Upload add_sub_sorl_v1_abs50_K1_50K
Browse files
add_sub_sorl_v1_abs50_K1_50K/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SorlModelWrapper"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 510,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2040,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention"
|
| 18 |
+
],
|
| 19 |
+
"max_position_embeddings": 128,
|
| 20 |
+
"max_window_layers": 28,
|
| 21 |
+
"model_type": "qwen3",
|
| 22 |
+
"num_attention_heads": 3,
|
| 23 |
+
"num_hidden_layers": 2,
|
| 24 |
+
"num_key_value_heads": 3,
|
| 25 |
+
"pad_token_id": null,
|
| 26 |
+
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_parameters": {
|
| 28 |
+
"rope_theta": 10000.0,
|
| 29 |
+
"rope_type": "default"
|
| 30 |
+
},
|
| 31 |
+
"sliding_window": null,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"transformers_version": "5.5.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"vocab_size": 151694
|
| 37 |
+
}
|
add_sub_sorl_v1_abs50_K1_50K/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.5.0",
|
| 6 |
+
"use_cache": true
|
| 7 |
+
}
|
add_sub_sorl_v1_abs50_K1_50K/metrics.json
ADDED
|
@@ -0,0 +1,2257 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"history": {
|
| 3 |
+
"step": [
|
| 4 |
+
50,
|
| 5 |
+
100,
|
| 6 |
+
150,
|
| 7 |
+
200,
|
| 8 |
+
250,
|
| 9 |
+
300,
|
| 10 |
+
350,
|
| 11 |
+
400,
|
| 12 |
+
450,
|
| 13 |
+
500,
|
| 14 |
+
550,
|
| 15 |
+
600,
|
| 16 |
+
650,
|
| 17 |
+
700,
|
| 18 |
+
750,
|
| 19 |
+
832,
|
| 20 |
+
882,
|
| 21 |
+
932,
|
| 22 |
+
982,
|
| 23 |
+
1032,
|
| 24 |
+
1082,
|
| 25 |
+
1132,
|
| 26 |
+
1182,
|
| 27 |
+
1232,
|
| 28 |
+
1282,
|
| 29 |
+
1332,
|
| 30 |
+
1382,
|
| 31 |
+
1432,
|
| 32 |
+
1482,
|
| 33 |
+
1532,
|
| 34 |
+
1614,
|
| 35 |
+
1664,
|
| 36 |
+
1714,
|
| 37 |
+
1764,
|
| 38 |
+
1814,
|
| 39 |
+
1864,
|
| 40 |
+
1914,
|
| 41 |
+
1964,
|
| 42 |
+
2014,
|
| 43 |
+
2064,
|
| 44 |
+
2114,
|
| 45 |
+
2164,
|
| 46 |
+
2214,
|
| 47 |
+
2264,
|
| 48 |
+
2314,
|
| 49 |
+
2396,
|
| 50 |
+
2446,
|
| 51 |
+
2496,
|
| 52 |
+
2546,
|
| 53 |
+
2596,
|
| 54 |
+
2646,
|
| 55 |
+
2696,
|
| 56 |
+
2746,
|
| 57 |
+
2796,
|
| 58 |
+
2846,
|
| 59 |
+
2896,
|
| 60 |
+
2946,
|
| 61 |
+
2996,
|
| 62 |
+
3046,
|
| 63 |
+
3096,
|
| 64 |
+
3178,
|
| 65 |
+
3228,
|
| 66 |
+
3278,
|
| 67 |
+
3328,
|
| 68 |
+
3378,
|
| 69 |
+
3428,
|
| 70 |
+
3478,
|
| 71 |
+
3528,
|
| 72 |
+
3578,
|
| 73 |
+
3628,
|
| 74 |
+
3678,
|
| 75 |
+
3728,
|
| 76 |
+
3778,
|
| 77 |
+
3828,
|
| 78 |
+
3878,
|
| 79 |
+
3960,
|
| 80 |
+
4010,
|
| 81 |
+
4060,
|
| 82 |
+
4110,
|
| 83 |
+
4160,
|
| 84 |
+
4210,
|
| 85 |
+
4260,
|
| 86 |
+
4310,
|
| 87 |
+
4360,
|
| 88 |
+
4410,
|
| 89 |
+
4460,
|
| 90 |
+
4510,
|
| 91 |
+
4560,
|
| 92 |
+
4610,
|
| 93 |
+
4660,
|
| 94 |
+
4742,
|
| 95 |
+
4792,
|
| 96 |
+
4842,
|
| 97 |
+
4892,
|
| 98 |
+
4942,
|
| 99 |
+
4992,
|
| 100 |
+
5042,
|
| 101 |
+
5092,
|
| 102 |
+
5142,
|
| 103 |
+
5192,
|
| 104 |
+
5242,
|
| 105 |
+
5292,
|
| 106 |
+
5342,
|
| 107 |
+
5392,
|
| 108 |
+
5442,
|
| 109 |
+
5524,
|
| 110 |
+
5574,
|
| 111 |
+
5624,
|
| 112 |
+
5674,
|
| 113 |
+
5724,
|
| 114 |
+
5774,
|
| 115 |
+
5824,
|
| 116 |
+
5874,
|
| 117 |
+
5924,
|
| 118 |
+
5974,
|
| 119 |
+
6024,
|
| 120 |
+
6074,
|
| 121 |
+
6124,
|
| 122 |
+
6174,
|
| 123 |
+
6224,
|
| 124 |
+
6306,
|
| 125 |
+
6356,
|
| 126 |
+
6406,
|
| 127 |
+
6456,
|
| 128 |
+
6506,
|
| 129 |
+
6556,
|
| 130 |
+
6606,
|
| 131 |
+
6656,
|
| 132 |
+
6706,
|
| 133 |
+
6756,
|
| 134 |
+
6806,
|
| 135 |
+
6856,
|
| 136 |
+
6906,
|
| 137 |
+
6956,
|
| 138 |
+
7006,
|
| 139 |
+
7088,
|
| 140 |
+
7138,
|
| 141 |
+
7188,
|
| 142 |
+
7238,
|
| 143 |
+
7288,
|
| 144 |
+
7338,
|
| 145 |
+
7388,
|
| 146 |
+
7438,
|
| 147 |
+
7488,
|
| 148 |
+
7538,
|
| 149 |
+
7588,
|
| 150 |
+
7638,
|
| 151 |
+
7688,
|
| 152 |
+
7738,
|
| 153 |
+
7788
|
| 154 |
+
],
|
| 155 |
+
"loss": [
|
| 156 |
+
-2.362311363220215,
|
| 157 |
+
4.142616271972656,
|
| 158 |
+
5.742372035980225,
|
| 159 |
+
4.385456562042236,
|
| 160 |
+
2.65998911857605,
|
| 161 |
+
2.6645395755767822,
|
| 162 |
+
2.4139466285705566,
|
| 163 |
+
2.3436119556427,
|
| 164 |
+
2.1938347816467285,
|
| 165 |
+
1.1786324977874756,
|
| 166 |
+
0.5501563549041748,
|
| 167 |
+
-2.4522831439971924,
|
| 168 |
+
-6.912477970123291,
|
| 169 |
+
-7.594290733337402,
|
| 170 |
+
-6.299901485443115,
|
| 171 |
+
-4.1144514083862305,
|
| 172 |
+
-2.9718146324157715,
|
| 173 |
+
-3.0891127586364746,
|
| 174 |
+
-3.0204803943634033,
|
| 175 |
+
-1.4713752269744873,
|
| 176 |
+
-2.009824275970459,
|
| 177 |
+
-1.9805353879928589,
|
| 178 |
+
-1.5139883756637573,
|
| 179 |
+
-1.2930357456207275,
|
| 180 |
+
-1.681591510772705,
|
| 181 |
+
-1.410130262374878,
|
| 182 |
+
-0.9018668532371521,
|
| 183 |
+
-1.495841145515442,
|
| 184 |
+
-1.1279966831207275,
|
| 185 |
+
-1.153012990951538,
|
| 186 |
+
-0.9365040063858032,
|
| 187 |
+
-1.1967496871948242,
|
| 188 |
+
-0.60008704662323,
|
| 189 |
+
-0.4546336233615875,
|
| 190 |
+
-0.2338147759437561,
|
| 191 |
+
-0.4052750766277313,
|
| 192 |
+
-0.021503061056137085,
|
| 193 |
+
-0.26955801248550415,
|
| 194 |
+
-0.672745406627655,
|
| 195 |
+
-0.23327162861824036,
|
| 196 |
+
-0.4855377972126007,
|
| 197 |
+
-0.13352718949317932,
|
| 198 |
+
-0.23082715272903442,
|
| 199 |
+
-0.1835346519947052,
|
| 200 |
+
-0.4483920931816101,
|
| 201 |
+
0.047375500202178955,
|
| 202 |
+
-0.2215544581413269,
|
| 203 |
+
-0.44033241271972656,
|
| 204 |
+
-0.5978419780731201,
|
| 205 |
+
-0.44466206431388855,
|
| 206 |
+
-0.2285054624080658,
|
| 207 |
+
-0.28812137246131897,
|
| 208 |
+
-0.35842379927635193,
|
| 209 |
+
0.01628749817609787,
|
| 210 |
+
-0.19608664512634277,
|
| 211 |
+
-0.19692540168762207,
|
| 212 |
+
-0.31407108902931213,
|
| 213 |
+
-0.3116561770439148,
|
| 214 |
+
-0.1530594825744629,
|
| 215 |
+
-0.1336585134267807,
|
| 216 |
+
-0.03226778283715248,
|
| 217 |
+
-0.12333834916353226,
|
| 218 |
+
0.0010370612144470215,
|
| 219 |
+
0.01887122169137001,
|
| 220 |
+
-0.07264796644449234,
|
| 221 |
+
-0.02627880498766899,
|
| 222 |
+
-0.295105904340744,
|
| 223 |
+
-0.12734602391719818,
|
| 224 |
+
-0.037976086139678955,
|
| 225 |
+
-0.06711544096469879,
|
| 226 |
+
0.03116016462445259,
|
| 227 |
+
-0.15805044770240784,
|
| 228 |
+
-0.055456213653087616,
|
| 229 |
+
-0.035786330699920654,
|
| 230 |
+
-0.057642608880996704,
|
| 231 |
+
-0.15556828677654266,
|
| 232 |
+
0.012920133769512177,
|
| 233 |
+
0.021311596035957336,
|
| 234 |
+
-0.12346473336219788,
|
| 235 |
+
-0.007266495376825333,
|
| 236 |
+
-0.013176698237657547,
|
| 237 |
+
-0.007413065060973167,
|
| 238 |
+
-0.03793773055076599,
|
| 239 |
+
0.037045057862997055,
|
| 240 |
+
0.018496377393603325,
|
| 241 |
+
0.012396834790706635,
|
| 242 |
+
-0.0014384295791387558,
|
| 243 |
+
-0.027611250057816505,
|
| 244 |
+
0.0006594806909561157,
|
| 245 |
+
-0.030753280967473984,
|
| 246 |
+
0.035470861941576004,
|
| 247 |
+
0.0019025392830371857,
|
| 248 |
+
0.007249578833580017,
|
| 249 |
+
0.023552823811769485,
|
| 250 |
+
-0.016448041424155235,
|
| 251 |
+
-0.11824400722980499,
|
| 252 |
+
-0.011335870251059532,
|
| 253 |
+
-0.0026189684867858887,
|
| 254 |
+
-0.07503114640712738,
|
| 255 |
+
0.007656330242753029,
|
| 256 |
+
0.0010218452662229538,
|
| 257 |
+
0.004992343485355377,
|
| 258 |
+
-0.04994726926088333,
|
| 259 |
+
0.02609233185648918,
|
| 260 |
+
0.025171207264065742,
|
| 261 |
+
0.02843359112739563,
|
| 262 |
+
0.0281149260699749,
|
| 263 |
+
-0.022132931277155876,
|
| 264 |
+
0.017087848857045174,
|
| 265 |
+
-0.03246891498565674,
|
| 266 |
+
-0.01691838912665844,
|
| 267 |
+
0.031263623386621475,
|
| 268 |
+
0.009899910539388657,
|
| 269 |
+
0.02031245455145836,
|
| 270 |
+
0.03743060305714607,
|
| 271 |
+
0.01620517484843731,
|
| 272 |
+
0.0024506673216819763,
|
| 273 |
+
-0.10918563604354858,
|
| 274 |
+
-0.03577355667948723,
|
| 275 |
+
0.013806315138936043,
|
| 276 |
+
0.005210202187299728,
|
| 277 |
+
0.0205706674605608,
|
| 278 |
+
-0.0055563002824783325,
|
| 279 |
+
0.014057239517569542,
|
| 280 |
+
0.023754511028528214,
|
| 281 |
+
0.02344704046845436,
|
| 282 |
+
-0.015303295105695724,
|
| 283 |
+
0.01502778846770525,
|
| 284 |
+
0.022722676396369934,
|
| 285 |
+
0.029621414840221405,
|
| 286 |
+
0.0191071517765522,
|
| 287 |
+
0.030115358531475067,
|
| 288 |
+
0.01589101552963257,
|
| 289 |
+
0.022458214312791824,
|
| 290 |
+
0.022770069539546967,
|
| 291 |
+
0.0058741457760334015,
|
| 292 |
+
0.03213969245553017,
|
| 293 |
+
0.026409529149532318,
|
| 294 |
+
0.028818590566515923,
|
| 295 |
+
0.017882106825709343,
|
| 296 |
+
-0.00808335468173027,
|
| 297 |
+
0.018027514219284058,
|
| 298 |
+
0.018644649535417557,
|
| 299 |
+
0.021471507847309113,
|
| 300 |
+
0.0185184758156538,
|
| 301 |
+
0.019755413755774498,
|
| 302 |
+
-0.009315568953752518,
|
| 303 |
+
0.0298157949000597,
|
| 304 |
+
0.028079446405172348,
|
| 305 |
+
0.029373809695243835
|
| 306 |
+
],
|
| 307 |
+
"base_loss": [
|
| 308 |
+
10.627317428588867,
|
| 309 |
+
7.785068988800049,
|
| 310 |
+
6.460549354553223,
|
| 311 |
+
4.235473155975342,
|
| 312 |
+
2.2067322731018066,
|
| 313 |
+
1.9645311832427979,
|
| 314 |
+
1.8720226287841797,
|
| 315 |
+
1.925799012184143,
|
| 316 |
+
1.8462870121002197,
|
| 317 |
+
1.7783663272857666,
|
| 318 |
+
1.8181790113449097,
|
| 319 |
+
1.7071102857589722,
|
| 320 |
+
1.7554022073745728,
|
| 321 |
+
1.5883513689041138,
|
| 322 |
+
1.3195432424545288,
|
| 323 |
+
0.9769352674484253,
|
| 324 |
+
0.7838889956474304,
|
| 325 |
+
0.7617303133010864,
|
| 326 |
+
0.7175022959709167,
|
| 327 |
+
0.5531765818595886,
|
| 328 |
+
0.568193793296814,
|
| 329 |
+
0.5213921666145325,
|
| 330 |
+
0.4586550295352936,
|
| 331 |
+
0.4510910212993622,
|
| 332 |
+
0.4354884922504425,
|
| 333 |
+
0.3853158950805664,
|
| 334 |
+
0.3368673026561737,
|
| 335 |
+
0.3837520182132721,
|
| 336 |
+
0.29517051577568054,
|
| 337 |
+
0.28589174151420593,
|
| 338 |
+
0.21043504774570465,
|
| 339 |
+
0.23332612216472626,
|
| 340 |
+
0.15762941539287567,
|
| 341 |
+
0.12949296832084656,
|
| 342 |
+
0.09909506142139435,
|
| 343 |
+
0.09850041568279266,
|
| 344 |
+
0.06913686543703079,
|
| 345 |
+
0.07611358165740967,
|
| 346 |
+
0.12447609007358551,
|
| 347 |
+
0.06315553188323975,
|
| 348 |
+
0.09700862318277359,
|
| 349 |
+
0.05409974977374077,
|
| 350 |
+
0.06287837773561478,
|
| 351 |
+
0.04576185718178749,
|
| 352 |
+
0.0762605145573616,
|
| 353 |
+
0.011524148285388947,
|
| 354 |
+
0.05566584691405296,
|
| 355 |
+
0.06595442444086075,
|
| 356 |
+
0.08124065399169922,
|
| 357 |
+
0.06380296498537064,
|
| 358 |
+
0.03999868407845497,
|
| 359 |
+
0.04607996344566345,
|
| 360 |
+
0.051112838089466095,
|
| 361 |
+
0.010583004914224148,
|
| 362 |
+
0.03285596892237663,
|
| 363 |
+
0.03204553201794624,
|
| 364 |
+
0.0443243645131588,
|
| 365 |
+
0.04439778998494148,
|
| 366 |
+
0.027180315926671028,
|
| 367 |
+
0.0239639300853014,
|
| 368 |
+
0.013277111575007439,
|
| 369 |
+
0.021815242245793343,
|
| 370 |
+
0.008101996965706348,
|
| 371 |
+
0.006606306415051222,
|
| 372 |
+
0.01517914142459631,
|
| 373 |
+
0.009214714169502258,
|
| 374 |
+
0.05038433521986008,
|
| 375 |
+
0.02156301960349083,
|
| 376 |
+
0.01082638930529356,
|
| 377 |
+
0.012730908580124378,
|
| 378 |
+
0.005083796102553606,
|
| 379 |
+
0.024667279794812202,
|
| 380 |
+
0.01190714817494154,
|
| 381 |
+
0.008711572736501694,
|
| 382 |
+
0.012311254628002644,
|
| 383 |
+
0.021373221650719643,
|
| 384 |
+
0.00401270529255271,
|
| 385 |
+
0.002357164165005088,
|
| 386 |
+
0.02084466442465782,
|
| 387 |
+
0.005394904408603907,
|
| 388 |
+
0.006502884905785322,
|
| 389 |
+
0.0055189430713653564,
|
| 390 |
+
0.008968108333647251,
|
| 391 |
+
0.0010382139589637518,
|
| 392 |
+
0.003825769992545247,
|
| 393 |
+
0.0022657078225165606,
|
| 394 |
+
0.0034016927238553762,
|
| 395 |
+
0.006108022294938564,
|
| 396 |
+
0.004202643875032663,
|
| 397 |
+
0.007591772358864546,
|
| 398 |
+
0.0016709069022908807,
|
| 399 |
+
0.004354614298790693,
|
| 400 |
+
0.0027823285199701786,
|
| 401 |
+
0.005420122295618057,
|
| 402 |
+
0.00497792661190033,
|
| 403 |
+
0.016467753797769547,
|
| 404 |
+
0.004529373254626989,
|
| 405 |
+
0.0037383229937404394,
|
| 406 |
+
0.011195746250450611,
|
| 407 |
+
0.0027013029903173447,
|
| 408 |
+
0.00282703316770494,
|
| 409 |
+
0.002905127825215459,
|
| 410 |
+
0.009927086532115936,
|
| 411 |
+
0.00048302210052497685,
|
| 412 |
+
0.0002695829898584634,
|
| 413 |
+
0.00021149407257325947,
|
| 414 |
+
0.0005133732920512557,
|
| 415 |
+
0.006057847756892443,
|
| 416 |
+
0.0011082622222602367,
|
| 417 |
+
0.0076715052127838135,
|
| 418 |
+
0.004582080524414778,
|
| 419 |
+
0.00019101824727840722,
|
| 420 |
+
0.002541859168559313,
|
| 421 |
+
0.000746950798202306,
|
| 422 |
+
0.0005463869892992079,
|
| 423 |
+
0.0004948082496412098,
|
| 424 |
+
0.0027375202625989914,
|
| 425 |
+
0.016332797706127167,
|
| 426 |
+
0.007129818666726351,
|
| 427 |
+
0.0017932195914909244,
|
| 428 |
+
0.0028880727477371693,
|
| 429 |
+
6.729422602802515e-05,
|
| 430 |
+
0.0049981712363660336,
|
| 431 |
+
0.0008069181931205094,
|
| 432 |
+
0.0004495505418162793,
|
| 433 |
+
0.0004886345705017447,
|
| 434 |
+
0.0046684034168720245,
|
| 435 |
+
0.0006491150124929845,
|
| 436 |
+
0.000614875927567482,
|
| 437 |
+
0.0003135884471703321,
|
| 438 |
+
0.0007408417877741158,
|
| 439 |
+
8.855603664414957e-05,
|
| 440 |
+
0.00016540275828447193,
|
| 441 |
+
6.872895028209314e-05,
|
| 442 |
+
0.00011193262616870925,
|
| 443 |
+
0.001047445577569306,
|
| 444 |
+
7.31844556867145e-05,
|
| 445 |
+
0.00010295258834958076,
|
| 446 |
+
8.612456440459937e-05,
|
| 447 |
+
0.00033025164157152176,
|
| 448 |
+
0.003862349083647132,
|
| 449 |
+
0.0016934244194999337,
|
| 450 |
+
0.00011782053479691967,
|
| 451 |
+
4.190853360341862e-05,
|
| 452 |
+
0.00030513000092469156,
|
| 453 |
+
9.66026636888273e-05,
|
| 454 |
+
0.0031207811553031206,
|
| 455 |
+
3.522406768752262e-05,
|
| 456 |
+
4.189743413007818e-05,
|
| 457 |
+
4.779660957865417e-05
|
| 458 |
+
],
|
| 459 |
+
"info_loss": [
|
| 460 |
+
-1.9433202743530273,
|
| 461 |
+
-0.827845573425293,
|
| 462 |
+
-0.35686588287353516,
|
| 463 |
+
-0.12140321731567383,
|
| 464 |
+
-0.0553131103515625,
|
| 465 |
+
-0.026409387588500977,
|
| 466 |
+
-0.04218101501464844,
|
| 467 |
+
-0.05390787124633789,
|
| 468 |
+
-0.06099236011505127,
|
| 469 |
+
-0.15502500534057617,
|
| 470 |
+
-0.22283828258514404,
|
| 471 |
+
-0.5115925073623657,
|
| 472 |
+
-0.9630846381187439,
|
| 473 |
+
-1.0147874355316162,
|
| 474 |
+
-0.8584111332893372,
|
| 475 |
+
-0.6050764918327332,
|
| 476 |
+
-0.47182497382164,
|
| 477 |
+
-0.4810875952243805,
|
| 478 |
+
-0.4704245328903198,
|
| 479 |
+
-0.2984234094619751,
|
| 480 |
+
-0.3534928262233734,
|
| 481 |
+
-0.3455793261528015,
|
| 482 |
+
-0.29131489992141724,
|
| 483 |
+
-0.26833248138427734,
|
| 484 |
+
-0.3037199378013611,
|
| 485 |
+
-0.2704985439777374,
|
| 486 |
+
-0.21183471381664276,
|
| 487 |
+
-0.2740691602230072,
|
| 488 |
+
-0.22347377240657806,
|
| 489 |
+
-0.2243187427520752,
|
| 490 |
+
-0.18676190078258514,
|
| 491 |
+
-0.21488259732723236,
|
| 492 |
+
-0.14173050224781036,
|
| 493 |
+
-0.11491023749113083,
|
| 494 |
+
-0.08179013431072235,
|
| 495 |
+
-0.09376046061515808,
|
| 496 |
+
-0.049157414585351944,
|
| 497 |
+
-0.07114850729703903,
|
| 498 |
+
-0.11135075986385345,
|
| 499 |
+
-0.05942864716053009,
|
| 500 |
+
-0.08550572395324707,
|
| 501 |
+
-0.04209126532077789,
|
| 502 |
+
-0.04797368496656418,
|
| 503 |
+
-0.040474776178598404,
|
| 504 |
+
-0.0701068639755249,
|
| 505 |
+
-0.010214709676802158,
|
| 506 |
+
-0.041996441781520844,
|
| 507 |
+
-0.06439362466335297,
|
| 508 |
+
-0.08016496151685715,
|
| 509 |
+
-0.06235777959227562,
|
| 510 |
+
-0.037715259939432144,
|
| 511 |
+
-0.04469200596213341,
|
| 512 |
+
-0.050741832703351974,
|
| 513 |
+
-0.009547635912895203,
|
| 514 |
+
-0.032625287771224976,
|
| 515 |
+
-0.03168065845966339,
|
| 516 |
+
-0.04413965344429016,
|
| 517 |
+
-0.04380486160516739,
|
| 518 |
+
-0.02625647559762001,
|
| 519 |
+
-0.023831762373447418,
|
| 520 |
+
-0.012906917370855808,
|
| 521 |
+
-0.021704470738768578,
|
| 522 |
+
-0.007957791909575462,
|
| 523 |
+
-0.006512778345495462,
|
| 524 |
+
-0.015087224543094635,
|
| 525 |
+
-0.009141429327428341,
|
| 526 |
+
-0.04238898307085037,
|
| 527 |
+
-0.021495986729860306,
|
| 528 |
+
-0.010736718773841858,
|
| 529 |
+
-0.012663411907851696,
|
| 530 |
+
-0.005024975631386042,
|
| 531 |
+
-0.024587683379650116,
|
| 532 |
+
-0.011854512616991997,
|
| 533 |
+
-0.008533379063010216,
|
| 534 |
+
-0.012254538014531136,
|
| 535 |
+
-0.021324578672647476,
|
| 536 |
+
-0.003948963712900877,
|
| 537 |
+
-0.002321532228961587,
|
| 538 |
+
-0.02080058492720127,
|
| 539 |
+
-0.005356201436370611,
|
| 540 |
+
-0.006445619743317366,
|
| 541 |
+
-0.0054868184961378574,
|
| 542 |
+
-0.008890531025826931,
|
| 543 |
+
-0.0008824460674077272,
|
| 544 |
+
-0.003581918077543378,
|
| 545 |
+
-0.0022404897026717663,
|
| 546 |
+
-0.003293395508080721,
|
| 547 |
+
-0.0060638305731117725,
|
| 548 |
+
-0.0041791899129748344,
|
| 549 |
+
-0.007528346031904221,
|
| 550 |
+
-0.0016216329531744123,
|
| 551 |
+
-0.004140305798500776,
|
| 552 |
+
-0.0027520006988197565,
|
| 553 |
+
-0.0018060882575809956,
|
| 554 |
+
-0.004957664757966995,
|
| 555 |
+
-0.016447870060801506,
|
| 556 |
+
-0.0045105102472007275,
|
| 557 |
+
-0.0037070501130074263,
|
| 558 |
+
-0.011178086511790752,
|
| 559 |
+
-0.0026843345258384943,
|
| 560 |
+
-0.0027829695027321577,
|
| 561 |
+
-0.002883198205381632,
|
| 562 |
+
-0.009909357875585556,
|
| 563 |
+
-0.00046625128015875816,
|
| 564 |
+
-0.0002557341940701008,
|
| 565 |
+
-0.00018528210057411343,
|
| 566 |
+
-0.0004995299968868494,
|
| 567 |
+
-0.0060438294894993305,
|
| 568 |
+
-0.001064400770701468,
|
| 569 |
+
-0.007659499067813158,
|
| 570 |
+
-0.004570694640278816,
|
| 571 |
+
-0.00017881339590530843,
|
| 572 |
+
-0.002529650693759322,
|
| 573 |
+
-0.0007380850147455931,
|
| 574 |
+
-0.0005302996723912656,
|
| 575 |
+
-0.00048183221952058375,
|
| 576 |
+
-0.0027232947759330273,
|
| 577 |
+
-0.01632087118923664,
|
| 578 |
+
-0.007120305672287941,
|
| 579 |
+
-0.0017694461857900023,
|
| 580 |
+
-0.002874758094549179,
|
| 581 |
+
-5.8506142522674054e-05,
|
| 582 |
+
-0.004986719228327274,
|
| 583 |
+
-0.0007938673952594399,
|
| 584 |
+
-0.0004411425907164812,
|
| 585 |
+
-0.0004810342798009515,
|
| 586 |
+
-0.004660286940634251,
|
| 587 |
+
-0.0006398305995389819,
|
| 588 |
+
-0.0006067802314646542,
|
| 589 |
+
-0.0003042097087018192,
|
| 590 |
+
-0.0007304014870896935,
|
| 591 |
+
-8.010549208847806e-05,
|
| 592 |
+
-0.000154368273797445,
|
| 593 |
+
-6.14623204455711e-05,
|
| 594 |
+
-0.00010350064258091152,
|
| 595 |
+
-0.0010388309601694345,
|
| 596 |
+
-6.717906944686547e-05,
|
| 597 |
+
-9.624105587136e-05,
|
| 598 |
+
-7.891710265539587e-05,
|
| 599 |
+
-0.00032456452026963234,
|
| 600 |
+
-0.0038312505930662155,
|
| 601 |
+
-0.0016877176240086555,
|
| 602 |
+
-0.00010944168025162071,
|
| 603 |
+
-3.5028784623136744e-05,
|
| 604 |
+
-0.0002996658440679312,
|
| 605 |
+
-8.839443034958094e-05,
|
| 606 |
+
-0.0031038373708724976,
|
| 607 |
+
-3.0444018193520606e-05,
|
| 608 |
+
-3.768734313780442e-05,
|
| 609 |
+
-4.2518451664363965e-05
|
| 610 |
+
],
|
| 611 |
+
"abs_loss": [
|
| 612 |
+
3.9058730602264404,
|
| 613 |
+
3.836529493331909,
|
| 614 |
+
3.7405383586883545,
|
| 615 |
+
3.243441343307495,
|
| 616 |
+
3.048604965209961,
|
| 617 |
+
3.010101318359375,
|
| 618 |
+
3.0992259979248047,
|
| 619 |
+
3.0503721237182617,
|
| 620 |
+
3.107789993286133,
|
| 621 |
+
3.018681764602661,
|
| 622 |
+
3.125788927078247,
|
| 623 |
+
3.0993168354034424,
|
| 624 |
+
3.0634496212005615,
|
| 625 |
+
3.0580875873565674,
|
| 626 |
+
3.06062388420105,
|
| 627 |
+
3.035083770751953,
|
| 628 |
+
3.0765769481658936,
|
| 629 |
+
3.0611305236816406,
|
| 630 |
+
3.137725591659546,
|
| 631 |
+
3.074432611465454,
|
| 632 |
+
3.0573785305023193,
|
| 633 |
+
3.062993288040161,
|
| 634 |
+
2.972001314163208,
|
| 635 |
+
2.930335283279419,
|
| 636 |
+
2.9305942058563232,
|
| 637 |
+
2.816206693649292,
|
| 638 |
+
2.782358169555664,
|
| 639 |
+
2.5866851806640625,
|
| 640 |
+
2.467491865158081,
|
| 641 |
+
2.2565219402313232,
|
| 642 |
+
2.0261261463165283,
|
| 643 |
+
1.9265187978744507,
|
| 644 |
+
1.8360919952392578,
|
| 645 |
+
1.5904289484024048,
|
| 646 |
+
1.3995674848556519,
|
| 647 |
+
1.3817917108535767,
|
| 648 |
+
1.1975356340408325,
|
| 649 |
+
1.0878820419311523,
|
| 650 |
+
1.053371548652649,
|
| 651 |
+
1.0705245733261108,
|
| 652 |
+
0.8897868990898132,
|
| 653 |
+
0.9148767590522766,
|
| 654 |
+
0.801529586315155,
|
| 655 |
+
0.6723634600639343,
|
| 656 |
+
0.6255919933319092,
|
| 657 |
+
0.5898261070251465,
|
| 658 |
+
0.5488032102584839,
|
| 659 |
+
0.5892140865325928,
|
| 660 |
+
0.5266454219818115,
|
| 661 |
+
0.47636714577674866,
|
| 662 |
+
0.41102632880210876,
|
| 663 |
+
0.42883172631263733,
|
| 664 |
+
0.3882034718990326,
|
| 665 |
+
0.36246514320373535,
|
| 666 |
+
0.3563854992389679,
|
| 667 |
+
0.37572789192199707,
|
| 668 |
+
0.3094463646411896,
|
| 669 |
+
0.4040512144565582,
|
| 670 |
+
0.3177582621574402,
|
| 671 |
+
0.28941503167152405,
|
| 672 |
+
0.2779967486858368,
|
| 673 |
+
0.23268987238407135,
|
| 674 |
+
0.24730391800403595,
|
| 675 |
+
0.20892749726772308,
|
| 676 |
+
0.22284547984600067,
|
| 677 |
+
0.17129582166671753,
|
| 678 |
+
0.18049044907093048,
|
| 679 |
+
0.14915691316127777,
|
| 680 |
+
0.14113618433475494,
|
| 681 |
+
0.13125668466091156,
|
| 682 |
+
0.15630997717380524,
|
| 683 |
+
0.12934143841266632,
|
| 684 |
+
0.13377706706523895,
|
| 685 |
+
0.14099036157131195,
|
| 686 |
+
0.1310848444700241,
|
| 687 |
+
0.10560987144708633,
|
| 688 |
+
0.10672527551651001,
|
| 689 |
+
0.11738106608390808,
|
| 690 |
+
0.10729807615280151,
|
| 691 |
+
0.10206899791955948,
|
| 692 |
+
0.08919984102249146,
|
| 693 |
+
0.11989644914865494,
|
| 694 |
+
0.11340248584747314,
|
| 695 |
+
0.08449236303567886,
|
| 696 |
+
0.06682342290878296,
|
| 697 |
+
0.057425662875175476,
|
| 698 |
+
0.061200182884931564,
|
| 699 |
+
0.06799478828907013,
|
| 700 |
+
0.049633320420980453,
|
| 701 |
+
0.05667348578572273,
|
| 702 |
+
0.0685342401266098,
|
| 703 |
+
0.05138104036450386,
|
| 704 |
+
0.05015311762690544,
|
| 705 |
+
0.034664783626794815,
|
| 706 |
+
0.03596033528447151,
|
| 707 |
+
0.04998330771923065,
|
| 708 |
+
0.02775459922850132,
|
| 709 |
+
0.051192302256822586,
|
| 710 |
+
0.035633716732263565,
|
| 711 |
+
0.03298192098736763,
|
| 712 |
+
0.04327242076396942,
|
| 713 |
+
0.044632941484451294,
|
| 714 |
+
0.0530560202896595,
|
| 715 |
+
0.03017588146030903,
|
| 716 |
+
0.03568728640675545,
|
| 717 |
+
0.035931508988142014,
|
| 718 |
+
0.04243310168385506,
|
| 719 |
+
0.02658197097480297,
|
| 720 |
+
0.033995114266872406,
|
| 721 |
+
0.037799570709466934,
|
| 722 |
+
0.0243062824010849,
|
| 723 |
+
0.025217527523636818,
|
| 724 |
+
0.022923991084098816,
|
| 725 |
+
0.021980104967951775,
|
| 726 |
+
0.03181498125195503,
|
| 727 |
+
0.03872985020279884,
|
| 728 |
+
0.02716980315744877,
|
| 729 |
+
0.027311721816658974,
|
| 730 |
+
0.02898067981004715,
|
| 731 |
+
0.021651500836014748,
|
| 732 |
+
0.03189697116613388,
|
| 733 |
+
0.020754819735884666,
|
| 734 |
+
0.02615179680287838,
|
| 735 |
+
0.024158934131264687,
|
| 736 |
+
0.020408356562256813,
|
| 737 |
+
0.01452732365578413,
|
| 738 |
+
0.03205832466483116,
|
| 739 |
+
0.018258022144436836,
|
| 740 |
+
0.020568842068314552,
|
| 741 |
+
0.019039256498217583,
|
| 742 |
+
0.02144511602818966,
|
| 743 |
+
0.02150823175907135,
|
| 744 |
+
0.02178180031478405,
|
| 745 |
+
0.01846039481461048,
|
| 746 |
+
0.01317529659718275,
|
| 747 |
+
0.014675094746053219,
|
| 748 |
+
0.016281811520457268,
|
| 749 |
+
0.012562199495732784,
|
| 750 |
+
0.009454809129238129,
|
| 751 |
+
0.013245371170341969,
|
| 752 |
+
0.011289101094007492,
|
| 753 |
+
0.02340284176170826,
|
| 754 |
+
0.018349329009652138,
|
| 755 |
+
0.010829237289726734,
|
| 756 |
+
0.008192529901862144,
|
| 757 |
+
0.010534784756600857,
|
| 758 |
+
0.016815941780805588,
|
| 759 |
+
0.00871493574231863,
|
| 760 |
+
0.010320407338440418,
|
| 761 |
+
0.010597857646644115
|
| 762 |
+
],
|
| 763 |
+
"zipf_loss": [
|
| 764 |
+
6.052987098693848,
|
| 765 |
+
4.252349853515625,
|
| 766 |
+
2.4764275550842285,
|
| 767 |
+
1.039671540260315,
|
| 768 |
+
0.7015275359153748,
|
| 769 |
+
0.6630921363830566,
|
| 770 |
+
0.6538114547729492,
|
| 771 |
+
0.651854395866394,
|
| 772 |
+
0.6466925144195557,
|
| 773 |
+
0.6486480236053467,
|
| 774 |
+
0.647781252861023,
|
| 775 |
+
0.6465995907783508,
|
| 776 |
+
0.6566208600997925,
|
| 777 |
+
0.659423828125,
|
| 778 |
+
0.6586042642593384,
|
| 779 |
+
0.6558700799942017,
|
| 780 |
+
0.6548885107040405,
|
| 781 |
+
0.6539199352264404,
|
| 782 |
+
0.6524903774261475,
|
| 783 |
+
0.6522390842437744,
|
| 784 |
+
0.6511721611022949,
|
| 785 |
+
0.6475664377212524,
|
| 786 |
+
0.6433051824569702,
|
| 787 |
+
0.6461644172668457,
|
| 788 |
+
0.6270601153373718,
|
| 789 |
+
0.6279184818267822,
|
| 790 |
+
0.6013771891593933,
|
| 791 |
+
0.602429986000061,
|
| 792 |
+
0.5648212432861328,
|
| 793 |
+
0.5786304473876953,
|
| 794 |
+
0.5180673599243164,
|
| 795 |
+
0.5260982513427734,
|
| 796 |
+
0.47597935795783997,
|
| 797 |
+
0.40593281388282776,
|
| 798 |
+
0.34503477811813354,
|
| 799 |
+
0.295649915933609,
|
| 800 |
+
0.28118064999580383,
|
| 801 |
+
0.2570253014564514,
|
| 802 |
+
0.21094900369644165,
|
| 803 |
+
0.19080683588981628,
|
| 804 |
+
0.18353208899497986,
|
| 805 |
+
0.14179804921150208,
|
| 806 |
+
0.10587838292121887,
|
| 807 |
+
0.10821489244699478,
|
| 808 |
+
0.11385685205459595,
|
| 809 |
+
0.0790158361196518,
|
| 810 |
+
0.08786381036043167,
|
| 811 |
+
0.07872800529003143,
|
| 812 |
+
0.06990247964859009,
|
| 813 |
+
0.0674760565161705,
|
| 814 |
+
0.06754579395055771,
|
| 815 |
+
0.06983557343482971,
|
| 816 |
+
0.05906135216355324,
|
| 817 |
+
0.06493433564901352,
|
| 818 |
+
0.061671726405620575,
|
| 819 |
+
0.050262849777936935,
|
| 820 |
+
0.05205643177032471,
|
| 821 |
+
0.04158949479460716,
|
| 822 |
+
0.050549112260341644,
|
| 823 |
+
0.051753684878349304,
|
| 824 |
+
0.0557246096432209,
|
| 825 |
+
0.04862213879823685,
|
| 826 |
+
0.047782592475414276,
|
| 827 |
+
0.05649994686245918,
|
| 828 |
+
0.0407605841755867,
|
| 829 |
+
0.03879119083285332,
|
| 830 |
+
0.060350529849529266,
|
| 831 |
+
0.051135119050741196,
|
| 832 |
+
0.044451095163822174,
|
| 833 |
+
0.033662099391222,
|
| 834 |
+
0.06069512665271759,
|
| 835 |
+
0.05022495985031128,
|
| 836 |
+
0.03780406713485718,
|
| 837 |
+
0.026736848056316376,
|
| 838 |
+
0.039483025670051575,
|
| 839 |
+
0.025743279606103897,
|
| 840 |
+
0.03772453963756561,
|
| 841 |
+
0.03043164685368538,
|
| 842 |
+
0.0529666393995285,
|
| 843 |
+
0.030693713575601578,
|
| 844 |
+
0.03585662692785263,
|
| 845 |
+
0.029946530237793922,
|
| 846 |
+
0.030659228563308716,
|
| 847 |
+
0.03638206794857979,
|
| 848 |
+
0.04380744695663452,
|
| 849 |
+
0.026793457567691803,
|
| 850 |
+
0.021973812952637672,
|
| 851 |
+
0.020119553431868553,
|
| 852 |
+
0.03328540548682213,
|
| 853 |
+
0.031271062791347504,
|
| 854 |
+
0.043162859976291656,
|
| 855 |
+
0.033812880516052246,
|
| 856 |
+
0.02697194553911686,
|
| 857 |
+
0.03272710368037224,
|
| 858 |
+
0.024554645642638206,
|
| 859 |
+
0.02476862445473671,
|
| 860 |
+
0.026464400812983513,
|
| 861 |
+
0.02559398114681244,
|
| 862 |
+
0.021990595385432243,
|
| 863 |
+
0.028500180691480637,
|
| 864 |
+
0.021697266027331352,
|
| 865 |
+
0.026455901563167572,
|
| 866 |
+
0.03391361981630325,
|
| 867 |
+
0.02725423499941826,
|
| 868 |
+
0.023890238255262375,
|
| 869 |
+
0.026481766253709793,
|
| 870 |
+
0.02835354208946228,
|
| 871 |
+
0.029589319601655006,
|
| 872 |
+
0.023224081844091415,
|
| 873 |
+
0.03267461806535721,
|
| 874 |
+
0.021775847300887108,
|
| 875 |
+
0.030338987708091736,
|
| 876 |
+
0.030362160876393318,
|
| 877 |
+
0.024748343974351883,
|
| 878 |
+
0.039005715399980545,
|
| 879 |
+
0.016655704006552696,
|
| 880 |
+
0.02422911487519741,
|
| 881 |
+
0.034959107637405396,
|
| 882 |
+
0.025401610881090164,
|
| 883 |
+
0.02754240855574608,
|
| 884 |
+
0.02788001298904419,
|
| 885 |
+
0.019012952223420143,
|
| 886 |
+
0.03669754043221474,
|
| 887 |
+
0.018773101270198822,
|
| 888 |
+
0.02567555010318756,
|
| 889 |
+
0.026316016912460327,
|
| 890 |
+
0.023425336927175522,
|
| 891 |
+
0.0189511775970459,
|
| 892 |
+
0.026118718087673187,
|
| 893 |
+
0.030445998534560204,
|
| 894 |
+
0.023525811731815338,
|
| 895 |
+
0.028677035123109818,
|
| 896 |
+
0.015091114677488804,
|
| 897 |
+
0.021158069372177124,
|
| 898 |
+
0.02237561345100403,
|
| 899 |
+
0.013747500255703926,
|
| 900 |
+
0.031110119074583054,
|
| 901 |
+
0.026012767106294632,
|
| 902 |
+
0.028576156124472618,
|
| 903 |
+
0.019472964107990265,
|
| 904 |
+
0.02523789182305336,
|
| 905 |
+
0.030870981514453888,
|
| 906 |
+
0.017786312848329544,
|
| 907 |
+
0.020696964114904404,
|
| 908 |
+
0.020390750840306282,
|
| 909 |
+
0.01948927715420723,
|
| 910 |
+
0.016920428723096848,
|
| 911 |
+
0.029213517904281616,
|
| 912 |
+
0.02738238126039505,
|
| 913 |
+
0.028691411018371582
|
| 914 |
+
],
|
| 915 |
+
"denoise_loss": [],
|
| 916 |
+
"ortho_loss": [
|
| 917 |
+
0.8346008062362671,
|
| 918 |
+
0.3907858729362488,
|
| 919 |
+
0.17515739798545837,
|
| 920 |
+
0.11944866925477982,
|
| 921 |
+
0.11406867951154709,
|
| 922 |
+
0.1059853807091713,
|
| 923 |
+
0.09238146990537643,
|
| 924 |
+
0.09110616892576218,
|
| 925 |
+
0.08909612894058228,
|
| 926 |
+
0.09168878942728043,
|
| 927 |
+
0.09412479400634766,
|
| 928 |
+
0.10443686693906784,
|
| 929 |
+
0.11815950274467468,
|
| 930 |
+
0.12763310968875885,
|
| 931 |
+
0.13446316123008728,
|
| 932 |
+
0.14940908551216125,
|
| 933 |
+
0.1571289300918579,
|
| 934 |
+
0.16322873532772064,
|
| 935 |
+
0.16985493898391724,
|
| 936 |
+
0.17381422221660614,
|
| 937 |
+
0.1741640567779541,
|
| 938 |
+
0.17640076577663422,
|
| 939 |
+
0.17971451580524445,
|
| 940 |
+
0.18441055715084076,
|
| 941 |
+
0.18912966549396515,
|
| 942 |
+
0.19178953766822815,
|
| 943 |
+
0.19310130178928375,
|
| 944 |
+
0.19510282576084137,
|
| 945 |
+
0.19889295101165771,
|
| 946 |
+
0.20357120037078857,
|
| 947 |
+
0.2052219659090042,
|
| 948 |
+
0.20363925397396088,
|
| 949 |
+
0.20488138496875763,
|
| 950 |
+
0.2041327953338623,
|
| 951 |
+
0.20154616236686707,
|
| 952 |
+
0.20048795640468597,
|
| 953 |
+
0.19385696947574615,
|
| 954 |
+
0.19331151247024536,
|
| 955 |
+
0.1909814476966858,
|
| 956 |
+
0.19315500557422638,
|
| 957 |
+
0.19334891438484192,
|
| 958 |
+
0.19046221673488617,
|
| 959 |
+
0.192839577794075,
|
| 960 |
+
0.19030462205410004,
|
| 961 |
+
0.18696968257427216,
|
| 962 |
+
0.1808437556028366,
|
| 963 |
+
0.17908300459384918,
|
| 964 |
+
0.17668798565864563,
|
| 965 |
+
0.17450466752052307,
|
| 966 |
+
0.17578569054603577,
|
| 967 |
+
0.17185476422309875,
|
| 968 |
+
0.17216168344020844,
|
| 969 |
+
0.17100204527378082,
|
| 970 |
+
0.16910654306411743,
|
| 971 |
+
0.16549545526504517,
|
| 972 |
+
0.1657339483499527,
|
| 973 |
+
0.1679120808839798,
|
| 974 |
+
0.16710339486598969,
|
| 975 |
+
0.16517405211925507,
|
| 976 |
+
0.16507413983345032,
|
| 977 |
+
0.16555523872375488,
|
| 978 |
+
0.1658637523651123,
|
| 979 |
+
0.16776184737682343,
|
| 980 |
+
0.1688799113035202,
|
| 981 |
+
0.16683374345302582,
|
| 982 |
+
0.1690855473279953,
|
| 983 |
+
0.17039917409420013,
|
| 984 |
+
0.1741783767938614,
|
| 985 |
+
0.17737336456775665,
|
| 986 |
+
0.17890101671218872,
|
| 987 |
+
0.18008092045783997,
|
| 988 |
+
0.17815418541431427,
|
| 989 |
+
0.17755572497844696,
|
| 990 |
+
0.18047258257865906,
|
| 991 |
+
0.1805938333272934,
|
| 992 |
+
0.18096090853214264,
|
| 993 |
+
0.17716756463050842,
|
| 994 |
+
0.17896567285060883,
|
| 995 |
+
0.17886556684970856,
|
| 996 |
+
0.17628921568393707,
|
| 997 |
+
0.1772650182247162,
|
| 998 |
+
0.176082044839859,
|
| 999 |
+
0.17696383595466614,
|
| 1000 |
+
0.1766868382692337,
|
| 1001 |
+
0.1778104603290558,
|
| 1002 |
+
0.1794768124818802,
|
| 1003 |
+
0.17751853168010712,
|
| 1004 |
+
0.17380660772323608,
|
| 1005 |
+
0.17284800112247467,
|
| 1006 |
+
0.17235341668128967,
|
| 1007 |
+
0.17603875696659088,
|
| 1008 |
+
0.17461921274662018,
|
| 1009 |
+
0.17676301300525665,
|
| 1010 |
+
0.17673002183437347,
|
| 1011 |
+
0.1746983677148819,
|
| 1012 |
+
0.17470526695251465,
|
| 1013 |
+
0.17406275868415833,
|
| 1014 |
+
0.17371778190135956,
|
| 1015 |
+
0.1729806661605835,
|
| 1016 |
+
0.1731955111026764,
|
| 1017 |
+
0.1741393357515335,
|
| 1018 |
+
0.1753096729516983,
|
| 1019 |
+
0.17489361763000488,
|
| 1020 |
+
0.17547819018363953,
|
| 1021 |
+
0.17919553816318512,
|
| 1022 |
+
0.1790146380662918,
|
| 1023 |
+
0.179719477891922,
|
| 1024 |
+
0.1773523986339569,
|
| 1025 |
+
0.17798514664173126,
|
| 1026 |
+
0.17839646339416504,
|
| 1027 |
+
0.1768946349620819,
|
| 1028 |
+
0.17508208751678467,
|
| 1029 |
+
0.17682206630706787,
|
| 1030 |
+
0.1759224534034729,
|
| 1031 |
+
0.178494393825531,
|
| 1032 |
+
0.17856447398662567,
|
| 1033 |
+
0.17874273657798767,
|
| 1034 |
+
0.1784323751926422,
|
| 1035 |
+
0.17625990509986877,
|
| 1036 |
+
0.1773957461118698,
|
| 1037 |
+
0.17702791094779968,
|
| 1038 |
+
0.17628365755081177,
|
| 1039 |
+
0.1764688938856125,
|
| 1040 |
+
0.17721740901470184,
|
| 1041 |
+
0.17663374543190002,
|
| 1042 |
+
0.17624999582767487,
|
| 1043 |
+
0.1757938116788864,
|
| 1044 |
+
0.1765153557062149,
|
| 1045 |
+
0.17661398649215698,
|
| 1046 |
+
0.17987975478172302,
|
| 1047 |
+
0.1803244799375534,
|
| 1048 |
+
0.18036377429962158,
|
| 1049 |
+
0.17962133884429932,
|
| 1050 |
+
0.1797693371772766,
|
| 1051 |
+
0.17994874715805054,
|
| 1052 |
+
0.17992182075977325,
|
| 1053 |
+
0.1798945963382721,
|
| 1054 |
+
0.17968730628490448,
|
| 1055 |
+
0.17990748584270477,
|
| 1056 |
+
0.18027549982070923,
|
| 1057 |
+
0.1810416579246521,
|
| 1058 |
+
0.1814541518688202,
|
| 1059 |
+
0.1810583621263504,
|
| 1060 |
+
0.18104512989521027,
|
| 1061 |
+
0.1812652200460434,
|
| 1062 |
+
0.18126952648162842,
|
| 1063 |
+
0.1813357025384903,
|
| 1064 |
+
0.1812535673379898,
|
| 1065 |
+
0.18106873333454132,
|
| 1066 |
+
0.18130409717559814
|
| 1067 |
+
],
|
| 1068 |
+
"lr": [
|
| 1069 |
+
8.376068376068378e-06,
|
| 1070 |
+
1.6923076923076924e-05,
|
| 1071 |
+
2.5470085470085475e-05,
|
| 1072 |
+
3.401709401709402e-05,
|
| 1073 |
+
4e-05,
|
| 1074 |
+
4e-05,
|
| 1075 |
+
4e-05,
|
| 1076 |
+
4e-05,
|
| 1077 |
+
4e-05,
|
| 1078 |
+
4e-05,
|
| 1079 |
+
4e-05,
|
| 1080 |
+
4e-05,
|
| 1081 |
+
4e-05,
|
| 1082 |
+
4e-05,
|
| 1083 |
+
4e-05,
|
| 1084 |
+
4e-05,
|
| 1085 |
+
4e-05,
|
| 1086 |
+
4e-05,
|
| 1087 |
+
4e-05,
|
| 1088 |
+
4e-05,
|
| 1089 |
+
4e-05,
|
| 1090 |
+
4e-05,
|
| 1091 |
+
4e-05,
|
| 1092 |
+
4e-05,
|
| 1093 |
+
4e-05,
|
| 1094 |
+
4e-05,
|
| 1095 |
+
4e-05,
|
| 1096 |
+
4e-05,
|
| 1097 |
+
4e-05,
|
| 1098 |
+
4e-05,
|
| 1099 |
+
4e-05,
|
| 1100 |
+
4e-05,
|
| 1101 |
+
4e-05,
|
| 1102 |
+
4e-05,
|
| 1103 |
+
4e-05,
|
| 1104 |
+
4e-05,
|
| 1105 |
+
4e-05,
|
| 1106 |
+
4e-05,
|
| 1107 |
+
4e-05,
|
| 1108 |
+
4e-05,
|
| 1109 |
+
4e-05,
|
| 1110 |
+
4e-05,
|
| 1111 |
+
4e-05,
|
| 1112 |
+
4e-05,
|
| 1113 |
+
4e-05,
|
| 1114 |
+
4e-05,
|
| 1115 |
+
4e-05,
|
| 1116 |
+
4e-05,
|
| 1117 |
+
4e-05,
|
| 1118 |
+
4e-05,
|
| 1119 |
+
4e-05,
|
| 1120 |
+
4e-05,
|
| 1121 |
+
4e-05,
|
| 1122 |
+
4e-05,
|
| 1123 |
+
4e-05,
|
| 1124 |
+
4e-05,
|
| 1125 |
+
4e-05,
|
| 1126 |
+
4e-05,
|
| 1127 |
+
4e-05,
|
| 1128 |
+
4e-05,
|
| 1129 |
+
4e-05,
|
| 1130 |
+
4e-05,
|
| 1131 |
+
4e-05,
|
| 1132 |
+
4e-05,
|
| 1133 |
+
4e-05,
|
| 1134 |
+
4e-05,
|
| 1135 |
+
4e-05,
|
| 1136 |
+
4e-05,
|
| 1137 |
+
4e-05,
|
| 1138 |
+
4e-05,
|
| 1139 |
+
4e-05,
|
| 1140 |
+
4e-05,
|
| 1141 |
+
4e-05,
|
| 1142 |
+
4e-05,
|
| 1143 |
+
4e-05,
|
| 1144 |
+
4e-05,
|
| 1145 |
+
4e-05,
|
| 1146 |
+
4e-05,
|
| 1147 |
+
4e-05,
|
| 1148 |
+
4e-05,
|
| 1149 |
+
4e-05,
|
| 1150 |
+
4e-05,
|
| 1151 |
+
4e-05,
|
| 1152 |
+
4e-05,
|
| 1153 |
+
4e-05,
|
| 1154 |
+
4e-05,
|
| 1155 |
+
4e-05,
|
| 1156 |
+
4e-05,
|
| 1157 |
+
4e-05,
|
| 1158 |
+
4e-05,
|
| 1159 |
+
4e-05,
|
| 1160 |
+
3.993593461639863e-05,
|
| 1161 |
+
3.934273662008964e-05,
|
| 1162 |
+
3.874953862378065e-05,
|
| 1163 |
+
3.815634062747166e-05,
|
| 1164 |
+
3.7563142631162665e-05,
|
| 1165 |
+
3.696994463485368e-05,
|
| 1166 |
+
3.637674663854469e-05,
|
| 1167 |
+
3.5783548642235693e-05,
|
| 1168 |
+
3.519035064592671e-05,
|
| 1169 |
+
3.459715264961771e-05,
|
| 1170 |
+
3.400395465330873e-05,
|
| 1171 |
+
3.341075665699973e-05,
|
| 1172 |
+
3.281755866069075e-05,
|
| 1173 |
+
3.2224360664381764e-05,
|
| 1174 |
+
3.1251515950435014e-05,
|
| 1175 |
+
3.065831795412602e-05,
|
| 1176 |
+
3.0065119957817037e-05,
|
| 1177 |
+
2.947192196150804e-05,
|
| 1178 |
+
2.887872396519905e-05,
|
| 1179 |
+
2.8285525968890065e-05,
|
| 1180 |
+
2.769232797258107e-05,
|
| 1181 |
+
2.709912997627208e-05,
|
| 1182 |
+
2.6505931979963087e-05,
|
| 1183 |
+
2.5912733983654104e-05,
|
| 1184 |
+
2.5319535987345117e-05,
|
| 1185 |
+
2.472633799103612e-05,
|
| 1186 |
+
2.4133139994727132e-05,
|
| 1187 |
+
2.3539941998418135e-05,
|
| 1188 |
+
2.2946744002109148e-05,
|
| 1189 |
+
2.1973899288162408e-05,
|
| 1190 |
+
2.138070129185341e-05,
|
| 1191 |
+
2.0787503295544424e-05,
|
| 1192 |
+
2.019430529923544e-05,
|
| 1193 |
+
1.9601107302926443e-05,
|
| 1194 |
+
1.900790930661746e-05,
|
| 1195 |
+
1.8414711310308462e-05,
|
| 1196 |
+
1.7821513313999475e-05,
|
| 1197 |
+
1.7228315317690488e-05,
|
| 1198 |
+
1.663511732138149e-05,
|
| 1199 |
+
1.6041919325072507e-05,
|
| 1200 |
+
1.544872132876351e-05,
|
| 1201 |
+
1.4855523332454524e-05,
|
| 1202 |
+
1.4262325336145537e-05,
|
| 1203 |
+
1.366912733983654e-05,
|
| 1204 |
+
1.2696282625889797e-05,
|
| 1205 |
+
1.2103084629580812e-05,
|
| 1206 |
+
1.1509886633271816e-05,
|
| 1207 |
+
1.0916688636962829e-05,
|
| 1208 |
+
1.0323490640653833e-05,
|
| 1209 |
+
9.730292644344846e-06,
|
| 1210 |
+
9.137094648035861e-06,
|
| 1211 |
+
8.543896651726864e-06,
|
| 1212 |
+
7.950698655417878e-06,
|
| 1213 |
+
7.357500659108881e-06,
|
| 1214 |
+
6.764302662799895e-06,
|
| 1215 |
+
6.171104666490909e-06,
|
| 1216 |
+
5.577906670181913e-06,
|
| 1217 |
+
4.984708673872927e-06,
|
| 1218 |
+
4.391510677563931e-06
|
| 1219 |
+
],
|
| 1220 |
+
"emb_lr": [],
|
| 1221 |
+
"eval_step": [
|
| 1222 |
+
750,
|
| 1223 |
+
1532,
|
| 1224 |
+
2314,
|
| 1225 |
+
3096,
|
| 1226 |
+
3878,
|
| 1227 |
+
4660,
|
| 1228 |
+
5442,
|
| 1229 |
+
6224,
|
| 1230 |
+
7006,
|
| 1231 |
+
7788
|
| 1232 |
+
],
|
| 1233 |
+
"eval_accuracy": [
|
| 1234 |
+
0.0,
|
| 1235 |
+
0.0,
|
| 1236 |
+
0.0,
|
| 1237 |
+
0.0,
|
| 1238 |
+
0.0,
|
| 1239 |
+
0.0,
|
| 1240 |
+
0.0,
|
| 1241 |
+
0.0,
|
| 1242 |
+
0.0,
|
| 1243 |
+
0.0
|
| 1244 |
+
]
|
| 1245 |
+
},
|
| 1246 |
+
"final_accuracy": 1.0,
|
| 1247 |
+
"sft_eval": {
|
| 1248 |
+
"config": {
|
| 1249 |
+
"ops": "add_sub",
|
| 1250 |
+
"K": null,
|
| 1251 |
+
"mode": "sft",
|
| 1252 |
+
"n_digits": 6,
|
| 1253 |
+
"n_per_split": 100
|
| 1254 |
+
},
|
| 1255 |
+
"splits": {
|
| 1256 |
+
"add_S0": {
|
| 1257 |
+
"full_accuracy": 1.0,
|
| 1258 |
+
"n_examples": 100,
|
| 1259 |
+
"per_subtask": {
|
| 1260 |
+
"SA": {
|
| 1261 |
+
"accuracy": 1.0,
|
| 1262 |
+
"count": 605
|
| 1263 |
+
},
|
| 1264 |
+
"SS": {
|
| 1265 |
+
"accuracy": 1.0,
|
| 1266 |
+
"count": 95
|
| 1267 |
+
}
|
| 1268 |
+
}
|
| 1269 |
+
},
|
| 1270 |
+
"add_S1": {
|
| 1271 |
+
"full_accuracy": 1.0,
|
| 1272 |
+
"n_examples": 100,
|
| 1273 |
+
"per_subtask": {
|
| 1274 |
+
"SA": {
|
| 1275 |
+
"accuracy": 1.0,
|
| 1276 |
+
"count": 204
|
| 1277 |
+
},
|
| 1278 |
+
"SC": {
|
| 1279 |
+
"accuracy": 1.0,
|
| 1280 |
+
"count": 169
|
| 1281 |
+
},
|
| 1282 |
+
"SS": {
|
| 1283 |
+
"accuracy": 1.0,
|
| 1284 |
+
"count": 31
|
| 1285 |
+
},
|
| 1286 |
+
"UC": {
|
| 1287 |
+
"accuracy": 1.0,
|
| 1288 |
+
"count": 296
|
| 1289 |
+
}
|
| 1290 |
+
}
|
| 1291 |
+
},
|
| 1292 |
+
"add_S2": {
|
| 1293 |
+
"full_accuracy": 1.0,
|
| 1294 |
+
"n_examples": 100,
|
| 1295 |
+
"per_subtask": {
|
| 1296 |
+
"SA": {
|
| 1297 |
+
"accuracy": 1.0,
|
| 1298 |
+
"count": 163
|
| 1299 |
+
},
|
| 1300 |
+
"SC": {
|
| 1301 |
+
"accuracy": 1.0,
|
| 1302 |
+
"count": 130
|
| 1303 |
+
},
|
| 1304 |
+
"SS": {
|
| 1305 |
+
"accuracy": 1.0,
|
| 1306 |
+
"count": 87
|
| 1307 |
+
},
|
| 1308 |
+
"UC": {
|
| 1309 |
+
"accuracy": 1.0,
|
| 1310 |
+
"count": 203
|
| 1311 |
+
},
|
| 1312 |
+
"US": {
|
| 1313 |
+
"accuracy": 1.0,
|
| 1314 |
+
"count": 117
|
| 1315 |
+
}
|
| 1316 |
+
}
|
| 1317 |
+
},
|
| 1318 |
+
"add_S3": {
|
| 1319 |
+
"full_accuracy": 1.0,
|
| 1320 |
+
"n_examples": 100,
|
| 1321 |
+
"per_subtask": {
|
| 1322 |
+
"SA": {
|
| 1323 |
+
"accuracy": 1.0,
|
| 1324 |
+
"count": 121
|
| 1325 |
+
},
|
| 1326 |
+
"SC": {
|
| 1327 |
+
"accuracy": 1.0,
|
| 1328 |
+
"count": 121
|
| 1329 |
+
},
|
| 1330 |
+
"SS": {
|
| 1331 |
+
"accuracy": 1.0,
|
| 1332 |
+
"count": 49
|
| 1333 |
+
},
|
| 1334 |
+
"UC": {
|
| 1335 |
+
"accuracy": 1.0,
|
| 1336 |
+
"count": 186
|
| 1337 |
+
},
|
| 1338 |
+
"US": {
|
| 1339 |
+
"accuracy": 1.0,
|
| 1340 |
+
"count": 223
|
| 1341 |
+
}
|
| 1342 |
+
}
|
| 1343 |
+
},
|
| 1344 |
+
"add_S4": {
|
| 1345 |
+
"full_accuracy": 0.99,
|
| 1346 |
+
"n_examples": 100,
|
| 1347 |
+
"per_subtask": {
|
| 1348 |
+
"SA": {
|
| 1349 |
+
"accuracy": 1.0,
|
| 1350 |
+
"count": 104
|
| 1351 |
+
},
