davidberenstein1957 HF staff commited on
Commit
4d736df
1 Parent(s): 8e86cc2

Model save

Browse files
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter0
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter1
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter1
15
+
16
+ This model is a fine-tuned version of [davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter0](https://huggingface.co/davidberenstein1957/ultra-feedback-dutch-cleaned-hq-spin-geitje-7b-ultra-sft_iter0) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0380
19
+ - Rewards/real: -5.1867
20
+ - Rewards/generated: -23.6116
21
+ - Rewards/accuracies: 0.9778
22
+ - Rewards/margins: 18.4250
23
+ - Logps/generated: -690.4515
24
+ - Logps/real: -469.2089
25
+ - Logits/generated: -1.6815
26
+ - Logits/real: -2.1280
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-07
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - distributed_type: multi-GPU
50
+ - num_devices: 4
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 64
53
+ - total_eval_batch_size: 32
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 2
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
62
+ |:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
63
+ | 0.591 | 0.04 | 25 | 0.4210 | -0.2501 | -1.0788 | 0.8500 | 0.8287 | -465.1227 | -419.8426 | -2.6984 | -2.7096 |
64
+ | 0.2223 | 0.08 | 50 | 0.2173 | -0.5659 | -3.0876 | 0.9176 | 2.5217 | -485.2113 | -423.0011 | -2.6306 | -2.6446 |
65
+ | 0.168 | 0.12 | 75 | 0.1532 | -0.7060 | -4.4771 | 0.9435 | 3.7711 | -499.1060 | -424.4022 | -2.5832 | -2.6005 |
66
+ | 0.1126 | 0.16 | 100 | 0.1218 | -1.2746 | -6.3162 | 0.9509 | 5.0415 | -517.4969 | -430.0886 | -2.5961 | -2.6118 |
67
+ | 0.0854 | 0.21 | 125 | 0.0921 | -1.7944 | -9.0378 | 0.9611 | 7.2433 | -544.7130 | -435.2866 | -2.5534 | -2.5859 |
68
+ | 0.0609 | 0.25 | 150 | 0.0738 | -1.6860 | -9.1926 | 0.9639 | 7.5065 | -546.2610 | -434.2025 | -2.5875 | -2.6239 |
69
+ | 0.0654 | 0.29 | 175 | 0.0733 | -2.0360 | -9.8189 | 0.9648 | 7.7828 | -552.5237 | -437.7025 | -2.5252 | -2.5698 |
70
+ | 0.0814 | 0.33 | 200 | 0.0714 | -2.3341 | -10.2294 | 0.9630 | 7.8952 | -556.6287 | -440.6832 | -2.4634 | -2.5260 |
71
+ | 0.0356 | 0.37 | 225 | 0.0698 | -2.6697 | -11.4164 | 0.9667 | 8.7467 | -568.4990 | -444.0394 | -2.4311 | -2.5142 |
72
+ | 0.0641 | 0.41 | 250 | 0.0586 | -2.3926 | -12.3053 | 0.9694 | 9.9126 | -577.3877 | -441.2684 | -2.3106 | -2.4202 |
73
+ | 0.0442 | 0.45 | 275 | 0.0672 | -2.5170 | -11.9462 | 0.9676 | 9.4293 | -573.7975 | -442.5117 | -2.3880 | -2.4773 |
74
+ | 0.0707 | 0.49 | 300 | 0.0540 | -3.8488 | -15.1469 | 0.9667 | 11.2982 | -605.8044 | -455.8299 | -2.2564 | -2.3913 |
75
+ | 0.0683 | 0.53 | 325 | 0.0574 | -5.2977 | -18.2377 | 0.9667 | 12.9400 | -636.7123 | -470.3190 | -2.1402 | -2.3222 |
76
+ | 0.0339 | 0.58 | 350 | 0.0495 | -3.7486 | -17.2926 | 0.9731 | 13.5439 | -627.2608 | -454.8286 | -2.1701 | -2.3731 |
77
+ | 0.0648 | 0.62 | 375 | 0.0537 | -2.4302 | -13.2604 | 0.9722 | 10.8301 | -586.9390 | -441.6444 | -2.3167 | -2.4783 |
78
+ | 0.0358 | 0.66 | 400 | 0.0460 | -3.8509 | -17.3389 | 0.9741 | 13.4880 | -627.7241 | -455.8509 | -2.1735 | -2.3874 |
79
+ | 0.0532 | 0.7 | 425 | 0.0483 | -4.3261 | -18.2030 | 0.9741 | 13.8769 | -636.3655 | -460.6029 | -2.1550 | -2.3751 |
80
+ | 0.0408 | 0.74 | 450 | 0.0567 | -4.8885 | -19.7272 | 0.9741 | 14.8387 | -651.6073 | -466.2276 | -2.2982 | -2.4811 |
81
+ | 0.0434 | 0.78 | 475 | 0.0467 | -2.8677 | -16.1120 | 0.9731 | 13.2443 | -615.4548 | -446.0187 | -2.1937 | -2.4242 |
82
+ | 0.0194 | 0.82 | 500 | 0.0455 | -3.2473 | -18.4707 | 0.9769 | 15.2234 | -639.0422 | -449.8151 | -2.0107 | -2.3291 |
83
+ | 0.0227 | 0.86 | 525 | 0.0543 | -4.5805 | -20.1131 | 0.9750 | 15.5326 | -655.4664 | -463.1471 | -2.2146 | -2.4100 |
84
+ | 0.0299 | 0.91 | 550 | 0.0481 | -4.3021 | -20.3869 | 0.9731 | 16.0848 | -658.2037 | -460.3627 | -2.0552 | -2.3301 |
85
+ | 0.0218 | 0.95 | 575 | 0.0464 | -4.4619 | -20.3587 | 0.9713 | 15.8967 | -657.9220 | -461.9616 | -1.9225 | -2.2635 |
86
+ | 0.0218 | 0.99 | 600 | 0.0451 | -5.3210 | -20.9811 | 0.9722 | 15.6602 | -664.1465 | -470.5517 | -1.9518 | -2.2964 |
87
+ | 0.0093 | 1.03 | 625 | 0.0429 | -4.3395 | -19.2716 | 0.9750 | 14.9321 | -647.0515 | -460.7374 | -1.7575 | -2.1708 |
88
+ | 0.0173 | 1.07 | 650 | 0.0492 | -4.1317 | -19.0745 | 0.9704 | 14.9428 | -645.0802 | -458.6593 | -1.8155 | -2.1757 |
89
+ | 0.0059 | 1.11 | 675 | 0.0449 | -5.7336 | -23.1577 | 0.9713 | 17.4241 | -685.9126 | -474.6784 | -1.6844 | -2.1123 |
90
+ | 0.0149 | 1.15 | 700 | 0.0608 | -7.1484 | -26.1989 | 0.9713 | 19.0504 | -716.3237 | -488.8266 | -2.0142 | -2.2748 |
91
+ | 0.0105 | 1.19 | 725 | 0.0479 | -4.4948 | -20.2513 | 0.9722 | 15.7564 | -656.8477 | -462.2903 | -2.1674 | -2.3962 |
92
+ | 0.032 | 1.23 | 750 | 0.0512 | -5.0950 | -21.3230 | 0.9685 | 16.2280 | -667.5649 | -468.2917 | -2.2426 | -2.4414 |
93
+ | 0.0042 | 1.28 | 775 | 0.0462 | -4.0296 | -19.2620 | 0.9704 | 15.2324 | -646.9548 | -457.6381 | -2.2156 | -2.4379 |
94
+ | 0.0041 | 1.32 | 800 | 0.0475 | -4.0348 | -19.8410 | 0.9731 | 15.8062 | -652.7453 | -457.6903 | -2.1330 | -2.3843 |
95
+ | 0.0075 | 1.36 | 825 | 0.0428 | -4.4696 | -20.8584 | 0.9722 | 16.3888 | -662.9192 | -462.0378 | -2.1122 | -2.3718 |
96
+ | 0.004 | 1.4 | 850 | 0.0468 | -6.2822 | -25.6273 | 0.9750 | 19.3451 | -710.6078 | -480.1642 | -1.7240 | -2.1709 |
97
+ | 0.0222 | 1.44 | 875 | 0.0584 | -6.0399 | -23.0778 | 0.9759 | 17.0379 | -685.1132 | -477.7408 | -1.6544 | -2.1242 |
98
+ | 0.0063 | 1.48 | 900 | 0.0490 | -3.8721 | -19.8020 | 0.9722 | 15.9298 | -652.3550 | -456.0635 | -1.7696 | -2.2026 |
99
+ | 0.006 | 1.52 | 925 | 0.0478 | -5.2822 | -23.7504 | 0.9750 | 18.4682 | -691.8392 | -470.1639 | -1.6461 | -2.1239 |
100
+ | 0.0169 | 1.56 | 950 | 0.0455 | -4.9375 | -22.9431 | 0.9731 | 18.0057 | -683.7665 | -466.7169 | -1.6890 | -2.1447 |
101
+ | 0.0063 | 1.6 | 975 | 0.0449 | -5.9782 | -25.0564 | 0.9741 | 19.0782 | -704.8994 | -477.1242 | -1.5890 | -2.0779 |
102
+ | 0.0144 | 1.65 | 1000 | 0.0428 | -5.2622 | -22.9304 | 0.9731 | 17.6682 | -683.6391 | -469.9639 | -1.6262 | -2.0859 |
103
+ | 0.0046 | 1.69 | 1025 | 0.0411 | -5.5146 | -24.0845 | 0.9759 | 18.5698 | -695.1800 | -472.4886 | -1.6070 | -2.0934 |
104
+ | 0.002 | 1.73 | 1050 | 0.0408 | -5.4174 | -23.7610 | 0.9750 | 18.3436 | -691.9457 | -471.5163 | -1.6779 | -2.1277 |
105
+ | 0.0047 | 1.77 | 1075 | 0.0411 | -5.6837 | -24.5512 | 0.9750 | 18.8674 | -699.8467 | -474.1796 | -1.7048 | -2.1412 |
106
+ | 0.0077 | 1.81 | 1100 | 0.0404 | -5.8712 | -25.3478 | 0.9759 | 19.4766 | -707.8129 | -476.0543 | -1.6257 | -2.0917 |
107
+ | 0.0145 | 1.85 | 1125 | 0.0385 | -5.0758 | -23.2450 | 0.9741 | 18.1692 | -686.7853 | -468.0999 | -1.6509 | -2.1029 |
108
+ | 0.0038 | 1.89 | 1150 | 0.0376 | -5.2077 | -23.5236 | 0.9759 | 18.3159 | -689.5715 | -469.4194 | -1.6736 | -2.1249 |
109
+ | 0.01 | 1.93 | 1175 | 0.0379 | -5.1247 | -23.3484 | 0.9750 | 18.2238 | -687.8193 | -468.5888 | -1.6969 | -2.1383 |
110
+ | 0.0055 | 1.98 | 1200 | 0.0380 | -5.1867 | -23.6116 | 0.9778 | 18.4250 | -690.4515 | -469.2089 | -1.6815 | -2.1280 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.37.0
116
+ - Pytorch 2.1.2+cu121
117
+ - Datasets 2.14.6
118
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.05120065249445122,
4
+ "train_runtime": 45973.3661,
5
+ "train_samples": 38852,
6
+ "train_samples_per_second": 1.69,
7
+ "train_steps_per_second": 0.026
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ab1fb03d982871fe781ccebade2028bfce3018643586bcd7dd68ad5912c1e2
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462b676d49df19fb636e3c5499372d158dcaf14198cb94e0a4fc5b1ec6093c68
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ab38f95ea0fc803bbceaad9a495ac671514286f5a7fe9bd932077d0e4bd9d9
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.05120065249445122,
4
+ "train_runtime": 45973.3661,
5
+ "train_samples": 38852,
6
+ "train_samples_per_second": 1.69,
7
+ "train_steps_per_second": 0.026
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2506 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9983539094650205,
5
+ "eval_steps": 25,
6
+ "global_step": 1214,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 4.098360655737705e-09,
14
+ "logits/generated": -2.6401095390319824,
15
+ "logits/real": -2.652092456817627,
16
+ "logps/generated": -522.5341796875,
17
+ "logps/real": -420.15106201171875,
18
+ "loss": 0.6931,
19
+ "rewards/accuracies": 0.0,
20
+ "rewards/generated": 0.0,
21
+ "rewards/margins": 0.0,
22
+ "rewards/real": 0.0,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "learning_rate": 4.0983606557377046e-08,
28
+ "logits/generated": -2.7537119388580322,
29
+ "logits/real": -2.749621868133545,
30
+ "logps/generated": -494.7628479003906,
31
+ "logps/real": -410.4559326171875,
32
+ "loss": 0.6882,
33
+ "rewards/accuracies": 0.4513888955116272,
34
+ "rewards/generated": -0.010888932272791862,
35
+ "rewards/margins": -0.00011028432345483452,
36
+ "rewards/real": -0.010999216698110104,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "learning_rate": 8.196721311475409e-08,
42
+ "logits/generated": -2.72717022895813,
43
+ "logits/real": -2.736893892288208,
44
+ "logps/generated": -487.6122131347656,
45
+ "logps/real": -399.52362060546875,
46
+ "loss": 0.591,
47
+ "rewards/accuracies": 0.731249988079071,
48
+ "rewards/generated": -0.3106920123100281,
49
+ "rewards/margins": 0.2161286622285843,
50
+ "rewards/real": -0.09456336498260498,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "eval_logits/generated": -2.698356866836548,
56
+ "eval_logits/real": -2.709562301635742,
57
+ "eval_logps/generated": -465.1226806640625,
58
+ "eval_logps/real": -419.8426208496094,
59
+ "eval_loss": 0.4210089147090912,
60
+ "eval_rewards/accuracies": 0.8500000238418579,
61
+ "eval_rewards/generated": -1.0787537097930908,
62
+ "eval_rewards/margins": 0.8287025094032288,
63
+ "eval_rewards/real": -0.25005120038986206,
64
+ "eval_runtime": 549.2945,
65
+ "eval_samples_per_second": 7.861,
66
+ "eval_steps_per_second": 0.246,
67
+ "step": 25
68
+ },
69
+ {
70
+ "epoch": 0.05,
71
+ "learning_rate": 1.2295081967213113e-07,
72
+ "logits/generated": -2.7093679904937744,
73
+ "logits/real": -2.718613624572754,
74
+ "logps/generated": -482.2759704589844,
75
+ "logps/real": -419.0752868652344,
76
+ "loss": 0.4538,
77
+ "rewards/accuracies": 0.862500011920929,
78
+ "rewards/generated": -0.9867717623710632,
79
+ "rewards/margins": 0.7356894016265869,
80
+ "rewards/real": -0.2510823607444763,
81
+ "step": 30
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 1.6393442622950818e-07,
86
+ "logits/generated": -2.679270029067993,
87
+ "logits/real": -2.691554307937622,
88
+ "logps/generated": -500.12786865234375,
89
+ "logps/real": -385.42303466796875,
90
+ "loss": 0.3118,
91
+ "rewards/accuracies": 0.8999999761581421,
92
+ "rewards/generated": -1.5584895610809326,
93
+ "rewards/margins": 1.3963291645050049,
94
+ "rewards/real": -0.16216044127941132,
95
+ "step": 40
96
+ },
97
+ {
98
+ "epoch": 0.08,
99
+ "learning_rate": 2.0491803278688524e-07,
100
+ "logits/generated": -2.6619114875793457,
101
+ "logits/real": -2.6760687828063965,
102
+ "logps/generated": -513.6600952148438,
103
+ "logps/real": -445.169677734375,
104
+ "loss": 0.2223,
105
+ "rewards/accuracies": 0.9375,
106
+ "rewards/generated": -2.419264316558838,
107
+ "rewards/margins": 2.2213003635406494,
108
+ "rewards/real": -0.19796383380889893,
109
+ "step": 50
110
+ },
111
+ {
112
+ "epoch": 0.08,
113
+ "eval_logits/generated": -2.630603551864624,
114
+ "eval_logits/real": -2.6445798873901367,
115
+ "eval_logps/generated": -485.2113342285156,
116
+ "eval_logps/real": -423.0011291503906,
117
+ "eval_loss": 0.2172713428735733,
118
+ "eval_rewards/accuracies": 0.9175925850868225,
119
+ "eval_rewards/generated": -3.0876214504241943,
120
+ "eval_rewards/margins": 2.5217204093933105,
121
+ "eval_rewards/real": -0.5659011602401733,
122
+ "eval_runtime": 547.8486,
123
+ "eval_samples_per_second": 7.882,
124
+ "eval_steps_per_second": 0.246,
125
+ "step": 50
126
+ },
127
+ {
128
+ "epoch": 0.1,
129
+ "learning_rate": 2.4590163934426226e-07,
