prxy5606's picture
Training in progress, step 50, checkpoint
4887dce verified
raw
history blame
9.87 kB
{
"best_metric": 1.83683443069458,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.33783783783783783,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006756756756756757,
"grad_norm": 1.4881850481033325,
"learning_rate": 1e-05,
"loss": 2.2896,
"step": 1
},
{
"epoch": 0.006756756756756757,
"eval_loss": 2.4700465202331543,
"eval_runtime": 18.7535,
"eval_samples_per_second": 13.331,
"eval_steps_per_second": 3.359,
"step": 1
},
{
"epoch": 0.013513513513513514,
"grad_norm": 1.8108983039855957,
"learning_rate": 2e-05,
"loss": 2.3382,
"step": 2
},
{
"epoch": 0.02027027027027027,
"grad_norm": 1.7592962980270386,
"learning_rate": 3e-05,
"loss": 2.3745,
"step": 3
},
{
"epoch": 0.02702702702702703,
"grad_norm": 1.7991939783096313,
"learning_rate": 4e-05,
"loss": 2.3313,
"step": 4
},
{
"epoch": 0.033783783783783786,
"grad_norm": 1.6926255226135254,
"learning_rate": 5e-05,
"loss": 2.2734,
"step": 5
},
{
"epoch": 0.04054054054054054,
"grad_norm": 1.478215217590332,
"learning_rate": 6e-05,
"loss": 2.1964,
"step": 6
},
{
"epoch": 0.0472972972972973,
"grad_norm": 1.6067980527877808,
"learning_rate": 7e-05,
"loss": 2.055,
"step": 7
},
{
"epoch": 0.05405405405405406,
"grad_norm": 1.6643190383911133,
"learning_rate": 8e-05,
"loss": 1.9669,
"step": 8
},
{
"epoch": 0.060810810810810814,
"grad_norm": 2.5624747276306152,
"learning_rate": 9e-05,
"loss": 2.108,
"step": 9
},
{
"epoch": 0.06756756756756757,
"grad_norm": 2.2052178382873535,
"learning_rate": 0.0001,
"loss": 2.0193,
"step": 10
},
{
"epoch": 0.07432432432432433,
"grad_norm": 1.8947843313217163,
"learning_rate": 9.999316524962345e-05,
"loss": 2.2201,
"step": 11
},
{
"epoch": 0.08108108108108109,
"grad_norm": 1.5539779663085938,
"learning_rate": 9.997266286704631e-05,
"loss": 1.7039,
"step": 12
},
{
"epoch": 0.08783783783783784,
"grad_norm": 1.84231698513031,
"learning_rate": 9.993849845741524e-05,
"loss": 1.7398,
"step": 13
},
{
"epoch": 0.0945945945945946,
"grad_norm": 1.828019380569458,
"learning_rate": 9.989068136093873e-05,
"loss": 1.8482,
"step": 14
},
{
"epoch": 0.10135135135135136,
"grad_norm": 1.671506643295288,
"learning_rate": 9.98292246503335e-05,
"loss": 1.9443,
"step": 15
},
{
"epoch": 0.10810810810810811,
"grad_norm": 1.468369722366333,
"learning_rate": 9.975414512725057e-05,
"loss": 1.8729,
"step": 16
},
{
"epoch": 0.11486486486486487,
"grad_norm": 1.5108083486557007,
"learning_rate": 9.966546331768191e-05,
"loss": 1.6741,
"step": 17
},
{
"epoch": 0.12162162162162163,
"grad_norm": 1.6598519086837769,
"learning_rate": 9.956320346634876e-05,
"loss": 1.8642,
"step": 18
},
{
"epoch": 0.12837837837837837,
"grad_norm": 1.6918882131576538,
"learning_rate": 9.944739353007344e-05,
"loss": 1.8382,
"step": 19
},
{
"epoch": 0.13513513513513514,
"grad_norm": 1.6050759553909302,
"learning_rate": 9.931806517013612e-05,
"loss": 1.7366,
"step": 20
},
{
"epoch": 0.14189189189189189,
"grad_norm": 1.6648799180984497,
"learning_rate": 9.917525374361912e-05,
"loss": 1.8261,
"step": 21
},
{
"epoch": 0.14864864864864866,
"grad_norm": 1.6134958267211914,
"learning_rate": 9.901899829374047e-05,
"loss": 1.7829,
"step": 22
},
{
"epoch": 0.1554054054054054,
"grad_norm": 2.065173625946045,
"learning_rate": 9.884934153917997e-05,
"loss": 1.9168,
"step": 23
},
{
"epoch": 0.16216216216216217,
"grad_norm": 1.8863788843154907,
"learning_rate": 9.86663298624003e-05,
"loss": 1.853,
"step": 24
},
{
"epoch": 0.16891891891891891,
"grad_norm": 1.7413650751113892,
"learning_rate": 9.847001329696653e-05,
"loss": 1.8379,
"step": 25
},
