| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.14272970561998216, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0007136485280999108, |
| "eval_loss": 0.6165480017662048, |
| "eval_runtime": 55.534, |
| "eval_samples_per_second": 10.624, |
| "eval_steps_per_second": 5.312, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007136485280999108, |
| "grad_norm": 0.39041173458099365, |
| "learning_rate": 0.00019967573081342103, |
| "loss": 0.4714, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.014272970561998216, |
| "grad_norm": 0.35318252444267273, |
| "learning_rate": 0.0001970941817426052, |
| "loss": 0.3333, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.021409455842997322, |
| "grad_norm": 0.22868792712688446, |
| "learning_rate": 0.00019199794436588243, |
| "loss": 0.3151, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.028545941123996433, |
| "grad_norm": 0.2561885714530945, |
| "learning_rate": 0.0001845190085543795, |
| "loss": 0.3316, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.03568242640499554, |
| "grad_norm": 0.27606117725372314, |
| "learning_rate": 0.00017485107481711012, |
| "loss": 0.2918, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03568242640499554, |
| "eval_loss": 0.3071356415748596, |
| "eval_runtime": 55.5552, |
| "eval_samples_per_second": 10.62, |
| "eval_steps_per_second": 5.31, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.042818911685994644, |
| "grad_norm": 0.22240565717220306, |
| "learning_rate": 0.00016324453755953773, |
| "loss": 0.3401, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.049955396966993755, |
| "grad_norm": 0.25228607654571533, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.3181, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.057091882247992866, |
| "grad_norm": 0.25924035906791687, |
| "learning_rate": 0.00013546048870425356, |
| "loss": 0.3091, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.06422836752899197, |
| "grad_norm": 0.22803744673728943, |
| "learning_rate": 0.00012000256937760445, |
| "loss": 0.3028, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.07136485280999108, |
| "grad_norm": 0.2437671571969986, |
| "learning_rate": 0.00010402659401094152, |
| "loss": 0.2869, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07136485280999108, |
| "eval_loss": 0.2971809506416321, |
| "eval_runtime": 55.5199, |
| "eval_samples_per_second": 10.627, |
| "eval_steps_per_second": 5.313, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07850133809099019, |
| "grad_norm": 0.26714345812797546, |
| "learning_rate": 8.79463319744677e-05, |
| "loss": 0.3431, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.08563782337198929, |
| "grad_norm": 0.21566510200500488, |
| "learning_rate": 7.217825360835473e-05, |
| "loss": 0.2721, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0927743086529884, |
| "grad_norm": 0.25159725546836853, |
| "learning_rate": 5.713074385969457e-05, |
| "loss": 0.3095, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.09991079393398751, |
| "grad_norm": 0.2559829652309418, |
| "learning_rate": 4.3193525326884435e-05, |
| "loss": 0.3015, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.10704727921498662, |
| "grad_norm": 0.22735165059566498, |
| "learning_rate": 3.072756464904006e-05, |
| "loss": 0.2623, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.10704727921498662, |
| "eval_loss": 0.2916809618473053, |
| "eval_runtime": 55.5435, |
| "eval_samples_per_second": 10.622, |
| "eval_steps_per_second": 5.311, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.11418376449598573, |
| "grad_norm": 0.24490103125572205, |
| "learning_rate": 2.0055723659649904e-05, |
| "loss": 0.3098, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.12132024977698483, |
| "grad_norm": 0.21790523827075958, |
| "learning_rate": 1.1454397434679021e-05, |
| "loss": 0.2828, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.12845673505798394, |
| "grad_norm": 0.24194355309009552, |
| "learning_rate": 5.146355805285452e-06, |
| "loss": 0.2992, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.13559322033898305, |
| "grad_norm": 0.29640981554985046, |
| "learning_rate": 1.2949737362087156e-06, |
| "loss": 0.3089, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.14272970561998216, |
| "grad_norm": 0.4439384341239929, |
| "learning_rate": 0.0, |
| "loss": 0.3361, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.14272970561998216, |
| "eval_loss": 0.2901231050491333, |
| "eval_runtime": 55.6242, |
| "eval_samples_per_second": 10.607, |
| "eval_steps_per_second": 5.303, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "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": 8.168526596957798e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
