|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.05383580080753701, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.005383580080753701, |
|
"grad_norm": 1.332345962524414, |
|
"learning_rate": 2e-05, |
|
"loss": 0.7345, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.005383580080753701, |
|
"eval_loss": 0.7382340431213379, |
|
"eval_runtime": 7.7076, |
|
"eval_samples_per_second": 10.25, |
|
"eval_steps_per_second": 5.19, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.010767160161507403, |
|
"grad_norm": 1.5144602060317993, |
|
"learning_rate": 4e-05, |
|
"loss": 0.7732, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.016150740242261104, |
|
"grad_norm": 1.4010770320892334, |
|
"learning_rate": 6e-05, |
|
"loss": 0.7996, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.016150740242261104, |
|
"eval_loss": 0.6860002279281616, |
|
"eval_runtime": 7.8686, |
|
"eval_samples_per_second": 10.04, |
|
"eval_steps_per_second": 5.083, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.021534320323014805, |
|
"grad_norm": 1.2587902545928955, |
|
"learning_rate": 8e-05, |
|
"loss": 0.665, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.026917900403768506, |
|
"grad_norm": 1.1400635242462158, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6649, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.03230148048452221, |
|
"grad_norm": 0.9094105362892151, |
|
"learning_rate": 0.00012, |
|
"loss": 0.5525, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.03230148048452221, |
|
"eval_loss": 0.5270073413848877, |
|
"eval_runtime": 7.7898, |
|
"eval_samples_per_second": 10.141, |
|
"eval_steps_per_second": 5.135, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.03768506056527591, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00012, |
|
"loss": 0.5412, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.04306864064602961, |
|
"grad_norm": 0.9600444436073303, |
|
"learning_rate": 0.00014, |
|
"loss": 0.6705, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.04845222072678331, |
|
"grad_norm": 1.114023208618164, |
|
"learning_rate": 0.00016, |
|
"loss": 0.4857, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.04845222072678331, |
|
"eval_loss": 0.424485981464386, |
|
"eval_runtime": 7.7991, |
|
"eval_samples_per_second": 10.129, |
|
"eval_steps_per_second": 5.129, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.05383580080753701, |
|
"grad_norm": 0.8380860686302185, |
|
"learning_rate": 0.00018, |
|
"loss": 0.383, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4716388916658176.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|