TracyTank's picture
Training in progress, step 51, checkpoint
d126e6c verified
{
"best_metric": 1.5307759046554565,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 3.0,
"eval_steps": 50,
"global_step": 51,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.058823529411764705,
"grad_norm": 0.23441748321056366,
"learning_rate": 1e-05,
"loss": 1.7143,
"step": 1
},
{
"epoch": 0.058823529411764705,
"eval_loss": 1.7731285095214844,
"eval_runtime": 25.6255,
"eval_samples_per_second": 4.488,
"eval_steps_per_second": 0.312,
"step": 1
},
{
"epoch": 0.11764705882352941,
"grad_norm": 0.2995237708091736,
"learning_rate": 2e-05,
"loss": 1.7333,
"step": 2
},
{
"epoch": 0.17647058823529413,
"grad_norm": 0.3397664427757263,
"learning_rate": 3e-05,
"loss": 1.7528,
"step": 3
},
{
"epoch": 0.23529411764705882,
"grad_norm": 0.3930438756942749,
"learning_rate": 4e-05,
"loss": 1.8381,
"step": 4
},
{
"epoch": 0.29411764705882354,
"grad_norm": 0.2326570302248001,
"learning_rate": 5e-05,
"loss": 1.6759,
"step": 5
},
{
"epoch": 0.35294117647058826,
"grad_norm": 0.3094904124736786,
"learning_rate": 6e-05,
"loss": 1.7455,
"step": 6
},
{
"epoch": 0.4117647058823529,
"grad_norm": 0.3576761782169342,
"learning_rate": 7e-05,
"loss": 1.7579,
"step": 7
},
{
"epoch": 0.47058823529411764,
"grad_norm": 0.3952060341835022,
"learning_rate": 8e-05,
"loss": 1.7631,
"step": 8
},
{
"epoch": 0.5294117647058824,
"grad_norm": 0.17181868851184845,
"learning_rate": 9e-05,
"loss": 1.6668,
"step": 9
},
{
"epoch": 0.5882352941176471,
"grad_norm": 0.2766295373439789,
"learning_rate": 0.0001,
"loss": 1.6894,
"step": 10
},
{
"epoch": 0.6470588235294118,
"grad_norm": 0.3067605495452881,
"learning_rate": 9.985329005918702e-05,
"loss": 1.6758,
"step": 11
},
{
"epoch": 0.7058823529411765,
"grad_norm": 0.30695968866348267,
"learning_rate": 9.941402118901744e-05,
"loss": 1.7233,
"step": 12
},
{
"epoch": 0.7647058823529411,
"grad_norm": 0.23806191980838776,
"learning_rate": 9.868477119388896e-05,
"loss": 1.6151,
"step": 13
},
{
"epoch": 0.8235294117647058,
"grad_norm": 0.252119779586792,
"learning_rate": 9.766981960274653e-05,
"loss": 1.6217,
"step": 14
},
{
"epoch": 0.8823529411764706,
"grad_norm": 0.2693735659122467,
"learning_rate": 9.637512255510475e-05,
"loss": 1.6265,
"step": 15
},
{
"epoch": 0.9411764705882353,
"grad_norm": 0.29563093185424805,
"learning_rate": 9.480827784805278e-05,
"loss": 1.6578,
"step": 16
},
{
"epoch": 1.0,
"grad_norm": 0.22258791327476501,
"learning_rate": 9.297848034936006e-05,
"loss": 1.5968,
"step": 17
},
{
"epoch": 1.0588235294117647,
"grad_norm": 0.2250705063343048,
"learning_rate": 9.089646803833589e-05,
"loss": 1.5776,
"step": 18
},
{
"epoch": 1.1176470588235294,
"grad_norm": 0.24266603589057922,
"learning_rate": 8.857445899109715e-05,
"loss": 1.6073,
"step": 19
},
{
"epoch": 1.1764705882352942,
"grad_norm": 0.27698013186454773,
"learning_rate": 8.602607968003935e-05,
"loss": 1.603,
"step": 20
},
{
"epoch": 1.2352941176470589,
"grad_norm": 0.2971300184726715,
"learning_rate": 8.326628500827826e-05,
"loss": 1.5675,
"step": 21
},
{
"epoch": 1.2941176470588236,
"grad_norm": 0.1933954358100891,
"learning_rate": 8.03112705483319e-05,
"loss": 1.5862,
"step": 22
},
{
"epoch": 1.3529411764705883,
"grad_norm": 0.22832177579402924,
"learning_rate": 7.717837750006106e-05,
"loss": 1.5411,
"step": 23
},
{
"epoch": 1.4117647058823528,
"grad_norm": 0.2414349913597107,
"learning_rate": 7.388599092561315e-05,
"loss": 1.5592,
"step": 24
},
{
"epoch": 1.4705882352941178,
"grad_norm": 0.29096826910972595,
"learning_rate": 7.045343185856701e-05,
"loss": 1.597,
"step": 25
},
{
"epoch": 1.5294117647058822,
"grad_norm": 0.18562051653862,
"learning_rate": 6.690084392042513e-05,
"loss": 1.5531,
