2118, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7570977917981072, | |
| "eval_loss": 1.1572917699813843, | |
| "eval_runtime": 6.43, | |
| "eval_samples_per_second": 87.558, | |
| "eval_steps_per_second": 11.042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1482649842271293, | |
| "grad_norm": 0.41862204670906067, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1684, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1482649842271293, | |
| "eval_loss": 1.0873514413833618, | |
| "eval_runtime": 6.4834, | |
| "eval_samples_per_second": 86.838, | |
| "eval_steps_per_second": 10.951, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.526813880126183, | |
| "grad_norm": 0.42144763469696045, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.526813880126183, | |
| "eval_loss": 1.0390795469284058, | |
| "eval_runtime": 6.4784, | |
| "eval_samples_per_second": 86.904, | |
| "eval_steps_per_second": 10.959, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9053627760252367, | |
| "grad_norm": 0.6625965237617493, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9053627760252367, | |
| "eval_loss": 0.9832194447517395, | |
| "eval_runtime": 6.4575, | |
| "eval_samples_per_second": 87.185, | |
| "eval_steps_per_second": 10.995, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2965299684542586, | |
| "grad_norm": 0.5491335391998291, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9537, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.2965299684542586, | |
| "eval_loss": 0.9610708355903625, | |
| "eval_runtime": 6.4935, | |
| "eval_samples_per_second": 86.702, | |
| "eval_steps_per_second": 10.934, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.6750788643533125, | |
| "grad_norm": 0.6222676038742065, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7753, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.6750788643533125, | |
| "eval_loss": 0.9286745190620422, | |
| "eval_runtime": 6.5271, | |
| "eval_samples_per_second": 86.256, | |
| "eval_steps_per_second": 10.878, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.0662460567823344, | |
| "grad_norm": 0.47406917810440063, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8796, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.0662460567823344, | |
| "eval_loss": 0.9002482891082764, | |
| "eval_runtime": 6.5139, | |
| "eval_samples_per_second": 86.43, | |
| "eval_steps_per_second": 10.9, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.444794952681388, | |
| "grad_norm": 0.54665207862854, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6697, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.444794952681388, | |
| "eval_loss": 0.8929345607757568, | |
| "eval_runtime": 6.349, | |
| "eval_samples_per_second": 88.676, | |
| "eval_steps_per_second": 11.183, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.823343848580442, | |
| "grad_norm": 0.47858959436416626, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7382, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.823343848580442, | |
| "eval_loss": 0.8687711358070374, | |
| "eval_runtime": 6.4617, | |
| "eval_samples_per_second": 87.129, | |
| "eval_steps_per_second": 10.988, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.214511041009464, | |
| "grad_norm": 0.6165306568145752, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6795, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.214511041009464, | |
| "eval_loss": 0.8820136189460754, | |
| "eval_runtime": 6.4456, | |
| "eval_samples_per_second": 87.346, | |
| "eval_steps_per_second": 11.015, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.593059936908517, | |
| "grad_norm": 0.5470077395439148, | |
| "learning_rate": 0.0002, | |
| "loss": 0.646, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.593059936908517, | |
| "eval_loss": 0.8543145060539246, | |
| "eval_runtime": 6.4186, | |
| "eval_samples_per_second": 87.713, | |
| "eval_steps_per_second": 11.062, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.971608832807571, | |
| "grad_norm": 0.5192540287971497, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5972, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.971608832807571, | |
| "eval_loss": 0.8454616069793701, | |
| "eval_runtime": 6.3674, | |
| "eval_samples_per_second": 88.419, | |
| "eval_steps_per_second": 11.151, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.3627760252365935, | |
| "grad_norm": 0.5664217472076416, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6179, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.3627760252365935, | |
| "eval_loss": 0.845314085483551, | |
| "eval_runtime": 6.4608, | |
| "eval_samples_per_second": 87.141, | |
| "eval_steps_per_second": 10.989, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.7413249211356465, | |
| "grad_norm": 0.5141603350639343, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5488, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.7413249211356465, | |
| "eval_loss": 0.8432615399360657, | |
| "eval_runtime": 6.4351, | |
| "eval_samples_per_second": 87.489, | |
| "eval_steps_per_second": 11.033, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.132492113564669, | |
| "grad_norm": 0.4900747835636139, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5574, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.132492113564669, | |
| "eval_loss": 0.8658251166343689, | |
| "eval_runtime": 6.4211, | |
| "eval_samples_per_second": 87.679, | |
| "eval_steps_per_second": 11.057, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.511041009463723, | |
| "grad_norm": 0.5367661118507385, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4778, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.511041009463723, | |
| "eval_loss": 0.8633659482002258, | |
| "eval_runtime": 6.4456, | |
| "eval_samples_per_second": 87.346, | |
| "eval_steps_per_second": 11.015, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.511041009463723, | |
| "step": 170, | |
| "total_flos": 1.5618225878728704e+16, | |
| "train_loss": 0.8142486740561092, | |
| "train_runtime": 890.4577, | |
| "train_samples_per_second": 39.817, | |
| "train_steps_per_second": 0.204 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 182, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5618225878728704e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |