Model save
Browse files- README.md +3 -3
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- metrics.jsonl +699 -500
- tokenizer.json +2 -2
- tokenizer_config.json +217 -8
- training_args.bin +2 -2
- trajectory.jsonl +2 -2
README.md
CHANGED
|
@@ -5,8 +5,8 @@ model_name: dispatchr-grpo
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
-
- hf_jobs
|
| 9 |
- grpo
|
|
|
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
|
@@ -28,7 +28,7 @@ print(output["generated_text"])
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
-
|
| 32 |
|
| 33 |
|
| 34 |
|
|
@@ -37,7 +37,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
| 37 |
### Framework versions
|
| 38 |
|
| 39 |
- TRL: 1.2.0
|
| 40 |
-
- Transformers:
|
| 41 |
- Pytorch: 2.10.0
|
| 42 |
- Datasets: 4.8.4
|
| 43 |
- Tokenizers: 0.22.2
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
|
|
|
| 8 |
- grpo
|
| 9 |
+
- hf_jobs
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ggtejas/dispatchr-grpo/runs/6sez5w7m)
|
| 32 |
|
| 33 |
|
| 34 |
|
|
|
|
| 37 |
### Framework versions
|
| 38 |
|
| 39 |
- TRL: 1.2.0
|
| 40 |
+
- Transformers: 4.57.6
|
| 41 |
- Pytorch: 2.10.0
|
| 42 |
- Datasets: 4.8.4
|
| 43 |
- Tokenizers: 0.22.2
|
adapter_config.json
CHANGED
|
@@ -30,10 +30,10 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
-
"k_proj",
|
| 34 |
"o_proj",
|
|
|
|
| 35 |
"q_proj",
|
| 36 |
-
"
|
| 37 |
],
|
| 38 |
"target_parameters": null,
|
| 39 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
| 33 |
"o_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
"q_proj",
|
| 36 |
+
"k_proj"
|
| 37 |
],
|
| 38 |
"target_parameters": null,
|
| 39 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 47224624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c2dee3d9941d580505a57f59bde7bc80311c24c35eedf4d2bd3b00544e4f72
|
| 3 |
size 47224624
|
metrics.jsonl
CHANGED
|
@@ -1,501 +1,700 @@
|
|
| 1 |
{"batch": 1, "reward": null, "loss": 0.0}
|
| 2 |
-
{"batch": 2, "reward": null, "loss":
|
| 3 |
-
{"batch": 3, "reward": null, "loss":
|
| 4 |
-
{"batch": 4, "reward": null, "loss":
|
| 5 |
-
{"batch": 5, "reward": null, "loss":
|
| 6 |
-
{"batch": 6, "reward": null, "loss":
|
| 7 |
-
{"batch": 7, "reward": null, "loss":
|
| 8 |
-
{"batch": 8, "reward": null, "loss":
|
| 9 |
-
{"batch": 9, "reward": null, "loss":
|
| 10 |
-
{"batch": 10, "reward": null, "loss":
|
| 11 |
-
{"batch": 11, "reward": null, "loss":
|
| 12 |
-
{"batch": 12, "reward": null, "loss":
|
| 13 |
-
{"batch": 13, "reward": null, "loss":
|
| 14 |
-
{"batch": 14, "reward": null, "loss":
|
| 15 |
-
{"batch": 15, "reward": null, "loss": 0.
|
| 16 |
-
{"batch": 16, "reward": null, "loss":
|
| 17 |
-
{"batch": 17, "reward": null, "loss":
|
| 18 |
-
{"batch": 18, "reward": null, "loss":
|
| 19 |
-
{"batch": 19, "reward": null, "loss":
|
| 20 |
-
{"batch": 20, "reward": null, "loss":
|
| 21 |
-
{"batch": 21, "reward": null, "loss":
|
| 22 |
-
{"batch": 22, "reward": null, "loss":
|
| 23 |
-
{"batch": 23, "reward": null, "loss":
|
| 24 |
-
{"batch": 24, "reward": null, "loss":
|
| 25 |
-
{"batch": 25, "reward": null, "loss":
|
| 26 |
-
{"batch": 26, "reward": null, "loss": 0.
|
| 27 |
-
{"batch": 27, "reward": null, "loss":
|
| 28 |
-
{"batch": 28, "reward": null, "loss":
|
| 29 |
-
{"batch": 29, "reward": null, "loss":
|
| 30 |
-
{"batch": 30, "reward": null, "loss": 0.
|
| 31 |
-
{"batch": 31, "reward": null, "loss":
|
| 32 |
-
{"batch": 32, "reward": null, "loss":
|
| 33 |
-
{"batch": 33, "reward": null, "loss":
|
| 34 |
-
{"batch": 34, "reward": null, "loss":
|
| 35 |
-
{"batch": 35, "reward": null, "loss":
|
| 36 |
-
{"batch": 36, "reward": null, "loss": 0.
|
| 37 |
-
{"batch": 37, "reward": null, "loss": 0.
|
| 38 |
-
{"batch": 38, "reward": null, "loss":
|
| 39 |
-
{"batch": 39, "reward": null, "loss":
|
| 40 |
-
{"batch": 40, "reward": null, "loss":
|
| 41 |
-
{"batch": 41, "reward": null, "loss": 0.
|
| 42 |
-
{"batch": 42, "reward": null, "loss":
|
| 43 |
-
{"batch": 43, "reward": null, "loss":
|
| 44 |
-
{"batch": 44, "reward": null, "loss": 0.
|
| 45 |
-
{"batch": 45, "reward": null, "loss": 0.
|
| 46 |
-
{"batch": 46, "reward": null, "loss":
|
| 47 |
-
{"batch": 47, "reward": null, "loss":
|
| 48 |
-
{"batch": 48, "reward": null, "loss": -
|
| 49 |
-
{"batch": 49, "reward": null, "loss":
|
| 50 |
-
{"batch": 50, "reward": null, "loss":
|
| 51 |
-
{"batch": 51, "reward": null, "loss":
|
| 52 |
-
{"batch": 52, "reward": null, "loss":
|
| 53 |
-
{"batch": 53, "reward": null, "loss":
|
| 54 |
-
{"batch": 54, "reward": null, "loss":
|
| 55 |
-
{"batch": 55, "reward": null, "loss":
|
| 56 |
-
{"batch": 56, "reward": null, "loss":
|
| 57 |
-
{"batch": 57, "reward": null, "loss":
|
| 58 |
-
{"batch": 58, "reward": null, "loss":
|
| 59 |
-
{"batch": 59, "reward": null, "loss":
|
| 60 |
-
{"batch": 60, "reward": null, "loss":
|
| 61 |
-
{"batch": 61, "reward": null, "loss":
|
| 62 |
-
{"batch": 62, "reward": null, "loss":
|
| 63 |
-
{"batch": 63, "reward": null, "loss":
|
| 64 |
-
{"batch": 64, "reward": null, "loss":
|
| 65 |
-
{"batch": 65, "reward": null, "loss":
|
| 66 |
-
{"batch": 66, "reward": null, "loss":
|
| 67 |
-
{"batch": 67, "reward": null, "loss":
|
| 68 |
-
{"batch": 68, "reward": null, "loss": 0.
|
| 69 |
-
{"batch": 69, "reward": null, "loss":
|
| 70 |
-
{"batch": 70, "reward": null, "loss":
|
| 71 |
-
{"batch": 71, "reward": null, "loss":
|
| 72 |
-
{"batch": 72, "reward": null, "loss":
|
| 73 |
-
{"batch": 73, "reward": null, "loss": 0.
|
| 74 |
-
{"batch": 74, "reward": null, "loss":
|
| 75 |
-
{"batch": 75, "reward": null, "loss":
|
| 76 |
-
{"batch": 76, "reward": null, "loss":
|
| 77 |
-
{"batch": 77, "reward": null, "loss":
|
| 78 |
-
{"batch": 78, "reward": null, "loss":
|
| 79 |
-
{"batch": 79, "reward": null, "loss":
|
| 80 |
-
{"batch": 80, "reward": null, "loss":
|
| 81 |
-
{"batch": 81, "reward": null, "loss": -0.
|
| 82 |
-
{"batch": 82, "reward": null, "loss":
|
| 83 |
-
{"batch": 83, "reward": null, "loss":
|
| 84 |
-
{"batch": 84, "reward": null, "loss": 0.
|
| 85 |
-
{"batch": 85, "reward": null, "loss":
|
| 86 |
-
{"batch": 86, "reward": null, "loss":
|
| 87 |
-
{"batch": 87, "reward": null, "loss":
|
| 88 |
-
{"batch": 88, "reward": null, "loss":
|
| 89 |
-
{"batch": 89, "reward": null, "loss":
|
| 90 |
-
{"batch": 90, "reward": null, "loss": 0.
|
| 91 |
-
{"batch": 91, "reward": null, "loss":
|
| 92 |
-
{"batch": 92, "reward": null, "loss":
|
| 93 |
-
{"batch": 93, "reward": null, "loss":
|
| 94 |
-
{"batch": 94, "reward": null, "loss":
|
| 95 |
-
{"batch": 95, "reward": null, "loss":
|
| 96 |
-
{"batch": 96, "reward": null, "loss":
|
| 97 |
-
{"batch": 97, "reward": null, "loss":
|
| 98 |
-
{"batch": 98, "reward": null, "loss":
|
| 99 |
-
{"batch": 99, "reward": null, "loss":
|
| 100 |
-
{"batch": 100, "reward": null, "loss":
|
| 101 |
-
{"batch": 101, "reward": null, "loss":
|
| 102 |
-
{"batch": 102, "reward": null, "loss":
|
| 103 |
-
{"batch": 103, "reward": null, "loss":
|
| 104 |
-
{"batch": 104, "reward": null, "loss":
|
| 105 |
-
{"batch": 105, "reward": null, "loss":
|
| 106 |
-
{"batch": 106, "reward": null, "loss":
|
| 107 |
-
{"batch": 107, "reward": null, "loss":
|
| 108 |
-
{"batch": 108, "reward": null, "loss":
|
| 109 |
-
{"batch": 109, "reward": null, "loss":
|
| 110 |
-
{"batch": 110, "reward": null, "loss":
|
| 111 |
-
{"batch": 111, "reward": null, "loss":
|
| 112 |
-
{"batch": 112, "reward": null, "loss":
|
| 113 |
-
{"batch": 113, "reward": null, "loss": 0.
|
| 114 |
-
{"batch": 114, "reward": null, "loss":
|
| 115 |
-
{"batch": 115, "reward": null, "loss":
|
| 116 |
-
{"batch": 116, "reward": null, "loss": 0.
|
| 117 |
-
{"batch": 117, "reward": null, "loss":
|
| 118 |
-
{"batch": 118, "reward": null, "loss": 0.
|
| 119 |
-
{"batch": 119, "reward": null, "loss":
|
| 120 |
-
{"batch": 120, "reward": null, "loss":
|
| 121 |
-
{"batch": 121, "reward": null, "loss":
|
| 122 |
-
{"batch": 122, "reward": null, "loss":
|
| 123 |
-
{"batch": 123, "reward": null, "loss":
|
| 124 |
-
{"batch": 124, "reward": null, "loss":
|
| 125 |
-
{"batch": 125, "reward": null, "loss":
|
| 126 |
-
{"batch": 126, "reward": null, "loss":
|
| 127 |
-
{"batch": 127, "reward": null, "loss":
|
| 128 |
-
{"batch": 128, "reward": null, "loss":
|
| 129 |
-
{"batch": 129, "reward": null, "loss":
|
| 130 |
-
{"batch": 130, "reward": null, "loss":
|
| 131 |
-
{"batch": 131, "reward": null, "loss":
|
| 132 |
-
{"batch": 132, "reward": null, "loss":
|
| 133 |
-
{"batch": 133, "reward": null, "loss":
|
| 134 |
-
{"batch": 134, "reward": null, "loss":
|
| 135 |
-
{"batch": 135, "reward": null, "loss":
|
| 136 |
-
{"batch": 136, "reward": null, "loss":
|
| 137 |
-
{"batch": 137, "reward": null, "loss":
|
| 138 |
-
{"batch": 138, "reward": null, "loss":
|
| 139 |
-
{"batch": 139, "reward": null, "loss":
|
| 140 |
-
{"batch": 140, "reward": null, "loss":
|
| 141 |
-
{"batch": 141, "reward": null, "loss": -
|
| 142 |
-
{"batch": 142, "reward": null, "loss":
|
| 143 |
-
{"batch": 143, "reward": null, "loss":
|
| 144 |
-
{"batch": 144, "reward": null, "loss":
|
| 145 |
-
{"batch": 145, "reward": null, "loss":
|
| 146 |
-
{"batch": 146, "reward": null, "loss":
|
| 147 |
-
{"batch": 147, "reward": null, "loss":
|
| 148 |
-
{"batch": 148, "reward": null, "loss":
|
| 149 |
-
{"batch": 149, "reward": null, "loss":
|
| 150 |
-
{"batch": 150, "reward": null, "loss":
|
| 151 |
-
{"batch": 151, "reward": null, "loss":
|
| 152 |
-
{"batch": 152, "reward": null, "loss":
|
| 153 |
-
{"batch": 153, "reward": null, "loss":
|
| 154 |
-
{"batch": 154, "reward": null, "loss":
|
| 155 |
-
{"batch": 155, "reward": null, "loss":
|
| 156 |
-
{"batch": 156, "reward": null, "loss":
|
| 157 |
-
{"batch": 157, "reward": null, "loss":
|
| 158 |
-
{"batch": 158, "reward": null, "loss":
|
| 159 |
-
{"batch": 159, "reward": null, "loss":
|
| 160 |
-
{"batch": 160, "reward": null, "loss":
|
| 161 |
-
{"batch": 161, "reward": null, "loss":
|
| 162 |
-
{"batch": 162, "reward": null, "loss":
|
| 163 |
-
{"batch": 163, "reward": null, "loss":
|
| 164 |
-
{"batch": 164, "reward": null, "loss":
|
| 165 |
-
{"batch": 165, "reward": null, "loss": 0.
|
| 166 |
-
{"batch": 166, "reward": null, "loss":
|
| 167 |
-
{"batch": 167, "reward": null, "loss":
|
| 168 |
-
{"batch": 168, "reward": null, "loss":
|
| 169 |
-
{"batch": 169, "reward": null, "loss":
|
| 170 |
-
{"batch": 170, "reward": null, "loss":
|
| 171 |
-
{"batch": 171, "reward": null, "loss":
|
| 172 |
-
{"batch": 172, "reward": null, "loss":
|
| 173 |
-
{"batch": 173, "reward": null, "loss":
|
| 174 |
-
{"batch": 174, "reward": null, "loss":
|
| 175 |
-
{"batch": 175, "reward": null, "loss":
|
| 176 |
-
{"batch": 176, "reward": null, "loss":
|
| 177 |
-
{"batch": 177, "reward": null, "loss":
|
| 178 |
-
{"batch": 178, "reward": null, "loss": 0.
|
| 179 |
-
{"batch": 179, "reward": null, "loss":
|
| 180 |
-
{"batch": 180, "reward": null, "loss":
|
| 181 |
-
{"batch": 181, "reward": null, "loss":
|
| 182 |
-
{"batch": 182, "reward": null, "loss":
|
| 183 |
-
{"batch": 183, "reward": null, "loss":
|
| 184 |
-
{"batch": 184, "reward": null, "loss": 0.
|
| 185 |
-
{"batch": 185, "reward": null, "loss":
|
| 186 |
-
{"batch": 186, "reward": null, "loss":
|
| 187 |
-
{"batch": 187, "reward": null, "loss": 0.
|
| 188 |
-
{"batch": 188, "reward": null, "loss":
|
| 189 |
-
{"batch": 189, "reward": null, "loss":
|
| 190 |
-
{"batch": 190, "reward": null, "loss":
|
| 191 |
-
{"batch": 191, "reward": null, "loss":
|
| 192 |
-
{"batch": 192, "reward": null, "loss":
|
| 193 |
-
{"batch": 193, "reward": null, "loss":
|
| 194 |
-
{"batch": 194, "reward": null, "loss":
|
| 195 |
-
{"batch": 195, "reward": null, "loss":
|
| 196 |
-
{"batch": 196, "reward": null, "loss":
|
| 197 |
-
{"batch": 197, "reward": null, "loss":
|
| 198 |
-
{"batch": 198, "reward": null, "loss":
|
| 199 |
-
{"batch": 199, "reward": null, "loss":
|
| 200 |
-
{"batch": 200, "reward": null, "loss": 0.
|
| 201 |
-
{"batch": 201, "reward": null, "loss":
|
| 202 |
-
{"batch": 202, "reward": null, "loss":
|
| 203 |
-
{"batch": 203, "reward": null, "loss":
|
| 204 |
-
{"batch": 204, "reward": null, "loss":
|
| 205 |
-
{"batch": 205, "reward": null, "loss":
|
| 206 |
-
{"batch": 206, "reward": null, "loss": 0.
|
| 207 |
-
{"batch": 207, "reward": null, "loss":
|
| 208 |
-
{"batch": 208, "reward": null, "loss":
|
| 209 |
-
{"batch": 209, "reward": null, "loss":
|
| 210 |
-
{"batch": 210, "reward": null, "loss":
|
| 211 |
-
{"batch": 211, "reward": null, "loss":
|
| 212 |
-
{"batch": 212, "reward": null, "loss":
|
| 213 |
-
{"batch": 213, "reward": null, "loss":
|
| 214 |
-
{"batch": 214, "reward": null, "loss":
|
| 215 |
-
{"batch": 215, "reward": null, "loss": -0.
|
| 216 |
-
{"batch": 216, "reward": null, "loss":
|
| 217 |
-
{"batch": 217, "reward": null, "loss":
|
| 218 |
-
{"batch": 218, "reward": null, "loss":
|
| 219 |
-
{"batch": 219, "reward": null, "loss":
|
| 220 |
-
{"batch": 220, "reward": null, "loss":
|
| 221 |
-
{"batch": 221, "reward": null, "loss":
|
| 222 |
-
{"batch": 222, "reward": null, "loss":
|
| 223 |
-
{"batch": 223, "reward": null, "loss":
|
| 224 |
-
{"batch": 224, "reward": null, "loss": 0.
|
| 225 |
-
{"batch": 225, "reward": null, "loss":
|
| 226 |
-
{"batch": 226, "reward": null, "loss":
|
| 227 |
-
{"batch": 227, "reward": null, "loss":
|
| 228 |
-
{"batch": 228, "reward": null, "loss":
|
| 229 |
-
{"batch": 229, "reward": null, "loss": 0.
|
| 230 |
-
{"batch": 230, "reward": null, "loss":
|
| 231 |
-
{"batch": 231, "reward": null, "loss":
|
| 232 |
-
{"batch": 232, "reward": null, "loss":
|
| 233 |
-
{"batch": 233, "reward": null, "loss":
|
| 234 |
-
{"batch": 234, "reward": null, "loss":
|
| 235 |
-
{"batch": 235, "reward": null, "loss":
|
| 236 |
-
{"batch": 236, "reward": null, "loss":
|
| 237 |
-
{"batch": 237, "reward": null, "loss":
|
| 238 |
-
{"batch": 238, "reward": null, "loss":
|
| 239 |
-
{"batch": 239, "reward": null, "loss":
|
| 240 |
-
{"batch": 240, "reward": null, "loss":
|
| 241 |
-
{"batch": 241, "reward": null, "loss":
|
| 242 |
-
{"batch": 242, "reward": null, "loss": -0.
|
| 243 |
-
{"batch": 243, "reward": null, "loss":
|
| 244 |
-
{"batch": 244, "reward": null, "loss":
|
| 245 |
-
{"batch": 245, "reward": null, "loss":
|
| 246 |
-
{"batch": 246, "reward": null, "loss":
|
| 247 |
-
{"batch": 247, "reward": null, "loss":
|
| 248 |
-
{"batch": 248, "reward": null, "loss":
|
| 249 |
-
{"batch": 249, "reward": null, "loss":
|
| 250 |
-
{"batch": 250, "reward": null, "loss":
|
| 251 |
-
{"batch": 251, "reward": null, "loss":
|
| 252 |
-
{"batch": 252, "reward": null, "loss":
|
| 253 |
-
{"batch": 253, "reward": null, "loss":
|
| 254 |
-
{"batch": 254, "reward": null, "loss":
|
| 255 |
-
{"batch": 255, "reward": null, "loss":
|
| 256 |
-
{"batch": 256, "reward": null, "loss":
|
| 257 |
-
{"batch": 257, "reward": null, "loss":
|
| 258 |
-
{"batch": 258, "reward": null, "loss":
|
| 259 |
-
{"batch": 259, "reward": null, "loss":
|
| 260 |
-
{"batch": 260, "reward": null, "loss":
|
| 261 |
-
{"batch": 261, "reward": null, "loss":
|
| 262 |
-
{"batch": 262, "reward": null, "loss":
|
| 263 |
-
{"batch": 263, "reward": null, "loss":
|
| 264 |
-
{"batch": 264, "reward": null, "loss":
|
| 265 |
-
{"batch": 265, "reward": null, "loss":
|
| 266 |
-
{"batch": 266, "reward": null, "loss":
|
| 267 |
-
{"batch": 267, "reward": null, "loss":
|
| 268 |
-
{"batch": 268, "reward": null, "loss":
|
| 269 |
-
{"batch": 269, "reward": null, "loss":
|
| 270 |
-
{"batch": 270, "reward": null, "loss":
|
| 271 |
-
{"batch": 271, "reward": null, "loss":
|
| 272 |
-
{"batch": 272, "reward": null, "loss":
|
| 273 |
-
{"batch": 273, "reward": null, "loss":
|
| 274 |
-
{"batch": 274, "reward": null, "loss":
|
| 275 |
-
{"batch": 275, "reward": null, "loss":
|
| 276 |
-
{"batch": 276, "reward": null, "loss":
|
| 277 |
-
{"batch": 277, "reward": null, "loss":
|
| 278 |
-
{"batch": 278, "reward": null, "loss":
|
| 279 |
-
{"batch": 279, "reward": null, "loss":
|
| 280 |
-
{"batch": 280, "reward": null, "loss":
|
| 281 |
-
{"batch": 281, "reward": null, "loss":
|
| 282 |
-
{"batch": 282, "reward": null, "loss":
|
| 283 |
-
{"batch": 283, "reward": null, "loss":
|
| 284 |
-
{"batch": 284, "reward": null, "loss":
|
| 285 |
-
{"batch": 285, "reward": null, "loss":
|
| 286 |
-
{"batch": 286, "reward": null, "loss":
|
| 287 |
-
{"batch": 287, "reward": null, "loss":
|
| 288 |
-
{"batch": 288, "reward": null, "loss":
|
| 289 |
-
{"batch": 289, "reward": null, "loss":
|
| 290 |
-
{"batch": 290, "reward": null, "loss":
|
| 291 |
-
{"batch": 291, "reward": null, "loss":
|
| 292 |
-
{"batch": 292, "reward": null, "loss": 0.
|
| 293 |
-
{"batch": 293, "reward": null, "loss":
|
| 294 |
-
{"batch": 294, "reward": null, "loss": 0.
|
| 295 |
-
{"batch": 295, "reward": null, "loss":
|
| 296 |
-
{"batch": 296, "reward": null, "loss":
|
| 297 |
-
{"batch": 297, "reward": null, "loss":
|
| 298 |
-
{"batch": 298, "reward": null, "loss":
|
| 299 |
-
{"batch": 299, "reward": null, "loss":
|
| 300 |
-
{"batch": 300, "reward": null, "loss":
|
| 301 |
-
{"batch": 301, "reward": null, "loss":
|
| 302 |
-
{"batch": 302, "reward": null, "loss":
|
| 303 |
-
{"batch": 303, "reward": null, "loss":
|
| 304 |
-
{"batch": 304, "reward": null, "loss":
|
| 305 |
-
{"batch": 305, "reward": null, "loss": 0.
|
| 306 |
-
{"batch": 306, "reward": null, "loss":
|
| 307 |
-
{"batch": 307, "reward": null, "loss":
|
| 308 |
-
{"batch": 308, "reward": null, "loss":
|
| 309 |
-
{"batch": 309, "reward": null, "loss":
|
| 310 |
-
{"batch": 310, "reward": null, "loss":
|
| 311 |
-
{"batch": 311, "reward": null, "loss": 0.
