Upload add_baseline_250K
Browse files
add_baseline_250K/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2048,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention"
|
| 19 |
+
],
|
| 20 |
+
"max_position_embeddings": 128,
|
| 21 |
+
"max_window_layers": 28,
|
| 22 |
+
"model_type": "qwen3",
|
| 23 |
+
"num_attention_heads": 4,
|
| 24 |
+
"num_hidden_layers": 3,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
+
"pad_token_id": null,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_parameters": {
|
| 29 |
+
"rope_theta": 10000.0,
|
| 30 |
+
"rope_type": "default"
|
| 31 |
+
},
|
| 32 |
+
"sliding_window": null,
|
| 33 |
+
"tie_word_embeddings": false,
|
| 34 |
+
"transformers_version": "5.5.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151645
|
| 38 |
+
}
|
add_baseline_250K/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_baseline_250K/metrics.json
ADDED
|
@@ -0,0 +1,949 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
800,
|
| 20 |
+
850,
|
| 21 |
+
900,
|
| 22 |
+
950,
|
| 23 |
+
1000,
|
| 24 |
+
1050,
|
| 25 |
+
1100,
|
| 26 |
+
1150,
|
| 27 |
+
1200,
|
| 28 |
+
1250,
|
| 29 |
+
1300,
|
| 30 |
+
1350,
|
| 31 |
+
1400,
|
| 32 |
+
1450,
|
| 33 |
+
1500,
|
| 34 |
+
1550,
|
| 35 |
+
1600,
|
| 36 |
+
1650,
|
| 37 |
+
1700,
|
| 38 |
+
1750,
|
| 39 |
+
1800,
|
| 40 |
+
1850,
|
| 41 |
+
1900,
|
| 42 |
+
1950,
|
| 43 |
+
2000,
|
| 44 |
+
2050,
|
| 45 |
+
2100,
|
| 46 |
+
2150,
|
| 47 |
+
2200,
|
| 48 |
+
2250,
|
| 49 |
+
2300,
|
| 50 |
+
2350,
|
| 51 |
+
2400,
|
| 52 |
+
2450,
|
| 53 |
+
2500,
|
| 54 |
+
2550,
|
| 55 |
+
2600,
|
| 56 |
+
2650,
|
| 57 |
+
2700,
|
| 58 |
+
2750,
|
| 59 |
+
2800,
|
| 60 |
+
2850,
|
| 61 |
+
2900,
|
| 62 |
+
2950,
|
| 63 |
+
3000,
|
| 64 |
+
3050,
|
| 65 |
+
3100,
|
| 66 |
+
3150,
|
| 67 |
+
3200,
|
| 68 |
+
3250,
|
| 69 |
+
3300,
|
| 70 |
+
3350,
|
| 71 |
+
3400,
|
| 72 |
+
3450,
|
| 73 |
+
3500,
|
| 74 |
+
3550,
|
| 75 |
+
3600,
|
| 76 |
+
3650,
|
| 77 |
+
3700,
|
| 78 |
+
3750,
|
| 79 |
+
3800,
|
| 80 |
+
3850,
|
| 81 |
+
3900,
|
| 82 |
+
3950,
|
| 83 |
+
4000,
|
| 84 |
+
4050,
|
| 85 |
+
4100,
|
| 86 |
+
4150,
|
| 87 |
+
4200,
|
| 88 |
+
4250,
|
| 89 |
+
4300,
|
| 90 |
+
4350,
|
| 91 |
+
4400,
|
| 92 |
+
4450,
|
| 93 |
+
4500,
|
| 94 |
+
4550,
|
| 95 |
+
4600,
|
| 96 |
+
4650,
|
| 97 |
+
4700,
|
| 98 |
+
4750,
|
| 99 |
+
4800,
|
| 100 |
+
4850,
|
| 101 |
+
4900,
|
| 102 |
+
4950,
|
| 103 |
+
5000,
|
| 104 |
+
5050,
|
| 105 |
+
5100,
|
| 106 |
+
5150,
|
| 107 |
+
5200,
|
| 108 |
+
5250,
|
| 109 |
+
5300,
|
| 110 |
+
5350,
|
| 111 |
+
5400,
|
| 112 |
+
5450,
|
| 113 |
+
5500,
|
| 114 |
+
5550,
|
| 115 |
+
5600,
|
| 116 |
+
5650,
|
| 117 |
+
5700,
|
| 118 |
+
5750,
|
| 119 |
+
5800,
|
| 120 |
+
5850,
|
| 121 |
+
5900,
|
| 122 |
+
5950,
|
| 123 |
+
6000,
|
| 124 |
+
6050,
|
| 125 |
+
6100,
|
| 126 |
+
6150,
|
| 127 |
+
6200,
|
| 128 |
+
6250,
|
| 129 |
+
6300,
|
| 130 |
+
6350,
|
| 131 |
+
6400,
|
| 132 |
+
6450,
|
| 133 |
+
6500,
|
| 134 |
+
6550,
|
| 135 |
+
6600,
|
| 136 |
+
6650,
|
| 137 |
+
6700,
|
| 138 |
+
6750,
|
| 139 |
+
6800,
|
| 140 |
+
6850,
|
| 141 |
+
6900,
|
| 142 |
+
6950,
|
| 143 |
+
7000,
|
| 144 |
+
7050,
|
| 145 |
+
7100,
|
| 146 |
+
7150,
|
| 147 |
+
7200,
|
| 148 |
+
7250,
|
| 149 |
+
7300,
|
| 150 |
+
7350,
|
| 151 |
+
7400,
|
| 152 |
+
7450,
|
| 153 |
+
7500,
|
| 154 |
+
7550,
|
| 155 |
+
7600,
|
| 156 |
+
7650,
|
| 157 |
+
7700,
|
| 158 |
+
7750,
|
| 159 |
+
7800,
|
| 160 |
+
7850,
|
| 161 |
+
7900,
|
| 162 |
+
7950,
|
| 163 |
+
8000,
|
| 164 |
+
8050,
|
| 165 |
+
8100,
|
| 166 |
+
8150,
|
| 167 |
+
8200,
|
| 168 |
+
8250,
|
| 169 |
+
8300,
|
| 170 |
+
8350,
|
| 171 |
+
8400,
|
| 172 |
+
8450,
|
| 173 |
+
8500,
|
| 174 |
+
8550,
|
| 175 |
+
8600,
|
| 176 |
+
8650,
|
| 177 |
+
8700,
|
| 178 |
+
8750,
|
| 179 |
+
8800,
|
| 180 |
+
8850,
|
| 181 |
+
8900,
|
| 182 |
+
8950,
|
| 183 |
+
9000,
|
| 184 |
+
9050,
|
| 185 |
+
9100,
|
| 186 |
+
9150,
|
| 187 |
+
9200,
|
| 188 |
+
9250,
|
| 189 |
+
9300,
|
| 190 |
+
9350,
|
| 191 |
+
9400,
|
| 192 |
+
9450,
|
| 193 |
+
9500,
|
| 194 |
+
9550,
|
| 195 |
+
9600,
|
| 196 |
+
9650,
|
| 197 |
+
9700,
|
| 198 |
+
9750,
|
| 199 |
+
9800,
|
| 200 |
+
9850,
|
| 201 |
+
9900,
|
| 202 |
+
9950,
|
| 203 |
+
10000,
|
| 204 |
+
10050,
|
| 205 |
+
10100,
|
| 206 |
+
10150,
|
| 207 |
+
10200,
|
| 208 |
+
10250,
|
| 209 |
+
10300,
|
| 210 |
+
10350,
|
| 211 |
+
10400,
|
| 212 |
+
10450,
|
| 213 |
+
10500,
|
| 214 |
+
10550,
|
| 215 |
+
10600,
|
| 216 |
+
10650,
|
| 217 |
+
10700,
|
| 218 |
+
10750,
|
| 219 |
+
10800,
|
| 220 |
+
10850,
|
| 221 |
+
10900,
|
| 222 |
+
10950,
|
| 223 |
+
11000,
|
| 224 |
+
11050,
|
| 225 |
+
11100,
|
| 226 |
+
11150,
|
| 227 |
+
11200,
|
| 228 |
+
11250,
|
| 229 |
+
11300,
|
| 230 |
+
11350,
|
| 231 |
+
11400,
|
| 232 |
+
11450,
|
| 233 |
+
11500,
|
| 234 |
+
11550,
|
| 235 |
+
11600,
|
| 236 |
+
11650,
|
| 237 |
+
11700
|
| 238 |
+
],
|
| 239 |
+
"loss": [
|
| 240 |
+
11.527762413024902,
|
| 241 |
+
9.60785961151123,
|
| 242 |
+
8.368090629577637,
|
| 243 |
+
7.383299350738525,
|
| 244 |
+
7.280657768249512,
|
| 245 |
+
6.5229620933532715,
|
| 246 |
+
6.247063636779785,
|
| 247 |
+
5.47233247756958,
|
| 248 |
+
5.035149574279785,
|
| 249 |
+
4.5038347244262695,
|
| 250 |
+
3.891714334487915,
|
| 251 |
+
3.095801830291748,
|
| 252 |
+
2.6873838901519775,
|
| 253 |
+
2.2019026279449463,
|
| 254 |
+
1.9425586462020874,
|
| 255 |
+
1.8074508905410767,
|
| 256 |
+
1.5963990688323975,
|
| 257 |
+
1.580202341079712,
|
| 258 |
+
1.3961509466171265,
|
| 259 |
+
1.356629729270935,
|
| 260 |
+
1.0582406520843506,
|
| 261 |
+
0.8591527938842773,
|
| 262 |
+
0.6051973104476929,
|
| 263 |
+
0.5020413994789124,
|
| 264 |
+
0.3830282390117645,
|
| 265 |
+
0.3321951925754547,
|
| 266 |
+
0.2272447794675827,
|
| 267 |
+
0.20413623750209808,
|
| 268 |
+
0.2055785208940506,
|
| 269 |
+
0.20350274443626404,
|
| 270 |
+
0.21641121804714203,
|
| 271 |
+
0.15464866161346436,
|
| 272 |
+
0.1415574997663498,
|
| 273 |
+
0.09492872655391693,
|
| 274 |
+
0.057180773466825485,
|
| 275 |
+
0.10457637161016464,
|
| 276 |
+
0.07520271837711334,
|
| 277 |
+
0.06334521621465683,
|
| 278 |
+
0.03505897521972656,
|
| 279 |
+
0.05057087540626526,
|
| 280 |
+
0.020688626915216446,
|
| 281 |
+
0.12356334179639816,
|
| 282 |
+
0.028574582189321518,
|
| 283 |
+
0.006245631258934736,
|
| 284 |
+
0.007917485199868679,
|
| 285 |
+
0.010751918889582157,
|
| 286 |
+
0.012803385965526104,
|
| 287 |
+
0.028944775462150574,
|
| 288 |
+
0.008806764148175716,
|
| 289 |
+
0.013823815621435642,
|
| 290 |
+
0.0017021530074998736,
|
| 291 |
+
0.011414808221161366,
|
| 292 |
+
0.0220631193369627,
|
| 293 |
+
0.05565088614821434,
|
| 294 |
+
0.010557984933257103,
|
| 295 |
+
0.012765188701450825,
|
| 296 |
+
0.0020553823560476303,
|
| 297 |
+
0.0034588086418807507,
|
| 298 |
+
0.0006399106932803988,
|
| 299 |
+
0.0011771806748583913,
|
| 300 |
+
0.0023959032259881496,
|
| 301 |
+
0.0023975500371307135,
|
| 302 |
+
0.018105758354067802,
|
| 303 |
+
0.04133778065443039,
|
| 304 |
+
0.0013915597228333354,
|
| 305 |
+
0.006245000753551722,
|
| 306 |
+
0.0005129611818119884,
|
| 307 |
+
0.0005555239040404558,
|
| 308 |
+
0.012398910708725452,
|
| 309 |
+
0.00034711038460955024,
|
| 310 |
+
0.031024495139718056,
|
| 311 |
+
0.0004809148085769266,
|
| 312 |
+
0.0059379274025559425,
|
| 313 |
+
0.0019757128320634365,
|
| 314 |
+
0.002303863177075982,
|
| 315 |
+
0.008580265566706657,
|
| 316 |
+
0.044498324394226074,
|
| 317 |
+
0.0005247122026048601,
|
| 318 |
+
0.0002977796539198607,
|
| 319 |
+
0.0001751357049215585,
|
| 320 |
+
0.00045993420644663274,
|
| 321 |
+
0.001147810253314674,
|
| 322 |
+
0.00020777320605702698,
|
| 323 |
+
0.001379889203235507,
|
| 324 |
+
0.10030525177717209,
|
| 325 |
+
0.0011350951390340924,
|
| 326 |
+
9.659335046308115e-05,
|
| 327 |
+
0.017756644636392593,
|
| 328 |
+
0.00024583865888416767,
|
| 329 |
+
0.0007470060954801738,
|
| 330 |
+
0.0035779124591499567,
|
| 331 |
+
6.258876237552613e-05,
|
| 332 |
+
0.00015140332106966525,
|
| 333 |
+
0.00010764774197014049,
|
| 334 |
+
0.0004173603665549308,
|
| 335 |
+
0.00039286998799070716,
|
| 336 |
+
0.009674607776105404,
|
| 337 |
+
0.0008037807419896126,
|
| 338 |
+
0.0003438284620642662,
|
| 339 |
+
2.7261923605692573e-05,
|
| 340 |
+
1.9322336811455898e-05,
|
| 341 |
+
1.4822441698925104e-05,
|
| 342 |
+
1.2943323781655636e-05,
|
| 343 |
+
9.299021257902496e-06,
|
| 344 |
+
8.155104296747595e-06,
|
| 345 |
+
5.793860964331543e-06,
|
| 346 |
+
4.422701294970466e-06,
|
| 347 |
+
3.674987965496257e-06,
|
| 348 |
+
2.6510701900406275e-06,
|
| 349 |
+
1.8860583850255352e-06,
|
| 350 |
+
1.303584099332511e-06,
|
| 351 |
+
1.0718167686718516e-06,
|
| 352 |
+
6.710839670631685e-07,
|
| 353 |
+
0.0009319929522462189,
|
| 354 |
+
0.005028906278312206,
|
| 355 |
+
0.0005372653831727803,
|
| 356 |
+
0.001486061024479568,
|
| 357 |
+
0.00043799448758363724,
|
| 358 |
+
6.41662427369738e-06,
|
| 359 |
+
2.2846294086775742e-05,
|
| 360 |
+
0.0011698914458975196,
|
| 361 |
+
1.411192806699546e-05,
|
| 362 |
+
3.597779368647025e-06,
|
| 363 |
+
2.8835968350904295e-06,
|
| 364 |
+
2.1955186184641207e-06,
|
| 365 |
+
1.761260364219197e-06,
|
| 366 |
+
2.0156246591795934e-06,
|
| 367 |
+
1.3381753660723916e-06,
|
| 368 |
+
1.087783516595664e-06,
|
| 369 |
+
8.376574101021106e-07,
|
| 370 |
+
7.514436788369494e-07,
|
| 371 |
+
6.274443649090244e-07,
|
| 372 |
+
4.76836959251159e-07,
|
| 373 |
+
4.37189243029934e-07,
|
| 374 |
+
2.9376568022598804e-07,
|
| 375 |
+
8.245482604252174e-06,
|
| 376 |
+
1.9750748833757825e-05,
|
| 377 |
+
3.447827793934266e-06,
|
| 378 |
+
1.0258479960612021e-05,
|
| 379 |
+
1.7356948092128732e-06,
|
| 380 |
+
9.67773644333647e-07,
|
| 381 |
+
9.065719837053621e-07,
|
| 382 |
+
8.836892106955929e-07,
|
| 383 |
+
7.876305971876718e-07,
|
| 384 |
+
6.122771765149082e-07,
|
| 385 |
+
5.670402174473566e-07,
|
| 386 |
+
0.00046179426135495305,
|
| 387 |
+
3.868092335324036e-06,
|
| 388 |
+
6.624807610933203e-06,
|
| 389 |
+
0.00026054339832626283,
|
| 390 |
+
1.8271704902872443e-05,
|
| 391 |
+
2.229476649517892e-06,
|
| 392 |
+
1.5850853287702193e-06,
|
| 393 |
+
1.3381724784267135e-05,
|
| 394 |
+
2.807744749588892e-06,
|
| 395 |
+
1.2921385632580495e-06,
|
| 396 |
+
1.3796767461826676e-06,
|
| 397 |
+
8.291417543659918e-07,
|
| 398 |
+
7.852366934457677e-07,
|
| 399 |
+
5.457544602904818e-07,
|
| 400 |
+
4.74442003906006e-07,
|
| 401 |
+
4.313349393214594e-07,
|
| 402 |
+
3.2223741186498955e-07,
|
| 403 |
+
3.009499778272584e-07,
|
| 404 |
+
2.394828584328934e-07,
|
| 405 |
+
2.394824036855425e-07,
|
| 406 |
+
1.381017682433594e-07,
|
| 407 |
+
1.0058282384761696e-07,
|
| 408 |
+
7.423970060926877e-08,
|
| 409 |
+
5.907244826630631e-08,
|
| 410 |
+
4.7896580923634247e-08,
|
| 411 |
+
3.299542328250027e-08,
|
| 412 |
+
2.7673580760279037e-08,
|
| 413 |
+
1.969081608876877e-08,
|
| 414 |
+
1.889254086506753e-08,
|
| 415 |
+
1.862644971595273e-08,
|
| 416 |
+
1.7562081566779852e-08,
|
| 417 |
+
1.6763804566721774e-08,
|
| 418 |
+
1.330460630555308e-08,
|
| 419 |
+
9.313224857976365e-09,
|
| 420 |
+
9.579316895269585e-09,
|
| 421 |
+
8.514947857918287e-09,
|
| 422 |
+
7.450580152834618e-09,
|
| 423 |
+
8.514947857918287e-09,
|
| 424 |
+
1.1441962044500542e-08,
|
| 425 |
+
8.781040783389926e-09,
|
| 426 |
+
9.047132820683146e-09,
|
| 427 |
+
7.184488115541399e-09,
|
| 428 |
+
1.1175870007207322e-08,
|
| 429 |
+
9.579316895269585e-09,
|
| 430 |
+
8.781040783389926e-09,
|
| 431 |
+
6.6523035968657496e-09,
|
| 432 |
+
6.65230315277654e-09,
|
| 433 |
+
8.781040783389926e-09,
|
| 434 |
+
8.514947857918287e-09,
|
| 435 |
+
6.918395190069759e-09,
|
| 436 |
+
9.579316895269585e-09,
|
| 437 |
+
8.248855820625067e-09,
|
| 438 |
+
6.38621155957253e-09,
|
| 439 |
+
6.1201190781901005e-09,
|
| 440 |
+
6.6523035968657496e-09,
|
| 441 |
+
7.982763783331848e-09,
|
| 442 |
+
1.0111500969856024e-08,
|
| 443 |
+
8.248855820625067e-09,
|
| 444 |
+
7.982763783331848e-09,
|
| 445 |
+
7.716671746038628e-09,
|
| 446 |
+
7.184487227362979e-09,
|
| 447 |
+
7.716672634217048e-09,
|
| 448 |
+
7.184488115541399e-09,
|
| 449 |
+
5.321842966310442e-09,
|
| 450 |
+
8.514947857918287e-09,
|
| 451 |
+
6.918395634158969e-09,
|
| 452 |
+
5.854027040896881e-09,
|
| 453 |
+
6.65230315277654e-09,
|
| 454 |
+
9.579316895269585e-09,
|
| 455 |
+
9.047132820683146e-09,
|
| 456 |
+
6.38621155957253e-09,
|
| 457 |
+
6.6523035968657496e-09,
|
| 458 |
+
1.0377593007149244e-08,
|
| 459 |
+
5.321842966310442e-09,
|
| 460 |
+
7.184487227362979e-09,
|
| 461 |
+
4.2574739289591434e-09,
|
| 462 |
+
6.1201190781901005e-09,
|
| 463 |
+
7.982763783331848e-09,
|
| 464 |
+
7.716671746038628e-09,
|
| 465 |
+
7.982763783331848e-09,
|
| 466 |
+
7.184488115541399e-09,
|
| 467 |
+
8.514947857918287e-09,
|
| 468 |
+
9.845408932562805e-09,
|
| 469 |
+
6.6523035968657496e-09,
|
| 470 |
+
7.716671746038628e-09,
|
| 471 |
+
6.65230315277654e-09,
|
| 472 |
+
5.321842966310442e-09,
|
| 473 |
+
6.6523035968657496e-09
|
| 474 |
+
],
|
| 475 |
+
"base_loss": [
|
| 476 |
+
11.527762413024902,
|
| 477 |
+
9.60785961151123,
|
| 478 |
+
8.368090629577637,
|
| 479 |
+
7.383299350738525,
|
| 480 |
+
7.280657768249512,
|
| 481 |
+
6.5229620933532715,
|
| 482 |
+
6.247063636779785,
|
| 483 |
+
5.47233247756958,
|
| 484 |
+
5.035149574279785,
|
| 485 |
+
4.5038347244262695,
|
| 486 |
+
3.891714334487915,
|
| 487 |
+
3.095801830291748,
|
| 488 |
+
2.6873838901519775,
|
| 489 |
+
2.2019026279449463,
|
| 490 |
+
1.9425586462020874,
|
| 491 |
+
1.8074508905410767,
|
| 492 |
+
1.5963990688323975,
|
| 493 |
+
1.580202341079712,
|
| 494 |
+
1.3961509466171265,
|
| 495 |
+
1.356629729270935,
|
| 496 |
+
1.0582406520843506,
|
| 497 |
+
0.8591527938842773,
|
| 498 |
+
0.6051973104476929,
|
| 499 |
+
0.5020413994789124,
|
| 500 |
+
0.3830282390117645,
|
| 501 |
+
0.3321951925754547,
|
| 502 |
+
0.2272447794675827,
|
| 503 |
+
0.20413623750209808,
|
| 504 |
+
0.2055785208940506,
|
| 505 |
+
0.20350274443626404,
|
| 506 |
+
0.21641121804714203,
|
| 507 |
+
0.15464866161346436,
|
| 508 |
+
0.1415574997663498,
|
| 509 |
+
0.09492872655391693,
|
| 510 |
+
0.057180773466825485,
|
| 511 |
+
0.10457637161016464,
|
| 512 |
+
0.07520271837711334,
|
| 513 |
+
0.06334521621465683,
|
| 514 |
+
0.03505897521972656,
|
| 515 |
+
0.05057087540626526,
|
| 516 |
+
0.020688626915216446,
|
| 517 |
+
0.12356334179639816,
|
| 518 |
+
0.028574582189321518,
|
| 519 |
+
0.006245631258934736,
|
| 520 |
+
0.007917485199868679,
|
| 521 |
+
0.010751918889582157,
|
| 522 |
+
0.012803385965526104,
|
| 523 |
+
0.028944775462150574,
|
| 524 |
+
0.008806764148175716,
|
| 525 |
+
0.013823815621435642,
|
| 526 |
+
0.0017021530074998736,
|
| 527 |
+
0.011414808221161366,
|
| 528 |
+
0.0220631193369627,
|
| 529 |
+
0.05565088614821434,
|
| 530 |
+
0.010557984933257103,
|
| 531 |
+
0.012765188701450825,
|
| 532 |
+
0.0020553823560476303,
|
| 533 |
+
0.0034588086418807507,
|
| 534 |
+
0.0006399106932803988,
|
| 535 |
+
0.0011771806748583913,
|
| 536 |
+
0.0023959032259881496,
|
| 537 |
+
0.0023975500371307135,
|
| 538 |
+
0.018105758354067802,
|
| 539 |
+
0.04133778065443039,
|
| 540 |
+
0.0013915597228333354,
|
| 541 |
+
0.006245000753551722,
|
| 542 |
+
0.0005129611818119884,
|
| 543 |
+
0.0005555239040404558,
|
| 544 |
+
0.012398910708725452,
|
| 545 |
+
0.00034711038460955024,
|
| 546 |
+
0.031024495139718056,
|
| 547 |
+
0.0004809148085769266,
|
| 548 |
+
0.0059379274025559425,
|
| 549 |
+
0.0019757128320634365,
|
| 550 |
+
0.002303863177075982,
|
| 551 |
+
0.008580265566706657,
|
| 552 |
+
0.044498324394226074,
|
| 553 |
+
0.0005247122026048601,
|
| 554 |
+
0.0002977796539198607,
|
| 555 |
+
0.0001751357049215585,
|
| 556 |
+
0.00045993420644663274,
|
| 557 |
+
0.001147810253314674,
|
| 558 |
+
0.00020777320605702698,
|
| 559 |
+
0.001379889203235507,
|
| 560 |
+
0.10030525177717209,
|
| 561 |
+
0.0011350951390340924,
|
| 562 |
+
9.659335046308115e-05,
|
| 563 |
+
0.017756644636392593,
|
| 564 |
+
0.00024583865888416767,
|
| 565 |
+
0.0007470060954801738,
|
| 566 |
+
0.0035779124591499567,
|
| 567 |
+
6.258876237552613e-05,
|
| 568 |
+
0.00015140332106966525,
|
| 569 |
+
0.00010764774197014049,
|
| 570 |
+
0.0004173603665549308,
|
| 571 |
+
0.00039286998799070716,
|
| 572 |
+
0.009674607776105404,
|
| 573 |
+
0.0008037807419896126,
|
| 574 |
+
0.0003438284620642662,
|
| 575 |
+
2.7261923605692573e-05,
|
| 576 |
+
1.9322336811455898e-05,
|
| 577 |
+
1.4822441698925104e-05,
|
| 578 |
+
1.2943323781655636e-05,
|
| 579 |
+
9.299021257902496e-06,
|
| 580 |
+
8.155104296747595e-06,
|
| 581 |
+
5.793860964331543e-06,
|
| 582 |
+
4.422701294970466e-06,
|
| 583 |
+
3.674987965496257e-06,
|
| 584 |
+
2.6510701900406275e-06,
|
| 585 |
+
1.8860583850255352e-06,
|
| 586 |
+
1.303584099332511e-06,
|
| 587 |
+
1.0718167686718516e-06,
|
| 588 |
+
6.710839670631685e-07,
|
| 589 |
+
0.0009319929522462189,
|
| 590 |
+
0.005028906278312206,
|
| 591 |
+
0.0005372653831727803,
|
| 592 |
+
0.001486061024479568,
|
| 593 |
+
0.00043799448758363724,
|
| 594 |
+
6.41662427369738e-06,
|
| 595 |
+
2.2846294086775742e-05,
|
| 596 |
+
0.0011698914458975196,
|
| 597 |
+
1.411192806699546e-05,
|
| 598 |
+
3.597779368647025e-06,
|
| 599 |
+
2.8835968350904295e-06,
|
| 600 |
+
2.1955186184641207e-06,
|
| 601 |
+
1.761260364219197e-06,
|
| 602 |
+
2.0156246591795934e-06,
|
| 603 |
+
1.3381753660723916e-06,
|
| 604 |
+
1.087783516595664e-06,
|
| 605 |
+
8.376574101021106e-07,
|
| 606 |
+
7.514436788369494e-07,
|
| 607 |
+
6.274443649090244e-07,
|
| 608 |
+
4.76836959251159e-07,
|
| 609 |
+
4.37189243029934e-07,
|
| 610 |
+
2.9376568022598804e-07,
|
| 611 |
+
8.245482604252174e-06,
|
| 612 |
+
1.9750748833757825e-05,
|
| 613 |
+
3.447827793934266e-06,
|
| 614 |
+
1.0258479960612021e-05,
|
| 615 |
+
1.7356948092128732e-06,
|
| 616 |
+
9.67773644333647e-07,
|
| 617 |
+
9.065719837053621e-07,
|
| 618 |
+
8.836892106955929e-07,
|
| 619 |
+
7.876305971876718e-07,
|
| 620 |
+
6.122771765149082e-07,
|
| 621 |
+
5.670402174473566e-07,
|
| 622 |
+
0.00046179426135495305,
|
| 623 |
+
3.868092335324036e-06,
|
| 624 |
+
6.624807610933203e-06,
|
| 625 |
+
0.00026054339832626283,
|
| 626 |
+
1.8271704902872443e-05,
|
| 627 |
+
2.229476649517892e-06,
|
| 628 |
+
1.5850853287702193e-06,
|
| 629 |
+
1.3381724784267135e-05,
|
| 630 |
+
2.807744749588892e-06,
|
| 631 |
+
1.2921385632580495e-06,
|
| 632 |
+
1.3796767461826676e-06,
|
| 633 |
+
8.291417543659918e-07,
|
| 634 |
+
7.852366934457677e-07,
|
| 635 |
+
5.457544602904818e-07,
|
| 636 |
+
4.74442003906006e-07,
|
| 637 |
+
4.313349393214594e-07,
|
| 638 |
+
3.2223741186498955e-07,
|
| 639 |
+
3.009499778272584e-07,
|
| 640 |
+
2.394828584328934e-07,
|
| 641 |
+
2.394824036855425e-07,
|
| 642 |
+
1.381017682433594e-07,
|
| 643 |
+
1.0058282384761696e-07,
|
| 644 |
+
7.423970060926877e-08,
|
| 645 |
+
5.907244826630631e-08,
|
| 646 |
+
4.7896580923634247e-08,
|
| 647 |
+
3.299542328250027e-08,
|
| 648 |
+
2.7673580760279037e-08,
|
| 649 |
+
1.969081608876877e-08,
|
| 650 |
+
1.889254086506753e-08,
|
| 651 |
+
1.862644971595273e-08,
|
| 652 |
+
1.7562081566779852e-08,
|
| 653 |
+
1.6763804566721774e-08,
|
| 654 |
+
1.330460630555308e-08,
