| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.040417649040080834, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013472549680026945, | |
| "eval_loss": 0.7738643288612366, | |
| "eval_runtime": 63.2289, | |
| "eval_samples_per_second": 4.95, | |
| "eval_steps_per_second": 2.483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0040417649040080834, | |
| "grad_norm": 0.36795666813850403, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7352, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736274840013472, | |
| "eval_loss": 0.7524806261062622, | |
| "eval_runtime": 63.7409, | |
| "eval_samples_per_second": 4.911, | |
| "eval_steps_per_second": 2.463, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008083529808016167, | |
| "grad_norm": 0.5426688194274902, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7558, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01212529471202425, | |
| "grad_norm": 0.45750245451927185, | |
| "learning_rate": 0.00018, | |
| "loss": 0.749, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013472549680026945, | |
| "eval_loss": 0.6806786060333252, | |
| "eval_runtime": 63.7004, | |
| "eval_samples_per_second": 4.914, | |
| "eval_steps_per_second": 2.465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016167059616032334, | |
| "grad_norm": 0.3981638252735138, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.6151, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020208824520040417, | |
| "grad_norm": 0.37302765250205994, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.574, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020208824520040417, | |
| "eval_loss": 0.6328597068786621, | |
| "eval_runtime": 63.7, | |
| "eval_samples_per_second": 4.914, | |
| "eval_steps_per_second": 2.465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0242505894240485, | |
| "grad_norm": 0.41704243421554565, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02694509936005389, | |
| "eval_loss": 0.6112756729125977, | |
| "eval_runtime": 63.7255, | |
| "eval_samples_per_second": 4.912, | |
| "eval_steps_per_second": 2.464, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028292354328056584, | |
| "grad_norm": 0.3000726103782654, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.5173, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03233411923206467, | |
| "grad_norm": 0.3670819103717804, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6015, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033681374200067365, | |
| "eval_loss": 0.6026643514633179, | |
| "eval_runtime": 63.7505, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 2.463, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.036375884136072754, | |
| "grad_norm": 0.3471182882785797, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.5993, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.040417649040080834, | |
| "grad_norm": 0.3501329720020294, | |
| "learning_rate": 0.0, | |
| "loss": 0.5647, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.040417649040080834, | |
| "eval_loss": 0.6006467342376709, | |
| "eval_runtime": 63.7576, | |
| "eval_samples_per_second": 4.909, | |
| "eval_steps_per_second": 2.462, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7341615253225472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |