Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- config.json +26 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- train_results.json +9 -0
- trainer_state.json +1962 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: TTTXXX01/All_like-zephyr-7b-sft-full
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: Bernoulli_Like_Negative1-zephyr-7b-sft-full
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Bernoulli_Like_Negative1-zephyr-7b-sft-full
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [TTTXXX01/All_like-zephyr-7b-sft-full](https://huggingface.co/TTTXXX01/All_like-zephyr-7b-sft-full) on an unknown dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 3e-07
|
38 |
+
- train_batch_size: 6
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 4
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 48
|
45 |
+
- total_eval_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.41.2
|
58 |
+
- Pytorch 2.2.2+cu118
|
59 |
+
- Datasets 2.19.2
|
60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 1.6157182269792543,
|
5 |
+
"train_runtime": 13119.408,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.66,
|
8 |
+
"train_steps_per_second": 0.097
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TTTXXX01/All_like-zephyr-7b-sft-full",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
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": "4.41.2"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:430a39f32e2a7a006dcddaf08b02ccd13603fbcaf64cd69c809c36efc84e7fe9
|
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:b1ca31b60aeda6e8c2f715b7852c2039ae214ae085a6de9f934ff667b3a4f0c8
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e07b4e875115187b38c56281ba56c4a30377493496a739910e9008e16c0ee14
|
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 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 1.6157182269792543,
|
5 |
+
"train_runtime": 13119.408,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.66,
|
8 |
+
"train_steps_per_second": 0.097
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1962 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1274,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0007849293563579278,
|
13 |
+
"grad_norm": 11.458238972118851,
|
14 |
+
"learning_rate": 2.34375e-09,
|
15 |
+
"logits/chosen": 5914.86328125,
|
16 |
+
"logits/rejected": 2785.05078125,
|
17 |
+
"logps/chosen": -212.39956665039062,
|
18 |
+
"logps/rejected": -98.58319854736328,
|
19 |
+
"loss": 1.6265,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.007849293563579277,
|
28 |
+
"grad_norm": 10.944765962770576,
|
29 |
+
"learning_rate": 2.34375e-08,
|
30 |
+
"logits/chosen": 4973.87255859375,
|
31 |
+
"logits/rejected": 4328.1787109375,
|
32 |
+
"logps/chosen": -204.2371826171875,
|
33 |
+
"logps/rejected": -179.72877502441406,
|
34 |
+
"loss": 1.6266,
|
35 |
+
"rewards/accuracies": 0.48148149251937866,
|
36 |
+
"rewards/chosen": -0.029761962592601776,
|
37 |
+
"rewards/margins": 0.007892987690865993,
|
38 |
+
"rewards/rejected": -0.03765495494008064,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 11.499267080001312,
|
44 |
+
"learning_rate": 4.6875e-08,
|
45 |
+
"logits/chosen": 6084.16796875,
|
46 |
+
"logits/rejected": 4834.16455078125,
|
47 |
+
"logps/chosen": -217.2034149169922,
|
48 |
+
"logps/rejected": -196.7104034423828,
|
49 |
+
"loss": 1.6266,
|
50 |
+
"rewards/accuracies": 0.46666669845581055,
|
51 |
+
"rewards/chosen": -0.013780605979263783,
|
52 |
+
"rewards/margins": -0.03623500093817711,
|
53 |
+
"rewards/rejected": 0.022454392164945602,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 9.932951594192556,
|
59 |
+
"learning_rate": 7.03125e-08,
|
60 |
+
"logits/chosen": 6083.6298828125,
|
61 |
+
"logits/rejected": 5104.6298828125,
|
62 |
+
"logps/chosen": -250.5565185546875,
|
63 |
+
"logps/rejected": -209.35964965820312,
|
64 |
+
"loss": 1.6264,
|
65 |
+
"rewards/accuracies": 0.5249999761581421,
|
66 |
+
"rewards/chosen": 0.02980937995016575,
|
67 |
+
"rewards/margins": 0.05544011667370796,
|
68 |
+
"rewards/rejected": -0.025630736723542213,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 10.560583055604155,
|
74 |
+
"learning_rate": 9.375e-08,
|
75 |
+
"logits/chosen": 5310.8251953125,
|
76 |
+
"logits/rejected": 4346.38134765625,
|
77 |
+
"logps/chosen": -212.0478973388672,
|
78 |
+
"logps/rejected": -181.7023162841797,
|
79 |
+
"loss": 1.6262,
|
80 |
+
"rewards/accuracies": 0.5166667103767395,
|
81 |
+
"rewards/chosen": 0.04025173932313919,
|
82 |
+
"rewards/margins": 0.06556080281734467,
|
83 |
+
"rewards/rejected": -0.025309067219495773,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 10.427628853427613,
|
89 |
+
"learning_rate": 1.1718749999999999e-07,
|
90 |
+
"logits/chosen": 6422.7939453125,
|
91 |
+
"logits/rejected": 5040.93017578125,
|
92 |
+
"logps/chosen": -265.3838195800781,
|
93 |
+
"logps/rejected": -206.63735961914062,
|
94 |
+
"loss": 1.6255,
|
95 |
+
"rewards/accuracies": 0.5833333730697632,
|
96 |
+
"rewards/chosen": 0.23301315307617188,
|
97 |
+
"rewards/margins": 0.15109717845916748,
|
98 |
+
"rewards/rejected": 0.0819159746170044,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 9.622689233248208,
|
104 |
+
"learning_rate": 1.40625e-07,
|
105 |
+
"logits/chosen": 5486.65087890625,
|
106 |
+
"logits/rejected": 4560.60400390625,
|
107 |
+
"logps/chosen": -213.68582153320312,
|
108 |
+
"logps/rejected": -208.76248168945312,
|
109 |
+
"loss": 1.6246,
|
110 |
+
"rewards/accuracies": 0.6000000238418579,
|
111 |
+
"rewards/chosen": 0.2914460599422455,
|
112 |
+
"rewards/margins": 0.19062557816505432,
|
113 |
+
"rewards/rejected": 0.10082048177719116,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 9.587956347814307,
|
119 |
+
"learning_rate": 1.640625e-07,
|
120 |
+
"logits/chosen": 5199.4384765625,
|
121 |
+
"logits/rejected": 4924.6708984375,
|
122 |
+
"logps/chosen": -177.8567657470703,
|
123 |
+
"logps/rejected": -176.4372100830078,
|
124 |
+
"loss": 1.6231,
|
125 |
+
"rewards/accuracies": 0.6250000596046448,
|
126 |
+
"rewards/chosen": 0.6440274715423584,
|
127 |
+
"rewards/margins": 0.3180614411830902,
|
128 |
+
"rewards/rejected": 0.3259660303592682,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 8.592067444398902,
|
134 |
+
"learning_rate": 1.875e-07,
|
135 |
+
"logits/chosen": 5778.53955078125,
|
136 |
+
"logits/rejected": 5285.609375,
|
137 |
+
"logps/chosen": -195.7733917236328,
|
138 |
+
"logps/rejected": -181.14984130859375,
|
139 |
+
"loss": 1.6212,
|
140 |
+
"rewards/accuracies": 0.5666666626930237,
|
141 |
+
"rewards/chosen": 0.8041629791259766,
|
142 |
+
"rewards/margins": 0.39861544966697693,
|
143 |
+
"rewards/rejected": 0.40554744005203247,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 10.124908249937006,
|
149 |
+
"learning_rate": 2.109375e-07,
|
150 |
+
"logits/chosen": 6056.23486328125,
|
151 |
+
"logits/rejected": 5209.0205078125,
|
152 |
+
"logps/chosen": -217.357421875,
|
153 |
+
"logps/rejected": -184.17950439453125,
|
154 |
+
"loss": 1.6184,
|
155 |
+
"rewards/accuracies": 0.7000000476837158,
|
156 |
+
"rewards/chosen": 1.5040231943130493,
|
157 |
+
"rewards/margins": 1.2358932495117188,
|
158 |
+
"rewards/rejected": 0.2681299149990082,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 9.637444838737146,
|
164 |
+
"learning_rate": 2.3437499999999998e-07,
|
165 |
+
"logits/chosen": 5975.40087890625,
|
166 |
+
"logits/rejected": 5763.3486328125,
|
167 |
+
"logps/chosen": -208.479248046875,
|
168 |
+
"logps/rejected": -198.80589294433594,
|
169 |
+
"loss": 1.6183,
|
170 |
+
"rewards/accuracies": 0.5916666388511658,
|
171 |
+
"rewards/chosen": 1.752227544784546,
|
172 |
+
"rewards/margins": 1.1407288312911987,
|
173 |
+
"rewards/rejected": 0.6114988327026367,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 9.016250169124682,
|
179 |
+
"learning_rate": 2.5781249999999997e-07,
|
180 |
+
"logits/chosen": 6438.27734375,
|
181 |
+
"logits/rejected": 5277.41748046875,
|
182 |
+
"logps/chosen": -180.60360717773438,
|
183 |
+
"logps/rejected": -178.02499389648438,
|
184 |
+
"loss": 1.6146,
|
185 |
+
"rewards/accuracies": 0.6666666865348816,
|
186 |
+
"rewards/chosen": 2.4966413974761963,
|
187 |
+
"rewards/margins": 1.597015619277954,
|
188 |
+
"rewards/rejected": 0.8996255993843079,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 10.2875643972245,
|
194 |
+
"learning_rate": 2.8125e-07,
|
195 |
+
"logits/chosen": 6324.859375,
|
196 |
+
"logits/rejected": 5255.02197265625,
|
197 |
+
"logps/chosen": -200.77735900878906,
|
198 |
+
"logps/rejected": -197.18515014648438,
|
199 |
+
"loss": 1.6142,
|
200 |
+
"rewards/accuracies": 0.5916667580604553,
|
201 |
+
"rewards/chosen": 2.0967907905578613,
|
202 |
+
"rewards/margins": 1.1320407390594482,
|
203 |
+
"rewards/rejected": 0.9647501111030579,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 8.720197352663515,
|
209 |
+
"learning_rate": 2.999977454977299e-07,
|
210 |
+
"logits/chosen": 6224.30419921875,
|
211 |
+
"logits/rejected": 5787.24609375,
|
212 |
+
"logps/chosen": -206.4401397705078,
|
213 |
+
"logps/rejected": -196.00332641601562,
|
214 |
+
"loss": 1.6121,
|
215 |
+
"rewards/accuracies": 0.6500000357627869,
|
216 |
+
"rewards/chosen": 3.3742451667785645,
|
217 |
+
"rewards/margins": 1.7132713794708252,
|
218 |
+
"rewards/rejected": 1.6609739065170288,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 9.129566422771084,
|
224 |
+
"learning_rate": 2.999188450339425e-07,
|
225 |
+
"logits/chosen": 6075.42626953125,
|
226 |
+
"logits/rejected": 5363.8330078125,
|
227 |
+
"logps/chosen": -182.21517944335938,
|
228 |
+
"logps/rejected": -175.36424255371094,
|
229 |
+
"loss": 1.6087,
|
230 |
+
"rewards/accuracies": 0.6250000596046448,
|
231 |
+
"rewards/chosen": 3.4619534015655518,
|
232 |
+
"rewards/margins": 1.249176263809204,
|
233 |
+
"rewards/rejected": 2.2127773761749268,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 11.857486318606039,
|
239 |
+
"learning_rate": 2.997272872179022e-07,
|
240 |
+
"logits/chosen": 6205.095703125,
|
241 |
+
"logits/rejected": 5208.36376953125,
|
242 |
+
"logps/chosen": -198.15518188476562,
|
243 |
+
"logps/rejected": -171.08432006835938,
|
244 |
+
"loss": 1.6098,
|
245 |
+
"rewards/accuracies": 0.6499999761581421,
|
246 |
+
"rewards/chosen": 3.4637317657470703,
|
247 |
+
"rewards/margins": 2.2425143718719482,
|
248 |
+
"rewards/rejected": 1.2212175130844116,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 8.968030441205661,
|
254 |
+
"learning_rate": 2.994232159967983e-07,
|
255 |
+
"logits/chosen": 6122.28564453125,
|
256 |
+
"logits/rejected": 5471.36572265625,
|
257 |
+
"logps/chosen": -194.1709747314453,
|
258 |
+
"logps/rejected": -195.9803009033203,
|
259 |
+
"loss": 1.609,
|
260 |
+
"rewards/accuracies": 0.574999988079071,
|
261 |
+
"rewards/chosen": 3.3317999839782715,
|
262 |
+
"rewards/margins": 2.249804973602295,
|
263 |
+
"rewards/rejected": 1.0819952487945557,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 9.653645250907548,
|
269 |
+
"learning_rate": 2.990068598666458e-07,
|
270 |
+
"logits/chosen": 6370.8193359375,
|
271 |
+
"logits/rejected": 5675.42236328125,
|
272 |
+
"logps/chosen": -206.18612670898438,
|
273 |
+
"logps/rejected": -194.17982482910156,
|
274 |
+
"loss": 1.608,
|
275 |
+
"rewards/accuracies": 0.625,
|
276 |
+
"rewards/chosen": 3.4253058433532715,
|
277 |
+
"rewards/margins": 1.2780392169952393,
|
278 |
+
"rewards/rejected": 2.1472671031951904,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 9.454673895277375,
|
284 |
+
"learning_rate": 2.984785317005808e-07,
|
285 |
+
"logits/chosen": 5601.3544921875,
|
286 |
+
"logits/rejected": 4895.4755859375,
|
287 |
+
"logps/chosen": -185.2515411376953,
|
288 |
+
"logps/rejected": -175.55259704589844,
|
289 |
+
"loss": 1.6091,
|
290 |
+
"rewards/accuracies": 0.5750000476837158,
|
291 |
+
"rewards/chosen": 3.3107008934020996,
|
292 |
+
"rewards/margins": 0.6890397071838379,
|
293 |
+
"rewards/rejected": 2.6216609477996826,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 9.654359692410358,
|
299 |
+
"learning_rate": 2.978386285137506e-07,
|
300 |
+
"logits/chosen": 5670.37841796875,
|
301 |
+
"logits/rejected": 4872.609375,
|
302 |
+
"logps/chosen": -199.90350341796875,
|
303 |
+
"logps/rejected": -190.27354431152344,
|
304 |
+
"loss": 1.6056,
|
305 |
+
"rewards/accuracies": 0.675000011920929,
|
306 |
+
"rewards/chosen": 3.8663978576660156,
|
307 |
+
"rewards/margins": 2.9279844760894775,
|
308 |
+
"rewards/rejected": 0.9384133219718933,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 10.197121119934124,
|
314 |
+
"learning_rate": 2.9708763116497365e-07,
|
315 |
+
"logits/chosen": 5597.7919921875,
|
316 |
+
"logits/rejected": 5161.28271484375,
|
317 |
+
"logps/chosen": -179.18333435058594,
|
318 |
+
"logps/rejected": -195.28829956054688,
|
319 |
+
"loss": 1.6087,
|
320 |
+
"rewards/accuracies": 0.6166666746139526,
|
321 |
+
"rewards/chosen": 3.3536689281463623,
|
322 |
+
"rewards/margins": 1.9326164722442627,
|
323 |
+
"rewards/rejected": 1.42105233669281,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 9.507119152719666,
|
329 |
+
"learning_rate": 2.962261039953964e-07,
|
330 |
+
"logits/chosen": 5043.921875,
|
331 |
+
"logits/rejected": 4512.1884765625,
|
332 |
+
"logps/chosen": -150.83897399902344,
|
333 |
+
"logps/rejected": -155.26417541503906,
|
334 |
+
"loss": 1.6066,
|
335 |
+
"rewards/accuracies": 0.5333333611488342,
|
336 |
+
"rewards/chosen": 3.090742826461792,
|
337 |
+
"rewards/margins": 1.139352798461914,
|
338 |
+
"rewards/rejected": 1.951390027999878,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 9.378684614749979,
|
344 |
+
"learning_rate": 2.952546944044155e-07,
|
345 |
+
"logits/chosen": 6175.8935546875,
|
346 |
+
"logits/rejected": 5279.80224609375,
|
347 |
+
"logps/chosen": -192.4020233154297,
|
348 |
+
"logps/rejected": -162.25759887695312,
|
349 |
+
"loss": 1.6063,
|
350 |
+
"rewards/accuracies": 0.6833333373069763,
|
351 |
+
"rewards/chosen": 3.872145175933838,
|
352 |
+
"rewards/margins": 2.17866587638855,
|
353 |
+
"rewards/rejected": 1.6934791803359985,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 9.79164707530873,
|
359 |
+
"learning_rate": 2.941741323631859e-07,
|
360 |
+
"logits/chosen": 5731.53564453125,
|
361 |
+
"logits/rejected": 5152.2685546875,
|
362 |
+
"logps/chosen": -183.71131896972656,
|
363 |
+
"logps/rejected": -178.02699279785156,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"rewards/accuracies": 0.6416666507720947,
|
366 |
+
"rewards/chosen": 3.631937026977539,
|
367 |
+
"rewards/margins": 1.891611099243164,
|
368 |
+
"rewards/rejected": 1.740325927734375,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 9.812812391985778,
|
374 |
+
"learning_rate": 2.929852298660803e-07,
|
375 |
+
"logits/chosen": 5198.8896484375,
|
376 |
+
"logits/rejected": 4139.96923828125,
|
377 |
+
"logps/chosen": -163.8915252685547,
|
378 |
+
"logps/rejected": -153.38279724121094,
|
379 |
+
"loss": 1.6049,
|
380 |
+
"rewards/accuracies": 0.625,
|
381 |
+
"rewards/chosen": 3.735271453857422,
|
382 |
+
"rewards/margins": 2.3994784355163574,
|
383 |
+
"rewards/rejected": 1.335792899131775,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 9.413138412548989,
|
389 |
+
"learning_rate": 2.9168888032051097e-07,
|
390 |
+
"logits/chosen": 6045.21923828125,
|
391 |
+
"logits/rejected": 5354.9951171875,
|
392 |
+
"logps/chosen": -163.71151733398438,
|
393 |
+
"logps/rejected": -183.2251434326172,
|
394 |
+
"loss": 1.6076,
|
395 |
+
"rewards/accuracies": 0.6500000357627869,
|
396 |
+
"rewards/chosen": 3.4429244995117188,
|
397 |
+
"rewards/margins": 2.1717002391815186,
|
398 |
+
"rewards/rejected": 1.2712242603302002,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 11.02606597842409,
|
404 |
+
"learning_rate": 2.9028605787557423e-07,
|
405 |
+
"logits/chosen": 6197.080078125,
|
406 |
+
"logits/rejected": 5034.4609375,
|
407 |
+
"logps/chosen": -195.53811645507812,
|
408 |
+
"logps/rejected": -164.32293701171875,
|
409 |
+
"loss": 1.6062,
|
410 |
+
"rewards/accuracies": 0.675000011920929,
|
411 |
+
"rewards/chosen": 4.181486129760742,
|
412 |
+
"rewards/margins": 2.2564964294433594,
|
413 |
+
"rewards/rejected": 1.9249897003173828,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 8.786474619717062,
|
419 |
+
"learning_rate": 2.8877781669002034e-07,
|
420 |
+
"logits/chosen": 6150.35302734375,
|
421 |
+
"logits/rejected": 5960.28759765625,
|
422 |
+
"logps/chosen": -192.77615356445312,
|
423 |
+
"logps/rejected": -185.39297485351562,
|
424 |
+
"loss": 1.6043,
|
425 |
+
"rewards/accuracies": 0.5583333373069763,
|
426 |
+
"rewards/chosen": 3.9804999828338623,
|
427 |
+
"rewards/margins": 0.6723251938819885,
|
428 |
+
"rewards/rejected": 3.3081748485565186,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 11.186569406268537,
|
434 |
+
"learning_rate": 2.871652901401002e-07,
|
435 |
+
"logits/chosen": 5263.07763671875,
|
436 |
+
"logits/rejected": 4574.97119140625,
|
437 |
+
"logps/chosen": -159.4766082763672,
|
438 |
+
"logps/rejected": -168.32589721679688,
|
439 |
+
"loss": 1.6041,
|
440 |
+
"rewards/accuracies": 0.699999988079071,
|
441 |
+
"rewards/chosen": 3.5813148021698,
|
442 |
+
"rewards/margins": 2.5793395042419434,
|
443 |
+
"rewards/rejected": 1.0019747018814087,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 10.641068152714297,
|
449 |
+
"learning_rate": 2.854496899678834e-07,
|
450 |
+
"logits/chosen": 7268.1611328125,
|
451 |
+
"logits/rejected": 5389.25732421875,
|
452 |
+
"logps/chosen": -233.04153442382812,
|
453 |
+
"logps/rejected": -181.015625,
|
454 |
+
"loss": 1.606,
|
455 |
+
"rewards/accuracies": 0.6583333611488342,
|
456 |
+
"rewards/chosen": 4.031437397003174,
|
457 |
+
"rewards/margins": 2.5249290466308594,
|
458 |
+
"rewards/rejected": 1.506508469581604,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 9.89515741424169,
|
464 |
+
"learning_rate": 2.8363230537068793e-07,
|
465 |
+
"logits/chosen": 5273.17578125,
|
466 |
+
"logits/rejected": 5249.6083984375,
|
467 |
+
"logps/chosen": -164.12420654296875,
|
468 |
+
"logps/rejected": -168.3370819091797,
|
469 |
+
"loss": 1.6072,
|
470 |
+
"rewards/accuracies": 0.6166666746139526,
|
471 |
+
"rewards/chosen": 3.3666069507598877,
|
472 |
+
"rewards/margins": 1.4807441234588623,
|
473 |
+
"rewards/rejected": 1.8858625888824463,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 9.156189036074041,
|
479 |
+
"learning_rate": 2.817145020323055e-07,
|
480 |
+
"logits/chosen": 5941.7890625,
|
481 |
+
"logits/rejected": 5263.54736328125,
|
482 |
+
"logps/chosen": -173.28579711914062,
|
483 |
+
"logps/rejected": -173.98643493652344,
|
484 |
+
"loss": 1.6053,
|
485 |
+
"rewards/accuracies": 0.6750000715255737,
|
486 |
+
"rewards/chosen": 4.284714698791504,
|
487 |
+
"rewards/margins": 2.821631908416748,
|
488 |
+
"rewards/rejected": 1.4630826711654663,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 10.434068381012322,
|
494 |
+
"learning_rate": 2.7969772109675106e-07,
|
495 |
+
"logits/chosen": 5937.4228515625,
|
496 |
+
"logits/rejected": 5140.39111328125,
|
497 |
+
"logps/chosen": -197.049560546875,
|
498 |
+
"logps/rejected": -200.171875,
|
499 |
+
"loss": 1.6065,
|
500 |
+
"rewards/accuracies": 0.6499999761581421,
|
501 |
+
"rewards/chosen": 4.066697597503662,
|
502 |
+
"rewards/margins": 2.1806929111480713,
|
503 |
+
"rewards/rejected": 1.8860050439834595,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 7.96980516077302,
|
509 |
+
"learning_rate": 2.775834780853069e-07,
|
510 |
+
"logits/chosen": 5770.4892578125,
|
511 |
+
"logits/rejected": 5251.03076171875,
|
512 |
+
"logps/chosen": -190.3749542236328,
|
513 |
+
"logps/rejected": -175.70028686523438,
|
514 |
+
"loss": 1.6057,
|
515 |
+
"rewards/accuracies": 0.6499999761581421,
|
516 |
+
"rewards/chosen": 4.041922092437744,
|
517 |
+
"rewards/margins": 2.4098730087280273,
|
518 |
+
"rewards/rejected": 1.6320489645004272,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 9.327241211208603,
|
524 |
+
"learning_rate": 2.75373361757676e-07,
|
525 |
+
"logits/chosen": 6020.267578125,
|
526 |
+
"logits/rejected": 6114.4892578125,
|
527 |
+
"logps/chosen": -189.46829223632812,
|
528 |
+
"logps/rejected": -218.3720703125,
|
529 |
+
"loss": 1.6054,
|
530 |
+
"rewards/accuracies": 0.6416666507720947,
|
531 |
+
"rewards/chosen": 4.399914741516113,
|
532 |
+
"rewards/margins": 2.4120266437530518,
|
533 |
+
"rewards/rejected": 1.9878880977630615,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 9.836682323090738,
|
539 |
+
"learning_rate": 2.730690329180992e-07,
|
540 |
+
"logits/chosen": 6336.00341796875,
|
541 |
+
"logits/rejected": 5750.68310546875,
|
542 |
+
"logps/chosen": -190.63604736328125,
|
543 |
+
"logps/rejected": -205.4300537109375,
|
544 |
+
"loss": 1.6049,
|
545 |
+
"rewards/accuracies": 0.6833332777023315,
|
546 |
+
"rewards/chosen": 4.227248191833496,
|
547 |
+
"rewards/margins": 2.878089189529419,
|
548 |
+
"rewards/rejected": 1.3491594791412354,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 10.19922545005082,
|
554 |
+
"learning_rate": 2.7067222316733527e-07,
|
555 |
+
"logits/chosen": 5833.3701171875,
|
556 |
+
"logits/rejected": 5751.5283203125,
|
557 |
+
"logps/chosen": -175.12269592285156,
|
558 |
+
"logps/rejected": -198.1387481689453,
|
559 |
+
"loss": 1.6072,
|
560 |
+
"rewards/accuracies": 0.6000000238418579,
|
561 |
+
"rewards/chosen": 2.7430808544158936,
|
562 |
+
"rewards/margins": 1.5406630039215088,
|
563 |
+
"rewards/rejected": 1.2024176120758057,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 10.34523599778714,
|
569 |
+
"learning_rate": 2.6818473360143916e-07,
|
570 |
+
"logits/chosen": 5338.24755859375,
|
571 |
+
"logits/rejected": 5045.15087890625,
|
572 |
+
"logps/chosen": -180.8574676513672,
|
573 |
+
"logps/rejected": -166.79676818847656,
|
574 |
+
"loss": 1.6067,
|
575 |
+
"rewards/accuracies": 0.6500000357627869,
|
576 |
+
"rewards/chosen": 3.5679619312286377,
|
577 |
+
"rewards/margins": 2.2969326972961426,
|
578 |
+
"rewards/rejected": 1.271028995513916,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 9.372139727854044,
|
584 |
+
"learning_rate": 2.6560843345831893e-07,
|
585 |
+
"logits/chosen": 6382.61181640625,
|
586 |
+
"logits/rejected": 5298.80224609375,
|
587 |
+
"logps/chosen": -223.8726348876953,
|
588 |
+
"logps/rejected": -181.1964874267578,
|
589 |
+
"loss": 1.6059,
|
590 |
+
"rewards/accuracies": 0.6916666626930237,
|
591 |
+
"rewards/chosen": 4.494563579559326,
|
592 |
+
"rewards/margins": 2.7286934852600098,
|
593 |
+
"rewards/rejected": 1.7658706903457642,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 10.887020734305196,
|
599 |
+
"learning_rate": 2.62945258713086e-07,
|
600 |
+
"logits/chosen": 6511.5537109375,
|
601 |
+
"logits/rejected": 4989.4306640625,
|
602 |
+
"logps/chosen": -211.2510986328125,
|
603 |
+
"logps/rejected": -179.0139923095703,
|
604 |
+
"loss": 1.6059,
|
605 |
+
"rewards/accuracies": 0.6750000715255737,
|
606 |
+
"rewards/chosen": 4.222726345062256,
|
607 |
+
"rewards/margins": 3.4083054065704346,
|
608 |
+
"rewards/rejected": 0.8144209980964661,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 10.72240359029845,
|
614 |
+
"learning_rate": 2.601972106232561e-07,
|
615 |
+
"logits/chosen": 5603.4267578125,
|
616 |
+
"logits/rejected": 5503.55078125,
|
617 |
+
"logps/chosen": -187.75234985351562,
|
618 |
+
"logps/rejected": -187.8725128173828,
|
619 |
+
"loss": 1.6064,
|
620 |
+
"rewards/accuracies": 0.6666666269302368,
|
621 |
+
"rewards/chosen": 3.06905460357666,
|
622 |
+
"rewards/margins": 2.2018256187438965,
|
623 |
+
"rewards/rejected": 0.8672292828559875,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 11.25468877955665,
|
629 |
+
"learning_rate": 2.5736635422489343e-07,
|
630 |
+
"logits/chosen": 6066.5107421875,
|
631 |
+
"logits/rejected": 5429.3359375,
|
632 |
+
"logps/chosen": -208.7128143310547,
|
633 |
+
"logps/rejected": -207.3098907470703,
|
634 |
+
"loss": 1.6046,
|
635 |
+
"rewards/accuracies": 0.625,
|
636 |
+
"rewards/chosen": 3.760521650314331,
|
637 |
+
"rewards/margins": 2.6000523567199707,
|
638 |
+
"rewards/rejected": 1.1604695320129395,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 11.575393675092053,
|
644 |
+
"learning_rate": 2.5445481678082706e-07,
|
645 |
+
"logits/chosen": 5705.2744140625,
|
646 |
+
"logits/rejected": 5208.12353515625,
|
647 |
+
"logps/chosen": -200.07925415039062,
|
648 |
+
"logps/rejected": -180.0633544921875,
|
649 |
+
"loss": 1.6052,
|
650 |
+
"rewards/accuracies": 0.6500000357627869,
|
651 |
+
"rewards/chosen": 3.9673619270324707,
|
652 |
+
"rewards/margins": 2.736542224884033,
|
653 |
+
"rewards/rejected": 1.2308193445205688,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 11.347255741193797,
|
659 |
+
"learning_rate": 2.514647861821081e-07,
|
660 |
+
"logits/chosen": 5512.1982421875,
|
661 |
+
"logits/rejected": 4594.4384765625,
|
662 |
+
"logps/chosen": -176.08999633789062,
|
663 |
+
"logps/rejected": -160.46536254882812,
|
664 |
+
"loss": 1.6052,
|
665 |
+
"rewards/accuracies": 0.6916667222976685,
|
666 |
+
"rewards/chosen": 3.6505095958709717,
|
667 |
+
"rewards/margins": 2.8529231548309326,
|
668 |
+
"rewards/rejected": 0.7975867986679077,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 11.251614329473432,
|
674 |
+
"learning_rate": 2.483985093039065e-07,
|
675 |
+
"logits/chosen": 5866.24609375,
|
676 |
+
"logits/rejected": 5800.03466796875,
|
677 |
+
"logps/chosen": -178.62997436523438,
|
678 |
+
"logps/rejected": -190.69210815429688,
|
679 |
+
"loss": 1.6071,
|
680 |
+
"rewards/accuracies": 0.6583333611488342,
|
681 |
+
"rewards/chosen": 3.7587838172912598,
|
682 |
+
"rewards/margins": 2.8152925968170166,
|
683 |
+
"rewards/rejected": 0.9434911608695984,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 10.238672574135192,
|
689 |
+
"learning_rate": 2.4525829031708404e-07,
|
690 |
+
"logits/chosen": 6755.23828125,
|
691 |
+
"logits/rejected": 4911.7578125,
|
692 |
+
"logps/chosen": -204.50540161132812,
|
693 |
+
"logps/rejected": -162.7772216796875,
|
694 |
+
"loss": 1.6075,
|
695 |
+
"rewards/accuracies": 0.7333333492279053,
|
696 |
+
"rewards/chosen": 4.24879264831543,
|
697 |
+
"rewards/margins": 4.009242057800293,
|
698 |
+
"rewards/rejected": 0.23955073952674866,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 10.124703408047377,
|
704 |
+
"learning_rate": 2.420464889567126e-07,
|
705 |
+
"logits/chosen": 6971.953125,
|
706 |
+
"logits/rejected": 5482.63330078125,
|
707 |
+
"logps/chosen": -246.63485717773438,
|
708 |
+
"logps/rejected": -189.0049591064453,
|
709 |
+
"loss": 1.6062,
|
710 |
+
"rewards/accuracies": 0.6583333015441895,
|
711 |
+
"rewards/chosen": 3.8507399559020996,
|
712 |
+
"rewards/margins": 2.7193245887756348,
|
713 |
+
"rewards/rejected": 1.1314153671264648,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 10.244451763866405,
|
719 |
+
"learning_rate": 2.3876551874883775e-07,
|
720 |
+
"logits/chosen": 5983.9541015625,
|
721 |
+
"logits/rejected": 5281.8173828125,
|
722 |
+
"logps/chosen": -208.52267456054688,
|
723 |
+
"logps/rejected": -201.57501220703125,
|
724 |
+
"loss": 1.6099,
|
725 |
+
"rewards/accuracies": 0.7083333730697632,
|
726 |
+
"rewards/chosen": 3.680980682373047,
|
727 |
+
"rewards/margins": 2.752244234085083,
|
728 |
+
"rewards/rejected": 0.9287362098693848,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 10.136642065676186,
|
734 |
+
"learning_rate": 2.354178451968214e-07,
|
735 |
+
"logits/chosen": 6450.548828125,
|
736 |
+
"logits/rejected": 5633.7119140625,
|
737 |
+
"logps/chosen": -203.6438751220703,
|
738 |
+
"logps/rejected": -173.91026306152344,
|
739 |
+
"loss": 1.6082,
|
740 |
+
"rewards/accuracies": 0.6833333969116211,
|
741 |
+
"rewards/chosen": 3.7612411975860596,
|
742 |
+
"rewards/margins": 3.274782657623291,
|
743 |
+
"rewards/rejected": 0.4864584505558014,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 11.463940168293135,
|
749 |
+
"learning_rate": 2.3200598392862542e-07,
|
750 |
+
"logits/chosen": 6044.64501953125,
|
751 |
+
"logits/rejected": 5817.2734375,
|
752 |
+
"logps/chosen": -172.8741912841797,
|
753 |
+
"logps/rejected": -201.54507446289062,
|
754 |
+
"loss": 1.6072,
|
755 |
+
"rewards/accuracies": 0.7583333253860474,
|
756 |
+
"rewards/chosen": 3.7329680919647217,
|
757 |
+
"rewards/margins": 3.2064049243927,
|
758 |
+
"rewards/rejected": 0.5265628695487976,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 10.258740856397358,
|
764 |
+
"learning_rate": 2.2853249880642897e-07,
|
765 |
+
"logits/chosen": 6601.33447265625,
|
766 |
+
"logits/rejected": 5118.966796875,
|
767 |
+
"logps/chosen": -219.5803985595703,
|
768 |
+
"logps/rejected": -203.1927490234375,
|
769 |
+
"loss": 1.6087,
|
770 |
+
"rewards/accuracies": 0.6916667222976685,
|
771 |
+
"rewards/chosen": 2.4150400161743164,
|
772 |
+
"rewards/margins": 3.0509958267211914,
|
773 |
+
"rewards/rejected": -0.635955810546875,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 9.618807221454839,
|
779 |
+
"learning_rate": 2.25e-07,
|
780 |
+
"logits/chosen": 5256.94482421875,
|
781 |
+
"logits/rejected": 4686.318359375,
|
782 |
+
"logps/chosen": -186.45138549804688,
|
783 |
+
"logps/rejected": -166.85733032226562,
|
784 |
+
"loss": 1.6107,
|
785 |
+
"rewards/accuracies": 0.7250000238418579,
|
786 |
+
"rewards/chosen": 2.9723703861236572,
|
787 |
+
"rewards/margins": 3.497563123703003,
|
788 |
+
"rewards/rejected": -0.5251928567886353,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 10.077787546594172,
|
794 |
+
"learning_rate": 2.2141114202526867e-07,
|
795 |
+
"logits/chosen": 5602.5029296875,
|
796 |
+
"logits/rejected": 5226.76904296875,
|
797 |
+
"logps/chosen": -195.4163818359375,
|
798 |
+
"logps/rejected": -194.8783721923828,
|
799 |
+
"loss": 1.6119,
|
800 |
+
"rewards/accuracies": 0.6500000357627869,
|
801 |
+
"rewards/chosen": 3.003880739212036,
|
802 |
+
"rewards/margins": 2.041459321975708,
|
803 |
+
"rewards/rejected": 0.9624212384223938,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 10.362808776797175,
|
809 |
+
"learning_rate": 2.1776862174957646e-07,
|
810 |
+
"logits/chosen": 6315.44482421875,
|
811 |
+
"logits/rejected": 5213.26953125,
|
812 |
+
"logps/chosen": -208.7710723876953,
|
813 |
+
"logps/rejected": -198.46128845214844,
|
814 |
+
"loss": 1.6075,
|
815 |
+
"rewards/accuracies": 0.7083333730697632,
|
816 |
+
"rewards/chosen": 4.163774490356445,
|
817 |
+
"rewards/margins": 3.857957363128662,
|
818 |
+
"rewards/rejected": 0.3058166205883026,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 11.129372316652974,
|
824 |
+
"learning_rate": 2.1407517636510023e-07,
|
825 |
+
"logits/chosen": 5997.4560546875,
|
826 |
+
"logits/rejected": 5399.8779296875,
|
827 |
+
"logps/chosen": -208.12722778320312,
|
828 |
+
"logps/rejected": -188.67626953125,
|
829 |
+
"loss": 1.6106,
|
830 |
+
"rewards/accuracies": 0.6333333253860474,
|
831 |
+
"rewards/chosen": 2.6769168376922607,
|
832 |
+
"rewards/margins": 3.085752487182617,
|
833 |
+
"rewards/rejected": -0.40883541107177734,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 10.874250167035393,
|
839 |
+
"learning_rate": 2.1033358133197376e-07,
|
840 |
+
"logits/chosen": 5797.27294921875,
|
841 |
+
"logits/rejected": 5422.5419921875,
|
842 |
+
"logps/chosen": -212.1249542236328,
|
843 |
+
"logps/rejected": -225.52099609375,
|
844 |
+
"loss": 1.6096,
|
845 |
+
"rewards/accuracies": 0.6916667222976685,
|
846 |
+
"rewards/chosen": 2.68788480758667,
|
847 |
+
"rewards/margins": 3.1572766304016113,
|
848 |
+
"rewards/rejected": -0.46939191222190857,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 11.368509816993306,
|
854 |
+
"learning_rate": 2.0654664829265295e-07,
|
855 |
+
"logits/chosen": 5849.35791015625,
|
856 |
+
"logits/rejected": 5507.40625,
|
857 |
+
"logps/chosen": -200.6465606689453,
|
858 |
+
"logps/rejected": -193.24252319335938,
|
859 |
+
"loss": 1.6123,
|
860 |
+
"rewards/accuracies": 0.6416667103767395,
|
861 |
+
"rewards/chosen": 2.6296989917755127,
|
862 |
+
"rewards/margins": 2.6346523761749268,
|
863 |
+
"rewards/rejected": -0.004953605122864246,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 9.634112543251097,
|
869 |
+
"learning_rate": 2.027172229590914e-07,
|
870 |
+
"logits/chosen": 6171.091796875,
|
871 |
+
"logits/rejected": 5716.99951171875,
|
872 |
+
"logps/chosen": -240.25399780273438,
|
873 |
+
"logps/rejected": -223.2677764892578,
|
874 |
+
"loss": 1.6112,
|
875 |
+
"rewards/accuracies": 0.6416667103767395,
|
876 |
+
"rewards/chosen": 2.6774706840515137,
|
877 |
+
"rewards/margins": 2.21945858001709,
|
878 |
+
"rewards/rejected": 0.45801201462745667,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 10.87514770443522,
|
884 |
+
"learning_rate": 1.9884818297431403e-07,
|
885 |
+
"logits/chosen": 6132.4013671875,
|
886 |
+
"logits/rejected": 5570.19921875,
|
887 |
+
"logps/chosen": -209.4405975341797,
|
888 |
+
"logps/rejected": -213.29257202148438,
|
889 |
+
"loss": 1.6114,
|
890 |
+
"rewards/accuracies": 0.7000001072883606,
|
891 |
+
"rewards/chosen": 2.9603564739227295,
|
892 |
+
"rewards/margins": 2.9691500663757324,
|
893 |
+
"rewards/rejected": -0.008793527260422707,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 11.895191217861239,
|
899 |
+
"learning_rate": 1.9494243574999645e-07,
|
900 |
+
"logits/chosen": 6698.8017578125,
|
901 |
+
"logits/rejected": 5693.74755859375,
|
902 |
+
"logps/chosen": -228.00796508789062,
|
903 |
+
"logps/rejected": -178.66822814941406,
|
904 |
+
"loss": 1.6102,
|
905 |
+
"rewards/accuracies": 0.6916667222976685,
|
906 |
+
"rewards/chosen": 3.6634438037872314,
|
907 |
+
"rewards/margins": 3.507164716720581,
|
908 |
+
"rewards/rejected": 0.15627913177013397,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 10.761146722421474,
|
914 |
+
"learning_rate": 1.9100291628167416e-07,
|
915 |
+
"logits/chosen": 6341.4296875,
|
916 |
+
"logits/rejected": 5422.83984375,
|
917 |
+
"logps/chosen": -175.03768920898438,
|
918 |
+
"logps/rejected": -189.64918518066406,
|
919 |
+
"loss": 1.6124,
|
920 |
+
"rewards/accuracies": 0.6750000715255737,
|
921 |
+
"rewards/chosen": 2.5099081993103027,
|
922 |
+
"rewards/margins": 2.4614367485046387,
|
923 |
+
"rewards/rejected": 0.04847153276205063,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 10.066536779214626,
|
929 |
+
"learning_rate": 1.870325849432238e-07,
|
930 |
+
"logits/chosen": 6092.59765625,
|
931 |
+
"logits/rejected": 5363.5263671875,
|
932 |
+
"logps/chosen": -203.3939971923828,
|
933 |
+
"logps/rejected": -186.27825927734375,
|
934 |
+
"loss": 1.6096,
|
935 |
+
"rewards/accuracies": 0.699999988079071,
|
936 |
+
"rewards/chosen": 2.739835023880005,
|
937 |
+
"rewards/margins": 3.611487627029419,
|
938 |
+
"rewards/rejected": -0.8716526031494141,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 9.620539433149245,
|
944 |
+
"learning_rate": 1.8303442526227364e-07,
|
945 |
+
"logits/chosen": 5198.9228515625,
|
946 |
+
"logits/rejected": 4301.599609375,
|
947 |
+
"logps/chosen": -181.21054077148438,
|
948 |
+
"logps/rejected": -162.38772583007812,
|
949 |
+
"loss": 1.6114,
|
950 |
+
"rewards/accuracies": 0.7583333253860474,
|
951 |
+
"rewards/chosen": 2.554405689239502,
|
952 |
+
"rewards/margins": 3.846482038497925,
|
953 |
+
"rewards/rejected": -1.2920769453048706,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 10.87064291559102,
|
959 |
+
"learning_rate": 1.7901144167821507e-07,
|
960 |
+
"logits/chosen": 6764.76171875,
|
961 |
+
"logits/rejected": 5845.1396484375,
|
962 |
+
"logps/chosen": -239.6127166748047,
|
963 |
+
"logps/rejected": -195.640869140625,
|
964 |
+
"loss": 1.6094,
|
965 |
+
"rewards/accuracies": 0.7250000238418579,
|
966 |
+
"rewards/chosen": 3.2196297645568848,
|
967 |
+
"rewards/margins": 4.5956902503967285,
|
968 |
+
"rewards/rejected": -1.3760606050491333,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 11.572214216615475,
|
974 |
+
"learning_rate": 1.749666572845e-07,
|
975 |
+
"logits/chosen": 6422.68505859375,
|
976 |
+
"logits/rejected": 5511.61083984375,
|
977 |
+
"logps/chosen": -208.0812225341797,
|
978 |
+
"logps/rejected": -215.52230834960938,
|
979 |
+
"loss": 1.6109,
|
980 |
+
"rewards/accuracies": 0.7083333134651184,
|
981 |
+
"rewards/chosen": 2.6956992149353027,
|
982 |
+
"rewards/margins": 3.72594952583313,
|
983 |
+
"rewards/rejected": -1.0302503108978271,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 10.924127233657837,
|
989 |
+
"learning_rate": 1.7090311155692034e-07,
|
990 |
+
"logits/chosen": 5531.26953125,
|
991 |
+
"logits/rejected": 4566.18115234375,
|
992 |
+
"logps/chosen": -194.7221221923828,
|
993 |
+
"logps/rejected": -170.06761169433594,
|
994 |
+
"loss": 1.6136,
|
995 |
+
"rewards/accuracies": 0.6916666626930237,
|
996 |
+
"rewards/chosen": 1.600431203842163,
|
997 |
+
"rewards/margins": 2.939448595046997,
|
998 |
+
"rewards/rejected": -1.339017391204834,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 11.128560662698712,
|
1004 |
+
"learning_rate": 1.6682385806957695e-07,
|
1005 |
+
"logits/chosen": 6207.12646484375,
|
1006 |
+
"logits/rejected": 5023.8916015625,
|
1007 |
+
"logps/chosen": -215.07473754882812,
|
1008 |
+
"logps/rejected": -189.7795867919922,
|
1009 |
+
"loss": 1.6147,
|
1010 |
+
"rewards/accuracies": 0.7916666865348816,
|
1011 |
+
"rewards/chosen": 2.3060238361358643,
|
1012 |
+
"rewards/margins": 4.0903449058532715,
|
1013 |
+
"rewards/rejected": -1.7843214273452759,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 11.101124136697601,
|
1019 |
+
"learning_rate": 1.627319622002544e-07,
|
1020 |
+
"logits/chosen": 6186.93798828125,
|
1021 |
+
"logits/rejected": 5106.5810546875,
|
1022 |
+
"logps/chosen": -204.43142700195312,
|
1023 |
+
"logps/rejected": -189.8342742919922,
|
1024 |
+
"loss": 1.6158,
|
1025 |
+
"rewards/accuracies": 0.7250000238418579,
|
1026 |
+
"rewards/chosen": 2.3008999824523926,
|
1027 |
+
"rewards/margins": 3.2730765342712402,
|
1028 |
+
"rewards/rejected": -0.9721772074699402,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 11.556695250472748,
|
1034 |
+
"learning_rate": 1.5863049882692565e-07,
|
1035 |
+
"logits/chosen": 6008.26904296875,
|
1036 |
+
"logits/rejected": 5051.5166015625,
|
1037 |
+
"logps/chosen": -212.3236083984375,
|
1038 |
+
"logps/rejected": -180.04847717285156,
|
1039 |
+
"loss": 1.6165,
|
1040 |
+
"rewards/accuracies": 0.6500000357627869,
|
1041 |
+
"rewards/chosen": 1.3081023693084717,
|
1042 |
+
"rewards/margins": 2.1385140419006348,
|
1043 |
+
"rewards/rejected": -0.8304115533828735,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 10.233108364900362,
|
1049 |
+
"learning_rate": 1.5452255001711795e-07,
|
1050 |
+
"logits/chosen": 5943.60302734375,
|
1051 |
+
"logits/rejected": 5483.03955078125,
|
1052 |
+
"logps/chosen": -207.3726348876953,
|
1053 |
+
"logps/rejected": -217.35693359375,
|
1054 |
+
"loss": 1.6141,
|
1055 |
+
"rewards/accuracies": 0.7000000476837158,
|
1056 |
+
"rewards/chosen": 1.7650575637817383,
|
1057 |
+
"rewards/margins": 2.921135425567627,
|
1058 |
+
"rewards/rejected": -1.1560779809951782,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 8.962560556788734,
|
1064 |
+
"learning_rate": 1.50411202711876e-07,
|
1065 |
+
"logits/chosen": 5653.8994140625,
|
1066 |
+
"logits/rejected": 5460.46044921875,
|
1067 |
+
"logps/chosen": -187.51516723632812,
|
1068 |
+
"logps/rejected": -188.84127807617188,
|
1069 |
+
"loss": 1.6177,
|
1070 |
+
"rewards/accuracies": 0.6333333253860474,
|
1071 |
+
"rewards/chosen": 1.7124507427215576,
|
1072 |
+
"rewards/margins": 3.6060166358947754,
|
1073 |
+
"rewards/rejected": -1.8935661315917969,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 10.815111342313953,
|
1079 |
+
"learning_rate": 1.4629954640606275e-07,
|
1080 |
+
"logits/chosen": 5610.15966796875,
|
1081 |
+
"logits/rejected": 5674.67822265625,
|
1082 |
+
"logps/chosen": -192.265625,
|
1083 |
+
"logps/rejected": -203.23452758789062,
|
1084 |
+
"loss": 1.6147,
|
1085 |
+
"rewards/accuracies": 0.6583333611488342,
|
1086 |
+
"rewards/chosen": 1.6721900701522827,
|
1087 |
+
"rewards/margins": 2.265028476715088,
|
1088 |
+
"rewards/rejected": -0.5928383469581604,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 11.454299662188049,
|
1094 |
+
"learning_rate": 1.4219067082674153e-07,
|
1095 |
+
"logits/chosen": 6028.6044921875,
|
1096 |
+
"logits/rejected": 5230.07373046875,
|
1097 |
+
"logps/chosen": -217.03543090820312,
|
1098 |
+
"logps/rejected": -201.26968383789062,
|
1099 |
+
"loss": 1.6162,
|
1100 |
+
"rewards/accuracies": 0.7416666746139526,
|
1101 |
+
"rewards/chosen": 1.9704124927520752,
|
1102 |
+
"rewards/margins": 3.4510631561279297,
|
1103 |
+
"rewards/rejected": -1.4806510210037231,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 11.472362484650057,
|
1109 |
+
"learning_rate": 1.3808766361138294e-07,
|
1110 |
+
"logits/chosen": 6529.74609375,
|
1111 |
+
"logits/rejected": 5061.63623046875,
|
1112 |
+
"logps/chosen": -224.10916137695312,
|
1113 |
+
"logps/rejected": -176.45887756347656,
|
1114 |
+
"loss": 1.6142,
|
1115 |
+
"rewards/accuracies": 0.6333333253860474,
|
1116 |
+
"rewards/chosen": 1.0688775777816772,
|
1117 |
+
"rewards/margins": 2.4734768867492676,
|
1118 |
+
"rewards/rejected": -1.4045993089675903,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 10.32346024402139,
|
1124 |
+
"learning_rate": 1.3399360798764307e-07,
|
1125 |
+
"logits/chosen": 5415.81103515625,
|
1126 |
+
"logits/rejected": 4646.49267578125,
|
1127 |
+
"logps/chosen": -191.19082641601562,
|
1128 |
+
"logps/rejected": -165.0283203125,
|
1129 |
+
"loss": 1.6157,
|
1130 |
+
"rewards/accuracies": 0.6916667222976685,
|
1131 |
+
"rewards/chosen": 1.2511141300201416,
|
1132 |
+
"rewards/margins": 3.6377835273742676,
|
1133 |
+
"rewards/rejected": -2.386669635772705,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 11.219416384074425,
|
1139 |
+
"learning_rate": 1.2991158045645435e-07,
|
1140 |
+
"logits/chosen": 5891.90380859375,
|
1141 |
+
"logits/rejected": 5381.7978515625,
|
1142 |
+
"logps/chosen": -179.5184326171875,
|
1143 |
+
"logps/rejected": -168.6924591064453,
|
1144 |
+
"loss": 1.6173,
|
1145 |
+
"rewards/accuracies": 0.6416667103767395,
|
1146 |
+
"rewards/chosen": 0.8637522459030151,
|
1147 |
+
"rewards/margins": 2.4437310695648193,
|
1148 |
+
"rewards/rejected": -1.5799791812896729,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 10.454823936279826,
