Commit
•
376e0d0
1
Parent(s):
3e71e8d
Model save
Browse files- README.md +3 -6
- all_results.json +5 -5
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +2150 -176
README.md
CHANGED
|
@@ -2,21 +2,18 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- generated_from_trainer
|
| 7 |
-
datasets:
|
| 8 |
-
- AmberYifan/spin-v
|
| 9 |
model-index:
|
| 10 |
-
- name: iter0
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
# iter0
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
+
- name: spin-v-iter0
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# spin-v-iter0
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.013782728538135369,
|
| 4 |
+
"train_runtime": 6445.5164,
|
| 5 |
+
"train_samples": 50000,
|
| 6 |
+
"train_samples_per_second": 7.757,
|
| 7 |
+
"train_steps_per_second": 0.242
|
| 8 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4943162336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2287d15b2fcb1fb205e4adc42291fcde8fb1cee220b10ecd86848891af878475
|
| 3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999819336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:044caa55b1d176de4e83fb8b652628cd4c5dd16aa01652a40d1183c417f2a27d
|
| 3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4540516344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c751c926b17417e470bd8d7fd0e67dff5572d037678b983e36cda87fd86063af
|
| 3 |
size 4540516344
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.013782728538135369,
|
| 4 |
+
"train_runtime": 6445.5164,
|
| 5 |
+
"train_samples": 50000,
|
| 6 |
+
"train_samples_per_second": 7.757,
|
| 7 |
+
"train_steps_per_second": 0.242
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -3,18 +3,18 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate": 3.
|
| 14 |
-
"logits/generated": -3.
|
| 15 |
-
"logits/real": -2.
|
| 16 |
-
"logps/generated": -
|
| 17 |
-
"logps/real": -
|
| 18 |
"loss": 0.6931,
|
| 19 |
"rewards/accuracies": 0.0,
|
| 20 |
"rewards/generated": 0.0,
|
|
@@ -23,227 +23,2201 @@
|
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"learning_rate": 3.
|
| 28 |
-
"logits/generated": -3.
|
| 29 |
-
"logits/real": -2.
|
| 30 |
-
"logps/generated": -
|
| 31 |
-
"logps/real": -
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"rewards/accuracies": 0.
|
| 34 |
-
"rewards/generated": -
|
| 35 |
-
"rewards/margins":
|
| 36 |
-
"rewards/real": 0.
|
| 37 |
"step": 10
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"learning_rate":
|
| 42 |
-
"logits/generated": -
|
| 43 |
-
"logits/real": -2.
|
| 44 |
-
"logps/generated": -
|
| 45 |
-
"logps/real": -
|
| 46 |
-
"loss": 0.
|
| 47 |
-
"rewards/accuracies": 1.0,
|
| 48 |
-
"rewards/generated": -
|
| 49 |
-
"rewards/margins":
|
| 50 |
-
"rewards/real": 0.
|
| 51 |
"step": 20
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"logits/generated": -
|
| 57 |
-
"logits/real": -2.
|
| 58 |
-
"logps/generated": -
|
| 59 |
-
"logps/real": -
|
| 60 |
-
"loss": 0.
|
| 61 |
-
"rewards/accuracies": 1.0,
|
| 62 |
-
"rewards/generated": -
|
| 63 |
-
"rewards/margins":
|
| 64 |
-
"rewards/real": 0.
|
| 65 |
"step": 30
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"logits/generated": -2.
|
| 71 |
-
"logits/real": -2.
|
| 72 |
-
"logps/generated": -
|
| 73 |
-
"logps/real": -
|
| 74 |
-
"loss": 0.
|
| 75 |
-
"rewards/accuracies": 0
|
| 76 |
-
"rewards/generated": -
|
| 77 |
-
"rewards/margins":
|
| 78 |
-
"rewards/real": 0.
|
| 79 |
"step": 40
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"learning_rate":
|
| 84 |
-
"logits/generated": -2.
|
| 85 |
-
"logits/real": -2.
|
| 86 |
-
"logps/generated": -
|
| 87 |
-
"logps/real": -
|
| 88 |
-
"loss": 0.
|
| 89 |
-
"rewards/accuracies":
|
| 90 |
-
"rewards/generated": -
|
| 91 |
-
"rewards/margins":
|
| 92 |
-
"rewards/real": 0.
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"logits/generated": -2.
|
| 99 |
-
"logits/real": -2.
|
| 100 |
-
"logps/generated": -
|
| 101 |
-
"logps/real": -
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"rewards/accuracies": 1.0,
|
| 104 |
-
"rewards/generated": -
|
| 105 |
-
"rewards/margins":
|
| 106 |
-
"rewards/real":
|
| 107 |
"step": 60
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"logits/generated": -2.
|
| 113 |
-
"logits/real": -2.
|
| 114 |
-
"logps/generated": -
|
| 115 |
-
"logps/real": -
|
| 116 |
-
"loss": 0.
|
| 117 |
-
"rewards/accuracies": 1.0,
|
| 118 |
-
"rewards/generated": -
|
| 119 |
-
"rewards/margins":
|
| 120 |
-
"rewards/real":
|
| 121 |
"step": 70
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"learning_rate": 2.
|
| 126 |
-
"logits/generated": -2.
|
| 127 |
-
"logits/real": -2.
|
| 128 |
-
"logps/generated": -
|
| 129 |
-
"logps/real": -
|
| 130 |
-
"loss": 0.
|
| 131 |
-
"rewards/accuracies": 1.0,
|
| 132 |
-
"rewards/generated": -
|
| 133 |
-
"rewards/margins":
|
| 134 |
-
"rewards/real":
|
| 135 |
"step": 80
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 2.
|
| 140 |
-
"logits/generated": -2.
|
| 141 |
-
"logits/real": -2.
|
| 142 |
-
"logps/generated": -
|
| 143 |
-
"logps/real": -
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"rewards/accuracies": 1.0,
|
| 146 |
-
"rewards/generated": -
|
| 147 |
-
"rewards/margins":
|
| 148 |
-
"rewards/real":
|
| 149 |
"step": 90
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"logits/generated": -2.
|
| 155 |
-
"logits/real": -2.
|
| 156 |
-
"logps/generated": -
|
| 157 |
-
"logps/real": -
|
| 158 |
-
"loss": 0.
|
| 159 |
-
"rewards/accuracies": 1.0,
|
| 160 |
-
"rewards/generated": -
|
| 161 |
-
"rewards/margins":
|
| 162 |
-
"rewards/real":
|
| 163 |
"step": 100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"learning_rate":
|
| 168 |
-
"logits/generated": -2.
|
| 169 |
-
"logits/real": -2.
|
| 170 |
-
"logps/generated": -
|
| 171 |
-
"logps/real": -
|
| 172 |
-
"loss": 0.
|
| 173 |
"rewards/accuracies": 1.0,
|
| 174 |
-
"rewards/generated": -
|
| 175 |
-
"rewards/margins":
|
| 176 |
-
"rewards/real":
|
| 177 |
"step": 110
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"logits/generated": -2.
|
| 183 |
-
"logits/real": -2.
|
| 184 |
-
"logps/generated": -
|
| 185 |
-
"logps/real": -
|
| 186 |
-
"loss": 0.
|
| 187 |
"rewards/accuracies": 1.0,
|
| 188 |
-
"rewards/generated": -
|
| 189 |
-
"rewards/margins":
|
| 190 |
-
"rewards/real":
|
| 191 |
"step": 120
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"learning_rate":
|
| 196 |
-
"logits/generated": -2.
|
| 197 |
-
"logits/real": -2.
|
| 198 |
-
"logps/generated": -
|
| 199 |
-
"logps/real": -
|
| 200 |
-
"loss": 0.
|
| 201 |
-
"rewards/accuracies":
|
| 202 |
-
"rewards/generated": -
|
| 203 |
-
"rewards/margins":
|
| 204 |
-
"rewards/real":
|
| 205 |
"step": 130
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"learning_rate":
|
| 210 |
-
"logits/generated": -2.
|
| 211 |
-
"logits/real": -2.
|
| 212 |
-
"logps/generated": -
|
| 213 |
-
"logps/real": -
|
| 214 |
-
"loss": 0.
|
| 215 |
-
"rewards/accuracies": 1.0,
|
| 216 |
-
"rewards/generated": -
|
| 217 |
-
"rewards/margins":
|
| 218 |
-
"rewards/real":
|
| 219 |
"step": 140
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"logits/generated": -2.
|
| 225 |
-
"logits/real": -2.
|
| 226 |
-
"logps/generated": -
|
| 227 |
-
"logps/real": -
|
| 228 |
-
"loss": 0.
|
| 229 |
-
"rewards/accuracies": 1.0,
|
| 230 |
-
"rewards/generated": -
|
| 231 |
-
"rewards/margins":
|
| 232 |
-
"rewards/real":
|
| 233 |
"step": 150
|
| 234 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 235 |
{
|
| 236 |
"epoch": 1.0,
|
| 237 |
-
"step":
|
| 238 |
"total_flos": 0.0,
|
| 239 |
-
"train_loss": 0.
|
| 240 |
-
"train_runtime":
|
| 241 |
-
"train_samples_per_second":
|
| 242 |
-
"train_steps_per_second": 0.
|
| 243 |
}
|
| 244 |
],
|
| 245 |
"logging_steps": 10,
|
| 246 |
-
"max_steps":
|
| 247 |
"num_input_tokens_seen": 0,
|
| 248 |
"num_train_epochs": 1,
|
| 249 |
"save_steps": 500,
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1563,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 3.1847133757961784e-09,
|
| 14 |
+
"logits/generated": -3.0906174182891846,
|
| 15 |
+
"logits/real": -2.9071245193481445,
|
| 16 |
+
"logps/generated": -108.96115112304688,
|
| 17 |
+
"logps/real": -115.27798461914062,
|
| 18 |
"loss": 0.6931,
|
| 19 |
"rewards/accuracies": 0.0,
|
| 20 |
"rewards/generated": 0.0,
|
|
|
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"learning_rate": 3.184713375796178e-08,
|
| 28 |
+
"logits/generated": -3.101412773132324,
|
| 29 |
+
"logits/real": -2.8992347717285156,
|
| 30 |
+
"logps/generated": -93.12618255615234,
|
| 31 |
+
"logps/real": -131.3624725341797,
|
| 32 |
+
"loss": 0.673,
|
| 33 |
+
"rewards/accuracies": 0.6388888955116272,
|
| 34 |
+
"rewards/generated": -0.032944224774837494,
|
| 35 |
+
"rewards/margins": 0.043352365493774414,
|
| 36 |
+
"rewards/real": 0.010408139787614346,
|
| 37 |
"step": 10
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"learning_rate": 6.369426751592356e-08,
|
| 42 |
+
"logits/generated": -3.102088212966919,
|
| 43 |
+
"logits/real": -2.8661417961120605,
|
| 44 |
+
"logps/generated": -102.2353744506836,
|
| 45 |
+
"logps/real": -127.91505432128906,
|
| 46 |
+
"loss": 0.4029,
|
| 47 |
+
"rewards/accuracies": 1.0,
|
| 48 |
+
"rewards/generated": -0.6219673156738281,
|
| 49 |
+
"rewards/margins": 0.8206232190132141,
|
| 50 |
+
"rewards/real": 0.1986558586359024,
|
| 51 |
"step": 20
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 9.554140127388536e-08,
|
| 56 |
+
"logits/generated": -3.0356736183166504,
|
| 57 |
+
"logits/real": -2.8853580951690674,
|
| 58 |
+
"logps/generated": -108.60257720947266,
|
| 59 |
+
"logps/real": -136.26560974121094,
|
| 60 |
+
"loss": 0.1801,
|
| 61 |
+
"rewards/accuracies": 1.0,
|
| 62 |
+
"rewards/generated": -1.4173569679260254,
|
| 63 |
+
"rewards/margins": 1.8655112981796265,
|
| 64 |
+
"rewards/real": 0.44815438985824585,
|
| 65 |
"step": 30
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"learning_rate": 1.2738853503184713e-07,
|
| 70 |
+
"logits/generated": -2.9984817504882812,
|
| 71 |
+
"logits/real": -2.8029284477233887,
|
| 72 |
+
"logps/generated": -112.51835632324219,
|
| 73 |
+
"logps/real": -127.77607727050781,
|
| 74 |
+
"loss": 0.1015,
|
| 75 |
+
"rewards/accuracies": 1.0,
|
| 76 |
+
"rewards/generated": -2.3742074966430664,
|
| 77 |
+
"rewards/margins": 3.116520643234253,
|
| 78 |
+
"rewards/real": 0.7423133254051208,
|
| 79 |
"step": 40
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"learning_rate": 1.592356687898089e-07,
|
| 84 |
+
"logits/generated": -2.9975199699401855,
|
| 85 |
+
"logits/real": -2.747887134552002,
|
| 86 |
+
"logps/generated": -118.49820709228516,
|
| 87 |
+
"logps/real": -118.71574401855469,
|
| 88 |
+
"loss": 0.074,
|
| 89 |
+
"rewards/accuracies": 0.987500011920929,
|
| 90 |
+
"rewards/generated": -2.736589193344116,
|
| 91 |
+
"rewards/margins": 3.6365692615509033,
|
| 92 |
+
"rewards/real": 0.8999798893928528,
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 1.9108280254777072e-07,
|
| 98 |
+
"logits/generated": -2.971416711807251,
|
| 99 |
+
"logits/real": -2.7840769290924072,
|
| 100 |
+
"logps/generated": -135.747802734375,
|
| 101 |
+
"logps/real": -127.07137298583984,
|
| 102 |
+
"loss": 0.0602,
|
| 103 |
+
"rewards/accuracies": 1.0,
|
| 104 |
+
"rewards/generated": -3.610677719116211,
|
| 105 |
+
"rewards/margins": 4.637597560882568,
|
| 106 |
+
"rewards/real": 1.0269203186035156,
|
| 107 |
"step": 60
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.04,
|
| 111 |
+
"learning_rate": 2.2292993630573247e-07,
|
| 112 |
+
"logits/generated": -2.9653122425079346,
|
| 113 |
+
"logits/real": -2.7327213287353516,
|
| 114 |
+
"logps/generated": -128.2880096435547,
|
| 115 |
+
"logps/real": -132.56533813476562,
|
| 116 |
+
"loss": 0.0526,
|
| 117 |
+
"rewards/accuracies": 1.0,
|
| 118 |
+
"rewards/generated": -3.613079786300659,
|
| 119 |
+
"rewards/margins": 4.637925148010254,
|
| 120 |
+
"rewards/real": 1.024846076965332,
|
| 121 |
"step": 70
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.05,
|
| 125 |
+
"learning_rate": 2.5477707006369425e-07,
|
| 126 |
+
"logits/generated": -2.9529290199279785,
|
| 127 |
+
"logits/real": -2.6906723976135254,
|
| 128 |
+
"logps/generated": -132.59231567382812,
|
| 129 |
+
"logps/real": -117.8273696899414,
|
| 130 |
+
"loss": 0.0357,
|
| 131 |
+
"rewards/accuracies": 1.0,
|
| 132 |
+
"rewards/generated": -4.144764423370361,
|
| 133 |
+
"rewards/margins": 5.101811408996582,
|
| 134 |
+
"rewards/real": 0.9570469856262207,
|
| 135 |
"step": 80
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 2.86624203821656e-07,
|
| 140 |
+
"logits/generated": -2.964216709136963,
|
| 141 |
+
"logits/real": -2.6785378456115723,
|
| 142 |
+
"logps/generated": -149.37193298339844,
|
| 143 |
+
"logps/real": -127.93388366699219,
|
| 144 |
+
"loss": 0.0275,
|
| 145 |
+
"rewards/accuracies": 1.0,
|
| 146 |
+
"rewards/generated": -4.871094703674316,
|
| 147 |
+
"rewards/margins": 5.973794460296631,
|
| 148 |
+
"rewards/real": 1.1027004718780518,
|
| 149 |
"step": 90
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.06,
|
| 153 |
+
"learning_rate": 3.184713375796178e-07,
|
| 154 |
+
"logits/generated": -2.907114028930664,
|
| 155 |
+
"logits/real": -2.6795763969421387,
|
| 156 |
+
"logps/generated": -150.70126342773438,
|
| 157 |
+
"logps/real": -117.441162109375,
|
| 158 |
+
"loss": 0.0225,
|
| 159 |
+
"rewards/accuracies": 1.0,
|
| 160 |
+
"rewards/generated": -5.468966960906982,
|
| 161 |
+
"rewards/margins": 6.453464508056641,
|
| 162 |
+
"rewards/real": 0.9844976663589478,
|
| 163 |
"step": 100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.07,
|
| 167 |
+
"learning_rate": 3.5031847133757957e-07,
|
| 168 |
+
"logits/generated": -2.871616840362549,
|
| 169 |
+
"logits/real": -2.663942813873291,
|
| 170 |
+
"logps/generated": -157.40907287597656,
|
| 171 |
+
"logps/real": -136.9542236328125,
|
| 172 |
+
"loss": 0.013,
|
| 173 |
"rewards/accuracies": 1.0,
|
| 174 |
+
"rewards/generated": -6.357569694519043,
|
| 175 |
+
"rewards/margins": 7.108318328857422,
|
| 176 |
+
"rewards/real": 0.7507485151290894,
|
| 177 |
"step": 110
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 3.8216560509554143e-07,
|
| 182 |
+
"logits/generated": -2.8702244758605957,
|
| 183 |
+
"logits/real": -2.6590588092803955,
|
| 184 |
+
"logps/generated": -170.4289093017578,
|
| 185 |
+
"logps/real": -124.03118896484375,
|
| 186 |
+
"loss": 0.0223,
|
| 187 |
"rewards/accuracies": 1.0,
|
| 188 |
+
"rewards/generated": -7.1928534507751465,
|
| 189 |
+
"rewards/margins": 7.969223976135254,
|
| 190 |
+
"rewards/real": 0.7763701677322388,
|
| 191 |
"step": 120
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.08,
|
| 195 |
+
"learning_rate": 4.140127388535032e-07,
|
| 196 |
+
"logits/generated": -2.8153131008148193,
|
| 197 |
+
"logits/real": -2.6566903591156006,
|
| 198 |
+
"logps/generated": -167.2792510986328,
|
| 199 |
+
"logps/real": -136.0323486328125,
|
| 200 |
+
"loss": 0.0241,
|
| 201 |
+
"rewards/accuracies": 0.987500011920929,
|
| 202 |
+
"rewards/generated": -7.404214382171631,
|
| 203 |
+
"rewards/margins": 7.8729753494262695,
|
| 204 |
+
"rewards/real": 0.46876010298728943,
|
| 205 |
"step": 130
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.09,
|
| 209 |
+
"learning_rate": 4.4585987261146494e-07,
|
| 210 |
+
"logits/generated": -2.8306140899658203,
|
| 211 |
+
"logits/real": -2.5934805870056152,
|
| 212 |
+
"logps/generated": -177.410400390625,
|
| 213 |
+
"logps/real": -118.83491516113281,
|
| 214 |
+
"loss": 0.009,
|
| 215 |
+
"rewards/accuracies": 1.0,
|
| 216 |
+
"rewards/generated": -8.25102710723877,
|
| 217 |
+
"rewards/margins": 8.96755599975586,
|
| 218 |
+
"rewards/real": 0.7165282368659973,
|
| 219 |
"step": 140
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 4.777070063694267e-07,
|
| 224 |
+
"logits/generated": -2.7984092235565186,
|
| 225 |
+
"logits/real": -2.5605010986328125,
|
| 226 |
+
"logps/generated": -189.8646697998047,
|
| 227 |
+
"logps/real": -135.84613037109375,
|
| 228 |
+
"loss": 0.0126,
|
| 229 |
+
"rewards/accuracies": 1.0,
|
| 230 |
+
"rewards/generated": -9.167638778686523,
|
| 231 |
+
"rewards/margins": 9.189529418945312,
|
| 232 |
+
"rewards/real": 0.02189045585691929,
|
| 233 |
"step": 150
|
| 234 |
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1,
|
| 237 |
+
"learning_rate": 4.989331436699858e-07,
|
| 238 |
+
"logits/generated": -2.7396292686462402,
|
| 239 |
+
"logits/real": -2.4274842739105225,
|
| 240 |
+
"logps/generated": -193.1374969482422,
|
| 241 |
+
"logps/real": -132.30447387695312,
|
| 242 |
+
"loss": 0.0128,
|
| 243 |
+
"rewards/accuracies": 1.0,
|
| 244 |
+
"rewards/generated": -9.727991104125977,
|
| 245 |
+
"rewards/margins": 9.82439136505127,
|
| 246 |
+
"rewards/real": 0.09639892727136612,
|
| 247 |
+
"step": 160
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11,
|
| 251 |
+
"learning_rate": 4.953769559032717e-07,
|
| 252 |
+
"logits/generated": -2.6616251468658447,
|
| 253 |
+
"logits/real": -2.3478448390960693,
|
| 254 |
+
"logps/generated": -217.52468872070312,
|
| 255 |
+
"logps/real": -131.3321533203125,
|
| 256 |
+
"loss": 0.0058,
|
| 257 |
+
"rewards/accuracies": 1.0,
|
| 258 |
+
"rewards/generated": -11.674753189086914,
|
| 259 |
+
"rewards/margins": 11.104844093322754,
|
| 260 |
+
"rewards/real": -0.5699089765548706,
|
| 261 |
+
"step": 170
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 4.918207681365576e-07,
|
| 266 |
+
"logits/generated": -2.6591293811798096,
|
| 267 |
+
"logits/real": -2.494908571243286,
|
| 268 |
+
"logps/generated": -206.00320434570312,
|
| 269 |
+
"logps/real": -150.77288818359375,
|
| 270 |
+
"loss": 0.0142,
|
| 271 |
+
"rewards/accuracies": 1.0,
|
| 272 |
+
"rewards/generated": -11.094930648803711,
|
| 273 |
+
"rewards/margins": 10.854555130004883,
|
| 274 |
+
"rewards/real": -0.24037650227546692,
|
| 275 |
+
"step": 180
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12,
|
| 279 |
+
"learning_rate": 4.882645803698435e-07,
|
| 280 |
+
"logits/generated": -2.8326282501220703,
|
| 281 |
+
"logits/real": -2.6284682750701904,
|
| 282 |
+
"logps/generated": -179.343505859375,
|
| 283 |
+
"logps/real": -135.4120635986328,
|
| 284 |
+
"loss": 0.0122,
|
| 285 |
+
"rewards/accuracies": 1.0,
|
| 286 |
+
"rewards/generated": -8.551453590393066,
|
| 287 |
+
"rewards/margins": 9.140141487121582,
|
| 288 |
+
"rewards/real": 0.5886881947517395,
|
| 289 |
+
"step": 190
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13,
|
| 293 |
+
"learning_rate": 4.847083926031294e-07,
|
| 294 |
+
"logits/generated": -2.8262526988983154,
|
| 295 |
+
"logits/real": -2.5684738159179688,
|
| 296 |
+
"logps/generated": -193.8768310546875,
|
| 297 |
+
"logps/real": -124.94401550292969,
|
| 298 |
+
"loss": 0.0162,
|
| 299 |
+
"rewards/accuracies": 1.0,
|
| 300 |
+
"rewards/generated": -9.435348510742188,
|
| 301 |
+
"rewards/margins": 9.74295711517334,
|
| 302 |
+
"rewards/real": 0.30760902166366577,
|
| 303 |
+
"step": 200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13,
|
| 307 |
+
"learning_rate": 4.811522048364154e-07,
|
| 308 |
+
"logits/generated": -2.79144024848938,
|
| 309 |
+
"logits/real": -2.559652805328369,
|
| 310 |
+
"logps/generated": -190.53530883789062,
|
| 311 |
+
"logps/real": -120.87144470214844,
|
| 312 |
+
"loss": 0.0062,
|
| 313 |
+
"rewards/accuracies": 1.0,
|
| 314 |
+
"rewards/generated": -9.56157112121582,
|
| 315 |
+
"rewards/margins": 9.428454399108887,
|
| 316 |
+
"rewards/real": -0.13311485946178436,
|
| 317 |
+
"step": 210
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.14,
|
| 321 |
+
"learning_rate": 4.775960170697012e-07,
|
| 322 |
+
"logits/generated": -2.811436891555786,
|
| 323 |
+
"logits/real": -2.487448215484619,
|
| 324 |
+
"logps/generated": -193.6876678466797,
|
| 325 |
+
"logps/real": -121.51069641113281,
|
| 326 |
+
"loss": 0.0082,
|
| 327 |
+
"rewards/accuracies": 1.0,
|
| 328 |
+
"rewards/generated": -9.918183326721191,
|
| 329 |
+
"rewards/margins": 9.770201683044434,
|
| 330 |
+
"rewards/real": -0.14798107743263245,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15,
|
| 335 |
+
"learning_rate": 4.7403982930298717e-07,
|
| 336 |
+
"logits/generated": -2.734006643295288,
|
| 337 |
+
"logits/real": -2.4587738513946533,
|
| 338 |
+
"logps/generated": -213.60696411132812,
|
| 339 |
+
"logps/real": -130.74220275878906,
|
| 340 |
+
"loss": 0.0071,
|
| 341 |
+
"rewards/accuracies": 1.0,
|
| 342 |
+
"rewards/generated": -11.748188972473145,
|
| 343 |
+
"rewards/margins": 11.48717975616455,
|
| 344 |
+
"rewards/real": -0.2610093653202057,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15,
|
| 349 |
+
"learning_rate": 4.7048364153627306e-07,
|
| 350 |
+
"logits/generated": -2.730823516845703,
|
| 351 |
+
"logits/real": -2.5302836894989014,
|
| 352 |
+
"logps/generated": -219.81698608398438,
|
| 353 |
+
"logps/real": -161.82106018066406,
|
| 354 |
+
"loss": 0.0057,
|
| 355 |
+
"rewards/accuracies": 1.0,
|
| 356 |
+
"rewards/generated": -12.201372146606445,
|
| 357 |
+
"rewards/margins": 11.630053520202637,
|
| 358 |
+
"rewards/real": -0.5713191628456116,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16,
|
| 363 |
+
"learning_rate": 4.66927453769559e-07,
|
| 364 |
+
"logits/generated": -2.729020595550537,
|
| 365 |
+
"logits/real": -2.496598720550537,
|
| 366 |
+
"logps/generated": -215.9888153076172,
|
| 367 |
+
"logps/real": -128.60816955566406,
|
| 368 |
+
"loss": 0.0045,
|
| 369 |
+
"rewards/accuracies": 1.0,
|
| 370 |
+
"rewards/generated": -11.882211685180664,
|
| 371 |
+
"rewards/margins": 11.468908309936523,
|
| 372 |
+
"rewards/real": -0.41330498456954956,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.17,
|
| 377 |
+
"learning_rate": 4.633712660028449e-07,
|
| 378 |
+
"logits/generated": -2.7439448833465576,
|
| 379 |
+
"logits/real": -2.3727543354034424,
|
| 380 |
+
"logps/generated": -228.0956268310547,
|
| 381 |
+
"logps/real": -129.4033966064453,
|
| 382 |
+
"loss": 0.003,
|
| 383 |
+
"rewards/accuracies": 1.0,
|
| 384 |
+
"rewards/generated": -12.761183738708496,
|
| 385 |
+
"rewards/margins": 12.336984634399414,
|
| 386 |
+
"rewards/real": -0.424199640750885,
|
| 387 |
+
"step": 260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17,
|
| 391 |
+
"learning_rate": 4.5981507823613085e-07,
|
| 392 |
+
"logits/generated": -2.7314658164978027,
|
| 393 |
+
"logits/real": -2.4101929664611816,
|
| 394 |
+
"logps/generated": -214.00106811523438,
|
| 395 |
+
"logps/real": -134.43858337402344,
|
| 396 |
+
"loss": 0.0052,
|
| 397 |
+
"rewards/accuracies": 1.0,
|
| 398 |
+
"rewards/generated": -12.232887268066406,
|
| 399 |
+
"rewards/margins": 11.716353416442871,
|
| 400 |
+
"rewards/real": -0.5165335536003113,
|
| 401 |
+
"step": 270
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.18,
|
| 405 |
+
"learning_rate": 4.562588904694168e-07,
|
| 406 |
+
"logits/generated": -2.689013719558716,
|
| 407 |
+
"logits/real": -2.4268341064453125,
|
| 408 |
+
"logps/generated": -228.33651733398438,
|
| 409 |
+
"logps/real": -147.5162811279297,
|
| 410 |
+
"loss": 0.0043,
|
| 411 |
+
"rewards/accuracies": 1.0,
|
| 412 |
+
"rewards/generated": -13.618290901184082,
|
| 413 |
+
"rewards/margins": 12.699493408203125,
|
| 414 |
+
"rewards/real": -0.9187966585159302,
|
| 415 |
+
"step": 280
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19,
|
| 419 |
+
"learning_rate": 4.5270270270270264e-07,
|
| 420 |
+
"logits/generated": -2.7094247341156006,
|
| 421 |
+
"logits/real": -2.386305332183838,
|
| 422 |
+
"logps/generated": -246.9062957763672,
|
| 423 |
+
"logps/real": -146.25164794921875,
|
| 424 |
+
"loss": 0.003,
|
| 425 |
+
"rewards/accuracies": 1.0,
|
| 426 |
+
"rewards/generated": -14.869857788085938,
|
| 427 |
+
"rewards/margins": 13.668147087097168,
|
| 428 |
+
"rewards/real": -1.2017114162445068,
|
| 429 |
+
"step": 290
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"learning_rate": 4.491465149359886e-07,
|
| 434 |
+
"logits/generated": -2.680655002593994,
|
| 435 |
+
"logits/real": -2.3289406299591064,
|
| 436 |
+
"logps/generated": -234.94284057617188,
|
| 437 |
+
"logps/real": -133.91293334960938,
|
| 438 |
+
"loss": 0.0024,
|
| 439 |
+
"rewards/accuracies": 1.0,
|
| 440 |
+
"rewards/generated": -14.264216423034668,
|
| 441 |
+
"rewards/margins": 13.502108573913574,
|
| 442 |
+
"rewards/real": -0.7621089220046997,
|
| 443 |
+
"step": 300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2,
|
| 447 |
+
"learning_rate": 4.4559032716927454e-07,
|
| 448 |
+
"logits/generated": -2.669834852218628,
|
| 449 |
+
"logits/real": -2.4426522254943848,
|
| 450 |
+
"logps/generated": -245.8262939453125,
|
| 451 |
+
"logps/real": -157.44009399414062,
|
| 452 |
+
"loss": 0.0032,
|
| 453 |
+
"rewards/accuracies": 1.0,
|
| 454 |
+
"rewards/generated": -14.951329231262207,
|
| 455 |
+
"rewards/margins": 14.07829761505127,
|
| 456 |
+
"rewards/real": -0.8730317950248718,
|
| 457 |
+
"step": 310
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2,
|
| 461 |
+
"learning_rate": 4.420341394025605e-07,
|
| 462 |
+
"logits/generated": -2.663137912750244,
|
| 463 |
+
"logits/real": -2.422542095184326,
|
| 464 |
+
"logps/generated": -252.69107055664062,
|
| 465 |
+
"logps/real": -147.78504943847656,
|
| 466 |
+
"loss": 0.0014,
|
| 467 |
+
"rewards/accuracies": 1.0,
|
| 468 |
+
"rewards/generated": -15.78465747833252,
|
| 469 |
+
"rewards/margins": 14.772485733032227,
|
| 470 |
+
"rewards/real": -1.0121715068817139,
|
| 471 |
+
"step": 320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"learning_rate": 4.384779516358463e-07,
|
| 476 |
+
"logits/generated": -2.630758762359619,
|
| 477 |
+
"logits/real": -2.3742423057556152,
|
| 478 |
+
"logps/generated": -244.6441192626953,
|
| 479 |
+
"logps/real": -161.9650421142578,
|
| 480 |
+
"loss": 0.0035,
|
| 481 |
+
"rewards/accuracies": 1.0,
|
| 482 |
+
"rewards/generated": -15.519983291625977,
|
| 483 |
+
"rewards/margins": 13.414645195007324,
|
| 484 |
+
"rewards/real": -2.1053380966186523,
|
| 485 |
+
"step": 330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.22,
|
| 489 |
+
"learning_rate": 4.3492176386913227e-07,
|
| 490 |
+
"logits/generated": -2.6415796279907227,
|
| 491 |
+
"logits/real": -2.356398105621338,
|
| 492 |
+
"logps/generated": -267.1407775878906,
|
| 493 |
+
"logps/real": -170.39505004882812,
|
| 494 |
+
"loss": 0.0016,
|
| 495 |
+
"rewards/accuracies": 1.0,
|
| 496 |
+
"rewards/generated": -17.32520866394043,
|
| 497 |
+
"rewards/margins": 14.95826244354248,
|
| 498 |
+
"rewards/real": -2.366948366165161,
|
| 499 |
+
"step": 340
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.22,
|
| 503 |
+
"learning_rate": 4.313655761024182e-07,
|
| 504 |
+
"logits/generated": -2.624446153640747,
|
| 505 |
+
"logits/real": -2.2451043128967285,
|
| 506 |
+
"logps/generated": -271.24444580078125,
|
| 507 |
+
"logps/real": -170.41299438476562,
|
| 508 |
+
"loss": 0.0023,
|
| 509 |
+
"rewards/accuracies": 1.0,
|
| 510 |
+
"rewards/generated": -18.118497848510742,
|
| 511 |
+
"rewards/margins": 14.8461332321167,
|
| 512 |
+
"rewards/real": -3.2723660469055176,
|
| 513 |
+
"step": 350
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"learning_rate": 4.278093883357041e-07,
|
| 518 |
+
"logits/generated": -2.638278007507324,
|
| 519 |
+
"logits/real": -2.3009445667266846,
|
| 520 |
+
"logps/generated": -258.6704406738281,
|
| 521 |
+
"logps/real": -148.07969665527344,
|
| 522 |
+
"loss": 0.0031,
|
| 523 |
+
"rewards/accuracies": 1.0,
|
| 524 |
+
"rewards/generated": -16.391494750976562,
|
| 525 |
+
"rewards/margins": 15.001701354980469,
|
| 526 |
+
"rewards/real": -1.3897945880889893,
|
| 527 |
+
"step": 360
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24,
|
| 531 |
+
"learning_rate": 4.2425320056899e-07,
|
| 532 |
+
"logits/generated": -2.621098756790161,
|
| 533 |
+
"logits/real": -2.34078049659729,
|
| 534 |
+
"logps/generated": -257.48077392578125,
|
| 535 |
+
"logps/real": -169.0782470703125,
|
| 536 |
+
"loss": 0.0015,
|
| 537 |
+
"rewards/accuracies": 1.0,
|
| 538 |
+
"rewards/generated": -16.38188934326172,
|
| 539 |
+
"rewards/margins": 14.900436401367188,
|
| 540 |
+
"rewards/real": -1.4814506769180298,
|
| 541 |
+
"step": 370
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.24,
|
| 545 |
+
"learning_rate": 4.2069701280227595e-07,
|
| 546 |
+
"logits/generated": -2.597550392150879,
|
| 547 |
+
"logits/real": -2.2361397743225098,
|
| 548 |
+
"logps/generated": -276.8401184082031,
|
| 549 |
+
"logps/real": -160.2169189453125,
|
| 550 |
+
"loss": 0.0022,
|
| 551 |
+
"rewards/accuracies": 1.0,
|
| 552 |
+
"rewards/generated": -17.763856887817383,
|
| 553 |
+
"rewards/margins": 16.03007698059082,
|
| 554 |
+
"rewards/real": -1.7337779998779297,
|
| 555 |
+
"step": 380
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"learning_rate": 4.1714082503556185e-07,
|
| 560 |
+
"logits/generated": -2.5919480323791504,
|
| 561 |
+
"logits/real": -2.3185667991638184,
|
| 562 |
+
"logps/generated": -278.0733947753906,
|
| 563 |
+
"logps/real": -163.49391174316406,
|
| 564 |
+
"loss": 0.002,
|
| 565 |
+
"rewards/accuracies": 1.0,
|
| 566 |
+
"rewards/generated": -18.25893783569336,
|
| 567 |
+
"rewards/margins": 15.166206359863281,
|
| 568 |
+
"rewards/real": -3.0927340984344482,
|
| 569 |
+
"step": 390
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.26,
|
| 573 |
+
"learning_rate": 4.135846372688478e-07,
|
| 574 |
+
"logits/generated": -2.635617971420288,
|
| 575 |
+
"logits/real": -2.3077096939086914,
|
| 576 |
+
"logps/generated": -234.7008056640625,
|
| 577 |
+
"logps/real": -155.15969848632812,
|
| 578 |
+
"loss": 0.0046,
|
| 579 |
+
"rewards/accuracies": 1.0,
|
| 580 |
+
"rewards/generated": -15.043414115905762,
|
| 581 |
+
"rewards/margins": 13.307294845581055,
|
| 582 |
+
"rewards/real": -1.7361185550689697,
|
| 583 |
+
"step": 400
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.26,
|
| 587 |
+
"learning_rate": 4.100284495021337e-07,
|
| 588 |
+
"logits/generated": -2.6545605659484863,
|
| 589 |
+
"logits/real": -2.3340840339660645,
|
| 590 |
+
"logps/generated": -252.66220092773438,
|
| 591 |
+
"logps/real": -143.4952850341797,
|
| 592 |
+
"loss": 0.0018,
|
| 593 |
+
"rewards/accuracies": 1.0,
|
| 594 |
+
"rewards/generated": -15.794622421264648,
|
| 595 |
+
"rewards/margins": 14.8565673828125,
|
| 596 |
+
"rewards/real": -0.9380534291267395,
|
| 597 |
+
"step": 410
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"learning_rate": 4.064722617354196e-07,
|
| 602 |
+
"logits/generated": -2.6176822185516357,
|
| 603 |
+
"logits/real": -2.291186809539795,
|
| 604 |
+
"logps/generated": -255.0669403076172,
|
| 605 |
+
"logps/real": -150.9188995361328,
|
| 606 |
+
"loss": 0.0036,
|
| 607 |
+
"rewards/accuracies": 1.0,
|
| 608 |
+
"rewards/generated": -16.221405029296875,
|
| 609 |
+
"rewards/margins": 14.909570693969727,
|
| 610 |
+
"rewards/real": -1.3118356466293335,
|
| 611 |
+
"step": 420
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.28,
|
| 615 |
+
"learning_rate": 4.0291607396870553e-07,
|
| 616 |
+
"logits/generated": -2.636864185333252,
|
| 617 |
+
"logits/real": -2.341648578643799,
|
| 618 |
+
"logps/generated": -249.6366424560547,
|
| 619 |
+
"logps/real": -140.9087677001953,
|
| 620 |
+
"loss": 0.0023,
|
| 621 |
+
"rewards/accuracies": 1.0,
|
| 622 |
+
"rewards/generated": -16.15219497680664,
|
| 623 |
+
"rewards/margins": 14.91722583770752,
|
| 624 |
+
"rewards/real": -1.23496675491333,
|
| 625 |
+
"step": 430
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.28,
|
| 629 |
+
"learning_rate": 3.993598862019915e-07,
|
| 630 |
+
"logits/generated": -2.6465516090393066,
|
| 631 |
+
"logits/real": -2.3501453399658203,
|
| 632 |
+
"logps/generated": -243.95895385742188,
|
| 633 |
+
"logps/real": -155.9197998046875,
|
| 634 |
+
"loss": 0.0097,
|
| 635 |
+
"rewards/accuracies": 1.0,
|
| 636 |
+
"rewards/generated": -15.268379211425781,
|
| 637 |
+
"rewards/margins": 12.943562507629395,
|
| 638 |
+
"rewards/real": -2.3248181343078613,
|
| 639 |
+
"step": 440
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"learning_rate": 3.9580369843527737e-07,
|
| 644 |
+
"logits/generated": -2.683403491973877,
|
| 645 |
+
"logits/real": -2.467794418334961,
|
| 646 |
+
"logps/generated": -246.9853057861328,
|
| 647 |
+
"logps/real": -143.61874389648438,
|
| 648 |
+
"loss": 0.001,
|
| 649 |
+
"rewards/accuracies": 1.0,
|
| 650 |
+
"rewards/generated": -14.511987686157227,
|
| 651 |
+
"rewards/margins": 13.070988655090332,
|
| 652 |
+
"rewards/real": -1.4409997463226318,
|
| 653 |
+
"step": 450
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.29,
|
| 657 |
+
"learning_rate": 3.9224751066856327e-07,
|
| 658 |
+
"logits/generated": -2.646587610244751,
|
| 659 |
+
"logits/real": -2.513019323348999,
|
| 660 |
+
"logps/generated": -249.4457550048828,
|
| 661 |
+
"logps/real": -171.30072021484375,
|
| 662 |
+
"loss": 0.0042,
|
| 663 |
+
"rewards/accuracies": 1.0,
|
| 664 |
+
"rewards/generated": -15.091230392456055,
|
| 665 |
+
"rewards/margins": 13.882911682128906,
|
| 666 |
+
"rewards/real": -1.2083193063735962,
|
| 667 |
+
"step": 460
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3,
|
| 671 |
+
"learning_rate": 3.886913229018492e-07,
|
| 672 |
+
"logits/generated": -2.6025052070617676,
|
| 673 |
+
"logits/real": -2.308351993560791,
|
| 674 |
+
"logps/generated": -260.1772155761719,
|
| 675 |
+
"logps/real": -152.1533660888672,
|
| 676 |
+
"loss": 0.0053,
|
| 677 |
+
"rewards/accuracies": 1.0,
|
| 678 |
+
"rewards/generated": -16.5654296875,
|
| 679 |
+
"rewards/margins": 14.767765998840332,
|
| 680 |
+
"rewards/real": -1.7976620197296143,
|
| 681 |
+
"step": 470
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.31,
|
| 685 |
+
"learning_rate": 3.851351351351351e-07,
|
| 686 |
+
"logits/generated": -2.6486258506774902,
|
| 687 |
+
"logits/real": -2.34824538230896,
|
| 688 |
+
"logps/generated": -243.5570831298828,
|
| 689 |
+
"logps/real": -147.68495178222656,
|
| 690 |
+
"loss": 0.0038,
|
| 691 |
+
"rewards/accuracies": 1.0,
|
| 692 |
+
"rewards/generated": -15.00477123260498,
|
| 693 |
+
"rewards/margins": 14.016987800598145,
|
| 694 |
+
"rewards/real": -0.9877821207046509,
|
| 695 |
+
"step": 480
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.31,
|
| 699 |
+
"learning_rate": 3.8157894736842105e-07,
|
| 700 |
+
"logits/generated": -2.6565589904785156,
|
| 701 |
+
"logits/real": -2.3215975761413574,
|
| 702 |
+
"logps/generated": -236.3148193359375,
|
| 703 |
+
"logps/real": -132.85011291503906,
|
| 704 |
+
"loss": 0.0023,
|
| 705 |
+
"rewards/accuracies": 1.0,
|
| 706 |
+
"rewards/generated": -14.406427383422852,
|
| 707 |
+
"rewards/margins": 13.613751411437988,
|
| 708 |
+
"rewards/real": -0.7926777601242065,
|
| 709 |
+
"step": 490
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.32,
|
| 713 |
+
"learning_rate": 3.7802275960170695e-07,
|
| 714 |
+
"logits/generated": -2.664989471435547,
|
| 715 |
+
"logits/real": -2.4229531288146973,
|
| 716 |
+
"logps/generated": -260.98944091796875,
|
| 717 |
+
"logps/real": -142.20501708984375,
|
| 718 |
+
"loss": 0.0039,
|
| 719 |
+
"rewards/accuracies": 1.0,
|
| 720 |
+
"rewards/generated": -16.135055541992188,
|
| 721 |
+
"rewards/margins": 15.381479263305664,
|
| 722 |
+
"rewards/real": -0.753574550151825,
|
| 723 |
+
"step": 500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.33,
|
| 727 |
+
"learning_rate": 3.7446657183499284e-07,
|
| 728 |
+
"logits/generated": -2.6360857486724854,
|
| 729 |
+
"logits/real": -2.356961488723755,
|
| 730 |
+
"logps/generated": -251.55740356445312,
|
| 731 |
+
"logps/real": -146.3067169189453,
|
| 732 |
+
"loss": 0.0004,
|
| 733 |
+
"rewards/accuracies": 1.0,
|
| 734 |
+
"rewards/generated": -15.945223808288574,
|
| 735 |
+
"rewards/margins": 14.57160758972168,
|
| 736 |
+
"rewards/real": -1.373616337776184,
|
| 737 |
+
"step": 510
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.33,
|
| 741 |
+
"learning_rate": 3.709103840682788e-07,
|
| 742 |
+
"logits/generated": -2.627017021179199,
|
| 743 |
+
"logits/real": -2.3511900901794434,
|
| 744 |
+
"logps/generated": -256.36798095703125,
|
| 745 |
+
"logps/real": -142.99703979492188,
|
| 746 |
+
"loss": 0.001,
|
| 747 |
+
"rewards/accuracies": 1.0,
|
| 748 |
+
"rewards/generated": -16.528518676757812,
|
| 749 |
+
"rewards/margins": 15.134465217590332,
|
| 750 |
+
"rewards/real": -1.394053339958191,
|
| 751 |
+
"step": 520
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.34,
|
| 755 |
+
"learning_rate": 3.6735419630156474e-07,
|
| 756 |
+
"logits/generated": -2.587278366088867,
|
| 757 |
+
"logits/real": -2.248208999633789,
|
| 758 |
+
"logps/generated": -266.53668212890625,
|
| 759 |
+
"logps/real": -140.9051971435547,
|
| 760 |
+
"loss": 0.0015,
|
| 761 |
+
"rewards/accuracies": 1.0,
|
| 762 |
+
"rewards/generated": -17.05879020690918,
|
| 763 |
+
"rewards/margins": 15.273892402648926,
|
| 764 |
+
"rewards/real": -1.7848970890045166,
|
| 765 |
+
"step": 530
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.35,
|
| 769 |
+
"learning_rate": 3.637980085348506e-07,
|
| 770 |
+
"logits/generated": -2.5869765281677246,
|
| 771 |
+
"logits/real": -2.275988817214966,
|
| 772 |
+
"logps/generated": -267.7913513183594,
|
| 773 |
+
"logps/real": -154.5830078125,
|
| 774 |
+
"loss": 0.0041,
|
| 775 |
+
"rewards/accuracies": 1.0,
|
| 776 |
+
"rewards/generated": -17.560646057128906,
|
| 777 |
+
"rewards/margins": 15.521791458129883,
|
| 778 |
+
"rewards/real": -2.038856267929077,
|
| 779 |
+
"step": 540
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.35,
|
| 783 |
+
"learning_rate": 3.602418207681365e-07,
|
| 784 |
+
"logits/generated": -2.610684871673584,
|
| 785 |
+
"logits/real": -2.302337169647217,
|
| 786 |
+
"logps/generated": -264.52764892578125,
|
| 787 |
+
"logps/real": -150.14028930664062,
|
| 788 |
+
"loss": 0.0013,
|
| 789 |
+
"rewards/accuracies": 1.0,
|
| 790 |
+
"rewards/generated": -16.939865112304688,
|
| 791 |
+
"rewards/margins": 15.928593635559082,
|
| 792 |
+
"rewards/real": -1.01127028465271,
|
| 793 |
+
"step": 550
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.36,
|
| 797 |
+
"learning_rate": 3.5668563300142247e-07,
|
| 798 |
+
"logits/generated": -2.5956525802612305,
|
| 799 |
+
"logits/real": -2.34203839302063,
|
| 800 |
+
"logps/generated": -273.79949951171875,
|
| 801 |
+
"logps/real": -144.4397430419922,
|
| 802 |
+
"loss": 0.0006,
|
| 803 |
+
"rewards/accuracies": 1.0,
|
| 804 |
+
"rewards/generated": -17.865262985229492,
|
| 805 |
+
"rewards/margins": 16.40726661682129,
|
| 806 |
+
"rewards/real": -1.4579969644546509,
|
| 807 |
+
"step": 560
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.36,
|
| 811 |
+
"learning_rate": 3.5312944523470837e-07,
|
| 812 |
+
"logits/generated": -2.558427095413208,
|
| 813 |
+
"logits/real": -2.191371440887451,
|
| 814 |
+
"logps/generated": -286.45184326171875,
|
| 815 |
+
"logps/real": -154.03485107421875,
|
| 816 |
+
"loss": 0.0003,
|
| 817 |
+
"rewards/accuracies": 1.0,
|
| 818 |
+
"rewards/generated": -19.122371673583984,
|
| 819 |
+
"rewards/margins": 16.966218948364258,
|
| 820 |
+
"rewards/real": -2.156151294708252,
|
| 821 |
+
"step": 570
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.37,
|
| 825 |
+
"learning_rate": 3.495732574679943e-07,
|
| 826 |
+
"logits/generated": -2.5747647285461426,
|
| 827 |
+
"logits/real": -2.2839667797088623,
|
| 828 |
+
"logps/generated": -280.7036437988281,
|
| 829 |
+
"logps/real": -149.42234802246094,
|
| 830 |
+
"loss": 0.0036,
|
| 831 |
+
"rewards/accuracies": 1.0,
|
| 832 |
+
"rewards/generated": -18.820329666137695,
|
| 833 |
+
"rewards/margins": 16.973482131958008,
|
| 834 |
+
"rewards/real": -1.8468481302261353,
|
| 835 |
+
"step": 580
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.38,
|
| 839 |
+
"learning_rate": 3.460170697012802e-07,
|
| 840 |
+
"logits/generated": -2.647414445877075,
|
| 841 |
+
"logits/real": -2.311011791229248,
|
| 842 |
+
"logps/generated": -271.14031982421875,
|
| 843 |
+
"logps/real": -145.47608947753906,
|
| 844 |
+
"loss": 0.0024,
|
| 845 |
+
"rewards/accuracies": 1.0,
|
| 846 |
+
"rewards/generated": -16.740116119384766,
|
| 847 |
+
"rewards/margins": 15.668981552124023,
|
| 848 |
+
"rewards/real": -1.0711352825164795,
|
| 849 |
+
"step": 590
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.38,
|
| 853 |
+
"learning_rate": 3.424608819345661e-07,
|
| 854 |
+
"logits/generated": -2.6572697162628174,
|
| 855 |
+
"logits/real": -2.2757163047790527,
|
| 856 |
+
"logps/generated": -256.30584716796875,
|
| 857 |
+
"logps/real": -147.24533081054688,
|
| 858 |
+
"loss": 0.0011,
|
| 859 |
+
"rewards/accuracies": 1.0,
|
| 860 |
+
"rewards/generated": -16.026338577270508,
|
| 861 |
+
"rewards/margins": 14.143951416015625,
|
| 862 |
+
"rewards/real": -1.8823878765106201,
|
| 863 |
+
"step": 600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.39,
|
| 867 |
+
"learning_rate": 3.3890469416785205e-07,
|
| 868 |
+
"logits/generated": -2.6201155185699463,
|
| 869 |
+
"logits/real": -2.3046302795410156,
|
| 870 |
+
"logps/generated": -271.51690673828125,
|
| 871 |
+
"logps/real": -159.52593994140625,
|
| 872 |
+
"loss": 0.0026,
|
| 873 |
+
"rewards/accuracies": 1.0,
|
| 874 |
+
"rewards/generated": -17.70832633972168,
|
| 875 |
+
"rewards/margins": 15.127041816711426,
|
| 876 |
+
"rewards/real": -2.581282377243042,
|
| 877 |
+
"step": 610
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4,
|
| 881 |
+
"learning_rate": 3.35348506401138e-07,
|
| 882 |
+
"logits/generated": -2.5929877758026123,
|
| 883 |
+
"logits/real": -2.066601514816284,
|
| 884 |
+
"logps/generated": -276.5373229980469,
|
| 885 |
+
"logps/real": -151.35279846191406,
|
| 886 |
+
"loss": 0.0014,
|
| 887 |
+
"rewards/accuracies": 1.0,
|
| 888 |
+
"rewards/generated": -17.873516082763672,
|
| 889 |
+
"rewards/margins": 15.789881706237793,
|
| 890 |
+
"rewards/real": -2.083634376525879,
|
| 891 |
+
"step": 620
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4,
|
| 895 |
+
"learning_rate": 3.3179231863442384e-07,
|
| 896 |
+
"logits/generated": -2.5061452388763428,
|
| 897 |
+
"logits/real": -2.165194511413574,
|
| 898 |
+
"logps/generated": -269.43182373046875,
|
| 899 |
+
"logps/real": -167.6754150390625,
|
| 900 |
+
"loss": 0.0008,
|
| 901 |
+
"rewards/accuracies": 1.0,
|
| 902 |
+
"rewards/generated": -17.984777450561523,
|
| 903 |
+
"rewards/margins": 15.614283561706543,
|
| 904 |
+
"rewards/real": -2.370495080947876,
|
| 905 |
+
"step": 630
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.41,
|
| 909 |
+
"learning_rate": 3.282361308677098e-07,
|
| 910 |
+
"logits/generated": -2.535046339035034,
|
| 911 |
+
"logits/real": -2.0150370597839355,
|
| 912 |
+
"logps/generated": -290.4701232910156,
|
| 913 |
+
"logps/real": -155.98748779296875,
|
| 914 |
+
"loss": 0.0009,
|
| 915 |
+
"rewards/accuracies": 1.0,
|
| 916 |
+
"rewards/generated": -19.04861068725586,
|
| 917 |
+
"rewards/margins": 17.140892028808594,
|
| 918 |
+
"rewards/real": -1.9077173471450806,
|
| 919 |
+
"step": 640
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.42,
|
| 923 |
+
"learning_rate": 3.2467994310099573e-07,
|
| 924 |
+
"logits/generated": -2.52227783203125,
|
| 925 |
+
"logits/real": -2.0042471885681152,
|
| 926 |
+
"logps/generated": -297.1048889160156,
|
| 927 |
+
"logps/real": -164.85296630859375,
|
| 928 |
+
"loss": 0.0005,
|
| 929 |
+
"rewards/accuracies": 1.0,
|
| 930 |
+
"rewards/generated": -19.86203384399414,
|
| 931 |
+
"rewards/margins": 18.030447006225586,
|
| 932 |
+
"rewards/real": -1.8315849304199219,
|
| 933 |
+
"step": 650
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.42,
|
| 937 |
+
"learning_rate": 3.211237553342817e-07,
|
| 938 |
+
"logits/generated": -2.4940333366394043,
|
| 939 |
+
"logits/real": -1.932329535484314,
|
| 940 |
+
"logps/generated": -293.40875244140625,
|
| 941 |
+
"logps/real": -152.46395874023438,
|
| 942 |
+
"loss": 0.001,
|
| 943 |
+
"rewards/accuracies": 1.0,
|
| 944 |
+
"rewards/generated": -19.75796890258789,
|
| 945 |
+
"rewards/margins": 17.733844757080078,
|
| 946 |
+
"rewards/real": -2.02412486076355,
|
| 947 |
+
"step": 660
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.43,
|
| 951 |
+
"learning_rate": 3.175675675675675e-07,
|
| 952 |
+
"logits/generated": -2.4778501987457275,
|
| 953 |
+
"logits/real": -1.9003286361694336,
|
| 954 |
+
"logps/generated": -285.62982177734375,
|
| 955 |
+
"logps/real": -146.41970825195312,
|
| 956 |
+
"loss": 0.0056,
|
| 957 |
+
"rewards/accuracies": 1.0,
|
| 958 |
+
"rewards/generated": -19.548839569091797,
|
| 959 |
+
"rewards/margins": 17.18503189086914,
|
| 960 |
+
"rewards/real": -2.363809823989868,
|
| 961 |
+
"step": 670
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.44,
|
| 965 |
+
"learning_rate": 3.1401137980085347e-07,
|
| 966 |
+
"logits/generated": -2.628258228302002,
|
| 967 |
+
"logits/real": -2.3583595752716064,
|
| 968 |
+
"logps/generated": -289.90972900390625,
|
| 969 |
+
"logps/real": -167.40670776367188,
|
| 970 |
+
"loss": 0.0063,
|
| 971 |
+
"rewards/accuracies": 0.987500011920929,
|
| 972 |
+
"rewards/generated": -19.053691864013672,
|
| 973 |
+
"rewards/margins": 15.783452987670898,
|
| 974 |
+
"rewards/real": -3.2702412605285645,
|
| 975 |
+
"step": 680
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.44,
|
| 979 |
+
"learning_rate": 3.104551920341394e-07,
|
| 980 |
+
"logits/generated": -2.6161983013153076,
|
| 981 |
+
"logits/real": -2.3759868144989014,
|
| 982 |
+
"logps/generated": -275.8905944824219,
|
| 983 |
+
"logps/real": -164.04794311523438,
|
| 984 |
+
"loss": 0.0027,
|
| 985 |
+
"rewards/accuracies": 1.0,
|
| 986 |
+
"rewards/generated": -18.127063751220703,
|
| 987 |
+
"rewards/margins": 15.362668991088867,
|
| 988 |
+
"rewards/real": -2.7643933296203613,
|
| 989 |
+
"step": 690
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.45,
|
| 993 |
+
"learning_rate": 3.068990042674253e-07,
|
| 994 |
+
"logits/generated": -2.63472318649292,
|
| 995 |
+
"logits/real": -2.4305763244628906,
|
| 996 |
+
"logps/generated": -252.68026733398438,
|
| 997 |
+
"logps/real": -149.27975463867188,
|
| 998 |
+
"loss": 0.0089,
|
| 999 |
+
"rewards/accuracies": 1.0,
|
| 1000 |
+
"rewards/generated": -16.35388946533203,
|
| 1001 |
+
"rewards/margins": 13.695645332336426,
|
| 1002 |
+
"rewards/real": -2.658242702484131,
|
| 1003 |
+
"step": 700
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.45,
|
| 1007 |
+
"learning_rate": 3.033428165007112e-07,
|
| 1008 |
+
"logits/generated": -2.6811423301696777,
|
| 1009 |
+
"logits/real": -2.379275321960449,
|
| 1010 |
+
"logps/generated": -289.7455139160156,
|
| 1011 |
+
"logps/real": -153.281005859375,
|
| 1012 |
+
"loss": 0.0016,
|
| 1013 |
+
"rewards/accuracies": 1.0,
|
| 1014 |
+
"rewards/generated": -18.906612396240234,
|
| 1015 |
+
"rewards/margins": 16.27779197692871,
|
| 1016 |
+
"rewards/real": -2.6288204193115234,
|
| 1017 |
+
"step": 710
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.46,
|
| 1021 |
+
"learning_rate": 2.9978662873399715e-07,
|
| 1022 |
+
"logits/generated": -2.642746686935425,
|
| 1023 |
+
"logits/real": -2.4080071449279785,
|
| 1024 |
+
"logps/generated": -280.27044677734375,
|
| 1025 |
+
"logps/real": -163.74325561523438,
|
| 1026 |
+
"loss": 0.0011,
|
| 1027 |
+
"rewards/accuracies": 1.0,
|
| 1028 |
+
"rewards/generated": -18.57528305053711,
|
| 1029 |
+
"rewards/margins": 15.842401504516602,
|
| 1030 |
+
"rewards/real": -2.7328832149505615,
|
| 1031 |
+
"step": 720
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.47,
|
| 1035 |
+
"learning_rate": 2.9623044096728305e-07,
|
| 1036 |
+
"logits/generated": -2.585597276687622,
|
| 1037 |
+
"logits/real": -2.384023666381836,
|
| 1038 |
+
"logps/generated": -289.5233459472656,
|
| 1039 |
+
"logps/real": -178.13461303710938,
|
| 1040 |
+
"loss": 0.0013,
|
| 1041 |
+
"rewards/accuracies": 1.0,
|
| 1042 |
+
"rewards/generated": -20.13193130493164,
|
| 1043 |
+
"rewards/margins": 17.022491455078125,
|
| 1044 |
+
"rewards/real": -3.1094412803649902,
|
| 1045 |
+
"step": 730
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.47,
|
| 1049 |
+
"learning_rate": 2.92674253200569e-07,
|
| 1050 |
+
"logits/generated": -2.564220428466797,
|
| 1051 |
+
"logits/real": -2.2639899253845215,
|
| 1052 |
+
"logps/generated": -318.0504455566406,
|
| 1053 |
+
"logps/real": -165.57601928710938,
|
| 1054 |
+
"loss": 0.0005,
|
| 1055 |
+
"rewards/accuracies": 1.0,
|
| 1056 |
+
"rewards/generated": -22.199588775634766,
|
| 1057 |
+
"rewards/margins": 19.12047004699707,
|
| 1058 |
+
"rewards/real": -3.0791163444519043,
|
| 1059 |
+
"step": 740
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.48,
|
| 1063 |
+
"learning_rate": 2.8911806543385494e-07,
|
| 1064 |
+
"logits/generated": -2.54494309425354,
|
| 1065 |
+
"logits/real": -2.243720054626465,
|
| 1066 |
+
"logps/generated": -335.9930114746094,
|
| 1067 |
+
"logps/real": -176.82962036132812,
|
| 1068 |
+
"loss": 0.0024,
|
| 1069 |
+
"rewards/accuracies": 1.0,
|
| 1070 |
+
"rewards/generated": -23.840442657470703,
|
| 1071 |
+
"rewards/margins": 21.033586502075195,
|
| 1072 |
+
"rewards/real": -2.8068575859069824,
|
| 1073 |
+
"step": 750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.49,
|
| 1077 |
+
"learning_rate": 2.855618776671408e-07,
|
| 1078 |
+
"logits/generated": -2.4757752418518066,
|
| 1079 |
+
"logits/real": -2.291566848754883,
|
| 1080 |
+
"logps/generated": -345.89788818359375,
|
| 1081 |
+
"logps/real": -186.32931518554688,
|
| 1082 |
+
"loss": 0.0011,
|
| 1083 |
+
"rewards/accuracies": 1.0,
|
| 1084 |
+
"rewards/generated": -24.59176254272461,
|
| 1085 |
+
"rewards/margins": 21.504487991333008,
|
| 1086 |
+
"rewards/real": -3.0872764587402344,
|
| 1087 |
+
"step": 760
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.49,
|
| 1091 |
+
"learning_rate": 2.8200568990042673e-07,
|
| 1092 |
+
"logits/generated": -2.4870519638061523,
|
| 1093 |
+
"logits/real": -2.2031798362731934,
|
| 1094 |
+
"logps/generated": -311.2699279785156,
|
| 1095 |
+
"logps/real": -153.85873413085938,
|
| 1096 |
+
"loss": 0.0007,
|
| 1097 |
+
"rewards/accuracies": 1.0,
|
| 1098 |
+
"rewards/generated": -21.774972915649414,
|
| 1099 |
+
"rewards/margins": 19.98200035095215,
|
| 1100 |
+
"rewards/real": -1.792970895767212,
|
| 1101 |
+
"step": 770
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5,
|
| 1105 |
+
"learning_rate": 2.784495021337127e-07,
|
| 1106 |
+
"logits/generated": -2.4991695880889893,
|
| 1107 |
+
"logits/real": -2.1358065605163574,
|
| 1108 |
+
"logps/generated": -317.76593017578125,
|
| 1109 |
+
"logps/real": -149.97769165039062,
|
| 1110 |
+
"loss": 0.0037,
|
| 1111 |
+
"rewards/accuracies": 1.0,
|
| 1112 |
+
"rewards/generated": -22.39531707763672,
|
| 1113 |
+
"rewards/margins": 19.940006256103516,
|
| 1114 |
+
"rewards/real": -2.455310821533203,
|
| 1115 |
+
"step": 780
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.51,
|
| 1119 |
+
"learning_rate": 2.7489331436699857e-07,
|
| 1120 |
+
"logits/generated": -2.4913153648376465,
|
| 1121 |
+
"logits/real": -2.2520499229431152,
|
| 1122 |
+
"logps/generated": -331.97198486328125,
|
| 1123 |
+
"logps/real": -168.5391845703125,
|
| 1124 |
+
"loss": 0.0005,
|
| 1125 |
+
"rewards/accuracies": 1.0,
|
| 1126 |
+
"rewards/generated": -23.301677703857422,
|
| 1127 |
+
"rewards/margins": 20.83787727355957,
|
| 1128 |
+
"rewards/real": -2.463801145553589,
|
| 1129 |
+
"step": 790
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.51,
|
| 1133 |
+
"learning_rate": 2.7133712660028446e-07,
|
| 1134 |
+
"logits/generated": -2.475283145904541,
|
| 1135 |
+
"logits/real": -2.12270188331604,
|
| 1136 |
+
"logps/generated": -358.60699462890625,
|
| 1137 |
+
"logps/real": -153.89566040039062,
|
| 1138 |
+
"loss": 0.0014,
|
| 1139 |
+
"rewards/accuracies": 1.0,
|
| 1140 |
+
"rewards/generated": -25.966594696044922,
|
| 1141 |
+
"rewards/margins": 23.213787078857422,
|
| 1142 |
+
"rewards/real": -2.752802848815918,
|
| 1143 |
+
"step": 800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.52,
|
| 1147 |
+
"learning_rate": 2.677809388335704e-07,
|
| 1148 |
+
"logits/generated": -2.552203893661499,
|
| 1149 |
+
"logits/real": -2.231297016143799,
|
| 1150 |
+
"logps/generated": -306.72418212890625,
|
| 1151 |
+
"logps/real": -151.74932861328125,
|
| 1152 |
+
"loss": 0.0047,
|
| 1153 |
+
"rewards/accuracies": 1.0,
|
| 1154 |
+
"rewards/generated": -21.487075805664062,
|
| 1155 |
+
"rewards/margins": 19.052860260009766,
|
| 1156 |
+
"rewards/real": -2.434213638305664,
|
| 1157 |
+
"step": 810
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.52,
|
| 1161 |
+
"learning_rate": 2.642247510668563e-07,
|
| 1162 |
+
"logits/generated": -2.5113425254821777,
|
| 1163 |
+
"logits/real": -2.2336676120758057,
|
| 1164 |
+
"logps/generated": -338.52764892578125,
|
| 1165 |
+
"logps/real": -156.8263702392578,
|
| 1166 |
+
"loss": 0.0004,
|
| 1167 |
+
"rewards/accuracies": 1.0,
|
| 1168 |
+
"rewards/generated": -24.256011962890625,
|
| 1169 |
+
"rewards/margins": 21.824642181396484,
|
| 1170 |
+
"rewards/real": -2.431368589401245,
|
| 1171 |
+
"step": 820
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.53,
|
| 1175 |
+
"learning_rate": 2.6066856330014225e-07,
|
| 1176 |
+
"logits/generated": -2.5100226402282715,
|
| 1177 |
+
"logits/real": -2.235252618789673,
|
| 1178 |
+
"logps/generated": -321.89739990234375,
|
| 1179 |
+
"logps/real": -163.9221954345703,
|
| 1180 |
+
"loss": 0.0028,
|
| 1181 |
+
"rewards/accuracies": 1.0,
|
| 1182 |
+
"rewards/generated": -22.618907928466797,
|
| 1183 |
+
"rewards/margins": 20.022174835205078,
|
| 1184 |
+
"rewards/real": -2.596730947494507,
|
| 1185 |
+
"step": 830
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.54,
|
| 1189 |
+
"learning_rate": 2.5711237553342815e-07,
|
| 1190 |
+
"logits/generated": -2.5395519733428955,
|
| 1191 |
+
"logits/real": -2.3223767280578613,
|
| 1192 |
+
"logps/generated": -332.1412048339844,
|
| 1193 |
+
"logps/real": -173.91867065429688,
|
| 1194 |
+
"loss": 0.0014,
|
| 1195 |
+
"rewards/accuracies": 1.0,
|
| 1196 |
+
"rewards/generated": -22.6175594329834,
|
| 1197 |
+
"rewards/margins": 20.04648780822754,
|
| 1198 |
+
"rewards/real": -2.5710747241973877,
|
| 1199 |
+
"step": 840
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.54,
|
| 1203 |
+
"learning_rate": 2.5355618776671404e-07,
|
| 1204 |
+
"logits/generated": -2.5228655338287354,
|
| 1205 |
+
"logits/real": -2.258119821548462,
|
| 1206 |
+
"logps/generated": -310.4747009277344,
|
| 1207 |
+
"logps/real": -156.8980255126953,
|
| 1208 |
+
"loss": 0.0026,
|
| 1209 |
+
"rewards/accuracies": 1.0,
|
| 1210 |
+
"rewards/generated": -21.987834930419922,
|
| 1211 |
+
"rewards/margins": 20.325721740722656,
|
| 1212 |
+
"rewards/real": -1.6621124744415283,
|
| 1213 |
+
"step": 850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.55,
|
| 1217 |
+
"learning_rate": 2.5e-07,
|
| 1218 |
+
"logits/generated": -2.494560718536377,
|
| 1219 |
+
"logits/real": -2.2443575859069824,
|
| 1220 |
+
"logps/generated": -309.8906555175781,
|
| 1221 |
+
"logps/real": -150.50845336914062,
|
| 1222 |
+
"loss": 0.0003,
|
| 1223 |
+
"rewards/accuracies": 1.0,
|
| 1224 |
+
"rewards/generated": -21.8504638671875,
|
| 1225 |
+
"rewards/margins": 19.960376739501953,
|
| 1226 |
+
"rewards/real": -1.8900905847549438,
|
| 1227 |
+
"step": 860
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.56,
|
| 1231 |
+
"learning_rate": 2.4644381223328594e-07,
|
| 1232 |
+
"logits/generated": -2.476022720336914,
|
| 1233 |
+
"logits/real": -2.208930730819702,
|
| 1234 |
+
"logps/generated": -324.40386962890625,
|
| 1235 |
+
"logps/real": -158.23794555664062,
|
| 1236 |
+
"loss": 0.0003,
|
| 1237 |
+
"rewards/accuracies": 1.0,
|
| 1238 |
+
"rewards/generated": -22.94091033935547,
|
| 1239 |
+
"rewards/margins": 21.123210906982422,
|
| 1240 |
+
"rewards/real": -1.8176969289779663,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.56,
|
| 1245 |
+
"learning_rate": 2.4288762446657183e-07,
|
| 1246 |
+
"logits/generated": -2.469374179840088,
|
| 1247 |
+
"logits/real": -2.2076289653778076,
|
| 1248 |
+
"logps/generated": -351.7542419433594,
|
| 1249 |
+
"logps/real": -168.60581970214844,
|
| 1250 |
+
"loss": 0.0001,
|
| 1251 |
+
"rewards/accuracies": 1.0,
|
| 1252 |
+
"rewards/generated": -26.091217041015625,
|
| 1253 |
+
"rewards/margins": 23.471628189086914,
|
| 1254 |
+
"rewards/real": -2.619591474533081,
|
| 1255 |
+
"step": 880
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.57,
|
| 1259 |
+
"learning_rate": 2.393314366998578e-07,
|
| 1260 |
+
"logits/generated": -2.462498188018799,
|
| 1261 |
+
"logits/real": -2.1745076179504395,
|
| 1262 |
+
"logps/generated": -356.53643798828125,
|
| 1263 |
+
"logps/real": -166.32203674316406,
|
| 1264 |
+
"loss": 0.0002,
|
| 1265 |
+
"rewards/accuracies": 1.0,
|
| 1266 |
+
"rewards/generated": -25.77919578552246,
|
| 1267 |
+
"rewards/margins": 22.798179626464844,
|
| 1268 |
+
"rewards/real": -2.9810147285461426,
|
| 1269 |
+
"step": 890
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.58,
|
| 1273 |
+
"learning_rate": 2.3577524893314365e-07,
|
| 1274 |
+
"logits/generated": -2.4472568035125732,
|
| 1275 |
+
"logits/real": -2.0861692428588867,
|
| 1276 |
+
"logps/generated": -373.2332458496094,
|
| 1277 |
+
"logps/real": -161.7514190673828,
|
| 1278 |
+
"loss": 0.0002,
|
| 1279 |
+
"rewards/accuracies": 1.0,
|
| 1280 |
+
"rewards/generated": -27.64597511291504,
|
| 1281 |
+
"rewards/margins": 24.518720626831055,
|
| 1282 |
+
"rewards/real": -3.127256393432617,
|
| 1283 |
+
"step": 900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.58,
|
| 1287 |
+
"learning_rate": 2.322190611664296e-07,
|
| 1288 |
+
"logits/generated": -2.4123172760009766,
|
| 1289 |
+
"logits/real": -2.2399840354919434,
|
| 1290 |
+
"logps/generated": -347.86602783203125,
|
| 1291 |
+
"logps/real": -176.418701171875,
|
| 1292 |
+
"loss": 0.0033,
|
| 1293 |
+
"rewards/accuracies": 1.0,
|
| 1294 |
+
"rewards/generated": -25.725696563720703,
|
| 1295 |
+
"rewards/margins": 23.024372100830078,
|
| 1296 |
+
"rewards/real": -2.701322078704834,
|
| 1297 |
+
"step": 910
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.59,
|
| 1301 |
+
"learning_rate": 2.2866287339971549e-07,
|
| 1302 |
+
"logits/generated": -2.4416496753692627,
|
| 1303 |
+
"logits/real": -2.165473461151123,
|
| 1304 |
+
"logps/generated": -350.0740051269531,
|
| 1305 |
+
"logps/real": -163.84527587890625,
|
| 1306 |
+
"loss": 0.0001,
|
| 1307 |
+
"rewards/accuracies": 1.0,
|
| 1308 |
+
"rewards/generated": -25.062084197998047,
|
| 1309 |
+
"rewards/margins": 22.562055587768555,
|
| 1310 |
+
"rewards/real": -2.5000269412994385,
|
| 1311 |
+
"step": 920
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.6,
|
| 1315 |
+
"learning_rate": 2.251066856330014e-07,
|
| 1316 |
+
"logits/generated": -2.3707525730133057,
|
| 1317 |
+
"logits/real": -2.133812665939331,
|
| 1318 |
+
"logps/generated": -331.30523681640625,
|
| 1319 |
+
"logps/real": -152.8733673095703,
|
| 1320 |
+
"loss": 0.0004,
|
| 1321 |
+
"rewards/accuracies": 1.0,
|
| 1322 |
+
"rewards/generated": -24.211957931518555,
|
| 1323 |
+
"rewards/margins": 21.420856475830078,
|
| 1324 |
+
"rewards/real": -2.791102886199951,
|
| 1325 |
+
"step": 930
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6,
|
| 1329 |
+
"learning_rate": 2.2155049786628733e-07,
|
| 1330 |
+
"logits/generated": -2.37143611907959,
|
| 1331 |
+
"logits/real": -2.1967265605926514,
|
| 1332 |
+
"logps/generated": -348.8166198730469,
|
| 1333 |
+
"logps/real": -173.89651489257812,
|
| 1334 |
+
"loss": 0.0009,
|
| 1335 |
+
"rewards/accuracies": 1.0,
|
| 1336 |
+
"rewards/generated": -25.457895278930664,
|
| 1337 |
+
"rewards/margins": 22.477210998535156,
|
| 1338 |
+
"rewards/real": -2.980682849884033,
|
| 1339 |
+
"step": 940
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.61,
|
| 1343 |
+
"learning_rate": 2.1799431009957325e-07,
|
| 1344 |
+
"logits/generated": -2.381801128387451,
|
| 1345 |
+
"logits/real": -2.059781074523926,
|
| 1346 |
+
"logps/generated": -362.11383056640625,
|
| 1347 |
+
"logps/real": -159.50637817382812,
|
| 1348 |
+
"loss": 0.0001,
|
| 1349 |
+
"rewards/accuracies": 1.0,
|
| 1350 |
+
"rewards/generated": -26.543100357055664,
|
| 1351 |
+
"rewards/margins": 22.987590789794922,
|
| 1352 |
+
"rewards/real": -3.5555107593536377,
|
| 1353 |
+
"step": 950
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.61,
|
| 1357 |
+
"learning_rate": 2.1443812233285914e-07,
|
| 1358 |
+
"logits/generated": -2.3684401512145996,
|
| 1359 |
+
"logits/real": -2.1415822505950928,
|
| 1360 |
+
"logps/generated": -351.82196044921875,
|
| 1361 |
+
"logps/real": -176.533203125,
|
| 1362 |
+
"loss": 0.0003,
|
| 1363 |
+
"rewards/accuracies": 1.0,
|
| 1364 |
+
"rewards/generated": -26.036602020263672,
|
| 1365 |
+
"rewards/margins": 22.72909164428711,
|
| 1366 |
+
"rewards/real": -3.30751371383667,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.62,
|
| 1371 |
+
"learning_rate": 2.108819345661451e-07,
|
| 1372 |
+
"logits/generated": -2.3761467933654785,
|
| 1373 |
+
"logits/real": -2.0534472465515137,
|
| 1374 |
+
"logps/generated": -355.33428955078125,
|
| 1375 |
+
"logps/real": -168.10891723632812,
|
| 1376 |
+
"loss": 0.0002,
|
| 1377 |
+
"rewards/accuracies": 1.0,
|
| 1378 |
+
"rewards/generated": -25.50898551940918,
|
| 1379 |
+
"rewards/margins": 22.156692504882812,
|
| 1380 |
+
"rewards/real": -3.3522915840148926,
|
| 1381 |
+
"step": 970
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.63,
|
| 1385 |
+
"learning_rate": 2.0732574679943098e-07,
|
| 1386 |
+
"logits/generated": -2.361323118209839,
|
| 1387 |
+
"logits/real": -1.9123132228851318,
|
| 1388 |
+
"logps/generated": -341.6062316894531,
|
| 1389 |
+
"logps/real": -151.2181854248047,
|
| 1390 |
+
"loss": 0.0006,
|
| 1391 |
+
"rewards/accuracies": 1.0,
|
| 1392 |
+
"rewards/generated": -24.98283576965332,
|
| 1393 |
+
"rewards/margins": 21.82351303100586,
|
| 1394 |
+
"rewards/real": -3.15932297706604,
|
| 1395 |
+
"step": 980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.63,
|
| 1399 |
+
"learning_rate": 2.0376955903271693e-07,
|
| 1400 |
+
"logits/generated": -2.4006187915802,
|
| 1401 |
+
"logits/real": -2.185279130935669,
|
| 1402 |
+
"logps/generated": -348.07781982421875,
|
| 1403 |
+
"logps/real": -179.2666778564453,
|
| 1404 |
+
"loss": 0.0003,
|
| 1405 |
+
"rewards/accuracies": 1.0,
|
| 1406 |
+
"rewards/generated": -25.35213851928711,
|
| 1407 |
+
"rewards/margins": 22.43604278564453,
|
| 1408 |
+
"rewards/real": -2.9160971641540527,
|
| 1409 |
+
"step": 990
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.64,
|
| 1413 |
+
"learning_rate": 2.0021337126600283e-07,
|
| 1414 |
+
"logits/generated": -2.4060044288635254,
|
| 1415 |
+
"logits/real": -2.060713529586792,
|
| 1416 |
+
"logps/generated": -333.03594970703125,
|
| 1417 |
+
"logps/real": -150.0802001953125,
|
| 1418 |
+
"loss": 0.0001,
|
| 1419 |
+
"rewards/accuracies": 1.0,
|
| 1420 |
+
"rewards/generated": -23.7082576751709,
|
| 1421 |
+
"rewards/margins": 21.07244300842285,
|
| 1422 |
+
"rewards/real": -2.6358113288879395,
|
| 1423 |
+
"step": 1000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.65,
|
| 1427 |
+
"learning_rate": 1.9665718349928875e-07,
|
| 1428 |
+
"logits/generated": -2.399757146835327,
|
| 1429 |
+
"logits/real": -2.0892844200134277,
|
| 1430 |
+
"logps/generated": -329.17266845703125,
|
| 1431 |
+
"logps/real": -147.83761596679688,
|
| 1432 |
+
"loss": 0.0003,
|
| 1433 |
+
"rewards/accuracies": 1.0,
|
| 1434 |
+
"rewards/generated": -24.133182525634766,
|
| 1435 |
+
"rewards/margins": 22.037132263183594,
|
| 1436 |
+
"rewards/real": -2.096048593521118,
|
| 1437 |
+
"step": 1010
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.65,
|
| 1441 |
+
"learning_rate": 1.931009957325747e-07,
|
| 1442 |
+
"logits/generated": -2.435051441192627,
|
| 1443 |
+
"logits/real": -2.0257344245910645,
|
| 1444 |
+
"logps/generated": -339.9688720703125,
|
| 1445 |
+
"logps/real": -136.052734375,
|
| 1446 |
+
"loss": 0.0027,
|
| 1447 |
+
"rewards/accuracies": 1.0,
|
| 1448 |
+
"rewards/generated": -24.32839012145996,
|
| 1449 |
+
"rewards/margins": 22.426374435424805,
|
| 1450 |
+
"rewards/real": -1.90201735496521,
|
| 1451 |
+
"step": 1020
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.66,
|
| 1455 |
+
"learning_rate": 1.895448079658606e-07,
|
| 1456 |
+
"logits/generated": -2.5459911823272705,
|
| 1457 |
+
"logits/real": -2.294416904449463,
|
| 1458 |
+
"logps/generated": -295.2132873535156,
|
| 1459 |
+
"logps/real": -164.39163208007812,
|
| 1460 |
+
"loss": 0.0065,
|
| 1461 |
+
"rewards/accuracies": 0.987500011920929,
|
| 1462 |
+
"rewards/generated": -20.07970428466797,
|
| 1463 |
+
"rewards/margins": 17.690706253051758,
|
| 1464 |
+
"rewards/real": -2.3889966011047363,
|
| 1465 |
+
"step": 1030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.67,
|
| 1469 |
+
"learning_rate": 1.859886201991465e-07,
|
| 1470 |
+
"logits/generated": -2.557673931121826,
|
| 1471 |
+
"logits/real": -2.352283000946045,
|
| 1472 |
+
"logps/generated": -305.96063232421875,
|
| 1473 |
+
"logps/real": -168.4624481201172,
|
| 1474 |
+
"loss": 0.0004,
|
| 1475 |
+
"rewards/accuracies": 1.0,
|
| 1476 |
+
"rewards/generated": -20.94136619567871,
|
| 1477 |
+
"rewards/margins": 18.588964462280273,
|
| 1478 |
+
"rewards/real": -2.3524010181427,
|
| 1479 |
+
"step": 1040
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.67,
|
| 1483 |
+
"learning_rate": 1.8243243243243243e-07,
|
| 1484 |
+
"logits/generated": -2.523613691329956,
|
| 1485 |
+
"logits/real": -2.266178607940674,
|
| 1486 |
+
"logps/generated": -326.160400390625,
|
| 1487 |
+
"logps/real": -161.75082397460938,
|
| 1488 |
+
"loss": 0.0004,
|
| 1489 |
+
"rewards/accuracies": 1.0,
|
| 1490 |
+
"rewards/generated": -22.259069442749023,
|
| 1491 |
+
"rewards/margins": 19.766599655151367,
|
| 1492 |
+
"rewards/real": -2.4924685955047607,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.68,
|
| 1497 |
+
"learning_rate": 1.7887624466571835e-07,
|
| 1498 |
+
"logits/generated": -2.527306079864502,
|
| 1499 |
+
"logits/real": -2.2957048416137695,
|
| 1500 |
+
"logps/generated": -305.22296142578125,
|
| 1501 |
+
"logps/real": -155.027099609375,
|
| 1502 |
+
"loss": 0.0006,
|
| 1503 |
+
"rewards/accuracies": 1.0,
|
| 1504 |
+
"rewards/generated": -20.85342788696289,
|
| 1505 |
+
"rewards/margins": 18.48206901550293,
|
| 1506 |
+
"rewards/real": -2.3713603019714355,
|
| 1507 |
+
"step": 1060
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.68,
|
| 1511 |
+
"learning_rate": 1.7532005689900424e-07,
|
| 1512 |
+
"logits/generated": -2.506270170211792,
|
| 1513 |
+
"logits/real": -2.255981206893921,
|
| 1514 |
+
"logps/generated": -325.351318359375,
|
| 1515 |
+
"logps/real": -159.0684051513672,
|
| 1516 |
+
"loss": 0.0002,
|
| 1517 |
+
"rewards/accuracies": 1.0,
|
| 1518 |
+
"rewards/generated": -22.69347381591797,
|
| 1519 |
+
"rewards/margins": 20.053133010864258,
|
| 1520 |
+
"rewards/real": -2.640340805053711,
|
| 1521 |
+
"step": 1070
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.69,
|
| 1525 |
+
"learning_rate": 1.717638691322902e-07,
|
| 1526 |
+
"logits/generated": -2.4864695072174072,
|
| 1527 |
+
"logits/real": -2.2343809604644775,
|
| 1528 |
+
"logps/generated": -316.3734130859375,
|
| 1529 |
+
"logps/real": -154.7774200439453,
|
| 1530 |
+
"loss": 0.0002,
|
| 1531 |
+
"rewards/accuracies": 1.0,
|
| 1532 |
+
"rewards/generated": -22.82534408569336,
|
| 1533 |
+
"rewards/margins": 20.07224464416504,
|
| 1534 |
+
"rewards/real": -2.753100633621216,
|
| 1535 |
+
"step": 1080
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.7,
|
| 1539 |
+
"learning_rate": 1.6820768136557609e-07,
|
| 1540 |
+
"logits/generated": -2.4980576038360596,
|
| 1541 |
+
"logits/real": -2.2096495628356934,
|
| 1542 |
+
"logps/generated": -332.5113220214844,
|
| 1543 |
+
"logps/real": -155.82949829101562,
|
| 1544 |
+
"loss": 0.0003,
|
| 1545 |
+
"rewards/accuracies": 1.0,
|
| 1546 |
+
"rewards/generated": -23.275163650512695,
|
| 1547 |
+
"rewards/margins": 20.510225296020508,
|
| 1548 |
+
"rewards/real": -2.764936923980713,
|
| 1549 |
+
"step": 1090
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.7,
|
| 1553 |
+
"learning_rate": 1.64651493598862e-07,
|
| 1554 |
+
"logits/generated": -2.4756176471710205,
|
| 1555 |
+
"logits/real": -2.231832981109619,
|
| 1556 |
+
"logps/generated": -312.5588073730469,
|
| 1557 |
+
"logps/real": -164.60313415527344,
|
| 1558 |
+
"loss": 0.0005,
|
| 1559 |
+
"rewards/accuracies": 1.0,
|
| 1560 |
+
"rewards/generated": -21.650741577148438,
|
| 1561 |
+
"rewards/margins": 19.549571990966797,
|
| 1562 |
+
"rewards/real": -2.101168394088745,
|
| 1563 |
+
"step": 1100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.71,
|
| 1567 |
+
"learning_rate": 1.6109530583214793e-07,
|
| 1568 |
+
"logits/generated": -2.479539632797241,
|
| 1569 |
+
"logits/real": -2.2095680236816406,
|
| 1570 |
+
"logps/generated": -301.00494384765625,
|
| 1571 |
+
"logps/real": -146.39959716796875,
|
| 1572 |
+
"loss": 0.0013,
|
| 1573 |
+
"rewards/accuracies": 1.0,
|
| 1574 |
+
"rewards/generated": -21.074636459350586,
|
| 1575 |
+
"rewards/margins": 19.5632381439209,
|
| 1576 |
+
"rewards/real": -1.5113978385925293,
|
| 1577 |
+
"step": 1110
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.72,
|
| 1581 |
+
"learning_rate": 1.5753911806543385e-07,
|
| 1582 |
+
"logits/generated": -2.481510877609253,
|
| 1583 |
+
"logits/real": -2.1283092498779297,
|
| 1584 |
+
"logps/generated": -334.80682373046875,
|
| 1585 |
+
"logps/real": -148.7257537841797,
|
| 1586 |
+
"loss": 0.0005,
|
| 1587 |
+
"rewards/accuracies": 1.0,
|
| 1588 |
+
"rewards/generated": -23.64105796813965,
|
| 1589 |
+
"rewards/margins": 22.138673782348633,
|
| 1590 |
+
"rewards/real": -1.5023812055587769,
|
| 1591 |
+
"step": 1120
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.72,
|
| 1595 |
+
"learning_rate": 1.5398293029871974e-07,
|
| 1596 |
+
"logits/generated": -2.427147150039673,
|
| 1597 |
+
"logits/real": -2.1763315200805664,
|
| 1598 |
+
"logps/generated": -332.43707275390625,
|
| 1599 |
+
"logps/real": -164.38101196289062,
|
| 1600 |
+
"loss": 0.0007,
|
| 1601 |
+
"rewards/accuracies": 1.0,
|
| 1602 |
+
"rewards/generated": -23.752038955688477,
|
| 1603 |
+
"rewards/margins": 21.313995361328125,
|
| 1604 |
+
"rewards/real": -2.438042640686035,
|
| 1605 |
+
"step": 1130
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.73,
|
| 1609 |
+
"learning_rate": 1.504267425320057e-07,
|
| 1610 |
+
"logits/generated": -2.4392311573028564,
|
| 1611 |
+
"logits/real": -2.0997610092163086,
|
| 1612 |
+
"logps/generated": -334.01568603515625,
|
| 1613 |
+
"logps/real": -156.3632354736328,
|
| 1614 |
+
"loss": 0.0003,
|
| 1615 |
+
"rewards/accuracies": 1.0,
|
| 1616 |
+
"rewards/generated": -24.041645050048828,
|
| 1617 |
+
"rewards/margins": 21.53177833557129,
|
| 1618 |
+
"rewards/real": -2.50986647605896,
|
| 1619 |
+
"step": 1140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.74,
|
| 1623 |
+
"learning_rate": 1.4687055476529158e-07,
|
| 1624 |
+
"logits/generated": -2.419010639190674,
|
| 1625 |
+
"logits/real": -2.111693859100342,
|
| 1626 |
+
"logps/generated": -342.69451904296875,
|
| 1627 |
+
"logps/real": -169.71495056152344,
|
| 1628 |
+
"loss": 0.0005,
|
| 1629 |
+
"rewards/accuracies": 1.0,
|
| 1630 |
+
"rewards/generated": -24.21269416809082,
|
| 1631 |
+
"rewards/margins": 21.255273818969727,
|
| 1632 |
+
"rewards/real": -2.9574201107025146,
|
| 1633 |
+
"step": 1150
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.74,
|
| 1637 |
+
"learning_rate": 1.4331436699857753e-07,
|
| 1638 |
+
"logits/generated": -2.381650447845459,
|
| 1639 |
+
"logits/real": -2.1679978370666504,
|
| 1640 |
+
"logps/generated": -366.71685791015625,
|
| 1641 |
+
"logps/real": -173.09190368652344,
|
| 1642 |
+
"loss": 0.0,
|
| 1643 |
+
"rewards/accuracies": 1.0,
|
| 1644 |
+
"rewards/generated": -26.46500015258789,
|
| 1645 |
+
"rewards/margins": 23.07950782775879,
|
| 1646 |
+
"rewards/real": -3.385493040084839,
|
| 1647 |
+
"step": 1160
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.75,
|
| 1651 |
+
"learning_rate": 1.3975817923186345e-07,
|
| 1652 |
+
"logits/generated": -2.3996267318725586,
|
| 1653 |
+
"logits/real": -2.159729480743408,
|
| 1654 |
+
"logps/generated": -342.78851318359375,
|
| 1655 |
+
"logps/real": -178.8369903564453,
|
| 1656 |
+
"loss": 0.0024,
|
| 1657 |
+
"rewards/accuracies": 1.0,
|
| 1658 |
+
"rewards/generated": -25.046499252319336,
|
| 1659 |
+
"rewards/margins": 22.436920166015625,
|
| 1660 |
+
"rewards/real": -2.6095809936523438,
|
| 1661 |
+
"step": 1170
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.75,
|
| 1665 |
+
"learning_rate": 1.3620199146514935e-07,
|
| 1666 |
+
"logits/generated": -2.4095382690429688,
|
| 1667 |
+
"logits/real": -2.130403518676758,
|
| 1668 |
+
"logps/generated": -355.113037109375,
|
| 1669 |
+
"logps/real": -153.84921264648438,
|
| 1670 |
+
"loss": 0.1458,
|
| 1671 |
+
"rewards/accuracies": 1.0,
|
| 1672 |
+
"rewards/generated": -26.34041404724121,
|
| 1673 |
+
"rewards/margins": 22.976913452148438,
|
| 1674 |
+
"rewards/real": -3.3634982109069824,
|
| 1675 |
+
"step": 1180
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.76,
|
| 1679 |
+
"learning_rate": 1.326458036984353e-07,
|
| 1680 |
+
"logits/generated": -2.4847569465637207,
|
| 1681 |
+
"logits/real": -2.2022132873535156,
|
| 1682 |
+
"logps/generated": -349.0047607421875,
|
| 1683 |
+
"logps/real": -167.6402130126953,
|
| 1684 |
+
"loss": 0.0002,
|
| 1685 |
+
"rewards/accuracies": 1.0,
|
| 1686 |
+
"rewards/generated": -25.467708587646484,
|
| 1687 |
+
"rewards/margins": 21.79030990600586,
|
| 1688 |
+
"rewards/real": -3.677398204803467,
|
| 1689 |
+
"step": 1190
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.77,
|
| 1693 |
+
"learning_rate": 1.290896159317212e-07,
|
| 1694 |
+
"logits/generated": -2.4859986305236816,
|
| 1695 |
+
"logits/real": -2.1584694385528564,
|
| 1696 |
+
"logps/generated": -378.67840576171875,
|
| 1697 |
+
"logps/real": -163.35751342773438,
|
| 1698 |
+
"loss": 0.003,
|
| 1699 |
+
"rewards/accuracies": 1.0,
|
| 1700 |
+
"rewards/generated": -27.922542572021484,
|
| 1701 |
+
"rewards/margins": 24.293628692626953,
|
| 1702 |
+
"rewards/real": -3.628913402557373,
|
| 1703 |
+
"step": 1200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.77,
|
| 1707 |
+
"learning_rate": 1.255334281650071e-07,
|
| 1708 |
+
"logits/generated": -2.4462192058563232,
|
| 1709 |
+
"logits/real": -2.1797935962677,
|
| 1710 |
+
"logps/generated": -360.53839111328125,
|
| 1711 |
+
"logps/real": -178.1334228515625,
|
| 1712 |
+
"loss": 0.0001,
|
| 1713 |
+
"rewards/accuracies": 1.0,
|
| 1714 |
+
"rewards/generated": -26.705047607421875,
|
| 1715 |
+
"rewards/margins": 22.96535301208496,
|
| 1716 |
+
"rewards/real": -3.7396953105926514,
|
| 1717 |
+
"step": 1210
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.78,
|
| 1721 |
+
"learning_rate": 1.2197724039829303e-07,
|
| 1722 |
+
"logits/generated": -2.4851443767547607,
|
| 1723 |
+
"logits/real": -2.0922763347625732,
|
| 1724 |
+
"logps/generated": -361.0836486816406,
|
| 1725 |
+
"logps/real": -165.01766967773438,
|
| 1726 |
+
"loss": 0.0012,
|
| 1727 |
+
"rewards/accuracies": 1.0,
|
| 1728 |
+
"rewards/generated": -26.491872787475586,
|
| 1729 |
+
"rewards/margins": 22.785490036010742,
|
| 1730 |
+
"rewards/real": -3.7063846588134766,
|
| 1731 |
+
"step": 1220
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.79,
|
| 1735 |
+
"learning_rate": 1.1842105263157894e-07,
|
| 1736 |
+
"logits/generated": -2.471233606338501,
|
| 1737 |
+
"logits/real": -2.112055540084839,
|
| 1738 |
+
"logps/generated": -336.9444274902344,
|
| 1739 |
+
"logps/real": -156.4147491455078,
|
| 1740 |
+
"loss": 0.0003,
|
| 1741 |
+
"rewards/accuracies": 1.0,
|
| 1742 |
+
"rewards/generated": -24.630247116088867,
|
| 1743 |
+
"rewards/margins": 20.876323699951172,
|
| 1744 |
+
"rewards/real": -3.7539241313934326,
|
| 1745 |
+
"step": 1230
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.79,
|
| 1749 |
+
"learning_rate": 1.1486486486486487e-07,
|
| 1750 |
+
"logits/generated": -2.475252389907837,
|
| 1751 |
+
"logits/real": -2.1622281074523926,
|
| 1752 |
+
"logps/generated": -350.2343444824219,
|
| 1753 |
+
"logps/real": -170.01983642578125,
|
| 1754 |
+
"loss": 0.0004,
|
| 1755 |
+
"rewards/accuracies": 1.0,
|
| 1756 |
+
"rewards/generated": -25.50958824157715,
|
| 1757 |
+
"rewards/margins": 22.2675724029541,
|
| 1758 |
+
"rewards/real": -3.2420172691345215,
|
| 1759 |
+
"step": 1240
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.8,
|
| 1763 |
+
"learning_rate": 1.1130867709815078e-07,
|
| 1764 |
+
"logits/generated": -2.4563283920288086,
|
| 1765 |
+
"logits/real": -2.14430570602417,
|
| 1766 |
+
"logps/generated": -346.8614196777344,
|
| 1767 |
+
"logps/real": -169.02615356445312,
|
| 1768 |
+
"loss": 0.0001,
|
| 1769 |
+
"rewards/accuracies": 1.0,
|
| 1770 |
+
"rewards/generated": -25.24651527404785,
|
| 1771 |
+
"rewards/margins": 21.750926971435547,
|
| 1772 |
+
"rewards/real": -3.495588779449463,
|
| 1773 |
+
"step": 1250
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.81,
|
| 1777 |
+
"learning_rate": 1.077524893314367e-07,
|
| 1778 |
+
"logits/generated": -2.45477032661438,
|
| 1779 |
+
"logits/real": -2.0709099769592285,
|
| 1780 |
+
"logps/generated": -356.8681640625,
|
| 1781 |
+
"logps/real": -159.69961547851562,
|
| 1782 |
+
"loss": 0.0002,
|
| 1783 |
+
"rewards/accuracies": 1.0,
|
| 1784 |
+
"rewards/generated": -26.31940269470215,
|
| 1785 |
+
"rewards/margins": 22.827180862426758,
|
| 1786 |
+
"rewards/real": -3.492220401763916,
|
| 1787 |
+
"step": 1260
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.81,
|
| 1791 |
+
"learning_rate": 1.0419630156472262e-07,
|
| 1792 |
+
"logits/generated": -2.453141450881958,
|
| 1793 |
+
"logits/real": -2.2395853996276855,
|
| 1794 |
+
"logps/generated": -378.34564208984375,
|
| 1795 |
+
"logps/real": -186.41482543945312,
|
| 1796 |
+
"loss": 0.0,
|
| 1797 |
+
"rewards/accuracies": 1.0,
|
| 1798 |
+
"rewards/generated": -28.221569061279297,
|
| 1799 |
+
"rewards/margins": 24.545499801635742,
|
| 1800 |
+
"rewards/real": -3.676067352294922,
|
| 1801 |
+
"step": 1270
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.82,
|
| 1805 |
+
"learning_rate": 1.0064011379800854e-07,
|
| 1806 |
+
"logits/generated": -2.4747064113616943,
|
| 1807 |
+
"logits/real": -2.2565696239471436,
|
| 1808 |
+
"logps/generated": -354.7027893066406,
|
| 1809 |
+
"logps/real": -179.99632263183594,
|
| 1810 |
+
"loss": 0.0024,
|
| 1811 |
+
"rewards/accuracies": 1.0,
|
| 1812 |
+
"rewards/generated": -25.973247528076172,
|
| 1813 |
+
"rewards/margins": 22.519550323486328,
|
| 1814 |
+
"rewards/real": -3.4536995887756348,
|
| 1815 |
+
"step": 1280
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.83,
|
| 1819 |
+
"learning_rate": 9.708392603129445e-08,
|
| 1820 |
+
"logits/generated": -2.4690163135528564,
|
| 1821 |
+
"logits/real": -2.232900857925415,
|
| 1822 |
+
"logps/generated": -339.08905029296875,
|
| 1823 |
+
"logps/real": -170.72555541992188,
|
| 1824 |
+
"loss": 0.0002,
|
| 1825 |
+
"rewards/accuracies": 1.0,
|
| 1826 |
+
"rewards/generated": -25.025901794433594,
|
| 1827 |
+
"rewards/margins": 21.20990562438965,
|
| 1828 |
+
"rewards/real": -3.8159968852996826,
|
| 1829 |
+
"step": 1290
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.83,
|
| 1833 |
+
"learning_rate": 9.352773826458037e-08,
|
| 1834 |
+
"logits/generated": -2.4715685844421387,
|
| 1835 |
+
"logits/real": -2.1666557788848877,
|
| 1836 |
+
"logps/generated": -385.85552978515625,
|
| 1837 |
+
"logps/real": -176.1797637939453,
|
| 1838 |
+
"loss": 0.0004,
|
| 1839 |
+
"rewards/accuracies": 1.0,
|
| 1840 |
+
"rewards/generated": -28.624618530273438,
|
| 1841 |
+
"rewards/margins": 24.681453704833984,
|
| 1842 |
+
"rewards/real": -3.9431674480438232,
|
| 1843 |
+
"step": 1300
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.84,
|
| 1847 |
+
"learning_rate": 8.997155049786629e-08,
|
| 1848 |
+
"logits/generated": -2.485658884048462,
|
| 1849 |
+
"logits/real": -2.087472438812256,
|
| 1850 |
+
"logps/generated": -363.4739685058594,
|
| 1851 |
+
"logps/real": -157.5010528564453,
|
| 1852 |
+
"loss": 0.0001,
|
| 1853 |
+
"rewards/accuracies": 1.0,
|
| 1854 |
+
"rewards/generated": -26.5460262298584,
|
| 1855 |
+
"rewards/margins": 23.222301483154297,
|
| 1856 |
+
"rewards/real": -3.3237223625183105,
|
| 1857 |
+
"step": 1310
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.84,
|
| 1861 |
+
"learning_rate": 8.64153627311522e-08,
|
| 1862 |
+
"logits/generated": -2.4857845306396484,
|
| 1863 |
+
"logits/real": -2.1609935760498047,
|
| 1864 |
+
"logps/generated": -358.87042236328125,
|
| 1865 |
+
"logps/real": -167.06588745117188,
|
| 1866 |
+
"loss": 0.0001,
|
| 1867 |
+
"rewards/accuracies": 1.0,
|
| 1868 |
+
"rewards/generated": -26.336450576782227,
|
| 1869 |
+
"rewards/margins": 23.036605834960938,
|
| 1870 |
+
"rewards/real": -3.2998440265655518,
|
| 1871 |
+
"step": 1320
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.85,
|
| 1875 |
+
"learning_rate": 8.285917496443812e-08,
|
| 1876 |
+
"logits/generated": -2.488786458969116,
|
| 1877 |
+
"logits/real": -2.1406562328338623,
|
| 1878 |
+
"logps/generated": -359.51123046875,
|
| 1879 |
+
"logps/real": -170.75405883789062,
|
| 1880 |
+
"loss": 0.0002,
|
| 1881 |
+
"rewards/accuracies": 1.0,
|
| 1882 |
+
"rewards/generated": -26.246429443359375,
|
| 1883 |
+
"rewards/margins": 23.00771713256836,
|
| 1884 |
+
"rewards/real": -3.2387115955352783,
|
| 1885 |
+
"step": 1330
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.86,
|
| 1889 |
+
"learning_rate": 7.930298719772404e-08,
|
| 1890 |
+
"logits/generated": -2.4988155364990234,
|
| 1891 |
+
"logits/real": -2.2278027534484863,
|
| 1892 |
+
"logps/generated": -346.3113098144531,
|
| 1893 |
+
"logps/real": -180.57955932617188,
|
| 1894 |
+
"loss": 0.0002,
|
| 1895 |
+
"rewards/accuracies": 1.0,
|
| 1896 |
+
"rewards/generated": -25.450998306274414,
|
| 1897 |
+
"rewards/margins": 21.88384437561035,
|
| 1898 |
+
"rewards/real": -3.567152738571167,
|
| 1899 |
+
"step": 1340
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.86,
|
| 1903 |
+
"learning_rate": 7.574679943100994e-08,
|
| 1904 |
+
"logits/generated": -2.4711849689483643,
|
| 1905 |
+
"logits/real": -2.1394145488739014,
|
| 1906 |
+
"logps/generated": -363.7166442871094,
|
| 1907 |
+
"logps/real": -153.56500244140625,
|
| 1908 |
+
"loss": 0.0001,
|
| 1909 |
+
"rewards/accuracies": 1.0,
|
| 1910 |
+
"rewards/generated": -27.254398345947266,
|
| 1911 |
+
"rewards/margins": 23.747648239135742,
|
| 1912 |
+
"rewards/real": -3.5067508220672607,
|
| 1913 |
+
"step": 1350
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.87,
|
| 1917 |
+
"learning_rate": 7.219061166429587e-08,
|
| 1918 |
+
"logits/generated": -2.4750030040740967,
|
| 1919 |
+
"logits/real": -2.165269136428833,
|
| 1920 |
+
"logps/generated": -348.77850341796875,
|
| 1921 |
+
"logps/real": -166.81552124023438,
|
| 1922 |
+
"loss": 0.0003,
|
| 1923 |
+
"rewards/accuracies": 1.0,
|
| 1924 |
+