|
| 1352 |
+
"SC": {
|
| 1353 |
+
"accuracy": 1.0,
|
| 1354 |
+
"count": 106
|
| 1355 |
+
},
|
| 1356 |
+
"SS": {
|
| 1357 |
+
"accuracy": 1.0,
|
| 1358 |
+
"count": 23
|
| 1359 |
+
},
|
| 1360 |
+
"UC": {
|
| 1361 |
+
"accuracy": 0.99375,
|
| 1362 |
+
"count": 160
|
| 1363 |
+
},
|
| 1364 |
+
"US": {
|
| 1365 |
+
"accuracy": 1.0,
|
| 1366 |
+
"count": 307
|
| 1367 |
+
}
|
| 1368 |
+
}
|
| 1369 |
+
},
|
| 1370 |
+
"add_S5": {
|
| 1371 |
+
"full_accuracy": 1.0,
|
| 1372 |
+
"n_examples": 100,
|
| 1373 |
+
"per_subtask": {
|
| 1374 |
+
"SA": {
|
| 1375 |
+
"accuracy": 1.0,
|
| 1376 |
+
"count": 100
|
| 1377 |
+
},
|
| 1378 |
+
"SC": {
|
| 1379 |
+
"accuracy": 1.0,
|
| 1380 |
+
"count": 100
|
| 1381 |
+
},
|
| 1382 |
+
"UC": {
|
| 1383 |
+
"accuracy": 1.0,
|
| 1384 |
+
"count": 100
|
| 1385 |
+
},
|
| 1386 |
+
"US": {
|
| 1387 |
+
"accuracy": 1.0,
|
| 1388 |
+
"count": 400
|
| 1389 |
+
}
|
| 1390 |
+
}
|
| 1391 |
+
},
|
| 1392 |
+
"add_S6": {
|
| 1393 |
+
"full_accuracy": 1.0,
|
| 1394 |
+
"n_examples": 100,
|
| 1395 |
+
"per_subtask": {
|
| 1396 |
+
"SC": {
|
| 1397 |
+
"accuracy": 1.0,
|
| 1398 |
+
"count": 100
|
| 1399 |
+
},
|
| 1400 |
+
"UC": {
|
| 1401 |
+
"accuracy": 1.0,
|
| 1402 |
+
"count": 100
|
| 1403 |
+
},
|
| 1404 |
+
"US": {
|
| 1405 |
+
"accuracy": 1.0,
|
| 1406 |
+
"count": 500
|
| 1407 |
+
}
|
| 1408 |
+
}
|
| 1409 |
+
},
|
| 1410 |
+
"add_random": {
|
| 1411 |
+
"full_accuracy": 1.0,
|
| 1412 |
+
"n_examples": 200,
|
| 1413 |
+
"per_subtask": {
|
| 1414 |
+
"SA": {
|
| 1415 |
+
"accuracy": 1.0,
|
| 1416 |
+
"count": 447
|
| 1417 |
+
},
|
| 1418 |
+
"SC": {
|
| 1419 |
+
"accuracy": 1.0,
|
| 1420 |
+
"count": 320
|
| 1421 |
+
},
|
| 1422 |
+
"SS": {
|
| 1423 |
+
"accuracy": 1.0,
|
| 1424 |
+
"count": 56
|
| 1425 |
+
},
|
| 1426 |
+
"UC": {
|
| 1427 |
+
"accuracy": 1.0,
|
| 1428 |
+
"count": 529
|
| 1429 |
+
},
|
| 1430 |
+
"US": {
|
| 1431 |
+
"accuracy": 1.0,
|
| 1432 |
+
"count": 48
|
| 1433 |
+
}
|
| 1434 |
+
}
|
| 1435 |
+
},
|
| 1436 |
+
"add_C3": {
|
| 1437 |
+
"full_accuracy": 1.0,
|
| 1438 |
+
"n_examples": 100,
|
| 1439 |
+
"per_subtask": {
|
| 1440 |
+
"SA": {
|
| 1441 |
+
"accuracy": 1.0,
|
| 1442 |
+
"count": 300
|
| 1443 |
+
},
|
| 1444 |
+
"SC": {
|
| 1445 |
+
"accuracy": 1.0,
|
| 1446 |
+
"count": 100
|
| 1447 |
+
},
|
| 1448 |
+
"UC": {
|
| 1449 |
+
"accuracy": 1.0,
|
| 1450 |
+
"count": 193
|
| 1451 |
+
},
|
| 1452 |
+
"US": {
|
| 1453 |
+
"accuracy": 1.0,
|
| 1454 |
+
"count": 107
|
| 1455 |
+
}
|
| 1456 |
+
}
|
| 1457 |
+
},
|
| 1458 |
+
"add_C4": {
|
| 1459 |
+
"full_accuracy": 1.0,
|
| 1460 |
+
"n_examples": 100,
|
| 1461 |
+
"per_subtask": {
|
| 1462 |
+
"SA": {
|
| 1463 |
+
"accuracy": 1.0,
|
| 1464 |
+
"count": 200
|
| 1465 |
+
},
|
| 1466 |
+
"SC": {
|
| 1467 |
+
"accuracy": 1.0,
|
| 1468 |
+
"count": 100
|
| 1469 |
+
},
|
| 1470 |
+
"UC": {
|
| 1471 |
+
"accuracy": 1.0,
|
| 1472 |
+
"count": 256
|
| 1473 |
+
},
|
| 1474 |
+
"US": {
|
| 1475 |
+
"accuracy": 1.0,
|
| 1476 |
+
"count": 144
|
| 1477 |
+
}
|
| 1478 |
+
}
|
| 1479 |
+
},
|
| 1480 |
+
"add_C5": {
|
| 1481 |
+
"full_accuracy": 1.0,
|
| 1482 |
+
"n_examples": 100,
|
| 1483 |
+
"per_subtask": {
|
| 1484 |
+
"SA": {
|
| 1485 |
+
"accuracy": 1.0,
|
| 1486 |
+
"count": 100
|
| 1487 |
+
},
|
| 1488 |
+
"SC": {
|
| 1489 |
+
"accuracy": 1.0,
|
| 1490 |
+
"count": 100
|
| 1491 |
+
},
|
| 1492 |
+
"UC": {
|
| 1493 |
+
"accuracy": 1.0,
|
| 1494 |
+
"count": 306
|
| 1495 |
+
},
|
| 1496 |
+
"US": {
|
| 1497 |
+
"accuracy": 1.0,
|
| 1498 |
+
"count": 194
|
| 1499 |
+
}
|
| 1500 |
+
}
|
| 1501 |
+
},
|
| 1502 |
+
"add_C6": {
|
| 1503 |
+
"full_accuracy": 1.0,
|
| 1504 |
+
"n_examples": 100,
|
| 1505 |
+
"per_subtask": {
|
| 1506 |
+
"SC": {
|
| 1507 |
+
"accuracy": 1.0,
|
| 1508 |
+
"count": 100
|
| 1509 |
+
},
|
| 1510 |
+
"UC": {
|
| 1511 |
+
"accuracy": 1.0,
|
| 1512 |
+
"count": 366
|
| 1513 |
+
},
|
| 1514 |
+
"US": {
|
| 1515 |
+
"accuracy": 1.0,
|
| 1516 |
+
"count": 234
|
| 1517 |
+
}
|
| 1518 |
+
}
|
| 1519 |
+
},
|
| 1520 |
+
"sub_M0": {
|
| 1521 |
+
"full_accuracy": 1.0,
|
| 1522 |
+
"n_examples": 100,
|
| 1523 |
+
"per_subtask": {
|
| 1524 |
+
"MD": {
|
| 1525 |
+
"accuracy": 1.0,
|
| 1526 |
+
"count": 601
|
| 1527 |
+
},
|
| 1528 |
+
"ME": {
|
| 1529 |
+
"accuracy": 1.0,
|
| 1530 |
+
"count": 99
|
| 1531 |
+
}
|
| 1532 |
+
}
|
| 1533 |
+
},
|
| 1534 |
+
"sub_M1": {
|
| 1535 |
+
"full_accuracy": 1.0,
|
| 1536 |
+
"n_examples": 100,
|
| 1537 |
+
"per_subtask": {
|
| 1538 |
+
"MD": {
|
| 1539 |
+
"accuracy": 1.0,
|
| 1540 |
+
"count": 279
|
| 1541 |
+
},
|
| 1542 |
+
"MB": {
|
| 1543 |
+
"accuracy": 1.0,
|
| 1544 |
+
"count": 145
|
| 1545 |
+
},
|
| 1546 |
+
"ME": {
|
| 1547 |
+
"accuracy": 1.0,
|
| 1548 |
+
"count": 24
|
| 1549 |
+
},
|
| 1550 |
+
"UB": {
|
| 1551 |
+
"accuracy": 1.0,
|
| 1552 |
+
"count": 252
|
| 1553 |
+
}
|
| 1554 |
+
}
|
| 1555 |
+
},
|
| 1556 |
+
"sub_M2": {
|
| 1557 |
+
"full_accuracy": 1.0,
|
| 1558 |
+
"n_examples": 100,
|
| 1559 |
+
"per_subtask": {
|
| 1560 |
+
"MD": {
|
| 1561 |
+
"accuracy": 1.0,
|
| 1562 |
+
"count": 213
|
| 1563 |
+
},
|
| 1564 |
+
"MB": {
|
| 1565 |
+
"accuracy": 1.0,
|
| 1566 |
+
"count": 113
|
| 1567 |
+
},
|
| 1568 |
+
"ME": {
|
| 1569 |
+
"accuracy": 1.0,
|
| 1570 |
+
"count": 85
|
| 1571 |
+
},
|
| 1572 |
+
"UB": {
|
| 1573 |
+
"accuracy": 1.0,
|
| 1574 |
+
"count": 181
|
| 1575 |
+
},
|
| 1576 |
+
"UD": {
|
| 1577 |
+
"accuracy": 1.0,
|
| 1578 |
+
"count": 108
|
| 1579 |
+
}
|
| 1580 |
+
}
|
| 1581 |
+
},
|
| 1582 |
+
"sub_M3": {
|
| 1583 |
+
"full_accuracy": 1.0,
|
| 1584 |
+
"n_examples": 100,
|
| 1585 |
+
"per_subtask": {
|
| 1586 |
+
"MD": {
|
| 1587 |
+
"accuracy": 1.0,
|
| 1588 |
+
"count": 179
|
| 1589 |
+
},
|
| 1590 |
+
"MB": {
|
| 1591 |
+
"accuracy": 1.0,
|
| 1592 |
+
"count": 103
|
| 1593 |
+
},
|
| 1594 |
+
"ME": {
|
| 1595 |
+
"accuracy": 1.0,
|
| 1596 |
+
"count": 56
|
| 1597 |
+
},
|
| 1598 |
+
"UB": {
|
| 1599 |
+
"accuracy": 1.0,
|
| 1600 |
+
"count": 149
|
| 1601 |
+
},
|
| 1602 |
+
"UD": {
|
| 1603 |
+
"accuracy": 1.0,
|
| 1604 |
+
"count": 213
|
| 1605 |
+
}
|
| 1606 |
+
}
|
| 1607 |
+
},
|
| 1608 |
+
"sub_M4": {
|
| 1609 |
+
"full_accuracy": 1.0,
|
| 1610 |
+
"n_examples": 100,
|
| 1611 |
+
"per_subtask": {
|
| 1612 |
+
"MD": {
|
| 1613 |
+
"accuracy": 1.0,
|
| 1614 |
+
"count": 200
|
| 1615 |
+
},
|
| 1616 |
+
"MB": {
|
| 1617 |
+
"accuracy": 1.0,
|
| 1618 |
+
"count": 100
|
| 1619 |
+
},
|
| 1620 |
+
"UB": {
|
| 1621 |
+
"accuracy": 1.0,
|
| 1622 |
+
"count": 100
|
| 1623 |
+
},
|
| 1624 |
+
"UD": {
|
| 1625 |
+
"accuracy": 1.0,
|
| 1626 |
+
"count": 300
|
| 1627 |
+
}
|
| 1628 |
+
}
|
| 1629 |
+
},
|
| 1630 |
+
"sub_M5": {
|
| 1631 |
+
"full_accuracy": 1.0,
|
| 1632 |
+
"n_examples": 100,
|
| 1633 |
+
"per_subtask": {
|
| 1634 |
+
"MD": {
|
| 1635 |
+
"accuracy": 1.0,
|
| 1636 |
+
"count": 100
|
| 1637 |
+
},
|
| 1638 |
+
"MB": {
|
| 1639 |
+
"accuracy": 1.0,
|
| 1640 |
+
"count": 100
|
| 1641 |
+
},
|
| 1642 |
+
"UB": {
|
| 1643 |
+
"accuracy": 1.0,
|
| 1644 |
+
"count": 100
|
| 1645 |
+
},
|
| 1646 |
+
"UD": {
|
| 1647 |
+
"accuracy": 1.0,
|
| 1648 |
+
"count": 400
|
| 1649 |
+
}
|
| 1650 |
+
}
|
| 1651 |
+
},
|
| 1652 |
+
"sub_random": {
|
| 1653 |
+
"full_accuracy": 1.0,
|
| 1654 |
+
"n_examples": 200,
|
| 1655 |
+
"per_subtask": {
|
| 1656 |
+
"MD": {
|
| 1657 |
+
"accuracy": 1.0,
|
| 1658 |
+
"count": 600
|
| 1659 |
+
},
|
| 1660 |
+
"MB": {
|
| 1661 |
+
"accuracy": 1.0,
|
| 1662 |
+
"count": 267
|
| 1663 |
+
},
|
| 1664 |
+
"ME": {
|
| 1665 |
+
"accuracy": 1.0,
|
| 1666 |
+
"count": 53
|
| 1667 |
+
},
|
| 1668 |
+
"UB": {
|
| 1669 |
+
"accuracy": 1.0,
|
| 1670 |
+
"count": 439
|
| 1671 |
+
},
|
| 1672 |
+
"UD": {
|
| 1673 |
+
"accuracy": 1.0,
|
| 1674 |
+
"count": 41
|
| 1675 |
+
}
|
| 1676 |
+
}
|
| 1677 |
+
},
|
| 1678 |
+
"sub_B3": {
|
| 1679 |
+
"full_accuracy": 1.0,
|
| 1680 |
+
"n_examples": 100,
|
| 1681 |
+
"per_subtask": {
|
| 1682 |
+
"MD": {
|
| 1683 |
+
"accuracy": 1.0,
|
| 1684 |
+
"count": 300
|
| 1685 |
+
},
|
| 1686 |
+
"MB": {
|
| 1687 |
+
"accuracy": 1.0,
|
| 1688 |
+
"count": 100
|
| 1689 |
+
},
|
| 1690 |
+
"UB": {
|
| 1691 |
+
"accuracy": 1.0,
|
| 1692 |
+
"count": 197
|
| 1693 |
+
},
|
| 1694 |
+
"UD": {
|
| 1695 |
+
"accuracy": 1.0,
|
| 1696 |
+
"count": 103
|
| 1697 |
+
}
|
| 1698 |
+
}
|
| 1699 |
+
},
|
| 1700 |
+
