| { |
| "best_metric": 0.9159524440765381, |
| "best_model_checkpoint": "./llama3/26-07-24-Weni-WeniGPT-Agents-Llama3-5.1.24-SFT_Experiment with DPO and Llama3 70b-2_max_steps-32_batch_8_2024-07-26/checkpoint-16", |
| "epoch": 14.222222222222221, |
| "eval_steps": 2, |
| "global_step": 16, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.7777777777777777, |
| "eval_bleu": 0.02170523150063329, |
| "eval_loss": 1.5546669960021973, |
| "eval_rouge1": 0.5658290942329046, |
| "eval_rouge2": 0.371216207944968, |
| "eval_rougeL": 0.5544380522179795, |
| "eval_rougeLsum": 0.557866697701094, |
| "eval_runtime": 8.903, |
| "eval_samples_per_second": 0.899, |
| "eval_steps_per_second": 0.112, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_bleu": 0.016226404911743514, |
| "eval_loss": 1.2373424768447876, |
| "eval_rouge1": 0.1880159013464857, |
| "eval_rouge2": 0.110501293225719, |
| "eval_rougeL": 0.16774584781013288, |
| "eval_rougeLsum": 0.18374679825109685, |
| "eval_runtime": 7.2666, |
| "eval_samples_per_second": 1.101, |
| "eval_steps_per_second": 0.138, |
| "step": 4 |
| }, |
| { |
| "epoch": 5.333333333333333, |
| "eval_bleu": 0.023706516954741297, |
| "eval_loss": 1.123119592666626, |
| "eval_rouge1": 0.6910290907363565, |
| "eval_rouge2": 0.4711964975736579, |
| "eval_rougeL": 0.673625245352441, |
| "eval_rougeLsum": 0.6773221910352027, |
| "eval_runtime": 5.1525, |
| "eval_samples_per_second": 1.553, |
| "eval_steps_per_second": 0.194, |
| "step": 6 |
| }, |
| { |
| "epoch": 7.111111111111111, |
| "eval_bleu": 0.02402168983627918, |
| "eval_loss": 1.0689845085144043, |
| "eval_rouge1": 0.6850615792026293, |
| "eval_rouge2": 0.4793755526234388, |
| "eval_rougeL": 0.6702061146380454, |
| "eval_rougeLsum": 0.6743158691399876, |
| "eval_runtime": 3.5693, |
| "eval_samples_per_second": 2.241, |
| "eval_steps_per_second": 0.28, |
| "step": 8 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.07844142016839124, |
| "learning_rate": 0.00015555702330196023, |
| "loss": 1.3804, |
| "step": 10 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "eval_bleu": 0.023887172871334808, |
| "eval_loss": 1.0223946571350098, |
| "eval_rouge1": 0.6905898370545817, |
| "eval_rouge2": 0.48557691609082443, |
| "eval_rougeL": 0.6761180651666854, |
| "eval_rougeLsum": 0.6790446004304602, |
| "eval_runtime": 3.5677, |
| "eval_samples_per_second": 2.242, |
| "eval_steps_per_second": 0.28, |
| "step": 10 |
| }, |
| { |
| "epoch": 10.666666666666666, |
| "eval_bleu": 0.024572108418943618, |
| "eval_loss": 0.9860392808914185, |
| "eval_rouge1": 0.7026862650772006, |
| "eval_rouge2": 0.5047043820859161, |
| "eval_rougeL": 0.6864786779541874, |
| "eval_rougeLsum": 0.6905060789723064, |
| "eval_runtime": 3.3868, |
| "eval_samples_per_second": 2.362, |
| "eval_steps_per_second": 0.295, |
| "step": 12 |
| }, |
| { |
| "epoch": 12.444444444444445, |
| "eval_bleu": 0.025429922278916713, |
| "eval_loss": 0.9487287998199463, |
| "eval_rouge1": 0.702795109607377, |
| "eval_rouge2": 0.5129806168696595, |
| "eval_rougeL": 0.6895042238397062, |
| "eval_rougeLsum": 0.6947769064530469, |
| "eval_runtime": 5.1904, |
| "eval_samples_per_second": 1.541, |
| "eval_steps_per_second": 0.193, |
| "step": 14 |
| }, |
| { |
| "epoch": 14.222222222222221, |
| "eval_bleu": 0.025784195587265114, |
| "eval_loss": 0.9159524440765381, |
| "eval_rouge1": 0.7050102641077431, |
| "eval_rouge2": 0.5179038464865816, |
| "eval_rougeL": 0.6926453468372398, |
| "eval_rougeLsum": 0.6956999803401138, |
| "eval_runtime": 3.0778, |
| "eval_samples_per_second": 2.599, |
| "eval_steps_per_second": 0.325, |
| "step": 16 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 32, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 11457749843968.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