130
+ "logits/generated": -2.6456358432769775,
131
+ "logits/real": -2.656313419342041,
132
+ "logps/generated": -483.8861389160156,
133
+ "logps/real": -392.04681396484375,
134
+ "loss": 0.1852,
135
+ "rewards/accuracies": 0.925000011920929,
136
+ "rewards/generated": -3.4535624980926514,
137
+ "rewards/margins": 2.996718168258667,
138
+ "rewards/real": -0.45684438943862915,
139
+ "step": 60
140
+ },
141
+ {
142
+ "epoch": 0.12,
143
+ "learning_rate": 2.868852459016393e-07,
144
+ "logits/generated": -2.593245029449463,
145
+ "logits/real": -2.633634328842163,
146
+ "logps/generated": -518.401611328125,
147
+ "logps/real": -430.7620544433594,
148
+ "loss": 0.168,
149
+ "rewards/accuracies": 0.949999988079071,
150
+ "rewards/generated": -3.725245237350464,
151
+ "rewards/margins": 3.4510974884033203,
152
+ "rewards/real": -0.27414828538894653,
153
+ "step": 70
154
+ },
155
+ {
156
+ "epoch": 0.12,
157
+ "eval_logits/generated": -2.583158254623413,
158
+ "eval_logits/real": -2.600541353225708,
159
+ "eval_logps/generated": -499.10601806640625,
160
+ "eval_logps/real": -424.4022216796875,
161
+ "eval_loss": 0.15319335460662842,
162
+ "eval_rewards/accuracies": 0.9435185194015503,
163
+ "eval_rewards/generated": -4.4770894050598145,
164
+ "eval_rewards/margins": 3.7710745334625244,
165
+ "eval_rewards/real": -0.7060146927833557,
166
+ "eval_runtime": 550.1138,
167
+ "eval_samples_per_second": 7.849,
168
+ "eval_steps_per_second": 0.245,
169
+ "step": 75
170
+ },
171
+ {
172
+ "epoch": 0.13,
173
+ "learning_rate": 3.2786885245901637e-07,
174
+ "logits/generated": -2.5965609550476074,
175
+ "logits/real": -2.6199886798858643,
176
+ "logps/generated": -503.3633728027344,
177
+ "logps/real": -432.483642578125,
178
+ "loss": 0.1364,
179
+ "rewards/accuracies": 0.949999988079071,
180
+ "rewards/generated": -4.042363166809082,
181
+ "rewards/margins": 3.511378765106201,
182
+ "rewards/real": -0.5309839248657227,
183
+ "step": 80
184
+ },
185
+ {
186
+ "epoch": 0.15,
187
+ "learning_rate": 3.6885245901639347e-07,
188
+ "logits/generated": -2.568969249725342,
189
+ "logits/real": -2.5813772678375244,
190
+ "logps/generated": -529.686767578125,
191
+ "logps/real": -427.0670471191406,
192
+ "loss": 0.1207,
193
+ "rewards/accuracies": 0.956250011920929,
194
+ "rewards/generated": -5.874642848968506,
195
+ "rewards/margins": 5.00606632232666,
196
+ "rewards/real": -0.8685771822929382,
197
+ "step": 90
198
+ },
199
+ {
200
+ "epoch": 0.16,
201
+ "learning_rate": 4.0983606557377047e-07,
202
+ "logits/generated": -2.590125560760498,
203
+ "logits/real": -2.594589948654175,
204
+ "logps/generated": -532.7440185546875,
205
+ "logps/real": -431.35028076171875,
206
+ "loss": 0.1126,
207
+ "rewards/accuracies": 0.956250011920929,
208
+ "rewards/generated": -5.600076198577881,
209
+ "rewards/margins": 4.819561958312988,
210
+ "rewards/real": -0.7805139422416687,
211
+ "step": 100
212
+ },
213
+ {
214
+ "epoch": 0.16,
215
+ "eval_logits/generated": -2.596092939376831,
216
+ "eval_logits/real": -2.611849784851074,
217
+ "eval_logps/generated": -517.4968872070312,
218
+ "eval_logps/real": -430.088623046875,
219
+ "eval_loss": 0.12175341695547104,
220
+ "eval_rewards/accuracies": 0.9509259462356567,
221
+ "eval_rewards/generated": -6.31616735458374,
222
+ "eval_rewards/margins": 5.041518211364746,
223
+ "eval_rewards/real": -1.2746495008468628,
224
+ "eval_runtime": 548.1161,
225
+ "eval_samples_per_second": 7.878,
226
+ "eval_steps_per_second": 0.246,
227
+ "step": 100
228
+ },
229
+ {
230
+ "epoch": 0.18,
231
+ "learning_rate": 4.508196721311475e-07,
232
+ "logits/generated": -2.637228012084961,
233
+ "logits/real": -2.649094343185425,
234
+ "logps/generated": -518.5374145507812,
235
+ "logps/real": -405.7285461425781,
236
+ "loss": 0.1257,
237
+ "rewards/accuracies": 0.9624999761581421,
238
+ "rewards/generated": -6.386349678039551,
239
+ "rewards/margins": 5.354151725769043,
240
+ "rewards/real": -1.0321977138519287,
241
+ "step": 110
242
+ },
243
+ {
244
+ "epoch": 0.2,
245
+ "learning_rate": 4.918032786885245e-07,
246
+ "logits/generated": -2.613947868347168,
247
+ "logits/real": -2.6607353687286377,
248
+ "logps/generated": -521.7745361328125,
249
+ "logps/real": -417.6166076660156,
250
+ "loss": 0.0854,
251
+ "rewards/accuracies": 0.981249988079071,
252
+ "rewards/generated": -7.714804649353027,
253
+ "rewards/margins": 6.425919532775879,
254
+ "rewards/real": -1.2888853549957275,
255
+ "step": 120
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "eval_logits/generated": -2.553359270095825,
260
+ "eval_logits/real": -2.585937023162842,
261
+ "eval_logps/generated": -544.7130126953125,
262
+ "eval_logps/real": -435.28656005859375,
263
+ "eval_loss": 0.09206286817789078,
264
+ "eval_rewards/accuracies": 0.9611111283302307,
265
+ "eval_rewards/generated": -9.037795066833496,
266
+ "eval_rewards/margins": 7.243347644805908,
267
+ "eval_rewards/real": -1.7944461107254028,
268
+ "eval_runtime": 549.7281,
269
+ "eval_samples_per_second": 7.855,
270
+ "eval_steps_per_second": 0.246,
271
+ "step": 125
272
+ },
273
+ {
274
+ "epoch": 0.21,
275
+ "learning_rate": 4.963369963369964e-07,
276
+ "logits/generated": -2.5732762813568115,
277
+ "logits/real": -2.6250641345977783,
278
+ "logps/generated": -594.252197265625,
279
+ "logps/real": -480.178955078125,
280
+ "loss": 0.1156,
281
+ "rewards/accuracies": 0.9624999761581421,
282
+ "rewards/generated": -8.990375518798828,
283
+ "rewards/margins": 7.42321252822876,
284
+ "rewards/real": -1.5671632289886475,
285
+ "step": 130
286
+ },
287
+ {
288
+ "epoch": 0.23,
289
+ "learning_rate": 4.917582417582417e-07,
290
+ "logits/generated": -2.588108777999878,
291
+ "logits/real": -2.616245746612549,
292
+ "logps/generated": -536.1387939453125,
293
+ "logps/real": -419.4244079589844,
294
+ "loss": 0.0895,
295
+ "rewards/accuracies": 0.949999988079071,
296
+ "rewards/generated": -8.070068359375,
297
+ "rewards/margins": 6.980319976806641,
298
+ "rewards/real": -1.089747667312622,
299
+ "step": 140
300
+ },
301
+ {
302
+ "epoch": 0.25,
303
+ "learning_rate": 4.871794871794871e-07,
304
+ "logits/generated": -2.6047449111938477,
305
+ "logits/real": -2.6315391063690186,
306
+ "logps/generated": -543.27978515625,
307
+ "logps/real": -417.0159606933594,
308
+ "loss": 0.0609,
309
+ "rewards/accuracies": 0.9750000238418579,
310
+ "rewards/generated": -8.380901336669922,
311
+ "rewards/margins": 7.630522727966309,
312
+ "rewards/real": -0.7503789067268372,
313
+ "step": 150
314
+ },
315
+ {
316
+ "epoch": 0.25,
317
+ "eval_logits/generated": -2.587456703186035,
318
+ "eval_logits/real": -2.6238744258880615,
319
+ "eval_logps/generated": -546.2610473632812,
320
+ "eval_logps/real": -434.2024841308594,
321
+ "eval_loss": 0.07384903728961945,
322
+ "eval_rewards/accuracies": 0.9638888835906982,
323
+ "eval_rewards/generated": -9.192586898803711,
324
+ "eval_rewards/margins": 7.506547451019287,
325
+ "eval_rewards/real": -1.686038851737976,
326
+ "eval_runtime": 548.206,
327
+ "eval_samples_per_second": 7.877,
328
+ "eval_steps_per_second": 0.246,
329
+ "step": 150
330
+ },
331
+ {
332
+ "epoch": 0.26,
333
+ "learning_rate": 4.826007326007326e-07,
334
+ "logits/generated": -2.591831684112549,
335
+ "logits/real": -2.607217788696289,
336
+ "logps/generated": -571.234619140625,
337
+ "logps/real": -392.61004638671875,
338
+ "loss": 0.0855,
339
+ "rewards/accuracies": 0.9624999761581421,
340
+ "rewards/generated": -9.883105278015137,
341
+ "rewards/margins": 7.8926191329956055,
342
+ "rewards/real": -1.9904861450195312,
343
+ "step": 160
344
+ },
345
+ {
346
+ "epoch": 0.28,
347
+ "learning_rate": 4.78021978021978e-07,
348
+ "logits/generated": -2.554612874984741,
349
+ "logits/real": -2.5981972217559814,
350
+ "logps/generated": -613.7628173828125,
351
+ "logps/real": -422.0660095214844,
352
+ "loss": 0.0654,
353
+ "rewards/accuracies": 0.981249988079071,
354
+ "rewards/generated": -11.727653503417969,
355
+ "rewards/margins": 9.922538757324219,
356
+ "rewards/real": -1.8051135540008545,
357
+ "step": 170
358
+ },
359
+ {
360
+ "epoch": 0.29,
361
+ "eval_logits/generated": -2.5252153873443604,
362
+ "eval_logits/real": -2.5698459148406982,
363
+ "eval_logps/generated": -552.5237426757812,
364
+ "eval_logps/real": -437.7025451660156,
365
+ "eval_loss": 0.07325886934995651,
366
+ "eval_rewards/accuracies": 0.9648148417472839,
367
+ "eval_rewards/generated": -9.818856239318848,
368
+ "eval_rewards/margins": 7.782812595367432,
369
+ "eval_rewards/real": -2.036044120788574,
370
+ "eval_runtime": 538.2331,
371
+ "eval_samples_per_second": 8.023,
372
+ "eval_steps_per_second": 0.251,
373
+ "step": 175
374
+ },
375
+ {
376
+ "epoch": 0.3,
377
+ "learning_rate": 4.734432234432234e-07,
378
+ "logits/generated": -2.5366225242614746,
379
+ "logits/real": -2.5802321434020996,
380
+ "logps/generated": -562.9288940429688,
381
+ "logps/real": -426.1321716308594,
382
+ "loss": 0.065,
383
+ "rewards/accuracies": 0.987500011920929,
384
+ "rewards/generated": -10.882379531860352,
385
+ "rewards/margins": 8.783550262451172,
386
+ "rewards/real": -2.098829984664917,
387
+ "step": 180
388
+ },
389
+ {
390
+ "epoch": 0.31,
391
+ "learning_rate": 4.6886446886446884e-07,
392
+ "logits/generated": -2.464695930480957,
393
+ "logits/real": -2.514756917953491,
394
+ "logps/generated": -585.3269653320312,
395
+ "logps/real": -439.30535888671875,
396
+ "loss": 0.0803,
397
+ "rewards/accuracies": 0.96875,
398
+ "rewards/generated": -13.198904037475586,
399
+ "rewards/margins": 10.291043281555176,
400
+ "rewards/real": -2.9078612327575684,
401
+ "step": 190
402
+ },
403
+ {
404
+ "epoch": 0.33,
405
+ "learning_rate": 4.6428571428571427e-07,
406
+ "logits/generated": -2.4625725746154785,
407
+ "logits/real": -2.5219738483428955,
408
+ "logps/generated": -573.2178955078125,
409
+ "logps/real": -413.1720275878906,
410
+ "loss": 0.0814,
411
+ "rewards/accuracies": 0.981249988079071,
412
+ "rewards/generated": -12.102069854736328,
413
+ "rewards/margins": 9.350552558898926,
414
+ "rewards/real": -2.751516342163086,
415
+ "step": 200
416
+ },
417
+ {
418
+ "epoch": 0.33,
419
+ "eval_logits/generated": -2.4633901119232178,
420
+ "eval_logits/real": -2.5260355472564697,
421
+ "eval_logps/generated": -556.628662109375,
422
+ "eval_logps/real": -440.68316650390625,
423
+ "eval_loss": 0.07137465476989746,
424
+ "eval_rewards/accuracies": 0.9629629850387573,
425
+ "eval_rewards/generated": -10.229352951049805,
426
+ "eval_rewards/margins": 7.8952484130859375,
427
+ "eval_rewards/real": -2.334104299545288,
428
+ "eval_runtime": 541.6446,
429
+ "eval_samples_per_second": 7.972,
430
+ "eval_steps_per_second": 0.249,
431
+ "step": 200
432
+ },
433
+ {
434
+ "epoch": 0.35,
435
+ "learning_rate": 4.5970695970695965e-07,
436
+ "logits/generated": -2.5092012882232666,
437
+ "logits/real": -2.543381929397583,
438
+ "logps/generated": -568.660888671875,
439
+ "logps/real": -418.6875,
440
+ "loss": 0.0591,
441
+ "rewards/accuracies": 0.949999988079071,
442
+ "rewards/generated": -10.36689281463623,
443
+ "rewards/margins": 8.45336627960205,
444
+ "rewards/real": -1.913527488708496,
445
+ "step": 210
446
+ },
447
+ {
448
+ "epoch": 0.36,
449
+ "learning_rate": 4.551282051282051e-07,
450
+ "logits/generated": -2.365678310394287,
451
+ "logits/real": -2.4535679817199707,
452
+ "logps/generated": -604.965087890625,
453
+ "logps/real": -432.04974365234375,
454
+ "loss": 0.0356,
455
+ "rewards/accuracies": 0.981249988079071,
456
+ "rewards/generated": -14.320533752441406,
457
+ "rewards/margins": 10.759347915649414,
458
+ "rewards/real": -3.5611863136291504,
459
+ "step": 220
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "eval_logits/generated": -2.4310951232910156,
464
+ "eval_logits/real": -2.5141642093658447,
465
+ "eval_logps/generated": -568.4989624023438,
466
+ "eval_logps/real": -444.03936767578125,
467
+ "eval_loss": 0.06977172195911407,
468
+ "eval_rewards/accuracies": 0.9666666388511658,
469
+ "eval_rewards/generated": -11.4163818359375,
470
+ "eval_rewards/margins": 8.746658325195312,
471
+ "eval_rewards/real": -2.6697258949279785,
472
+ "eval_runtime": 540.5003,
473
+ "eval_samples_per_second": 7.989,
474
+ "eval_steps_per_second": 0.25,
475
+ "step": 225
476
+ },
477
+ {
478
+ "epoch": 0.38,
479
+ "learning_rate": 4.5054945054945056e-07,
480
+ "logits/generated": -2.40238618850708,
481
+ "logits/real": -2.490166425704956,
482
+ "logps/generated": -583.9486083984375,
483
+ "logps/real": -433.9161682128906,
484
+ "loss": 0.0966,
485
+ "rewards/accuracies": 0.9750000238418579,
486
+ "rewards/generated": -11.47558879852295,
487
+ "rewards/margins": 8.76927661895752,
488
+ "rewards/real": -2.7063136100769043,
489
+ "step": 230
490
+ },
491
+ {
492
+ "epoch": 0.4,
493
+ "learning_rate": 4.45970695970696e-07,
494
+ "logits/generated": -2.3658084869384766,
495
+ "logits/real": -2.4398703575134277,
496
+ "logps/generated": -579.8946533203125,
497
+ "logps/real": -403.6769104003906,
498
+ "loss": 0.0714,
499
+ "rewards/accuracies": 0.9624999761581421,
500
+ "rewards/generated": -12.590639114379883,
501
+ "rewards/margins": 9.855241775512695,
502
+ "rewards/real": -2.735395908355713,
503
+ "step": 240
504
+ },
505
+ {
506
+ "epoch": 0.41,
507
+ "learning_rate": 4.4139194139194137e-07,
508
+ "logits/generated": -2.3249025344848633,
509
+ "logits/real": -2.421391010284424,
510
+ "logps/generated": -627.2833251953125,
511
+ "logps/real": -436.53399658203125,
512
+ "loss": 0.0641,
513
+ "rewards/accuracies": 0.9624999761581421,
514
+ "rewards/generated": -13.549036979675293,
515
+ "rewards/margins": 11.038546562194824,
516
+ "rewards/real": -2.510490894317627,
517
+ "step": 250
518
+ },
519
+ {
520
+ "epoch": 0.41,
521
+ "eval_logits/generated": -2.310610055923462,
522
+ "eval_logits/real": -2.4202382564544678,
523
+ "eval_logps/generated": -577.3876953125,
524
+ "eval_logps/real": -441.26837158203125,
525
+ "eval_loss": 0.0585518442094326,
526
+ "eval_rewards/accuracies": 0.9694444537162781,
527
+ "eval_rewards/generated": -12.305254936218262,
528
+ "eval_rewards/margins": 9.912630081176758,
529
+ "eval_rewards/real": -2.3926241397857666,
530
+ "eval_runtime": 544.2791,
531
+ "eval_samples_per_second": 7.933,
532
+ "eval_steps_per_second": 0.248,
533
+ "step": 250
534
+ },
535
+ {
536
+ "epoch": 0.43,
537
+ "learning_rate": 4.368131868131868e-07,
538
+ "logits/generated": -2.352004289627075,
539
+ "logits/real": -2.446444034576416,
540
+ "logps/generated": -596.7254638671875,
541
+ "logps/real": -417.0332946777344,
542
+ "loss": 0.0495,
543
+ "rewards/accuracies": 0.981249988079071,
544
+ "rewards/generated": -12.558148384094238,
545
+ "rewards/margins": 10.505435943603516,
546
+ "rewards/real": -2.0527119636535645,
547
+ "step": 260
548
+ },
549
+ {
550
+ "epoch": 0.44,
551
+ "learning_rate": 4.3223443223443223e-07,
552
+ "logits/generated": -2.3381831645965576,
553
+ "logits/real": -2.430725574493408,
554
+ "logps/generated": -658.2124633789062,
555
+ "logps/real": -449.29461669921875,
556
+ "loss": 0.0442,
557
+ "rewards/accuracies": 0.9624999761581421,
558
+ "rewards/generated": -17.05294418334961,
559
+ "rewards/margins": 13.15046215057373,
560
+ "rewards/real": -3.9024810791015625,
561
+ "step": 270
562
+ },
563
+ {
564
+ "epoch": 0.45,
565
+ "eval_logits/generated": -2.3879544734954834,
566
+ "eval_logits/real": -2.4772706031799316,
567
+ "eval_logps/generated": -573.7975463867188,
568
+ "eval_logps/real": -442.5116882324219,
569
+ "eval_loss": 0.06716620177030563,
570
+ "eval_rewards/accuracies": 0.9675925970077515,
571
+ "eval_rewards/generated": -11.946240425109863,
572
+ "eval_rewards/margins": 9.429278373718262,
573
+ "eval_rewards/real": -2.516960382461548,
574
+ "eval_runtime": 543.8707,
575
+ "eval_samples_per_second": 7.939,
576
+ "eval_steps_per_second": 0.248,
577
+ "step": 275
578
+ },
579
+ {
580
+ "epoch": 0.46,
581
+ "learning_rate": 4.276556776556776e-07,
582
+ "logits/generated": -2.2920713424682617,
583
+ "logits/real": -2.4120707511901855,
584
+ "logps/generated": -625.0443115234375,
585
+ "logps/real": -443.11773681640625,
586
+ "loss": 0.0455,
587
+ "rewards/accuracies": 0.987500011920929,
588
+ "rewards/generated": -15.292150497436523,
589
+ "rewards/margins": 12.260358810424805,
590
+ "rewards/real": -3.0317909717559814,
591
+ "step": 280
592
+ },
593
+ {
594
+ "epoch": 0.48,
595
+ "learning_rate": 4.2307692307692304e-07,
596
+ "logits/generated": -2.2416317462921143,
597
+ "logits/real": -2.3849129676818848,
598
+ "logps/generated": -620.5736083984375,
599
+ "logps/real": -438.10302734375,
600
+ "loss": 0.0638,
601
+ "rewards/accuracies": 0.96875,
602
+ "rewards/generated": -15.206059455871582,
603
+ "rewards/margins": 11.891336441040039,
604
+ "rewards/real": -3.314722776412964,
605
+ "step": 290
606
+ },
607
+ {
608
+ "epoch": 0.49,
609
+ "learning_rate": 4.1849816849816847e-07,
610
+ "logits/generated": -2.2657132148742676,
611
+ "logits/real": -2.416287660598755,
612
+ "logps/generated": -596.555908203125,
613
+ "logps/real": -443.7845764160156,
614
+ "loss": 0.0707,
615
+ "rewards/accuracies": 0.96875,
616
+ "rewards/generated": -13.721325874328613,
617
+ "rewards/margins": 11.418547630310059,
618
+ "rewards/real": -2.30277681350708,
619
+ "step": 300
620
+ },
621
+ {
622
+ "epoch": 0.49,
623
+ "eval_logits/generated": -2.256381034851074,
624
+ "eval_logits/real": -2.391341209411621,
625
+ "eval_logps/generated": -605.804443359375,
626
+ "eval_logps/real": -455.82989501953125,
627
+ "eval_loss": 0.05395643413066864,
628
+ "eval_rewards/accuracies": 0.9666666388511658,
629
+ "eval_rewards/generated": -15.146928787231445,
630
+ "eval_rewards/margins": 11.298150062561035,
631
+ "eval_rewards/real": -3.8487789630889893,
632
+ "eval_runtime": 543.6439,
633
+ "eval_samples_per_second": 7.943,
634
+ "eval_steps_per_second": 0.248,
635
+ "step": 300
636
+ },
637
+ {
638
+ "epoch": 0.51,
639
+ "learning_rate": 4.1391941391941385e-07,
640
+ "logits/generated": -2.2252917289733887,
641
+ "logits/real": -2.3379065990448,
642
+ "logps/generated": -627.6759033203125,
643
+ "logps/real": -425.13201904296875,
644
+ "loss": 0.0306,
645
+ "rewards/accuracies": 0.9750000238418579,
646
+ "rewards/generated": -16.1324462890625,
647
+ "rewards/margins": 12.730301856994629,
648
+ "rewards/real": -3.40214467048645,
649
+ "step": 310
650
+ },
651
+ {
652
+ "epoch": 0.53,
653
+ "learning_rate": 4.0934065934065933e-07,
654
+ "logits/generated": -2.301344633102417,
655
+ "logits/real": -2.4362711906433105,
656
+ "logps/generated": -602.3247680664062,
657
+ "logps/real": -444.23974609375,
658
+ "loss": 0.0683,
659
+ "rewards/accuracies": 0.9624999761581421,
660
+ "rewards/generated": -13.596293449401855,
661
+ "rewards/margins": 10.262487411499023,
662
+ "rewards/real": -3.333805799484253,
663
+ "step": 320
664
+ },
665
+ {
666
+ "epoch": 0.53,
667
+ "eval_logits/generated": -2.1402149200439453,
668
+ "eval_logits/real": -2.322171926498413,
669
+ "eval_logps/generated": -636.7122802734375,
670
+ "eval_logps/real": -470.3190002441406,
671
+ "eval_loss": 0.057357266545295715,
672
+ "eval_rewards/accuracies": 0.9666666388511658,
673
+ "eval_rewards/generated": -18.237712860107422,
674
+ "eval_rewards/margins": 12.940022468566895,
675
+ "eval_rewards/real": -5.297689437866211,
676
+ "eval_runtime": 537.4705,
677
+ "eval_samples_per_second": 8.034,
678
+ "eval_steps_per_second": 0.251,
679
+ "step": 325
680
+ },
681
+ {
682
+ "epoch": 0.54,
683
+ "learning_rate": 4.0476190476190476e-07,
684
+ "logits/generated": -2.1620073318481445,
685
+ "logits/real": -2.3063290119171143,
686
+ "logps/generated": -652.4406127929688,
687
+ "logps/real": -435.88494873046875,
688
+ "loss": 0.0379,
689
+ "rewards/accuracies": 0.987500011920929,
690
+ "rewards/generated": -18.206768035888672,
691
+ "rewards/margins": 13.691610336303711,
692
+ "rewards/real": -4.51515531539917,
693
+ "step": 330
694
+ },
695
+ {
696
+ "epoch": 0.56,
697
+ "learning_rate": 4.001831501831502e-07,
698
+ "logits/generated": -2.236128330230713,
699
+ "logits/real": -2.3870835304260254,
700
+ "logps/generated": -652.0904541015625,
701
+ "logps/real": -450.24859619140625,
702
+ "loss": 0.0553,
703
+ "rewards/accuracies": 0.987500011920929,
704
+ "rewards/generated": -17.906084060668945,
705
+ "rewards/margins": 14.117843627929688,
706
+ "rewards/real": -3.7882392406463623,
707
+ "step": 340
708
+ },
709
+ {
710
+ "epoch": 0.58,
711
+ "learning_rate": 3.9560439560439557e-07,
712
+ "logits/generated": -2.176945209503174,
713
+ "logits/real": -2.368508815765381,
714
+ "logps/generated": -651.4620361328125,
715
+ "logps/real": -432.74658203125,
716
+ "loss": 0.0339,
717
+ "rewards/accuracies": 0.987500011920929,
718
+ "rewards/generated": -18.662532806396484,
719
+ "rewards/margins": 14.847686767578125,
720
+ "rewards/real": -3.8148434162139893,
721
+ "step": 350
722
+ },
723
+ {
724
+ "epoch": 0.58,
725
+ "eval_logits/generated": -2.1701033115386963,
726
+ "eval_logits/real": -2.3731424808502197,
727
+ "eval_logps/generated": -627.2608032226562,
728
+ "eval_logps/real": -454.8285827636719,
729
+ "eval_loss": 0.04949037358164787,
730
+ "eval_rewards/accuracies": 0.9731481671333313,
731
+ "eval_rewards/generated": -17.292573928833008,
732
+ "eval_rewards/margins": 13.543929100036621,
733
+ "eval_rewards/real": -3.748645305633545,
734
+ "eval_runtime": 537.9029,
735
+ "eval_samples_per_second": 8.027,
736
+ "eval_steps_per_second": 0.251,
737
+ "step": 350
738
+ },
739
+ {
740
+ "epoch": 0.59,
741
+ "learning_rate": 3.91025641025641e-07,
742
+ "logits/generated": -2.2481982707977295,
743
+ "logits/real": -2.3865692615509033,
744
+ "logps/generated": -664.8062744140625,
745
+ "logps/real": -430.34857177734375,
746
+ "loss": 0.0464,
747
+ "rewards/accuracies": 0.987500011920929,
748
+ "rewards/generated": -17.22327423095703,
749
+ "rewards/margins": 13.856378555297852,
750
+ "rewards/real": -3.366894245147705,
751
+ "step": 360
752
+ },
753
+ {
754
+ "epoch": 0.61,
755
+ "learning_rate": 3.8644688644688643e-07,
756
+ "logits/generated": -2.1518349647521973,
757
+ "logits/real": -2.3465476036071777,
758
+ "logps/generated": -613.2617797851562,
759
+ "logps/real": -446.73834228515625,
760
+ "loss": 0.0648,
761
+ "rewards/accuracies": 0.9750000238418579,
762
+ "rewards/generated": -18.795753479003906,
763
+ "rewards/margins": 14.179173469543457,
764
+ "rewards/real": -4.616580009460449,
765
+ "step": 370
766
+ },
767
+ {
768
+ "epoch": 0.62,
769
+ "eval_logits/generated": -2.316718339920044,
770
+ "eval_logits/real": -2.478287935256958,
771
+ "eval_logps/generated": -586.93896484375,
772
+ "eval_logps/real": -441.6444091796875,
773
+ "eval_loss": 0.053722720593214035,
774
+ "eval_rewards/accuracies": 0.9722222089767456,
775
+ "eval_rewards/generated": -13.260376930236816,
776
+ "eval_rewards/margins": 10.830145835876465,
777
+ "eval_rewards/real": -2.4302310943603516,
778
+ "eval_runtime": 539.3726,
779
+ "eval_samples_per_second": 8.006,
780
+ "eval_steps_per_second": 0.25,
781
+ "step": 375
782
+ },
783
+ {
784
+ "epoch": 0.63,
785
+ "learning_rate": 3.818681318681318e-07,
786
+ "logits/generated": -2.279561758041382,
787
+ "logits/real": -2.478255033493042,
788
+ "logps/generated": -601.7288208007812,
789
+ "logps/real": -449.01702880859375,
790
+ "loss": 0.0427,
791
+ "rewards/accuracies": 0.987500011920929,
792
+ "rewards/generated": -14.500157356262207,
793
+ "rewards/margins": 11.545099258422852,
794
+ "rewards/real": -2.9550578594207764,
795
+ "step": 380
796
+ },
797
+ {
798
+ "epoch": 0.64,
799
+ "learning_rate": 3.7728937728937724e-07,
800
+ "logits/generated": -2.285148859024048,
801
+ "logits/real": -2.452268123626709,
802
+ "logps/generated": -673.3703002929688,
803
+ "logps/real": -449.6754455566406,
804
+ "loss": 0.0272,
805
+ "rewards/accuracies": 0.981249988079071,
806
+ "rewards/generated": -17.92129898071289,
807
+ "rewards/margins": 14.363734245300293,
808
+ "rewards/real": -3.5575671195983887,
809
+ "step": 390
810
+ },
811
+ {
812
+ "epoch": 0.66,
813
+ "learning_rate": 3.727106227106227e-07,
814
+ "logits/generated": -2.158463954925537,
815
+ "logits/real": -2.3927464485168457,
816
+ "logps/generated": -665.3966064453125,
817
+ "logps/real": -455.4427185058594,
818
+ "loss": 0.0358,
819
+ "rewards/accuracies": 0.9937499761581421,
820
+ "rewards/generated": -20.033100128173828,
821
+ "rewards/margins": 16.113994598388672,
822
+ "rewards/real": -3.9191043376922607,
823
+ "step": 400
824
+ },
825
+ {
826
+ "epoch": 0.66,
827
+ "eval_logits/generated": -2.1734633445739746,
828
+ "eval_logits/real": -2.3874428272247314,
829
+ "eval_logps/generated": -627.7240600585938,
830
+ "eval_logps/real": -455.8509216308594,
831
+ "eval_loss": 0.04597338289022446,
832
+ "eval_rewards/accuracies": 0.9740740656852722,
833
+ "eval_rewards/generated": -17.338891983032227,
834
+ "eval_rewards/margins": 13.488015174865723,
835
+ "eval_rewards/real": -3.8508799076080322,
836
+ "eval_runtime": 545.3223,
837
+ "eval_samples_per_second": 7.918,
838
+ "eval_steps_per_second": 0.248,
839
+ "step": 400
840
+ },
841
+ {
842
+ "epoch": 0.67,
843
+ "learning_rate": 3.6813186813186816e-07,
844
+ "logits/generated": -2.1853232383728027,
845
+ "logits/real": -2.3945891857147217,
846
+ "logps/generated": -642.46044921875,
847
+ "logps/real": -399.55694580078125,
848
+ "loss": 0.0221,
849
+ "rewards/accuracies": 0.9937499761581421,
850
+ "rewards/generated": -18.870121002197266,
851
+ "rewards/margins": 16.129247665405273,
852
+ "rewards/real": -2.7408719062805176,
853
+ "step": 410
854
+ },
855
+ {
856
+ "epoch": 0.69,
857
+ "learning_rate": 3.6355311355311353e-07,
858
+ "logits/generated": -2.1754229068756104,
859
+ "logits/real": -2.381279468536377,
860
+ "logps/generated": -595.3236083984375,
861
+ "logps/real": -405.1600341796875,
862
+ "loss": 0.0532,
863
+ "rewards/accuracies": 0.981249988079071,
864
+ "rewards/generated": -14.932568550109863,
865
+ "rewards/margins": 12.319165229797363,
866
+ "rewards/real": -2.6134040355682373,
867
+ "step": 420
868
+ },
869
+ {
870
+ "epoch": 0.7,
871
+ "eval_logits/generated": -2.1550426483154297,
872
+ "eval_logits/real": -2.3750507831573486,
873
+ "eval_logps/generated": -636.3655395507812,
874
+ "eval_logps/real": -460.6029052734375,
875
+ "eval_loss": 0.048347219824790955,
876
+ "eval_rewards/accuracies": 0.9740740656852722,
877
+ "eval_rewards/generated": -18.20302963256836,
878
+ "eval_rewards/margins": 13.876949310302734,
879
+ "eval_rewards/real": -4.32607889175415,
880
+ "eval_runtime": 546.9938,
881
+ "eval_samples_per_second": 7.894,
882
+ "eval_steps_per_second": 0.247,
883
+ "step": 425
884
+ },
885
+ {
886
+ "epoch": 0.71,
887
+ "learning_rate": 3.5897435897435896e-07,
888
+ "logits/generated": -2.183345317840576,
889
+ "logits/real": -2.4247512817382812,
890
+ "logps/generated": -591.2523193359375,
891
+ "logps/real": -400.4705810546875,
892
+ "loss": 0.043,
893
+ "rewards/accuracies": 0.9624999761581421,
894
+ "rewards/generated": -16.82411766052246,
895
+ "rewards/margins": 14.277923583984375,
896
+ "rewards/real": -2.5461928844451904,
897
+ "step": 430
898
+ },
899
+ {
900
+ "epoch": 0.72,
901
+ "learning_rate": 3.543956043956044e-07,
902
+ "logits/generated": -2.2292613983154297,
903
+ "logits/real": -2.4110050201416016,
904
+ "logps/generated": -626.2135620117188,
905
+ "logps/real": -403.21368408203125,
906
+ "loss": 0.0332,
907
+ "rewards/accuracies": 0.987500011920929,
908
+ "rewards/generated": -17.94637680053711,
909
+ "rewards/margins": 15.042144775390625,
910
+ "rewards/real": -2.9042327404022217,
911
+ "step": 440
912
+ },
913
+ {
914
+ "epoch": 0.74,
915
+ "learning_rate": 3.4981684981684977e-07,
916
+ "logits/generated": -2.2957308292388916,
917
+ "logits/real": -2.483898639678955,
918
+ "logps/generated": -624.1409301757812,
919
+ "logps/real": -416.9951171875,
920
+ "loss": 0.0408,
921
+ "rewards/accuracies": 0.981249988079071,
922
+ "rewards/generated": -17.344409942626953,
923
+ "rewards/margins": 14.197443962097168,
924
+ "rewards/real": -3.1469688415527344,
925
+ "step": 450
926
+ },
927
+ {
928
+ "epoch": 0.74,
929
+ "eval_logits/generated": -2.29823899269104,
930
+ "eval_logits/real": -2.481050968170166,
931
+ "eval_logps/generated": -651.6072998046875,
932
+ "eval_logps/real": -466.22760009765625,
933
+ "eval_loss": 0.05667389929294586,
934
+ "eval_rewards/accuracies": 0.9740740656852722,
935
+ "eval_rewards/generated": -19.727210998535156,
936
+ "eval_rewards/margins": 14.838663101196289,
937
+ "eval_rewards/real": -4.888548851013184,
938
+ "eval_runtime": 546.6533,
939
+ "eval_samples_per_second": 7.899,
940
+ "eval_steps_per_second": 0.247,
941
+ "step": 450
942
+ },
943
+ {
944
+ "epoch": 0.76,
945
+ "learning_rate": 3.452380952380952e-07,
946
+ "logits/generated": -2.3011131286621094,
947
+ "logits/real": -2.4612629413604736,
948
+ "logps/generated": -647.5547485351562,
949
+ "logps/real": -426.67205810546875,
950
+ "loss": 0.0449,
951
+ "rewards/accuracies": 0.96875,
952
+ "rewards/generated": -17.85089111328125,
953
+ "rewards/margins": 14.307988166809082,
954
+ "rewards/real": -3.5429024696350098,
955
+ "step": 460
956
+ },
957
+ {
958
+ "epoch": 0.77,
959
+ "learning_rate": 3.4065934065934063e-07,
960
+ "logits/generated": -2.1878461837768555,
961
+ "logits/real": -2.4027976989746094,
962
+ "logps/generated": -651.8814697265625,
963
+ "logps/real": -432.30828857421875,
964
+ "loss": 0.0434,
965
+ "rewards/accuracies": 0.9937499761581421,
966
+ "rewards/generated": -18.791553497314453,
967
+ "rewards/margins": 14.97038459777832,
968
+ "rewards/real": -3.8211684226989746,
969
+ "step": 470
970
+ },
971
+ {
972
+ "epoch": 0.78,
973
+ "eval_logits/generated": -2.1936686038970947,
974
+ "eval_logits/real": -2.424220323562622,
975
+ "eval_logps/generated": -615.4547729492188,
976
+ "eval_logps/real": -446.01873779296875,
977
+ "eval_loss": 0.04669804871082306,
978
+ "eval_rewards/accuracies": 0.9731481671333313,
979
+ "eval_rewards/generated": -16.111957550048828,
980
+ "eval_rewards/margins": 13.244292259216309,
981
+ "eval_rewards/real": -2.8676631450653076,
982
+ "eval_runtime": 548.2901,
983
+ "eval_samples_per_second": 7.875,
984
+ "eval_steps_per_second": 0.246,
985
+ "step": 475
986
+ },
987
+ {
988
+ "epoch": 0.79,
989
+ "learning_rate": 3.360805860805861e-07,
990
+ "logits/generated": -2.170032501220703,
991
+ "logits/real": -2.3914527893066406,
992
+ "logps/generated": -638.609619140625,
993
+ "logps/real": -419.04473876953125,
994
+ "loss": 0.0184,
995
+ "rewards/accuracies": 1.0,
996
+ "rewards/generated": -17.431259155273438,
997
+ "rewards/margins": 14.863021850585938,
998
+ "rewards/real": -2.568234920501709,
999
+ "step": 480
1000
+ },
1001
+ {
1002
+ "epoch": 0.81,
1003
+ "learning_rate": 3.315018315018315e-07,
1004
+ "logits/generated": -2.125486135482788,
1005
+ "logits/real": -2.35538911819458,
1006
+ "logps/generated": -608.1831665039062,
1007
+ "logps/real": -426.45733642578125,
1008
+ "loss": 0.0437,
1009
+ "rewards/accuracies": 0.96875,
1010
+ "rewards/generated": -16.634971618652344,
1011
+ "rewards/margins": 13.581262588500977,
1012
+ "rewards/real": -3.053709030151367,
1013
+ "step": 490
1014
+ },
1015
+ {
1016
+ "epoch": 0.82,
1017
+ "learning_rate": 3.269230769230769e-07,
1018
+ "logits/generated": -2.0204501152038574,
1019
+ "logits/real": -2.329942226409912,
1020
+ "logps/generated": -684.5260620117188,
1021
+ "logps/real": -425.2499084472656,
1022
+ "loss": 0.0194,
1023
+ "rewards/accuracies": 0.9937499761581421,
1024
+ "rewards/generated": -20.701831817626953,
1025
+ "rewards/margins": 17.69593620300293,
1026
+ "rewards/real": -3.0058956146240234,
1027
+ "step": 500
1028
+ },
1029
+ {
1030
+ "epoch": 0.82,
1031
+ "eval_logits/generated": -2.0107169151306152,
1032
+ "eval_logits/real": -2.3290646076202393,
1033
+ "eval_logps/generated": -639.0421752929688,
1034
+ "eval_logps/real": -449.8150939941406,
1035
+ "eval_loss": 0.04547751694917679,
1036
+ "eval_rewards/accuracies": 0.9768518805503845,
1037
+ "eval_rewards/generated": -18.4707088470459,
1038
+ "eval_rewards/margins": 15.223410606384277,
1039
+ "eval_rewards/real": -3.2472991943359375,
1040
+ "eval_runtime": 547.436,
1041
+ "eval_samples_per_second": 7.888,
1042
+ "eval_steps_per_second": 0.247,
1043
+ "step": 500
1044
+ },
1045
+ {
1046
+ "epoch": 0.84,
1047
+ "learning_rate": 3.2234432234432236e-07,
1048
+ "logits/generated": -2.1318891048431396,
1049
+ "logits/real": -2.373379707336426,
1050
+ "logps/generated": -664.7022705078125,
1051
+ "logps/real": -426.9652404785156,
1052
+ "loss": 0.0487,
1053
+ "rewards/accuracies": 0.96875,
1054
+ "rewards/generated": -20.184797286987305,
1055
+ "rewards/margins": 16.790945053100586,
1056
+ "rewards/real": -3.393852949142456,
1057
+ "step": 510
1058
+ },
1059
+ {
1060
+ "epoch": 0.86,
1061
+ "learning_rate": 3.1776556776556773e-07,
1062
+ "logits/generated": -2.1151123046875,
1063
+ "logits/real": -2.3613884449005127,
1064
+ "logps/generated": -723.1424560546875,
1065
+ "logps/real": -472.94879150390625,
1066
+ "loss": 0.0227,
1067
+ "rewards/accuracies": 0.987500011920929,
1068
+ "rewards/generated": -21.221763610839844,
1069
+ "rewards/margins": 17.593347549438477,
1070
+ "rewards/real": -3.6284186840057373,
1071
+ "step": 520
1072
+ },
1073
+ {
1074
+ "epoch": 0.86,
1075
+ "eval_logits/generated": -2.214646100997925,
1076
+ "eval_logits/real": -2.409980297088623,
1077
+ "eval_logps/generated": -655.4663696289062,
1078
+ "eval_logps/real": -463.1470947265625,
1079
+ "eval_loss": 0.05429470166563988,
1080
+ "eval_rewards/accuracies": 0.9750000238418579,
1081
+ "eval_rewards/generated": -20.113121032714844,
1082
+ "eval_rewards/margins": 15.532620429992676,
1083
+ "eval_rewards/real": -4.580500602722168,
1084
+ "eval_runtime": 546.7755,
1085
+ "eval_samples_per_second": 7.897,
1086
+ "eval_steps_per_second": 0.247,
1087
+ "step": 525
1088
+ },
1089
+ {
1090
+ "epoch": 0.87,
1091
+ "learning_rate": 3.1318681318681316e-07,
1092
+ "logits/generated": -2.1360554695129395,
1093
+ "logits/real": -2.357234001159668,
1094
+ "logps/generated": -686.1627197265625,
1095
+ "logps/real": -463.78594970703125,
1096
+ "loss": 0.1081,
1097
+ "rewards/accuracies": 0.987500011920929,
1098
+ "rewards/generated": -21.75899887084961,
1099
+ "rewards/margins": 17.28326416015625,
1100
+ "rewards/real": -4.475732803344727,
1101
+ "step": 530
1102
+ },
1103
+ {
1104
+ "epoch": 0.89,
1105
+ "learning_rate": 3.086080586080586e-07,
1106
+ "logits/generated": -2.198076009750366,
1107
+ "logits/real": -2.3724374771118164,
1108
+ "logps/generated": -632.1812133789062,
1109
+ "logps/real": -408.17999267578125,
1110
+ "loss": 0.0384,
1111
+ "rewards/accuracies": 1.0,
1112
+ "rewards/generated": -17.84307098388672,
1113
+ "rewards/margins": 14.931114196777344,
1114
+ "rewards/real": -2.911957263946533,
1115
+ "step": 540
1116
+ },
1117
+ {
1118
+ "epoch": 0.91,
1119
+ "learning_rate": 3.0402930402930397e-07,
1120
+ "logits/generated": -2.0505592823028564,
1121
+ "logits/real": -2.2820277214050293,
1122
+ "logps/generated": -675.8702392578125,
1123
+ "logps/real": -435.8621520996094,
1124
+ "loss": 0.0299,
1125
+ "rewards/accuracies": 0.9937499761581421,
1126
+ "rewards/generated": -21.609846115112305,
1127
+ "rewards/margins": 17.412473678588867,
1128
+ "rewards/real": -4.197373390197754,
1129
+ "step": 550
1130
+ },
1131
+ {
1132
+ "epoch": 0.91,
1133
+ "eval_logits/generated": -2.055241823196411,
1134
+ "eval_logits/real": -2.3300585746765137,
1135
+ "eval_logps/generated": -658.2036743164062,
1136
+ "eval_logps/real": -460.3627014160156,
1137
+ "eval_loss": 0.04806026816368103,
1138
+ "eval_rewards/accuracies": 0.9731481671333313,
1139
+ "eval_rewards/generated": -20.386852264404297,
1140
+ "eval_rewards/margins": 16.084793090820312,
1141
+ "eval_rewards/real": -4.302060604095459,
1142
+ "eval_runtime": 545.5178,
1143
+ "eval_samples_per_second": 7.915,
1144
+ "eval_steps_per_second": 0.247,
1145
+ "step": 550
1146
+ },
1147
+ {
1148
+ "epoch": 0.92,
1149
+ "learning_rate": 2.994505494505494e-07,
1150
+ "logits/generated": -2.05330491065979,
1151
+ "logits/real": -2.319866418838501,
1152
+ "logps/generated": -671.1466674804688,
1153
+ "logps/real": -431.24298095703125,
1154
+ "loss": 0.0253,
1155
+ "rewards/accuracies": 0.987500011920929,
1156
+ "rewards/generated": -21.11385154724121,
1157
+ "rewards/margins": 16.92177963256836,
1158
+ "rewards/real": -4.1920695304870605,
1159
+ "step": 560
1160
+ },
1161
+ {
1162
+ "epoch": 0.94,
1163
+ "learning_rate": 2.948717948717949e-07,
1164
+ "logits/generated": -1.8845161199569702,
1165
+ "logits/real": -2.2347493171691895,
1166
+ "logps/generated": -694.9982299804688,
1167
+ "logps/real": -455.690185546875,
1168
+ "loss": 0.0218,
1169
+ "rewards/accuracies": 0.9937499761581421,
1170
+ "rewards/generated": -24.400421142578125,
1171
+ "rewards/margins": 19.314403533935547,
1172
+ "rewards/real": -5.086018085479736,
1173
+ "step": 570
1174
+ },
1175
+ {
1176
+ "epoch": 0.95,
1177
+ "eval_logits/generated": -1.9225108623504639,
1178
+ "eval_logits/real": -2.2634739875793457,
1179
+ "eval_logps/generated": -657.9219970703125,
1180
+ "eval_logps/real": -461.96160888671875,
1181
+ "eval_loss": 0.04638593643903732,
1182
+ "eval_rewards/accuracies": 0.9712963104248047,
1183
+ "eval_rewards/generated": -20.358694076538086,
1184
+ "eval_rewards/margins": 15.896740913391113,
1185
+ "eval_rewards/real": -4.461949348449707,
1186
+ "eval_runtime": 549.2313,
1187
+ "eval_samples_per_second": 7.862,
1188
+ "eval_steps_per_second": 0.246,
1189
+ "step": 575
1190
+ },
1191
+ {
1192
+ "epoch": 0.95,
1193
+ "learning_rate": 2.902930402930403e-07,
1194
+ "logits/generated": -1.9606196880340576,
1195
+ "logits/real": -2.286708354949951,
1196
+ "logps/generated": -673.0288696289062,
1197
+ "logps/real": -418.47332763671875,
1198
+ "loss": 0.0254,
1199
+ "rewards/accuracies": 0.987500011920929,
1200
+ "rewards/generated": -21.76241683959961,
1201
+ "rewards/margins": 18.28946304321289,
1202
+ "rewards/real": -3.472952365875244,
1203
+ "step": 580
1204
+ },
1205
+ {
1206
+ "epoch": 0.97,
1207
+ "learning_rate": 2.857142857142857e-07,
1208
+ "logits/generated": -1.8293163776397705,
1209
+ "logits/real": -2.22106671333313,
1210
+ "logps/generated": -645.2640380859375,
1211
+ "logps/real": -431.3738708496094,
1212
+ "loss": 0.0245,
1213
+ "rewards/accuracies": 0.981249988079071,
1214
+ "rewards/generated": -22.095638275146484,
1215
+ "rewards/margins": 17.28582000732422,
1216
+ "rewards/real": -4.8098225593566895,
1217
+ "step": 590
1218
+ },
1219
+ {
1220
+ "epoch": 0.99,
1221
+ "learning_rate": 2.811355311355311e-07,
1222
+ "logits/generated": -1.9109601974487305,
1223
+ "logits/real": -2.295834541320801,
1224
+ "logps/generated": -623.3287963867188,
1225
+ "logps/real": -419.62939453125,
1226
+ "loss": 0.0218,
1227
+ "rewards/accuracies": 0.96875,
1228
+ "rewards/generated": -19.795055389404297,
1229
+ "rewards/margins": 15.8367280960083,
1230
+ "rewards/real": -3.9583258628845215,
1231
+ "step": 600
1232
+ },
1233
+ {
1234
+ "epoch": 0.99,
1235
+ "eval_logits/generated": -1.9517701864242554,
1236
+ "eval_logits/real": -2.2964491844177246,
1237
+ "eval_logps/generated": -664.1465454101562,
1238
+ "eval_logps/real": -470.55169677734375,
1239
+ "eval_loss": 0.04514331370592117,
1240
+ "eval_rewards/accuracies": 0.9722222089767456,
1241
+ "eval_rewards/generated": -20.981136322021484,
1242
+ "eval_rewards/margins": 15.660176277160645,
1243
+ "eval_rewards/real": -5.320960521697998,
1244
+ "eval_runtime": 544.3521,
1245
+ "eval_samples_per_second": 7.932,
1246
+ "eval_steps_per_second": 0.248,
1247
+ "step": 600
1248
+ },
1249
+ {
1250
+ "epoch": 1.0,
1251
+ "learning_rate": 2.7655677655677655e-07,
1252
+ "logits/generated": -1.8589156866073608,
1253
+ "logits/real": -2.271904468536377,
1254
+ "logps/generated": -683.95654296875,
1255
+ "logps/real": -455.6640625,
1256
+ "loss": 0.0219,
1257
+ "rewards/accuracies": 0.9937499761581421,
1258
+ "rewards/generated": -22.11398696899414,
1259
+ "rewards/margins": 17.55306053161621,
1260
+ "rewards/real": -4.560924530029297,
1261
+ "step": 610
1262
+ },
1263
+ {
1264
+ "epoch": 1.02,
1265
+ "learning_rate": 2.7197802197802193e-07,
1266
+ "logits/generated": -1.9177764654159546,
1267
+ "logits/real": -2.2215471267700195,
1268
+ "logps/generated": -666.0201416015625,
1269
+ "logps/real": -429.0519104003906,
1270
+ "loss": 0.0093,
1271
+ "rewards/accuracies": 0.9937499761581421,
1272
+ "rewards/generated": -18.098499298095703,
1273
+ "rewards/margins": 15.7960205078125,
1274
+ "rewards/real": -2.302478790283203,
1275
+ "step": 620
1276
+ },
1277
+ {
1278
+ "epoch": 1.03,
1279
+ "eval_logits/generated": -1.7574790716171265,
1280
+ "eval_logits/real": -2.170833110809326,
1281
+ "eval_logps/generated": -647.0514526367188,
1282
+ "eval_logps/real": -460.7373962402344,
1283
+ "eval_loss": 0.042933978140354156,
1284
+ "eval_rewards/accuracies": 0.9750000238418579,
1285
+ "eval_rewards/generated": -19.27163314819336,
1286
+ "eval_rewards/margins": 14.932106971740723,
1287
+ "eval_rewards/real": -4.3395256996154785,
1288
+ "eval_runtime": 542.4468,
1289
+ "eval_samples_per_second": 7.96,
1290
+ "eval_steps_per_second": 0.249,
1291
+ "step": 625
1292
+ },
1293
+ {
1294
+ "epoch": 1.04,
1295
+ "learning_rate": 2.6739926739926736e-07,
1296
+ "logits/generated": -1.8621714115142822,
1297
+ "logits/real": -2.1959869861602783,
1298
+ "logps/generated": -680.0298461914062,
1299
+ "logps/real": -468.26580810546875,
1300
+ "loss": 0.0276,
1301
+ "rewards/accuracies": 1.0,
1302
+ "rewards/generated": -19.896984100341797,
1303
+ "rewards/margins": 16.92976951599121,
1304
+ "rewards/real": -2.9672141075134277,
1305
+ "step": 630
1306
+ },
1307
+ {
1308
+ "epoch": 1.05,
1309
+ "learning_rate": 2.628205128205128e-07,
1310
+ "logits/generated": -2.157670736312866,
1311
+ "logits/real": -2.3523807525634766,
1312
+ "logps/generated": -636.9368286132812,
1313
+ "logps/real": -439.37841796875,
1314
+ "loss": 0.0045,
1315
+ "rewards/accuracies": 1.0,
1316
+ "rewards/generated": -15.98005199432373,
1317
+ "rewards/margins": 13.84521198272705,
1318
+ "rewards/real": -2.1348421573638916,
1319
+ "step": 640
1320
+ },
1321
+ {
1322
+ "epoch": 1.07,
1323
+ "learning_rate": 2.582417582417583e-07,
1324
+ "logits/generated": -1.9907798767089844,
1325
+ "logits/real": -2.246988534927368,
1326
+ "logps/generated": -686.9197387695312,
1327
+ "logps/real": -434.936767578125,
1328
+ "loss": 0.0173,
1329
+ "rewards/accuracies": 1.0,
1330
+ "rewards/generated": -20.37822914123535,
1331
+ "rewards/margins": 17.642370223999023,
1332
+ "rewards/real": -2.7358591556549072,
1333
+ "step": 650
1334
+ },
1335
+ {
1336
+ "epoch": 1.07,
1337
+ "eval_logits/generated": -1.8154959678649902,
1338
+ "eval_logits/real": -2.1757171154022217,
1339
+ "eval_logps/generated": -645.0802001953125,
1340
+ "eval_logps/real": -458.6592712402344,
1341
+ "eval_loss": 0.049214281141757965,
1342
+ "eval_rewards/accuracies": 0.970370352268219,
1343
+ "eval_rewards/generated": -19.07451057434082,
1344
+ "eval_rewards/margins": 14.942792892456055,
1345
+ "eval_rewards/real": -4.131715297698975,
1346
+ "eval_runtime": 543.2173,
1347
+ "eval_samples_per_second": 7.949,
1348
+ "eval_steps_per_second": 0.249,
1349
+ "step": 650
1350
+ },
1351
+ {
1352
+ "epoch": 1.09,
1353
+ "learning_rate": 2.5366300366300365e-07,
1354
+ "logits/generated": -1.7823787927627563,
1355
+ "logits/real": -2.136547565460205,
1356
+ "logps/generated": -721.7634887695312,
1357
+ "logps/real": -412.015625,
1358
+ "loss": 0.0057,
1359
+ "rewards/accuracies": 0.987500011920929,
1360
+ "rewards/generated": -24.206735610961914,
1361
+ "rewards/margins": 20.0247745513916,
1362
+ "rewards/real": -4.181961536407471,
1363
+ "step": 660
1364
+ },
1365
+ {
1366
+ "epoch": 1.1,
1367
+ "learning_rate": 2.490842490842491e-07,
1368
+ "logits/generated": -1.7356059551239014,
1369
+ "logits/real": -2.120824098587036,
1370
+ "logps/generated": -722.6532592773438,
1371
+ "logps/real": -429.0586853027344,
1372
+ "loss": 0.0059,
1373
+ "rewards/accuracies": 0.9937499761581421,
1374
+ "rewards/generated": -25.548004150390625,
1375
+ "rewards/margins": 20.72186851501465,
1376
+ "rewards/real": -4.826132774353027,
1377
+ "step": 670
1378
+ },
1379
+ {
1380
+ "epoch": 1.11,
1381
+ "eval_logits/generated": -1.6843816041946411,
1382
+ "eval_logits/real": -2.1123154163360596,
1383
+ "eval_logps/generated": -685.91259765625,
1384
+ "eval_logps/real": -474.67840576171875,
1385
+ "eval_loss": 0.04492348060011864,
1386
+ "eval_rewards/accuracies": 0.9712963104248047,
1387
+ "eval_rewards/generated": -23.157739639282227,
1388
+ "eval_rewards/margins": 17.424118041992188,
1389
+ "eval_rewards/real": -5.733626365661621,
1390
+ "eval_runtime": 538.5314,
1391
+ "eval_samples_per_second": 8.018,
1392
+ "eval_steps_per_second": 0.251,
1393
+ "step": 675
1394
+ },
1395
+ {
1396
+ "epoch": 1.12,
1397
+ "learning_rate": 2.4450549450549446e-07,
1398
+ "logits/generated": -1.6796834468841553,
1399
+ "logits/real": -2.1368143558502197,
1400
+ "logps/generated": -713.38916015625,
1401
+ "logps/real": -448.4339904785156,
1402
+ "loss": 0.0073,
1403
+ "rewards/accuracies": 0.9937499761581421,
1404
+ "rewards/generated": -26.294750213623047,
1405
+ "rewards/margins": 21.05908966064453,
1406
+ "rewards/real": -5.235660552978516,
1407
+ "step": 680
1408
+ },
1409
+ {
1410
+ "epoch": 1.14,
1411
+ "learning_rate": 2.3992673992673995e-07,
1412
+ "logits/generated": -1.6848552227020264,
1413
+ "logits/real": -2.062554121017456,
1414
+ "logps/generated": -727.1676025390625,
1415
+ "logps/real": -474.197998046875,
1416
+ "loss": 0.0004,
1417
+ "rewards/accuracies": 1.0,
1418
+ "rewards/generated": -26.072521209716797,
1419
+ "rewards/margins": 20.835004806518555,
1420
+ "rewards/real": -5.23751974105835,
1421
+ "step": 690
1422
+ },
1423
+ {
1424
+ "epoch": 1.15,
1425
+ "learning_rate": 2.3534798534798532e-07,
1426
+ "logits/generated": -1.83333420753479,
1427
+ "logits/real": -2.158902406692505,
1428
+ "logps/generated": -751.34423828125,
1429
+ "logps/real": -447.7481994628906,
1430
+ "loss": 0.0149,
1431
+ "rewards/accuracies": 0.9937499761581421,
1432
+ "rewards/generated": -26.157222747802734,
1433
+ "rewards/margins": 21.213214874267578,
1434
+ "rewards/real": -4.944005966186523,
1435
+ "step": 700
1436
+ },
1437
+ {
1438
+ "epoch": 1.15,
1439
+ "eval_logits/generated": -2.014181613922119,
1440
+ "eval_logits/real": -2.2748398780822754,
1441
+ "eval_logps/generated": -716.32373046875,
1442
+ "eval_logps/real": -488.8265686035156,
1443
+ "eval_loss": 0.060765769332647324,
1444
+ "eval_rewards/accuracies": 0.9712963104248047,
1445
+ "eval_rewards/generated": -26.19886016845703,
1446
+ "eval_rewards/margins": 19.0504150390625,
1447
+ "eval_rewards/real": -7.1484456062316895,
1448
+ "eval_runtime": 546.2873,
1449
+ "eval_samples_per_second": 7.904,
1450
+ "eval_steps_per_second": 0.247,
1451
+ "step": 700
1452
+ },
1453
+ {
1454
+ "epoch": 1.17,
1455
+ "learning_rate": 2.3076923076923078e-07,
1456
+ "logits/generated": -2.009290933609009,
1457
+ "logits/real": -2.248413562774658,
1458
+ "logps/generated": -723.00830078125,
1459
+ "logps/real": -485.6675720214844,
1460
+ "loss": 0.0156,
1461
+ "rewards/accuracies": 1.0,
1462
+ "rewards/generated": -26.66790771484375,
1463
+ "rewards/margins": 20.04497718811035,
1464
+ "rewards/real": -6.622932434082031,
1465
+ "step": 710
1466
+ },
1467
+ {
1468
+ "epoch": 1.19,
1469
+ "learning_rate": 2.2619047619047619e-07,
1470
+ "logits/generated": -2.0311272144317627,
1471
+ "logits/real": -2.2884433269500732,
1472
+ "logps/generated": -705.41259765625,
1473
+ "logps/real": -439.14654541015625,
1474
+ "loss": 0.0105,
1475
+ "rewards/accuracies": 0.9937499761581421,
1476
+ "rewards/generated": -25.88492202758789,
1477
+ "rewards/margins": 21.01565170288086,
1478
+ "rewards/real": -4.869270324707031,
1479
+ "step": 720
1480
+ },
1481
+ {
1482
+ "epoch": 1.19,
1483
+ "eval_logits/generated": -2.1674070358276367,
1484
+ "eval_logits/real": -2.3962087631225586,
1485
+ "eval_logps/generated": -656.84765625,
1486
+ "eval_logps/real": -462.290283203125,
1487
+ "eval_loss": 0.04788418486714363,
1488
+ "eval_rewards/accuracies": 0.9722222089767456,
1489
+ "eval_rewards/generated": -20.25126075744629,
1490
+ "eval_rewards/margins": 15.756444931030273,
1491
+ "eval_rewards/real": -4.494814872741699,
1492
+ "eval_runtime": 549.4973,
1493
+ "eval_samples_per_second": 7.858,
1494
+ "eval_steps_per_second": 0.246,
1495
+ "step": 725
1496
+ },
1497
+ {
1498
+ "epoch": 1.2,
1499
+ "learning_rate": 2.216117216117216e-07,
1500
+ "logits/generated": -2.1520206928253174,
1501
+ "logits/real": -2.384286403656006,
1502
+ "logps/generated": -693.1768188476562,
1503
+ "logps/real": -427.69384765625,
1504
+ "loss": 0.0129,
1505
+ "rewards/accuracies": 0.981249988079071,
1506
+ "rewards/generated": -21.8217830657959,
1507
+ "rewards/margins": 18.449357986450195,
1508
+ "rewards/real": -3.3724265098571777,
1509
+ "step": 730
1510
+ },
1511
+ {
1512
+ "epoch": 1.22,
1513
+ "learning_rate": 2.1703296703296702e-07,
1514
+ "logits/generated": -2.164816379547119,
1515
+ "logits/real": -2.4095542430877686,
1516
+ "logps/generated": -731.2252807617188,
1517
+ "logps/real": -431.8036193847656,
1518
+ "loss": 0.0117,
1519
+ "rewards/accuracies": 1.0,
1520
+ "rewards/generated": -22.88985252380371,
1521
+ "rewards/margins": 19.35944938659668,
1522
+ "rewards/real": -3.5304055213928223,
1523
+ "step": 740
1524
+ },
1525
+ {
1526
+ "epoch": 1.23,
1527
+ "learning_rate": 2.1245421245421245e-07,
1528
+ "logits/generated": -2.3042044639587402,
1529
+ "logits/real": -2.4798831939697266,
1530
+ "logps/generated": -710.3934326171875,
1531
+ "logps/real": -447.3128967285156,
1532
+ "loss": 0.032,
1533
+ "rewards/accuracies": 0.9750000238418579,
1534
+ "rewards/generated": -22.082233428955078,
1535
+ "rewards/margins": 17.938434600830078,
1536
+ "rewards/real": -4.143797874450684,
1537
+ "step": 750
1538
+ },
1539
+ {
1540
+ "epoch": 1.23,
1541
+ "eval_logits/generated": -2.2425506114959717,
1542
+ "eval_logits/real": -2.4413764476776123,
1543
+ "eval_logps/generated": -667.56494140625,
1544
+ "eval_logps/real": -468.2917175292969,
1545
+ "eval_loss": 0.05120517686009407,
1546
+ "eval_rewards/accuracies": 0.9685184955596924,
1547
+ "eval_rewards/generated": -21.322982788085938,
1548
+ "eval_rewards/margins": 16.22801971435547,
1549
+ "eval_rewards/real": -5.094962120056152,
1550
+ "eval_runtime": 548.9256,
1551
+ "eval_samples_per_second": 7.866,
1552
+ "eval_steps_per_second": 0.246,
1553
+ "step": 750
1554
+ },
1555
+ {
1556
+ "epoch": 1.25,
1557
+ "learning_rate": 2.0787545787545788e-07,
1558
+ "logits/generated": -2.3006973266601562,
1559
+ "logits/real": -2.4579455852508545,
1560
+ "logps/generated": -678.5315551757812,
1561
+ "logps/real": -444.89593505859375,
1562
+ "loss": 0.0108,
1563
+ "rewards/accuracies": 0.987500011920929,
1564
+ "rewards/generated": -20.485198974609375,
1565
+ "rewards/margins": 17.16245460510254,
1566
+ "rewards/real": -3.322744846343994,
1567
+ "step": 760
1568
+ },
1569
+ {
1570
+ "epoch": 1.27,
1571
+ "learning_rate": 2.0329670329670329e-07,
1572
+ "logits/generated": -2.276136875152588,
1573
+ "logits/real": -2.4627890586853027,
1574
+ "logps/generated": -626.4572143554688,
1575
+ "logps/real": -460.61090087890625,
1576
+ "loss": 0.0042,
1577
+ "rewards/accuracies": 0.9937499761581421,
1578
+ "rewards/generated": -18.86962890625,
1579
+ "rewards/margins": 15.991884231567383,
1580
+ "rewards/real": -2.8777451515197754,
1581
+ "step": 770
1582
+ },
1583
+ {
1584
+ "epoch": 1.28,
1585
+ "eval_logits/generated": -2.215578317642212,
1586
+ "eval_logits/real": -2.4378671646118164,
1587
+ "eval_logps/generated": -646.9547729492188,
1588
+ "eval_logps/real": -457.63812255859375,
1589
+ "eval_loss": 0.04618338495492935,
1590
+ "eval_rewards/accuracies": 0.970370352268219,
1591
+ "eval_rewards/generated": -19.261966705322266,
1592
+ "eval_rewards/margins": 15.232365608215332,
1593
+ "eval_rewards/real": -4.029602527618408,
1594
+ "eval_runtime": 545.4173,
1595
+ "eval_samples_per_second": 7.917,
1596
+ "eval_steps_per_second": 0.248,
1597
+ "step": 775
1598
+ },
1599
+ {
1600
+ "epoch": 1.28,
1601
+ "learning_rate": 1.987179487179487e-07,
1602
+ "logits/generated": -2.1666736602783203,
1603
+ "logits/real": -2.430644989013672,
1604
+ "logps/generated": -617.3143310546875,
1605
+ "logps/real": -455.05450439453125,
1606
+ "loss": 0.0181,
1607
+ "rewards/accuracies": 0.9937499761581421,
1608
+ "rewards/generated": -19.36526870727539,
1609
+ "rewards/margins": 16.152751922607422,
1610
+ "rewards/real": -3.2125182151794434,
1611
+ "step": 780
1612
+ },
1613
+ {
1614
+ "epoch": 1.3,
1615
+ "learning_rate": 1.9413919413919415e-07,
1616
+ "logits/generated": -2.1149790287017822,
1617
+ "logits/real": -2.3885388374328613,
1618
+ "logps/generated": -665.8757934570312,
1619
+ "logps/real": -415.7660217285156,
1620
+ "loss": 0.0105,
1621
+ "rewards/accuracies": 0.9937499761581421,
1622
+ "rewards/generated": -21.40970230102539,
1623
+ "rewards/margins": 19.079601287841797,
1624
+ "rewards/real": -2.3301024436950684,
1625
+ "step": 790
1626
+ },
1627
+ {
1628
+ "epoch": 1.32,
1629
+ "learning_rate": 1.8956043956043955e-07,
1630
+ "logits/generated": -2.172045946121216,
1631
+ "logits/real": -2.39658784866333,
1632
+ "logps/generated": -646.7432861328125,
1633
+ "logps/real": -423.2108459472656,
1634
+ "loss": 0.0041,
1635
+ "rewards/accuracies": 1.0,
1636
+ "rewards/generated": -20.290569305419922,
1637
+ "rewards/margins": 17.622339248657227,
1638
+ "rewards/real": -2.6682305335998535,
1639
+ "step": 800
1640
+ },
1641
+ {
1642
+ "epoch": 1.32,
1643
+ "eval_logits/generated": -2.132990598678589,
1644
+ "eval_logits/real": -2.384284019470215,
1645
+ "eval_logps/generated": -652.7453002929688,
1646
+ "eval_logps/real": -457.6903381347656,
1647
+ "eval_loss": 0.04753004014492035,
1648
+ "eval_rewards/accuracies": 0.9731481671333313,
1649
+ "eval_rewards/generated": -19.841014862060547,
1650
+ "eval_rewards/margins": 15.806192398071289,
1651
+ "eval_rewards/real": -4.034823894500732,
1652
+ "eval_runtime": 542.7194,
1653
+ "eval_samples_per_second": 7.956,
1654
+ "eval_steps_per_second": 0.249,
1655
+ "step": 800
1656
+ },
1657
+ {
1658
+ "epoch": 1.33,
1659
+ "learning_rate": 1.8498168498168498e-07,
1660
+ "logits/generated": -2.2161784172058105,
1661
+ "logits/real": -2.3784358501434326,
1662
+ "logps/generated": -677.4197998046875,
1663
+ "logps/real": -415.10162353515625,
1664
+ "loss": 0.0139,
1665
+ "rewards/accuracies": 0.987500011920929,
1666
+ "rewards/generated": -20.94455909729004,
1667
+ "rewards/margins": 18.23735809326172,
1668
+ "rewards/real": -2.707200527191162,
1669
+ "step": 810
1670
+ },
1671
+ {
1672
+ "epoch": 1.35,
1673
+ "learning_rate": 1.8040293040293039e-07,
1674
+ "logits/generated": -2.162409782409668,
1675
+ "logits/real": -2.4266014099121094,
1676
+ "logps/generated": -634.3106689453125,
1677
+ "logps/real": -426.293212890625,
1678
+ "loss": 0.0075,
1679
+ "rewards/accuracies": 1.0,
1680
+ "rewards/generated": -19.84092140197754,
1681
+ "rewards/margins": 17.243751525878906,
1682
+ "rewards/real": -2.5971689224243164,
1683
+ "step": 820
1684
+ },
1685
+ {
1686
+ "epoch": 1.36,
1687
+ "eval_logits/generated": -2.1121842861175537,
1688
+ "eval_logits/real": -2.371814012527466,
1689
+ "eval_logps/generated": -662.919189453125,
1690
+ "eval_logps/real": -462.037841796875,
1691
+ "eval_loss": 0.042767442762851715,
1692
+ "eval_rewards/accuracies": 0.9722222089767456,
1693
+ "eval_rewards/generated": -20.858409881591797,
1694
+ "eval_rewards/margins": 16.388830184936523,
1695
+ "eval_rewards/real": -4.469577789306641,
1696
+ "eval_runtime": 539.1341,
1697
+ "eval_samples_per_second": 8.009,
1698
+ "eval_steps_per_second": 0.25,
1699
+ "step": 825
1700
+ },
1701
+ {
1702
+ "epoch": 1.37,
1703
+ "learning_rate": 1.7582417582417584e-07,
1704
+ "logits/generated": -2.063286304473877,
1705
+ "logits/real": -2.3742778301239014,
1706
+ "logps/generated": -688.5067138671875,
1707
+ "logps/real": -435.5904846191406,
1708
+ "loss": 0.0075,
1709
+ "rewards/accuracies": 0.987500011920929,
1710
+ "rewards/generated": -22.731130599975586,
1711
+ "rewards/margins": 19.344463348388672,
1712
+ "rewards/real": -3.3866665363311768,
1713
+ "step": 830
1714
+ },
1715
+ {
1716
+ "epoch": 1.38,
1717
+ "learning_rate": 1.7124542124542125e-07,
1718
+ "logits/generated": -1.8474409580230713,
1719
+ "logits/real": -2.223342180252075,
1720
+ "logps/generated": -727.342041015625,
1721
+ "logps/real": -428.4285583496094,
1722
+ "loss": 0.0029,
1723
+ "rewards/accuracies": 1.0,
1724
+ "rewards/generated": -27.19036293029785,
1725
+ "rewards/margins": 22.461837768554688,
1726
+ "rewards/real": -4.728522300720215,
1727
+ "step": 840
1728
+ },
1729
+ {
1730
+ "epoch": 1.4,
1731
+ "learning_rate": 1.6666666666666665e-07,
1732
+ "logits/generated": -1.7657016515731812,
1733
+ "logits/real": -2.246410369873047,
1734
+ "logps/generated": -764.67236328125,
1735
+ "logps/real": -466.6670837402344,
1736
+ "loss": 0.004,
1737
+ "rewards/accuracies": 0.9937499761581421,
1738
+ "rewards/generated": -28.994009017944336,
1739
+ "rewards/margins": 23.707733154296875,
1740
+ "rewards/real": -5.286276817321777,
1741
+ "step": 850
1742
+ },
1743
+ {
1744
+ "epoch": 1.4,
1745
+ "eval_logits/generated": -1.7239781618118286,
1746
+ "eval_logits/real": -2.1708648204803467,
1747
+ "eval_logps/generated": -710.6077880859375,
1748
+ "eval_logps/real": -480.1641845703125,
1749
+ "eval_loss": 0.04679808393120766,
1750
+ "eval_rewards/accuracies": 0.9750000238418579,
1751
+ "eval_rewards/generated": -25.62726593017578,
1752
+ "eval_rewards/margins": 19.34505844116211,
1753
+ "eval_rewards/real": -6.282209396362305,
1754
+ "eval_runtime": 539.6647,
1755
+ "eval_samples_per_second": 8.001,
1756
+ "eval_steps_per_second": 0.25,
1757
+ "step": 850
1758
+ },
1759
+ {
1760
+ "epoch": 1.42,
1761
+ "learning_rate": 1.6208791208791208e-07,
1762
+ "logits/generated": -1.5984615087509155,
1763
+ "logits/real": -2.1419482231140137,
1764
+ "logps/generated": -743.21337890625,
1765
+ "logps/real": -483.67608642578125,
1766
+ "loss": 0.0002,
1767
+ "rewards/accuracies": 1.0,
1768
+ "rewards/generated": -27.930688858032227,
1769
+ "rewards/margins": 22.560997009277344,
1770
+ "rewards/real": -5.369691371917725,
1771
+ "step": 860
1772
+ },
1773
+ {
1774
+ "epoch": 1.43,
1775
+ "learning_rate": 1.5750915750915748e-07,
1776
+ "logits/generated": -1.7401374578475952,
1777
+ "logits/real": -2.2165982723236084,
1778
+ "logps/generated": -744.0372314453125,
1779
+ "logps/real": -467.1297912597656,
1780
+ "loss": 0.0222,
1781
+ "rewards/accuracies": 0.987500011920929,
1782
+ "rewards/generated": -26.236160278320312,
1783
+ "rewards/margins": 20.77927017211914,
1784
+ "rewards/real": -5.456892013549805,
1785
+ "step": 870
1786
+ },
1787
+ {
1788
+ "epoch": 1.44,
1789
+ "eval_logits/generated": -1.6543631553649902,
1790
+ "eval_logits/real": -2.1242499351501465,
1791
+ "eval_logps/generated": -685.1132202148438,
1792
+ "eval_logps/real": -477.74078369140625,
1793
+ "eval_loss": 0.05835163965821266,
1794
+ "eval_rewards/accuracies": 0.9759259223937988,
1795
+ "eval_rewards/generated": -23.077802658081055,
1796
+ "eval_rewards/margins": 17.037935256958008,
1797
+ "eval_rewards/real": -6.039866924285889,
1798
+ "eval_runtime": 542.9056,
1799
+ "eval_samples_per_second": 7.954,
1800
+ "eval_steps_per_second": 0.249,
1801
+ "step": 875
1802
+ },
1803
+ {
1804
+ "epoch": 1.45,
1805
+ "learning_rate": 1.5293040293040294e-07,
1806
+ "logits/generated": -1.6089227199554443,
1807
+ "logits/real": -2.1636829376220703,
1808
+ "logps/generated": -724.6553344726562,
1809
+ "logps/real": -462.1668395996094,
1810
+ "loss": 0.0095,
1811
+ "rewards/accuracies": 1.0,
1812
+ "rewards/generated": -25.3486385345459,
1813
+ "rewards/margins": 20.25618553161621,
1814
+ "rewards/real": -5.0924506187438965,
1815
+ "step": 880
1816
+ },
1817
+ {
1818
+ "epoch": 1.47,
1819
+ "learning_rate": 1.4835164835164835e-07,
1820
+ "logits/generated": -1.762058973312378,
1821
+ "logits/real": -2.180694818496704,
1822
+ "logps/generated": -734.1724853515625,
1823
+ "logps/real": -474.927978515625,
1824
+ "loss": 0.0228,
1825
+ "rewards/accuracies": 1.0,
1826
+ "rewards/generated": -24.476972579956055,
1827
+ "rewards/margins": 20.52760124206543,
1828
+ "rewards/real": -3.949371814727783,
1829
+ "step": 890
1830
+ },
1831
+ {
1832
+ "epoch": 1.48,
1833
+ "learning_rate": 1.4377289377289375e-07,
1834
+ "logits/generated": -1.8223994970321655,
1835
+ "logits/real": -2.230008602142334,
1836
+ "logps/generated": -674.3191528320312,
1837
+ "logps/real": -437.16448974609375,
1838
+ "loss": 0.0063,
1839
+ "rewards/accuracies": 0.9937499761581421,
1840
+ "rewards/generated": -22.358070373535156,
1841
+ "rewards/margins": 19.133329391479492,
1842
+ "rewards/real": -3.2247397899627686,
1843
+ "step": 900
1844
+ },
1845
+ {
1846
+ "epoch": 1.48,
1847
+ "eval_logits/generated": -1.7696380615234375,
1848
+ "eval_logits/real": -2.202569007873535,
1849
+ "eval_logps/generated": -652.3550415039062,
1850
+ "eval_logps/real": -456.0634765625,
1851
+ "eval_loss": 0.04898802191019058,
1852
+ "eval_rewards/accuracies": 0.9722222089767456,
1853
+ "eval_rewards/generated": -19.801984786987305,
1854
+ "eval_rewards/margins": 15.92984676361084,
1855
+ "eval_rewards/real": -3.8721377849578857,
1856
+ "eval_runtime": 541.3411,
1857
+ "eval_samples_per_second": 7.976,
1858
+ "eval_steps_per_second": 0.249,
1859
+ "step": 900
1860
+ },
1861
+ {
1862
+ "epoch": 1.5,
1863
+ "learning_rate": 1.3919413919413918e-07,
1864
+ "logits/generated": -1.7800897359848022,
1865
+ "logits/real": -2.215033531188965,
1866
+ "logps/generated": -680.4356689453125,
1867
+ "logps/real": -436.82257080078125,
1868
+ "loss": 0.0095,
1869
+ "rewards/accuracies": 0.987500011920929,
1870
+ "rewards/generated": -21.27292251586914,
1871
+ "rewards/margins": 17.82526969909668,
1872
+ "rewards/real": -3.4476523399353027,
1873
+ "step": 910
1874
+ },
1875
+ {
1876
+ "epoch": 1.51,
1877
+ "learning_rate": 1.346153846153846e-07,
1878
+ "logits/generated": -1.6774091720581055,
1879
+ "logits/real": -2.172245740890503,
1880
+ "logps/generated": -713.2435302734375,
1881
+ "logps/real": -457.10125732421875,
1882
+ "loss": 0.006,
1883
+ "rewards/accuracies": 1.0,
1884
+ "rewards/generated": -23.64259147644043,
1885
+ "rewards/margins": 19.829133987426758,
1886
+ "rewards/real": -3.813458204269409,
1887
+ "step": 920
1888
+ },
1889
+ {
1890
+ "epoch": 1.52,
1891
+ "eval_logits/generated": -1.6461421251296997,
1892
+ "eval_logits/real": -2.1238648891448975,
1893
+ "eval_logps/generated": -691.8392333984375,
1894
+ "eval_logps/real": -470.1639404296875,
1895
+ "eval_loss": 0.04775296524167061,
1896
+ "eval_rewards/accuracies": 0.9750000238418579,
1897
+ "eval_rewards/generated": -23.750408172607422,
1898
+ "eval_rewards/margins": 18.46822738647461,
1899
+ "eval_rewards/real": -5.282179355621338,
1900
+ "eval_runtime": 545.1425,
1901
+ "eval_samples_per_second": 7.921,
1902
+ "eval_steps_per_second": 0.248,
1903
+ "step": 925
1904
+ },
1905
+ {
1906
+ "epoch": 1.53,
1907
+ "learning_rate": 1.3003663003663004e-07,
1908
+ "logits/generated": -1.691014051437378,
1909
+ "logits/real": -2.090836763381958,
1910
+ "logps/generated": -717.5584716796875,
1911
+ "logps/real": -426.21075439453125,
1912
+ "loss": 0.0146,
1913
+ "rewards/accuracies": 0.987500011920929,
1914
+ "rewards/generated": -24.57354736328125,
1915
+ "rewards/margins": 20.423908233642578,
1916
+ "rewards/real": -4.1496381759643555,
1917
+ "step": 930
1918
+ },
1919
+ {
1920
+ "epoch": 1.55,
1921
+ "learning_rate": 1.2545787545787545e-07,
1922
+ "logits/generated": -1.7866837978363037,
1923
+ "logits/real": -2.1096789836883545,
1924
+ "logps/generated": -695.7778930664062,
1925
+ "logps/real": -430.5741271972656,
1926
+ "loss": 0.0098,
1927
+ "rewards/accuracies": 0.981249988079071,
1928
+ "rewards/generated": -23.648204803466797,
1929
+ "rewards/margins": 19.338354110717773,
1930
+ "rewards/real": -4.30985164642334,
1931
+ "step": 940
1932
+ },
1933
+ {
1934
+ "epoch": 1.56,
1935
+ "learning_rate": 1.2087912087912088e-07,
1936
+ "logits/generated": -1.6880855560302734,
1937
+ "logits/real": -2.137526512145996,
1938
+ "logps/generated": -677.9566040039062,
1939
+ "logps/real": -424.09771728515625,
1940
+ "loss": 0.0169,
1941
+ "rewards/accuracies": 0.981249988079071,
1942
+ "rewards/generated": -23.116125106811523,
1943
+ "rewards/margins": 19.75508689880371,
1944
+ "rewards/real": -3.3610382080078125,
1945
+ "step": 950
1946
+ },
1947
+ {
1948
+ "epoch": 1.56,
1949
+ "eval_logits/generated": -1.6890491247177124,
1950
+ "eval_logits/real": -2.1447362899780273,
1951
+ "eval_logps/generated": -683.7665405273438,
1952
+ "eval_logps/real": -466.7169189453125,
1953
+ "eval_loss": 0.045488789677619934,
1954
+ "eval_rewards/accuracies": 0.9731481671333313,
1955
+ "eval_rewards/generated": -22.943147659301758,
1956
+ "eval_rewards/margins": 18.005666732788086,
1957
+ "eval_rewards/real": -4.937481880187988,
1958
+ "eval_runtime": 541.292,
1959
+ "eval_samples_per_second": 7.977,
1960
+ "eval_steps_per_second": 0.249,
1961
+ "step": 950
1962
+ },
1963
+ {
1964
+ "epoch": 1.58,
1965
+ "learning_rate": 1.163003663003663e-07,
1966
+ "logits/generated": -1.7114064693450928,
1967
+ "logits/real": -2.16520094871521,
1968
+ "logps/generated": -719.1756591796875,
1969
+ "logps/real": -456.89697265625,
1970
+ "loss": 0.0044,
1971
+ "rewards/accuracies": 1.0,
1972
+ "rewards/generated": -25.02173614501953,
1973
+ "rewards/margins": 20.79627227783203,
1974
+ "rewards/real": -4.225462913513184,
1975
+ "step": 960
1976
+ },
1977
+ {
1978
+ "epoch": 1.6,
1979
+ "learning_rate": 1.1172161172161172e-07,
1980
+ "logits/generated": -1.6347287893295288,
1981
+ "logits/real": -2.1204426288604736,
1982
+ "logps/generated": -683.4697875976562,
1983
+ "logps/real": -454.54461669921875,
1984
+ "loss": 0.0063,
1985
+ "rewards/accuracies": 0.987500011920929,
1986
+ "rewards/generated": -24.318696975708008,
1987
+ "rewards/margins": 19.61166763305664,
1988
+ "rewards/real": -4.707026958465576,
1989
+ "step": 970
1990
+ },
1991
+ {
1992
+ "epoch": 1.6,
1993
+ "eval_logits/generated": -1.5889698266983032,
1994
+ "eval_logits/real": -2.077850818634033,
1995
+ "eval_logps/generated": -704.8994140625,
1996
+ "eval_logps/real": -477.1242370605469,
1997
+ "eval_loss": 0.04485413804650307,
1998
+ "eval_rewards/accuracies": 0.9740740656852722,
1999
+ "eval_rewards/generated": -25.056419372558594,
2000
+ "eval_rewards/margins": 19.078208923339844,
2001
+ "eval_rewards/real": -5.978213787078857,
2002
+ "eval_runtime": 545.2881,
2003
+ "eval_samples_per_second": 7.919,
2004
+ "eval_steps_per_second": 0.248,
2005
+ "step": 975
2006
+ },
2007
+ {
2008
+ "epoch": 1.61,
2009
+ "learning_rate": 1.0714285714285713e-07,
2010
+ "logits/generated": -1.6600666046142578,
2011
+ "logits/real": -2.114758014678955,
2012
+ "logps/generated": -709.62890625,
2013
+ "logps/real": -427.54022216796875,
2014
+ "loss": 0.0122,
2015
+ "rewards/accuracies": 0.981249988079071,
2016
+ "rewards/generated": -24.828792572021484,
2017
+ "rewards/margins": 20.330127716064453,
2018
+ "rewards/real": -4.498665809631348,
2019
+ "step": 980
2020
+ },
2021
+ {
2022
+ "epoch": 1.63,
2023
+ "learning_rate": 1.0256410256410256e-07,
2024
+ "logits/generated": -1.5314631462097168,
2025
+ "logits/real": -2.0638275146484375,
2026
+ "logps/generated": -710.69482421875,
2027
+ "logps/real": -447.7142028808594,
2028
+ "loss": 0.0176,
2029
+ "rewards/accuracies": 0.9937499761581421,
2030
+ "rewards/generated": -25.278757095336914,
2031
+ "rewards/margins": 20.97730255126953,
2032
+ "rewards/real": -4.301451683044434,
2033
+ "step": 990
2034
+ },
2035
+ {
2036
+ "epoch": 1.65,
2037
+ "learning_rate": 9.798534798534798e-08,
2038
+ "logits/generated": -1.659684181213379,
2039
+ "logits/real": -2.0716404914855957,
2040
+ "logps/generated": -747.033203125,
2041
+ "logps/real": -457.4671936035156,
2042
+ "loss": 0.0144,
2043
+ "rewards/accuracies": 0.987500011920929,
2044
+ "rewards/generated": -26.58378028869629,
2045
+ "rewards/margins": 22.331199645996094,
2046
+ "rewards/real": -4.2525811195373535,
2047
+ "step": 1000
2048
+ },
2049
+ {
2050
+ "epoch": 1.65,
2051
+ "eval_logits/generated": -1.626175880432129,
2052
+ "eval_logits/real": -2.085879325866699,
2053
+ "eval_logps/generated": -683.6390991210938,
2054
+ "eval_logps/real": -469.9638671875,
2055
+ "eval_loss": 0.04278276115655899,
2056
+ "eval_rewards/accuracies": 0.9731481671333313,
2057
+ "eval_rewards/generated": -22.93039894104004,
2058
+ "eval_rewards/margins": 17.668224334716797,
2059
+ "eval_rewards/real": -5.262173175811768,
2060
+ "eval_runtime": 544.8826,
2061
+ "eval_samples_per_second": 7.925,
2062
+ "eval_steps_per_second": 0.248,
2063
+ "step": 1000
2064
+ },
2065
+ {
2066
+ "epoch": 1.66,
2067
+ "learning_rate": 9.340659340659341e-08,
2068
+ "logits/generated": -1.5913441181182861,
2069
+ "logits/real": -2.1010706424713135,
2070
+ "logps/generated": -683.9640502929688,
2071
+ "logps/real": -461.71038818359375,
2072
+ "loss": 0.0053,
2073
+ "rewards/accuracies": 1.0,
2074
+ "rewards/generated": -23.161916732788086,
2075
+ "rewards/margins": 19.142833709716797,
2076
+ "rewards/real": -4.0190839767456055,
2077
+ "step": 1010
2078
+ },
2079
+ {
2080
+ "epoch": 1.68,
2081
+ "learning_rate": 8.882783882783882e-08,
2082
+ "logits/generated": -1.6814014911651611,
2083
+ "logits/real": -2.1148276329040527,
2084
+ "logps/generated": -701.2926025390625,
2085
+ "logps/real": -449.57421875,
2086
+ "loss": 0.0046,
2087
+ "rewards/accuracies": 1.0,
2088
+ "rewards/generated": -24.634958267211914,
2089
+ "rewards/margins": 20.201641082763672,
2090
+ "rewards/real": -4.433315753936768,
2091
+ "step": 1020
2092
+ },
2093
+ {
2094
+ "epoch": 1.69,
2095
+ "eval_logits/generated": -1.607029914855957,
2096
+ "eval_logits/real": -2.093400478363037,
2097
+ "eval_logps/generated": -695.1799926757812,
2098
+ "eval_logps/real": -472.4885559082031,
2099
+ "eval_loss": 0.04106166213750839,
2100
+ "eval_rewards/accuracies": 0.9759259223937988,
2101
+ "eval_rewards/generated": -24.0844783782959,
2102
+ "eval_rewards/margins": 18.56983757019043,
2103
+ "eval_rewards/real": -5.514641284942627,
2104
+ "eval_runtime": 541.5376,
2105
+ "eval_samples_per_second": 7.974,
2106
+ "eval_steps_per_second": 0.249,
2107
+ "step": 1025
2108
+ },
2109
+ {
2110
+ "epoch": 1.7,
2111
+ "learning_rate": 8.424908424908425e-08,
2112
+ "logits/generated": -1.6199986934661865,
2113
+ "logits/real": -2.0736172199249268,
2114
+ "logps/generated": -728.6807861328125,
2115
+ "logps/real": -431.51824951171875,
2116
+ "loss": 0.0066,
2117
+ "rewards/accuracies": 0.9937499761581421,
2118
+ "rewards/generated": -25.239320755004883,
2119
+ "rewards/margins": 21.229106903076172,
2120
+ "rewards/real": -4.0102128982543945,
2121
+ "step": 1030
2122
+ },
2123
+ {
2124
+ "epoch": 1.71,
2125
+ "learning_rate": 7.967032967032966e-08,
2126
+ "logits/generated": -1.6336625814437866,
2127
+ "logits/real": -2.1006054878234863,
2128
+ "logps/generated": -734.5277709960938,
2129
+ "logps/real": -478.76446533203125,
2130
+ "loss": 0.0034,
2131
+ "rewards/accuracies": 1.0,
2132
+ "rewards/generated": -26.6556339263916,
2133
+ "rewards/margins": 21.211820602416992,
2134
+ "rewards/real": -5.443814277648926,
2135
+ "step": 1040
2136
+ },
2137
+ {
2138
+ "epoch": 1.73,
2139
+ "learning_rate": 7.509157509157509e-08,
2140
+ "logits/generated": -1.649921178817749,
2141
+ "logits/real": -2.090855598449707,
2142
+ "logps/generated": -750.3670043945312,
2143
+ "logps/real": -452.450927734375,
2144
+ "loss": 0.002,
2145
+ "rewards/accuracies": 1.0,
2146
+ "rewards/generated": -26.29367446899414,
2147
+ "rewards/margins": 22.180587768554688,
2148
+ "rewards/real": -4.113083362579346,
2149
+ "step": 1050
2150
+ },
2151
+ {
2152
+ "epoch": 1.73,
2153
+ "eval_logits/generated": -1.6779299974441528,
2154
+ "eval_logits/real": -2.1277213096618652,
2155
+ "eval_logps/generated": -691.9456787109375,
2156
+ "eval_logps/real": -471.51629638671875,
2157
+ "eval_loss": 0.04077158868312836,
2158
+ "eval_rewards/accuracies": 0.9750000238418579,
2159
+ "eval_rewards/generated": -23.761049270629883,
2160
+ "eval_rewards/margins": 18.3436336517334,
2161
+ "eval_rewards/real": -5.417417049407959,
2162
+ "eval_runtime": 539.3269,
2163
