Upload add_sub_sorl_v1_abs10_K1_50K
Browse files
add_sub_sorl_v1_abs10_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": 151654
|
| 37 |
+
}
|
add_sub_sorl_v1_abs10_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_abs10_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 |
+
7.291482925415039,
|
| 157 |
+
4.033167839050293,
|
| 158 |
+
3.4122180938720703,
|
| 159 |
+
3.0403032302856445,
|
| 160 |
+
3.001980781555176,
|
| 161 |
+
2.982646942138672,
|
| 162 |
+
2.7727580070495605,
|
| 163 |
+
2.1000826358795166,
|
| 164 |
+
1.4242171049118042,
|
| 165 |
+
-0.10749959945678711,
|
| 166 |
+
-2.012298583984375,
|
| 167 |
+
-4.46280574798584,
|
| 168 |
+
-6.6882829666137695,
|
| 169 |
+
-7.129601955413818,
|
| 170 |
+
-7.274585723876953,
|
| 171 |
+
-6.2049970626831055,
|
| 172 |
+
-5.417169570922852,
|
| 173 |
+
-4.86923885345459,
|
| 174 |
+
-4.55937385559082,
|
| 175 |
+
-3.540888547897339,
|
| 176 |
+
-4.229403972625732,
|
| 177 |
+
-3.292853832244873,
|
| 178 |
+
-2.741316795349121,
|
| 179 |
+
-3.3925161361694336,
|
| 180 |
+
-2.6337685585021973,
|
| 181 |
+
-2.5086615085601807,
|
| 182 |
+
-2.414508581161499,
|
| 183 |
+
-2.070335865020752,
|
| 184 |
+
-2.396928310394287,
|
| 185 |
+
-1.793986439704895,
|
| 186 |
+
-0.9649119973182678,
|
| 187 |
+
-0.9085626006126404,
|
| 188 |
+
-0.6782669425010681,
|
| 189 |
+
-0.48969733715057373,
|
| 190 |
+
-0.37728095054626465,
|
| 191 |
+
-0.5114427208900452,
|
| 192 |
+
-0.3232823610305786,
|
| 193 |
+
-0.42648670077323914,
|
| 194 |
+
-0.7195917963981628,
|
| 195 |
+
-0.744903028011322,
|
| 196 |
+
-0.6740866899490356,
|
| 197 |
+
-0.33350852131843567,
|
| 198 |
+
-0.27009108662605286,
|
| 199 |
+
-0.26920798420906067,
|
| 200 |
+
-0.22950142621994019,
|
| 201 |
+
-0.26204606890678406,
|
| 202 |
+
-0.29803380370140076,
|
| 203 |
+
-0.30089274048805237,
|
| 204 |
+
-0.17959536612033844,
|
| 205 |
+
-0.2130807489156723,
|
| 206 |
+
-0.26070791482925415,
|
| 207 |
+
-0.23502995073795319,
|
| 208 |
+
-0.14740601181983948,
|
| 209 |
+
-0.12747667729854584,
|
| 210 |
+
-0.16737529635429382,
|
| 211 |
+
-0.2518279254436493,
|
| 212 |
+
-0.1113758385181427,
|
| 213 |
+
-0.09704112261533737,
|
| 214 |
+
0.016159119084477425,
|
| 215 |
+
-0.11811869591474533,
|
| 216 |
+
-0.1814730316400528,
|
| 217 |
+
-0.016289565712213516,
|
| 218 |
+
-0.1350007951259613,
|
| 219 |
+
-0.2632235884666443,
|
| 220 |
+
-0.07215753197669983,
|
| 221 |
+
-0.06786702573299408,
|
| 222 |
+
-0.05473274365067482,
|
| 223 |
+
-0.11306267976760864,
|
| 224 |
+
-0.008685859851539135,
|
| 225 |
+
-0.26242750883102417,
|
| 226 |
+
-0.03735169768333435,
|
| 227 |
+
-0.01853231154382229,
|
| 228 |
+
-0.07519838958978653,
|
| 229 |
+
-0.0790640115737915,
|
| 230 |
+
-0.06906218081712723,
|
| 231 |
+
-0.039443038403987885,
|
| 232 |
+
-0.0738786831498146,
|
| 233 |
+
-0.044155001640319824,
|
| 234 |
+
-0.07805009186267853,
|
| 235 |
+
-0.04168146848678589,
|
| 236 |
+
-0.12484845519065857,
|
| 237 |
+
-0.051792487502098083,
|
| 238 |
+
-0.04258032515645027,
|
| 239 |
+
-0.04226825386285782,
|
| 240 |
+
-0.07702398300170898,
|
| 241 |
+
-0.058789029717445374,
|
| 242 |
+
-0.03826560452580452,
|
| 243 |
+
-0.018153337761759758,
|
| 244 |
+
-0.021531714126467705,
|
| 245 |
+
-0.01795976608991623,
|
| 246 |
+
-0.03070964477956295,
|
| 247 |
+
-0.006802724674344063,
|
| 248 |
+
-0.003459150902926922,
|
| 249 |
+
0.0014321315102279186,
|
| 250 |
+
-0.022512346506118774,
|
| 251 |
+
-0.15685448050498962,
|
| 252 |
+
0.0004717526026070118,
|
| 253 |
+
-0.08908119797706604,
|
| 254 |
+
-0.006331631913781166,
|
| 255 |
+
-0.055951304733753204,
|
| 256 |
+
-0.08887043595314026,
|
| 257 |
+
0.40162384510040283,
|
| 258 |
+
-0.007660364266484976,
|
| 259 |
+
-0.0002518543042242527,
|
| 260 |
+
-0.034914687275886536,
|
| 261 |
+
0.008662399835884571,
|
| 262 |
+
-0.006906072609126568,
|
| 263 |
+
-0.008926203474402428,
|
| 264 |
+
-0.053697872906923294,
|
| 265 |
+
-0.04174011945724487,
|
| 266 |
+
-0.00622951053082943,
|
| 267 |
+
-0.03008740395307541,
|
| 268 |
+
0.0052336109802126884,
|
| 269 |
+
-0.09772835671901703,
|
| 270 |
+
-0.02276228368282318,
|
| 271 |
+
0.0019192327745258808,
|
| 272 |
+
0.004020964726805687,
|
| 273 |
+
0.0033772005699574947,
|
| 274 |
+
0.0018916467670351267,
|
| 275 |
+
-0.00820618774741888,
|
| 276 |
+
0.004954045172780752,
|
| 277 |
+
-0.04910368472337723,
|
| 278 |
+
-0.014934251084923744,
|
| 279 |
+
-0.0010213176719844341,
|
| 280 |
+
-0.01465108897536993,
|
| 281 |
+
0.006254756823182106,
|
| 282 |
+
0.004511718172580004,
|
| 283 |
+
-0.14273616671562195,
|
| 284 |
+
0.005409314297139645,
|
| 285 |
+
-0.026461634784936905,
|
| 286 |
+
0.0013872201088815928,
|
| 287 |
+
0.007202650420367718,
|
| 288 |
+
0.007318790070712566,
|
| 289 |
+
0.005063582677394152,
|
| 290 |
+
0.0029275300912559032,
|
| 291 |
+
0.007748285308480263,
|
| 292 |
+
0.0013876920565962791,
|
| 293 |
+
0.0028375410474836826,
|
| 294 |
+
0.009077148512005806,
|
| 295 |
+
0.0024727603886276484,
|
| 296 |
+
0.0072018057107925415,
|
| 297 |
+
0.0035855781752616167,
|
| 298 |
+
0.004427475389093161,
|
| 299 |
+
0.005288178101181984,
|
| 300 |
+
0.006763830315321684,
|
| 301 |
+
0.007230003830045462,
|
| 302 |
+
0.006502293515950441,
|
| 303 |
+
0.006789479870349169,
|
| 304 |
+
0.0021875742822885513,
|
| 305 |
+
0.0073264106176793575
|
| 306 |
+
],
|
| 307 |
+
"base_loss": [
|
| 308 |
+
6.516536235809326,
|
| 309 |
+
2.4835619926452637,
|
| 310 |
+
1.899435043334961,
|
| 311 |
+
1.8553259372711182,
|
| 312 |
+
1.9413520097732544,
|
| 313 |
+
1.8268587589263916,
|
| 314 |
+
1.7858167886734009,
|
| 315 |
+
1.7588903903961182,
|
| 316 |
+
1.794765830039978,
|
| 317 |
+
1.750693440437317,
|
| 318 |
+
1.748929738998413,
|
| 319 |
+
1.68966543674469,
|
| 320 |
+
1.7001359462738037,
|
| 321 |
+
1.5033057928085327,
|
| 322 |
+
1.4678022861480713,
|
| 323 |
+
1.2599419355392456,
|
| 324 |
+
1.0703829526901245,
|
| 325 |
+
0.9103147387504578,
|
| 326 |
+
0.9035982489585876,
|
| 327 |
+
0.7412249445915222,
|
| 328 |
+
0.7162189483642578,
|
| 329 |
+
0.6284891963005066,
|
| 330 |
+
0.5025827288627625,
|
| 331 |
+
0.5255685448646545,
|
| 332 |
+
0.44132092595100403,
|
| 333 |
+
0.403102844953537,
|
| 334 |
+
0.33637675642967224,
|
| 335 |
+
0.3013179302215576,
|
| 336 |
+
0.3363364040851593,
|
| 337 |
+
0.25080448389053345,
|
| 338 |
+
0.13762901723384857,
|
| 339 |
+
0.13802115619182587,
|
| 340 |
+
0.09735461324453354,
|
| 341 |
+
0.07956259697675705,
|
| 342 |
+
0.06039976328611374,
|
| 343 |
+
0.09545262902975082,
|
| 344 |
+
0.04513740912079811,
|
| 345 |
+
0.05585834011435509,
|
| 346 |
+
0.08786828815937042,
|
| 347 |
+
0.09875041991472244,
|
| 348 |
+
0.08633076399564743,
|
| 349 |
+
0.05746101960539818,
|
| 350 |
+
0.035193223506212234,
|
| 351 |
+
0.03549731522798538,
|
| 352 |
+
0.02876146510243416,
|
| 353 |
+
0.032679636031389236,
|
| 354 |
+
0.04298492148518562,
|
| 355 |
+
0.03797732666134834,
|
| 356 |
+
0.024759531021118164,
|
| 357 |
+
0.0304957814514637,
|
| 358 |
+
0.03193579241633415,
|
| 359 |
+
0.027899155393242836,
|
| 360 |
+
0.01801885850727558,
|
| 361 |
+
0.017517048865556717,
|
| 362 |
+
0.019884327426552773,
|
| 363 |
+
0.03035196103155613,
|
| 364 |
+
0.01430182158946991,
|
| 365 |
+
0.011786989867687225,
|
| 366 |
+
0.018495408818125725,
|
| 367 |
+
0.014813835732638836,
|
| 368 |
+
0.021165570244193077,
|
| 369 |
+
0.00257376697845757,
|
| 370 |
+
0.01620938815176487,
|
| 371 |
+
0.030093954876065254,
|
| 372 |
+
0.008949460461735725,
|
| 373 |
+
0.008293701335787773,
|
| 374 |
+
0.0069602918811142445,
|
| 375 |
+
0.013352221809327602,
|
| 376 |
+
0.00192145979963243,
|
| 377 |
+
0.03061601147055626,
|
| 378 |
+
0.005475928541272879,
|
| 379 |
+
0.00301953568123281,
|
| 380 |
+
0.00922973733395338,
|
| 381 |
+
0.01043914258480072,
|
| 382 |
+
0.008999384008347988,
|
| 383 |
+
0.005764245521277189,
|
| 384 |
+
0.009663080796599388,
|
| 385 |
+
0.005371266044676304,
|
| 386 |
+
0.009819733910262585,
|
| 387 |
+
0.006027544848620892,
|
| 388 |
+
0.014493056572973728,
|
| 389 |
+
0.006732997950166464,
|
| 390 |
+
0.00728581240400672,
|
| 391 |
+
0.006032108794897795,
|
| 392 |
+
0.009137012995779514,
|
| 393 |
+
0.007936102338135242,
|
| 394 |
+
0.005118044558912516,
|
| 395 |
+
0.0029691599775105715,
|
| 396 |
+
0.003965041600167751,
|
| 397 |
+
0.003704359754920006,
|
| 398 |
+
0.004141169600188732,
|
| 399 |
+
0.0015686674742028117,
|
| 400 |
+
0.001501810154877603,
|
| 401 |
+
0.0002402652899036184,
|
| 402 |
+
0.0029597077518701553,
|
| 403 |
+
0.018230454996228218,
|
| 404 |
+
0.0006747310981154442,
|
| 405 |
+
0.010286212898790836,
|
| 406 |
+
0.001309316256083548,
|
| 407 |
+
0.00767873739823699,
|
| 408 |
+
0.010770417749881744,
|
| 409 |
+
0.0008323562215082347,
|
| 410 |
+
0.0013423433993011713,
|
| 411 |
+
0.0005205980269238353,
|
| 412 |
+
0.0044253370724618435,
|
| 413 |
+
9.446766489418224e-05,
|
| 414 |
+
0.0013240036787465215,
|
| 415 |
+
0.0024794754572212696,
|
| 416 |
+
0.007238837890326977,
|
| 417 |
+
0.005449187941849232,
|
| 418 |
+
0.0012252583401277661,
|
| 419 |
+
0.004047301132231951,
|
| 420 |
+
6.462168676080182e-05,
|
| 421 |
+
0.0121733034029603,
|
| 422 |
+
0.0035667994525283575,
|
| 423 |
+
0.0005734098376706243,
|
| 424 |
+
0.0004332214593887329,
|
| 425 |
+
0.0005883773555979133,
|
| 426 |
+
0.000351788941770792,
|
| 427 |
+
0.0014397574122995138,
|
| 428 |
+
0.00022652784537058324,
|
| 429 |
+
0.006164551712572575,
|
| 430 |
+
0.001950864098034799,
|
| 431 |
+
0.0008269333047792315,
|
| 432 |
+
0.002537141088396311,
|
| 433 |
+
2.746866266534198e-05,
|
| 434 |
+
0.00023421202786266804,
|
| 435 |
+
0.016300244256854057,
|
| 436 |
+
0.0003031859523616731,
|
| 437 |
+
0.0032388202380388975,
|
| 438 |
+
0.00036090545472688973,
|
| 439 |
+
0.00011428723519202322,
|
| 440 |
+
0.00010272496001562104,
|
| 441 |
+
0.00026342846103943884,
|
| 442 |
+
7.695650856476277e-05,
|
| 443 |
+
0.00025681612896732986,
|
| 444 |
+
0.0010053400183096528,
|
| 445 |
+
9.518813021713868e-05,
|
| 446 |
+
4.364967389847152e-05,
|
| 447 |
+
9.891855006571859e-05,
|
| 448 |
+
3.729294257936999e-05,
|
| 449 |
+
8.083302236627787e-05,
|
| 450 |
+
0.00014823059609625489,
|
| 451 |
+
3.982062844443135e-05,
|
| 452 |
+
4.8367975978180766e-05,
|
| 453 |
+
3.223081512260251e-05,
|
| 454 |
+
5.926141238887794e-05,
|
| 455 |
+
0.00012397172395139933,
|
| 456 |
+
4.300850923755206e-05,
|
| 457 |
+
2.1748028302681632e-05
|
| 458 |
+
],
|
| 459 |
+
"info_loss": [
|
| 460 |
+
-0.39558982849121094,
|
| 461 |
+
-0.04619121551513672,
|
| 462 |
+
-0.03844738006591797,
|
| 463 |
+
-0.06993865966796875,
|
| 464 |
+
-0.0818336009979248,
|
| 465 |
+
-0.071785569190979,
|
| 466 |
+
-0.08853816986083984,
|
| 467 |
+
-0.15343570709228516,
|
| 468 |
+
-0.2237008810043335,
|
| 469 |
+
-0.37132859230041504,
|
| 470 |
+
-0.5553083419799805,
|
| 471 |
+
-0.78294438123703,
|
| 472 |
+
-0.9912639856338501,
|
| 473 |
+
-1.0034464597702026,
|
| 474 |
+
-1.0093202590942383,
|
| 475 |
+
-0.8740698099136353,
|
| 476 |
+
-0.7721136212348938,
|
| 477 |
+
-0.6993796825408936,
|
| 478 |
+
-0.6589730381965637,
|
| 479 |
+
-0.5287246108055115,
|
| 480 |
+
-0.5838943719863892,
|
| 481 |
+
-0.4729439616203308,
|
| 482 |
+
-0.3963608741760254,
|
| 483 |
+
-0.4527805745601654,
|
| 484 |
+
-0.36455219984054565,
|
| 485 |
+
-0.3377186357975006,
|
| 486 |
+
-0.31269681453704834,
|
| 487 |
+
-0.27766433358192444,
|
| 488 |
+
-0.3063477575778961,
|
| 489 |
+
-0.23108206689357758,
|
| 490 |
+
-0.13183042407035828,
|
| 491 |
+
-0.12639640271663666,
|
| 492 |
+
-0.09110953658819199,
|
| 493 |
+
-0.06630340218544006,
|
| 494 |
+
-0.0564069002866745,
|
| 495 |
+
-0.07329370081424713,
|
| 496 |
+
-0.043559543788433075,
|
| 497 |
+
-0.05424797162413597,
|
| 498 |
+
-0.08596842736005783,
|
| 499 |
+
-0.0910455510020256,
|
| 500 |
+
-0.08357047289609909,
|
| 501 |
+
-0.04377105087041855,
|
| 502 |
+
-0.03403441235423088,
|
| 503 |
+
-0.03457903489470482,
|
| 504 |
+
-0.028307367116212845,
|
| 505 |
+
-0.03156619891524315,
|
| 506 |
+
-0.037180345505476,
|
| 507 |
+
-0.03508739173412323,
|
| 508 |
+
-0.02273467183113098,
|
| 509 |
+
-0.02561572939157486,
|
| 510 |
+
-0.031209608539938927,
|
| 511 |
+
-0.02763480320572853,
|
| 512 |
+
-0.017675096169114113,
|
| 513 |
+
-0.016021262854337692,
|
| 514 |
+
-0.01964615099132061,
|
| 515 |
+
-0.029404595494270325,
|
| 516 |
+
-0.0141890374943614,
|
| 517 |
+
-0.01162042934447527,
|
| 518 |
+
-0.001841643825173378,
|
| 519 |
+
-0.014748577028512955,
|
| 520 |
+
-0.021103857085108757,
|
| 521 |
+
-0.0025317047256976366,
|
| 522 |
+
-0.016158735379576683,
|
| 523 |
+
-0.030070843175053596,
|
| 524 |
+
-0.008906206116080284,
|
| 525 |
+
-0.0082675376906991,
|
| 526 |
+
-0.006873094942420721,
|
| 527 |
+
-0.013306264765560627,
|
| 528 |
+
-0.0018865098245441914,
|
| 529 |
+
-0.030588379129767418,
|
| 530 |
+
-0.005302963312715292,
|
| 531 |
+
-0.0029850159771740437,
|
| 532 |
+
-0.00920331384986639,
|
| 533 |
+
-0.010163646191358566,
|
| 534 |
+
-0.00896731298416853,
|
| 535 |
+
-0.005701817572116852,
|
| 536 |
+
-0.009641165845096111,
|
| 537 |
+
-0.005342759657651186,
|
| 538 |
+
-0.009793885052204132,
|
| 539 |
+
-0.00600464129820466,
|
| 540 |
+
-0.014428073540329933,
|
| 541 |
+
-0.006682424806058407,
|
| 542 |
+
-0.005700113717466593,
|
| 543 |
+
-0.00503776129335165,
|
| 544 |
+
-0.009123606607317924,
|
| 545 |
+
-0.007870280183851719,
|
| 546 |
+
-0.005100195296108723,
|
| 547 |
+
-0.002949395217001438,
|
| 548 |
+
-0.0039481655694544315,
|
| 549 |
+
-0.003691060934215784,
|
| 550 |
+
-0.00412713410332799,
|
| 551 |
+
-0.0015408744802698493,
|
| 552 |
+
-0.0014740722253918648,
|
| 553 |
+
-0.00021267203555908054,
|
| 554 |
+
-0.002890156116336584,
|
| 555 |
+
-0.018215106800198555,
|
| 556 |
+
-0.0006676774355582893,
|
| 557 |
+
-0.0102800028398633,
|
| 558 |
+
-0.0013014374999329448,
|
| 559 |
+
-0.007669177837669849,
|
| 560 |
+
-0.010761483572423458,
|
| 561 |
+
0.03959464281797409,
|
| 562 |
+
-0.0013354456750676036,
|
| 563 |
+
-0.0004929776769131422,
|
| 564 |
+
-0.0044188955798745155,
|
| 565 |
+
-9.018523996928707e-05,
|
| 566 |
+
-0.0013183815171942115,
|
| 567 |
+
-0.0024549937807023525,
|
| 568 |
+
-0.00722320144996047,
|
| 569 |
+
-0.005443317350000143,
|
| 570 |
+
-0.001220099744386971,
|
| 571 |
+
-0.004042269662022591,
|
| 572 |
+
-6.167100218590349e-05,
|
| 573 |
+
-0.012167608365416527,
|
| 574 |
+
-0.0035586960148066282,
|
| 575 |
+
-0.0005662220646627247,
|
| 576 |
+
-0.0004291559162084013,
|
| 577 |
+
-0.0005853284965269268,
|
| 578 |
+
-0.0003490628441795707,
|
| 579 |
+
-0.0014374355087056756,
|
| 580 |
+
-0.00022408299264498055,
|
| 581 |
+
-0.00616141501814127,
|
| 582 |
+
-0.001947026583366096,
|
| 583 |
+
-0.0008238331065513194,
|
| 584 |
+
-0.002534637926146388,
|
| 585 |
+
-2.5075705707422458e-05,
|
| 586 |
+
-0.00023122489801608026,
|
| 587 |
+
-0.0162954144179821,
|
| 588 |
+
-0.0002997294650413096,
|
| 589 |
+
-0.0032353017013520002,
|
| 590 |
+
-0.00035792760900221765,
|
| 591 |
+
-0.00011160584108438343,
|
| 592 |
+
-0.00010035171726485714,
|
| 593 |
+
-0.0002614471595734358,
|
| 594 |
+
-7.487701077479869e-05,
|
| 595 |
+
-0.0002547329058870673,
|
| 596 |
+
-0.0010033685248345137,
|
| 597 |
+
-9.309347660746425e-05,
|
| 598 |
+
-4.177000664640218e-05,
|
| 599 |
+
-9.644340752856806e-05,
|
| 600 |
+
-3.56615346390754e-05,
|
| 601 |
+
-7.872026617405936e-05,
|
| 602 |
+
-0.00014596803521271795,
|
| 603 |
+
-3.823072984232567e-05,
|
| 604 |
+
-4.660113700083457e-05,
|
| 605 |
+
-3.038973045477178e-05,
|
| 606 |
+
-5.761536885984242e-05,
|
| 607 |
+
-0.0001223341969307512,
|
| 608 |
+
-4.1437237086938694e-05,
|
| 609 |
+
-2.0190593204461038e-05
|
| 610 |
+
],
|
| 611 |
+
"abs_loss": [
|
| 612 |
+
2.103454351425171,
|
| 613 |
+
1.8856569528579712,
|
| 614 |
+
1.8366988897323608,
|
| 615 |
+
1.853995680809021,
|
| 616 |
+
1.8650015592575073,
|
| 617 |
+
1.8378944396972656,
|
| 618 |
+
1.8304977416992188,
|
| 619 |
+
1.8361488580703735,
|
| 620 |
+
1.821694016456604,
|
| 621 |
+
1.807782769203186,
|
| 622 |
+
1.6753603219985962,
|
| 623 |
+
1.4515177011489868,
|
| 624 |
+
1.322694182395935,
|
| 625 |
+
1.1485607624053955,
|
| 626 |
+
1.1458325386047363,
|
| 627 |
+
0.9455111622810364,
|
| 628 |
+
0.8843372464179993,
|
| 629 |
+
0.8360934853553772,
|
| 630 |
+
0.7149937748908997,
|
| 631 |
+
0.5886721611022949,
|
| 632 |
+
0.5124597549438477,
|
| 633 |
+
0.43022820353507996,
|
| 634 |
+
0.3434896767139435,
|
| 635 |
+
0.29655787348747253,
|
| 636 |
+
0.26246532797813416,
|
| 637 |
+
0.22259850800037384,
|
| 638 |
+
0.19756682217121124,
|
| 639 |
+
0.22054968774318695,
|
| 640 |
+
0.17242246866226196,
|
| 641 |
+
0.1368202120065689,
|
| 642 |
+
0.1471979171037674,
|
| 643 |
+
0.1158660277724266,
|
| 644 |
+
0.10501883178949356,
|
| 645 |
+
0.08231943845748901,
|
| 646 |
+
0.08551102876663208,
|
| 647 |
+
0.09424110502004623,
|
| 648 |
+
0.06484600156545639,
|
| 649 |
+
0.05951952934265137,
|
| 650 |
+
0.04611345753073692,
|
| 651 |
+
0.05700722336769104,
|
| 652 |
+
0.045443009585142136,
|
| 653 |
+
0.052510228008031845,
|
| 654 |
+
0.04553452134132385,
|
| 655 |
+
0.027561327442526817,
|
| 656 |
+
0.03692733123898506,
|
| 657 |
+
0.029859310016036034,
|
| 658 |
+
0.01610124669969082,
|
| 659 |
+
0.01593116857111454,
|
| 660 |
+
0.012548821978271008,
|
| 661 |
+
0.024183565750718117,
|
| 662 |
+
0.015415686182677746,
|
| 663 |
+
0.008188403211534023,
|
| 664 |
+
0.013608518056571484,
|
| 665 |
+
0.02348317764699459,
|
| 666 |
+
0.02088686265051365,
|
| 667 |
+
0.0142488032579422,
|
| 668 |
+
0.010507809929549694,
|
| 669 |
+
0.011757518164813519,
|
| 670 |
+
0.007792810443788767,
|
| 671 |
+
0.007188592571765184,
|
| 672 |
+
0.012610410340130329,
|
| 673 |
+
0.009439573623239994,
|
| 674 |
+
0.0064491513185203075,
|
| 675 |
+
0.006307272240519524,
|
| 676 |
+
0.0056409514509141445,
|
| 677 |
+
0.006569093093276024,
|
| 678 |
+
0.007965529337525368,
|
| 679 |
+
0.008747314102947712,
|
| 680 |
+
0.010841268114745617,
|
| 681 |
+
0.008278321474790573,
|
| 682 |
+
0.009732459671795368,
|
| 683 |
+
0.010417111217975616,
|
| 684 |
+
0.008557966910302639,
|
| 685 |
+
0.005075481254607439,
|
| 686 |
+
0.001646698801778257,
|
| 687 |
+
0.00539746368303895,
|
| 688 |
+
0.002312362426891923,
|
| 689 |
+
0.004107427317649126,
|
| 690 |
+
0.008200561627745628,
|
| 691 |
+
0.0017948299646377563,
|
| 692 |
+
0.0003762578417081386,
|
| 693 |
+
0.002077900804579258,
|
| 694 |
+
0.006949333474040031,
|
| 695 |
+
0.004756436217576265,
|
| 696 |
+
0.002833310514688492,
|
| 697 |
+
0.0020073887426406145,
|
| 698 |
+
0.006080996710807085,
|
| 699 |
+
0.0006730963359586895,
|
| 700 |
+
0.001914774184115231,
|
| 701 |
+
0.02848239243030548,
|
| 702 |
+
0.008244752883911133,
|
| 703 |
+
0.003306052880361676,
|
| 704 |
+
0.005812538787722588,
|
| 705 |
+
0.0005439592059701681,
|
| 706 |
+
0.0033859622199088335,
|
| 707 |
+
0.00019894744036719203,
|
| 708 |
+
0.003157586557790637,
|
| 709 |
+
0.0017652591923251748,
|
| 710 |
+
0.0005068835453130305,
|
| 711 |
+
0.0009860001737251878,
|
| 712 |
+
0.0002652962866704911,
|
| 713 |
+
0.0014243596233427525,
|
| 714 |
+
0.00014402759552467614,
|
| 715 |
+
0.001731699681840837,
|
| 716 |
+
0.0007810410461388528,
|
| 717 |
+
0.0018737445352599025,
|
| 718 |
+
0.004320906475186348,
|
| 719 |
+
0.007283887360244989,
|
| 720 |
+
0.0010027083335444331,
|
| 721 |
+
0.002329479670152068,
|
| 722 |
+
7.454246951965615e-05,
|
| 723 |
+
0.0003903764591086656,
|
| 724 |
+
0.0004755467234645039,
|
| 725 |
+
0.00022724166046828032,
|
| 726 |
+
8.931435877457261e-05,
|
| 727 |
+
0.0002792776213027537,
|
| 728 |
+
0.0016023950884118676,
|
| 729 |
+
9.345952275907621e-05,
|
| 730 |
+
0.00014107099559623748,
|
| 731 |
+
0.00021528666547965258,
|
| 732 |
+
0.00014757552708033472,
|
| 733 |
+
0.00025952685973607004,
|
| 734 |
+
0.00019442291522864252,
|
| 735 |
+
0.00011387479025870562,
|
| 736 |
+
5.852747199242003e-05,
|
| 737 |
+
0.0016362796304747462,
|
| 738 |
+
5.2294944907771423e-05,
|
| 739 |
+
0.00010021971684182063,
|
| 740 |
+
8.62984816194512e-05,
|
| 741 |
+
0.00018095503037329763,
|
| 742 |
+
0.00010219896648777649,
|
| 743 |
+
0.00011972735956078395,
|
| 744 |
+
6.06870926276315e-05,
|
| 745 |
+
9.31524918996729e-05,
|
| 746 |
+
4.9771664635045454e-05,
|
| 747 |
+
3.388823461136781e-05,
|
| 748 |
+
3.732774348463863e-05,
|
| 749 |
+
4.141781755606644e-05,
|
| 750 |
+
2.3655571567360312e-05,
|
| 751 |
+
0.00012349901953712106,
|
| 752 |
+
2.4177439627237618e-05,
|
| 753 |
+
3.144523725495674e-05,
|
| 754 |
+
3.530609319568612e-05,
|
| 755 |
+
0.00014106860908214003,
|
| 756 |
+
4.612208067555912e-05,
|
| 757 |
+
5.547635373659432e-05,
|
| 758 |
+
5.11908256157767e-05,
|
| 759 |
+
3.4463100746506825e-05,
|
| 760 |
+
4.004925722256303e-05,
|
| 761 |
+
4.555788837024011e-05
|
| 762 |
+
],
|
| 763 |
+
"zipf_loss": [
|
| 764 |
+
4.520499229431152,
|
| 765 |
+
1.822952151298523,
|
| 766 |
+
1.7135869264602661,
|
| 767 |
+
1.6989643573760986,
|
| 768 |
+
1.6924647092819214,
|
| 769 |
+
1.689854383468628,
|
| 770 |
+
1.6892731189727783,
|
| 771 |
+
1.69193434715271,
|
| 772 |
+
1.6842906475067139,
|
| 773 |
+
1.6743146181106567,
|
| 774 |
+
1.6243189573287964,
|
| 775 |
+
1.531821370124817,
|
| 776 |
+
1.3919508457183838,
|
| 777 |
+
1.2867016792297363,
|
| 778 |
+
1.236231803894043,
|
| 779 |
+
1.1812078952789307,
|
| 780 |
+
1.1451495885849,
|
| 781 |
+
1.1306335926055908,
|
| 782 |
+
1.0552587509155273,
|
| 783 |
+
0.9462655186653137,
|
| 784 |
+
0.8420745134353638,
|
| 785 |
+
0.7650742530822754,
|
| 786 |
+
0.6853601336479187,
|
| 787 |
+
0.5800656080245972,
|
| 788 |
+
0.5441861152648926,
|
| 789 |
+
0.44316205382347107,
|
| 790 |
+
0.3563261330127716,
|
| 791 |
+
0.3829346299171448,
|
| 792 |
+
0.31297069787979126,
|
| 793 |
+
0.2523476183414459,
|
| 794 |
+
0.20104341208934784,
|
| 795 |
+
0.2057938128709793,
|
| 796 |
+
0.12497197836637497,
|
| 797 |
+
0.08554214239120483,
|
| 798 |
+
0.11783720552921295,
|
| 799 |
+
0.11661753803491592,
|
| 800 |
+
0.06069108471274376,
|
| 801 |
+
0.05418270081281662,
|
| 802 |
+
0.04761284589767456,
|
| 803 |
+
0.06110139936208725,
|
| 804 |
+
0.07074299454689026,
|
| 805 |
+
0.041489966213703156,
|
| 806 |
+
0.030506331473588943,
|
| 807 |
+
0.03832893818616867,
|
| 808 |
+
0.021118007600307465,
|
| 809 |
+
0.017950356006622314,
|
| 810 |
+
0.029174601659178734,
|
| 811 |
+
0.010410734452307224,
|
| 812 |
+
0.021736932918429375,
|
| 813 |
+
0.01016240008175373,
|
| 814 |
+
0.017910826951265335,
|
| 815 |
+
0.012600082904100418,
|
| 816 |
+
0.00996524840593338,
|
| 817 |
+
0.012870588339865208,
|
| 818 |
+
0.007113197818398476,
|
| 819 |
+
0.010441196151077747,
|
| 820 |
+
0.015161935240030289,
|
| 821 |
+
0.006200422998517752,
|
| 822 |
+
0.015300867147743702,
|
| 823 |
+
0.013834364712238312,
|
| 824 |
+
0.0071389381773769855,
|
| 825 |
+
0.005509757436811924,
|
| 826 |
+
0.009732245467603207,
|
| 827 |
+
0.006760149262845516,
|
| 828 |
+
0.007390973158180714,
|
| 829 |
+
0.005857738666236401,
|
| 830 |
+
0.006241363473236561,
|
| 831 |
+
0.005773015320301056,
|
| 832 |
+
0.007173650898039341,
|
| 833 |
+
0.012012462131679058,
|
| 834 |
+
0.009228762239217758,
|
| 835 |
+
0.007256601005792618,
|
| 836 |
+
0.006749220658093691,
|
| 837 |
+
0.011625763028860092,
|
| 838 |
+
0.011446894146502018,
|
| 839 |
+
0.011271147057414055,
|
| 840 |
+
0.01263866014778614,
|
| 841 |
+
0.0034905869979411364,
|
| 842 |
+
0.00924896914511919,
|
| 843 |
+
0.012157914228737354,
|
| 844 |
+
0.0049015856347978115,
|
| 845 |
+
0.008090977557003498,
|
| 846 |
+
0.006440065801143646,
|
| 847 |
+
0.0016016059089452028,
|
| 848 |
+
0.004791740328073502,
|
| 849 |
+
0.011776924133300781,
|
| 850 |
+
0.007010199595242739,
|
| 851 |
+
0.008304143324494362,
|
| 852 |
+
0.013793421909213066,
|
| 853 |
+
0.01239824015647173,
|
| 854 |
+
0.005596051458269358,
|
| 855 |
+
0.006706747226417065,
|
| 856 |
+
0.0091985072940588,
|
| 857 |
+
0.0032641906291246414,
|
| 858 |
+
0.0030909115448594093,
|
| 859 |
+
0.007046230137348175,
|
| 860 |
+
0.006158037111163139,
|
| 861 |
+
0.0032560895197093487,
|
| 862 |
+
0.00532273855060339,
|
| 863 |
+
0.012963132932782173,
|
| 864 |
+
0.00794745422899723,
|
| 865 |
+
0.004702637903392315,
|
| 866 |
+
0.004337346646934748,
|
| 867 |
+
0.00398415420204401,
|
| 868 |
+
0.004770827479660511,
|
| 869 |
+
0.009282410144805908,
|
| 870 |
+
0.004521648399531841,
|
| 871 |
+
0.012415871024131775,
|
| 872 |
+
0.011195037513971329,
|
| 873 |
+
0.007010922767221928,
|
| 874 |
+
0.00473877415060997,
|
| 875 |
+
0.006248955614864826,
|
| 876 |
+
0.005738144740462303,
|
| 877 |
+
0.011751700192689896,
|
| 878 |
+
0.00924894493073225,
|
| 879 |
+
0.0069801160134375095,
|
| 880 |
+
0.007719063200056553,
|
| 881 |
+
0.008632762357592583,
|
| 882 |
+
0.0050163790583610535,
|
| 883 |
+
0.004706881009042263,
|
| 884 |
+
0.006953589618206024,
|
| 885 |
+
0.006319958716630936,
|
| 886 |
+
0.002565708477050066,
|
| 887 |
+
0.006378693040460348,
|
| 888 |
+
0.00815229769796133,
|
| 889 |
+
0.006314417347311974,
|
| 890 |
+
0.00658452557399869,
|
| 891 |
+
0.00390771497040987,
|
| 892 |
+
0.008094793185591698,
|
| 893 |
+
0.002634467789903283,
|
| 894 |
+
0.004595370963215828,
|
| 895 |
+
0.008192448876798153,
|
| 896 |
+
0.008213513530790806,
|
| 897 |
+
0.007405310403555632,
|
| 898 |
+
0.003594366367906332,
|
| 899 |
+
0.010035409592092037,
|
| 900 |
+
0.010412304662168026,
|
| 901 |
+
0.0036691459827125072,
|
| 902 |
+
0.009448833763599396,
|
| 903 |
+
0.0033259259071201086,
|
| 904 |
+
0.007518710568547249,
|
| 905 |
+
0.004288803320378065,
|
| 906 |
+
0.005735394544899464,
|
| 907 |
+
0.005616557784378529,
|
| 908 |
+
0.007176861632615328,
|
| 909 |
+
0.007496122736483812,
|
| 910 |
+
0.0070140669122338295,
|
| 911 |
+
0.0078854039311409,
|
| 912 |
+
0.0025549333076924086,
|
| 913 |
+
0.007502012886106968
|
| 914 |
+
],
|
| 915 |
+
"denoise_loss": [],
|
| 916 |
+
"ortho_loss": [
|
| 917 |
+
0.2111450433731079,
|
| 918 |
+
0.1435524970293045,
|
| 919 |
+
0.06681142747402191,
|
| 920 |
+
0.052996307611465454,
|
| 921 |
+
0.05158527195453644,
|
| 922 |
+
0.052943676710128784,
|
| 923 |
+
0.05298374965786934,
|
| 924 |
+
0.06948061287403107,
|
| 925 |
+
0.0728166475892067,
|
| 926 |
+
0.080330990254879,
|
| 927 |
+
0.09410754591226578,
|
| 928 |
+
0.12913890182971954,
|
| 929 |
+
0.1634664088487625,
|
| 930 |
+
0.17435631155967712,
|
| 931 |
+
0.18374793231487274,
|
| 932 |
+
0.19662483036518097,
|
| 933 |
+
0.21952885389328003,
|
| 934 |
+
0.23227910697460175,
|
| 935 |
+
0.2511540353298187,
|
| 936 |
+
0.24509447813034058,
|
| 937 |
+
0.24284040927886963,
|
| 938 |
+
0.24897213280200958,
|
| 939 |
+
0.2506718933582306,
|
| 940 |
+
0.2575362026691437,
|
| 941 |
+
0.2686024606227875,
|
| 942 |
+
0.2750362753868103,
|
| 943 |
+
0.2782677114009857,
|
| 944 |
+
0.2853957712650299,
|
| 945 |
+
0.29871729016304016,
|
| 946 |
+
0.30882352590560913,
|
| 947 |
+
0.3340570032596588,
|
| 948 |
+
0.32771769165992737,
|
| 949 |
+
0.32639268040657043,
|
| 950 |
+
0.3189693093299866,
|
| 951 |
+
0.31750908493995667,
|
| 952 |
+
0.32593634724617004,
|
| 953 |
+
0.3260767161846161,
|
| 954 |
+
0.3234666585922241,
|
| 955 |
+
0.3184603154659271,
|
| 956 |
+
0.31702885031700134,
|
| 957 |
+
0.31575602293014526,
|
| 958 |
+
0.3068729639053345,
|
| 959 |
+
0.31276628375053406,
|
| 960 |
+
0.29689764976501465,
|
| 961 |
+
0.30121129751205444,
|
| 962 |
+
0.3054710626602173,
|
| 963 |
+
0.3092142939567566,
|
| 964 |
+
0.3109016418457031,
|
| 965 |
+
0.30108126997947693,
|
| 966 |
+
0.2955969274044037,
|
| 967 |
+
0.2946198880672455,
|
| 968 |
+
0.29174482822418213,
|
| 969 |
+
0.285043865442276,
|
| 970 |
+
0.28630417585372925,
|
| 971 |
+
0.2912791967391968,
|
| 972 |
+
0.2771497368812561,
|
| 973 |
+
0.2789520025253296,
|
| 974 |
+
0.28473028540611267,
|
| 975 |
+
0.28749844431877136,
|
| 976 |
+
0.28734689950942993,
|
| 977 |
+
0.28948697447776794,
|
| 978 |
+
0.29193195700645447,
|
| 979 |
+
0.2959407567977905,
|
| 980 |
+
0.29702845215797424,
|
| 981 |
+
0.2931220233440399,
|
| 982 |
+
0.2979944050312042,
|
| 983 |
+
0.297878235578537,
|
| 984 |
+
0.30620715022087097,
|
| 985 |
+
0.3166170120239258,
|
| 986 |
+
0.3252231180667877,
|
| 987 |
+
0.32210466265678406,
|
| 988 |
+
0.32464829087257385,
|
| 989 |
+
0.32355090975761414,
|
| 990 |
+
0.3284517526626587,
|
| 991 |
+
0.32824888825416565,
|
| 992 |
+
0.32835543155670166,
|
| 993 |
+
0.32803553342819214,
|
| 994 |
+
0.3309395909309387,
|
| 995 |
+
0.3305571675300598,
|
| 996 |
+
0.3290838897228241,
|
| 997 |
+
0.33054694533348083,
|
| 998 |
+
0.32293567061424255,
|
| 999 |
+
0.3265998661518097,
|
| 1000 |
+
0.3343144953250885,
|
| 1001 |
+
0.33344414830207825,
|
| 1002 |
+
0.3310560882091522,
|
| 1003 |
+
0.337158739566803,
|
| 1004 |
+
0.33970019221305847,
|
| 1005 |
+
0.3424912393093109,
|
| 1006 |
+
0.34168195724487305,
|
| 1007 |
+
0.34499648213386536,
|
| 1008 |
+
0.3437992036342621,
|
| 1009 |
+
0.346343994140625,
|
| 1010 |
+
0.34596961736679077,
|
| 1011 |
+
0.3452761769294739,
|
| 1012 |
+
0.34677624702453613,
|
| 1013 |
+
0.3484945297241211,
|
| 1014 |
+
0.3473084568977356,
|
| 1015 |
+
0.35560914874076843,
|
| 1016 |
+
0.3561987280845642,
|
| 1017 |
+
0.357473760843277,
|
| 1018 |
+
0.35667869448661804,
|
| 1019 |
+
0.35596200823783875,
|
| 1020 |
+
0.3558987081050873,
|
| 1021 |
+
0.3573693335056305,
|
| 1022 |
+
0.3576008677482605,
|
| 1023 |
+
0.355884313583374,
|
| 1024 |
+
0.3569817543029785,
|
| 1025 |
+
0.3577706217765808,
|
| 1026 |
+
0.35831722617149353,
|
| 1027 |
+
0.3573484718799591,
|
| 1028 |
+
0.35760417580604553,
|
| 1029 |
+
0.35809966921806335,
|
| 1030 |
+
0.35827332735061646,
|
| 1031 |
+
0.36096251010894775,
|
| 1032 |
+
0.3610628843307495,
