| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 312, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06433453960595094, |
| "grad_norm": 3.45802150331781, |
| "learning_rate": 9e-06, |
| "loss": 1.2375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12866907921190188, |
| "grad_norm": 1.1539024437598726, |
| "learning_rate": 9.701986754966888e-06, |
| "loss": 0.9458, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.19300361881785283, |
| "grad_norm": 0.9061861869896987, |
| "learning_rate": 9.370860927152319e-06, |
| "loss": 0.8553, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.25733815842380375, |
| "grad_norm": 0.9981148139996454, |
| "learning_rate": 9.039735099337749e-06, |
| "loss": 0.8223, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.32167269802975473, |
| "grad_norm": 0.8365225486736688, |
| "learning_rate": 8.70860927152318e-06, |
| "loss": 0.7753, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.38600723763570566, |
| "grad_norm": 0.8456361592054138, |
| "learning_rate": 8.37748344370861e-06, |
| "loss": 0.7945, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.45034177724165664, |
| "grad_norm": 0.8510899654200162, |
| "learning_rate": 8.04635761589404e-06, |
| "loss": 0.7906, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5146763168476075, |
| "grad_norm": 0.8094078169285094, |
| "learning_rate": 7.715231788079471e-06, |
| "loss": 0.7744, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5790108564535585, |
| "grad_norm": 0.7429293470064048, |
| "learning_rate": 7.384105960264901e-06, |
| "loss": 0.7717, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6433453960595095, |
| "grad_norm": 0.7512159253738925, |
| "learning_rate": 7.052980132450332e-06, |
| "loss": 0.7744, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7076799356654604, |
| "grad_norm": 0.826044235136776, |
| "learning_rate": 6.721854304635762e-06, |
| "loss": 0.7491, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.7720144752714113, |
| "grad_norm": 0.8503335376772373, |
| "learning_rate": 6.390728476821193e-06, |
| "loss": 0.7593, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8363490148773622, |
| "grad_norm": 0.7306086642250036, |
| "learning_rate": 6.059602649006623e-06, |
| "loss": 0.7555, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.9006835544833133, |
| "grad_norm": 0.745854567446407, |
| "learning_rate": 5.728476821192054e-06, |
| "loss": 0.7434, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9650180940892642, |
| "grad_norm": 0.7574425315504884, |
| "learning_rate": 5.397350993377483e-06, |
| "loss": 0.7764, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0257338158423803, |
| "grad_norm": 0.7250372088806204, |
| "learning_rate": 5.066225165562915e-06, |
| "loss": 0.709, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.0900683554483312, |
| "grad_norm": 0.75139008443435, |
| "learning_rate": 4.7350993377483445e-06, |
| "loss": 0.6574, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.1544028950542822, |
| "grad_norm": 0.7181949393746255, |
| "learning_rate": 4.403973509933775e-06, |
| "loss": 0.6573, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.218737434660233, |
| "grad_norm": 0.7970783454719403, |
| "learning_rate": 4.072847682119206e-06, |
| "loss": 0.6617, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.2830719742661842, |
| "grad_norm": 0.741621225992888, |
| "learning_rate": 3.7417218543046362e-06, |
| "loss": 0.6625, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3474065138721352, |
| "grad_norm": 0.7244825073568412, |
| "learning_rate": 3.4105960264900668e-06, |
| "loss": 0.6516, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.411741053478086, |
| "grad_norm": 0.6328326617408025, |
| "learning_rate": 3.079470198675497e-06, |
| "loss": 0.6478, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.476075593084037, |
| "grad_norm": 0.7325603487325139, |
| "learning_rate": 2.7483443708609275e-06, |
| "loss": 0.6512, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.540410132689988, |
| "grad_norm": 0.6447452871518153, |
| "learning_rate": 2.417218543046358e-06, |
| "loss": 0.6454, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.6047446722959389, |
| "grad_norm": 0.7076398532029401, |
| "learning_rate": 2.086092715231788e-06, |
| "loss": 0.6539, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.6690792119018898, |
| "grad_norm": 0.6775962757094781, |
| "learning_rate": 1.7549668874172188e-06, |
| "loss": 0.6499, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.7334137515078407, |
| "grad_norm": 0.6345994881996349, |
| "learning_rate": 1.4238410596026491e-06, |
| "loss": 0.6456, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.7977482911137916, |
| "grad_norm": 0.6759310052346794, |
| "learning_rate": 1.0927152317880797e-06, |
| "loss": 0.6499, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.8620828307197428, |
| "grad_norm": 0.686752021394961, |
| "learning_rate": 7.6158940397351e-07, |
| "loss": 0.6526, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.9264173703256935, |
| "grad_norm": 0.6535588837970772, |
| "learning_rate": 4.304635761589404e-07, |
| "loss": 0.6394, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.9907519099316446, |
| "grad_norm": 0.7094514579767396, |
| "learning_rate": 9.933774834437088e-08, |
| "loss": 0.643, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 312, |
| "total_flos": 119307564613632.0, |
| "train_loss": 0.7332022241674937, |
| "train_runtime": 6450.9735, |
| "train_samples_per_second": 6.168, |
| "train_steps_per_second": 0.048 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 312, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 119307564613632.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