+ "eval_samples_per_second": 8.006,
2164
+ "eval_steps_per_second": 0.25,
2165
+ "step": 1050
2166
+ },
2167
+ {
2168
+ "epoch": 1.74,
2169
+ "learning_rate": 7.051282051282051e-08,
2170
+ "logits/generated": -1.722020149230957,
2171
+ "logits/real": -2.128837823867798,
2172
+ "logps/generated": -728.57861328125,
2173
+ "logps/real": -456.64312744140625,
2174
+ "loss": 0.0026,
2175
+ "rewards/accuracies": 1.0,
2176
+ "rewards/generated": -25.133262634277344,
2177
+ "rewards/margins": 21.077022552490234,
2178
+ "rewards/real": -4.0562424659729,
2179
+ "step": 1060
2180
+ },
2181
+ {
2182
+ "epoch": 1.76,
2183
+ "learning_rate": 6.593406593406594e-08,
2184
+ "logits/generated": -1.723589539527893,
2185
+ "logits/real": -2.129660129547119,
2186
+ "logps/generated": -737.1346435546875,
2187
+ "logps/real": -446.6085510253906,
2188
+ "loss": 0.0047,
2189
+ "rewards/accuracies": 1.0,
2190
+ "rewards/generated": -26.5841064453125,
2191
+ "rewards/margins": 21.89805030822754,
2192
+ "rewards/real": -4.686056137084961,
2193
+ "step": 1070
2194
+ },
2195
+ {
2196
+ "epoch": 1.77,
2197
+ "eval_logits/generated": -1.704836130142212,
2198
+ "eval_logits/real": -2.1411664485931396,
2199
+ "eval_logps/generated": -699.8467407226562,
2200
+ "eval_logps/real": -474.1795654296875,
2201
+ "eval_loss": 0.04111822694540024,
2202
+ "eval_rewards/accuracies": 0.9750000238418579,
2203
+ "eval_rewards/generated": -24.55116081237793,
2204
+ "eval_rewards/margins": 18.867414474487305,
2205
+ "eval_rewards/real": -5.683747291564941,
2206
+ "eval_runtime": 540.5677,
2207
+ "eval_samples_per_second": 7.988,
2208
+ "eval_steps_per_second": 0.25,
2209
+ "step": 1075
2210
+ },
2211
+ {
2212
+ "epoch": 1.78,
2213
+ "learning_rate": 6.135531135531135e-08,
2214
+ "logits/generated": -1.6880667209625244,
2215
+ "logits/real": -2.135887861251831,
2216
+ "logps/generated": -704.2137451171875,
2217
+ "logps/real": -462.7354431152344,
2218
+ "loss": 0.0019,
2219
+ "rewards/accuracies": 1.0,
2220
+ "rewards/generated": -25.7542724609375,
2221
+ "rewards/margins": 20.865833282470703,
2222
+ "rewards/real": -4.88844108581543,
2223
+ "step": 1080
2224
+ },
2225
+ {
2226
+ "epoch": 1.79,
2227
+ "learning_rate": 5.677655677655677e-08,
2228
+ "logits/generated": -1.630059003829956,
2229
+ "logits/real": -2.092768430709839,
2230
+ "logps/generated": -720.8707275390625,
2231
+ "logps/real": -457.188720703125,
2232
+ "loss": 0.0069,
2233
+ "rewards/accuracies": 1.0,
2234
+ "rewards/generated": -26.587078094482422,
2235
+ "rewards/margins": 21.475454330444336,
2236
+ "rewards/real": -5.1116228103637695,
2237
+ "step": 1090
2238
+ },
2239
+ {
2240
+ "epoch": 1.81,
2241
+ "learning_rate": 5.2197802197802196e-08,
2242
+ "logits/generated": -1.6180572509765625,
2243
+ "logits/real": -2.073620080947876,
2244
+ "logps/generated": -702.1611328125,
2245
+ "logps/real": -436.5894470214844,
2246
+ "loss": 0.0077,
2247
+ "rewards/accuracies": 0.987500011920929,
2248
+ "rewards/generated": -26.184375762939453,
2249
+ "rewards/margins": 21.657176971435547,
2250
+ "rewards/real": -4.52719783782959,
2251
+ "step": 1100
2252
+ },
2253
+ {
2254
+ "epoch": 1.81,
2255
+ "eval_logits/generated": -1.6256543397903442,
2256
+ "eval_logits/real": -2.091676950454712,
2257
+ "eval_logps/generated": -707.8128662109375,
2258
+ "eval_logps/real": -476.0543212890625,
2259
+ "eval_loss": 0.04039894789457321,
2260
+ "eval_rewards/accuracies": 0.9759259223937988,
2261
+ "eval_rewards/generated": -25.347776412963867,
2262
+ "eval_rewards/margins": 19.476551055908203,
2263
+ "eval_rewards/real": -5.87122106552124,
2264
+ "eval_runtime": 541.5935,
2265
+ "eval_samples_per_second": 7.973,
2266
+ "eval_steps_per_second": 0.249,
2267
+ "step": 1100
2268
+ },
2269
+ {
2270
+ "epoch": 1.83,
2271
+ "learning_rate": 4.7619047619047613e-08,
2272
+ "logits/generated": -1.6621770858764648,
2273
+ "logits/real": -2.0922763347625732,
2274
+ "logps/generated": -746.7325439453125,
2275
+ "logps/real": -442.34857177734375,
2276
+ "loss": 0.0109,
2277
+ "rewards/accuracies": 0.9937499761581421,
2278
+ "rewards/generated": -28.543167114257812,
2279
+ "rewards/margins": 23.869972229003906,
2280
+ "rewards/real": -4.6731953620910645,
2281
+ "step": 1110
2282
+ },
2283
+ {
2284
+ "epoch": 1.84,
2285
+ "learning_rate": 4.304029304029304e-08,
2286
+ "logits/generated": -1.6281875371932983,
2287
+ "logits/real": -2.095040798187256,
2288
+ "logps/generated": -751.2948608398438,
2289
+ "logps/real": -464.0716857910156,
2290
+ "loss": 0.0145,
2291
+ "rewards/accuracies": 1.0,
2292
+ "rewards/generated": -25.601943969726562,
2293
+ "rewards/margins": 21.863361358642578,
2294
+ "rewards/real": -3.738584041595459,
2295
+ "step": 1120
2296
+ },
2297
+ {
2298
+ "epoch": 1.85,
2299
+ "eval_logits/generated": -1.6509149074554443,
2300
+ "eval_logits/real": -2.1029398441314697,
2301
+ "eval_logps/generated": -686.7852783203125,
2302
+ "eval_logps/real": -468.099853515625,
2303
+ "eval_loss": 0.038483668118715286,
2304
+ "eval_rewards/accuracies": 0.9740740656852722,
2305
+ "eval_rewards/generated": -23.245014190673828,
2306
+ "eval_rewards/margins": 18.169240951538086,
2307
+ "eval_rewards/real": -5.075774192810059,
2308
+ "eval_runtime": 542.4541,
2309
+ "eval_samples_per_second": 7.96,
2310
+ "eval_steps_per_second": 0.249,
2311
+ "step": 1125
2312
+ },
2313
+ {
2314
+ "epoch": 1.86,
2315
+ "learning_rate": 3.846153846153846e-08,
2316
+ "logits/generated": -1.7731685638427734,
2317
+ "logits/real": -2.1262717247009277,
2318
+ "logps/generated": -718.3228149414062,
2319
+ "logps/real": -450.9098205566406,
2320
+ "loss": 0.018,
2321
+ "rewards/accuracies": 0.9750000238418579,
2322
+ "rewards/generated": -23.984769821166992,
2323
+ "rewards/margins": 19.602436065673828,
2324
+ "rewards/real": -4.382335662841797,
2325
+ "step": 1130
2326
+ },
2327
+ {
2328
+ "epoch": 1.88,
2329
+ "learning_rate": 3.388278388278388e-08,
2330
+ "logits/generated": -1.7456114292144775,
2331
+ "logits/real": -2.1026391983032227,
2332
+ "logps/generated": -726.411376953125,
2333
+ "logps/real": -401.18524169921875,
2334
+ "loss": 0.0146,
2335
+ "rewards/accuracies": 0.9937499761581421,
2336
+ "rewards/generated": -25.529359817504883,
2337
+ "rewards/margins": 21.635169982910156,
2338
+ "rewards/real": -3.8941879272460938,
2339
+ "step": 1140
2340
+ },
2341
+ {
2342
+ "epoch": 1.89,
2343
+ "learning_rate": 2.9304029304029303e-08,
2344
+ "logits/generated": -1.6194369792938232,
2345
+ "logits/real": -2.1418557167053223,
2346
+ "logps/generated": -741.9666748046875,
2347
+ "logps/real": -464.30682373046875,
2348
+ "loss": 0.0038,
2349
+ "rewards/accuracies": 0.9937499761581421,
2350
+ "rewards/generated": -27.52840232849121,
2351
+ "rewards/margins": 22.9106388092041,
2352
+ "rewards/real": -4.617762565612793,
2353
+ "step": 1150
2354
+ },
2355
+ {
2356
+ "epoch": 1.89,
2357
+ "eval_logits/generated": -1.6736239194869995,
2358
+ "eval_logits/real": -2.1248714923858643,
2359
+ "eval_logps/generated": -689.571533203125,
2360
+ "eval_logps/real": -469.41937255859375,
2361
+ "eval_loss": 0.03756081312894821,
2362
+ "eval_rewards/accuracies": 0.9759259223937988,
2363
+ "eval_rewards/generated": -23.52364158630371,
2364
+ "eval_rewards/margins": 18.315916061401367,
2365
+ "eval_rewards/real": -5.20772647857666,
2366
+ "eval_runtime": 546.839,
2367
+ "eval_samples_per_second": 7.896,
2368
+ "eval_steps_per_second": 0.247,
2369
+ "step": 1150
2370
+ },
2371
+ {
2372
+ "epoch": 1.91,
2373
+ "learning_rate": 2.4725274725274723e-08,
2374
+ "logits/generated": -1.757741928100586,
2375
+ "logits/real": -2.1521947383880615,
2376
+ "logps/generated": -727.6856689453125,
2377
+ "logps/real": -433.1048889160156,
2378
+ "loss": 0.0049,
2379
+ "rewards/accuracies": 0.9937499761581421,
2380
+ "rewards/generated": -25.25569725036621,
2381
+ "rewards/margins": 21.249250411987305,
2382
+ "rewards/real": -4.0064473152160645,
2383
+ "step": 1160
2384
+ },
2385
+ {
2386
+ "epoch": 1.93,
2387
+ "learning_rate": 2.0146520146520147e-08,
2388
+ "logits/generated": -1.6687755584716797,
2389
+ "logits/real": -2.1527109146118164,
2390
+ "logps/generated": -697.9734497070312,
2391
+ "logps/real": -447.568359375,
2392
+ "loss": 0.01,
2393
+ "rewards/accuracies": 1.0,
2394
+ "rewards/generated": -24.455238342285156,
2395
+ "rewards/margins": 20.623992919921875,
2396
+ "rewards/real": -3.831244945526123,
2397
+ "step": 1170
2398
+ },
2399
+ {
2400
+ "epoch": 1.93,
2401
+ "eval_logits/generated": -1.6968693733215332,
2402
+ "eval_logits/real": -2.138258218765259,
2403
+ "eval_logps/generated": -687.8193359375,
2404
+ "eval_logps/real": -468.58880615234375,
2405
+ "eval_loss": 0.03790770843625069,
2406
+ "eval_rewards/accuracies": 0.9750000238418579,
2407
+ "eval_rewards/generated": -23.348421096801758,
2408
+ "eval_rewards/margins": 18.223752975463867,
2409
+ "eval_rewards/real": -5.124669075012207,
2410
+ "eval_runtime": 546.4967,
2411
+ "eval_samples_per_second": 7.901,
2412
+ "eval_steps_per_second": 0.247,
2413
+ "step": 1175
2414
+ },
2415
+ {
2416
+ "epoch": 1.94,
2417
+ "learning_rate": 1.5567765567765568e-08,
2418
+ "logits/generated": -1.6982448101043701,
2419
+ "logits/real": -2.162806987762451,
2420
+ "logps/generated": -685.9969482421875,
2421
+ "logps/real": -421.25787353515625,
2422
+ "loss": 0.0054,
2423
+ "rewards/accuracies": 0.9937499761581421,
2424
+ "rewards/generated": -25.75900650024414,
2425
+ "rewards/margins": 22.124160766601562,
2426
+ "rewards/real": -3.63484525680542,
2427
+ "step": 1180
2428
+ },
2429
+ {
2430
+ "epoch": 1.96,
2431
+ "learning_rate": 1.098901098901099e-08,
2432
+ "logits/generated": -1.7311254739761353,
2433
+ "logits/real": -2.1759705543518066,
2434
+ "logps/generated": -742.8027954101562,
2435
+ "logps/real": -477.0604553222656,
2436
+ "loss": 0.0025,
2437
+ "rewards/accuracies": 1.0,
2438
+ "rewards/generated": -25.570262908935547,
2439
+ "rewards/margins": 21.3287410736084,
2440
+ "rewards/real": -4.2415266036987305,
2441
+ "step": 1190
2442
+ },
2443
+ {
2444
+ "epoch": 1.98,
2445
+ "learning_rate": 6.41025641025641e-09,
2446
+ "logits/generated": -1.7832437753677368,
2447
+ "logits/real": -2.145749568939209,
2448
+ "logps/generated": -705.14697265625,
2449
+ "logps/real": -451.7295837402344,
2450
+ "loss": 0.0055,
2451
+ "rewards/accuracies": 1.0,
2452
+ "rewards/generated": -24.158727645874023,
2453
+ "rewards/margins": 20.19052505493164,
2454
+ "rewards/real": -3.968203067779541,
2455
+ "step": 1200
2456
+ },
2457
+ {
2458
+ "epoch": 1.98,
2459
+ "eval_logits/generated": -1.6814604997634888,
2460
+ "eval_logits/real": -2.1279709339141846,
2461
+ "eval_logps/generated": -690.4514770507812,
2462
+ "eval_logps/real": -469.20892333984375,
2463
+ "eval_loss": 0.03795896843075752,
2464
+ "eval_rewards/accuracies": 0.9777777791023254,
2465
+ "eval_rewards/generated": -23.611637115478516,
2466
+ "eval_rewards/margins": 18.424955368041992,
2467
+ "eval_rewards/real": -5.186681747436523,
2468
+ "eval_runtime": 540.8892,
2469
+ "eval_samples_per_second": 7.983,
2470
+ "eval_steps_per_second": 0.25,
2471
+ "step": 1200
2472
+ },
2473
+ {
2474
+ "epoch": 1.99,
2475
+ "learning_rate": 1.8315018315018314e-09,
2476
+ "logits/generated": -1.7156912088394165,
2477
+ "logits/real": -2.155310869216919,
2478
+ "logps/generated": -734.7672119140625,
2479
+ "logps/real": -468.51580810546875,
2480
+ "loss": 0.0047,
2481
+ "rewards/accuracies": 0.9937499761581421,
2482
+ "rewards/generated": -27.58634376525879,
2483
+ "rewards/margins": 23.325031280517578,
2484
+ "rewards/real": -4.261313438415527,
2485
+ "step": 1210
2486
+ },
2487
+ {
2488
+ "epoch": 2.0,
2489
+ "step": 1214,
2490
+ "total_flos": 0.0,
2491
+ "train_loss": 0.05120065249445122,
2492
+ "train_runtime": 45973.3661,
2493
+ "train_samples_per_second": 1.69,
2494
+ "train_steps_per_second": 0.026
2495
+ }
2496
+ ],
2497
+ "logging_steps": 10,
2498
+ "max_steps": 1214,
2499
+ "num_input_tokens_seen": 0,
2500
+ "num_train_epochs": 2,
2501
+ "save_steps": 500,
2502
+ "total_flos": 0.0,
2503
+ "train_batch_size": 8,
2504
+ "trial_name": null,
2505
+ "trial_params": null
2506
+ }