{
"epoch": 0.17567567567567569,
"grad_norm": 2.1949267387390137,
"learning_rate": 9.826044551386744e-05,
"loss": 1.9647,
"step": 26
},
{
"epoch": 0.18243243243243243,
"grad_norm": 1.8597412109375,
"learning_rate": 9.803768380684242e-05,
"loss": 1.8375,
"step": 27
},
{
"epoch": 0.1891891891891892,
"grad_norm": 1.9108561277389526,
"learning_rate": 9.780178907671789e-05,
"loss": 1.7963,
"step": 28
},
{
"epoch": 0.19594594594594594,
"grad_norm": 1.9742248058319092,
"learning_rate": 9.755282581475769e-05,
"loss": 1.8186,
"step": 29
},
{
"epoch": 0.20270270270270271,
"grad_norm": 2.1315524578094482,
"learning_rate": 9.729086208503174e-05,
"loss": 1.7129,
"step": 30
},
{
"epoch": 0.20945945945945946,
"grad_norm": 2.3003602027893066,
"learning_rate": 9.701596950580806e-05,
"loss": 1.8527,
"step": 31
},
{
"epoch": 0.21621621621621623,
"grad_norm": 2.4031295776367188,
"learning_rate": 9.672822322997305e-05,
"loss": 1.739,
"step": 32
},
{
"epoch": 0.22297297297297297,
"grad_norm": 2.5433454513549805,
"learning_rate": 9.642770192448536e-05,
"loss": 1.8151,
"step": 33
},
{
"epoch": 0.22972972972972974,
"grad_norm": 2.519287347793579,
"learning_rate": 9.611448774886924e-05,
"loss": 1.962,
"step": 34
},
{
"epoch": 0.23648648648648649,
"grad_norm": 3.300830125808716,
"learning_rate": 9.578866633275288e-05,
"loss": 1.8442,
"step": 35
},
{
"epoch": 0.24324324324324326,
"grad_norm": 2.7878737449645996,
"learning_rate": 9.545032675245813e-05,
"loss": 1.7497,
"step": 36
},
{
"epoch": 0.25,
"grad_norm": 3.9603471755981445,
"learning_rate": 9.509956150664796e-05,
"loss": 2.1078,
"step": 37
},
{
"epoch": 0.25675675675675674,
"grad_norm": 2.3182380199432373,
"learning_rate": 9.473646649103818e-05,
"loss": 2.2206,
"step": 38
},
{
"epoch": 0.2635135135135135,
"grad_norm": 1.6530444622039795,
"learning_rate": 9.43611409721806e-05,
"loss": 2.1639,
"step": 39
},
{
"epoch": 0.2702702702702703,
"grad_norm": 1.4002788066864014,
"learning_rate": 9.397368756032445e-05,
"loss": 1.9908,
"step": 40
},
{
"epoch": 0.27702702702702703,
"grad_norm": 1.275628685951233,
"learning_rate": 9.357421218136386e-05,
"loss": 1.9277,
"step": 41
},
{
"epoch": 0.28378378378378377,
"grad_norm": 1.3413888216018677,
"learning_rate": 9.316282404787871e-05,
"loss": 1.938,
"step": 42
},
{
"epoch": 0.2905405405405405,
"grad_norm": 1.3855804204940796,
"learning_rate": 9.273963562927695e-05,
"loss": 2.0718,
"step": 43
},
{
"epoch": 0.2972972972972973,
"grad_norm": 1.3543145656585693,
"learning_rate": 9.230476262104677e-05,
"loss": 1.8385,
"step": 44
},
{
"epoch": 0.30405405405405406,
"grad_norm": 1.2580598592758179,
"learning_rate": 9.185832391312644e-05,
"loss": 1.6167,
"step": 45
},
{
"epoch": 0.3108108108108108,
"grad_norm": 1.4251524209976196,
"learning_rate": 9.140044155740101e-05,
"loss": 1.9111,
"step": 46
},
{
"epoch": 0.31756756756756754,
"grad_norm": 1.4891302585601807,
"learning_rate": 9.093124073433463e-05,
"loss": 1.7776,
"step": 47
},
{
"epoch": 0.32432432432432434,
"grad_norm": 1.366258978843689,
"learning_rate": 9.045084971874738e-05,
"loss": 1.8972,
"step": 48
},
{
"epoch": 0.3310810810810811,
"grad_norm": 1.3790669441223145,
"learning_rate": 8.995939984474624e-05,
"loss": 1.752,
"step": 49
},
{
"epoch": 0.33783783783783783,
"grad_norm": 1.4619343280792236,
"learning_rate": 8.945702546981969e-05,
"loss": 1.7721,
"step": 50
},
{
"epoch": 0.33783783783783783,
"eval_loss": 1.83683443069458,
"eval_runtime": 19.0928,
"eval_samples_per_second": 13.094,
"eval_steps_per_second": 3.3,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.54256789372928e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}