|
| 655 |
+
9.313224857976365e-09,
|
| 656 |
+
9.579316895269585e-09,
|
| 657 |
+
8.514947857918287e-09,
|
| 658 |
+
7.450580152834618e-09,
|
| 659 |
+
8.514947857918287e-09,
|
| 660 |
+
1.1441962044500542e-08,
|
| 661 |
+
8.781040783389926e-09,
|
| 662 |
+
9.047132820683146e-09,
|
| 663 |
+
7.184488115541399e-09,
|
| 664 |
+
1.1175870007207322e-08,
|
| 665 |
+
9.579316895269585e-09,
|
| 666 |
+
8.781040783389926e-09,
|
| 667 |
+
6.6523035968657496e-09,
|
| 668 |
+
6.65230315277654e-09,
|
| 669 |
+
8.781040783389926e-09,
|
| 670 |
+
8.514947857918287e-09,
|
| 671 |
+
6.918395190069759e-09,
|
| 672 |
+
9.579316895269585e-09,
|
| 673 |
+
8.248855820625067e-09,
|
| 674 |
+
6.38621155957253e-09,
|
| 675 |
+
6.1201190781901005e-09,
|
| 676 |
+
6.6523035968657496e-09,
|
| 677 |
+
7.982763783331848e-09,
|
| 678 |
+
1.0111500969856024e-08,
|
| 679 |
+
8.248855820625067e-09,
|
| 680 |
+
7.982763783331848e-09,
|
| 681 |
+
7.716671746038628e-09,
|
| 682 |
+
7.184487227362979e-09,
|
| 683 |
+
7.716672634217048e-09,
|
| 684 |
+
7.184488115541399e-09,
|
| 685 |
+
5.321842966310442e-09,
|
| 686 |
+
8.514947857918287e-09,
|
| 687 |
+
6.918395634158969e-09,
|
| 688 |
+
5.854027040896881e-09,
|
| 689 |
+
6.65230315277654e-09,
|
| 690 |
+
9.579316895269585e-09,
|
| 691 |
+
9.047132820683146e-09,
|
| 692 |
+
6.38621155957253e-09,
|
| 693 |
+
6.6523035968657496e-09,
|
| 694 |
+
1.0377593007149244e-08,
|
| 695 |
+
5.321842966310442e-09,
|
| 696 |
+
7.184487227362979e-09,
|
| 697 |
+
4.2574739289591434e-09,
|
| 698 |
+
6.1201190781901005e-09,
|
| 699 |
+
7.982763783331848e-09,
|
| 700 |
+
7.716671746038628e-09,
|
| 701 |
+
7.982763783331848e-09,
|
| 702 |
+
7.184488115541399e-09,
|
| 703 |
+
8.514947857918287e-09,
|
| 704 |
+
9.845408932562805e-09,
|
| 705 |
+
6.6523035968657496e-09,
|
| 706 |
+
7.716671746038628e-09,
|
| 707 |
+
6.65230315277654e-09,
|
| 708 |
+
5.321842966310442e-09,
|
| 709 |
+
6.6523035968657496e-09
|
| 710 |
+
],
|
| 711 |
+
"lr": [
|
| 712 |
+
1.6723549488054611e-06,
|
| 713 |
+
3.378839590443686e-06,
|
| 714 |
+
5.085324232081912e-06,
|
| 715 |
+
6.791808873720137e-06,
|
| 716 |
+
8.498293515358363e-06,
|
| 717 |
+
1.0204778156996587e-05,
|
| 718 |
+
1.1911262798634814e-05,
|
| 719 |
+
1.3617747440273039e-05,
|
| 720 |
+
1.5324232081911263e-05,
|
| 721 |
+
1.703071672354949e-05,
|
| 722 |
+
1.8737201365187715e-05,
|
| 723 |
+
2.044368600682594e-05,
|
| 724 |
+
2.2150170648464163e-05,
|
| 725 |
+
2.385665529010239e-05,
|
| 726 |
+
2.556313993174062e-05,
|
| 727 |
+
2.726962457337884e-05,
|
| 728 |
+
2.8976109215017067e-05,
|
| 729 |
+
3.068259385665529e-05,
|
| 730 |
+
3.2389078498293516e-05,
|
| 731 |
+
3.4095563139931745e-05,
|
| 732 |
+
3.580204778156997e-05,
|
| 733 |
+
3.75085324232082e-05,
|
| 734 |
+
3.921501706484642e-05,
|
| 735 |
+
4.092150170648464e-05,
|
| 736 |
+
4.262798634812287e-05,
|
| 737 |
+
4.43344709897611e-05,
|
| 738 |
+
4.6040955631399317e-05,
|
| 739 |
+
4.7747440273037546e-05,
|
| 740 |
+
4.945392491467577e-05,
|
| 741 |
+
5.1160409556314e-05,
|
| 742 |
+
5.286689419795223e-05,
|
| 743 |
+
5.457337883959044e-05,
|
| 744 |
+
5.627986348122867e-05,
|
| 745 |
+
5.79863481228669e-05,
|
| 746 |
+
5.9692832764505124e-05,
|
| 747 |
+
6.139931740614335e-05,
|
| 748 |
+
6.310580204778158e-05,
|
| 749 |
+
6.481228668941979e-05,
|
| 750 |
+
6.651877133105803e-05,
|
| 751 |
+
6.822525597269625e-05,
|
| 752 |
+
6.993174061433447e-05,
|
| 753 |
+
7.16382252559727e-05,
|
| 754 |
+
7.334470989761093e-05,
|
| 755 |
+
7.505119453924915e-05,
|
| 756 |
+
7.675767918088738e-05,
|
| 757 |
+
7.846416382252561e-05,
|
| 758 |
+
7.999994387687875e-05,
|
| 759 |
+
7.999320929288793e-05,
|
| 760 |
+
7.997525225003474e-05,
|
| 761 |
+
7.9946077787229e-05,
|
| 762 |
+
7.990569409109077e-05,
|
| 763 |
+
7.985411249365304e-05,
|
| 764 |
+
7.979134746918198e-05,
