0x1202's picture
Training in progress, step 50, checkpoint
4d08f87 verified
raw
history blame
9.88 kB
{
"best_metric": 1.066644549369812,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.35650623885918004,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0071301247771836,
"grad_norm": 1.0823220014572144,
"learning_rate": 1e-05,
"loss": 6.6569,
"step": 1
},
{
"epoch": 0.0071301247771836,
"eval_loss": 2.150402069091797,
"eval_runtime": 23.6394,
"eval_samples_per_second": 10.026,
"eval_steps_per_second": 1.269,
"step": 1
},
{
"epoch": 0.0142602495543672,
"grad_norm": 1.3017756938934326,
"learning_rate": 2e-05,
"loss": 7.4693,
"step": 2
},
{
"epoch": 0.0213903743315508,
"grad_norm": 1.8406498432159424,
"learning_rate": 3e-05,
"loss": 7.979,
"step": 3
},
{
"epoch": 0.0285204991087344,
"grad_norm": 1.9255220890045166,
"learning_rate": 4e-05,
"loss": 8.4457,
"step": 4
},
{
"epoch": 0.035650623885918005,
"grad_norm": 2.0620336532592773,
"learning_rate": 5e-05,
"loss": 8.2665,
"step": 5
},
{
"epoch": 0.0427807486631016,
"grad_norm": 2.0017974376678467,
"learning_rate": 6e-05,
"loss": 8.0234,
"step": 6
},
{
"epoch": 0.049910873440285206,
"grad_norm": 1.9698922634124756,
"learning_rate": 7e-05,
"loss": 7.7345,
"step": 7
},
{
"epoch": 0.0570409982174688,
"grad_norm": 2.260509729385376,
"learning_rate": 8e-05,
"loss": 7.4526,
"step": 8
},
{
"epoch": 0.06417112299465241,
"grad_norm": 2.485492467880249,
"learning_rate": 9e-05,
"loss": 7.1721,
"step": 9
},
{
"epoch": 0.07130124777183601,
"grad_norm": 2.157437801361084,
"learning_rate": 0.0001,
"loss": 6.8119,
"step": 10
},
{
"epoch": 0.0784313725490196,
"grad_norm": 2.448948621749878,
"learning_rate": 9.99695413509548e-05,
"loss": 6.4423,
"step": 11
},
{
"epoch": 0.0855614973262032,
"grad_norm": 2.756315231323242,
"learning_rate": 9.987820251299122e-05,
"loss": 6.2086,
"step": 12
},
{
"epoch": 0.09269162210338681,
"grad_norm": 2.5967438220977783,
"learning_rate": 9.972609476841367e-05,
"loss": 6.0689,
"step": 13
},
{
"epoch": 0.09982174688057041,
"grad_norm": 2.21612548828125,
"learning_rate": 9.951340343707852e-05,
"loss": 5.4971,
"step": 14
},
{
"epoch": 0.10695187165775401,
"grad_norm": 2.2803194522857666,
"learning_rate": 9.924038765061042e-05,
"loss": 5.9092,
"step": 15
},
{
"epoch": 0.1140819964349376,
"grad_norm": 2.4728004932403564,
"learning_rate": 9.890738003669029e-05,
"loss": 6.0649,
"step": 16
},
{
"epoch": 0.12121212121212122,
"grad_norm": 2.0314323902130127,
"learning_rate": 9.851478631379982e-05,
"loss": 5.4864,
"step": 17
},
{
"epoch": 0.12834224598930483,
"grad_norm": 2.048257827758789,
"learning_rate": 9.806308479691595e-05,
"loss": 5.4174,
"step": 18
},
{
"epoch": 0.1354723707664884,
"grad_norm": 2.128129720687866,
"learning_rate": 9.755282581475769e-05,
"loss": 5.2619,
"step": 19
},
{
"epoch": 0.14260249554367202,
"grad_norm": 1.9913911819458008,
"learning_rate": 9.698463103929542e-05,
"loss": 5.0575,
"step": 20
},
{
"epoch": 0.1497326203208556,
"grad_norm": 1.9190443754196167,
"learning_rate": 9.635919272833938e-05,
"loss": 4.8892,
"step": 21
},
{
"epoch": 0.1568627450980392,
"grad_norm": 1.6445850133895874,
"learning_rate": 9.567727288213005e-05,
"loss": 4.5256,
"step": 22
},
{
"epoch": 0.16399286987522282,
"grad_norm": 1.8742074966430664,
"learning_rate": 9.493970231495835e-05,
"loss": 4.8064,
"step": 23
},
{
"epoch": 0.1711229946524064,
"grad_norm": 1.8904237747192383,
"learning_rate": 9.414737964294636e-05,
"loss": 4.7587,
"step": 24
},
{
"epoch": 0.17825311942959002,
"grad_norm": 1.9763126373291016,
"learning_rate": 9.330127018922194e-05,
"loss": 4.3992,
"step": 25
},
{
