Mistral-7b-CS-AR / trainer_state.json
Kamyar Zeinalipour
Add files from checkpoint-225
dd09e09
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9988901220865705,
"eval_steps": 500,
"global_step": 225,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.022197558268590455,
"grad_norm": 508.4661515845952,
"learning_rate": 9.998646205897309e-05,
"loss": 1.583,
"step": 5
},
{
"epoch": 0.04439511653718091,
"grad_norm": 63.408651161770806,
"learning_rate": 9.994585556692624e-05,
"loss": 1.0456,
"step": 10
},
{
"epoch": 0.06659267480577137,
"grad_norm": 14.042068557047731,
"learning_rate": 9.987820251299122e-05,
"loss": 0.8426,
"step": 15
},
{
"epoch": 0.08879023307436182,
"grad_norm": 25.347876076858604,
"learning_rate": 9.978353953249022e-05,
"loss": 0.7886,
"step": 20
},
{
"epoch": 0.11098779134295228,
"grad_norm": 12.656650981233698,
"learning_rate": 9.966191788709716e-05,
"loss": 0.7669,
"step": 25
},
{
"epoch": 0.13318534961154274,
"grad_norm": 11.065995415612106,
"learning_rate": 9.951340343707852e-05,
"loss": 0.7213,
"step": 30
},
{
"epoch": 0.15538290788013318,
"grad_norm": 11.959290367786375,
"learning_rate": 9.933807660562898e-05,
"loss": 0.7023,
"step": 35
},
{
"epoch": 0.17758046614872364,
"grad_norm": 11.780180213713495,
"learning_rate": 9.913603233532067e-05,
"loss": 0.6584,
"step": 40
},
{
"epoch": 0.1997780244173141,
"grad_norm": 11.330035535527745,
"learning_rate": 9.890738003669029e-05,
"loss": 0.6557,
"step": 45
},
{
"epoch": 0.22197558268590456,
"grad_norm": 13.977239368720625,
"learning_rate": 9.865224352899119e-05,
"loss": 0.636,
"step": 50
},
{
"epoch": 0.244173140954495,
"grad_norm": 10.843819536568102,
"learning_rate": 9.837076097314319e-05,
"loss": 0.6343,
"step": 55
},
{
"epoch": 0.2663706992230855,
"grad_norm": 10.887860517166084,
"learning_rate": 9.806308479691595e-05,
"loss": 0.6181,
"step": 60
},
{
"epoch": 0.2885682574916759,
"grad_norm": 10.499851042734015,
"learning_rate": 9.77293816123866e-05,
"loss": 0.6262,
"step": 65
},
{
"epoch": 0.31076581576026635,
"grad_norm": 10.495634751624701,
"learning_rate": 9.736983212571646e-05,
"loss": 0.6056,
"step": 70
},
{
"epoch": 0.33296337402885684,
"grad_norm": 9.742924132121486,
"learning_rate": 9.698463103929542e-05,
"loss": 0.601,
"step": 75
},
{
"epoch": 0.3551609322974473,
"grad_norm": 10.191372463323502,
"learning_rate": 9.657398694630712e-05,
"loss": 0.6,
"step": 80
},
{
"epoch": 0.37735849056603776,
"grad_norm": 10.81810385438888,
"learning_rate": 9.613812221777212e-05,
"loss": 0.6063,
"step": 85
},
{
"epoch": 0.3995560488346282,
"grad_norm": 8.5634204396571,
"learning_rate": 9.567727288213005e-05,
"loss": 0.5784,
"step": 90
},
{
"epoch": 0.42175360710321863,
"grad_norm": 9.468473350420114,
"learning_rate": 9.519168849742604e-05,
"loss": 0.5912,
"step": 95
},
{
"epoch": 0.4439511653718091,
"grad_norm": 9.277181214892803,
"learning_rate": 9.468163201617062e-05,
"loss": 0.5754,
"step": 100
},
{
"epoch": 0.46614872364039955,
"grad_norm": 9.617308596864437,
"learning_rate": 9.414737964294636e-05,
"loss": 0.5667,
"step": 105
},
{
"epoch": 0.48834628190899,
"grad_norm": 10.426531513830742,
"learning_rate": 9.358922068483812e-05,
"loss": 0.567,
"step": 110
},
{
"epoch": 0.5105438401775805,
"grad_norm": 9.210104173252594,
"learning_rate": 9.300745739476829e-05,