|
1154 |
+
"learning_rate": 1.2584464848017214e-07,
|
1155 |
+
"logits/chosen": 6189.07373046875,
|
1156 |
+
"logits/rejected": 4946.9921875,
|
1157 |
+
"logps/chosen": -201.6912078857422,
|
1158 |
+
"logps/rejected": -176.08975219726562,
|
1159 |
+
"loss": 1.6189,
|
1160 |
+
"rewards/accuracies": 0.708333432674408,
|
1161 |
+
"rewards/chosen": 1.5779491662979126,
|
1162 |
+
"rewards/margins": 3.1704206466674805,
|
1163 |
+
"rewards/rejected": -1.592471718788147,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 11.144568917516514,
|
1169 |
+
"learning_rate": 1.2179586817751263e-07,
|
1170 |
+
"logits/chosen": 6398.5439453125,
|
1171 |
+
"logits/rejected": 5549.02197265625,
|
1172 |
+
"logps/chosen": -229.02297973632812,
|
1173 |
+
"logps/rejected": -226.2268829345703,
|
1174 |
+
"loss": 1.6196,
|
1175 |
+
"rewards/accuracies": 0.699999988079071,
|
1176 |
+
"rewards/chosen": 0.6905540227890015,
|
1177 |
+
"rewards/margins": 3.0377731323242188,
|
1178 |
+
"rewards/rejected": -2.3472187519073486,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 11.784984283909536,
|
1184 |
+
"learning_rate": 1.177682820270159e-07,
|
1185 |
+
"logits/chosen": 6260.98388671875,
|
1186 |
+
"logits/rejected": 5981.9970703125,
|
1187 |
+
"logps/chosen": -215.8638153076172,
|
1188 |
+
"logps/rejected": -239.6117706298828,
|
1189 |
+
"loss": 1.62,
|
1190 |
+
"rewards/accuracies": 0.6000000238418579,
|
1191 |
+
"rewards/chosen": 0.24781355261802673,
|
1192 |
+
"rewards/margins": 2.456618309020996,
|
1193 |
+
"rewards/rejected": -2.2088046073913574,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 11.336513282533264,
|
1199 |
+
"learning_rate": 1.13764916580758e-07,
|
1200 |
+
"logits/chosen": 5813.20849609375,
|
1201 |
+
"logits/rejected": 5193.22705078125,
|
1202 |
+
"logps/chosen": -197.9930877685547,
|
1203 |
+
"logps/rejected": -192.1040496826172,
|
1204 |
+
"loss": 1.6205,
|
1205 |
+
"rewards/accuracies": 0.699999988079071,
|
1206 |
+
"rewards/chosen": 0.16777479648590088,
|
1207 |
+
"rewards/margins": 3.6429495811462402,
|
1208 |
+
"rewards/rejected": -3.47517466545105,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 11.37275833046531,
|
1214 |
+
"learning_rate": 1.0978878019003183e-07,
|
1215 |
+
"logits/chosen": 5823.0517578125,
|
1216 |
+
"logits/rejected": 5127.9541015625,
|
1217 |
+
"logps/chosen": -216.37841796875,
|
1218 |
+
"logps/rejected": -215.0908203125,
|
1219 |
+
"loss": 1.6191,
|
1220 |
+
"rewards/accuracies": 0.6333333253860474,
|
1221 |
+
"rewards/chosen": 0.3729097247123718,
|
1222 |
+
"rewards/margins": 2.810680866241455,
|
1223 |
+
"rewards/rejected": -2.4377713203430176,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 11.92843313737738,
|
1229 |
+
"learning_rate": 1.0584286074470446e-07,
|
1230 |
+
"logits/chosen": 5377.32421875,
|
1231 |
+
"logits/rejected": 4863.58154296875,
|
1232 |
+
"logps/chosen": -201.692626953125,
|
1233 |
+
"logps/rejected": -224.701171875,
|
1234 |
+
"loss": 1.6182,
|
1235 |
+
"rewards/accuracies": 0.7666667103767395,
|
1236 |
+
"rewards/chosen": 0.7583420872688293,
|
1237 |
+
"rewards/margins": 4.198758602142334,
|
1238 |
+
"rewards/rejected": -3.4404168128967285,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 11.620823490647497,
|
1244 |
+
"learning_rate": 1.0193012342795095e-07,
|
1245 |
+
"logits/chosen": 5848.99462890625,
|
1246 |
+
"logits/rejected": 4559.11669921875,
|
1247 |
+
"logps/chosen": -219.4331512451172,
|
1248 |
+
"logps/rejected": -170.939697265625,
|
1249 |
+
"loss": 1.6184,
|
1250 |
+
"rewards/accuracies": 0.7250000238418579,
|
1251 |
+
"rewards/chosen": 1.7729305028915405,
|
1252 |
+
"rewards/margins": 4.044053077697754,
|
1253 |
+
"rewards/rejected": -2.271122694015503,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 10.399323259266707,
|
1259 |
+
"learning_rate": 9.805350848805078e-08,
|
1260 |
+
"logits/chosen": 5789.95068359375,
|
1261 |
+
"logits/rejected": 5189.4072265625,
|
1262 |
+
"logps/chosen": -203.59767150878906,
|
1263 |
+
"logps/rejected": -195.38893127441406,
|
1264 |
+
"loss": 1.6199,
|
1265 |
+
"rewards/accuracies": 0.699999988079071,
|
1266 |
+
"rewards/chosen": 0.5932119488716125,
|
1267 |
+
"rewards/margins": 3.508798122406006,
|
1268 |
+
"rewards/rejected": -2.915585994720459,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 10.035390499048138,
|
1274 |
+
"learning_rate": 9.421592902892184e-08,
|
1275 |
+
"logits/chosen": 6314.8837890625,
|
1276 |
+
"logits/rejected": 5214.59326171875,
|
1277 |
+
"logps/chosen": -227.4573974609375,
|
1278 |
+
"logps/rejected": -215.1611785888672,
|
1279 |
+
"loss": 1.6204,
|
1280 |
+
"rewards/accuracies": 0.5833333134651184,
|
1281 |
+
"rewards/chosen": -0.09185920655727386,
|
1282 |
+
"rewards/margins": 2.265404462814331,
|
1283 |
+
"rewards/rejected": -2.3572635650634766,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 11.544156642460049,
|
1289 |
+
"learning_rate": 9.042026882105215e-08,
|
1290 |
+
"logits/chosen": 5835.57275390625,
|
1291 |
+
"logits/rejected": 5284.0244140625,
|
1292 |
+
"logps/chosen": -214.9558563232422,
|
1293 |
+
"logps/rejected": -203.69520568847656,
|
1294 |
+
"loss": 1.618,
|
1295 |
+
"rewards/accuracies": 0.7083333730697632,
|
1296 |
+
"rewards/chosen": 0.5202548503875732,
|
1297 |
+
"rewards/margins": 3.6990485191345215,
|
1298 |
+
"rewards/rejected": -3.1787941455841064,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 11.190718842900319,
|
1304 |
+
"learning_rate": 8.666938013447484e-08,
|
1305 |
+
"logits/chosen": 6286.025390625,
|
1306 |
+
"logits/rejected": 5394.0,
|
1307 |
+
"logps/chosen": -247.1281280517578,
|
1308 |
+
"logps/rejected": -205.7931671142578,
|
1309 |
+
"loss": 1.6199,
|
1310 |
+
"rewards/accuracies": 0.7583333253860474,
|
1311 |
+
"rewards/chosen": 0.6725990772247314,
|
1312 |
+
"rewards/margins": 3.7918269634246826,
|
1313 |
+
"rewards/rejected": -3.119227886199951,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 11.069681395938431,
|
1319 |
+
"learning_rate": 8.29660815954134e-08,
|
1320 |
+
"logits/chosen": 6258.58837890625,
|
1321 |
+
"logits/rejected": 5223.68017578125,
|
1322 |
+
"logps/chosen": -229.8612518310547,
|
1323 |
+
"logps/rejected": -203.4960174560547,
|
1324 |
+
"loss": 1.6203,
|
1325 |
+
"rewards/accuracies": 0.7416666746139526,
|
1326 |
+
"rewards/chosen": 0.273890882730484,
|
1327 |
+
"rewards/margins": 3.0515148639678955,
|
1328 |
+
"rewards/rejected": -2.7776238918304443,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 10.760516756235438,
|
1334 |
+
"learning_rate": 7.931315606820979e-08,
|
1335 |
+
"logits/chosen": 5503.98388671875,
|
1336 |
+
"logits/rejected": 5300.1279296875,
|
1337 |
+
"logps/chosen": -210.29623413085938,
|
1338 |
+
"logps/rejected": -234.48428344726562,
|
1339 |
+
"loss": 1.6209,
|
1340 |
+
"rewards/accuracies": 0.7250000238418579,
|
1341 |
+
"rewards/chosen": 0.23874196410179138,
|
1342 |
+
"rewards/margins": 3.12656831741333,
|
1343 |
+
"rewards/rejected": -2.887826442718506,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 11.62760722742798,
