Upload folder using huggingface_hub
Browse files- checkpoints-v1.0-discrete-conditional/checkpoint-6075/model.safetensors +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/optimizer.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/rng_state.pth +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/scaler.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/scheduler.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/trainer_state.json +586 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-6075/training_args.bin +3 -0
checkpoints-v1.0-discrete-conditional/checkpoint-6075/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f308d28a715af9add8b1de2802f5fe0d790cf13b3da275d2033da2142579491f
|
| 3 |
+
size 24241232
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5894db628b27dc538b3dd2f5afb2580f7e6b9b5ff294a45e847dee74fd85ae81
|
| 3 |
+
size 2090059
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef57ee88dfae1c93d3f03788067008bcafcaf720d6594dbfbcb3217f35b3914
|
| 3 |
+
size 14645
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad5272f5bbb3e1f5e5a02b236aff7f184d3dfb0d9e4a9da7851f5c7531043fe1
|
| 3 |
+
size 1383
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedfcc2552d8a73e9f34b1abb5aa7d8a44e2a78a10791d5cf93e6b506cdec12b
|
| 3 |
+
size 1465
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/trainer_state.json
ADDED
|
@@ -0,0 +1,586 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 256,
|
| 7 |
+
"global_step": 6075,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.12641975308641976,
|
| 14 |
+
"grad_norm": 0.492948055267334,
|
| 15 |
+
"learning_rate": 0.000498046875,
|
| 16 |
+
"loss": 1.2244964838027954,
|
| 17 |
+
"step": 256
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12641975308641976,
|
| 21 |
+
"eval_bleu": 0.023732509698572428,
|
| 22 |
+
"eval_loss": 1.1824145491530256,
|
| 23 |
+
"eval_mse_loss": 1.1824145491530256,
|
| 24 |
+
"step": 256
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12641975308641976,
|
| 28 |
+
"eval_bleu": 0.023732509698572428,
|
| 29 |
+
"eval_loss": 1.1824145491530256,
|
| 30 |
+
"eval_mse_loss": 1.1824145491530256,
|
| 31 |
+
"eval_runtime": 7.5989,
|
| 32 |
+
"eval_samples_per_second": 344.523,
|
| 33 |
+
"eval_steps_per_second": 5.396,
|
| 34 |
+
"step": 256
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.2528395061728395,
|
| 38 |
+
"grad_norm": 0.5793251395225525,
|
| 39 |
+
"learning_rate": 0.000998046875,
|
| 40 |
+
"loss": 1.1349375247955322,
|
| 41 |
+
"step": 512
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.2528395061728395,
|
| 45 |
+
"eval_bleu": 0.022541652789025497,
|
| 46 |
+
"eval_loss": 1.072069642020435,
|
| 47 |
+
"eval_mse_loss": 1.072069642020435,
|
| 48 |
+
"step": 512
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.2528395061728395,
|
| 52 |
+
"eval_bleu": 0.022541652789025497,
|
| 53 |
+
"eval_loss": 1.072069642020435,
|
| 54 |
+
"eval_mse_loss": 1.072069642020435,
|
| 55 |
+
"eval_runtime": 10.3846,
|
| 56 |
+
"eval_samples_per_second": 252.104,
|
| 57 |
+
"eval_steps_per_second": 3.948,
|
| 58 |
+
"step": 512
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.37925925925925924,
|
| 62 |
+
"grad_norm": 1.0635820627212524,
|
| 63 |
+
"learning_rate": 0.0009948245115884234,
|
| 64 |
+
"loss": 1.0092785358428955,
|
| 65 |
+
"step": 768
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.37925925925925924,
|
| 69 |
+
"eval_bleu": 0.033273457001155124,
|
| 70 |
+
"eval_loss": 0.9512386612775849,
|
| 71 |
+
"eval_mse_loss": 0.9512386612775849,
|
| 72 |
+
"step": 768
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.37925925925925924,
|
| 76 |
+
"eval_bleu": 0.033273457001155124,
|
| 77 |
+
"eval_loss": 0.9512386612775849,
|
| 78 |
+
"eval_mse_loss": 0.9512386612775849,
|
| 79 |
+
"eval_runtime": 7.8124,
|
| 80 |
+
"eval_samples_per_second": 335.109,
|
| 81 |
+
"eval_steps_per_second": 5.248,
|
| 82 |
+
"step": 768
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.505679012345679,
|
| 86 |
+
"grad_norm": 1.4405001401901245,
|
| 87 |
+
"learning_rate": 0.0009793249077302685,
|
| 88 |
+
"loss": 0.9039018750190735,
|
| 89 |
+
"step": 1024
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.505679012345679,
|
| 93 |
+
"eval_bleu": 0.052676822222678464,
|
| 94 |
+
"eval_loss": 0.8639799516375471,
|
| 95 |
+
"eval_mse_loss": 0.8639799516375471,
|
| 96 |
+
"step": 1024
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.505679012345679,
|
| 100 |
+
"eval_bleu": 0.052676822222678464,
|
| 101 |
+
"eval_loss": 0.8639799516375471,
|
| 102 |
+
"eval_mse_loss": 0.8639799516375471,
|
| 103 |
+
"eval_runtime": 7.9883,
|
| 104 |
+
"eval_samples_per_second": 327.728,
|
| 105 |
+
"eval_steps_per_second": 5.132,
|
| 106 |
+
"step": 1024
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.6320987654320988,
|
| 110 |
+
"grad_norm": 1.0358325242996216,
|
| 111 |
+
"learning_rate": 0.0009538244979611361,
|
| 112 |
+
"loss": 0.8407024145126343,
|
| 113 |
+
"step": 1280
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.6320987654320988,
|
| 117 |
+
"eval_bleu": 0.06327640177191206,
|
| 118 |
+
"eval_loss": 0.8159576320066685,
|
| 119 |
+
"eval_mse_loss": 0.8159576320066685,
|
| 120 |
+
"step": 1280
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.6320987654320988,
|
| 124 |
+
"eval_bleu": 0.06327640177191206,
|
| 125 |
+
"eval_loss": 0.8159576320066685,
|
| 126 |
+
"eval_mse_loss": 0.8159576320066685,
|
| 127 |
+
"eval_runtime": 7.5298,
|
| 128 |
+
"eval_samples_per_second": 347.684,
|
| 129 |
+
"eval_steps_per_second": 5.445,
|
| 130 |
+
"step": 1280
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.7585185185185185,
|
| 134 |
+
"grad_norm": 1.162336826324463,
|
| 135 |
+
"learning_rate": 0.000918855331929685,
|
| 136 |
+
"loss": 0.7959167957305908,
|
| 137 |
+
"step": 1536
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.7585185185185185,
|
| 141 |
+
"eval_bleu": 0.08702573079240403,
|
| 142 |
+
"eval_loss": 0.7736199585402884,
|
| 143 |
+
"eval_mse_loss": 0.7736199585402884,
|
| 144 |
+
"step": 1536
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.7585185185185185,
|
| 148 |
+
"eval_bleu": 0.08702573079240403,
|
| 149 |
+
"eval_loss": 0.7736199585402884,
|
| 150 |
+
"eval_mse_loss": 0.7736199585402884,
|
| 151 |
+
"eval_runtime": 7.3212,
|
| 152 |
+
"eval_samples_per_second": 357.594,
|
| 153 |
+
"eval_steps_per_second": 5.6,
|
| 154 |
+
"step": 1536
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.8849382716049383,
|
| 158 |
+
"grad_norm": 1.069529414176941,
|
| 159 |
+
"learning_rate": 0.0008751470187939401,
|
| 160 |
+
"loss": 0.765856146812439,
|
| 161 |
+
"step": 1792
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.8849382716049383,
|
| 165 |
+
"eval_bleu": 0.09888737557922633,
|
| 166 |
+
"eval_loss": 0.7493347060389635,
|
| 167 |
+
"eval_mse_loss": 0.7493347060389635,
|
| 168 |
+
"step": 1792
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.8849382716049383,
|
| 172 |
+
"eval_bleu": 0.09888737557922633,
|
| 173 |
+
"eval_loss": 0.7493347060389635,
|
| 174 |
+
"eval_mse_loss": 0.7493347060389635,
|
| 175 |
+
"eval_runtime": 7.8836,
|
| 176 |
+
"eval_samples_per_second": 332.081,
|
| 177 |
+
"eval_steps_per_second": 5.201,
|
| 178 |
+
"step": 1792
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.011358024691358,
|
| 182 |
+
"grad_norm": 1.7033277750015259,
|
| 183 |
+
"learning_rate": 0.000823611504395474,
|
| 184 |
+
"loss": 0.7400754690170288,
|
| 185 |
+
"step": 2048
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.011358024691358,
|
| 189 |
+
"eval_bleu": 0.109763799561906,
|
| 190 |
+
"eval_loss": 0.7278894520387417,
|
| 191 |
+
"eval_mse_loss": 0.7278894520387417,
|
| 192 |
+
"step": 2048
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.011358024691358,
|
| 196 |
+
"eval_bleu": 0.109763799561906,
|
| 197 |
+
"eval_loss": 0.7278894520387417,
|
| 198 |
+
"eval_mse_loss": 0.7278894520387417,
|
| 199 |
+
"eval_runtime": 8.1701,
|
| 200 |
+
"eval_samples_per_second": 320.438,
|
| 201 |
+
"eval_steps_per_second": 5.018,
|
| 202 |
+
"step": 2048
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.1377777777777778,
|
| 206 |
+
"grad_norm": 1.650696039199829,
|
| 207 |
+
"learning_rate": 0.0007653240440959618,
|
| 208 |
+
"loss": 0.717435359954834,
|
| 209 |
+
"step": 2304
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.1377777777777778,
|
| 213 |
+
"eval_bleu": 0.10638359304769301,
|
| 214 |
+
"eval_loss": 0.7039981920544695,
|
| 215 |
+
"eval_mse_loss": 0.7039981920544695,
|
| 216 |
+
"step": 2304
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.1377777777777778,
|
| 220 |
+
"eval_bleu": 0.10638359304769301,
|
| 221 |
+
"eval_loss": 0.7039981920544695,
|
| 222 |
+
"eval_mse_loss": 0.7039981920544695,
|
| 223 |
+
"eval_runtime": 7.2661,
|
| 224 |
+
"eval_samples_per_second": 360.301,
|
| 225 |
+
"eval_steps_per_second": 5.643,
|
| 226 |
+
"step": 2304
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2641975308641975,
|
| 230 |
+
"grad_norm": 1.51780366897583,
|
| 231 |
+
"learning_rate": 0.0007015007682656353,
|
| 232 |
+
"loss": 0.6996763944625854,
|
| 233 |
+
"step": 2560
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2641975308641975,
|
| 237 |
+
"eval_bleu": 0.12510003883439522,
|
| 238 |
+
"eval_loss": 0.6899523284377121,
|
| 239 |
+
"eval_mse_loss": 0.6899523284377121,
|
| 240 |
+
"step": 2560
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2641975308641975,
|
| 244 |
+
"eval_bleu": 0.12510003883439522,
|
| 245 |
+
"eval_loss": 0.6899523284377121,
|
| 246 |
+
"eval_mse_loss": 0.6899523284377121,
|
| 247 |
+
"eval_runtime": 7.9616,
|
| 248 |
+
"eval_samples_per_second": 328.827,
|
| 249 |
+
"eval_steps_per_second": 5.15,
|
| 250 |
+
"step": 2560
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.3906172839506172,
|
| 254 |
+
"grad_norm": 1.5419062376022339,
|
| 255 |
+
"learning_rate": 0.0006334733085052896,
|
| 256 |
+
"loss": 0.6830626726150513,
|
| 257 |
+
"step": 2816
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.3906172839506172,
|
| 261 |
+
"eval_bleu": 0.1434415539389988,
|
| 262 |
+
"eval_loss": 0.6733295452304002,
|
| 263 |
+
"eval_mse_loss": 0.6733295452304002,
|
| 264 |
+
"step": 2816
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.3906172839506172,
|
| 268 |
+
"eval_bleu": 0.1434415539389988,
|
| 269 |
+
"eval_loss": 0.6733295452304002,
|
| 270 |
+
"eval_mse_loss": 0.6733295452304002,
|
| 271 |
+
"eval_runtime": 7.8649,
|
| 272 |
+
"eval_samples_per_second": 332.873,
|
| 273 |
+
"eval_steps_per_second": 5.213,
|
| 274 |
+
"step": 2816
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5170370370370372,
|
| 278 |
+
"grad_norm": 1.7831259965896606,
|
| 279 |
+
"learning_rate": 0.0005626610140094024,
|
| 280 |
+
"loss": 0.6682955026626587,
|
| 281 |
+
"step": 3072
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.5170370370370372,
|
| 285 |
+
"eval_bleu": 0.1462795204156182,
|
| 286 |
+
"eval_loss": 0.6550371501503921,
|
| 287 |
+
"eval_mse_loss": 0.6550371501503921,
|
| 288 |
+
"step": 3072
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.5170370370370372,
|
| 292 |
+
"eval_bleu": 0.1462795204156182,
|
| 293 |
+
"eval_loss": 0.6550371501503921,
|
| 294 |
+
"eval_mse_loss": 0.6550371501503921,
|
| 295 |
+
"eval_runtime": 8.3223,
|
| 296 |
+
"eval_samples_per_second": 314.575,
|
| 297 |
+
"eval_steps_per_second": 4.927,
|
| 298 |
+
"step": 3072
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.643456790123457,
|
| 302 |
+
"grad_norm": 1.8476954698562622,
|
| 303 |
+
"learning_rate": 0.0004905413377580782,
|
| 304 |
+
"loss": 0.655277669429779,
|
| 305 |
+
"step": 3328
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.643456790123457,
|
| 309 |
+
"eval_bleu": 0.15115082134880684,
|
| 310 |
+
"eval_loss": 0.6512059845575472,
|
| 311 |
+
"eval_mse_loss": 0.6512059845575472,
|
| 312 |
+
"step": 3328
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.643456790123457,
|
| 316 |
+
"eval_bleu": 0.15115082134880684,
|
| 317 |
+
"eval_loss": 0.6512059845575472,
|
| 318 |
+
"eval_mse_loss": 0.6512059845575472,
|
| 319 |
+
"eval_runtime": 7.1783,
|
| 320 |
+
"eval_samples_per_second": 364.712,
|
| 321 |
+
"eval_steps_per_second": 5.712,
|
| 322 |
+
"step": 3328
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.7698765432098766,
|
| 326 |
+
"grad_norm": 1.8581129312515259,
|
| 327 |
+
"learning_rate": 0.0004186190104108759,
|
| 328 |
+
"loss": 0.6462851166725159,
|
| 329 |
+
"step": 3584
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.7698765432098766,
|
| 333 |
+
"eval_bleu": 0.15871631534957106,
|
| 334 |
+
"eval_loss": 0.6409407970381946,
|
| 335 |
+
"eval_mse_loss": 0.6409407970381946,
|
| 336 |
+
"step": 3584
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.7698765432098766,
|
| 340 |
+
"eval_bleu": 0.15871631534957106,
|
| 341 |
+
"eval_loss": 0.6409407970381946,
|
| 342 |
+
"eval_mse_loss": 0.6409407970381946,
|
| 343 |
+
"eval_runtime": 7.8013,
|
| 344 |
+
"eval_samples_per_second": 335.586,
|
| 345 |
+
"eval_steps_per_second": 5.256,
|
| 346 |
+
"step": 3584
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.8962962962962964,
|
| 350 |
+
"grad_norm": 1.4670681953430176,
|
| 351 |
+
"learning_rate": 0.00034839464506939983,
|
| 352 |
+
"loss": 0.6346220374107361,
|
| 353 |
+
"step": 3840
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.8962962962962964,
|
| 357 |
+
"eval_bleu": 0.16468961242826577,
|
| 358 |
+
"eval_loss": 0.6350918848340105,
|
| 359 |
+
"eval_mse_loss": 0.6350918848340105,
|
| 360 |
+
"step": 3840
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.8962962962962964,
|
| 364 |
+
"eval_bleu": 0.16468961242826577,
|
| 365 |
+
"eval_loss": 0.6350918848340105,
|
| 366 |
+
"eval_mse_loss": 0.6350918848340105,
|
| 367 |
+
"eval_runtime": 7.8698,
|
| 368 |
+
"eval_samples_per_second": 332.666,
|
| 369 |
+
"eval_steps_per_second": 5.21,
|
| 370 |
+
"step": 3840
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.022716049382716,
|
| 374 |
+
"grad_norm": 1.6064578294754028,
|
| 375 |
+
"learning_rate": 0.0002813334279500873,
|
| 376 |
+
"loss": 0.6261877417564392,
|
| 377 |
+
"step": 4096
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.022716049382716,
|
| 381 |
+
"eval_bleu": 0.18248380444483625,
|
| 382 |
+
"eval_loss": 0.6185257740137053,
|
| 383 |
+
"eval_mse_loss": 0.6185257740137053,
|
| 384 |
+
"step": 4096
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.022716049382716,
|
| 388 |
+
"eval_bleu": 0.18248380444483625,
|
| 389 |
+
"eval_loss": 0.6185257740137053,
|
| 390 |
+
"eval_mse_loss": 0.6185257740137053,
|
| 391 |
+
"eval_runtime": 8.3116,
|
| 392 |
+
"eval_samples_per_second": 314.98,
|
| 393 |
+
"eval_steps_per_second": 4.933,
|
| 394 |
+
"step": 4096
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.149135802469136,
|
| 398 |
+
"grad_norm": 1.1933625936508179,
|
| 399 |
+
"learning_rate": 0.0002188345482161727,
|
| 400 |
+
"loss": 0.6169702410697937,
|
| 401 |
+
"step": 4352
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.149135802469136,
|
| 405 |
+
"eval_bleu": 0.17739074250184356,
|
| 406 |
+
"eval_loss": 0.619684124865183,
|
| 407 |
+
"eval_mse_loss": 0.619684124865183,
|
| 408 |
+
"step": 4352
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.149135802469136,
|
| 412 |
+
"eval_bleu": 0.17739074250184356,
|
| 413 |
+
"eval_loss": 0.619684124865183,
|
| 414 |
+
"eval_mse_loss": 0.619684124865183,
|
| 415 |
+
"eval_runtime": 7.0884,
|
| 416 |
+
"eval_samples_per_second": 369.337,
|
| 417 |
+
"eval_steps_per_second": 5.784,
|
| 418 |
+
"step": 4352
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.2755555555555556,
|
| 422 |
+
"grad_norm": 1.3906270265579224,
|
| 423 |
+
"learning_rate": 0.00016220200479571452,
|
| 424 |
+
"loss": 0.612635612487793,
|
| 425 |
+
"step": 4608
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.2755555555555556,
|
| 429 |
+
"eval_bleu": 0.19037059494496988,
|
| 430 |
+
"eval_loss": 0.6192231905169603,
|
| 431 |
+
"eval_mse_loss": 0.6192231905169603,
|
| 432 |
+
"step": 4608
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.2755555555555556,
|
| 436 |
+
"eval_bleu": 0.19037059494496988,
|
| 437 |
+
"eval_loss": 0.6192231905169603,
|
| 438 |
+
"eval_mse_loss": 0.6192231905169603,
|
| 439 |
+
"eval_runtime": 7.2603,
|
| 440 |
+
"eval_samples_per_second": 360.593,
|
| 441 |
+
"eval_steps_per_second": 5.647,
|
| 442 |
+
"step": 4608
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.4019753086419753,
|
| 446 |
+
"grad_norm": 1.3547346591949463,
|
| 447 |
+
"learning_rate": 0.00011261739928266108,
|
| 448 |
+
"loss": 0.6073014736175537,
|
| 449 |
+
"step": 4864
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.4019753086419753,
|
| 453 |
+
"eval_bleu": 0.19665228309802169,
|
| 454 |
+
"eval_loss": 0.6012938604122255,
|
| 455 |
+
"eval_mse_loss": 0.6012938604122255,
|
| 456 |
+
"step": 4864
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.4019753086419753,
|
| 460 |
+
"eval_bleu": 0.19665228309802169,
|
| 461 |
+
"eval_loss": 0.6012938604122255,
|
| 462 |
+
"eval_mse_loss": 0.6012938604122255,
|
| 463 |
+
"eval_runtime": 7.3255,
|
| 464 |
+
"eval_samples_per_second": 357.382,
|
| 465 |
+
"eval_steps_per_second": 5.597,
|
| 466 |
+
"step": 4864
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.528395061728395,
|
| 470 |
+
"grad_norm": 1.2325892448425293,
|
| 471 |
+
"learning_rate": 7.111528257956546e-05,
|
| 472 |
+
"loss": 0.6047106981277466,
|
| 473 |
+
"step": 5120
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.528395061728395,
|
| 477 |
+
"eval_bleu": 0.18764803384320677,
|
| 478 |
+
"eval_loss": 0.6008666448476838,
|
| 479 |
+
"eval_mse_loss": 0.6008666448476838,
|
| 480 |
+
"step": 5120
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.528395061728395,
|
| 484 |
+
"eval_bleu": 0.18764803384320677,
|
| 485 |
+
"eval_loss": 0.6008666448476838,
|
| 486 |
+
"eval_mse_loss": 0.6008666448476838,
|
| 487 |
+
"eval_runtime": 7.2141,
|
| 488 |
+
"eval_samples_per_second": 362.901,
|
| 489 |
+
"eval_steps_per_second": 5.683,
|
| 490 |
+
"step": 5120
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.6548148148148147,
|
| 494 |
+
"grad_norm": 1.2043205499649048,
|
| 495 |
+
"learning_rate": 3.856156965839863e-05,
|
| 496 |
+
"loss": 0.6008339524269104,
|
| 497 |
+
"step": 5376
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.6548148148148147,
|
| 501 |
+
"eval_bleu": 0.1778719937984465,
|
| 502 |
+
"eval_loss": 0.6019039372118508,
|
| 503 |
+
"eval_mse_loss": 0.6019039372118508,
|
| 504 |
+
"step": 5376
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.6548148148148147,
|
| 508 |
+
"eval_bleu": 0.1778719937984465,
|
| 509 |
+
"eval_loss": 0.6019039372118508,
|
| 510 |
+
"eval_mse_loss": 0.6019039372118508,
|
| 511 |
+
"eval_runtime": 7.2108,
|
| 512 |
+
"eval_samples_per_second": 363.066,
|
| 513 |
+
"eval_steps_per_second": 5.686,
|
| 514 |
+
"step": 5376
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.7812345679012345,
|
| 518 |
+
"grad_norm": 0.8030632734298706,
|
| 519 |
+
"learning_rate": 1.56354728015935e-05,
|
| 520 |
+
"loss": 0.5988247990608215,
|
| 521 |
+
"step": 5632
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.7812345679012345,
|
| 525 |
+
"eval_bleu": 0.1821845130406551,
|
| 526 |
+
"eval_loss": 0.6124805255634028,
|
| 527 |
+
"eval_mse_loss": 0.6124805255634028,
|
| 528 |
+
"step": 5632
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.7812345679012345,
|
| 532 |
+
"eval_bleu": 0.1821845130406551,
|
| 533 |
+
"eval_loss": 0.6124805255634028,
|
| 534 |
+
"eval_mse_loss": 0.6124805255634028,
|
| 535 |
+
"eval_runtime": 7.2547,
|
| 536 |
+
"eval_samples_per_second": 360.87,
|
| 537 |
+
"eval_steps_per_second": 5.652,
|
| 538 |
+
"step": 5632
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.907654320987654,
|
| 542 |
+
"grad_norm": 0.7116315364837646,
|
| 543 |
+
"learning_rate": 2.81533027462183e-06,
|
| 544 |
+
"loss": 0.5993514657020569,
|
| 545 |
+
"step": 5888
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.907654320987654,
|
| 549 |
+
"eval_bleu": 0.1971691623533449,
|
| 550 |
+
"eval_loss": 0.593609597624802,
|
| 551 |
+
"eval_mse_loss": 0.593609597624802,
|
| 552 |
+
"step": 5888
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.907654320987654,
|
| 556 |
+
"eval_bleu": 0.1971691623533449,
|
| 557 |
+
"eval_loss": 0.593609597624802,
|
| 558 |
+
"eval_mse_loss": 0.593609597624802,
|
| 559 |
+
"eval_runtime": 7.1929,
|
| 560 |
+
"eval_samples_per_second": 363.972,
|
| 561 |
+
"eval_steps_per_second": 5.7,
|
| 562 |
+
"step": 5888
|
| 563 |
+
}
|
| 564 |
+
],
|
| 565 |
+
"logging_steps": 256,
|
| 566 |
+
"max_steps": 6075,
|
| 567 |
+
"num_input_tokens_seen": 0,
|
| 568 |
+
"num_train_epochs": 3,
|
| 569 |
+
"save_steps": 256,
|
| 570 |
+
"stateful_callbacks": {
|
| 571 |
+
"TrainerControl": {
|
| 572 |
+
"args": {
|
| 573 |
+
"should_epoch_stop": false,
|
| 574 |
+
"should_evaluate": false,
|
| 575 |
+
"should_log": false,
|
| 576 |
+
"should_save": true,
|
| 577 |
+
"should_training_stop": true
|
| 578 |
+
},
|
| 579 |
+
"attributes": {}
|
| 580 |
+
}
|
| 581 |
+
},
|
| 582 |
+
"total_flos": 0.0,
|
| 583 |
+
"train_batch_size": 64,
|
| 584 |
+
"trial_name": null,
|
| 585 |
+
"trial_params": null
|
| 586 |
+
}
|
checkpoints-v1.0-discrete-conditional/checkpoint-6075/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2792db1613dd46e912da1df5b55d8147d2f8e78f28906344920814707c74766f
|
| 3 |
+
size 5137
|