albert-base-imdb / trainer_state.json
jialicheng's picture
Upload folder using huggingface_hub
d2382c6 verified
raw
history blame
3.84 kB
{
"best_metric": 0.84072,
"best_model_checkpoint": "checkpoint/albert-base-v2/imdb_42/checkpoint-1564",
"epoch": 10.0,
"global_step": 7820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.8094,
"eval_loss": 0.39343979954719543,
"eval_runtime": 19.8571,
"eval_samples_per_second": 1258.993,
"eval_steps_per_second": 4.935,
"step": 782
},
{
"epoch": 1.28,
"learning_rate": 4.360613810741688e-05,
"loss": 0.5098,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.84072,
"eval_loss": 0.3598405718803406,
"eval_runtime": 19.9131,
"eval_samples_per_second": 1255.458,
"eval_steps_per_second": 4.921,
"step": 1564
},
{
"epoch": 2.56,
"learning_rate": 3.721227621483376e-05,
"loss": 0.3335,
"step": 2000
},
{
"epoch": 3.0,
"eval_accuracy": 0.83936,
"eval_loss": 0.4151993691921234,
"eval_runtime": 19.8841,
"eval_samples_per_second": 1257.285,
"eval_steps_per_second": 4.929,
"step": 2346
},
{
"epoch": 3.84,
"learning_rate": 3.081841432225064e-05,
"loss": 0.2248,
"step": 3000
},
{
"epoch": 4.0,
"eval_accuracy": 0.82468,
"eval_loss": 0.44072645902633667,
"eval_runtime": 19.8311,
"eval_samples_per_second": 1260.645,
"eval_steps_per_second": 4.942,
"step": 3128
},
{
"epoch": 5.0,
"eval_accuracy": 0.82064,
"eval_loss": 0.6104266047477722,
"eval_runtime": 19.826,
"eval_samples_per_second": 1260.968,
"eval_steps_per_second": 4.943,
"step": 3910
},
{
"epoch": 5.12,
"learning_rate": 2.442455242966752e-05,
"loss": 0.1481,
"step": 4000
},
{
"epoch": 6.0,
"eval_accuracy": 0.78312,
"eval_loss": 0.9157971143722534,
"eval_runtime": 19.8594,
"eval_samples_per_second": 1258.849,
"eval_steps_per_second": 4.935,
"step": 4692
},
{
"epoch": 6.39,
"learning_rate": 1.80306905370844e-05,
"loss": 0.0904,
"step": 5000
},
{
"epoch": 7.0,
"eval_accuracy": 0.81568,
"eval_loss": 0.8991187214851379,
"eval_runtime": 19.845,
"eval_samples_per_second": 1259.764,
"eval_steps_per_second": 4.938,
"step": 5474
},
{
"epoch": 7.67,
"learning_rate": 1.163682864450128e-05,
"loss": 0.0532,
"step": 6000
},
{
"epoch": 8.0,
"eval_accuracy": 0.82364,
"eval_loss": 1.0848387479782104,
"eval_runtime": 19.903,
"eval_samples_per_second": 1256.093,
"eval_steps_per_second": 4.924,
"step": 6256
},
{
"epoch": 8.95,
"learning_rate": 5.242966751918159e-06,
"loss": 0.026,
"step": 7000
},
{
"epoch": 9.0,
"eval_accuracy": 0.8226,
"eval_loss": 1.1122615337371826,
"eval_runtime": 19.8109,
"eval_samples_per_second": 1261.933,
"eval_steps_per_second": 4.947,
"step": 7038
},
{
"epoch": 10.0,
"eval_accuracy": 0.81924,
"eval_loss": 1.2039557695388794,
"eval_runtime": 19.8508,
"eval_samples_per_second": 1259.396,
"eval_steps_per_second": 4.937,
"step": 7820
},
{
"epoch": 10.0,
"step": 7820,
"total_flos": 1493631360000000.0,
"train_loss": 0.17865913017936375,
"train_runtime": 809.0649,
"train_samples_per_second": 308.999,
"train_steps_per_second": 9.665
}
],
"max_steps": 7820,
"num_train_epochs": 10,
"total_flos": 1493631360000000.0,
"trial_name": null,
"trial_params": null
}