|
| 765 |
+
7.971741663011522e-05,
|
| 766 |
+
7.963234072211973e-05,
|
| 767 |
+
7.953614361827032e-05,
|
| 768 |
+
7.942885231235067e-05,
|
| 769 |
+
7.931049691127864e-05,
|
| 770 |
+
7.918111062665798e-05,
|
| 771 |
+
7.904072976545885e-05,
|
| 772 |
+
7.888939371982977e-05,
|
| 773 |
+
7.872714495604378e-05,
|
| 774 |
+
7.85540290025821e-05,
|
| 775 |
+
7.837009443735831e-05,
|
| 776 |
+
7.817539287408707e-05,
|
| 777 |
+
7.796997894780074e-05,
|
| 778 |
+
7.775391029951834e-05,
|
| 779 |
+
7.752724756007093e-05,
|
| 780 |
+
7.72900543330881e-05,
|
| 781 |
+
7.704239717715015e-05,
|
| 782 |
+
7.678434558711115e-05,
|
| 783 |
+
7.651597197459809e-05,
|
| 784 |
+
7.623735164769155e-05,
|
| 785 |
+
7.594856278979342e-05,
|
| 786 |
+
7.564968643768808e-05,
|
| 787 |
+
7.53408064588027e-05,
|
| 788 |
+
7.502200952767318e-05,
|
| 789 |
+
7.469338510162264e-05,
|
| 790 |
+
7.435502539565875e-05,
|
| 791 |
+
7.400702535659744e-05,
|
| 792 |
+
7.364948263641994e-05,
|
| 793 |
+
7.328249756487067e-05,
|
| 794 |
+
7.290617312130396e-05,
|
| 795 |
+
7.252061490578694e-05,
|
| 796 |
+
7.212593110946728e-05,
|
| 797 |
+
7.172223248421377e-05,
|
| 798 |
+
7.13096323115383e-05,
|
| 799 |
+
7.08882463708081e-05,
|
| 800 |
+
7.045819290675694e-05,
|
| 801 |
+
7.001959259630454e-05,
|
| 802 |
+
6.957256851469366e-05,
|
| 803 |
+
6.911724610095394e-05,
|
| 804 |
+
6.865375312270262e-05,
|
| 805 |
+
6.818221964029179e-05,
|
| 806 |
+
6.770277797031225e-05,
|
| 807 |
+
6.721556264846422e-05,
|
| 808 |
+
6.672071039180557e-05,
|
| 809 |
+
6.621836006038756e-05,
|
| 810 |
+
6.570865261828953e-05,
|
| 811 |
+
6.519173109406314e-05,
|
| 812 |
+
6.466774054059721e-05,
|
| 813 |
+
6.413682799441454e-05,
|
| 814 |
+
6.359914243441216e-05,
|
| 815 |
+
6.305483474005648e-05,
|
| 816 |
+
6.250405764904512e-05,
|
| 817 |
+
6.194696571444738e-05,
|
| 818 |
+
6.138371526133514e-05,
|
| 819 |
+
6.081446434291672e-05,
|
| 820 |
+
6.0239372696185644e-05,
|
| 821 |
+
5.965860169709706e-05,
|
| 822 |
+
5.907231431528405e-05,
|
| 823 |
+
5.848067506832697e-05,
|
| 824 |
+
5.788384997558835e-05,
|
| 825 |
+
5.728200651162618e-05,
|
| 826 |
+
5.667531355919924e-05,
|
| 827 |
+
5.606394136187687e-05,
|
| 828 |
+
5.5448061476267194e-05,
|
| 829 |
+
5.482784672387675e-05,
|
| 830 |
+
5.420347114261514e-05,
|
| 831 |
+
5.357510993795849e-05,
|
| 832 |
+
5.294293943378513e-05,
|
| 833 |
+
5.230713702289755e-05,
|
| 834 |
+
5.1667881117244385e-05,
|
| 835 |
+
5.102535109785628e-05,
|
| 836 |
+
5.037972726451011e-05,
|
| 837 |
+
4.973119078513507e-05,
|
| 838 |
+
4.9079923644975386e-05,
|
| 839 |
+
4.842610859552357e-05,
|
| 840 |
+
4.7769929103238724e-05,
|
| 841 |
+
4.711156929806411e-05,
|
| 842 |
+
4.645121392175865e-05,
|
| 843 |
+
4.578904827605673e-05,
|
| 844 |
+
4.5125258170670815e-05,
|
| 845 |
+
4.4460029871151516e-05,
|
| 846 |
+
4.37935500466199e-05,
|
| 847 |
+
4.312600571738626e-05,
|
| 848 |
+
4.245758420247067e-05,
|
| 849 |
+
4.178847306703949e-05,
|
| 850 |
+
4.1118860069772856e-05,
|
| 851 |
+
4.0448933110177934e-05,
|
| 852 |
+
3.9778880175862544e-05,
|
| 853 |
+
3.91088892897842e-05,
|
| 854 |
+
3.843914845748907e-05,
|
| 855 |
+
3.7769845614355994e-05,
|
| 856 |
+
3.710116857286006e-05,
|
| 857 |
+
3.6433304969870695e-05,
|
| 858 |
+
3.5766442213999064e-05,
|
| 859 |
+
3.510076743300955e-05,
|
| 860 |
+
3.443646742130994e-05,
|
| 861 |
+
3.3773728587535196e-05,
|
| 862 |
+
3.3112736902239625e-05,
|
| 863 |
+
3.245367784571167e-05,
|
| 864 |
+
3.1796736355926556e-05,
|
| 865 |
+
3.1142096776651025e-05,
|
| 866 |
+
3.0489942805714706e-05,
|
| 867 |
+
2.984045744346295e-05,
|
| 868 |
+
2.9193822941405118e-05,
|
| 869 |
+
2.8550220751073297e-05,
|
| 870 |
+
2.7909831473105265e-05,
|
| 871 |
+
2.7272834806566284e-05,
|
| 872 |
+
2.6639409498523995e-05,
|
| 873 |
+
2.6009733293890285e-05,
