| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.035523978685612786, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "eval_loss": 1.6369138956069946, | |
| "eval_runtime": 9.2366, | |
| "eval_samples_per_second": 38.542, | |
| "eval_steps_per_second": 19.271, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003552397868561279, | |
| "grad_norm": 1.125115990638733, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5806, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007104795737122558, | |
| "grad_norm": 1.3579832315444946, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4473, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009473060982830076, | |
| "eval_loss": 1.5975923538208008, | |
| "eval_runtime": 8.4282, | |
| "eval_samples_per_second": 42.239, | |
| "eval_steps_per_second": 21.12, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010657193605683837, | |
| "grad_norm": 0.8596746921539307, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7489, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014209591474245116, | |
| "grad_norm": 1.6216509342193604, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.8584322929382324, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.3152, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018946121965660152, | |
| "eval_loss": 1.5188313722610474, | |
| "eval_runtime": 8.5113, | |
| "eval_samples_per_second": 41.827, | |
| "eval_steps_per_second": 20.913, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021314387211367674, | |
| "grad_norm": 1.149415135383606, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5686, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02486678507992895, | |
| "grad_norm": 0.9773281216621399, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.3848, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028419182948490232, | |
| "grad_norm": 1.2781157493591309, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.4521, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028419182948490232, | |
| "eval_loss": 1.490580677986145, | |
| "eval_runtime": 8.504, | |
| "eval_samples_per_second": 41.862, | |
| "eval_steps_per_second": 20.931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03197158081705151, | |
| "grad_norm": 1.0305604934692383, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.663, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "grad_norm": 0.8461658954620361, | |
| "learning_rate": 0.0, | |
| "loss": 1.2382, | |
| "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": 599293262561280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |