fasthypernet-16k / checkpoint-300 /trainer_state.json
aixk's picture
Upload folder using huggingface_hub
cf950db verified
Raw
History Blame Contribute Delete
5.91 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0010372726644077173,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.4575755480257244e-05,
"grad_norm": 38.12546920776367,
"learning_rate": 4.8e-07,
"loss": 9.3097,
"step": 10
},
{
"epoch": 6.915151096051449e-05,
"grad_norm": 31.766887664794922,
"learning_rate": 1.0799999999999998e-06,
"loss": 9.293,
"step": 20
},
{
"epoch": 0.00010372726644077173,
"grad_norm": 48.67866897583008,
"learning_rate": 1.6799999999999998e-06,
"loss": 9.2784,
"step": 30
},
{
"epoch": 0.00013830302192102898,
"grad_norm": 33.25461959838867,
"learning_rate": 2.2799999999999998e-06,
"loss": 9.2793,
"step": 40
},
{
"epoch": 0.00017287877740128623,
"grad_norm": 35.62735366821289,
"learning_rate": 2.8799999999999995e-06,
"loss": 9.2657,
"step": 50
},
{
"epoch": 0.00020745453288154345,
"grad_norm": 43.818328857421875,
"learning_rate": 3.4799999999999993e-06,
"loss": 9.2616,
"step": 60
},
{
"epoch": 0.0002420302883618007,
"grad_norm": 43.82963943481445,
"learning_rate": 4.079999999999999e-06,
"loss": 9.2633,
"step": 70
},
{
"epoch": 0.00027660604384205796,
"grad_norm": 57.38799285888672,
"learning_rate": 4.679999999999999e-06,
"loss": 9.2308,
"step": 80
},
{
"epoch": 0.0003111817993223152,
"grad_norm": 44.78755187988281,
"learning_rate": 5.28e-06,
"loss": 9.2083,
"step": 90
},
{
"epoch": 0.00034575755480257246,
"grad_norm": 40.440338134765625,
"learning_rate": 5.88e-06,
"loss": 9.2418,
"step": 100
},
{
"epoch": 0.00038033331028282965,
"grad_norm": 36.28009033203125,
"learning_rate": 6.48e-06,
"loss": 9.2208,
"step": 110
},
{
"epoch": 0.0004149090657630869,
"grad_norm": 42.1943473815918,
"learning_rate": 7.079999999999999e-06,
"loss": 9.2197,
"step": 120
},
{
"epoch": 0.00044948482124334416,
"grad_norm": 37.897483825683594,
"learning_rate": 7.68e-06,
"loss": 9.2271,
"step": 130
},
{
"epoch": 0.0004840605767236014,
"grad_norm": 33.77066421508789,
"learning_rate": 8.279999999999999e-06,
"loss": 9.2311,
"step": 140
},
{
"epoch": 0.0005186363322038587,
"grad_norm": 34.798553466796875,
"learning_rate": 8.88e-06,
"loss": 9.2079,
"step": 150
},
{
"epoch": 0.0005532120876841159,
"grad_norm": 39.236812591552734,
"learning_rate": 9.48e-06,
"loss": 9.2186,
"step": 160
},
{
"epoch": 0.0005877878431643732,
"grad_norm": 37.878868103027344,
"learning_rate": 1.0079999999999998e-05,
"loss": 9.2176,
"step": 170
},
{
"epoch": 0.0006223635986446304,
"grad_norm": 64.34676361083984,
"learning_rate": 1.068e-05,
"loss": 9.2086,
"step": 180
},
{
"epoch": 0.0006569393541248877,
"grad_norm": 35.60507583618164,
"learning_rate": 1.1279999999999999e-05,
"loss": 9.2045,
"step": 190
},
{
"epoch": 0.0006915151096051449,
"grad_norm": 45.516971588134766,
"learning_rate": 1.188e-05,
"loss": 9.2144,
"step": 200
},
{
"epoch": 0.0007260908650854022,
"grad_norm": 33.20392608642578,
"learning_rate": 1.2479999999999999e-05,
"loss": 9.1846,
"step": 210
},
{
"epoch": 0.0007606666205656593,
"grad_norm": 33.04153060913086,
"learning_rate": 1.3019999999999999e-05,
"loss": 9.1875,
"step": 220
},
{
"epoch": 0.0007952423760459166,
"grad_norm": 29.512754440307617,
"learning_rate": 1.362e-05,
"loss": 9.1849,
"step": 230
},
{
"epoch": 0.0008298181315261738,
"grad_norm": 24.111255645751953,
"learning_rate": 1.4219999999999998e-05,
"loss": 9.2074,
"step": 240
},
{
"epoch": 0.0008643938870064311,
"grad_norm": 36.84242630004883,
"learning_rate": 1.4819999999999999e-05,
"loss": 9.1818,
"step": 250
},
{
"epoch": 0.0008989696424866883,
"grad_norm": 22.629037857055664,
"learning_rate": 1.5419999999999998e-05,
"loss": 9.1991,
"step": 260
},
{
"epoch": 0.0009335453979669456,
"grad_norm": 28.257951736450195,
"learning_rate": 1.602e-05,
"loss": 9.1579,
"step": 270
},
{
"epoch": 0.0009681211534472028,
"grad_norm": 26.29328155517578,
"learning_rate": 1.6619999999999997e-05,
"loss": 9.1753,
"step": 280
},
{
"epoch": 0.00100269690892746,
"grad_norm": 30.55463981628418,
"learning_rate": 1.7219999999999998e-05,
"loss": 9.1663,
"step": 290
},
{
"epoch": 0.0010372726644077173,
"grad_norm": 30.852642059326172,
"learning_rate": 1.782e-05,
"loss": 9.1624,
"step": 300
}
],
"logging_steps": 10,
"max_steps": 1000000,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 957906800640000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}