"loss": 0.5742,
"step": 115
},
{
"epoch": 0.532741398446171,
"grad_norm": 9.602394635525636,
"learning_rate": 9.24024048078213e-05,
"loss": 0.5634,
"step": 120
},
{
"epoch": 0.5549389567147613,
"grad_norm": 10.130601405102672,
"learning_rate": 9.177439057064683e-05,
"loss": 0.5714,
"step": 125
},
{
"epoch": 0.5771365149833518,
"grad_norm": 9.94780731196881,
"learning_rate": 9.112375476403312e-05,
"loss": 0.5546,
"step": 130
},
{
"epoch": 0.5993340732519423,
"grad_norm": 9.793729854446266,
"learning_rate": 9.045084971874738e-05,
"loss": 0.5423,
"step": 135
},
{
"epoch": 0.6215316315205327,
"grad_norm": 8.763008150061346,
"learning_rate": 8.97560398247424e-05,
"loss": 0.5695,
"step": 140
},
{
"epoch": 0.6437291897891232,
"grad_norm": 8.319454810060318,
"learning_rate": 8.903970133383297e-05,
"loss": 0.5348,
"step": 145
},
{
"epoch": 0.6659267480577137,
"grad_norm": 9.257665364760308,
"learning_rate": 8.83022221559489e-05,
"loss": 0.5281,
"step": 150
},
{
"epoch": 0.6881243063263041,
"grad_norm": 9.078192205410708,
"learning_rate": 8.754400164907497e-05,
"loss": 0.5369,
"step": 155
},
{
"epoch": 0.7103218645948945,
"grad_norm": 8.44925092098244,
"learning_rate": 8.676545040299145e-05,
"loss": 0.5154,
"step": 160
},
{
"epoch": 0.732519422863485,
"grad_norm": 9.803727387472671,
"learning_rate": 8.596699001693255e-05,
"loss": 0.5206,
"step": 165
},
{
"epoch": 0.7547169811320755,
"grad_norm": 10.562737285970007,
"learning_rate": 8.51490528712831e-05,
"loss": 0.5373,
"step": 170
},
{
"epoch": 0.7769145394006659,
"grad_norm": 9.429289089308323,
"learning_rate": 8.43120818934367e-05,
"loss": 0.5358,
"step": 175
},
{
"epoch": 0.7991120976692564,
"grad_norm": 8.481094765111386,
"learning_rate": 8.345653031794292e-05,
"loss": 0.5354,
"step": 180
},
{
"epoch": 0.8213096559378469,
"grad_norm": 9.047588302577825,
"learning_rate": 8.258286144107276e-05,
"loss": 0.5349,
"step": 185
},
{
"epoch": 0.8435072142064373,
"grad_norm": 8.86043961391346,
"learning_rate": 8.169154836993551e-05,
"loss": 0.5132,
"step": 190
},
{
"epoch": 0.8657047724750278,
"grad_norm": 8.095864972318497,
"learning_rate": 8.07830737662829e-05,
"loss": 0.5123,
"step": 195
},
{
"epoch": 0.8879023307436182,
"grad_norm": 8.975157227045662,
"learning_rate": 7.985792958513931e-05,
"loss": 0.5109,
"step": 200
},
{
"epoch": 0.9100998890122086,
"grad_norm": 9.977626570306237,
"learning_rate": 7.891661680839932e-05,
"loss": 0.5126,
"step": 205
},
{
"epoch": 0.9322974472807991,
"grad_norm": 8.185944469376132,
"learning_rate": 7.795964517353735e-05,
"loss": 0.5181,
"step": 210
},
{
"epoch": 0.9544950055493896,
"grad_norm": 8.733959774898256,
"learning_rate": 7.698753289757565e-05,
"loss": 0.5185,
"step": 215
},
{
"epoch": 0.97669256381798,
"grad_norm": 8.456212091905767,
"learning_rate": 7.600080639646077e-05,
"loss": 0.506,
"step": 220
},
{
"epoch": 0.9988901220865705,
"grad_norm": 7.694032529021555,
"learning_rate": 7.500000000000001e-05,
"loss": 0.4949,
"step": 225
},
{
"epoch": 0.9988901220865705,
"eval_loss": 0.5675469636917114,
"eval_runtime": 119.5801,
"eval_samples_per_second": 21.266,
"eval_steps_per_second": 1.33,
"step": 225
}
],
"logging_steps": 5,
"max_steps": 675,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 724509598154752.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}