| { | |
| "best_global_step": 100, | |
| "best_metric": 0.0855652242898941, | |
| "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-100", | |
| "epoch": 1.0, | |
| "eval_steps": 50, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 4.794777870178223, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 1.382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.3279643058776855, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.137, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 2.1661813259124756, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.5598, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.8853991627693176, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.1709, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.6071189045906067, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.1248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.5462613105773926, | |
| "learning_rate": 1.9921147013144782e-05, | |
| "loss": 0.113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.30068546533584595, | |
| "learning_rate": 1.9602936856769432e-05, | |
| "loss": 0.097, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.24529214203357697, | |
| "learning_rate": 1.9048270524660197e-05, | |
| "loss": 0.0942, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.34275591373443604, | |
| "learning_rate": 1.827080574274562e-05, | |
| "loss": 0.0846, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.4993797540664673, | |
| "learning_rate": 1.7289686274214116e-05, | |
| "loss": 0.1221, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.09657509624958038, | |
| "eval_runtime": 208.9341, | |
| "eval_samples_per_second": 9.137, | |
| "eval_steps_per_second": 2.288, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.3436923325061798, | |
| "learning_rate": 1.6129070536529767e-05, | |
| "loss": 0.0948, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.2951667606830597, | |
| "learning_rate": 1.4817536741017153e-05, | |
| "loss": 0.1001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.38240548968315125, | |
| "learning_rate": 1.3387379202452917e-05, | |
| "loss": 0.0818, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.42684170603752136, | |
| "learning_rate": 1.187381314585725e-05, | |
| "loss": 0.098, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.31239619851112366, | |
| "learning_rate": 1.0314107590781284e-05, | |
| "loss": 0.0794, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.34961387515068054, | |
| "learning_rate": 8.746667664356957e-06, | |
| "loss": 0.0817, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.16344477236270905, | |
| "learning_rate": 7.210088939607709e-06, | |
| "loss": 0.0943, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.3913956880569458, | |
| "learning_rate": 5.742207084349274e-06, | |
| "loss": 0.09, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.25667184591293335, | |
| "learning_rate": 4.379166221478697e-06, | |
| "loss": 0.0937, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.4211198687553406, | |
| "learning_rate": 3.1545289407131128e-06, | |
| "loss": 0.065, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.0855652242898941, | |
| "eval_runtime": 208.8455, | |
| "eval_samples_per_second": 9.141, | |
| "eval_steps_per_second": 2.289, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.29967519640922546, | |
| "learning_rate": 2.098449876243096e-06, | |
| "loss": 0.0767, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.20352894067764282, | |
| "learning_rate": 1.2369331995613664e-06, | |
| "loss": 0.082, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.7709794640541077, | |
| "learning_rate": 5.911923104577455e-07, | |
| "loss": 0.072, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3068474531173706, | |
| "learning_rate": 1.7712749271311392e-07, | |
| "loss": 0.1011, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4012337625026703, | |
| "learning_rate": 4.9343963426840006e-09, | |
| "loss": 0.0976, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 1.0131315374424064e+16, | |
| "train_loss": 0.2077410476207733, | |
| "train_runtime": 2982.9955, | |
| "train_samples_per_second": 1.341, | |
| "train_steps_per_second": 0.042 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0131315374424064e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |