antimage88's picture
Training in progress, step 57, checkpoint
65bd990 verified
Raw History Blame Contribute Delete
11 kB
{
"best_metric": 1.1817097663879395,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 3.0,
"eval_steps": 50,
"global_step": 57,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05263157894736842,
"grad_norm": 5.714753150939941,
"learning_rate": 1e-05,
"loss": 1.8152,
"step": 1
},
{
"epoch": 0.05263157894736842,
"eval_loss": 2.4003829956054688,
"eval_runtime": 1.4264,
"eval_samples_per_second": 22.434,
"eval_steps_per_second": 5.608,
"step": 1
},
{
"epoch": 0.10526315789473684,
"grad_norm": 7.170670986175537,
"learning_rate": 2e-05,
"loss": 2.2306,
"step": 2
},
{
"epoch": 0.15789473684210525,
"grad_norm": 7.550725936889648,
"learning_rate": 3e-05,
"loss": 2.4062,
"step": 3
},
{
"epoch": 0.21052631578947367,
"grad_norm": 6.948938846588135,
"learning_rate": 4e-05,
"loss": 2.2318,
"step": 4
},
{
"epoch": 0.2631578947368421,
"grad_norm": 6.083446502685547,
"learning_rate": 5e-05,
"loss": 1.2827,
"step": 5
},
{
"epoch": 0.3157894736842105,
"grad_norm": 5.913970470428467,
"learning_rate": 6e-05,
"loss": 1.371,
"step": 6
},
{
"epoch": 0.3684210526315789,
"grad_norm": 5.238213062286377,
"learning_rate": 7e-05,
"loss": 1.5717,
"step": 7
},
{
"epoch": 0.42105263157894735,
"grad_norm": 5.236299991607666,
"learning_rate": 8e-05,
"loss": 1.3621,
"step": 8
},
{
"epoch": 0.47368421052631576,
"grad_norm": 2.496065378189087,
"learning_rate": 9e-05,
"loss": 1.143,
"step": 9
},
{
"epoch": 0.5263157894736842,
"grad_norm": 2.8024847507476807,
"learning_rate": 0.0001,
"loss": 1.2504,
"step": 10
},
{
"epoch": 0.5789473684210527,
"grad_norm": 3.0046355724334717,
"learning_rate": 9.988834393115767e-05,
"loss": 1.2389,
"step": 11
},
{
"epoch": 0.631578947368421,
"grad_norm": 3.0082316398620605,
"learning_rate": 9.9553874407739e-05,
"loss": 1.2786,
"step": 12
},
{
"epoch": 0.6842105263157895,
"grad_norm": 2.118980646133423,
"learning_rate": 9.899808525182935e-05,
"loss": 1.2954,
"step": 13
},
{
"epoch": 0.7368421052631579,
"grad_norm": 2.031477689743042,
"learning_rate": 9.822345875271883e-05,
"loss": 0.9797,
"step": 14
},
{
"epoch": 0.7894736842105263,
"grad_norm": 2.3263585567474365,
"learning_rate": 9.723345458039594e-05,
"loss": 1.2429,
"step": 15
},
{
"epoch": 0.8421052631578947,
"grad_norm": 2.6109251976013184,
"learning_rate": 9.603249433382144e-05,
"loss": 1.2715,
"step": 16
},
{
"epoch": 0.8947368421052632,
"grad_norm": 1.9126944541931152,
"learning_rate": 9.462594179299406e-05,
"loss": 1.109,
"step": 17
},
{
"epoch": 0.9473684210526315,
"grad_norm": 1.9470820426940918,
"learning_rate": 9.302007896300698e-05,
"loss": 0.8364,
"step": 18
},
{
"epoch": 1.0,
"grad_norm": 2.2464423179626465,
"learning_rate": 9.122207801708802e-05,
"loss": 1.1474,
"step": 19
},
{
"epoch": 1.0526315789473684,
"grad_norm": 1.3209232091903687,
"learning_rate": 8.923996926393305e-05,
"loss": 0.9024,
"step": 20
},
{
"epoch": 1.1052631578947367,
"grad_norm": 1.6488995552062988,
"learning_rate": 8.708260528239788e-05,
"loss": 0.8782,
"step": 21
},
{
"epoch": 1.1578947368421053,
"grad_norm": 1.6716432571411133,
"learning_rate": 8.475962138373213e-05,
"loss": 0.8521,
"step": 22
},
{
"epoch": 1.2105263157894737,
"grad_norm": 2.1739349365234375,
"learning_rate": 8.228139257794012e-05,
"loss": 0.9933,
"step": 23
},
{
"epoch": 1.263157894736842,
"grad_norm": 1.4730769395828247,
"learning_rate": 7.965898723646776e-05,
"loss": 0.7727,
"step": 24
},
{
"epoch": 1.3157894736842106,
"grad_norm": 1.5656155347824097,
"learning_rate": 7.690411765816864e-05,
"loss": 0.8817,
"step": 25
},
{
"epoch": 1.368421052631579,
"grad_norm": 2.1506686210632324,
"learning_rate": 7.402908775933419e-05,
"loss": 1.0105,
"step": 26
},
{
"epoch": 1.4210526315789473,
"grad_norm": 2.0018692016601562,
"learning_rate": 7.104673812141675e-05,
"loss": 0.7928,
"step": 27
},
{
"epoch": 1.4736842105263157,
"grad_norm": 1.695372223854065,
"learning_rate": 6.797038864187564e-05,
"loss": 0.8946,
"step": 28
},
{
"epoch": 1.526315789473684,
"grad_norm": 1.8244125843048096,
