aleegis10's picture
Training in progress, step 50, checkpoint
5a71267 verified
raw
history blame
10 kB
{
"best_metric": 0.40518489480018616,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.006744225257123588,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00013488450514247176,
"grad_norm": 0.7375573515892029,
"learning_rate": 1e-05,
"loss": 0.619,
"step": 1
},
{
"epoch": 0.00013488450514247176,
"eval_loss": 0.5535552501678467,
"eval_runtime": 262.1617,
"eval_samples_per_second": 47.631,
"eval_steps_per_second": 11.909,
"step": 1
},
{
"epoch": 0.0002697690102849435,
"grad_norm": 0.7183876633644104,
"learning_rate": 2e-05,
"loss": 0.6297,
"step": 2
},
{
"epoch": 0.00040465351542741526,
"grad_norm": 0.6348766088485718,
"learning_rate": 3e-05,
"loss": 0.5755,
"step": 3
},
{
"epoch": 0.000539538020569887,
"grad_norm": 0.5318180322647095,
"learning_rate": 4e-05,
"loss": 0.5212,
"step": 4
},
{
"epoch": 0.0006744225257123588,
"grad_norm": 0.4897218644618988,
"learning_rate": 5e-05,
"loss": 0.4963,
"step": 5
},
{
"epoch": 0.0008093070308548305,
"grad_norm": 0.4619118273258209,
"learning_rate": 6e-05,
"loss": 0.4524,
"step": 6
},
{
"epoch": 0.0009441915359973024,
"grad_norm": 0.4772312641143799,
"learning_rate": 7e-05,
"loss": 0.4057,
"step": 7
},
{
"epoch": 0.001079076041139774,
"grad_norm": 0.49830466508865356,
"learning_rate": 8e-05,
"loss": 0.4654,
"step": 8
},
{
"epoch": 0.0012139605462822458,
"grad_norm": 0.5150027275085449,
"learning_rate": 9e-05,
"loss": 0.4528,
"step": 9
},
{
"epoch": 0.0013488450514247176,
"grad_norm": 0.4883197247982025,
"learning_rate": 0.0001,
"loss": 0.4683,
"step": 10
},
{
"epoch": 0.0014837295565671893,
"grad_norm": 0.5665213465690613,
"learning_rate": 9.999316524962345e-05,
"loss": 0.5624,
"step": 11
},
{
"epoch": 0.001618614061709661,
"grad_norm": 0.4944498836994171,
"learning_rate": 9.997266286704631e-05,
"loss": 0.5727,
"step": 12
},
{
"epoch": 0.0017534985668521328,
"grad_norm": 0.457690566778183,
"learning_rate": 9.993849845741524e-05,
"loss": 0.4831,
"step": 13
},
{
"epoch": 0.0018883830719946047,
"grad_norm": 0.4723391830921173,
"learning_rate": 9.989068136093873e-05,
"loss": 0.4807,
"step": 14
},
{
"epoch": 0.0020232675771370764,
"grad_norm": 0.46450331807136536,
"learning_rate": 9.98292246503335e-05,
"loss": 0.5013,
"step": 15
},
{
"epoch": 0.002158152082279548,
"grad_norm": 0.4473508596420288,
"learning_rate": 9.975414512725057e-05,
"loss": 0.4734,
"step": 16
},
{
"epoch": 0.00229303658742202,
"grad_norm": 0.44036874175071716,
"learning_rate": 9.966546331768191e-05,
"loss": 0.4924,
"step": 17
},
{
"epoch": 0.0024279210925644916,
"grad_norm": 0.43315592408180237,
"learning_rate": 9.956320346634876e-05,
"loss": 0.4552,
"step": 18
},
{
"epoch": 0.0025628055977069634,
"grad_norm": 0.42718714475631714,
"learning_rate": 9.944739353007344e-05,
"loss": 0.4542,
"step": 19
},
{
"epoch": 0.002697690102849435,
"grad_norm": 0.42780622839927673,
"learning_rate": 9.931806517013612e-05,
"loss": 0.4212,
"step": 20
},
{
"epoch": 0.002832574607991907,
"grad_norm": 0.48322251439094543,
"learning_rate": 9.917525374361912e-05,
"loss": 0.4701,
"step": 21
},
{
"epoch": 0.0029674591131343786,
"grad_norm": 0.4247865080833435,
"learning_rate": 9.901899829374047e-05,
"loss": 0.4139,
"step": 22
},
{
"epoch": 0.0031023436182768503,
"grad_norm": 0.46833139657974243,
"learning_rate": 9.884934153917997e-05,
"loss": 0.4707,
"step": 23
},
{
"epoch": 0.003237228123419322,
"grad_norm": 0.4637615382671356,
"learning_rate": 9.86663298624003e-05,
"loss": 0.4475,
"step": 24
},
{
"epoch": 0.003372112628561794,
"grad_norm": 0.47445815801620483,
"learning_rate": 9.847001329696653e-05,
"loss": 0.427,
"step": 25
},
