224 lines
5.6 KiB
JSON
224 lines
5.6 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0,
|
|
"eval_steps": 500,
|
|
"global_step": 1374,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.07285974499089254,
|
|
"grad_norm": 0.33655378222465515,
|
|
"learning_rate": 0.00019428152492668624,
|
|
"loss": 1.248601837158203,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.14571948998178508,
|
|
"grad_norm": 0.3381595313549042,
|
|
"learning_rate": 0.00018695014662756598,
|
|
"loss": 0.8999367523193359,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.2185792349726776,
|
|
"grad_norm": 0.30710718035697937,
|
|
"learning_rate": 0.00017961876832844575,
|
|
"loss": 0.8563268280029297,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.29143897996357016,
|
|
"grad_norm": 0.39056596159935,
|
|
"learning_rate": 0.0001722873900293255,
|
|
"loss": 0.8502767181396484,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.36429872495446264,
|
|
"grad_norm": 0.35749396681785583,
|
|
"learning_rate": 0.0001649560117302053,
|
|
"loss": 0.8379911804199218,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.4371584699453552,
|
|
"grad_norm": 0.41779738664627075,
|
|
"learning_rate": 0.00015762463343108504,
|
|
"loss": 0.8131264495849609,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5100182149362478,
|
|
"grad_norm": 0.40256431698799133,
|
|
"learning_rate": 0.0001502932551319648,
|
|
"loss": 0.8029293060302735,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.5828779599271403,
|
|
"grad_norm": 0.39221078157424927,
|
|
"learning_rate": 0.00014296187683284457,
|
|
"loss": 0.7728028106689453,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.6557377049180327,
|
|
"grad_norm": 0.3179788887500763,
|
|
"learning_rate": 0.00013563049853372434,
|
|
"loss": 0.775037841796875,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.7285974499089253,
|
|
"grad_norm": 0.4592280685901642,
|
|
"learning_rate": 0.0001282991202346041,
|
|
"loss": 0.7742440032958985,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.8014571948998178,
|
|
"grad_norm": 0.46030479669570923,
|
|
"learning_rate": 0.00012096774193548388,
|
|
"loss": 0.7653812408447266,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.8743169398907104,
|
|
"grad_norm": 0.47871556878089905,
|
|
"learning_rate": 0.00011363636363636365,
|
|
"loss": 0.7765991973876953,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.9471766848816029,
|
|
"grad_norm": 0.4337916076183319,
|
|
"learning_rate": 0.0001063049853372434,
|
|
"loss": 0.7484037017822266,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 1.018943533697632,
|
|
"grad_norm": 0.34845250844955444,
|
|
"learning_rate": 9.897360703812317e-05,
|
|
"loss": 0.710738525390625,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 1.0918032786885246,
|
|
"grad_norm": 0.5349538922309875,
|
|
"learning_rate": 9.164222873900293e-05,
|
|
"loss": 0.6187635040283204,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 1.164663023679417,
|
|
"grad_norm": 0.4864880442619324,
|
|
"learning_rate": 8.431085043988271e-05,
|
|
"loss": 0.640613784790039,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 1.2375227686703096,
|
|
"grad_norm": 0.5053865909576416,
|
|
"learning_rate": 7.697947214076246e-05,
|
|
"loss": 0.6253266906738282,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 1.3103825136612022,
|
|
"grad_norm": 0.5343588590621948,
|
|
"learning_rate": 6.964809384164224e-05,
|
|
"loss": 0.6396315383911133,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 1.3832422586520947,
|
|
"grad_norm": 0.46341976523399353,
|
|
"learning_rate": 6.2316715542522e-05,
|
|
"loss": 0.6397412490844726,
|
|
"step": 950
|
|
},
|
|
{
|
|
"epoch": 1.4561020036429873,
|
|
"grad_norm": 0.6249243021011353,
|
|
"learning_rate": 5.498533724340176e-05,
|
|
"loss": 0.6349585723876953,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 1.5289617486338798,
|
|
"grad_norm": 0.5683321356773376,
|
|
"learning_rate": 4.765395894428153e-05,
|
|
"loss": 0.6123217391967773,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"epoch": 1.6018214936247723,
|
|
"grad_norm": 0.5973424911499023,
|
|
"learning_rate": 4.032258064516129e-05,
|
|
"loss": 0.6341474533081055,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 1.6746812386156649,
|
|
"grad_norm": 0.540243923664093,
|
|
"learning_rate": 3.2991202346041056e-05,
|
|
"loss": 0.6104950714111328,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"epoch": 1.7475409836065574,
|
|
"grad_norm": 0.47242051362991333,
|
|
"learning_rate": 2.565982404692082e-05,
|
|
"loss": 0.5970580291748047,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 1.82040072859745,
|
|
"grad_norm": 0.651258111000061,
|
|
"learning_rate": 1.8328445747800586e-05,
|
|
"loss": 0.629194221496582,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"epoch": 1.8932604735883425,
|
|
"grad_norm": 0.6018247604370117,
|
|
"learning_rate": 1.0997067448680352e-05,
|
|
"loss": 0.6117166137695312,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 1.966120218579235,
|
|
"grad_norm": 0.541965901851654,
|
|
"learning_rate": 3.6656891495601177e-06,
|
|
"loss": 0.6098161315917969,
|
|
"step": 1350
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 1374,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 2,
|
|
"save_steps": 200,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 8.08676495418409e+16,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|