"learning_rate": 6.481377904428171e-05,
"loss": 0.8284,
"step": 29
},
{
"epoch": 1.5789473684210527,
"grad_norm": 1.7244329452514648,
"learning_rate": 6.159100751337642e-05,
"loss": 0.7186,
"step": 30
},
{
"epoch": 1.631578947368421,
"grad_norm": 2.0243990421295166,
"learning_rate": 5.831646772915651e-05,
"loss": 0.8093,
"step": 31
},
{
"epoch": 1.6842105263157894,
"grad_norm": 1.6297742128372192,
"learning_rate": 5.5004784581204927e-05,
"loss": 0.8709,
"step": 32
},
{
"epoch": 1.736842105263158,
"grad_norm": 1.8952237367630005,
"learning_rate": 5.167074885038373e-05,
"loss": 0.8952,
"step": 33
},
{
"epoch": 1.7894736842105263,
"grad_norm": 1.7852932214736938,
"learning_rate": 4.832925114961629e-05,
"loss": 0.7839,
"step": 34
},
{
"epoch": 1.8421052631578947,
"grad_norm": 2.1525204181671143,
"learning_rate": 4.4995215418795085e-05,
"loss": 0.8763,
"step": 35
},
{
"epoch": 1.8947368421052633,
"grad_norm": 1.8198322057724,
"learning_rate": 4.1683532270843504e-05,
"loss": 0.8486,
"step": 36
},
{
"epoch": 1.9473684210526314,
"grad_norm": 1.5310567617416382,
"learning_rate": 3.840899248662358e-05,
"loss": 0.5251,
"step": 37
},
{
"epoch": 2.0,
"grad_norm": 2.179245710372925,
"learning_rate": 3.5186220955718306e-05,
"loss": 0.8381,
"step": 38
},
{
"epoch": 2.0526315789473686,
"grad_norm": 1.1245640516281128,
"learning_rate": 3.202961135812437e-05,
"loss": 0.6164,
"step": 39
},
{
"epoch": 2.1052631578947367,
"grad_norm": 1.41566002368927,
"learning_rate": 2.895326187858326e-05,
"loss": 0.6059,
"step": 40
},
{
"epoch": 2.1578947368421053,
"grad_norm": 1.5508769750595093,
"learning_rate": 2.5970912240665813e-05,
"loss": 0.6455,
"step": 41
},
{
"epoch": 2.2105263157894735,
"grad_norm": 1.7090671062469482,
"learning_rate": 2.3095882341831372e-05,
"loss": 0.5792,
"step": 42
},
{
"epoch": 2.263157894736842,
"grad_norm": 1.374485731124878,
"learning_rate": 2.0341012763532243e-05,
"loss": 0.6782,
"step": 43
},
{
"epoch": 2.3157894736842106,
"grad_norm": 1.590584397315979,
"learning_rate": 1.771860742205988e-05,
"loss": 0.7556,
"step": 44
},
{
"epoch": 2.3684210526315788,
"grad_norm": 1.459409236907959,
"learning_rate": 1.5240378616267886e-05,
"loss": 0.4689,
"step": 45
},
{
"epoch": 2.4210526315789473,
"grad_norm": 1.5467756986618042,
"learning_rate": 1.2917394717602121e-05,
"loss": 0.4195,
"step": 46
},
{
"epoch": 2.473684210526316,
"grad_norm": 1.3657021522521973,
"learning_rate": 1.0760030736066951e-05,
"loss": 0.4721,
"step": 47
},
{
"epoch": 2.526315789473684,
"grad_norm": 1.7539397478103638,
"learning_rate": 8.777921982911996e-06,
"loss": 0.5767,
"step": 48
},
{
"epoch": 2.5789473684210527,
"grad_norm": 1.5453059673309326,
"learning_rate": 6.979921036993042e-06,
"loss": 0.6237,
"step": 49
},
{
"epoch": 2.6315789473684212,
"grad_norm": 2.2058823108673096,
"learning_rate": 5.374058207005944e-06,
"loss": 0.6392,
"step": 50
},
{
"epoch": 2.6315789473684212,
"eval_loss": 1.1817097663879395,
"eval_runtime": 1.4393,
"eval_samples_per_second": 22.234,
"eval_steps_per_second": 5.558,
"step": 50
},
{
"epoch": 2.6842105263157894,
"grad_norm": 1.3148783445358276,
"learning_rate": 3.967505666178556e-06,
"loss": 0.5752,
"step": 51
},
{
"epoch": 2.736842105263158,
"grad_norm": 1.693260669708252,
"learning_rate": 2.7665454196040664e-06,
"loss": 0.5934,
"step": 52
},
{
"epoch": 2.7894736842105265,
"grad_norm": 1.6923569440841675,
"learning_rate": 1.7765412472811771e-06,
"loss": 0.6168,
"step": 53
},
{
"epoch": 2.8421052631578947,
"grad_norm": 1.6930750608444214,
"learning_rate": 1.0019147481706625e-06,
"loss": 0.5091,
"step": 54
},
{
"epoch": 2.8947368421052633,
"grad_norm": 1.4638423919677734,
"learning_rate": 4.461255922609986e-07,
"loss": 0.634,
"step": 55
},
{
"epoch": 2.9473684210526314,
"grad_norm": 1.329147219657898,
"learning_rate": 1.1165606884234181e-07,
"loss": 0.4201,
"step": 56
},
{
"epoch": 3.0,
"grad_norm": 1.8009886741638184,
"learning_rate": 0.0,
"loss": 0.5192,
"step": 57
}
],
"logging_steps": 1,
"max_steps": 57,
"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": 2.338589547115315e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}