chat-24b / trainer_state.json
Delta-Vector's picture
Upload folder using huggingface_hub
23c31bf verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"eval_steps": 500,
"global_step": 16,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6666666666666666,
"grad_norm": 171.21589855027844,
"learning_rate": 2e-05,
"loss": 3.1436,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 171.21589855027844,
"learning_rate": 4e-05,
"loss": 6.2428,
"step": 2
},
{
"epoch": 1.6666666666666665,
"grad_norm": 471.01340030167887,
"learning_rate": 6.000000000000001e-05,
"loss": 9.1236,
"step": 3
},
{
"epoch": 2.0,
"grad_norm": 1490.2938502466984,
"learning_rate": 8e-05,
"loss": 12.0519,
"step": 4
},
{
"epoch": 2.6666666666666665,
"grad_norm": 942.081671418508,
"learning_rate": 0.0001,
"loss": 11.5508,
"step": 5
},
{
"epoch": 3.0,
"grad_norm": 942.081671418508,
"learning_rate": 9.900990099009903e-05,
"loss": 10.2465,
"step": 6
},
{
"epoch": 3.6666666666666665,
"grad_norm": 614.2143809762082,
"learning_rate": 9.782608695652174e-05,
"loss": 9.6248,
"step": 7
},
{
"epoch": 4.0,
"grad_norm": 206.13959236392643,
"learning_rate": 9.638554216867471e-05,
"loss": 9.0348,
"step": 8
},
{
"epoch": 4.666666666666667,
"grad_norm": 310.4054985828841,
"learning_rate": 9.45945945945946e-05,
"loss": 24.1443,
"step": 9
},
{
"epoch": 5.0,
"grad_norm": 310.4054985828841,
"learning_rate": 9.230769230769229e-05,
"loss": 13.3258,
"step": 10
},
{
"epoch": 5.666666666666667,
"grad_norm": 369.6066414261131,
"learning_rate": 8.92857142857143e-05,
"loss": 10.9274,
"step": 11
},
{
"epoch": 6.0,
"grad_norm": 64.75267375733827,
"learning_rate": 8.510638297872342e-05,
"loss": 8.5392,
"step": 12
},
{
"epoch": 6.666666666666667,
"grad_norm": 32.39084296483837,
"learning_rate": 7.894736842105262e-05,
"loss": 8.531,
"step": 13
},
{
"epoch": 7.0,
"grad_norm": 32.39084296483837,
"learning_rate": 6.896551724137931e-05,
"loss": 7.9085,
"step": 14
},
{
"epoch": 7.666666666666667,
"grad_norm": 254.05049483006297,
"learning_rate": 5e-05,
"loss": 7.8081,
"step": 15
},
{
"epoch": 8.0,
"grad_norm": 179.19756327998078,
"learning_rate": 0,
"loss": 7.6925,
"step": 16
}
],
"logging_steps": 1,
"max_steps": 16,
"num_input_tokens_seen": 0,
"num_train_epochs": 16,
"save_steps": 1,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6340688404807680.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}