{
"epoch": 0.0035069971337042655,
"grad_norm": 0.4429916441440582,
"learning_rate": 9.826044551386744e-05,
"loss": 0.3974,
"step": 26
},
{
"epoch": 0.0036418816388467377,
"grad_norm": 0.4321354031562805,
"learning_rate": 9.803768380684242e-05,
"loss": 0.4111,
"step": 27
},
{
"epoch": 0.0037767661439892094,
"grad_norm": 0.42871013283729553,
"learning_rate": 9.780178907671789e-05,
"loss": 0.3995,
"step": 28
},
{
"epoch": 0.003911650649131681,
"grad_norm": 0.4513198435306549,
"learning_rate": 9.755282581475769e-05,
"loss": 0.3615,
"step": 29
},
{
"epoch": 0.004046535154274153,
"grad_norm": 0.4309406280517578,
"learning_rate": 9.729086208503174e-05,
"loss": 0.3835,
"step": 30
},
{
"epoch": 0.004181419659416624,
"grad_norm": 0.4923899173736572,
"learning_rate": 9.701596950580806e-05,
"loss": 0.4012,
"step": 31
},
{
"epoch": 0.004316304164559096,
"grad_norm": 0.4715842008590698,
"learning_rate": 9.672822322997305e-05,
"loss": 0.344,
"step": 32
},
{
"epoch": 0.004451188669701568,
"grad_norm": 0.4990752041339874,
"learning_rate": 9.642770192448536e-05,
"loss": 0.414,
"step": 33
},
{
"epoch": 0.00458607317484404,
"grad_norm": 0.5114120841026306,
"learning_rate": 9.611448774886924e-05,
"loss": 0.4346,
"step": 34
},
{
"epoch": 0.004720957679986511,
"grad_norm": 0.5033982396125793,
"learning_rate": 9.578866633275288e-05,
"loss": 0.3961,
"step": 35
},
{
"epoch": 0.004855842185128983,
"grad_norm": 0.5176622271537781,
"learning_rate": 9.545032675245813e-05,
"loss": 0.3634,
"step": 36
},
{
"epoch": 0.0049907266902714555,
"grad_norm": 0.4883003234863281,
"learning_rate": 9.509956150664796e-05,
"loss": 0.3363,
"step": 37
},
{
"epoch": 0.005125611195413927,
"grad_norm": 0.49539199471473694,
"learning_rate": 9.473646649103818e-05,
"loss": 0.3966,
"step": 38
},
{
"epoch": 0.005260495700556399,
"grad_norm": 0.5086225271224976,
"learning_rate": 9.43611409721806e-05,
"loss": 0.3377,
"step": 39
},
{
"epoch": 0.00539538020569887,
"grad_norm": 0.47139525413513184,
"learning_rate": 9.397368756032445e-05,
"loss": 0.325,
"step": 40
},
{
"epoch": 0.005530264710841342,
"grad_norm": 0.5271187424659729,
"learning_rate": 9.357421218136386e-05,
"loss": 0.3476,
"step": 41
},
{
"epoch": 0.005665149215983814,
"grad_norm": 0.5539581179618835,
"learning_rate": 9.316282404787871e-05,
"loss": 0.3642,
"step": 42
},
{
"epoch": 0.005800033721126286,
"grad_norm": 0.5593342781066895,
"learning_rate": 9.273963562927695e-05,
"loss": 0.3203,
"step": 43
},
{
"epoch": 0.005934918226268757,
"grad_norm": 0.563308835029602,
"learning_rate": 9.230476262104677e-05,
"loss": 0.325,
"step": 44
},
{
"epoch": 0.006069802731411229,
"grad_norm": 0.5519070625305176,
"learning_rate": 9.185832391312644e-05,
"loss": 0.3488,
"step": 45
},
{
"epoch": 0.006204687236553701,
"grad_norm": 0.5657252669334412,
"learning_rate": 9.140044155740101e-05,
"loss": 0.3344,
"step": 46
},
{
"epoch": 0.006339571741696173,
"grad_norm": 0.5870583057403564,
"learning_rate": 9.093124073433463e-05,
"loss": 0.3087,
"step": 47
},
{
"epoch": 0.006474456246838644,
"grad_norm": 0.6925362944602966,
"learning_rate": 9.045084971874738e-05,
"loss": 0.361,
"step": 48
},
{
"epoch": 0.006609340751981116,
"grad_norm": 0.6307148337364197,
"learning_rate": 8.995939984474624e-05,
"loss": 0.3025,
"step": 49
},
{
"epoch": 0.006744225257123588,
"grad_norm": 0.7876100540161133,
"learning_rate": 8.945702546981969e-05,
"loss": 0.2675,
"step": 50
},
{
"epoch": 0.006744225257123588,
"eval_loss": 0.40518489480018616,
"eval_runtime": 262.0707,
"eval_samples_per_second": 47.647,
"eval_steps_per_second": 11.913,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 4791659107713024.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}