"epoch": 0.18538324420677363,
"grad_norm": 1.9289206266403198,
"learning_rate": 9.24024048078213e-05,
"loss": 4.2309,
"step": 26
},
{
"epoch": 0.1925133689839572,
"grad_norm": 1.7819998264312744,
"learning_rate": 9.145187862775209e-05,
"loss": 3.4531,
"step": 27
},
{
"epoch": 0.19964349376114082,
"grad_norm": 1.782440423965454,
"learning_rate": 9.045084971874738e-05,
"loss": 3.7593,
"step": 28
},
{
"epoch": 0.20677361853832443,
"grad_norm": 1.7480669021606445,
"learning_rate": 8.940053768033609e-05,
"loss": 3.5102,
"step": 29
},
{
"epoch": 0.21390374331550802,
"grad_norm": 2.0515565872192383,
"learning_rate": 8.83022221559489e-05,
"loss": 3.5653,
"step": 30
},
{
"epoch": 0.22103386809269163,
"grad_norm": 1.7866798639297485,
"learning_rate": 8.715724127386972e-05,
"loss": 3.3327,
"step": 31
},
{
"epoch": 0.2281639928698752,
"grad_norm": 2.0945322513580322,
"learning_rate": 8.596699001693255e-05,
"loss": 3.4173,
"step": 32
},
{
"epoch": 0.23529411764705882,
"grad_norm": 2.085531711578369,
"learning_rate": 8.473291852294987e-05,
"loss": 3.3953,
"step": 33
},
{
"epoch": 0.24242424242424243,
"grad_norm": 2.5686299800872803,
"learning_rate": 8.345653031794292e-05,
"loss": 3.7318,
"step": 34
},
{
"epoch": 0.24955436720142601,
"grad_norm": 3.195141077041626,
"learning_rate": 8.213938048432697e-05,
"loss": 3.3963,
"step": 35
},
{
"epoch": 0.25668449197860965,
"grad_norm": 3.8207287788391113,
"learning_rate": 8.07830737662829e-05,
"loss": 5.6455,
"step": 36
},
{
"epoch": 0.2638146167557932,
"grad_norm": 3.6521031856536865,
"learning_rate": 7.938926261462366e-05,
"loss": 6.3745,
"step": 37
},
{
"epoch": 0.2709447415329768,
"grad_norm": 3.1133363246917725,
"learning_rate": 7.795964517353735e-05,
"loss": 6.3022,
"step": 38
},
{
"epoch": 0.27807486631016043,
"grad_norm": 2.0272369384765625,
"learning_rate": 7.649596321166024e-05,
"loss": 6.0136,
"step": 39
},
{
"epoch": 0.28520499108734404,
"grad_norm": 1.4717522859573364,
"learning_rate": 7.500000000000001e-05,
"loss": 5.7502,
"step": 40
},
{
"epoch": 0.29233511586452765,
"grad_norm": 1.413915753364563,
"learning_rate": 7.347357813929454e-05,
"loss": 5.1095,
"step": 41
},
{
"epoch": 0.2994652406417112,
"grad_norm": 1.3348373174667358,
"learning_rate": 7.191855733945387e-05,
"loss": 4.7922,
"step": 42
},
{
"epoch": 0.3065953654188948,
"grad_norm": 1.3580721616744995,
"learning_rate": 7.033683215379002e-05,
"loss": 4.9455,
"step": 43
},
{
"epoch": 0.3137254901960784,
"grad_norm": 1.3433594703674316,
"learning_rate": 6.873032967079561e-05,
"loss": 4.675,
"step": 44
},
{
"epoch": 0.32085561497326204,
"grad_norm": 1.2860838174819946,
"learning_rate": 6.710100716628344e-05,
"loss": 4.2363,
"step": 45
},
{
"epoch": 0.32798573975044565,
"grad_norm": 1.2380250692367554,
"learning_rate": 6.545084971874738e-05,
"loss": 4.2934,
"step": 46
},
{
"epoch": 0.33511586452762926,
"grad_norm": 1.2230507135391235,
"learning_rate": 6.378186779084995e-05,
"loss": 4.8291,
"step": 47
},
{
"epoch": 0.3422459893048128,
"grad_norm": 1.3353351354599,
"learning_rate": 6.209609477998338e-05,
"loss": 4.2347,
"step": 48
},
{
"epoch": 0.3493761140819964,
"grad_norm": 1.3078246116638184,
"learning_rate": 6.0395584540887963e-05,
"loss": 4.2804,
"step": 49
},
{
"epoch": 0.35650623885918004,
"grad_norm": 1.3531790971755981,
"learning_rate": 5.868240888334653e-05,
"loss": 4.4055,
"step": 50
},
{
"epoch": 0.35650623885918004,
"eval_loss": 1.066644549369812,
"eval_runtime": 24.0327,
"eval_samples_per_second": 9.862,
"eval_steps_per_second": 1.248,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 6.719068728773837e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}