|
| 312 |
-
{"batch": 312, "reward": null, "loss":
|
| 313 |
-
{"batch": 313, "reward": null, "loss":
|
| 314 |
-
{"batch": 314, "reward": null, "loss":
|
| 315 |
-
{"batch": 315, "reward": null, "loss": 0.
|
| 316 |
-
{"batch": 316, "reward": null, "loss":
|
| 317 |
-
{"batch": 317, "reward": null, "loss":
|
| 318 |
-
{"batch": 318, "reward": null, "loss":
|
| 319 |
-
{"batch": 319, "reward": null, "loss":
|
| 320 |
-
{"batch": 320, "reward": null, "loss":
|
| 321 |
-
{"batch": 321, "reward": null, "loss": 0.
|
| 322 |
-
{"batch": 322, "reward": null, "loss":
|
| 323 |
-
{"batch": 323, "reward": null, "loss":
|
| 324 |
-
{"batch": 324, "reward": null, "loss":
|
| 325 |
-
{"batch": 325, "reward": null, "loss":
|
| 326 |
-
{"batch": 326, "reward": null, "loss":
|
| 327 |
-
{"batch": 327, "reward": null, "loss":
|
| 328 |
-
{"batch": 328, "reward": null, "loss":
|
| 329 |
-
{"batch": 329, "reward": null, "loss":
|
| 330 |
-
{"batch": 330, "reward": null, "loss":
|
| 331 |
-
{"batch": 331, "reward": null, "loss":
|
| 332 |
-
{"batch": 332, "reward": null, "loss":
|
| 333 |
-
{"batch": 333, "reward": null, "loss":
|
| 334 |
-
{"batch": 334, "reward": null, "loss":
|
| 335 |
-
{"batch": 335, "reward": null, "loss":
|
| 336 |
-
{"batch": 336, "reward": null, "loss":
|
| 337 |
-
{"batch": 337, "reward": null, "loss":
|
| 338 |
-
{"batch": 338, "reward": null, "loss": 0.
|
| 339 |
-
{"batch": 339, "reward": null, "loss":
|
| 340 |
-
{"batch": 340, "reward": null, "loss":
|
| 341 |
-
{"batch": 341, "reward": null, "loss":
|
| 342 |
-
{"batch": 342, "reward": null, "loss":
|
| 343 |
-
{"batch": 343, "reward": null, "loss": -0.
|
| 344 |
-
{"batch": 344, "reward": null, "loss":
|
| 345 |
-
{"batch": 345, "reward": null, "loss":
|
| 346 |
-
{"batch": 346, "reward": null, "loss":
|
| 347 |
-
{"batch": 347, "reward": null, "loss":
|
| 348 |
-
{"batch": 348, "reward": null, "loss":
|
| 349 |
-
{"batch": 349, "reward": null, "loss":
|
| 350 |
-
{"batch": 350, "reward": null, "loss":
|
| 351 |
-
{"batch": 351, "reward": null, "loss":
|
| 352 |
-
{"batch": 352, "reward": null, "loss":
|
| 353 |
-
{"batch": 353, "reward": null, "loss":
|
| 354 |
-
{"batch": 354, "reward": null, "loss":
|
| 355 |
-
{"batch": 355, "reward": null, "loss":
|
| 356 |
-
{"batch": 356, "reward": null, "loss":
|
| 357 |
-
{"batch": 357, "reward": null, "loss":
|
| 358 |
-
{"batch": 358, "reward": null, "loss":
|
| 359 |
-
{"batch": 359, "reward": null, "loss": 0.
|
| 360 |
-
{"batch": 360, "reward": null, "loss":
|
| 361 |
-
{"batch": 361, "reward": null, "loss":
|
| 362 |
-
{"batch": 362, "reward": null, "loss":
|
| 363 |
-
{"batch": 363, "reward": null, "loss":
|
| 364 |
-
{"batch": 364, "reward": null, "loss":
|
| 365 |
-
{"batch": 365, "reward": null, "loss":
|
| 366 |
-
{"batch": 366, "reward": null, "loss":
|
| 367 |
-
{"batch": 367, "reward": null, "loss": 0.
|
| 368 |
-
{"batch": 368, "reward": null, "loss":
|
| 369 |
-
{"batch": 369, "reward": null, "loss":
|
| 370 |
-
{"batch": 370, "reward": null, "loss": -0.
|
| 371 |
-
{"batch": 371, "reward": null, "loss":
|
| 372 |
-
{"batch": 372, "reward": null, "loss":
|
| 373 |
-
{"batch": 373, "reward": null, "loss":
|
| 374 |
-
{"batch": 374, "reward": null, "loss":
|
| 375 |
-
{"batch": 375, "reward": null, "loss":
|
| 376 |
-
{"batch": 376, "reward": null, "loss":
|
| 377 |
-
{"batch": 377, "reward": null, "loss":
|
| 378 |
-
{"batch": 378, "reward": null, "loss":
|
| 379 |
-
{"batch": 379, "reward": null, "loss":
|
| 380 |
-
{"batch": 380, "reward": null, "loss":
|
| 381 |
-
{"batch": 381, "reward": null, "loss":
|
| 382 |
-
{"batch": 382, "reward": null, "loss":
|
| 383 |
-
{"batch": 383, "reward": null, "loss": 0.
|
| 384 |
-
{"batch": 384, "reward": null, "loss":
|
| 385 |
-
{"batch": 385, "reward": null, "loss":
|
| 386 |
-
{"batch": 386, "reward": null, "loss":
|
| 387 |
-
{"batch": 387, "reward": null, "loss":
|
| 388 |
-
{"batch": 388, "reward": null, "loss":
|
| 389 |
-
{"batch": 389, "reward": null, "loss":
|
| 390 |
-
{"batch": 390, "reward": null, "loss":
|
| 391 |
-
{"batch": 391, "reward": null, "loss":
|
| 392 |
-
{"batch": 392, "reward": null, "loss":
|
| 393 |
-
{"batch": 393, "reward": null, "loss":
|
| 394 |
-
{"batch": 394, "reward": null, "loss":
|
| 395 |
-
{"batch": 395, "reward": null, "loss":
|
| 396 |
-
{"batch": 396, "reward": null, "loss":
|
| 397 |
-
{"batch": 397, "reward": null, "loss":
|
| 398 |
-
{"batch": 398, "reward": null, "loss":
|
| 399 |
-
{"batch": 399, "reward": null, "loss":
|
| 400 |
-
{"batch": 400, "reward": null, "loss":
|
| 401 |
-
{"batch": 401, "reward": null, "loss":
|
| 402 |
-
{"batch": 402, "reward": null, "loss":
|
| 403 |
-
{"batch": 403, "reward": null, "loss":
|
| 404 |
-
{"batch": 404, "reward": null, "loss":
|
| 405 |
-
{"batch": 405, "reward": null, "loss":
|
| 406 |
-
{"batch": 406, "reward": null, "loss":
|
| 407 |
-
{"batch": 407, "reward": null, "loss":
|
| 408 |
-
{"batch": 408, "reward": null, "loss":
|
| 409 |
-
{"batch": 409, "reward": null, "loss":
|
| 410 |
-
{"batch": 410, "reward": null, "loss":
|
| 411 |
-
{"batch": 411, "reward": null, "loss": 0.
|
| 412 |
-
{"batch": 412, "reward": null, "loss":
|
| 413 |
-
{"batch": 413, "reward": null, "loss":
|
| 414 |
-
{"batch": 414, "reward": null, "loss":
|
| 415 |
-
{"batch": 415, "reward": null, "loss":
|
| 416 |
-
{"batch": 416, "reward": null, "loss":
|
| 417 |
-
{"batch": 417, "reward": null, "loss":
|
| 418 |
-
{"batch": 418, "reward": null, "loss": 0.
|
| 419 |
-
{"batch": 419, "reward": null, "loss":
|
| 420 |
-
{"batch": 420, "reward": null, "loss":
|
| 421 |
-
{"batch": 421, "reward": null, "loss": 0.
|
| 422 |
-
{"batch": 422, "reward": null, "loss":
|
| 423 |
-
{"batch": 423, "reward": null, "loss":
|
| 424 |
-
{"batch": 424, "reward": null, "loss":
|
| 425 |
-
{"batch": 425, "reward": null, "loss":
|
| 426 |
-
{"batch": 426, "reward": null, "loss":
|
| 427 |
-
{"batch": 427, "reward": null, "loss":
|
| 428 |
-
{"batch": 428, "reward": null, "loss":
|
| 429 |
-
{"batch": 429, "reward": null, "loss":
|
| 430 |
-
{"batch": 430, "reward": null, "loss":
|
| 431 |
-
{"batch": 431, "reward": null, "loss":
|
| 432 |
-
{"batch": 432, "reward": null, "loss":
|
| 433 |
-
{"batch": 433, "reward": null, "loss":
|
| 434 |
-
{"batch": 434, "reward": null, "loss":
|
| 435 |
-
{"batch": 435, "reward": null, "loss":
|
| 436 |
-
{"batch": 436, "reward": null, "loss":
|
| 437 |
-
{"batch": 437, "reward": null, "loss":
|
| 438 |
-
{"batch": 438, "reward": null, "loss":
|
| 439 |
-
{"batch": 439, "reward": null, "loss":
|
| 440 |
-
{"batch": 440, "reward": null, "loss":
|
| 441 |
-
{"batch": 441, "reward": null, "loss":
|
| 442 |
-
{"batch": 442, "reward": null, "loss":
|
| 443 |
-
{"batch": 443, "reward": null, "loss":
|
| 444 |
-
{"batch": 444, "reward": null, "loss":
|
| 445 |
-
{"batch": 445, "reward": null, "loss":
|
| 446 |
-
{"batch": 446, "reward": null, "loss":
|
| 447 |
-
{"batch": 447, "reward": null, "loss":
|
| 448 |
-
{"batch": 448, "reward": null, "loss":
|
| 449 |
-
{"batch": 449, "reward": null, "loss":
|
| 450 |
-
{"batch": 450, "reward": null, "loss":
|
| 451 |
-
{"batch": 451, "reward": null, "loss":
|
| 452 |
-
{"batch": 452, "reward": null, "loss":
|
| 453 |
-
{"batch": 453, "reward": null, "loss":
|
| 454 |
-
{"batch": 454, "reward": null, "loss":
|
| 455 |
-
{"batch": 455, "reward": null, "loss":
|
| 456 |
-
{"batch": 456, "reward": null, "loss":
|
| 457 |
-
{"batch": 457, "reward": null, "loss": 0.
|
| 458 |
-
{"batch": 458, "reward": null, "loss":
|
| 459 |
-
{"batch": 459, "reward": null, "loss":
|
| 460 |
-
{"batch": 460, "reward": null, "loss":
|
| 461 |
-
{"batch": 461, "reward": null, "loss":
|
| 462 |
-
{"batch": 462, "reward": null, "loss":
|
| 463 |
-
{"batch": 463, "reward": null, "loss":
|
| 464 |
-
{"batch": 464, "reward": null, "loss":
|
| 465 |
-
{"batch": 465, "reward": null, "loss":
|
| 466 |
-
{"batch": 466, "reward": null, "loss":
|
| 467 |
-
{"batch": 467, "reward": null, "loss":
|
| 468 |
-
{"batch": 468, "reward": null, "loss":
|
| 469 |
-
{"batch": 469, "reward": null, "loss":
|
| 470 |
-
{"batch": 470, "reward": null, "loss":
|
| 471 |
-
{"batch": 471, "reward": null, "loss":
|
| 472 |
-
{"batch": 472, "reward": null, "loss":
|
| 473 |
-
{"batch": 473, "reward": null, "loss":
|
| 474 |
-
{"batch": 474, "reward": null, "loss":
|
| 475 |
-
{"batch": 475, "reward": null, "loss":
|
| 476 |
-
{"batch": 476, "reward": null, "loss":
|
| 477 |
-
{"batch": 477, "reward": null, "loss":
|
| 478 |
-
{"batch": 478, "reward": null, "loss":
|
| 479 |
-
{"batch": 479, "reward": null, "loss":
|
| 480 |
-
{"batch": 480, "reward": null, "loss": 0.
|
| 481 |
-
{"batch": 481, "reward": null, "loss":
|
| 482 |
-
{"batch": 482, "reward": null, "loss":
|
| 483 |
-
{"batch": 483, "reward": null, "loss":
|
| 484 |
-
{"batch": 484, "reward": null, "loss": 0.