|
| 1033 |
+
0.36021000146865845,
|
| 1034 |
+
0.36042484641075134,
|
| 1035 |
+
0.36087724566459656,
|
| 1036 |
+
0.36099040508270264,
|
| 1037 |
+
0.3603220582008362,
|
| 1038 |
+
0.35995814204216003,
|
| 1039 |
+
0.35976719856262207,
|
| 1040 |
+
0.3594537079334259,
|
| 1041 |
+
0.36095303297042847,
|
| 1042 |
+
0.3614071309566498,
|
| 1043 |
+
0.36208659410476685,
|
| 1044 |
+
0.36218127608299255,
|
| 1045 |
+
0.36316877603530884,
|
| 1046 |
+
0.36409878730773926,
|
| 1047 |
+
0.36422309279441833,
|
| 1048 |
+
0.36380311846733093,
|
| 1049 |
+
0.36408865451812744,
|
| 1050 |
+
0.36326295137405396,
|
| 1051 |
+
0.36311736702919006,
|
| 1052 |
+
0.3631589412689209,
|
| 1053 |
+
0.3635577857494354,
|
| 1054 |
+
0.3654131591320038,
|
| 1055 |
+
0.3654572069644928,
|
| 1056 |
+
0.36536282300949097,
|
| 1057 |
+
0.365400493144989,
|
| 1058 |
+
0.3654620051383972,
|
| 1059 |
+
0.3656059801578522,
|
| 1060 |
+
0.3652297258377075,
|
| 1061 |
+
0.36522072553634644,
|
| 1062 |
+
0.3652559518814087,
|
| 1063 |
+
0.36530348658561707,
|
| 1064 |
+
0.36531174182891846,
|
| 1065 |
+
0.36535152792930603,
|
| 1066 |
+
0.3653797209262848
|
| 1067 |
+
],
|
| 1068 |
+
"lr": [
|
| 1069 |
+
7.840000000000001e-05,
|
| 1070 |
+
8e-05,
|
| 1071 |
+
8e-05,
|
| 1072 |
+
8e-05,
|
| 1073 |
+
8e-05,
|
| 1074 |
+
8e-05,
|
| 1075 |
+
8e-05,
|
| 1076 |
+
8e-05,
|
| 1077 |
+
8e-05,
|
| 1078 |
+
8e-05,
|
| 1079 |
+
8e-05,
|
| 1080 |
+
8e-05,
|
| 1081 |
+
8e-05,
|
| 1082 |
+
8e-05,
|
| 1083 |
+
8e-05,
|
| 1084 |
+
8e-05,
|
| 1085 |
+
8e-05,
|
| 1086 |
+
8e-05,
|
| 1087 |
+
8e-05,
|
| 1088 |
+
8e-05,
|
| 1089 |
+
8e-05,
|
| 1090 |
+
8e-05,
|
| 1091 |
+
8e-05,
|
| 1092 |
+
8e-05,
|
| 1093 |
+
8e-05,
|
| 1094 |
+
8e-05,
|
| 1095 |
+
8e-05,
|
| 1096 |
+
8e-05,
|
| 1097 |
+
8e-05,
|
| 1098 |
+
8e-05,
|
| 1099 |
+
8e-05,
|
| 1100 |
+
8e-05,
|
| 1101 |
+
8e-05,
|
| 1102 |
+
8e-05,
|
| 1103 |
+
8e-05,
|
| 1104 |
+
8e-05,
|
| 1105 |
+
8e-05,
|
| 1106 |
+
8e-05,
|
| 1107 |
+
8e-05,
|
| 1108 |
+
8e-05,
|
| 1109 |
+
8e-05,
|
| 1110 |
+
8e-05,
|
| 1111 |
+
8e-05,
|
| 1112 |
+
8e-05,
|
| 1113 |
+
8e-05,
|
| 1114 |
+
8e-05,
|
| 1115 |
+
8e-05,
|
| 1116 |
+
8e-05,
|
| 1117 |
+
8e-05,
|
| 1118 |
+
8e-05,
|
| 1119 |
+
8e-05,
|
| 1120 |
+
8e-05,
|
| 1121 |
+
8e-05,
|
| 1122 |
+
8e-05,
|
| 1123 |
+
8e-05,
|
| 1124 |
+
8e-05,
|
| 1125 |
+
8e-05,
|
| 1126 |
+
8e-05,
|
| 1127 |
+
8e-05,
|
| 1128 |
+
8e-05,
|
| 1129 |
+
8e-05,
|
| 1130 |
+
8e-05,
|
| 1131 |
+
8e-05,
|
| 1132 |
+
8e-05,
|
| 1133 |
+
8e-05,
|
| 1134 |
+
8e-05,
|
| 1135 |
+
8e-05,
|
| 1136 |
+
8e-05,
|
| 1137 |
+
8e-05,
|
| 1138 |
+
8e-05,
|
| 1139 |
+
8e-05,
|
| 1140 |
+
8e-05,
|
| 1141 |
+
8e-05,
|
| 1142 |
+
8e-05,
|
| 1143 |
+
8e-05,
|
| 1144 |
+
8e-05,
|
| 1145 |
+
8e-05,
|
| 1146 |
+
8e-05,
|
| 1147 |
+
8e-05,
|
| 1148 |
+
8e-05,
|
| 1149 |
+
8e-05,
|
| 1150 |
+
8e-05,
|
| 1151 |
+
8e-05,
|
| 1152 |
+
8e-05,
|
| 1153 |
+
8e-05,
|
| 1154 |
+
8e-05,
|
| 1155 |
+
8e-05,
|
| 1156 |
+
8e-05,
|
| 1157 |
+
8e-05,
|
| 1158 |
+
8e-05,
|
| 1159 |
+
7.932818532818534e-05,
|
| 1160 |
+
7.816988416988418e-05,
|
| 1161 |
+
7.701158301158302e-05,
|
| 1162 |
+
7.585328185328185e-05,
|
| 1163 |
+
7.469498069498071e-05,
|
| 1164 |
+
7.353667953667954e-05,
|
| 1165 |
+
7.237837837837838e-05,
|
| 1166 |
+
7.122007722007721e-05,
|
| 1167 |
+
7.006177606177606e-05,
|
| 1168 |
+
6.890347490347492e-05,
|
| 1169 |
+
6.774517374517375e-05,
|
| 1170 |
+
6.65868725868726e-05,
|
| 1171 |
+
6.542857142857144e-05,
|
| 1172 |
+
6.427027027027027e-05,
|
| 1173 |
+
6.311196911196911e-05,
|
| 1174 |
+
6.121235521235521e-05,
|
| 1175 |
+
6.0054054054054064e-05,
|
| 1176 |
+
5.8895752895752895e-05,
|
| 1177 |
+
5.773745173745175e-05,
|
| 1178 |
+
5.6579150579150584e-05,
|
| 1179 |
+
5.542084942084943e-05,
|
| 1180 |
+
5.426254826254825e-05,
|
| 1181 |
+
5.310424710424711e-05,
|
| 1182 |
+
5.194594594594594e-05,
|
| 1183 |
+
5.0787644787644786e-05,
|
| 1184 |
+
4.9629343629343644e-05,
|
| 1185 |
+
4.8471042471042475e-05,
|
| 1186 |
+
4.7312741312741326e-05,
|
| 1187 |
+
4.615444015444014e-05,
|
| 1188 |
+
4.4996138996139e-05,
|
| 1189 |
+
4.309652509652511e-05,
|
| 1190 |
+
4.1938223938223946e-05,
|
| 1191 |
+
4.07799227799228e-05,
|
| 1192 |
+
3.962162162162162e-05,
|
| 1193 |
+
3.846332046332047e-05,
|
| 1194 |
+
3.73050193050193e-05,
|
| 1195 |
+
3.6146718146718155e-05,
|
| 1196 |
+
3.4988416988416986e-05,
|
| 1197 |
+
3.383011583011584e-05,
|
| 1198 |
+
3.267181467181467e-05,
|
| 1199 |
+
3.151351351351352e-05,
|
| 1200 |
+
3.0355212355212367e-05,
|
| 1201 |
+
2.9196911196911198e-05,
|
| 1202 |
+
2.8038610038610046e-05,
|
| 1203 |
+
2.6880308880308876e-05,
|
| 1204 |
+
2.4980694980694983e-05,
|
| 1205 |
+
2.3822393822393838e-05,
|
| 1206 |
+
2.266409266409267e-05,
|
| 1207 |
+
2.1505791505791517e-05,
|
| 1208 |
+
2.0347490347490348e-05,
|
| 1209 |
+
1.9189189189189195e-05,
|
| 1210 |
+
1.8030888030888026e-05,
|
| 1211 |
+
1.6872586872586878e-05,
|
| 1212 |
+
1.571428571428571e-05,
|
| 1213 |
+
1.455598455598456e-05,
|
| 1214 |
+
1.3397683397683389e-05,
|
| 1215 |
+
1.223938223938224e-05,
|
| 1216 |
+
1.1081081081081092e-05,
|
| 1217 |
+
9.92277992277992e-06,
|
| 1218 |
+
8.764478764478772e-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": 50
|
| 1254 |
+
},
|
| 1255 |
+
"splits": {
|
| 1256 |
+
"add_S0": {
|
| 1257 |
+
"full_accuracy": 1.0,
|
| 1258 |
+
"n_examples": 50,
|
| 1259 |
+
"per_subtask": {
|
| 1260 |
+
"SA": {
|
| 1261 |
+
"accuracy": 1.0,
|
| 1262 |
+
"count": 295
|
| 1263 |
+
},
|
| 1264 |
+
"SS": {
|
| 1265 |
+
"accuracy": 1.0,
|
| 1266 |
+
"count": 55
|
| 1267 |
+
}
|
| 1268 |
+
}
|
| 1269 |
+
},
|
| 1270 |
+
"add_S1": {
|
| 1271 |
+
"full_accuracy": 1.0,
|
| 1272 |
+
"n_examples": 50,
|
| 1273 |
+
"per_subtask": {
|
| 1274 |
+
"SA": {
|
| 1275 |
+
"accuracy": 1.0,
|
| 1276 |
+
"count": 126
|
| 1277 |
+
},
|
| 1278 |
+
"SC": {
|
| 1279 |
+
"accuracy": 1.0,
|
| 1280 |
+
"count": 79
|
| 1281 |
+
},
|
| 1282 |
+
"SS": {
|
| 1283 |
+
"accuracy": 1.0,
|
| 1284 |
+
"count": 21
|
| 1285 |
+
},
|
| 1286 |
+
"UC": {
|
| 1287 |
+
"accuracy": 1.0,
|
| 1288 |
+
"count": 124
|
| 1289 |
+
}
|
| 1290 |
+
}
|
| 1291 |
+
},
|
| 1292 |
+
"add_S2": {
|
| 1293 |
+
"full_accuracy": 1.0,
|
| 1294 |
+
"n_examples": 50,
|
| 1295 |
+
"per_subtask": {
|
| 1296 |
+
"SA": {
|
| 1297 |
+
"accuracy": 1.0,
|
| 1298 |
+
"count": 75
|
| 1299 |
+
},
|
| 1300 |
+
"SC": {
|
| 1301 |
+
"accuracy": 1.0,
|
| 1302 |
+
"count": 62
|
| 1303 |
+
},
|
| 1304 |
+
"SS": {
|
| 1305 |
+
"accuracy": 1.0,
|
| 1306 |
+
"count": 39
|
| 1307 |
+
},
|
| 1308 |
+
"UC": {
|
| 1309 |
+
"accuracy": 1.0,
|
| 1310 |
+
"count": 111
|
| 1311 |
+
},
|
| 1312 |
+
"US": {
|
| 1313 |
+
"accuracy": 1.0,
|
| 1314 |
+
"count": 63
|
| 1315 |
+
}
|
| 1316 |
+
}
|
| 1317 |
+
},
|
| 1318 |
+
"add_S3": {
|
| 1319 |
+
"full_accuracy": 1.0,
|
| 1320 |
+
"n_examples": 50,
|
| 1321 |
+
"per_subtask": {
|
| 1322 |
+
"SA": {
|
| 1323 |
+
"accuracy": 1.0,
|
| 1324 |
+
"count": 60
|
| 1325 |
+
},
|
| 1326 |
+
"SC": {
|
| 1327 |
+
"accuracy": 1.0,
|
| 1328 |
+
"count": 57
|
| 1329 |
+
},
|
| 1330 |
+
"SS": {
|
| 1331 |
+
"accuracy": 1.0,
|
| 1332 |
+
"count": 19
|
| 1333 |
+
},
|
| 1334 |
+
"UC": {
|
| 1335 |
+
"accuracy": 1.0,
|
| 1336 |
+
"count": 104
|
| 1337 |
+
},
|
| 1338 |
+
"US": {
|
| 1339 |
+
"accuracy": 1.0,
|
| 1340 |
+
"count": 110
|
| 1341 |
+
}
|
| 1342 |
+
}
|
| 1343 |
+
},
|
| 1344 |
+
"add_S4": {
|
| 1345 |
+
"full_accuracy": 0.98,
|
| 1346 |
+
"n_examples": 50,
|
| 1347 |
+
"per_subtask": {
|
| 1348 |
+
"SA": {
|
| 1349 |
+
"accuracy": 1.0,
|
| 1350 |
+
"count": 48
|
| 1351 |
+
},
|
| 1352 |
+
"SC": {
|
| 1353 |
+
"accuracy": 1.0,
|
| 1354 |
+
"count": 52
|
| 1355 |
+
},
|
| 1356 |
+
"SS": {
|
| 1357 |
+
"accuracy": 1.0,
|
| 1358 |
+
"count": 7
|
| 1359 |
+
},
|
| 1360 |
+
"UC": {
|
| 1361 |
+
"accuracy": 0.9887640449438202,
|
| 1362 |
+
"count": 89
|
| 1363 |
+
},
|
| 1364 |
+
"US": {
|
| 1365 |
+
"accuracy": 1.0,
|
| 1366 |
+
"count": 154
|
| 1367 |
+
}
|
| 1368 |
+
}
|
| 1369 |
+
},
|
| 1370 |
+
"add_S5": {
|
| 1371 |
+
"full_accuracy": 0.96,
|
| 1372 |
+
"n_examples": 50,
|
| 1373 |
+
"per_subtask": {
|
| 1374 |
+
"SA": {
|
| 1375 |
+
"accuracy": 1.0,
|
| 1376 |
+
"count": 50
|
| 1377 |
+
},
|
| 1378 |
+
"SC": {
|
| 1379 |
+
"accuracy": 1.0,
|
| 1380 |
+
"count": 50
|
| 1381 |
+
},
|
| 1382 |
+
"UC": {
|
| 1383 |
+
"accuracy": 0.96,
|
| 1384 |
+
"count": 50
|
| 1385 |
+
},
|
| 1386 |
+
"US": {
|
| 1387 |
+
"accuracy": 1.0,
|
| 1388 |
+
"count": 200
|
| 1389 |
+
}
|
| 1390 |
+
}
|
| 1391 |
+
},
|
| 1392 |
+
"add_S6": {
|
| 1393 |
+
"full_accuracy": 1.0,
|
| 1394 |
+
"n_examples": 50,
|
| 1395 |
+
"per_subtask": {
|
| 1396 |
+
"SC": {
|
| 1397 |
+
"accuracy": 1.0,
|
| 1398 |
+
"count": 50
|
| 1399 |
+
},
|
| 1400 |
+
"UC": {
|
| 1401 |
+
"accuracy": 1.0,
|
| 1402 |
+
"count": 50
|
| 1403 |
+
},
|
| 1404 |
+
"US": {
|
| 1405 |
+
"accuracy": 1.0,
|
| 1406 |
+
"count": 250
|
| 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": 431
|
| 1417 |
+
},
|
| 1418 |
+
"SC": {
|
| 1419 |
+
"accuracy": 1.0,
|
| 1420 |
+
"count": 316
|
| 1421 |
+
},
|
| 1422 |
+
"SS": {
|
| 1423 |
+
"accuracy": 1.0,
|
| 1424 |
+
"count": 39
|
| 1425 |
+
},
|
| 1426 |
+
"UC": {
|
| 1427 |
+
"accuracy": 1.0,
|
| 1428 |
+
"count": 560
|
| 1429 |
+
},
|
| 1430 |
+
"US": {
|
| 1431 |
+
"accuracy": 1.0,
|
| 1432 |
+
"count": 54
|
| 1433 |
+
}
|
| 1434 |
+
}
|
| 1435 |
+
},
|
| 1436 |
+
"add_C3": {
|
| 1437 |
+
"full_accuracy": 1.0,
|
| 1438 |
+
"n_examples": 50,
|
| 1439 |
+
"per_subtask": {
|
| 1440 |
+
"SA": {
|
| 1441 |
+
"accuracy": 1.0,
|
| 1442 |
+
"count": 150
|
| 1443 |
+
},
|
| 1444 |
+
"SC": {
|
| 1445 |
+
"accuracy": 1.0,
|
| 1446 |
+
"count": 50
|
| 1447 |
+
},
|
| 1448 |
+
"UC": {
|
| 1449 |
+
"accuracy": 1.0,
|
| 1450 |
+
"count": 104
|
| 1451 |
+
},
|
| 1452 |
+
"US": {
|
| 1453 |
+
"accuracy": 1.0,
|
| 1454 |
+
"count": 46
|
| 1455 |
+
}
|
| 1456 |
+
}
|
| 1457 |
+
},
|
| 1458 |
+
"add_C4": {
|
| 1459 |
+
"full_accuracy": 0.96,
|
| 1460 |
+
"n_examples": 50,
|
| 1461 |
+
"per_subtask": {
|
| 1462 |
+
"SA": {
|
| 1463 |
+
"accuracy": 1.0,
|
| 1464 |
+
"count": 100
|
| 1465 |
+
},
|
| 1466 |
+
"SC": {
|
| 1467 |
+
"accuracy": 1.0,
|
| 1468 |
+
"count": 50
|
| 1469 |
+
},
|
| 1470 |
+
"UC": {
|
| 1471 |
+
"accuracy": 0.983739837398374,
|
| 1472 |
+
"count": 123
|
| 1473 |
+
},
|
| 1474 |
+
"US": {
|
| 1475 |
+
"accuracy": 1.0,
|
| 1476 |
+
"count": 77
|
| 1477 |
+
}
|
| 1478 |
+
}
|
| 1479 |
+
},
|
| 1480 |
+
"add_C5": {
|
| 1481 |
+
"full_accuracy": 1.0,
|
| 1482 |
+
"n_examples": 50,
|
| 1483 |
+
"per_subtask": {
|
| 1484 |
+
"SA": {
|
| 1485 |
+
"accuracy": 1.0,
|
| 1486 |
+
"count": 50
|
| 1487 |
+
},
|
| 1488 |
+
"SC": {
|
| 1489 |
+
"accuracy": 1.0,
|
| 1490 |
+
"count": 50
|
| 1491 |
+
},
|
| 1492 |
+
"UC": {
|
| 1493 |
+
"accuracy": 1.0,
|
| 1494 |
+
"count": 154
|
| 1495 |
+
},
|
| 1496 |
+
"US": {
|
| 1497 |
+
"accuracy": 1.0,
|
| 1498 |
+
"count": 96
|
| 1499 |
+
}
|
| 1500 |
+
}
|
| 1501 |
+
},
|
| 1502 |
+
"add_C6": {
|
| 1503 |
+
"full_accuracy": 1.0,
|
| 1504 |
+
"n_examples": 50,
|
| 1505 |
+
"per_subtask": {
|
| 1506 |
+
"SC": {
|
| 1507 |
+
"accuracy": 1.0,
|
| 1508 |
+
"count": 50
|
| 1509 |
+
},
|
| 1510 |
+
"UC": {
|
| 1511 |
+
"accuracy": 1.0,
|
| 1512 |
+
"count": 182
|
| 1513 |
+
},
|
| 1514 |
+
"US": {
|
| 1515 |
+
"accuracy": 1.0,
|
| 1516 |
+
"count": 118
|
| 1517 |
+
}
|
| 1518 |
+
}
|
| 1519 |
+
},
|
| 1520 |
+
"sub_M0": {
|
| 1521 |
+
"full_accuracy": 1.0,
|
| 1522 |
+
"n_examples": 50,
|
| 1523 |
+
"per_subtask": {
|
| 1524 |
+
"MD": {
|
| 1525 |
+
"accuracy": 1.0,
|
| 1526 |
+
"count": 294
|
| 1527 |
+
},
|
| 1528 |
+
"ME": {
|
| 1529 |
+
"accuracy": 1.0,
|
| 1530 |
+
"count": 56
|
| 1531 |
+
}
|
| 1532 |
+
}
|
| 1533 |
+
},
|
| 1534 |
+
"sub_M1": {
|
| 1535 |
+
"full_accuracy": 1.0,
|
| 1536 |
+
"n_examples": 50,
|
| 1537 |
+
"per_subtask": {
|
| 1538 |
+
"MD": {
|
| 1539 |
+
"accuracy": 1.0,
|
| 1540 |
+
"count": 143
|
| 1541 |
+
},
|
| 1542 |
+
"MB": {
|
| 1543 |
+
"accuracy": 1.0,
|
| 1544 |
+
"count": 69
|
| 1545 |
+
},
|
| 1546 |
+
"ME": {
|
| 1547 |
+
"accuracy": 1.0,
|
| 1548 |
+
"count": 15
|
| 1549 |
+
},
|
| 1550 |
+
"UB": {
|
| 1551 |
+
"accuracy": 1.0,
|
| 1552 |
+
"count": 123
|
| 1553 |
+
}
|
| 1554 |
+
}
|
| 1555 |
+
},
|
| 1556 |
+
"sub_M2": {
|
| 1557 |
+
"full_accuracy": 1.0,
|
| 1558 |
+
"n_examples": 50,
|
| 1559 |
+
"per_subtask": {
|
| 1560 |
+
"MD": {
|
| 1561 |
+
"accuracy": 1.0,
|
| 1562 |
+
"count": 108
|
| 1563 |
+
},
|
| 1564 |
+
"MB": {
|
| 1565 |
+
"accuracy": 1.0,
|
| 1566 |
+
"count": 52
|
| 1567 |
+
},
|
| 1568 |
+
"ME": {
|
| 1569 |
+
"accuracy": 1.0,
|
| 1570 |
+
"count": 52
|
| 1571 |
+
},
|
| 1572 |
+
"UB": {
|
| 1573 |
+
"accuracy": 1.0,
|
| 1574 |
+
"count": 87
|
| 1575 |
+
},
|
| 1576 |
+
"UD": {
|
| 1577 |
+
"accuracy": 1.0,
|
| 1578 |
+
"count": 51
|
| 1579 |
+
}
|
| 1580 |
+
}
|
| 1581 |
+
},
|
| 1582 |
+
"sub_M3": {
|
| 1583 |
+
"full_accuracy": 1.0,
|
| 1584 |
+
"n_examples": 50,
|
| 1585 |
+
"per_subtask": {
|
| 1586 |
+
"MD": {
|
| 1587 |
+
"accuracy": 1.0,
|
| 1588 |
+
"count": 94
|
| 1589 |
+
},
|
| 1590 |
+
"MB": {
|
| 1591 |
+
"accuracy": 1.0,
|
| 1592 |
+
"count": 51
|
| 1593 |
+
},
|
| 1594 |
+
"ME": {
|
| 1595 |
+
"accuracy": 1.0,
|
| 1596 |
+
"count": 25
|
| 1597 |
+
},
|
| 1598 |
+
"UB": {
|
| 1599 |
+
"accuracy": 1.0,
|
| 1600 |
+
"count": 78
|
| 1601 |
+
},
|
| 1602 |
+
"UD": {
|
| 1603 |
+
"accuracy": 1.0,
|
| 1604 |
+
"count": 102
|
| 1605 |
+
}
|
| 1606 |
+
}
|
| 1607 |
+
},
|
| 1608 |
+
"sub_M4": {
|
| 1609 |
+
"full_accuracy": 1.0,
|
| 1610 |
+
"n_examples": 50,
|
| 1611 |
+
"per_subtask": {
|
| 1612 |
+
"MD": {
|
| 1613 |
+
"accuracy": 1.0,
|
| 1614 |
+
"count": 100
|
| 1615 |
+
},
|
| 1616 |
+
"MB": {
|
| 1617 |
+
"accuracy": 1.0,
|
| 1618 |
+
"count": 50
|
| 1619 |
+
},
|
| 1620 |
+
"UB": {
|
| 1621 |
+
"accuracy": 1.0,
|
| 1622 |
+
"count": 50
|
| 1623 |
+
},
|
| 1624 |
+
"UD": {
|
| 1625 |
+
"accuracy": 1.0,
|
| 1626 |
+
"count": 150
|
| 1627 |
+
}
|
| 1628 |
+
}
|
| 1629 |
+
},
|
| 1630 |
+
"sub_M5": {
|
| 1631 |
+
"full_accuracy": 1.0,
|
| 1632 |
+
"n_examples": 50,
|
| 1633 |
+
"per_subtask": {
|
| 1634 |
+
"MD": {
|
| 1635 |
+
"accuracy": 1.0,
|
| 1636 |
+
"count": 50
|
| 1637 |
+
},
|
| 1638 |
+
"MB": {
|
| 1639 |
+
"accuracy": 1.0,
|
| 1640 |
+
"count": 50
|
| 1641 |
+
},
|
| 1642 |
+
"UB": {
|
| 1643 |
+
"accuracy": 1.0,
|
| 1644 |
+
"count": 50
|
| 1645 |
+
},
|
| 1646 |
+
"UD": {
|
| 1647 |
+
"accuracy": 1.0,
|
| 1648 |
+
"count": 200
|
| 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": 588
|
| 1659 |
+
},
|
| 1660 |
+
"MB": {
|
| 1661 |
+
"accuracy": 1.0,
|
| 1662 |
+
"count": 268
|
| 1663 |
+
},
|
| 1664 |
+
"ME": {
|
| 1665 |
+
"accuracy": 1.0,
|
| 1666 |
+
"count": 60
|
| 1667 |
+
},
|
| 1668 |
+
"UB": {
|
| 1669 |
+
"accuracy": 1.0,
|
| 1670 |
+
"count": 447
|
| 1671 |
+
},
|
| 1672 |
+
"UD": {
|
| 1673 |
+
"accuracy": 1.0,
|
| 1674 |
+
"count": 37
