deepseek-coder-1.3b-base_10k / trainer_state.json
samahadhoud's picture
Upload folder using huggingface_hub
1d0cb95 verified
raw
history blame
4.62 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9850083287062743,
"eval_steps": 500,
"global_step": 210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.14214325374791784,
"grad_norm": 169.88966369628906,
"learning_rate": 3.9978448764777626e-05,
"loss": 0.6834,
"step": 10
},
{
"epoch": 0.28428650749583567,
"grad_norm": 54.618568420410156,
"learning_rate": 3.959660638919169e-05,
"loss": 0.5486,
"step": 20
},
{
"epoch": 0.4264297612437535,
"grad_norm": 43.16204071044922,
"learning_rate": 3.8746358948775716e-05,
"loss": 0.4913,
"step": 30
},
{
"epoch": 0.5685730149916713,
"grad_norm": 48.552268981933594,
"learning_rate": 3.744802936064812e-05,
"loss": 0.4547,
"step": 40
},
{
"epoch": 0.7107162687395892,
"grad_norm": 46.303123474121094,
"learning_rate": 3.573265076099684e-05,
"loss": 0.4369,
"step": 50
},
{
"epoch": 0.852859522487507,
"grad_norm": 41.551841735839844,
"learning_rate": 3.364122474000644e-05,
"loss": 0.4045,
"step": 60
},
{
"epoch": 0.9950027762354248,
"grad_norm": 40.26322937011719,
"learning_rate": 3.122374130724765e-05,
"loss": 0.3868,
"step": 70
},
{
"epoch": 1.1371460299833425,
"grad_norm": 44.65827178955078,
"learning_rate": 2.8537984012665694e-05,
"loss": 0.3198,
"step": 80
},
{
"epoch": 1.2792892837312604,
"grad_norm": 43.81541061401367,
"learning_rate": 2.5648148783591142e-05,
"loss": 0.2947,
"step": 90
},
{
"epoch": 1.4214325374791783,
"grad_norm": 46.52042007446289,
"learning_rate": 2.262330949082285e-05,
"loss": 0.3113,
"step": 100
},
{
"epoch": 1.563575791227096,
"grad_norm": 45.781368255615234,
"learning_rate": 1.9535766920368888e-05,
"loss": 0.2925,
"step": 110
},
{
"epoch": 1.705719044975014,
"grad_norm": 41.623714447021484,
"learning_rate": 1.6459320614311036e-05,
"loss": 0.2727,
"step": 120
},
{
"epoch": 1.8478622987229318,
"grad_norm": 45.5695686340332,
"learning_rate": 1.3467504887867757e-05,
"loss": 0.2807,
"step": 130
},
{
"epoch": 1.9900055524708495,
"grad_norm": 43.23165512084961,
"learning_rate": 1.06318311860042e-05,
"loss": 0.2787,
"step": 140
},
{
"epoch": 2.1321488062187672,
"grad_norm": 45.97528839111328,
"learning_rate": 8.02007879140733e-06,
"loss": 0.2183,
"step": 150
},
{
"epoch": 2.274292059966685,
"grad_norm": 45.93974304199219,
"learning_rate": 5.694674739932999e-06,
"loss": 0.2137,
"step": 160
},
{
"epoch": 2.416435313714603,
"grad_norm": 42.48658752441406,
"learning_rate": 3.7112016673628604e-06,
"loss": 0.1967,
"step": 170
},
{
"epoch": 2.5585785674625208,
"grad_norm": 42.581512451171875,
"learning_rate": 2.1170692534493486e-06,
"loss": 0.2094,
"step": 180
},
{
"epoch": 2.700721821210439,
"grad_norm": 44.522151947021484,
"learning_rate": 9.503810188662465e-07,
"loss": 0.2069,
"step": 190
},
{
"epoch": 2.8428650749583566,
"grad_norm": 43.30495071411133,
"learning_rate": 2.3902356128783e-07,
"loss": 0.2065,
"step": 200
},
{
"epoch": 2.9850083287062743,
"grad_norm": 40.3427848815918,
"learning_rate": 0.0,
"loss": 0.2078,
"step": 210
},
{
"epoch": 2.9850083287062743,
"step": 210,
"total_flos": 1.9543845637973606e+17,
"train_loss": 0.3293344878015064,
"train_runtime": 5186.2133,
"train_samples_per_second": 5.209,
"train_steps_per_second": 0.04
}
],
"logging_steps": 10,
"max_steps": 210,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 1.9543845637973606e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}