|
| 485 |
-
{"batch": 485, "reward": null, "loss":
|
| 486 |
-
{"batch": 486, "reward": null, "loss":
|
| 487 |
-
{"batch": 487, "reward": null, "loss":
|
| 488 |
-
{"batch": 488, "reward": null, "loss":
|
| 489 |
-
{"batch": 489, "reward": null, "loss":
|
| 490 |
-
{"batch": 490, "reward": null, "loss":
|
| 491 |
-
{"batch": 491, "reward": null, "loss":
|
| 492 |
-
{"batch": 492, "reward": null, "loss": 0.
|
| 493 |
-
{"batch": 493, "reward": null, "loss":
|
| 494 |
-
{"batch": 494, "reward": null, "loss":
|
| 495 |
-
{"batch": 495, "reward": null, "loss":
|
| 496 |
-
{"batch": 496, "reward": null, "loss":
|
| 497 |
-
{"batch": 497, "reward": null, "loss":
|
| 498 |
-
{"batch": 498, "reward": null, "loss":
|
| 499 |
-
{"batch": 499, "reward": null, "loss":
|
| 500 |
-
{"batch": 500, "reward": null, "loss":
|
| 501 |
-
{"batch": 501, "reward": null, "loss":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{"batch": 1, "reward": null, "loss": 0.0}
|
| 2 |
+
{"batch": 2, "reward": null, "loss": 0.0}
|
| 3 |
+
{"batch": 3, "reward": null, "loss": 0.0}
|
| 4 |
+
{"batch": 4, "reward": null, "loss": 0.0}
|
| 5 |
+
{"batch": 5, "reward": null, "loss": 0.0}
|
| 6 |
+
{"batch": 6, "reward": null, "loss": 0.0}
|
| 7 |
+
{"batch": 7, "reward": null, "loss": 0.0}
|
| 8 |
+
{"batch": 8, "reward": null, "loss": 0.0}
|
| 9 |
+
{"batch": 9, "reward": null, "loss": 0.0}
|
| 10 |
+
{"batch": 10, "reward": null, "loss": 0.0}
|
| 11 |
+
{"batch": 11, "reward": null, "loss": 0.5388}
|
| 12 |
+
{"batch": 12, "reward": null, "loss": 0.0}
|
| 13 |
+
{"batch": 13, "reward": null, "loss": 0.0}
|
| 14 |
+
{"batch": 14, "reward": null, "loss": 0.0}
|
| 15 |
+
{"batch": 15, "reward": null, "loss": 0.0}
|
| 16 |
+
{"batch": 16, "reward": null, "loss": 0.0}
|
| 17 |
+
{"batch": 17, "reward": null, "loss": 0.0}
|
| 18 |
+
{"batch": 18, "reward": null, "loss": -1.0771}
|
| 19 |
+
{"batch": 19, "reward": null, "loss": 0.0}
|
| 20 |
+
{"batch": 20, "reward": null, "loss": 0.0}
|
| 21 |
+
{"batch": 21, "reward": null, "loss": 0.0}
|
| 22 |
+
{"batch": 22, "reward": null, "loss": 0.0}
|
| 23 |
+
{"batch": 23, "reward": null, "loss": 0.0}
|
| 24 |
+
{"batch": 24, "reward": null, "loss": 0.0}
|
| 25 |
+
{"batch": 25, "reward": null, "loss": 0.1115}
|
| 26 |
+
{"batch": 26, "reward": null, "loss": 0.0}
|
| 27 |
+
{"batch": 27, "reward": null, "loss": 0.0001}
|
| 28 |
+
{"batch": 28, "reward": null, "loss": 0.0}
|
| 29 |
+
{"batch": 29, "reward": null, "loss": 0.1189}
|
| 30 |
+
{"batch": 30, "reward": null, "loss": 0.0}
|
| 31 |
+
{"batch": 31, "reward": null, "loss": 0.0}
|
| 32 |
+
{"batch": 32, "reward": null, "loss": 0.0}
|
| 33 |
+
{"batch": 33, "reward": null, "loss": 0.0}
|
| 34 |
+
{"batch": 34, "reward": null, "loss": 0.0}
|
| 35 |
+
{"batch": 35, "reward": null, "loss": 0.3886}
|
| 36 |
+
{"batch": 36, "reward": null, "loss": 0.0}
|
| 37 |
+
{"batch": 37, "reward": null, "loss": 0.0}
|
| 38 |
+
{"batch": 38, "reward": null, "loss": 0.0}
|
| 39 |
+
{"batch": 39, "reward": null, "loss": 0.0}
|
| 40 |
+
{"batch": 40, "reward": null, "loss": 0.3769}
|
| 41 |
+
{"batch": 41, "reward": null, "loss": 0.0}
|
| 42 |
+
{"batch": 42, "reward": null, "loss": 0.0}
|
| 43 |
+
{"batch": 43, "reward": null, "loss": 0.0}
|
| 44 |
+
{"batch": 44, "reward": null, "loss": 0.0}
|
| 45 |
+
{"batch": 45, "reward": null, "loss": 0.0}
|
| 46 |
+
{"batch": 46, "reward": null, "loss": 0.0001}
|
| 47 |
+
{"batch": 47, "reward": null, "loss": 0.0}
|
| 48 |
+
{"batch": 48, "reward": null, "loss": -0.1641}
|
| 49 |
+
{"batch": 49, "reward": null, "loss": 0.0}
|
| 50 |
+
{"batch": 50, "reward": null, "loss": -0.0944}
|
| 51 |
+
{"batch": 51, "reward": null, "loss": 0.0}
|
| 52 |
+
{"batch": 52, "reward": null, "loss": 0.0}
|
| 53 |
+
{"batch": 53, "reward": null, "loss": 0.0}
|
| 54 |
+
{"batch": 54, "reward": null, "loss": 0.0}
|
| 55 |
+
{"batch": 55, "reward": null, "loss": 0.0}
|
| 56 |
+
{"batch": 56, "reward": null, "loss": 0.0}
|
| 57 |
+
{"batch": 57, "reward": null, "loss": 0.0}
|
| 58 |
+
{"batch": 58, "reward": null, "loss": 0.0}
|
| 59 |
+
{"batch": 59, "reward": null, "loss": 0.0}
|
| 60 |
+
{"batch": 60, "reward": null, "loss": 0.0}
|
| 61 |
+
{"batch": 61, "reward": null, "loss": -0.4932}
|
| 62 |
+
{"batch": 62, "reward": null, "loss": 0.0}
|
| 63 |
+
{"batch": 63, "reward": null, "loss": 0.0335}
|
| 64 |
+
{"batch": 64, "reward": null, "loss": 0.0}
|
| 65 |
+
{"batch": 65, "reward": null, "loss": 0.0}
|
| 66 |
+
{"batch": 66, "reward": null, "loss": -0.0811}
|
| 67 |
+
{"batch": 67, "reward": null, "loss": 0.0}
|
| 68 |
+
{"batch": 68, "reward": null, "loss": 0.0}
|
| 69 |
+
{"batch": 69, "reward": null, "loss": 0.0}
|
| 70 |
+
{"batch": 70, "reward": null, "loss": 0.3967}
|
| 71 |
+
{"batch": 71, "reward": null, "loss": 0.0}
|
| 72 |
+
{"batch": 72, "reward": null, "loss": 0.0002}
|
| 73 |
+
{"batch": 73, "reward": null, "loss": 0.0}
|
| 74 |
+
{"batch": 74, "reward": null, "loss": 0.0}
|
| 75 |
+
{"batch": 75, "reward": null, "loss": 0.0}
|
| 76 |
+
{"batch": 76, "reward": null, "loss": 0.0}
|
| 77 |
+
{"batch": 77, "reward": null, "loss": 0.0}
|
| 78 |
+
{"batch": 78, "reward": null, "loss": 0.0}
|
| 79 |
+
{"batch": 79, "reward": null, "loss": 0.0}
|
| 80 |
+
{"batch": 80, "reward": null, "loss": 0.0}
|
| 81 |
+
{"batch": 81, "reward": null, "loss": -0.2583}
|
| 82 |
+
{"batch": 82, "reward": null, "loss": 0.5617}
|
| 83 |
+
{"batch": 83, "reward": null, "loss": 0.0}
|
| 84 |
+
{"batch": 84, "reward": null, "loss": 0.0001}
|
| 85 |
+
{"batch": 85, "reward": null, "loss": 0.0008}
|
| 86 |
+
{"batch": 86, "reward": null, "loss": 0.0}
|
| 87 |
+
{"batch": 87, "reward": null, "loss": 0.0}
|
| 88 |
+
{"batch": 88, "reward": null, "loss": 0.0921}
|
| 89 |
+
{"batch": 89, "reward": null, "loss": 0.0}
|
| 90 |
+
{"batch": 90, "reward": null, "loss": 0.0}
|
| 91 |
+
{"batch": 91, "reward": null, "loss": 0.0}
|
| 92 |
+
{"batch": 92, "reward": null, "loss": 0.0}
|
| 93 |
+
{"batch": 93, "reward": null, "loss": 0.0001}
|
| 94 |
+
{"batch": 94, "reward": null, "loss": 0.0}
|
| 95 |
+
{"batch": 95, "reward": null, "loss": 0.0}
|
| 96 |
+
{"batch": 96, "reward": null, "loss": 0.0}
|
| 97 |
+
{"batch": 97, "reward": null, "loss": 0.0}
|
| 98 |
+
{"batch": 98, "reward": null, "loss": 0.0001}
|
| 99 |
+
{"batch": 99, "reward": null, "loss": 0.0}
|
| 100 |
+
{"batch": 100, "reward": null, "loss": 0.0}
|
| 101 |
+
{"batch": 101, "reward": null, "loss": 0.0}
|
| 102 |
+
{"batch": 102, "reward": null, "loss": 0.0}
|
| 103 |
+
{"batch": 103, "reward": null, "loss": 0.0}
|
| 104 |
+
{"batch": 104, "reward": null, "loss": 0.0}
|
| 105 |
+
{"batch": 105, "reward": null, "loss": -0.3722}
|
| 106 |
+
{"batch": 106, "reward": null, "loss": 0.0}
|
| 107 |
+
{"batch": 107, "reward": null, "loss": 0.1709}
|
| 108 |
+
{"batch": 108, "reward": null, "loss": 0.0}
|
| 109 |
+
{"batch": 109, "reward": null, "loss": 0.0}
|
| 110 |
+
{"batch": 110, "reward": null, "loss": 0.0}
|
| 111 |
+
{"batch": 111, "reward": null, "loss": 0.0}
|
| 112 |
+
{"batch": 112, "reward": null, "loss": 0.0}
|
| 113 |
+
{"batch": 113, "reward": null, "loss": -0.7259}
|
| 114 |
+
{"batch": 114, "reward": null, "loss": 0.0}
|
| 115 |
+
{"batch": 115, "reward": null, "loss": 0.0}
|
| 116 |
+
{"batch": 116, "reward": null, "loss": 0.0}
|
| 117 |
+
{"batch": 117, "reward": null, "loss": 0.1245}
|
| 118 |
+
{"batch": 118, "reward": null, "loss": 0.0002}
|
| 119 |
+
{"batch": 119, "reward": null, "loss": -0.6463}
|
| 120 |
+
{"batch": 120, "reward": null, "loss": 0.0}
|
| 121 |
+
{"batch": 121, "reward": null, "loss": 0.0001}
|
| 122 |
+
{"batch": 122, "reward": null, "loss": 0.0}
|
| 123 |
+
{"batch": 123, "reward": null, "loss": 0.0}
|
| 124 |
+
{"batch": 124, "reward": null, "loss": 0.212}
|
| 125 |
+
{"batch": 125, "reward": null, "loss": 0.0}
|
| 126 |
+
{"batch": 126, "reward": null, "loss": 0.0}
|
| 127 |
+
{"batch": 127, "reward": null, "loss": -0.4137}
|
| 128 |
+
{"batch": 128, "reward": null, "loss": 0.0001}
|
| 129 |
+
{"batch": 129, "reward": null, "loss": -0.1818}
|
| 130 |
+
{"batch": 130, "reward": null, "loss": 0.0001}
|
| 131 |
+
{"batch": 131, "reward": null, "loss": -0.4392}
|
| 132 |
+
{"batch": 132, "reward": null, "loss": 0.0001}
|
| 133 |
+
{"batch": 133, "reward": null, "loss": 0.0}
|
| 134 |
+
{"batch": 134, "reward": null, "loss": 0.0}
|
| 135 |
+
{"batch": 135, "reward": null, "loss": 0.0}
|
| 136 |
+
{"batch": 136, "reward": null, "loss": -0.0196}
|
| 137 |
+
{"batch": 137, "reward": null, "loss": 0.0}