|
| 1675 |
+
}
|
| 1676 |
+
}
|
| 1677 |
+
},
|
| 1678 |
+
"sub_B3": {
|
| 1679 |
+
"full_accuracy": 1.0,
|
| 1680 |
+
"n_examples": 50,
|
| 1681 |
+
"per_subtask": {
|
| 1682 |
+
"MD": {
|
| 1683 |
+
"accuracy": 1.0,
|
| 1684 |
+
"count": 150
|
| 1685 |
+
},
|
| 1686 |
+
"MB": {
|
| 1687 |
+
"accuracy": 1.0,
|
| 1688 |
+
"count": 50
|
| 1689 |
+
},
|
| 1690 |
+
"UB": {
|
| 1691 |
+
"accuracy": 1.0,
|
| 1692 |
+
"count": 107
|
| 1693 |
+
},
|
| 1694 |
+
"UD": {
|
| 1695 |
+
"accuracy": 1.0,
|
| 1696 |
+
"count": 43
|
| 1697 |
+
}
|
| 1698 |
+
}
|
| 1699 |
+
},
|
| 1700 |
+
"sub_B4": {
|
| 1701 |
+
"full_accuracy": 1.0,
|
| 1702 |
+
"n_examples": 50,
|
| 1703 |
+
"per_subtask": {
|
| 1704 |
+
"MD": {
|
| 1705 |
+
"accuracy": 1.0,
|
| 1706 |
+
"count": 100
|
| 1707 |
+
},
|
| 1708 |
+
"MB": {
|
| 1709 |
+
"accuracy": 1.0,
|
| 1710 |
+
"count": 50
|
| 1711 |
+
},
|
| 1712 |
+
"UB": {
|
| 1713 |
+
"accuracy": 1.0,
|
| 1714 |
+
"count": 114
|
| 1715 |
+
},
|
| 1716 |
+
"UD": {
|
| 1717 |
+
"accuracy": 1.0,
|
| 1718 |
+
"count": 86
|
| 1719 |
+
}
|
| 1720 |
+
}
|
| 1721 |
+
},
|
| 1722 |
+
"sub_B5": {
|
| 1723 |
+
"full_accuracy": 1.0,
|
| 1724 |
+
"n_examples": 50,
|
| 1725 |
+
"per_subtask": {
|
| 1726 |
+
"MD": {
|
| 1727 |
+
"accuracy": 1.0,
|
| 1728 |
+
"count": 50
|
| 1729 |
+
},
|
| 1730 |
+
"MB": {
|
| 1731 |
+
"accuracy": 1.0,
|
| 1732 |
+
"count": 50
|
| 1733 |
+
},
|
| 1734 |
+
"UB": {
|
| 1735 |
+
"accuracy": 1.0,
|
| 1736 |
+
"count": 153
|
| 1737 |
+
},
|
| 1738 |
+
"UD": {
|
| 1739 |
+
"accuracy": 1.0,
|
| 1740 |
+
"count": 97
|
| 1741 |
+
}
|
| 1742 |
+
}
|
| 1743 |
+
}
|
| 1744 |
+
},
|
| 1745 |
+
"summary": {
|
| 1746 |
+
"overall_accuracy": 0.9964285714285714,
|
| 1747 |
+
"total_examples": 1400,
|
| 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": 50
|
| 1758 |
+
},
|
| 1759 |
+
"splits": {
|
| 1760 |
+
"add_S0": {
|
| 1761 |
+
"full_accuracy": 1.0,
|
| 1762 |
+
"n_examples": 50,
|
| 1763 |
+
"per_subtask": {
|
| 1764 |
+
"SA": {
|
| 1765 |
+
"accuracy": 1.0,
|
| 1766 |
+
"count": 295
|
| 1767 |
+
},
|
| 1768 |
+
"SS": {
|
| 1769 |
+
"accuracy": 1.0,
|
| 1770 |
+
"count": 55
|
| 1771 |
+
}
|
| 1772 |
+
}
|
| 1773 |
+
},
|
| 1774 |
+
"add_S1": {
|
| 1775 |
+
"full_accuracy": 1.0,
|
| 1776 |
+
"n_examples": 50,
|
| 1777 |
+
"per_subtask": {
|
| 1778 |
+
"SA": {
|
| 1779 |
+
"accuracy": 1.0,
|
| 1780 |
+
"count": 126
|
| 1781 |
+
},
|
| 1782 |
+
"SC": {
|
| 1783 |
+
"accuracy": 1.0,
|
| 1784 |
+
"count": 79
|
| 1785 |
+
},
|
| 1786 |
+
"SS": {
|
| 1787 |
+
"accuracy": 1.0,
|
| 1788 |
+
"count": 21
|
| 1789 |
+
},
|
| 1790 |
+
"UC": {
|
| 1791 |
+
"accuracy": 1.0,
|
| 1792 |
+
"count": 124
|
| 1793 |
+
}
|
| 1794 |
+
}
|
| 1795 |
+
},
|
| 1796 |
+
"add_S2": {
|
| 1797 |
+
"full_accuracy": 1.0,
|
| 1798 |
+
"n_examples": 50,
|
| 1799 |
+
"per_subtask": {
|
| 1800 |
+
"SA": {
|
| 1801 |
+
"accuracy": 1.0,
|
| 1802 |
+
"count": 75
|
| 1803 |
+
},
|
| 1804 |
+
"SC": {
|
| 1805 |
+
"accuracy": 1.0,
|
| 1806 |
+
"count": 62
|
| 1807 |
+
},
|
| 1808 |
+
"SS": {
|
| 1809 |
+
"accuracy": 1.0,
|
| 1810 |
+
"count": 39
|
| 1811 |
+
},
|
| 1812 |
+
"UC": {
|
| 1813 |
+
"accuracy": 1.0,
|
| 1814 |
+
"count": 111
|
| 1815 |
+
},
|
| 1816 |
+
"US": {
|
| 1817 |
+
"accuracy": 1.0,
|
| 1818 |
+
"count": 63
|
| 1819 |
+
}
|
| 1820 |
+
}
|
| 1821 |
+
},
|
| 1822 |
+
"add_S3": {
|
| 1823 |
+
"full_accuracy": 1.0,
|
| 1824 |
+
"n_examples": 50,
|
| 1825 |
+
"per_subtask": {
|
| 1826 |
+
"SA": {
|
| 1827 |
+
"accuracy": 1.0,
|
| 1828 |
+
"count": 60
|
| 1829 |
+
},
|
| 1830 |
+
"SC": {
|
| 1831 |
+
"accuracy": 1.0,
|
| 1832 |
+
"count": 57
|
| 1833 |
+
},
|
| 1834 |
+
"SS": {
|
| 1835 |
+
"accuracy": 1.0,
|
| 1836 |
+
"count": 19
|
| 1837 |
+
},
|
| 1838 |
+
"UC": {
|
| 1839 |
+
"accuracy": 1.0,
|
| 1840 |
+
"count": 104
|
| 1841 |
+
},
|
| 1842 |
+
"US": {
|
| 1843 |
+
"accuracy": 1.0,
|
| 1844 |
+
"count": 110
|
| 1845 |
+
}
|
| 1846 |
+
}
|
| 1847 |
+
},
|
| 1848 |
+
"add_S4": {
|
| 1849 |
+
"full_accuracy": 1.0,
|
| 1850 |
+
"n_examples": 50,
|
| 1851 |
+
"per_subtask": {
|
| 1852 |
+
"SA": {
|
| 1853 |
+
"accuracy": 1.0,
|
| 1854 |
+
"count": 48
|
| 1855 |
+
},
|
| 1856 |
+
"SC": {
|
| 1857 |
+
"accuracy": 1.0,
|
| 1858 |
+
"count": 52
|
| 1859 |
+
},
|
| 1860 |
+
"SS": {
|
| 1861 |
+
"accuracy": 1.0,
|
| 1862 |
+
"count": 7
|
| 1863 |
+
},
|
| 1864 |
+
"UC": {
|
| 1865 |
+
"accuracy": 1.0,
|
| 1866 |
+
"count": 89
|
| 1867 |
+
},
|
| 1868 |
+
"US": {
|
| 1869 |
+
"accuracy": 1.0,
|
| 1870 |
+
"count": 154
|
| 1871 |
+
}
|
| 1872 |
+
}
|
| 1873 |
+
},
|
| 1874 |
+
"add_S5": {
|
| 1875 |
+
"full_accuracy": 1.0,
|
| 1876 |
+
"n_examples": 50,
|
| 1877 |
+
"per_subtask": {
|
| 1878 |
+
"SA": {
|
| 1879 |
+
"accuracy": 1.0,
|
| 1880 |
+
"count": 50
|
| 1881 |
+
},
|
| 1882 |
+
"SC": {
|
| 1883 |
+
"accuracy": 1.0,
|
| 1884 |
+
"count": 50
|
| 1885 |
+
},
|
| 1886 |
+
"UC": {
|
| 1887 |
+
"accuracy": 1.0,
|
| 1888 |
+
"count": 50
|
| 1889 |
+
},
|
| 1890 |
+
"US": {
|
| 1891 |
+
"accuracy": 1.0,
|
| 1892 |
+
"count": 200
|
| 1893 |
+
}
|
| 1894 |
+
}
|
| 1895 |
+
},
|
| 1896 |
+
"add_S6": {
|
| 1897 |
+
"full_accuracy": 1.0,
|
| 1898 |
+
"n_examples": 50,
|
| 1899 |
+
"per_subtask": {
|
| 1900 |
+
"SC": {
|
| 1901 |
+
"accuracy": 1.0,
|
| 1902 |
+
"count": 50
|
| 1903 |
+
},
|
| 1904 |
+
"UC": {
|
| 1905 |
+
"accuracy": 1.0,
|
| 1906 |
+
"count": 50
|
| 1907 |
+
},
|
| 1908 |
+
"US": {
|
| 1909 |
+
"accuracy": 1.0,
|
| 1910 |
+
"count": 250
|
| 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": 431
|
| 1921 |
+
},
|
| 1922 |
+
"SC": {
|
| 1923 |
+
"accuracy": 1.0,
|
| 1924 |
+
"count": 316
|
| 1925 |
+
},
|
| 1926 |
+
"SS": {
|
| 1927 |
+
"accuracy": 1.0,
|
| 1928 |
+
"count": 39
|
| 1929 |
+
},
|
| 1930 |
+
"UC": {
|
| 1931 |
+
"accuracy": 1.0,
|
| 1932 |
+
"count": 560
|
| 1933 |
+
},
|
| 1934 |
+
"US": {
|
| 1935 |
+
"accuracy": 1.0,
|
| 1936 |
+
"count": 54
|
| 1937 |
+
}
|
| 1938 |
+
}
|
| 1939 |
+
},
|
| 1940 |
+
"add_C3": {
|
| 1941 |
+
"full_accuracy": 1.0,
|
| 1942 |
+
"n_examples": 50,
|
| 1943 |
+
"per_subtask": {
|
| 1944 |
+
"SA": {
|
| 1945 |
+
"accuracy": 1.0,
|
| 1946 |
+
"count": 150
|
| 1947 |
+
},
|
| 1948 |
+
"SC": {
|
| 1949 |
+
"accuracy": 1.0,
|
| 1950 |
+
"count": 50
|
| 1951 |
+
},
|
| 1952 |
+
"UC": {
|
| 1953 |
+
"accuracy": 1.0,
|
| 1954 |
+
"count": 104
|
| 1955 |
+
},
|
| 1956 |
+
"US": {
|
| 1957 |
+
"accuracy": 1.0,
|
| 1958 |
+
"count": 46
|
| 1959 |
+
}
|
| 1960 |
+
}
|
| 1961 |
+
},
|
| 1962 |
+
"add_C4": {
|
| 1963 |
+
"full_accuracy": 1.0,
|
| 1964 |
+
"n_examples": 50,
|
| 1965 |
+
"per_subtask": {
|
| 1966 |
+
"SA": {
|
| 1967 |
+
"accuracy": 1.0,
|
| 1968 |
+
"count": 100
|
| 1969 |
+
},
|
| 1970 |
+
"SC": {
|
| 1971 |
+
"accuracy": 1.0,
|
| 1972 |
+
"count": 50
|
| 1973 |
+
},
|
| 1974 |
+
"UC": {
|
| 1975 |
+
"accuracy": 1.0,
|
| 1976 |
+
"count": 123
|
| 1977 |
+
},
|
| 1978 |
+
"US": {
|
| 1979 |
+
"accuracy": 1.0,
|
| 1980 |
+
"count": 77
|
| 1981 |
+
}
|
| 1982 |
+
}
|
| 1983 |
+
},
|
| 1984 |
+
"add_C5": {
|
| 1985 |
+
"full_accuracy": 1.0,
|
| 1986 |
+
"n_examples": 50,
|
| 1987 |
+
"per_subtask": {
|
| 1988 |
+
"SA": {
|
| 1989 |
+
"accuracy": 1.0,
|
| 1990 |
+
"count": 50
|
| 1991 |
+
},
|
| 1992 |
+
"SC": {
|
| 1993 |
+
"accuracy": 1.0,
|
| 1994 |
+
"count": 50
|
| 1995 |
+
},
|
| 1996 |
+
"UC": {
|
| 1997 |
+
"accuracy": 1.0,
|
| 1998 |
+
"count": 154
|
| 1999 |
+
},
|
| 2000 |
+
"US": {
|
| 2001 |
+
"accuracy": 1.0,
|
| 2002 |
+
"count": 96
|