"sub_B4": {
|
| 1701 |
+
"full_accuracy": 1.0,
|
| 1702 |
+
"n_examples": 100,
|
| 1703 |
+
"per_subtask": {
|
| 1704 |
+
"MD": {
|
| 1705 |
+
"accuracy": 1.0,
|
| 1706 |
+
"count": 200
|
| 1707 |
+
},
|
| 1708 |
+
"MB": {
|
| 1709 |
+
"accuracy": 1.0,
|
| 1710 |
+
"count": 100
|
| 1711 |
+
},
|
| 1712 |
+
"UB": {
|
| 1713 |
+
"accuracy": 1.0,
|
| 1714 |
+
"count": 247
|
| 1715 |
+
},
|
| 1716 |
+
"UD": {
|
| 1717 |
+
"accuracy": 1.0,
|
| 1718 |
+
"count": 153
|
| 1719 |
+
}
|
| 1720 |
+
}
|
| 1721 |
+
},
|
| 1722 |
+
"sub_B5": {
|
| 1723 |
+
"full_accuracy": 1.0,
|
| 1724 |
+
"n_examples": 100,
|
| 1725 |
+
"per_subtask": {
|
| 1726 |
+
"MD": {
|
| 1727 |
+
"accuracy": 1.0,
|
| 1728 |
+
"count": 100
|
| 1729 |
+
},
|
| 1730 |
+
"MB": {
|
| 1731 |
+
"accuracy": 1.0,
|
| 1732 |
+
"count": 100
|
| 1733 |
+
},
|
| 1734 |
+
"UB": {
|
| 1735 |
+
"accuracy": 1.0,
|
| 1736 |
+
"count": 298
|
| 1737 |
+
},
|
| 1738 |
+
"UD": {
|
| 1739 |
+
"accuracy": 1.0,
|
| 1740 |
+
"count": 202
|
| 1741 |
+
}
|
| 1742 |
+
}
|
| 1743 |
+
}
|
| 1744 |
+
},
|
| 1745 |
+
"summary": {
|
| 1746 |
+
"overall_accuracy": 0.9995833333333334,
|
| 1747 |
+
"total_examples": 2400,
|
| 1748 |
+
"n_splits": 22
|
| 1749 |
+
}
|
| 1750 |
+
},
|
| 1751 |
+
"sorl_eval": {
|
| 1752 |
+
"config": {
|
| 1753 |
+
"ops": "add_sub",
|
| 1754 |
+
"K": 1,
|
| 1755 |
+
"mode": "sorl",
|
| 1756 |
+
"n_digits": 6,
|
| 1757 |
+
"n_per_split": 100
|
| 1758 |
+
},
|
| 1759 |
+
"splits": {
|
| 1760 |
+
"add_S0": {
|
| 1761 |
+
"full_accuracy": 1.0,
|
| 1762 |
+
"n_examples": 100,
|
| 1763 |
+
"per_subtask": {
|
| 1764 |
+
"SA": {
|
| 1765 |
+
"accuracy": 1.0,
|
| 1766 |
+
"count": 605
|
| 1767 |
+
},
|
| 1768 |
+
"SS": {
|
| 1769 |
+
"accuracy": 1.0,
|
| 1770 |
+
"count": 95
|
| 1771 |
+
}
|
| 1772 |
+
}
|
| 1773 |
+
},
|
| 1774 |
+
"add_S1": {
|
| 1775 |
+
"full_accuracy": 1.0,
|
| 1776 |
+
"n_examples": 100,
|
| 1777 |
+
"per_subtask": {
|
| 1778 |
+
"SA": {
|
| 1779 |
+
"accuracy": 1.0,
|
| 1780 |
+
"count": 204
|
| 1781 |
+
},
|
| 1782 |
+
"SC": {
|
| 1783 |
+
"accuracy": 1.0,
|
| 1784 |
+
"count": 169
|
| 1785 |
+
},
|
| 1786 |
+
"SS": {
|
| 1787 |
+
"accuracy": 1.0,
|
| 1788 |
+
"count": 31
|
| 1789 |
+
},
|
| 1790 |
+
"UC": {
|
| 1791 |
+
"accuracy": 1.0,
|
| 1792 |
+
"count": 296
|
| 1793 |
+
}
|
| 1794 |
+
}
|
| 1795 |
+
},
|
| 1796 |
+
"add_S2": {
|
| 1797 |
+
"full_accuracy": 1.0,
|
| 1798 |
+
"n_examples": 100,
|
| 1799 |
+
"per_subtask": {
|
| 1800 |
+
"SA": {
|
| 1801 |
+
"accuracy": 1.0,
|
| 1802 |
+
"count": 163
|
| 1803 |
+
},
|
| 1804 |
+
"SC": {
|
| 1805 |
+
"accuracy": 1.0,
|
| 1806 |
+
"count": 130
|
| 1807 |
+
},
|
| 1808 |
+
"SS": {
|
| 1809 |
+
"accuracy": 1.0,
|
| 1810 |
+
"count": 87
|
| 1811 |
+
},
|
| 1812 |
+
"UC": {
|
| 1813 |
+
"accuracy": 1.0,
|
| 1814 |
+
"count": 203
|
| 1815 |
+
},
|
| 1816 |
+
"US": {
|
| 1817 |
+
"accuracy": 1.0,
|
| 1818 |
+
"count": 117
|
| 1819 |
+
}
|
| 1820 |
+
}
|
| 1821 |
+
},
|
| 1822 |
+
"add_S3": {
|
| 1823 |
+
"full_accuracy": 1.0,
|
| 1824 |
+
"n_examples": 100,
|
| 1825 |
+
"per_subtask": {
|
| 1826 |
+
"SA": {
|
| 1827 |
+
"accuracy": 1.0,
|
| 1828 |
+
"count": 121
|
| 1829 |
+
},
|
| 1830 |
+
"SC": {
|
| 1831 |
+
"accuracy": 1.0,
|
| 1832 |
+
"count": 121
|
| 1833 |
+
},
|
| 1834 |
+
"SS": {
|
| 1835 |
+
"accuracy": 1.0,
|
| 1836 |
+
"count": 49
|
| 1837 |
+
},
|
| 1838 |
+
"UC": {
|
| 1839 |
+
"accuracy": 1.0,
|
| 1840 |
+
"count": 186
|
| 1841 |
+
},
|
| 1842 |
+
"US": {
|
| 1843 |
+
"accuracy": 1.0,
|
| 1844 |
+
"count": 223
|
| 1845 |
+
}
|
| 1846 |
+
}
|
| 1847 |
+
},
|
| 1848 |
+
"add_S4": {
|
| 1849 |
+
"full_accuracy": 1.0,
|
| 1850 |
+
"n_examples": 100,
|
| 1851 |
+
"per_subtask": {
|
| 1852 |
+
"SA": {
|
| 1853 |
+
"accuracy": 1.0,
|
| 1854 |
+
"count": 104
|
| 1855 |
+
},
|
| 1856 |
+
"SC": {
|
| 1857 |
+
"accuracy": 1.0,
|
| 1858 |
+
"count": 106
|
| 1859 |
+
},
|
| 1860 |
+
"SS": {
|
| 1861 |
+
"accuracy": 1.0,
|
| 1862 |
+
"count": 23
|
| 1863 |
+
},
|
| 1864 |
+
"UC": {
|
| 1865 |
+
"accuracy": 1.0,
|
| 1866 |
+
"count": 160
|
| 1867 |
+
},
|
| 1868 |
+
"US": {
|
| 1869 |
+
"accuracy": 1.0,
|
| 1870 |
+
"count": 307
|
| 1871 |
+
}
|
| 1872 |
+
}
|
| 1873 |
+
},
|
| 1874 |
+
"add_S5": {
|
| 1875 |
+
"full_accuracy": 1.0,
|
| 1876 |
+
"n_examples": 100,
|
| 1877 |
+
"per_subtask": {
|
| 1878 |
+
"SA": {
|
| 1879 |
+
"accuracy": 1.0,
|
| 1880 |
+
"count": 100
|
| 1881 |
+
},
|
| 1882 |
+
"SC": {
|
| 1883 |
+
"accuracy": 1.0,
|
| 1884 |
+
"count": 100
|
| 1885 |
+
},
|
| 1886 |
+
"UC": {
|
| 1887 |
+
"accuracy": 1.0,
|
| 1888 |
+
"count": 100
|
| 1889 |
+
},
|
| 1890 |
+
"US": {
|
| 1891 |
+
"accuracy": 1.0,
|
| 1892 |
+
"count": 400
|
| 1893 |
+
}
|
| 1894 |
+
}
|
| 1895 |
+
},
|
| 1896 |
+
"add_S6": {
|
| 1897 |
+
"full_accuracy": 1.0,
|
| 1898 |
+
"n_examples": 100,
|
| 1899 |
+
"per_subtask": {
|
| 1900 |
+
"SC": {
|
| 1901 |
+
"accuracy": 1.0,
|
| 1902 |
+
"count": 100
|
| 1903 |
+
},
|
| 1904 |
+
"UC": {
|
| 1905 |
+
"accuracy": 1.0,
|
| 1906 |
+
"count": 100
|
| 1907 |
+
},
|
| 1908 |
+
"US": {
|
| 1909 |
+
"accuracy": 1.0,
|
| 1910 |
+
"count": 500
|
| 1911 |
+
}
|
| 1912 |
+
}
|
| 1913 |
+
},
|
| 1914 |
+
"add_random": {
|
| 1915 |
+
"full_accuracy": 1.0,
|
| 1916 |
+
"n_examples": 200,
|
| 1917 |
+
"per_subtask": {
|
| 1918 |
+
"SA": {
|
| 1919 |
+
"accuracy": 1.0,
|
| 1920 |
+
"count": 447
|
| 1921 |
+
},
|
| 1922 |
+
"SC": {
|
| 1923 |
+
"accuracy": 1.0,
|
| 1924 |
+
"count": 320
|
| 1925 |
+
},
|
| 1926 |
+
"SS": {
|
| 1927 |
+
"accuracy": 1.0,
|
| 1928 |
+
"count": 56
|
| 1929 |
+
},
|
| 1930 |
+
"UC": {
|
| 1931 |
+
"accuracy": 1.0,
|
| 1932 |
+
"count": 529
|
| 1933 |
+
},
|
| 1934 |
+
"US": {
|
| 1935 |
+
"accuracy": 1.0,
|
| 1936 |
+
"count": 48
|
| 1937 |
+
}
|
| 1938 |
+
}
|
| 1939 |
+
},
|
| 1940 |
+
"add_C3": {
|
| 1941 |
+
"full_accuracy": 1.0,
|
| 1942 |
+
"n_examples": 100,
|
| 1943 |
+
"per_subtask": {
|
| 1944 |
+
"SA": {
|
| 1945 |
+
"accuracy": 1.0,
|
| 1946 |
+
"count": 300
|
| 1947 |
+
},
|
| 1948 |
+
"SC": {
|
| 1949 |
+
"accuracy": 1.0,
|
| 1950 |
+
"count": 100
|
| 1951 |
+
},
|
| 1952 |
+
"UC": {
|
| 1953 |
+
"accuracy": 1.0,
|
| 1954 |
+
"count": 193
|
| 1955 |
+
},
|
| 1956 |
+
"US": {
|
| 1957 |
+
"accuracy": 1.0,
|
| 1958 |
+
"count": 107
|
| 1959 |
+
}
|
| 1960 |
+
}
|
| 1961 |
+
},
|
| 1962 |
+
"add_C4": {
|
| 1963 |
+
"full_accuracy": 1.0,
|
| 1964 |
+
"n_examples": 100,
|
| 1965 |
+
"per_subtask": {
|
| 1966 |
+
"SA": {
|
| 1967 |
+
"accuracy": 1.0,
|
| 1968 |
+
"count": 200
|
| 1969 |
+
},
|
| 1970 |
+
"SC": {
|
| 1971 |
+
"accuracy": 1.0,
|
| 1972 |
+
"count": 100
|
| 1973 |
+
},
|
| 1974 |
+
"UC": {
|
| 1975 |
+
"accuracy": 1.0,
|
| 1976 |
+
"count": 256
|
| 1977 |
+
},
|
| 1978 |
+
"US": {
|
| 1979 |
+
"accuracy": 1.0,
|
| 1980 |
+
"count": 144
|
| 1981 |
+
}
|
| 1982 |
+
}
|
| 1983 |
+
},
|
| 1984 |
+
"add_C5": {
|
| 1985 |
+
"full_accuracy": 1.0,
|
| 1986 |
+
"n_examples": 100,
|
| 1987 |
+
"per_subtask": {
|
| 1988 |
+
"SA": {
|
| 1989 |
+
"accuracy": 1.0,
|
| 1990 |
+
"count": 100
|
| 1991 |
+
},
|
| 1992 |
+
"SC": {
|
| 1993 |
+
"accuracy": 1.0,
|
| 1994 |
+
"count": 100
|
| 1995 |
+
},
|
| 1996 |
+
"UC": {
|
| 1997 |
+
"accuracy": 1.0,
|
| 1998 |
+
"count": 306
|
| 1999 |
+
},
|
| 2000 |
+
"US": {
|
| 2001 |
+
"accuracy": 1.0,
|
| 2002 |
+
"count": 194
|
| 2003 |
+
}
|
| 2004 |
+
}
|
| 2005 |
+
},
|
| 2006 |
+
"add_C6": {
|
| 2007 |
+
"full_accuracy": 1.0,
|
| 2008 |
+
"n_examples": 100,
|
| 2009 |
+
"per_subtask": {
|
| 2010 |
+
"SC": {
|
| 2011 |
+
"accuracy": 1.0,
|
| 2012 |
+
"count": 100
|
| 2013 |
+
},
|
| 2014 |
+
"UC": {
|
| 2015 |
+
"accuracy": 1.0,
|
| 2016 |
+
"count": 366
|
| 2017 |
+
},
|
| 2018 |
+
"US": {
|
| 2019 |
+
"accuracy": 1.0,
|
| 2020 |
+
"count": 234
|
| 2021 |
+
}
|
| 2022 |
+
}
|
| 2023 |
+
},
|
| 2024 |
+
"sub_M0": {
|
| 2025 |
+
"full_accuracy": 1.0,
|
| 2026 |
+
"n_examples": 100,
|
| 2027 |
+
"per_subtask": {
|
| 2028 |
+
"MD": {
|
| 2029 |
+
"accuracy": 1.0,
|
| 2030 |
+
"count": 601
|
| 2031 |
+
},
|
| 2032 |
+
"ME": {
|
| 2033 |
+
"accuracy": 1.0,
|
| 2034 |
+
"count": 99
|
| 2035 |
+
}
|
| 2036 |
+
}
|
| 2037 |
+
},
|
| 2038 |
+
"sub_M1": {
|
| 2039 |
+
"full_accuracy": 1.0,
|
| 2040 |
+
"n_examples": 100,
|
| 2041 |
+
"per_subtask": {
|
| 2042 |
+
"MD": {
|
| 2043 |
+
"accuracy": 1.0,
|
| 2044 |
+
"count": 279