|
| 138 |
+
{"batch": 138, "reward": null, "loss": -0.7102}
|
| 139 |
+
{"batch": 139, "reward": null, "loss": 0.3092}
|
| 140 |
+
{"batch": 140, "reward": null, "loss": 0.0001}
|
| 141 |
+
{"batch": 141, "reward": null, "loss": -0.2392}
|
| 142 |
+
{"batch": 142, "reward": null, "loss": 0.0001}
|
| 143 |
+
{"batch": 143, "reward": null, "loss": -0.1893}
|
| 144 |
+
{"batch": 144, "reward": null, "loss": -1.0399}
|
| 145 |
+
{"batch": 145, "reward": null, "loss": 0.0}
|
| 146 |
+
{"batch": 146, "reward": null, "loss": 0.0}
|
| 147 |
+
{"batch": 147, "reward": null, "loss": 0.0}
|
| 148 |
+
{"batch": 148, "reward": null, "loss": 0.0001}
|
| 149 |
+
{"batch": 149, "reward": null, "loss": 0.0}
|
| 150 |
+
{"batch": 150, "reward": null, "loss": -0.2623}
|
| 151 |
+
{"batch": 151, "reward": null, "loss": 0.0}
|
| 152 |
+
{"batch": 152, "reward": null, "loss": 0.0}
|
| 153 |
+
{"batch": 153, "reward": null, "loss": 0.2957}
|
| 154 |
+
{"batch": 154, "reward": null, "loss": -0.4308}
|
| 155 |
+
{"batch": 155, "reward": null, "loss": -0.1464}
|
| 156 |
+
{"batch": 156, "reward": null, "loss": 0.0}
|
| 157 |
+
{"batch": 157, "reward": null, "loss": 0.0001}
|
| 158 |
+
{"batch": 158, "reward": null, "loss": 0.0}
|
| 159 |
+
{"batch": 159, "reward": null, "loss": 0.0}
|
| 160 |
+
{"batch": 160, "reward": null, "loss": 0.0}
|
| 161 |
+
{"batch": 161, "reward": null, "loss": 0.0}
|
| 162 |
+
{"batch": 162, "reward": null, "loss": -0.2758}
|
| 163 |
+
{"batch": 163, "reward": null, "loss": 0.0}
|
| 164 |
+
{"batch": 164, "reward": null, "loss": 0.0}
|
| 165 |
+
{"batch": 165, "reward": null, "loss": -0.0491}
|
| 166 |
+
{"batch": 166, "reward": null, "loss": 0.0}
|
| 167 |
+
{"batch": 167, "reward": null, "loss": -0.2902}
|
| 168 |
+
{"batch": 168, "reward": null, "loss": -0.0828}
|
| 169 |
+
{"batch": 169, "reward": null, "loss": 0.563}
|
| 170 |
+
{"batch": 170, "reward": null, "loss": 0.0}
|
| 171 |
+
{"batch": 171, "reward": null, "loss": -0.1134}
|
| 172 |
+
{"batch": 172, "reward": null, "loss": 0.0005}
|
| 173 |
+
{"batch": 173, "reward": null, "loss": 0.0}
|
| 174 |
+
{"batch": 174, "reward": null, "loss": 0.1086}
|
| 175 |
+
{"batch": 175, "reward": null, "loss": 0.0001}
|
| 176 |
+
{"batch": 176, "reward": null, "loss": -1.3525}
|
| 177 |
+
{"batch": 177, "reward": null, "loss": 0.0}
|
| 178 |
+
{"batch": 178, "reward": null, "loss": 0.1238}
|
| 179 |
+
{"batch": 179, "reward": null, "loss": -0.2254}
|
| 180 |
+
{"batch": 180, "reward": null, "loss": 0.0011}
|
| 181 |
+
{"batch": 181, "reward": null, "loss": 0.0}
|
| 182 |
+
{"batch": 182, "reward": null, "loss": 0.0002}
|
| 183 |
+
{"batch": 183, "reward": null, "loss": 0.0}
|
| 184 |
+
{"batch": 184, "reward": null, "loss": 0.0826}
|
| 185 |
+
{"batch": 185, "reward": null, "loss": 0.0005}
|
| 186 |
+
{"batch": 186, "reward": null, "loss": -0.1388}
|
| 187 |
+
{"batch": 187, "reward": null, "loss": 0.0}
|
| 188 |
+
{"batch": 188, "reward": null, "loss": 0.0003}
|
| 189 |
+
{"batch": 189, "reward": null, "loss": 0.0043}
|
| 190 |
+
{"batch": 190, "reward": null, "loss": 0.0001}
|
| 191 |
+
{"batch": 191, "reward": null, "loss": 0.0007}
|
| 192 |
+
{"batch": 192, "reward": null, "loss": -0.1357}
|
| 193 |
+
{"batch": 193, "reward": null, "loss": -0.122}
|
| 194 |
+
{"batch": 194, "reward": null, "loss": -0.1916}
|
| 195 |
+
{"batch": 195, "reward": null, "loss": 0.0005}
|
| 196 |
+
{"batch": 196, "reward": null, "loss": 0.0}
|
| 197 |
+
{"batch": 197, "reward": null, "loss": 0.0002}
|
| 198 |
+
{"batch": 198, "reward": null, "loss": 0.0006}
|
| 199 |
+
{"batch": 199, "reward": null, "loss": 0.1541}
|
| 200 |
+
{"batch": 200, "reward": null, "loss": 0.0004}
|
| 201 |
+
{"batch": 201, "reward": null, "loss": 0.0}
|
| 202 |
+
{"batch": 202, "reward": null, "loss": 0.0002}
|
| 203 |
+
{"batch": 203, "reward": null, "loss": -0.1682}
|
| 204 |
+
{"batch": 204, "reward": null, "loss": 0.0004}
|
| 205 |
+
{"batch": 205, "reward": null, "loss": 0.0002}
|
| 206 |
+
{"batch": 206, "reward": null, "loss": 0.0}
|
| 207 |
+
{"batch": 207, "reward": null, "loss": -0.1111}
|
| 208 |
+
{"batch": 208, "reward": null, "loss": -0.0276}
|
| 209 |
+
{"batch": 209, "reward": null, "loss": -0.0052}
|
| 210 |
+
{"batch": 210, "reward": null, "loss": 0.0}
|
| 211 |
+
{"batch": 211, "reward": null, "loss": 0.0375}
|
| 212 |
+
{"batch": 212, "reward": null, "loss": 0.0002}
|
| 213 |
+
{"batch": 213, "reward": null, "loss": 0.1519}
|
| 214 |
+
{"batch": 214, "reward": null, "loss": 0.0495}
|
| 215 |
+
{"batch": 215, "reward": null, "loss": -0.1927}
|
| 216 |
+
{"batch": 216, "reward": null, "loss": 0.4832}
|
| 217 |
+
{"batch": 217, "reward": null, "loss": 0.0}
|
| 218 |
+
{"batch": 218, "reward": null, "loss": 0.0002}
|
| 219 |
+
{"batch": 219, "reward": null, "loss": -0.1173}
|
| 220 |
+
{"batch": 220, "reward": null, "loss": 0.0002}
|
| 221 |
+
{"batch": 221, "reward": null, "loss": 0.0}
|
| 222 |
+
{"batch": 222, "reward": null, "loss": 0.0693}
|
| 223 |
+
{"batch": 223, "reward": null, "loss": 0.0075}
|
| 224 |
+
{"batch": 224, "reward": null, "loss": 0.0}
|
| 225 |
+
{"batch": 225, "reward": null, "loss": 0.0001}
|
| 226 |
+
{"batch": 226, "reward": null, "loss": 0.0004}
|
| 227 |
+
{"batch": 227, "reward": null, "loss": 0.0}
|
| 228 |
+
{"batch": 228, "reward": null, "loss": 0.0001}
|
| 229 |
+
{"batch": 229, "reward": null, "loss": 0.2038}
|
| 230 |
+
{"batch": 230, "reward": null, "loss": 0.0001}
|
| 231 |
+
{"batch": 231, "reward": null, "loss": 0.0}
|
| 232 |
+
{"batch": 232, "reward": null, "loss": 0.0001}
|
| 233 |
+
{"batch": 233, "reward": null, "loss": 0.0}
|
| 234 |
+
{"batch": 234, "reward": null, "loss": 0.0}
|
| 235 |
+
{"batch": 235, "reward": null, "loss": 0.2558}
|
| 236 |
+
{"batch": 236, "reward": null, "loss": 0.0}
|
| 237 |
+
{"batch": 237, "reward": null, "loss": 0.0}
|
| 238 |
+
{"batch": 238, "reward": null, "loss": 0.0}
|
| 239 |
+
{"batch": 239, "reward": null, "loss": 0.0}
|
| 240 |
+
{"batch": 240, "reward": null, "loss": 0.0001}
|
| 241 |
+
{"batch": 241, "reward": null, "loss": 0.0002}
|
| 242 |
+
{"batch": 242, "reward": null, "loss": -0.1441}
|
| 243 |
+
{"batch": 243, "reward": null, "loss": -0.1986}
|
| 244 |
+
{"batch": 244, "reward": null, "loss": 0.1212}
|
| 245 |
+
{"batch": 245, "reward": null, "loss": 0.0}
|
| 246 |
+
{"batch": 246, "reward": null, "loss": 0.0}
|
| 247 |
+
{"batch": 247, "reward": null, "loss": 0.0}
|
| 248 |
+
{"batch": 248, "reward": null, "loss": 0.0}
|
| 249 |
+
{"batch": 249, "reward": null, "loss": 0.0}
|
| 250 |
+
{"batch": 250, "reward": null, "loss": 0.0}
|
| 251 |
+
{"batch": 251, "reward": null, "loss": 0.0001}
|
| 252 |
+
{"batch": 252, "reward": null, "loss": 0.0001}
|
| 253 |
+
{"batch": 253, "reward": null, "loss": 0.0}
|
| 254 |
+
{"batch": 254, "reward": null, "loss": 0.0071}
|
| 255 |
+
{"batch": 255, "reward": null, "loss": 0.0001}
|
| 256 |
+
{"batch": 256, "reward": null, "loss": 0.0}
|
| 257 |
+
{"batch": 257, "reward": null, "loss": 0.0}
|
| 258 |
+
{"batch": 258, "reward": null, "loss": 0.0}
|
| 259 |
+
{"batch": 259, "reward": null, "loss": 0.0002}
|
| 260 |
+
{"batch": 260, "reward": null, "loss": 0.0}
|
| 261 |
+
{"batch": 261, "reward": null, "loss": 0.0}
|
| 262 |
+
{"batch": 262, "reward": null, "loss": 0.0002}
|
| 263 |
+
{"batch": 263, "reward": null, "loss": 0.0}
|
| 264 |
+
{"batch": 264, "reward": null, "loss": -0.3006}
|
| 265 |
+
{"batch": 265, "reward": null, "loss": 0.0004}
|
| 266 |
+
{"batch": 266, "reward": null, "loss": 0.0}
|
| 267 |
+
{"batch": 267, "reward": null, "loss": 0.0}
|
| 268 |
+
{"batch": 268, "reward": null, "loss": 0.0}
|
| 269 |
+
{"batch": 269, "reward": null, "loss": 0.0}
|
| 270 |
+
{"batch": 270, "reward": null, "loss": 0.0}
|
| 271 |
+
{"batch": 271, "reward": null, "loss": 0.0}
|
| 272 |
+
{"batch": 272, "reward": null, "loss": 0.0}
|
| 273 |
+
{"batch": 273, "reward": null, "loss": 0.0}
|
| 274 |
+
{"batch": 274, "reward": null, "loss": 0.0}
|
| 275 |
+
{"batch": 275, "reward": null, "loss": 0.0002}
|
| 276 |
+
{"batch": 276, "reward": null, "loss": 0.0001}
|
| 277 |
+
{"batch": 277, "reward": null, "loss": -0.3842}
|
| 278 |
+
{"batch": 278, "reward": null, "loss": 0.0}
|
| 279 |
+
{"batch": 279, "reward": null, "loss": 0.0}
|
| 280 |
+
{"batch": 280, "reward": null, "loss": 0.0}
|
| 281 |
+
{"batch": 281, "reward": null, "loss": 0.0}
|
| 282 |
+
{"batch": 282, "reward": null, "loss": 0.0}
|
| 283 |
+
{"batch": 283, "reward": null, "loss": 0.0001}
|
| 284 |
+