|
| 874 |
+
2.5383982885544446e-05,
|
| 875 |
+
2.4762333864751625e-05,
|
| 876 |
+
2.41449606718902e-05,
|
| 877 |
+
2.353203654750234e-05,
|
| 878 |
+
2.2923733483680996e-05,
|
| 879 |
+
2.23202221758075e-05,
|
| 880 |
+
2.1721671974652772e-05,
|
| 881 |
+
2.1128250838855958e-05,
|
| 882 |
+
2.054012528779383e-05,
|
| 883 |
+
1.9957460354853774e-05,
|
| 884 |
+
1.9380419541123997e-05,
|
| 885 |
+
1.8809164769513625e-05,
|
| 886 |
+
1.824385633931566e-05,
|
| 887 |
+
1.7684652881225525e-05,
|
| 888 |
+
1.7131711312827855e-05,
|
| 889 |
+
1.6585186794563996e-05,
|
| 890 |
+
1.6045232686192566e-05,
|
| 891 |
+
1.551200050375531e-05,
|
| 892 |
+
1.4985639877060315e-05,
|
| 893 |
+
1.446629850769453e-05,
|
| 894 |
+
1.3954122127577385e-05,
|
| 895 |
+
1.3449254458066991e-05,
|
| 896 |
+
1.2951837169630714e-05,
|
| 897 |
+
1.2462009842091152e-05,
|
| 898 |
+
1.1979909925458655e-05,
|
| 899 |
+
1.1505672701361755e-05,
|
| 900 |
+
1.1039431245085796e-05,
|
| 901 |
+
1.0581316388230789e-05,
|
| 902 |
+
1.0131456681998992e-05,
|
| 903 |
+
9.68997836112215e-06,
|
| 904 |
+
9.257005308438928e-06,
|
| 905 |
+
8.832659020132261e-06,
|
| 906 |
+
8.417058571636403e-06,
|
| 907 |
+
8.01032058422329e-06,
|
| 908 |
+
7.612559192277533e-06,
|
| 909 |
+
7.223886011269297e-06,
|
| 910 |
+
6.8444101064339385e-06,
|
| 911 |
+
6.474237962167356e-06,
|
| 912 |
+
6.113473452145467e-06,
|
| 913 |
+
5.76221781017631e-06,
|
| 914 |
+
5.420569601792953e-06,
|
| 915 |
+
5.088624696595034e-06,
|
| 916 |
+
4.76647624134694e-06,
|
| 917 |
+
4.454214633839984e-06,
|
| 918 |
+
4.151927497525883e-06,
|
| 919 |
+
3.859699656928899e-06,
|
| 920 |
+
3.5776131138432944e-06,
|
| 921 |
+
3.3057470243228295e-06,
|
| 922 |
+
3.0441776764688958e-06,
|
| 923 |
+
2.7929784690233865e-06,
|
| 924 |
+
2.5522198907723228e-06,
|
| 925 |
+
2.321969500766024e-06,
|
| 926 |
+
2.1022919093615136e-06,
|
| 927 |
+
1.8932487600921722e-06,
|
| 928 |
+
1.6948987123700567e-06,
|
| 929 |
+
1.5072974250255023e-06,
|
| 930 |
+
1.3304975406887777e-06,
|
| 931 |
+
1.1645486710180554e-06,
|
| 932 |
+
1.0094973827779441e-06,
|
| 933 |
+
8.653871847724349e-07,
|
| 934 |
+
7.322585156359108e-07,
|
| 935 |
+
6.101487324857314e-07,
|
| 936 |
+
4.990921004394489e-07,
|
| 937 |
+
3.99119782999744e-07,
|
| 938 |
+
3.102598333096163e-07,
|
| 939 |
+
2.3253718628046373e-07,
|
| 940 |
+
1.6597365159509272e-07,
|
| 941 |
+
1.1058790758771587e-07,
|
| 942 |
+
6.63954960026647e-08,
|
| 943 |
+
3.340881763322035e-08,
|
| 944 |
+
1.1637128841837098e-08,
|
| 945 |
+
1.086538962731254e-09
|
| 946 |
+
]
|
| 947 |
+
},
|
| 948 |
+
"final_accuracy": 1.0
|
| 949 |
+
}
|
add_baseline_250K/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7233bf1df25d3d20449a43ccb9be00f5c412754dc2d0c2ca2f4195d856bfef9
|
| 3 |
+
size 671794850
|
add_baseline_250K/train_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mode": "baseline",
|
| 3 |
+
"ops": "add",
|
| 4 |
+
"n_digits": 6,
|
| 5 |
+
"n_layer": 3,
|
| 6 |
+
"n_head": 4,
|
| 7 |
+
"n_embd": 512,
|
| 8 |
+
"abs_vocab": 0,
|
| 9 |
+
"K": 4,
|
| 10 |
+
"batch_size": 64,
|
| 11 |
+
"num_epochs": 3,
|
| 12 |
+
"dataset_size": 250000,
|
| 13 |
+
"lr": 8e-05,
|
| 14 |
+
"output_dir": "ckpt/r/add_baseline_250K",
|
| 15 |
+
"device": "cuda",
|
| 16 |
+
"push_to_hub": true,
|
| 17 |
+
"no_wandb": false,
|
| 18 |
+
"n_params": 167871744,
|
| 19 |
+
"run_name": "add_baseline_250K",
|
| 20 |
+
"git_commit": "9e4530548a98f8c7f5c14930ac4aec4886bb4b1b",
|
| 21 |
+
"timestamp": "2026-04-07T05:29:32.985354",
|
| 22 |
+
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 23 |
+
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 24 |
+
"dataset_config": "add_6digit",
|
| 25 |
+
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 26 |
+
"trainer_version": "sft",
|
| 27 |
+
"final_accuracy": 1.0
|
| 28 |
+
}
|