180 lines
5.0 KiB
JSON
180 lines
5.0 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 10,
|
|
"global_step": 45,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 0.5051268041133881,
|
|
"epoch": 0.1111111111111111,
|
|
"grad_norm": 1.7442580461502075,
|
|
"learning_rate": 0.0002984015052112665,
|
|
"loss": 1.0908665657043457,
|
|
"mean_token_accuracy": 0.8142835974693299,
|
|
"num_tokens": 59002.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 0.7225139260292053,
|
|
"epoch": 0.2222222222222222,
|
|
"grad_norm": 0.7206196784973145,
|
|
"learning_rate": 0.0002808074112215711,
|
|
"loss": 0.6919548034667968,
|
|
"mean_token_accuracy": 0.8514000058174134,
|
|
"num_tokens": 120432.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.2222222222222222,
|
|
"eval_entropy": 0.9578993916511536,
|
|
"eval_loss": 0.9403628706932068,
|
|
"eval_mean_token_accuracy": 0.8023552894592285,
|
|
"eval_num_tokens": 120432.0,
|
|
"eval_runtime": 1.6133,
|
|
"eval_samples_per_second": 45.869,
|
|
"eval_steps_per_second": 1.86,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 0.8998202800750732,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 0.6158784031867981,
|
|
"learning_rate": 0.00024595095323383365,
|
|
"loss": 0.8696078300476074,
|
|
"mean_token_accuracy": 0.8144582986831665,
|
|
"num_tokens": 179678.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 0.7956753373146057,
|
|
"epoch": 0.4444444444444444,
|
|
"grad_norm": 0.638497531414032,
|
|
"learning_rate": 0.00019843206071571692,
|
|
"loss": 0.8670864105224609,
|
|
"mean_token_accuracy": 0.8208897352218628,
|
|
"num_tokens": 240600.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.4444444444444444,
|
|
"eval_entropy": 0.8266730904579163,
|
|
"eval_loss": 0.9242745637893677,
|
|
"eval_mean_token_accuracy": 0.803473949432373,
|
|
"eval_num_tokens": 240600.0,
|
|
"eval_runtime": 1.6168,
|
|
"eval_samples_per_second": 45.77,
|
|
"eval_steps_per_second": 1.856,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 0.7963908970355987,
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 0.42324671149253845,
|
|
"learning_rate": 0.00014452169654135115,
|
|
"loss": 0.8695890426635742,
|
|
"mean_token_accuracy": 0.8264959454536438,
|
|
"num_tokens": 301638.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 0.9203879475593567,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 0.6087479591369629,
|
|
"learning_rate": 9.133429192647661e-05,
|
|
"loss": 0.9359363555908203,
|
|
"mean_token_accuracy": 0.8043835282325744,
|
|
"num_tokens": 359243.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.6666666666666666,
|
|
"eval_entropy": 0.861892561117808,
|
|
"eval_loss": 0.918761670589447,
|
|
"eval_mean_token_accuracy": 0.8063527544339498,
|
|
"eval_num_tokens": 359243.0,
|
|
"eval_runtime": 1.6289,
|
|
"eval_samples_per_second": 45.43,
|
|
"eval_steps_per_second": 1.842,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 0.6894854545593262,
|
|
"epoch": 0.7777777777777778,
|
|
"grad_norm": 0.48022472858428955,
|
|
"learning_rate": 4.58888707169049e-05,
|
|
"loss": 0.6996908187866211,
|
|
"mean_token_accuracy": 0.849899160861969,
|
|
"num_tokens": 417098.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 0.8869106888771057,
|
|
"epoch": 0.8888888888888888,
|
|
"grad_norm": 0.5962172746658325,
|
|
"learning_rate": 1.4182764376028006e-05,
|
|
"loss": 0.9062419891357422,
|
|
"mean_token_accuracy": 0.8095215201377869,
|
|
"num_tokens": 480008.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.8888888888888888,
|
|
"eval_entropy": 0.8640047709147135,
|
|
"eval_loss": 0.9166465997695923,
|
|
"eval_mean_token_accuracy": 0.8074178695678711,
|
|
"eval_num_tokens": 480008.0,
|
|
"eval_runtime": 1.6231,
|
|
"eval_samples_per_second": 45.593,
|
|
"eval_steps_per_second": 1.848,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 0.8551887631416321,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.8982498049736023,
|
|
"learning_rate": 4.0015745046725336e-07,
|
|
"loss": 0.8875165939331054,
|
|
"mean_token_accuracy": 0.8184282779693604,
|
|
"num_tokens": 530794.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"eval_entropy": 0.8636427720387777,
|
|
"eval_loss": 0.9162904620170593,
|
|
"eval_mean_token_accuracy": 0.8047811388969421,
|
|
"eval_num_tokens": 530794.0,
|
|
"eval_runtime": 1.6244,
|
|
"eval_samples_per_second": 45.555,
|
|
"eval_steps_per_second": 1.847,
|
|
"step": 45
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 45,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1952299008000000.0,
|
|
"train_batch_size": 32,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|