{"batch": 284, "reward": null, "loss": 0.0}
|
| 285 |
+
{"batch": 285, "reward": null, "loss": 0.0001}
|
| 286 |
+
{"batch": 286, "reward": null, "loss": 0.0}
|
| 287 |
+
{"batch": 287, "reward": null, "loss": 0.0}
|
| 288 |
+
{"batch": 288, "reward": null, "loss": -0.1238}
|
| 289 |
+
{"batch": 289, "reward": null, "loss": 0.0}
|
| 290 |
+
{"batch": 290, "reward": null, "loss": 0.0002}
|
| 291 |
+
{"batch": 291, "reward": null, "loss": 0.0003}
|
| 292 |
+
{"batch": 292, "reward": null, "loss": 0.1719}
|
| 293 |
+
{"batch": 293, "reward": null, "loss": 0.0}
|
| 294 |
+
{"batch": 294, "reward": null, "loss": 0.0}
|
| 295 |
+
{"batch": 295, "reward": null, "loss": 0.0}
|
| 296 |
+
{"batch": 296, "reward": null, "loss": 0.0}
|
| 297 |
+
{"batch": 297, "reward": null, "loss": 0.0}
|
| 298 |
+
{"batch": 298, "reward": null, "loss": 0.0004}
|
| 299 |
+
{"batch": 299, "reward": null, "loss": 0.0}
|
| 300 |
+
{"batch": 300, "reward": null, "loss": 0.0}
|
| 301 |
+
{"batch": 301, "reward": null, "loss": 0.0002}
|
| 302 |
+
{"batch": 302, "reward": null, "loss": 0.0}
|
| 303 |
+
{"batch": 303, "reward": null, "loss": 0.0002}
|
| 304 |
+
{"batch": 304, "reward": null, "loss": 0.0}
|
| 305 |
+
{"batch": 305, "reward": null, "loss": 0.0}
|
| 306 |
+
{"batch": 306, "reward": null, "loss": 0.0}
|
| 307 |
+
{"batch": 307, "reward": null, "loss": 0.0}
|
| 308 |
+
{"batch": 308, "reward": null, "loss": 0.0}
|
| 309 |
+
{"batch": 309, "reward": null, "loss": 0.0}
|
| 310 |
+
{"batch": 310, "reward": null, "loss": 0.0003}
|
| 311 |
+
{"batch": 311, "reward": null, "loss": 0.0}
|
| 312 |
+
{"batch": 312, "reward": null, "loss": 0.0003}
|
| 313 |
+
{"batch": 313, "reward": null, "loss": 0.0}
|
| 314 |
+
{"batch": 314, "reward": null, "loss": 0.0}
|
| 315 |
+
{"batch": 315, "reward": null, "loss": 0.0001}
|
| 316 |
+
{"batch": 316, "reward": null, "loss": 0.0}
|
| 317 |
+
{"batch": 317, "reward": null, "loss": -0.3798}
|
| 318 |
+
{"batch": 318, "reward": null, "loss": 0.0001}
|
| 319 |
+
{"batch": 319, "reward": null, "loss": 0.0}
|
| 320 |
+
{"batch": 320, "reward": null, "loss": 0.0}
|
| 321 |
+
{"batch": 321, "reward": null, "loss": 0.0}
|
| 322 |
+
{"batch": 322, "reward": null, "loss": 0.0}
|
| 323 |
+
{"batch": 323, "reward": null, "loss": 0.0002}
|
| 324 |
+
{"batch": 324, "reward": null, "loss": -0.4639}
|
| 325 |
+
{"batch": 325, "reward": null, "loss": 0.0}
|
| 326 |
+
{"batch": 326, "reward": null, "loss": 0.0007}
|
| 327 |
+
{"batch": 327, "reward": null, "loss": 0.0003}
|
| 328 |
+
{"batch": 328, "reward": null, "loss": 0.0}
|
| 329 |
+
{"batch": 329, "reward": null, "loss": 0.0}
|
| 330 |
+
{"batch": 330, "reward": null, "loss": 1.8149}
|
| 331 |
+
{"batch": 331, "reward": null, "loss": 0.0}
|
| 332 |
+
{"batch": 332, "reward": null, "loss": 0.0}
|
| 333 |
+
{"batch": 333, "reward": null, "loss": -0.3356}
|
| 334 |
+
{"batch": 334, "reward": null, "loss": 0.0}
|
| 335 |
+
{"batch": 335, "reward": null, "loss": 0.0}
|
| 336 |
+
{"batch": 336, "reward": null, "loss": 0.3428}
|
| 337 |
+
{"batch": 337, "reward": null, "loss": 0.0}
|
| 338 |
+
{"batch": 338, "reward": null, "loss": 0.0}
|
| 339 |
+
{"batch": 339, "reward": null, "loss": -0.3915}
|
| 340 |
+
{"batch": 340, "reward": null, "loss": 0.7089}
|
| 341 |
+
{"batch": 341, "reward": null, "loss": 0.0002}
|
| 342 |
+
{"batch": 342, "reward": null, "loss": 0.0}
|
| 343 |
+
{"batch": 343, "reward": null, "loss": -0.1102}
|
| 344 |
+
{"batch": 344, "reward": null, "loss": 0.0006}
|
| 345 |
+
{"batch": 345, "reward": null, "loss": 0.0}
|
| 346 |
+
{"batch": 346, "reward": null, "loss": 0.0001}
|
| 347 |
+
{"batch": 347, "reward": null, "loss": -0.1697}
|
| 348 |
+
{"batch": 348, "reward": null, "loss": 0.0}
|
| 349 |
+
{"batch": 349, "reward": null, "loss": -0.1854}
|
| 350 |
+
{"batch": 350, "reward": null, "loss": 0.0}
|
| 351 |
+
{"batch": 351, "reward": null, "loss": 0.0001}
|
| 352 |
+
{"batch": 352, "reward": null, "loss": 0.0}
|
| 353 |
+
{"batch": 353, "reward": null, "loss": -0.2091}
|
| 354 |
+
{"batch": 354, "reward": null, "loss": 0.0002}
|
| 355 |
+
{"batch": 355, "reward": null, "loss": 0.0005}
|
| 356 |
+
{"batch": 356, "reward": null, "loss": -0.1955}
|
| 357 |
+
{"batch": 357, "reward": null, "loss": 0.0005}
|
| 358 |
+
{"batch": 358, "reward": null, "loss": 0.0006}
|
| 359 |
+
{"batch": 359, "reward": null, "loss": -0.3331}
|
| 360 |
+
{"batch": 360, "reward": null, "loss": 0.0003}
|
| 361 |
+
{"batch": 361, "reward": null, "loss": -0.0331}
|
| 362 |
+
{"batch": 362, "reward": null, "loss": -0.1548}
|
| 363 |
+
{"batch": 363, "reward": null, "loss": 0.0905}
|
| 364 |
+
{"batch": 364, "reward": null, "loss": 0.022}
|
| 365 |
+
{"batch": 365, "reward": null, "loss": 0.0006}
|
| 366 |
+
{"batch": 366, "reward": null, "loss": 0.0006}
|
| 367 |
+
{"batch": 367, "reward": null, "loss": 0.0005}
|
| 368 |
+
{"batch": 368, "reward": null, "loss": 0.0002}
|
| 369 |
+
{"batch": 369, "reward": null, "loss": 0.0006}
|
| 370 |
+
{"batch": 370, "reward": null, "loss": -0.1233}
|
| 371 |
+
{"batch": 371, "reward": null, "loss": 0.0444}
|
| 372 |
+
{"batch": 372, "reward": null, "loss": -0.0265}
|
| 373 |
+
{"batch": 373, "reward": null, "loss": 0.0007}
|
| 374 |
+
{"batch": 374, "reward": null, "loss": 0.0021}
|
| 375 |
+
{"batch": 375, "reward": null, "loss": 0.0016}
|
| 376 |
+
{"batch": 376, "reward": null, "loss": 0.0016}
|
| 377 |
+
{"batch": 377, "reward": null, "loss": 0.0014}
|
| 378 |
+
{"batch": 378, "reward": null, "loss": 0.001}
|
| 379 |
+
{"batch": 379, "reward": null, "loss": 0.0009}
|
| 380 |
+
{"batch": 380, "reward": null, "loss": 0.0006}
|
| 381 |
+
{"batch": 381, "reward": null, "loss": -0.0813}
|
| 382 |
+
{"batch": 382, "reward": null, "loss": 0.0742}
|
| 383 |
+
{"batch": 383, "reward": null, "loss": -0.2846}
|
| 384 |
+
{"batch": 384, "reward": null, "loss": 0.0007}
|
| 385 |
+
{"batch": 385, "reward": null, "loss": 0.0014}
|
| 386 |
+
{"batch": 386, "reward": null, "loss": 0.001}
|
| 387 |
+
{"batch": 387, "reward": null, "loss": 0.1245}
|
| 388 |
+
{"batch": 388, "reward": null, "loss": -0.3089}
|
| 389 |
+
{"batch": 389, "reward": null, "loss": 0.0015}
|
| 390 |
+
{"batch": 390, "reward": null, "loss": 0.0554}
|
| 391 |
+
{"batch": 391, "reward": null, "loss": -0.3556}
|
| 392 |
+
{"batch": 392, "reward": null, "loss": -0.5092}
|
| 393 |
+
{"batch": 393, "reward": null, "loss": 0.5805}
|
| 394 |
+
{"batch": 394, "reward": null, "loss": 0.2305}
|
| 395 |
+
{"batch": 395, "reward": null, "loss": 0.0016}
|
| 396 |
+
{"batch": 396, "reward": null, "loss": -0.3271}
|
| 397 |
+
{"batch": 397, "reward": null, "loss": 0.1501}
|
| 398 |
+
{"batch": 398, "reward": null, "loss": 0.0011}
|
| 399 |
+
{"batch": 399, "reward": null, "loss": 0.1504}
|
| 400 |
+
{"batch": 400, "reward": null, "loss": -0.1074}
|
| 401 |
+
{"batch": 401, "reward": null, "loss": 0.0017}
|
| 402 |
+
{"batch": 402, "reward": null, "loss": 0.0015}
|
| 403 |
+
{"batch": 403, "reward": null, "loss": 0.0022}
|
| 404 |
+
{"batch": 404, "reward": null, "loss": -0.0654}
|
| 405 |
+
{"batch": 405, "reward": null, "loss": 0.0024}
|
| 406 |
+
{"batch": 406, "reward": null, "loss": 0.2718}
|
| 407 |
+
{"batch": 407, "reward": null, "loss": 0.003}
|
| 408 |
+
{"batch": 408, "reward": null, "loss": 0.0025}
|
| 409 |
+
{"batch": 409, "reward": null, "loss": 0.3295}
|
| 410 |
+
{"batch": 410, "reward": null, "loss": 0.0017}
|
| 411 |
+
{"batch": 411, "reward": null, "loss": 0.0017}
|
| 412 |
+
{"batch": 412, "reward": null, "loss": 0.0023}
|
| 413 |
+
{"batch": 413, "reward": null, "loss": 0.0012}
|
| 414 |
+
{"batch": 414, "reward": null, "loss": 0.1744}
|
| 415 |
+
{"batch": 415, "reward": null, "loss": 0.0024}
|
| 416 |
+
{"batch": 416, "reward": null, "loss": 0.0014}
|
| 417 |
+
{"batch": 417, "reward": null, "loss": 0.0009}
|
| 418 |
+
{"batch": 418, "reward": null, "loss": 0.0019}
|
| 419 |
+
{"batch": 419, "reward": null, "loss": 0.0563}
|
| 420 |
+
{"batch": 420, "reward": null, "loss": 0.002}
|
| 421 |
+
{"batch": 421, "reward": null, "loss": 0.0017}
|
| 422 |
+
{"batch": 422, "reward": null, "loss": -0.0397}
|
| 423 |
+
{"batch": 423, "reward": null, "loss": 0.0031}
|
| 424 |
+
{"batch": 424, "reward": null, "loss": 0.002}
|
| 425 |
+
{"batch": 425, "reward": null, "loss": 0.0019}
|
| 426 |
+
{"batch": 426, "reward": null, "loss": 0.0164}
|
| 427 |
+
{"batch": 427, "reward": null, "loss": 0.4875}
|
| 428 |
+
{"batch": 428, "reward": null, "loss": 0.0015}
|
| 429 |
+
{"batch": 429, "reward": null, "loss": 0.0379}