"step": 26
},
{
"epoch": 1.5882352941176472,
"grad_norm": 0.23579668998718262,
"learning_rate": 6.32490751098331e-05,
"loss": 1.5509,
"step": 27
},
{
"epoch": 1.6470588235294117,
"grad_norm": 0.2646644711494446,
"learning_rate": 5.951955545823342e-05,
"loss": 1.5151,
"step": 28
},
{
"epoch": 1.7058823529411766,
"grad_norm": 0.3131634294986725,
"learning_rate": 5.573417126992003e-05,
"loss": 1.5696,
"step": 29
},
{
"epoch": 1.7647058823529411,
"grad_norm": 0.17213383316993713,
"learning_rate": 5.191513668450178e-05,
"loss": 1.5437,
"step": 30
},
{
"epoch": 1.8235294117647058,
"grad_norm": 0.22894638776779175,
"learning_rate": 4.8084863315498234e-05,
"loss": 1.5117,
"step": 31
},
{
"epoch": 1.8823529411764706,
"grad_norm": 0.2376885563135147,
"learning_rate": 4.4265828730079987e-05,
"loss": 1.5042,
"step": 32
},
{
"epoch": 1.9411764705882353,
"grad_norm": 0.28285500407218933,
"learning_rate": 4.0480444541766576e-05,
"loss": 1.5944,
"step": 33
},
{
"epoch": 2.0,
"grad_norm": 0.1876649260520935,
"learning_rate": 3.675092489016693e-05,
"loss": 1.5096,
"step": 34
},
{
"epoch": 2.0588235294117645,
"grad_norm": 0.16908113658428192,
"learning_rate": 3.309915607957487e-05,
"loss": 1.4847,
"step": 35
},
{
"epoch": 2.1176470588235294,
"grad_norm": 0.23162907361984253,
"learning_rate": 2.9546568141433006e-05,
"loss": 1.529,
"step": 36
},
{
"epoch": 2.176470588235294,
"grad_norm": 0.2607622742652893,
"learning_rate": 2.6114009074386846e-05,
"loss": 1.5385,
"step": 37
},
{
"epoch": 2.235294117647059,
"grad_norm": 0.3039644658565521,
"learning_rate": 2.282162249993895e-05,
"loss": 1.5517,
"step": 38
},
{
"epoch": 2.2941176470588234,
"grad_norm": 0.16194254159927368,
"learning_rate": 1.9688729451668114e-05,
"loss": 1.5257,
"step": 39
},
{
"epoch": 2.3529411764705883,
"grad_norm": 0.22298642992973328,
"learning_rate": 1.673371499172174e-05,
"loss": 1.5088,
"step": 40
},
{
"epoch": 2.411764705882353,
"grad_norm": 0.24472153186798096,
"learning_rate": 1.3973920319960655e-05,
"loss": 1.5153,
"step": 41
},
{
"epoch": 2.4705882352941178,
"grad_norm": 0.285709023475647,
"learning_rate": 1.1425541008902851e-05,
"loss": 1.5514,
"step": 42
},
{
"epoch": 2.5294117647058822,
"grad_norm": 0.16069068014621735,
"learning_rate": 9.103531961664118e-06,
"loss": 1.5179,
"step": 43
},
{
"epoch": 2.588235294117647,
"grad_norm": 0.22797466814517975,
"learning_rate": 7.0215196506399515e-06,
"loss": 1.4949,
"step": 44
},
{
"epoch": 2.6470588235294117,
"grad_norm": 0.25084009766578674,
"learning_rate": 5.191722151947226e-06,
"loss": 1.497,
"step": 45
},
{
"epoch": 2.7058823529411766,
"grad_norm": 0.3240495026111603,
"learning_rate": 3.6248774448952695e-06,
"loss": 1.5205,
"step": 46
},
{
"epoch": 2.764705882352941,
"grad_norm": 0.16425733268260956,
"learning_rate": 2.330180397253473e-06,
"loss": 1.52,
"step": 47
},
{
"epoch": 2.8235294117647056,
"grad_norm": 0.22014911472797394,
"learning_rate": 1.3152288061110518e-06,
"loss": 1.4788,
"step": 48
},
{
"epoch": 2.8823529411764706,
"grad_norm": 0.23008312284946442,
"learning_rate": 5.859788109825793e-07,
"loss": 1.4741,
"step": 49
},
{
"epoch": 2.9411764705882355,
"grad_norm": 0.2939811646938324,
"learning_rate": 1.4670994081297795e-07,
"loss": 1.5087,
"step": 50
},
{
"epoch": 2.9411764705882355,
"eval_loss": 1.5307759046554565,
"eval_runtime": 7.1997,
"eval_samples_per_second": 15.973,
"eval_steps_per_second": 1.111,
"step": 50
},
{
"epoch": 3.0,
"grad_norm": 0.1972215622663498,
"learning_rate": 0.0,
"loss": 1.485,
"step": 51
}
],
"logging_steps": 1,
"max_steps": 51,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": true
},
"attributes": {}
}
},
"total_flos": 1.435595821809664e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}