Deepseek-R1-Distill-14B-Code / trainer_state.json
realYinkaIyiola's picture
Upload folder using huggingface_hub
ca78b15 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 1000,
"global_step": 3360,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08928571428571429,
"grad_norm": 0.42009279659859,
"learning_rate": 2.9761904761904763e-06,
"loss": 0.5182,
"step": 100
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.38633756820312576,
"learning_rate": 5.9523809523809525e-06,
"loss": 0.4851,
"step": 200
},
{
"epoch": 0.26785714285714285,
"grad_norm": 0.45962638823829793,
"learning_rate": 8.92857142857143e-06,
"loss": 0.4816,
"step": 300
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.4226066822293375,
"learning_rate": 9.988952191691925e-06,
"loss": 0.4868,
"step": 400
},
{
"epoch": 0.44642857142857145,
"grad_norm": 0.3827199419252431,
"learning_rate": 9.927604254015586e-06,
"loss": 0.4895,
"step": 500
},
{
"epoch": 0.5357142857142857,
"grad_norm": 0.446330637822688,
"learning_rate": 9.81312123475006e-06,
"loss": 0.49,
"step": 600
},
{
"epoch": 0.625,
"grad_norm": 0.38997662785153187,
"learning_rate": 9.646737621134112e-06,
"loss": 0.4875,
"step": 700
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.3660382818183833,
"learning_rate": 9.430247552150673e-06,
"loss": 0.4856,
"step": 800
},
{
"epoch": 0.8035714285714286,
"grad_norm": 0.3644345773145445,
"learning_rate": 9.165985472062245e-06,
"loss": 0.4846,
"step": 900
},
{
"epoch": 0.8928571428571429,
"grad_norm": 0.3563534770415374,
"learning_rate": 8.856800957755e-06,
"loss": 0.4844,
"step": 1000
},
{
"epoch": 0.8928571428571429,
"eval_loss": 0.4723494052886963,
"eval_runtime": 527.1023,
"eval_samples_per_second": 3.777,
"eval_steps_per_second": 0.472,
"step": 1000
},
{
"epoch": 0.9821428571428571,
"grad_norm": 0.3915169737374782,
"learning_rate": 8.50602799133199e-06,
"loss": 0.4835,
"step": 1100
},
{
"epoch": 1.0714285714285714,
"grad_norm": 0.3986100916298589,
"learning_rate": 8.117449009293668e-06,
"loss": 0.4388,
"step": 1200
},
{
"epoch": 1.1607142857142858,
"grad_norm": 0.38571453527776084,
"learning_rate": 7.69525411596865e-06,
"loss": 0.4311,
"step": 1300
},
{
"epoch": 1.25,
"grad_norm": 0.3530259346548572,
"learning_rate": 7.243995901002312e-06,
"loss": 0.427,
"step": 1400
},
{
"epoch": 1.3392857142857144,
"grad_norm": 0.4069536036588859,
"learning_rate": 6.768540348112908e-06,
"loss": 0.429,
"step": 1500
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.40040431306856655,
"learning_rate": 6.274014364473274e-06,
"loss": 0.4282,
"step": 1600
},
{
"epoch": 1.5178571428571428,
"grad_norm": 0.34105714911676593,
"learning_rate": 5.765750496516547e-06,
"loss": 0.4318,
"step": 1700
},
{
"epoch": 1.6071428571428572,
"grad_norm": 0.3679992579349683,
"learning_rate": 5.249229428303486e-06,
"loss": 0.4272,
"step": 1800
},
{
"epoch": 1.6964285714285714,
"grad_norm": 0.37091945305243507,
"learning_rate": 4.730020882499964e-06,
"loss": 0.4292,
"step": 1900
},
{
"epoch": 1.7857142857142856,
"grad_norm": 0.4210486903676345,
"learning_rate": 4.213723561238074e-06,
"loss": 0.4258,
"step": 2000
},
{
"epoch": 1.7857142857142856,
"eval_loss": 0.472212553024292,
"eval_runtime": 526.9195,
"eval_samples_per_second": 3.779,
"eval_steps_per_second": 0.473,
"step": 2000
},
{
"epoch": 1.875,
"grad_norm": 0.4028542180886112,
"learning_rate": 3.705904774487396e-06,
"loss": 0.4307,
"step": 2100
},
{
"epoch": 1.9642857142857144,
"grad_norm": 0.4621878586501629,
"learning_rate": 3.2120404069325695e-06,
"loss": 0.4271,
"step": 2200
},
{
"epoch": 2.0535714285714284,
"grad_norm": 0.4678503190324282,
"learning_rate": 2.737455870703155e-06,
"loss": 0.3889,
"step": 2300
},
{
"epoch": 2.142857142857143,
"grad_norm": 0.4575407722156448,
"learning_rate": 2.2872686806712037e-06,
"loss": 0.374,
"step": 2400
},
{
"epoch": 2.232142857142857,
"grad_norm": 0.4241549942755108,
"learning_rate": 1.8663332715355399e-06,
"loss": 0.3694,
"step": 2500
},
{
"epoch": 2.3214285714285716,
"grad_norm": 0.4261640971882884,
"learning_rate": 1.4791886517382415e-06,
"loss": 0.3695,
"step": 2600
},
{
"epoch": 2.4107142857142856,
"grad_norm": 0.4640732620056673,
"learning_rate": 1.1300094586688632e-06,
"loss": 0.3719,
"step": 2700
},
{
"epoch": 2.5,
"grad_norm": 0.3661173371298237,
"learning_rate": 8.225609429353187e-07,
"loss": 0.3749,
"step": 2800
},
{
"epoch": 2.5892857142857144,
"grad_norm": 0.4357767645022839,
"learning_rate": 5.601583671126532e-07,
"loss": 0.3702,
"step": 2900
},
{
"epoch": 2.678571428571429,
"grad_norm": 0.41225890414805616,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.3709,
"step": 3000
},
{
"epoch": 2.678571428571429,
"eval_loss": 0.48118627071380615,
"eval_runtime": 526.9164,
"eval_samples_per_second": 3.779,
"eval_steps_per_second": 0.473,
"step": 3000
},
{
"epoch": 2.767857142857143,
"grad_norm": 0.5194673179252723,
"learning_rate": 1.8129288932490276e-07,
"loss": 0.3689,
"step": 3100
},
{
"epoch": 2.857142857142857,
"grad_norm": 0.4488783086501226,
"learning_rate": 6.891534954310886e-08,
"loss": 0.3666,
"step": 3200
},
{
"epoch": 2.946428571428571,
"grad_norm": 0.3580886076427873,
"learning_rate": 9.710420977340763e-09,
"loss": 0.3702,
"step": 3300
},
{
"epoch": 3.0,
"step": 3360,
"total_flos": 3000194903834624.0,
"train_loss": 0.4290710630871001,
"train_runtime": 89946.115,
"train_samples_per_second": 0.597,
"train_steps_per_second": 0.037
}
],
"logging_steps": 100,
"max_steps": 3360,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3000194903834624.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}