|
| 430 |
+
{"batch": 430, "reward": null, "loss": 0.0026}
|
| 431 |
+
{"batch": 431, "reward": null, "loss": 0.0021}
|
| 432 |
+
{"batch": 432, "reward": null, "loss": 0.0021}
|
| 433 |
+
{"batch": 433, "reward": null, "loss": -0.0616}
|
| 434 |
+
{"batch": 434, "reward": null, "loss": 0.0023}
|
| 435 |
+
{"batch": 435, "reward": null, "loss": 0.0023}
|
| 436 |
+
{"batch": 436, "reward": null, "loss": 0.0028}
|
| 437 |
+
{"batch": 437, "reward": null, "loss": 0.0024}
|
| 438 |
+
{"batch": 438, "reward": null, "loss": 0.0016}
|
| 439 |
+
{"batch": 439, "reward": null, "loss": -0.2101}
|
| 440 |
+
{"batch": 440, "reward": null, "loss": 0.0039}
|
| 441 |
+
{"batch": 441, "reward": null, "loss": 0.0022}
|
| 442 |
+
{"batch": 442, "reward": null, "loss": 0.0016}
|
| 443 |
+
{"batch": 443, "reward": null, "loss": -0.2245}
|
| 444 |
+
{"batch": 444, "reward": null, "loss": 0.0018}
|
| 445 |
+
{"batch": 445, "reward": null, "loss": 0.0016}
|
| 446 |
+
{"batch": 446, "reward": null, "loss": -0.2169}
|
| 447 |
+
{"batch": 447, "reward": null, "loss": 0.3038}
|
| 448 |
+
{"batch": 448, "reward": null, "loss": 0.0022}
|
| 449 |
+
{"batch": 449, "reward": null, "loss": -0.0997}
|
| 450 |
+
{"batch": 450, "reward": null, "loss": 0.0018}
|
| 451 |
+
{"batch": 451, "reward": null, "loss": 0.0015}
|
| 452 |
+
{"batch": 452, "reward": null, "loss": 0.0009}
|
| 453 |
+
{"batch": 453, "reward": null, "loss": 0.0039}
|
| 454 |
+
{"batch": 454, "reward": null, "loss": 0.0015}
|
| 455 |
+
{"batch": 455, "reward": null, "loss": 0.0012}
|
| 456 |
+
{"batch": 456, "reward": null, "loss": 0.0019}
|
| 457 |
+
{"batch": 457, "reward": null, "loss": 0.0018}
|
| 458 |
+
{"batch": 458, "reward": null, "loss": 0.0026}
|
| 459 |
+
{"batch": 459, "reward": null, "loss": 0.0009}
|
| 460 |
+
{"batch": 460, "reward": null, "loss": 0.0024}
|
| 461 |
+
{"batch": 461, "reward": null, "loss": 0.0015}
|
| 462 |
+
{"batch": 462, "reward": null, "loss": 0.0018}
|
| 463 |
+
{"batch": 463, "reward": null, "loss": 0.0019}
|
| 464 |
+
{"batch": 464, "reward": null, "loss": -0.2974}
|
| 465 |
+
{"batch": 465, "reward": null, "loss": 0.0019}
|
| 466 |
+
{"batch": 466, "reward": null, "loss": 0.0766}
|
| 467 |
+
{"batch": 467, "reward": null, "loss": 0.0015}
|
| 468 |
+
{"batch": 468, "reward": null, "loss": 0.0014}
|
| 469 |
+
{"batch": 469, "reward": null, "loss": -0.1842}
|
| 470 |
+
{"batch": 470, "reward": null, "loss": 0.1515}
|
| 471 |
+
{"batch": 471, "reward": null, "loss": -0.2248}
|
| 472 |
+
{"batch": 472, "reward": null, "loss": 0.3911}
|
| 473 |
+
{"batch": 473, "reward": null, "loss": 0.1886}
|
| 474 |
+
{"batch": 474, "reward": null, "loss": -0.5793}
|
| 475 |
+
{"batch": 475, "reward": null, "loss": 0.0963}
|
| 476 |
+
{"batch": 476, "reward": null, "loss": 0.0012}
|
| 477 |
+
{"batch": 477, "reward": null, "loss": -0.0636}
|
| 478 |
+
{"batch": 478, "reward": null, "loss": 0.1246}
|
| 479 |
+
{"batch": 479, "reward": null, "loss": 0.0012}
|
| 480 |
+
{"batch": 480, "reward": null, "loss": 0.187}
|
| 481 |
+
{"batch": 481, "reward": null, "loss": 0.0016}
|
| 482 |
+
{"batch": 482, "reward": null, "loss": -0.1915}
|
| 483 |
+
{"batch": 483, "reward": null, "loss": 0.2539}
|
| 484 |
+
{"batch": 484, "reward": null, "loss": 0.855}
|
| 485 |
+
{"batch": 485, "reward": null, "loss": 0.2355}
|
| 486 |
+
{"batch": 486, "reward": null, "loss": 0.0019}
|
| 487 |
+
{"batch": 487, "reward": null, "loss": 0.2691}
|
| 488 |
+
{"batch": 488, "reward": null, "loss": 0.0024}
|
| 489 |
+
{"batch": 489, "reward": null, "loss": 0.0014}
|
| 490 |
+
{"batch": 490, "reward": null, "loss": 0.1395}
|
| 491 |
+
{"batch": 491, "reward": null, "loss": -0.0525}
|
| 492 |
+
{"batch": 492, "reward": null, "loss": 0.0011}
|
| 493 |
+
{"batch": 493, "reward": null, "loss": -0.0113}
|
| 494 |
+
{"batch": 494, "reward": null, "loss": -0.1069}
|
| 495 |
+
{"batch": 495, "reward": null, "loss": -0.0011}
|
| 496 |
+
{"batch": 496, "reward": null, "loss": -0.2093}
|
| 497 |
+
{"batch": 497, "reward": null, "loss": 0.0042}
|
| 498 |
+
{"batch": 498, "reward": null, "loss": -0.0375}
|
| 499 |
+
{"batch": 499, "reward": null, "loss": 0.001}
|
| 500 |
+
{"batch": 500, "reward": null, "loss": 0.0014}
|
| 501 |
+
{"batch": 501, "reward": null, "loss": 0.0921}
|
| 502 |
+
{"batch": 502, "reward": null, "loss": 0.0008}
|
| 503 |
+
{"batch": 503, "reward": null, "loss": 0.0016}
|
| 504 |
+
{"batch": 504, "reward": null, "loss": 0.0013}
|
| 505 |
+
{"batch": 505, "reward": null, "loss": 0.0008}
|
| 506 |
+
{"batch": 506, "reward": null, "loss": 0.0013}
|
| 507 |
+
{"batch": 507, "reward": null, "loss": 0.0024}
|
| 508 |
+
{"batch": 508, "reward": null, "loss": 0.0005}
|
| 509 |
+
{"batch": 509, "reward": null, "loss": -0.564}
|
| 510 |
+
{"batch": 510, "reward": null, "loss": 0.0014}
|
| 511 |
+
{"batch": 511, "reward": null, "loss": 0.0015}
|
| 512 |
+
{"batch": 512, "reward": null, "loss": 0.001}
|
| 513 |
+
{"batch": 513, "reward": null, "loss": -0.0212}
|
| 514 |
+
{"batch": 514, "reward": null, "loss": 0.0011}
|
| 515 |
+
{"batch": 515, "reward": null, "loss": 0.0022}
|
| 516 |
+
{"batch": 516, "reward": null, "loss": 0.0011}
|
| 517 |
+
{"batch": 517, "reward": null, "loss": 0.0013}
|
| 518 |
+
{"batch": 518, "reward": null, "loss": 0.1415}
|
| 519 |
+
{"batch": 519, "reward": null, "loss": 0.0006}
|
| 520 |
+
{"batch": 520, "reward": null, "loss": 0.4645}
|
| 521 |
+
{"batch": 521, "reward": null, "loss": 0.1457}
|
| 522 |
+
{"batch": 522, "reward": null, "loss": -0.0021}
|
| 523 |
+
{"batch": 523, "reward": null, "loss": -0.1741}
|
| 524 |
+
{"batch": 524, "reward": null, "loss": 0.0012}
|
| 525 |
+
{"batch": 525, "reward": null, "loss": 0.0004}
|
| 526 |
+
{"batch": 526, "reward": null, "loss": 0.0007}
|
| 527 |
+
{"batch": 527, "reward": null, "loss": 0.0012}
|
| 528 |
+
{"batch": 528, "reward": null, "loss": 0.0}
|
| 529 |
+
{"batch": 529, "reward": null, "loss": 0.0008}
|
| 530 |
+
{"batch": 530, "reward": null, "loss": 0.0013}
|
| 531 |
+
{"batch": 531, "reward": null, "loss": 0.0008}
|
| 532 |
+
{"batch": 532, "reward": null, "loss": 0.001}
|
| 533 |
+
{"batch": 533, "reward": null, "loss": 0.1198}
|
| 534 |
+
{"batch": 534, "reward": null, "loss": 0.0017}
|
| 535 |
+
{"batch": 535, "reward": null, "loss": 0.0012}
|
| 536 |
+
{"batch": 536, "reward": null, "loss": 0.0014}
|
| 537 |
+
{"batch": 537, "reward": null, "loss": 0.0551}
|
| 538 |
+
{"batch": 538, "reward": null, "loss": 0.0012}
|
| 539 |
+
{"batch": 539, "reward": null, "loss": 0.0438}
|
| 540 |
+
{"batch": 540, "reward": null, "loss": 0.0011}
|
| 541 |
+
{"batch": 541, "reward": null, "loss": 0.0006}
|
| 542 |
+
{"batch": 542, "reward": null, "loss": 0.0006}
|
| 543 |
+
{"batch": 543, "reward": null, "loss": 0.0009}
|
| 544 |
+
{"batch": 544, "reward": null, "loss": -0.1417}
|
| 545 |
+
{"batch": 545, "reward": null, "loss": 0.0013}
|
| 546 |
+
{"batch": 546, "reward": null, "loss": 0.0663}
|
| 547 |
+
{"batch": 547, "reward": null, "loss": 0.0016}
|
| 548 |
+
{"batch": 548, "reward": null, "loss": 0.0015}
|
| 549 |
+
{"batch": 549, "reward": null, "loss": -0.0807}
|
| 550 |
+
{"batch": 550, "reward": null, "loss": 0.0011}
|
| 551 |
+
{"batch": 551, "reward": null, "loss": 0.001}
|
| 552 |
+
{"batch": 552, "reward": null, "loss": 0.001}
|
| 553 |
+
{"batch": 553, "reward": null, "loss": 0.0009}
|
| 554 |
+
{"batch": 554, "reward": null, "loss": 0.001}
|
| 555 |
+
{"batch": 555, "reward": null, "loss": 0.0008}
|
| 556 |
+
{"batch": 556, "reward": null, "loss": 0.0017}
|
| 557 |
+
{"batch": 557, "reward": null, "loss": 0.2058}
|
| 558 |
+
{"batch": 558, "reward": null, "loss": -0.4254}
|
| 559 |
+
{"batch": 559, "reward": null, "loss": 0.1967}
|
| 560 |
+
{"batch": 560, "reward": null, "loss": -0.5081}
|
| 561 |
+
{"batch": 561, "reward": null, "loss": 0.001}
|
| 562 |
+
{"batch": 562, "reward": null, "loss": 0.0004}
|
| 563 |
+
{"batch": 563, "reward": null, "loss": 0.0763}
|
| 564 |
+
{"batch": 564, "reward": null, "loss": 0.0015}
|
| 565 |
+
{"batch": 565, "reward": null, "loss": 0.0004}
|
| 566 |
+
{"batch": 566, "reward": null, "loss": 0.0006}
|
| 567 |
+
{"batch": 567, "reward": null, "loss": 0.1802}
|
| 568 |
+
{"batch": 568, "reward": null, "loss": 0.0004}
|
| 569 |
+
{"batch": 569, "reward": null, "loss": 0.0004}
|
| 570 |
+
{"batch": 570, "reward": null, "loss": -0.1773}
|
| 571 |
+
{"batch": 571, "reward": null, "loss": -0.207}
|
| 572 |
+
{"batch": 572, "reward": null, "loss": 0.2138}
|
| 573 |
+
{"batch": 573, "reward": null, "loss": 0.0005}