| 2003 |
+
}
|
| 2004 |
+
}
|
| 2005 |
+
},
|
| 2006 |
+
"add_C6": {
|
| 2007 |
+
"full_accuracy": 1.0,
|
| 2008 |
+
"n_examples": 50,
|
| 2009 |
+
"per_subtask": {
|
| 2010 |
+
"SC": {
|
| 2011 |
+
"accuracy": 1.0,
|
| 2012 |
+
"count": 50
|
| 2013 |
+
},
|
| 2014 |
+
"UC": {
|
| 2015 |
+
"accuracy": 1.0,
|
| 2016 |
+
"count": 182
|
| 2017 |
+
},
|
| 2018 |
+
"US": {
|
| 2019 |
+
"accuracy": 1.0,
|
| 2020 |
+
"count": 118
|
| 2021 |
+
}
|
| 2022 |
+
}
|
| 2023 |
+
},
|
| 2024 |
+
"sub_M0": {
|
| 2025 |
+
"full_accuracy": 1.0,
|
| 2026 |
+
"n_examples": 50,
|
| 2027 |
+
"per_subtask": {
|
| 2028 |
+
"MD": {
|
| 2029 |
+
"accuracy": 1.0,
|
| 2030 |
+
"count": 294
|
| 2031 |
+
},
|
| 2032 |
+
"ME": {
|
| 2033 |
+
"accuracy": 1.0,
|
| 2034 |
+
"count": 56
|
| 2035 |
+
}
|
| 2036 |
+
}
|
| 2037 |
+
},
|
| 2038 |
+
"sub_M1": {
|
| 2039 |
+
"full_accuracy": 1.0,
|
| 2040 |
+
"n_examples": 50,
|
| 2041 |
+
"per_subtask": {
|
| 2042 |
+
"MD": {
|
| 2043 |
+
"accuracy": 1.0,
|
| 2044 |
+
"count": 143
|
| 2045 |
+
},
|
| 2046 |
+
"MB": {
|
| 2047 |
+
"accuracy": 1.0,
|
| 2048 |
+
"count": 69
|
| 2049 |
+
},
|
| 2050 |
+
"ME": {
|
| 2051 |
+
"accuracy": 1.0,
|
| 2052 |
+
"count": 15
|
| 2053 |
+
},
|
| 2054 |
+
"UB": {
|
| 2055 |
+
"accuracy": 1.0,
|
| 2056 |
+
"count": 123
|
| 2057 |
+
}
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"sub_M2": {
|
| 2061 |
+
"full_accuracy": 1.0,
|
| 2062 |
+
"n_examples": 50,
|
| 2063 |
+
"per_subtask": {
|
| 2064 |
+
"MD": {
|
| 2065 |
+
"accuracy": 1.0,
|
| 2066 |
+
"count": 108
|
| 2067 |
+
},
|
| 2068 |
+
"MB": {
|
| 2069 |
+
"accuracy": 1.0,
|
| 2070 |
+
"count": 52
|
| 2071 |
+
},
|
| 2072 |
+
"ME": {
|
| 2073 |
+
"accuracy": 1.0,
|
| 2074 |
+
"count": 52
|
| 2075 |
+
},
|
| 2076 |
+
"UB": {
|
| 2077 |
+
"accuracy": 1.0,
|
| 2078 |
+
"count": 87
|
| 2079 |
+
},
|
| 2080 |
+
"UD": {
|
| 2081 |
+
"accuracy": 1.0,
|
| 2082 |
+
"count": 51
|
| 2083 |
+
}
|
| 2084 |
+
}
|
| 2085 |
+
},
|
| 2086 |
+
"sub_M3": {
|
| 2087 |
+
"full_accuracy": 1.0,
|
| 2088 |
+
"n_examples": 50,
|
| 2089 |
+
"per_subtask": {
|
| 2090 |
+
"MD": {
|
| 2091 |
+
"accuracy": 1.0,
|
| 2092 |
+
"count": 94
|
| 2093 |
+
},
|
| 2094 |
+
"MB": {
|
| 2095 |
+
"accuracy": 1.0,
|
| 2096 |
+
"count": 51
|
| 2097 |
+
},
|
| 2098 |
+
"ME": {
|
| 2099 |
+
"accuracy": 1.0,
|
| 2100 |
+
"count": 25
|
| 2101 |
+
},
|
| 2102 |
+
"UB": {
|
| 2103 |
+
"accuracy": 1.0,
|
| 2104 |
+
"count": 78
|
| 2105 |
+
},
|
| 2106 |
+
"UD": {
|
| 2107 |
+
"accuracy": 1.0,
|
| 2108 |
+
"count": 102
|
| 2109 |
+
}
|
| 2110 |
+
}
|
| 2111 |
+
},
|
| 2112 |
+
"sub_M4": {
|
| 2113 |
+
"full_accuracy": 1.0,
|
| 2114 |
+
"n_examples": 50,
|
| 2115 |
+
"per_subtask": {
|
| 2116 |
+
"MD": {
|
| 2117 |
+
"accuracy": 1.0,
|
| 2118 |
+
"count": 100
|
| 2119 |
+
},
|
| 2120 |
+
"MB": {
|
| 2121 |
+
"accuracy": 1.0,
|
| 2122 |
+
"count": 50
|
| 2123 |
+
},
|
| 2124 |
+
"UB": {
|
| 2125 |
+
"accuracy": 1.0,
|
| 2126 |
+
"count": 50
|
| 2127 |
+
},
|
| 2128 |
+
"UD": {
|
| 2129 |
+
"accuracy": 1.0,
|
| 2130 |
+
"count": 150
|
| 2131 |
+
}
|
| 2132 |
+
}
|
| 2133 |
+
},
|
| 2134 |
+
"sub_M5": {
|
| 2135 |
+
"full_accuracy": 1.0,
|
| 2136 |
+
"n_examples": 50,
|
| 2137 |
+
"per_subtask": {
|
| 2138 |
+
"MD": {
|
| 2139 |
+
"accuracy": 1.0,
|
| 2140 |
+
"count": 50
|
| 2141 |
+
},
|
| 2142 |
+
"MB": {
|
| 2143 |
+
"accuracy": 1.0,
|
| 2144 |
+
"count": 50
|
| 2145 |
+
},
|
| 2146 |
+
"UB": {
|
| 2147 |
+
"accuracy": 1.0,
|
| 2148 |
+
"count": 50
|
| 2149 |
+
},
|
| 2150 |
+
"UD": {
|
| 2151 |
+
"accuracy": 1.0,
|
| 2152 |
+
"count": 200
|
| 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": 588
|
| 2163 |
+
},
|
| 2164 |
+
"MB": {
|
| 2165 |
+
"accuracy": 1.0,
|
| 2166 |
+
"count": 268
|
| 2167 |
+
},
|
| 2168 |
+
"ME": {
|
| 2169 |
+
"accuracy": 1.0,
|
| 2170 |
+
"count": 60
|
| 2171 |
+
},
|
| 2172 |
+
"UB": {
|
| 2173 |
+
"accuracy": 1.0,
|
| 2174 |
+
"count": 447
|
| 2175 |
+
},
|
| 2176 |
+
"UD": {
|
| 2177 |
+
"accuracy": 1.0,
|
| 2178 |
+
"count": 37
|
| 2179 |
+
}
|
| 2180 |
+
}
|
| 2181 |
+
},
|
| 2182 |
+
"sub_B3": {
|
| 2183 |
+
"full_accuracy": 1.0,
|
| 2184 |
+
"n_examples": 50,
|
| 2185 |
+
"per_subtask": {
|
| 2186 |
+
"MD": {
|
| 2187 |
+
"accuracy": 1.0,
|
| 2188 |
+
"count": 150
|
| 2189 |
+
},
|
| 2190 |
+
"MB": {
|
| 2191 |
+
"accuracy": 1.0,
|
| 2192 |
+
"count": 50
|
| 2193 |
+
},
|
| 2194 |
+
"UB": {
|
| 2195 |
+
"accuracy": 1.0,
|
| 2196 |
+
"count": 107
|
| 2197 |
+
},
|
| 2198 |
+
"UD": {
|
| 2199 |
+
"accuracy": 1.0,
|
| 2200 |
+
"count": 43
|
| 2201 |
+
}
|
| 2202 |
+
}
|
| 2203 |
+
},
|
| 2204 |
+
"sub_B4": {
|
| 2205 |
+
"full_accuracy": 1.0,
|
| 2206 |
+
"n_examples": 50,
|
| 2207 |
+
"per_subtask": {
|
| 2208 |
+
"MD": {
|
| 2209 |
+
"accuracy": 1.0,
|
| 2210 |
+
"count": 100
|
| 2211 |
+
},
|
| 2212 |
+
"MB": {
|
| 2213 |
+
"accuracy": 1.0,
|
| 2214 |
+
"count": 50
|
| 2215 |
+
},
|
| 2216 |
+
"UB": {
|
| 2217 |
+
"accuracy": 1.0,
|
| 2218 |
+
"count": 114
|
| 2219 |
+
},
|
| 2220 |
+
"UD": {
|
| 2221 |
+
"accuracy": 1.0,
|
| 2222 |
+
"count": 86
|
| 2223 |
+
}
|
| 2224 |
+
}
|
| 2225 |
+
},
|
| 2226 |
+
"sub_B5": {
|
| 2227 |
+
"full_accuracy": 1.0,
|
| 2228 |
+
"n_examples": 50,
|
| 2229 |
+
"per_subtask": {
|
| 2230 |
+
"MD": {
|
| 2231 |
+
"accuracy": 1.0,
|
| 2232 |
+
"count": 50
|
| 2233 |
+
},
|
| 2234 |
+
"MB": {
|
| 2235 |
+
"accuracy": 1.0,
|
| 2236 |
+
"count": 50
|
| 2237 |
+
},
|
| 2238 |
+
"UB": {
|
| 2239 |
+
"accuracy": 1.0,
|
| 2240 |
+
"count": 153
|
| 2241 |
+
},
|
| 2242 |
+
"UD": {
|
| 2243 |
+
"accuracy": 1.0,
|
| 2244 |
+
"count": 97
|
| 2245 |
+
}
|
| 2246 |
+
}
|
| 2247 |
+
}
|
| 2248 |
+
},
|
| 2249 |
+
"summary": {
|
| 2250 |
+
"overall_accuracy": 1.0,
|
| 2251 |
+
"total_examples": 1400,
|
| 2252 |
+
"n_splits": 22
|
| 2253 |
+
}
|
| 2254 |
+
},
|
| 2255 |
+
"sorl_overall_accuracy": 1.0,
|
| 2256 |
+
"sft_overall_accuracy": 0.9964285714285714
|
| 2257 |
+
}
|
add_sub_sorl_v1_abs10_K1_50K/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dcf90a20c26c5b68f843a61059999485f735079999d942153afd32e303fdb71
|
| 3 |
+
size 650303660
|
add_sub_sorl_v1_abs10_K1_50K/train_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mode": "sorl",
|
| 3 |
+
"ops": "add_sub",
|
| 4 |
+
"n_digits": 6,
|
| 5 |
+
"n_layer": 2,
|
| 6 |
+
"n_head": 3,
|
| 7 |
+
"n_embd": 510,
|
| 8 |
+
"abs_vocab": 10,
|
| 9 |
+
"K": 1,
|
| 10 |
+
"alpha_info_gain": 10.0,
|
| 11 |
+
"alpha_abs": 0.1,
|
| 12 |
+
"alpha_soft_zipf": 1.0,
|
| 13 |
+
"batch_size": 64,
|
| 14 |
+
"num_epochs": 10,
|
| 15 |
+
"dataset_size": 50000,
|
| 16 |
+
"lr": 8e-05,
|
| 17 |
+
"output_dir": "ckpt/sweep/as_sorl_abs10_K1_50K",
|
| 18 |
+
"device": "cuda",
|
| 19 |
+
"push_to_hub": true,
|
| 20 |
+
"no_wandb": false,
|
| 21 |
+
"n_params": 162499262,
|
| 22 |
+
"run_name": "add_sub_sorl_v1_abs10_K1_50K",
|
| 23 |
+
"git_commit": "800625019270114adcda289bbd550c4f1109a514",
|
| 24 |
+
"timestamp": "2026-04-12T01:58:11.881229+00:00",
|
| 25 |
+
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 26 |
+
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 27 |
+
"dataset_config": "add_sub_6digit",
|
| 28 |
+
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 29 |
+
"trainer_version": "v1",
|
| 30 |
+
"wandb_run_id": "yb0fucvp",
|
| 31 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/yb0fucvp",
|
| 32 |
+
"final_accuracy": 1.0,
|
| 33 |
+
"sft_accuracy": 0.9964285714285714,
|
| 34 |
+
"eval_method": "ArithmeticEvaluator"
|
| 35 |
+
}
|