"rewards/generated": -25.863576889038086,
|
| 1925 |
+
"rewards/margins": 22.189855575561523,
|
| 1926 |
+
"rewards/real": -3.673719882965088,
|
| 1927 |
+
"step": 1360
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.88,
|
| 1931 |
+
"learning_rate": 6.863442389758179e-08,
|
| 1932 |
+
"logits/generated": -2.470283269882202,
|
| 1933 |
+
"logits/real": -2.1896414756774902,
|
| 1934 |
+
"logps/generated": -360.472412109375,
|
| 1935 |
+
"logps/real": -183.18991088867188,
|
| 1936 |
+
"loss": 0.0003,
|
| 1937 |
+
"rewards/accuracies": 1.0,
|
| 1938 |
+
"rewards/generated": -26.284610748291016,
|
| 1939 |
+
"rewards/margins": 22.66669464111328,
|
| 1940 |
+
"rewards/real": -3.6179168224334717,
|
| 1941 |
+
"step": 1370
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.88,
|
| 1945 |
+
"learning_rate": 6.507823613086771e-08,
|
| 1946 |
+
"logits/generated": -2.503307819366455,
|
| 1947 |
+
"logits/real": -2.1919872760772705,
|
| 1948 |
+
"logps/generated": -367.18853759765625,
|
| 1949 |
+
"logps/real": -180.93328857421875,
|
| 1950 |
+
"loss": 0.0002,
|
| 1951 |
+
"rewards/accuracies": 1.0,
|
| 1952 |
+
"rewards/generated": -26.932886123657227,
|
| 1953 |
+
"rewards/margins": 23.0779972076416,
|
| 1954 |
+
"rewards/real": -3.854888916015625,
|
| 1955 |
+
"step": 1380
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.89,
|
| 1959 |
+
"learning_rate": 6.152204836415363e-08,
|
| 1960 |
+
"logits/generated": -2.4691319465637207,
|
| 1961 |
+
"logits/real": -2.1717336177825928,
|
| 1962 |
+
"logps/generated": -356.29571533203125,
|
| 1963 |
+
"logps/real": -177.71517944335938,
|
| 1964 |
+
"loss": 0.0001,
|
| 1965 |
+
"rewards/accuracies": 1.0,
|
| 1966 |
+
"rewards/generated": -26.687480926513672,
|
| 1967 |
+
"rewards/margins": 22.633920669555664,
|
| 1968 |
+
"rewards/real": -4.053561687469482,
|
| 1969 |
+
"step": 1390
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.9,
|
| 1973 |
+
"learning_rate": 5.796586059743954e-08,
|
| 1974 |
+
"logits/generated": -2.466785430908203,
|
| 1975 |
+
"logits/real": -2.1675827503204346,
|
| 1976 |
+
"logps/generated": -370.415283203125,
|
| 1977 |
+
"logps/real": -170.87490844726562,
|
| 1978 |
+
"loss": 0.0001,
|
| 1979 |
+
"rewards/accuracies": 1.0,
|
| 1980 |
+
"rewards/generated": -27.176166534423828,
|
| 1981 |
+
"rewards/margins": 23.794544219970703,
|
| 1982 |
+
"rewards/real": -3.381622314453125,
|
| 1983 |
+
"step": 1400
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.9,
|
| 1987 |
+
"learning_rate": 5.4409672830725456e-08,
|
| 1988 |
+
"logits/generated": -2.4945216178894043,
|
| 1989 |
+
"logits/real": -2.188453197479248,
|
| 1990 |
+
"logps/generated": -364.7228088378906,
|
| 1991 |
+
"logps/real": -170.24136352539062,
|
| 1992 |
+
"loss": 0.0002,
|
| 1993 |
+
"rewards/accuracies": 1.0,
|
| 1994 |
+
"rewards/generated": -26.309009552001953,
|
| 1995 |
+
"rewards/margins": 22.98163604736328,
|
| 1996 |
+
"rewards/real": -3.3273673057556152,
|
| 1997 |
+
"step": 1410
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.91,
|
| 2001 |
+
"learning_rate": 5.0853485064011376e-08,
|
| 2002 |
+
"logits/generated": -2.460291624069214,
|
| 2003 |
+
"logits/real": -2.0653367042541504,
|
| 2004 |
+
"logps/generated": -367.35638427734375,
|
| 2005 |
+
"logps/real": -158.03836059570312,
|
| 2006 |
+
"loss": 0.0004,
|
| 2007 |
+
"rewards/accuracies": 1.0,
|
| 2008 |
+
"rewards/generated": -27.220428466796875,
|
| 2009 |
+
"rewards/margins": 23.743730545043945,
|
| 2010 |
+
"rewards/real": -3.4767017364501953,
|
| 2011 |
+
"step": 1420
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.91,
|
| 2015 |
+
"learning_rate": 4.72972972972973e-08,
|
| 2016 |
+
"logits/generated": -2.4655089378356934,
|
| 2017 |
+
"logits/real": -2.1470799446105957,
|
| 2018 |
+
"logps/generated": -363.5157165527344,
|
| 2019 |
+
"logps/real": -169.77064514160156,
|
| 2020 |
+
"loss": 0.0002,
|
| 2021 |
+
"rewards/accuracies": 1.0,
|
| 2022 |
+
"rewards/generated": -27.16286849975586,
|
| 2023 |
+
"rewards/margins": 23.716289520263672,
|
| 2024 |
+
"rewards/real": -3.4465808868408203,
|
| 2025 |
+
"step": 1430
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.92,
|
| 2029 |
+
"learning_rate": 4.374110953058322e-08,
|
| 2030 |
+
"logits/generated": -2.4361727237701416,
|
| 2031 |
+
"logits/real": -2.1429202556610107,
|
| 2032 |
+
"logps/generated": -346.8465270996094,
|
| 2033 |
+
"logps/real": -169.4228515625,
|
| 2034 |
+
"loss": 0.0002,
|
| 2035 |
+
"rewards/accuracies": 1.0,
|
| 2036 |
+
"rewards/generated": -25.74833106994629,
|
| 2037 |
+
"rewards/margins": 21.9796142578125,
|
| 2038 |
+
"rewards/real": -3.7687153816223145,
|
| 2039 |
+
"step": 1440
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.93,
|
| 2043 |
+
"learning_rate": 4.018492176386913e-08,
|
| 2044 |
+
"logits/generated": -2.479517936706543,
|
| 2045 |
+
"logits/real": -2.1686959266662598,
|
| 2046 |
+
"logps/generated": -345.124267578125,
|
| 2047 |
+
"logps/real": -168.16627502441406,
|
| 2048 |
+
"loss": 0.0001,
|
| 2049 |
+
"rewards/accuracies": 1.0,
|
| 2050 |
+
"rewards/generated": -24.663585662841797,
|
| 2051 |
+
"rewards/margins": 21.2713565826416,
|
| 2052 |
+
"rewards/real": -3.3922317028045654,
|
| 2053 |
+
"step": 1450
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.93,
|
| 2057 |
+
"learning_rate": 3.6628733997155046e-08,
|
| 2058 |
+
"logits/generated": -2.4482412338256836,
|
| 2059 |
+
"logits/real": -2.036306381225586,
|
| 2060 |
+
"logps/generated": -369.10015869140625,
|
| 2061 |
+
"logps/real": -149.97622680664062,
|
| 2062 |
+
"loss": 0.0008,
|
| 2063 |
+
"rewards/accuracies": 1.0,
|
| 2064 |
+
"rewards/generated": -27.136011123657227,
|
| 2065 |
+
"rewards/margins": 23.369976043701172,
|
| 2066 |
+
"rewards/real": -3.7660350799560547,
|
| 2067 |
+
"step": 1460
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.94,
|
| 2071 |
+
"learning_rate": 3.3072546230440967e-08,
|
| 2072 |
+
"logits/generated": -2.4708914756774902,
|
| 2073 |
+
"logits/real": -2.184417247772217,
|
| 2074 |
+
"logps/generated": -365.8651428222656,
|
| 2075 |
+
"logps/real": -165.40721130371094,
|
| 2076 |
+
"loss": 0.0002,
|
| 2077 |
+
"rewards/accuracies": 1.0,
|
| 2078 |
+
"rewards/generated": -26.8408203125,
|
| 2079 |
+
"rewards/margins": 23.29212188720703,
|
| 2080 |
+
"rewards/real": -3.5486953258514404,
|
| 2081 |
+
"step": 1470
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.95,
|
| 2085 |
+
"learning_rate": 2.9516358463726884e-08,
|
| 2086 |
+
"logits/generated": -2.474561929702759,
|
| 2087 |
+
"logits/real": -2.19511342048645,
|
| 2088 |
+
"logps/generated": -355.9462890625,
|
| 2089 |
+
"logps/real": -176.87612915039062,
|
| 2090 |
+
"loss": 0.0023,
|
| 2091 |
+
"rewards/accuracies": 1.0,
|
| 2092 |
+
"rewards/generated": -25.89398765563965,
|
| 2093 |
+
"rewards/margins": 22.387157440185547,
|
| 2094 |
+
"rewards/real": -3.5068275928497314,
|
| 2095 |
+
"step": 1480
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.95,
|
| 2099 |
+
"learning_rate": 2.59601706970128e-08,
|
| 2100 |
+
"logits/generated": -2.4852168560028076,
|
| 2101 |
+
"logits/real": -2.187443256378174,
|
| 2102 |
+
"logps/generated": -361.1342468261719,
|
| 2103 |
+
"logps/real": -179.21498107910156,
|
| 2104 |
+
"loss": 0.0047,
|
| 2105 |
+
"rewards/accuracies": 1.0,
|
| 2106 |
+
"rewards/generated": -26.83822250366211,
|
| 2107 |
+
"rewards/margins": 23.508623123168945,
|
| 2108 |
+
"rewards/real": -3.329601764678955,
|
| 2109 |
+
"step": 1490
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.96,
|
| 2113 |
+
"learning_rate": 2.240398293029872e-08,
|
| 2114 |
+
"logits/generated": -2.467862606048584,
|
| 2115 |
+
"logits/real": -2.135467767715454,
|
| 2116 |
+
"logps/generated": -343.44512939453125,
|
| 2117 |
+
"logps/real": -165.08482360839844,
|
| 2118 |
+
"loss": 0.0001,
|
| 2119 |
+
"rewards/accuracies": 1.0,
|
| 2120 |
+
"rewards/generated": -24.802982330322266,
|
| 2121 |
+
"rewards/margins": 21.32632064819336,
|
| 2122 |
+
"rewards/real": -3.4766650199890137,
|
| 2123 |
+
"step": 1500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.97,
|
| 2127 |
+
"learning_rate": 1.8847795163584636e-08,
|
| 2128 |
+
"logits/generated": -2.481208324432373,
|
| 2129 |
+
"logits/real": -2.150805950164795,
|
| 2130 |
+
"logps/generated": -353.4545593261719,
|
| 2131 |
+
"logps/real": -169.54278564453125,
|
| 2132 |
+
"loss": 0.0004,
|
| 2133 |
+
"rewards/accuracies": 1.0,
|
| 2134 |
+
"rewards/generated": -25.823211669921875,
|
| 2135 |
+
"rewards/margins": 22.245121002197266,
|
| 2136 |
+
"rewards/real": -3.578090190887451,
|
| 2137 |
+
"step": 1510
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.97,
|
| 2141 |
+
"learning_rate": 1.5291607396870554e-08,
|
| 2142 |
+
"logits/generated": -2.46956467628479,
|
| 2143 |
+
"logits/real": -2.140104055404663,
|
| 2144 |
+
"logps/generated": -342.57061767578125,
|
| 2145 |
+
"logps/real": -167.4196014404297,
|
| 2146 |
+
"loss": 0.0001,
|
| 2147 |
+
"rewards/accuracies": 1.0,
|
| 2148 |
+
"rewards/generated": -25.0306339263916,
|
| 2149 |
+
"rewards/margins": 21.307403564453125,
|
| 2150 |
+
"rewards/real": -3.7232296466827393,
|
| 2151 |
+
"step": 1520
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.98,
|
| 2155 |
+
"learning_rate": 1.1735419630156473e-08,
|
| 2156 |
+
"logits/generated": -2.48580002784729,
|
| 2157 |
+
"logits/real": -2.194272518157959,
|
| 2158 |
+
"logps/generated": -368.3807678222656,
|
| 2159 |
+
"logps/real": -169.20266723632812,
|
| 2160 |
+
"loss": 0.0003,
|
| 2161 |
+
"rewards/accuracies": 1.0,
|
| 2162 |
+
"rewards/generated": -27.17935562133789,
|
| 2163 |
+
"rewards/margins": 23.502368927001953,
|
| 2164 |
+
"rewards/real": -3.6769843101501465,
|
| 2165 |
+
"step": 1530
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.99,
|
| 2169 |
+
"learning_rate": 8.179231863442388e-09,
|
| 2170 |
+
"logits/generated": -2.4726576805114746,
|
| 2171 |
+
"logits/real": -2.1791956424713135,
|
| 2172 |
+
"logps/generated": -354.394775390625,
|
| 2173 |
+
"logps/real": -170.46163940429688,
|
| 2174 |
+
"loss": 0.0014,
|
| 2175 |
+
"rewards/accuracies": 1.0,
|
| 2176 |
+
"rewards/generated": -25.885757446289062,
|
| 2177 |
+
"rewards/margins": 22.697250366210938,
|
| 2178 |
+
"rewards/real": -3.188507080078125,
|
| 2179 |
+
"step": 1540
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.99,
|
| 2183 |
+
"learning_rate": 4.623044096728307e-09,
|
| 2184 |
+
"logits/generated": -2.4750819206237793,
|
| 2185 |
+
"logits/real": -2.1696460247039795,
|
| 2186 |
+
"logps/generated": -358.7183532714844,
|
| 2187 |
+
"logps/real": -176.12982177734375,
|
| 2188 |
+
"loss": 0.0003,
|
| 2189 |
+
"rewards/accuracies": 1.0,
|
| 2190 |
+
"rewards/generated": -26.65958023071289,
|
| 2191 |
+
"rewards/margins": 23.13229751586914,
|
| 2192 |
+
"rewards/real": -3.52728271484375,
|
| 2193 |
+
"step": 1550
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.0,
|
| 2197 |
+
"learning_rate": 1.0668563300142248e-09,
|
| 2198 |
+
"logits/generated": -2.493542194366455,
|
| 2199 |
+
"logits/real": -2.1412835121154785,
|
| 2200 |
+
"logps/generated": -353.84625244140625,
|
| 2201 |
+
"logps/real": -169.55062866210938,
|
| 2202 |
+
"loss": 0.0013,
|
| 2203 |
+
"rewards/accuracies": 1.0,
|
| 2204 |
+
"rewards/generated": -25.792984008789062,
|
| 2205 |
+
"rewards/margins": 22.017263412475586,
|
| 2206 |
+
"rewards/real": -3.7757201194763184,
|
| 2207 |
+
"step": 1560
|
| 2208 |
+
},
|
| 2209 |
{
|
| 2210 |
"epoch": 1.0,
|
| 2211 |
+
"step": 1563,
|
| 2212 |
"total_flos": 0.0,
|
| 2213 |
+
"train_loss": 0.013782728538135369,
|
| 2214 |
+
"train_runtime": 6445.5164,
|
| 2215 |
+
"train_samples_per_second": 7.757,
|
| 2216 |
+
"train_steps_per_second": 0.242
|
| 2217 |
}
|
| 2218 |
],
|
| 2219 |
"logging_steps": 10,
|
| 2220 |
+
"max_steps": 1563,
|
| 2221 |
"num_input_tokens_seen": 0,
|
| 2222 |
"num_train_epochs": 1,
|
| 2223 |
"save_steps": 500,
|