|
| 574 |
+
{"batch": 574, "reward": null, "loss": 0.0003}
|
| 575 |
+
{"batch": 575, "reward": null, "loss": -0.0032}
|
| 576 |
+
{"batch": 576, "reward": null, "loss": 0.0005}
|
| 577 |
+
{"batch": 577, "reward": null, "loss": 0.022}
|
| 578 |
+
{"batch": 578, "reward": null, "loss": 0.175}
|
| 579 |
+
{"batch": 579, "reward": null, "loss": 0.0015}
|
| 580 |
+
{"batch": 580, "reward": null, "loss": 0.0}
|
| 581 |
+
{"batch": 581, "reward": null, "loss": 0.0}
|
| 582 |
+
{"batch": 582, "reward": null, "loss": -0.1531}
|
| 583 |
+
{"batch": 583, "reward": null, "loss": 0.0007}
|
| 584 |
+
{"batch": 584, "reward": null, "loss": 0.1648}
|
| 585 |
+
{"batch": 585, "reward": null, "loss": 0.0001}
|
| 586 |
+
{"batch": 586, "reward": null, "loss": 0.0002}
|
| 587 |
+
{"batch": 587, "reward": null, "loss": 0.0561}
|
| 588 |
+
{"batch": 588, "reward": null, "loss": 0.0006}
|
| 589 |
+
{"batch": 589, "reward": null, "loss": 0.0004}
|
| 590 |
+
{"batch": 590, "reward": null, "loss": 0.0002}
|
| 591 |
+
{"batch": 591, "reward": null, "loss": 0.0002}
|
| 592 |
+
{"batch": 592, "reward": null, "loss": 0.0}
|
| 593 |
+
{"batch": 593, "reward": null, "loss": 0.0072}
|
| 594 |
+
{"batch": 594, "reward": null, "loss": 0.0009}
|
| 595 |
+
{"batch": 595, "reward": null, "loss": 0.0001}
|
| 596 |
+
{"batch": 596, "reward": null, "loss": 0.0001}
|
| 597 |
+
{"batch": 597, "reward": null, "loss": -0.0272}
|
| 598 |
+
{"batch": 598, "reward": null, "loss": 0.0}
|
| 599 |
+
{"batch": 599, "reward": null, "loss": 0.0203}
|
| 600 |
+
{"batch": 600, "reward": null, "loss": 0.0011}
|
| 601 |
+
{"batch": 601, "reward": null, "loss": 0.0009}
|
| 602 |
+
{"batch": 602, "reward": null, "loss": -0.1922}
|
| 603 |
+
{"batch": 603, "reward": null, "loss": 0.0}
|
| 604 |
+
{"batch": 604, "reward": null, "loss": 0.0004}
|
| 605 |
+
{"batch": 605, "reward": null, "loss": 0.0}
|
| 606 |
+
{"batch": 606, "reward": null, "loss": 0.0}
|
| 607 |
+
{"batch": 607, "reward": null, "loss": 0.0003}
|
| 608 |
+
{"batch": 608, "reward": null, "loss": 0.0003}
|
| 609 |
+
{"batch": 609, "reward": null, "loss": 0.0002}
|
| 610 |
+
{"batch": 610, "reward": null, "loss": 0.001}
|
| 611 |
+
{"batch": 611, "reward": null, "loss": -0.2336}
|
| 612 |
+
{"batch": 612, "reward": null, "loss": 0.0004}
|
| 613 |
+
{"batch": 613, "reward": null, "loss": 0.0004}
|
| 614 |
+
{"batch": 614, "reward": null, "loss": 0.001}
|
| 615 |
+
{"batch": 615, "reward": null, "loss": 0.0001}
|
| 616 |
+
{"batch": 616, "reward": null, "loss": -0.3014}
|
| 617 |
+
{"batch": 617, "reward": null, "loss": -0.1901}
|
| 618 |
+
{"batch": 618, "reward": null, "loss": 0.0}
|
| 619 |
+
{"batch": 619, "reward": null, "loss": 0.0001}
|
| 620 |
+
{"batch": 620, "reward": null, "loss": -0.1035}
|
| 621 |
+
{"batch": 621, "reward": null, "loss": 0.0009}
|
| 622 |
+
{"batch": 622, "reward": null, "loss": 0.0004}
|
| 623 |
+
{"batch": 623, "reward": null, "loss": 0.0}
|
| 624 |
+
{"batch": 624, "reward": null, "loss": 0.5883}
|
| 625 |
+
{"batch": 625, "reward": null, "loss": 0.0006}
|
| 626 |
+
{"batch": 626, "reward": null, "loss": 0.0005}
|
| 627 |
+
{"batch": 627, "reward": null, "loss": 0.0003}
|
| 628 |
+
{"batch": 628, "reward": null, "loss": -0.1259}
|
| 629 |
+
{"batch": 629, "reward": null, "loss": 0.0004}
|
| 630 |
+
{"batch": 630, "reward": null, "loss": -0.1976}
|
| 631 |
+
{"batch": 631, "reward": null, "loss": 0.0}
|
| 632 |
+
{"batch": 632, "reward": null, "loss": 0.0001}
|
| 633 |
+
{"batch": 633, "reward": null, "loss": 0.0007}
|
| 634 |
+
{"batch": 634, "reward": null, "loss": 0.0003}
|
| 635 |
+
{"batch": 635, "reward": null, "loss": -0.0439}
|
| 636 |
+
{"batch": 636, "reward": null, "loss": 0.0003}
|
| 637 |
+
{"batch": 637, "reward": null, "loss": 0.0008}
|
| 638 |
+
{"batch": 638, "reward": null, "loss": 0.0009}
|
| 639 |
+
{"batch": 639, "reward": null, "loss": 0.0}
|
| 640 |
+
{"batch": 640, "reward": null, "loss": 0.0006}
|
| 641 |
+
{"batch": 641, "reward": null, "loss": 0.0001}
|
| 642 |
+
{"batch": 642, "reward": null, "loss": 0.0001}
|
| 643 |
+
{"batch": 643, "reward": null, "loss": 0.0012}
|
| 644 |
+
{"batch": 644, "reward": null, "loss": 0.0004}
|
| 645 |
+
{"batch": 645, "reward": null, "loss": 0.0002}
|
| 646 |
+
{"batch": 646, "reward": null, "loss": 0.0011}
|
| 647 |
+
{"batch": 647, "reward": null, "loss": 0.0002}
|
| 648 |
+
{"batch": 648, "reward": null, "loss": 0.0006}
|
| 649 |
+
{"batch": 649, "reward": null, "loss": 0.0001}
|
| 650 |
+
{"batch": 650, "reward": null, "loss": -0.2404}
|
| 651 |
+
{"batch": 651, "reward": null, "loss": 0.0011}
|
| 652 |
+
{"batch": 652, "reward": null, "loss": 0.0}
|
| 653 |
+
{"batch": 653, "reward": null, "loss": 0.0003}
|
| 654 |
+
{"batch": 654, "reward": null, "loss": 0.0}
|
| 655 |
+
{"batch": 655, "reward": null, "loss": 0.0002}
|
| 656 |
+
{"batch": 656, "reward": null, "loss": 0.0}
|
| 657 |
+
{"batch": 657, "reward": null, "loss": 0.0}
|
| 658 |
+
{"batch": 658, "reward": null, "loss": 0.0003}
|
| 659 |
+
{"batch": 659, "reward": null, "loss": 0.0002}
|
| 660 |
+
{"batch": 660, "reward": null, "loss": 0.0003}
|
| 661 |
+
{"batch": 661, "reward": null, "loss": 0.0001}
|
| 662 |
+
{"batch": 662, "reward": null, "loss": 0.0003}
|
| 663 |
+
{"batch": 663, "reward": null, "loss": 0.0}
|
| 664 |
+
{"batch": 664, "reward": null, "loss": 0.0001}
|
| 665 |
+
{"batch": 665, "reward": null, "loss": 0.0001}
|
| 666 |
+
{"batch": 666, "reward": null, "loss": 0.1231}
|
| 667 |
+
{"batch": 667, "reward": null, "loss": 0.0}
|
| 668 |
+
{"batch": 668, "reward": null, "loss": 0.305}
|
| 669 |
+
{"batch": 669, "reward": null, "loss": 0.0007}
|
| 670 |
+
{"batch": 670, "reward": null, "loss": 0.0002}
|
| 671 |
+
{"batch": 671, "reward": null, "loss": 0.0001}
|
| 672 |
+
{"batch": 672, "reward": null, "loss": 0.0}
|
| 673 |
+
{"batch": 673, "reward": null, "loss": 0.049}
|
| 674 |
+
{"batch": 674, "reward": null, "loss": 0.0004}
|
| 675 |
+
{"batch": 675, "reward": null, "loss": 0.0}
|
| 676 |
+
{"batch": 676, "reward": null, "loss": 0.0}
|
| 677 |
+
{"batch": 677, "reward": null, "loss": 0.0007}
|
| 678 |
+
{"batch": 678, "reward": null, "loss": 0.0001}
|
| 679 |
+
{"batch": 679, "reward": null, "loss": 0.0006}
|
| 680 |
+
{"batch": 680, "reward": null, "loss": 0.0}
|
| 681 |
+
{"batch": 681, "reward": null, "loss": -0.4554}
|
| 682 |
+
{"batch": 682, "reward": null, "loss": 0.0}
|
| 683 |
+
{"batch": 683, "reward": null, "loss": -0.2173}
|
| 684 |
+
{"batch": 684, "reward": null, "loss": 0.0}
|
| 685 |
+
{"batch": 685, "reward": null, "loss": 0.0003}
|
| 686 |
+
{"batch": 686, "reward": null, "loss": 0.0001}
|
| 687 |
+
{"batch": 687, "reward": null, "loss": 0.0}
|
| 688 |
+
{"batch": 688, "reward": null, "loss": 0.0}
|
| 689 |
+
{"batch": 689, "reward": null, "loss": 0.0}
|
| 690 |
+
{"batch": 690, "reward": null, "loss": -0.1889}
|
| 691 |
+
{"batch": 691, "reward": null, "loss": 0.0001}
|
| 692 |
+
{"batch": 692, "reward": null, "loss": 0.0008}
|
| 693 |
+
{"batch": 693, "reward": null, "loss": 0.103}
|
| 694 |
+
{"batch": 694, "reward": null, "loss": 0.0}
|
| 695 |
+
{"batch": 695, "reward": null, "loss": 0.0}
|
| 696 |
+
{"batch": 696, "reward": null, "loss": 0.0009}
|
| 697 |
+
{"batch": 697, "reward": null, "loss": 0.5903}
|
| 698 |
+
{"batch": 698, "reward": null, "loss": 0.0002}
|
| 699 |
+
{"batch": 699, "reward": null, "loss": 0.0007}
|
| 700 |
+
{"batch": 700, "reward": null, "loss": 0.0001}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,217 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"<|im_start|>",
|
| 10 |
"<|im_end|>",
|
| 11 |
"<|object_ref_start|>",
|
|
@@ -20,8 +226,11 @@
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
| 23 |
-
"
|
| 24 |
-
"
|
|
|
|
|
|
|
|
|
|
| 25 |
"model_max_length": 131072,
|
| 26 |
"pad_token": "<|endoftext|>",
|
| 27 |
"split_special_tokens": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
"<|im_start|>",
|
| 216 |
"<|im_end|>",
|
| 217 |
"<|object_ref_start|>",
|
|
|
|
| 226 |
"<|image_pad|>",
|
| 227 |
"<|video_pad|>"
|
| 228 |
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 131072,
|
| 235 |
"pad_token": "<|endoftext|>",
|
| 236 |
"split_special_tokens": false,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b346bee98cdce11d13871c68c2cac5fc786cbd0bcbfcad7aaf525b08f9f5300
|
| 3 |
+
size 7889
|
trajectory.jsonl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad6f86a962be05be4ba06217b25af91333559146847c758dda772d7cbc64e914
|
| 3 |
+
size 1180578
|