|
| 2045 |
+
},
|
| 2046 |
+
"MB": {
|
| 2047 |
+
"accuracy": 1.0,
|
| 2048 |
+
"count": 145
|
| 2049 |
+
},
|
| 2050 |
+
"ME": {
|
| 2051 |
+
"accuracy": 1.0,
|
| 2052 |
+
"count": 24
|
| 2053 |
+
},
|
| 2054 |
+
"UB": {
|
| 2055 |
+
"accuracy": 1.0,
|
| 2056 |
+
"count": 252
|
| 2057 |
+
}
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"sub_M2": {
|
| 2061 |
+
"full_accuracy": 1.0,
|
| 2062 |
+
"n_examples": 100,
|
| 2063 |
+
"per_subtask": {
|
| 2064 |
+
"MD": {
|
| 2065 |
+
"accuracy": 1.0,
|
| 2066 |
+
"count": 213
|
| 2067 |
+
},
|
| 2068 |
+
"MB": {
|
| 2069 |
+
"accuracy": 1.0,
|
| 2070 |
+
"count": 113
|
| 2071 |
+
},
|
| 2072 |
+
"ME": {
|
| 2073 |
+
"accuracy": 1.0,
|
| 2074 |
+
"count": 85
|
| 2075 |
+
},
|
| 2076 |
+
"UB": {
|
| 2077 |
+
"accuracy": 1.0,
|
| 2078 |
+
"count": 181
|
| 2079 |
+
},
|
| 2080 |
+
"UD": {
|
| 2081 |
+
"accuracy": 1.0,
|
| 2082 |
+
"count": 108
|
| 2083 |
+
}
|
| 2084 |
+
}
|
| 2085 |
+
},
|
| 2086 |
+
"sub_M3": {
|
| 2087 |
+
"full_accuracy": 1.0,
|
| 2088 |
+
"n_examples": 100,
|
| 2089 |
+
"per_subtask": {
|
| 2090 |
+
"MD": {
|
| 2091 |
+
"accuracy": 1.0,
|
| 2092 |
+
"count": 179
|
| 2093 |
+
},
|
| 2094 |
+
"MB": {
|
| 2095 |
+
"accuracy": 1.0,
|
| 2096 |
+
"count": 103
|
| 2097 |
+
},
|
| 2098 |
+
"ME": {
|
| 2099 |
+
"accuracy": 1.0,
|
| 2100 |
+
"count": 56
|
| 2101 |
+
},
|
| 2102 |
+
"UB": {
|
| 2103 |
+
"accuracy": 1.0,
|
| 2104 |
+
"count": 149
|
| 2105 |
+
},
|
| 2106 |
+
"UD": {
|
| 2107 |
+
"accuracy": 1.0,
|
| 2108 |
+
"count": 213
|
| 2109 |
+
}
|
| 2110 |
+
}
|
| 2111 |
+
},
|
| 2112 |
+
"sub_M4": {
|
| 2113 |
+
"full_accuracy": 1.0,
|
| 2114 |
+
"n_examples": 100,
|
| 2115 |
+
"per_subtask": {
|
| 2116 |
+
"MD": {
|
| 2117 |
+
"accuracy": 1.0,
|
| 2118 |
+
"count": 200
|
| 2119 |
+
},
|
| 2120 |
+
"MB": {
|
| 2121 |
+
"accuracy": 1.0,
|
| 2122 |
+
"count": 100
|
| 2123 |
+
},
|
| 2124 |
+
"UB": {
|
| 2125 |
+
"accuracy": 1.0,
|
| 2126 |
+
"count": 100
|
| 2127 |
+
},
|
| 2128 |
+
"UD": {
|
| 2129 |
+
"accuracy": 1.0,
|
| 2130 |
+
"count": 300
|
| 2131 |
+
}
|
| 2132 |
+
}
|
| 2133 |
+
},
|
| 2134 |
+
"sub_M5": {
|
| 2135 |
+
"full_accuracy": 1.0,
|
| 2136 |
+
"n_examples": 100,
|
| 2137 |
+
"per_subtask": {
|
| 2138 |
+
"MD": {
|
| 2139 |
+
"accuracy": 1.0,
|
| 2140 |
+
"count": 100
|
| 2141 |
+
},
|
| 2142 |
+
"MB": {
|
| 2143 |
+
"accuracy": 1.0,
|
| 2144 |
+
"count": 100
|
| 2145 |
+
},
|
| 2146 |
+
"UB": {
|
| 2147 |
+
"accuracy": 1.0,
|
| 2148 |
+
"count": 100
|
| 2149 |
+
},
|
| 2150 |
+
"UD": {
|
| 2151 |
+
"accuracy": 1.0,
|
| 2152 |
+
"count": 400
|
| 2153 |
+
}
|
| 2154 |
+
}
|
| 2155 |
+
},
|
| 2156 |
+
"sub_random": {
|
| 2157 |
+
"full_accuracy": 1.0,
|
| 2158 |
+
"n_examples": 200,
|
| 2159 |
+
"per_subtask": {
|
| 2160 |
+
"MD": {
|
| 2161 |
+
"accuracy": 1.0,
|
| 2162 |
+
"count": 600
|
| 2163 |
+
},
|
| 2164 |
+
"MB": {
|
| 2165 |
+
"accuracy": 1.0,
|
| 2166 |
+
"count": 267
|
| 2167 |
+
},
|
| 2168 |
+
"ME": {
|
| 2169 |
+
"accuracy": 1.0,
|
| 2170 |
+
"count": 53
|
| 2171 |
+
},
|
| 2172 |
+
"UB": {
|
| 2173 |
+
"accuracy": 1.0,
|
| 2174 |
+
"count": 439
|
| 2175 |
+
},
|
| 2176 |
+
"UD": {
|
| 2177 |
+
"accuracy": 1.0,
|
| 2178 |
+
"count": 41
|
| 2179 |
+
}
|
| 2180 |
+
}
|
| 2181 |
+
},
|
| 2182 |
+
"sub_B3": {
|
| 2183 |
+
"full_accuracy": 1.0,
|
| 2184 |
+
"n_examples": 100,
|
| 2185 |
+
"per_subtask": {
|
| 2186 |
+
"MD": {
|
| 2187 |
+
"accuracy": 1.0,
|
| 2188 |
+
"count": 300
|
| 2189 |
+
},
|
| 2190 |
+
"MB": {
|
| 2191 |
+
"accuracy": 1.0,
|
| 2192 |
+
"count": 100
|
| 2193 |
+
},
|
| 2194 |
+
"UB": {
|
| 2195 |
+
"accuracy": 1.0,
|
| 2196 |
+
"count": 197
|
| 2197 |
+
},
|
| 2198 |
+
"UD": {
|
| 2199 |
+
"accuracy": 1.0,
|
| 2200 |
+
"count": 103
|
| 2201 |
+
}
|
| 2202 |
+
}
|
| 2203 |
+
},
|
| 2204 |
+
"sub_B4": {
|
| 2205 |
+
"full_accuracy": 1.0,
|
| 2206 |
+
"n_examples": 100,
|
| 2207 |
+
"per_subtask": {
|
| 2208 |
+
"MD": {
|
| 2209 |
+
"accuracy": 1.0,
|
| 2210 |
+
"count": 200
|
| 2211 |
+
},
|
| 2212 |
+
"MB": {
|
| 2213 |
+
"accuracy": 1.0,
|
| 2214 |
+
"count": 100
|
| 2215 |
+
},
|
| 2216 |
+
"UB": {
|
| 2217 |
+
"accuracy": 1.0,
|
| 2218 |
+
"count": 247
|
| 2219 |
+
},
|
| 2220 |
+
"UD": {
|
| 2221 |
+
"accuracy": 1.0,
|
| 2222 |
+
"count": 153
|
| 2223 |
+
}
|
| 2224 |
+
}
|
| 2225 |
+
},
|
| 2226 |
+
"sub_B5": {
|
| 2227 |
+
"full_accuracy": 1.0,
|
| 2228 |
+
"n_examples": 100,
|
| 2229 |
+
"per_subtask": {
|
| 2230 |
+
"MD": {
|
| 2231 |
+
"accuracy": 1.0,
|
| 2232 |
+
"count": 100
|
| 2233 |
+
},
|
| 2234 |
+
"MB": {
|
| 2235 |
+
"accuracy": 1.0,
|
| 2236 |
+
"count": 100
|
| 2237 |
+
},
|
| 2238 |
+
"UB": {
|
| 2239 |
+
"accuracy": 1.0,
|
| 2240 |
+
"count": 298
|
| 2241 |
+
},
|
| 2242 |
+
"UD": {
|
| 2243 |
+
"accuracy": 1.0,
|
| 2244 |
+
"count": 202
|
| 2245 |
+
}
|
| 2246 |
+
}
|
| 2247 |
+
}
|
| 2248 |
+
},
|
| 2249 |
+
"summary": {
|
| 2250 |
+
"overall_accuracy": 1.0,
|
| 2251 |
+
"total_examples": 2400,
|
| 2252 |
+
"n_splits": 22
|
| 2253 |
+
}
|
| 2254 |
+
},
|
| 2255 |
+
"sorl_overall_accuracy": 1.0,
|
| 2256 |
+
"sft_overall_accuracy": 0.9995833333333334
|
| 2257 |
+
}
|
add_sub_sorl_v1_abs50_K1_50K/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b974b054eac92dde90bb7e02878e774beaa0bdf6eab8cd77fc534d92a0beb4cd
|
| 3 |
+
size 650466940
|
add_sub_sorl_v1_abs50_K1_50K/train_config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_rollouts": 4,
|
| 3 |
+
"K": 1,
|
| 4 |
+
"max_iterations": 2,
|
| 5 |
+
"memory_span_abs": 1792,
|
| 6 |
+
"memory_span_traj": 1792,
|
| 7 |
+
"temperature": 1.0,
|
| 8 |
+
"ar_search": false,
|
| 9 |
+
"response_only_abs": false,
|
| 10 |
+
"alpha_info_gain": 10.0,
|
| 11 |
+
"alpha_abs": 0.1,
|
| 12 |
+
"alpha_soft_zipf": 1.0,
|
| 13 |
+
"alpha_ortho": 0.0,
|
| 14 |
+
"alpha_anchor": 0.0,
|
| 15 |
+
"alpha_jacobi": 0.0,
|
| 16 |
+
"decay": 0.8,
|
| 17 |
+
"target_vocab_util": 0.8,
|
| 18 |
+
"min_abs_ppl": 0.0,
|
| 19 |
+
"zipf_alpha": 1.0,
|
| 20 |
+
"lr": 4e-05,
|
| 21 |
+
"emb_lr_mult": 1.0,
|
| 22 |
+
"weight_decay": 0.01,
|
| 23 |
+
"warmup_steps": 234,
|
| 24 |
+
"cooldown_frac": 0.4,
|
| 25 |
+
"max_grad_norm": 1.0,
|
| 26 |
+
"vq_abs_pretrain_steps": 0,
|
| 27 |
+
"vq_abs_pretrain_lr": 0.001,
|
| 28 |
+
"vq_abs_pretrain_layer": -1,
|
| 29 |
+
"vq_abs_pretrain_batch_size": 256,
|
| 30 |
+
"vq_abs_pretrain_target_vectors": 20000,
|
| 31 |
+
"batch_size": 64,
|
| 32 |
+
"gradient_accumulation_steps": 1,
|
| 33 |
+
"num_epochs": 10,
|
| 34 |
+
"emb_warmup_steps": 0,
|
| 35 |
+
"log_every": 50,
|
| 36 |
+
"eval_every": 781,
|
| 37 |
+
"save_every": 999999,
|
| 38 |
+
"eval_samples": 100,
|
| 39 |
+
"output_dir": "ckpt/sweep/as_sorl_abs50_K1_50K",
|
| 40 |
+
"eval_K": 4,
|
| 41 |
+
"alpha_traj": 0.0,
|
| 42 |
+
"corrupt_method": "shuffle",
|
| 43 |
+
"corrupt_ratio": 0.3,
|
| 44 |
+
"alpha_contrastive": 1.0,
|
| 45 |
+
"gamma_contrastive": 0.5,
|
| 46 |
+
"alpha_masked_traj": 0.0,
|
| 47 |
+
"mask_nl_ratio": 0.3,
|
| 48 |
+
"mask_nl_mode": "fixed",
|
| 49 |
+
"mask_nl_fixed_id": 0,
|
| 50 |
+
"use_ste": true,
|
| 51 |
+
"n_inner": 1,
|
| 52 |
+
"random_K": null,
|
| 53 |
+
"strip_suffix": null,
|
| 54 |
+
"compress_prefix": null,
|
| 55 |
+
"random_mem_span": null,
|
| 56 |
+
"warmup_ratio": 0.03,
|
| 57 |
+
"beta2": 0.999,
|
| 58 |
+
"seed": 42,
|
| 59 |
+
"n_digits": 6,
|
| 60 |
+
"n_layer": 2,
|
| 61 |
+
"n_head": 3,
|
| 62 |
+
"n_embd": 510,
|
| 63 |
+
"ops": "add_sub",
|
| 64 |
+
"abs_vocab": 50,
|
| 65 |
+
"dataset_size": 50000,
|
| 66 |
+
"mode": "sorl",
|
| 67 |
+
"device": "cuda",
|
| 68 |
+
"push_to_hub": true,
|
| 69 |
+
"no_wandb": false,
|
| 70 |
+
"n_params": 162540062,
|
| 71 |
+
"run_name": "add_sub_sorl_v1_abs50_K1_50K",
|
| 72 |
+
"git_commit": "f447da529caceac8c7d256cbb2cd185cbc50feac",
|
| 73 |
+
"timestamp": "2026-04-12T14:06:38.991781+00:00",
|
| 74 |
+
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
+
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
+
"dataset_config": "add_sub_6digit",
|
| 77 |
+
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
+
"trainer_version": "v1",
|
| 79 |
+
"wandb_run_id": "b21pydm5",
|
| 80 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/b21pydm5",
|
| 81 |
+
"final_accuracy": 1.0,
|
| 82 |
+
"sft_accuracy": 0.9995833333333334,
|
| 83 |
+
"eval_method": "ArithmeticEvaluator"
|
| 84 |
+
}
|