|
1349 |
+
"learning_rate": 7.571334856412503e-08,
|
1350 |
+
"logits/chosen": 6500.73779296875,
|
1351 |
+
"logits/rejected": 5318.8017578125,
|
1352 |
+
"logps/chosen": -257.2298278808594,
|
1353 |
+
"logps/rejected": -215.5242156982422,
|
1354 |
+
"loss": 1.6219,
|
1355 |
+
"rewards/accuracies": 0.7250000238418579,
|
1356 |
+
"rewards/chosen": 0.3969727158546448,
|
1357 |
+
"rewards/margins": 4.151793003082275,
|
1358 |
+
"rewards/rejected": -3.754819869995117,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 9.458870050953964,
|
1364 |
+
"learning_rate": 7.216936417858549e-08,
|
1365 |
+
"logits/chosen": 5499.93701171875,
|
1366 |
+
"logits/rejected": 5135.26318359375,
|
1367 |
+
"logps/chosen": -204.2237548828125,
|
1368 |
+
"logps/rejected": -214.3614959716797,
|
1369 |
+
"loss": 1.622,
|
1370 |
+
"rewards/accuracies": 0.7583333253860474,
|
1371 |
+
"rewards/chosen": 0.10146790742874146,
|
1372 |
+
"rewards/margins": 4.020596027374268,
|
1373 |
+
"rewards/rejected": -3.919127941131592,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 11.195584952901939,
|
1379 |
+
"learning_rate": 6.868386605842379e-08,
|
1380 |
+
"logits/chosen": 5412.22216796875,
|
1381 |
+
"logits/rejected": 5166.134765625,
|
1382 |
+
"logps/chosen": -207.86279296875,
|
1383 |
+
"logps/rejected": -212.60983276367188,
|
1384 |
+
"loss": 1.6223,
|
1385 |
+
"rewards/accuracies": 0.7666666507720947,
|
1386 |
+
"rewards/chosen": 0.4062539041042328,
|
1387 |
+
"rewards/margins": 5.072477340698242,
|
1388 |
+
"rewards/rejected": -4.666223049163818,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 10.447859698886178,
|
1394 |
+
"learning_rate": 6.525947340064232e-08,
|
1395 |
+
"logits/chosen": 5988.22265625,
|
1396 |
+
"logits/rejected": 4997.0390625,
|
1397 |
+
"logps/chosen": -232.16281127929688,
|
1398 |
+
"logps/rejected": -202.34010314941406,
|
1399 |
+
"loss": 1.6219,
|
1400 |
+
"rewards/accuracies": 0.7583333849906921,
|
1401 |
+
"rewards/chosen": 0.2832966446876526,
|
1402 |
+
"rewards/margins": 4.437819480895996,
|
1403 |
+
"rewards/rejected": -4.154522895812988,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 11.894379056711179,
|
1409 |
+
"learning_rate": 6.189875948420276e-08,
|
1410 |
+
"logits/chosen": 5893.60205078125,
|
1411 |
+
"logits/rejected": 4513.279296875,
|
1412 |
+
"logps/chosen": -236.3983612060547,
|
1413 |
+
"logps/rejected": -190.51617431640625,
|
1414 |
+
"loss": 1.6224,
|
1415 |
+
"rewards/accuracies": 0.7250000238418579,
|
1416 |
+
"rewards/chosen": -0.3916471600532532,
|
1417 |
+
"rewards/margins": 4.208518981933594,
|
1418 |
+
"rewards/rejected": -4.600167274475098,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 10.98098284583286,
|
1424 |
+
"learning_rate": 5.86042497363215e-08,
|
1425 |
+
"logits/chosen": 5721.9482421875,
|
1426 |
+
"logits/rejected": 5032.0947265625,
|
1427 |
+
"logps/chosen": -218.5546875,
|
1428 |
+
"logps/rejected": -209.4766387939453,
|
1429 |
+
"loss": 1.6227,
|
1430 |
+
"rewards/accuracies": 0.6916666626930237,
|
1431 |
+
"rewards/chosen": -0.21962371468544006,
|
1432 |
+
"rewards/margins": 4.292196273803711,
|
1433 |
+
"rewards/rejected": -4.511819362640381,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 10.09472856202966,
|
1439 |
+
"learning_rate": 5.537841983472337e-08,
|
1440 |
+
"logits/chosen": 5903.6142578125,
|
1441 |
+
"logits/rejected": 5460.48779296875,
|
1442 |
+
"logps/chosen": -217.61929321289062,
|
1443 |
+
"logps/rejected": -217.16525268554688,
|
1444 |
+
"loss": 1.6233,
|
1445 |
+
"rewards/accuracies": 0.6833333373069763,
|
1446 |
+
"rewards/chosen": 0.16755667328834534,
|
1447 |
+
"rewards/margins": 3.2451682090759277,
|
1448 |
+
"rewards/rejected": -3.0776114463806152,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 11.803340128971255,
|
1454 |
+
"learning_rate": 5.222369384727954e-08,
|
1455 |
+
"logits/chosen": 5730.85205078125,
|
1456 |
+
"logits/rejected": 5144.63037109375,
|
1457 |
+
"logps/chosen": -218.22622680664062,
|
1458 |
+
"logps/rejected": -206.0850372314453,
|
1459 |
+
"loss": 1.6222,
|
1460 |
+
"rewards/accuracies": 0.7916666269302368,
|
1461 |
+
"rewards/chosen": 0.27254268527030945,
|
1462 |
+
"rewards/margins": 3.8942532539367676,
|
1463 |
+
"rewards/rejected": -3.6217105388641357,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 11.454679795991241,
|
1469 |
+
"learning_rate": 4.914244241042832e-08,
|
1470 |
+
"logits/chosen": 5840.7158203125,
|
1471 |
+
"logits/rejected": 4928.1845703125,
|
1472 |
+
"logps/chosen": -240.2581787109375,
|
1473 |
+
"logps/rejected": -210.8507537841797,
|
1474 |
+
"loss": 1.6232,
|
1475 |
+
"rewards/accuracies": 0.7249999642372131,
|
1476 |
+
"rewards/chosen": -0.018189292401075363,
|
1477 |
+
"rewards/margins": 4.160759925842285,
|
1478 |
+
"rewards/rejected": -4.178948402404785,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 11.99470899522862,
|
1484 |
+
"learning_rate": 4.613698094774715e-08,
|
1485 |
+
"logits/chosen": 5542.8330078125,
|
1486 |
+
"logits/rejected": 4527.66015625,
|
1487 |
+
"logps/chosen": -228.67837524414062,
|
1488 |
+
"logps/rejected": -195.180419921875,
|
1489 |
+
"loss": 1.622,
|
1490 |
+
"rewards/accuracies": 0.7583333253860474,
|
1491 |
+
"rewards/chosen": 0.15695662796497345,
|
1492 |
+
"rewards/margins": 4.860254764556885,
|
1493 |
+
"rewards/rejected": -4.703298091888428,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 13.577338184519638,
|
1499 |
+
"learning_rate": 4.3209567930014746e-08,
|
1500 |
+
"logits/chosen": 5864.568359375,
|
1501 |
+
"logits/rejected": 4959.56396484375,
|
1502 |
+
"logps/chosen": -226.41036987304688,
|
1503 |
+
"logps/rejected": -198.62289428710938,
|
1504 |
+
"loss": 1.622,
|
1505 |
+
"rewards/accuracies": 0.6416667103767395,
|
1506 |
+
"rewards/chosen": -0.5170873403549194,
|
1507 |
+
"rewards/margins": 4.038225173950195,
|
1508 |
+
"rewards/rejected": -4.555312156677246,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 11.227134966757461,
|
1514 |
+
"learning_rate": 4.036240317807059e-08,
|
1515 |
+
"logits/chosen": 5562.1455078125,
|
1516 |
+
"logits/rejected": 4746.4765625,
|
1517 |
+
"logps/chosen": -213.9759979248047,
|
1518 |
+
"logps/rejected": -184.7088165283203,
|
1519 |
+
"loss": 1.6223,
|
1520 |
+
"rewards/accuracies": 0.6750000715255737,
|
1521 |
+
"rewards/chosen": -0.1758609116077423,
|
1522 |
+
"rewards/margins": 4.17446231842041,
|
1523 |
+
"rewards/rejected": -4.35032320022583,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 10.788480554925878,
|
1529 |
+
"learning_rate": 3.759762620974716e-08,
|
1530 |
+
"logits/chosen": 5739.294921875,
|
1531 |
+
"logits/rejected": 4851.3935546875,
|
1532 |
+
"logps/chosen": -214.68118286132812,
|
1533 |
+
"logps/rejected": -195.8408203125,
|
1534 |
+
"loss": 1.6224,
|
1535 |
+
"rewards/accuracies": 0.699999988079071,
|
1536 |
+
"rewards/chosen": 0.02830815315246582,
|
1537 |
+
"rewards/margins": 4.474509239196777,
|
1538 |
+
"rewards/rejected": -4.446200847625732,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 10.560717225935313,
|
1544 |
+
"learning_rate": 3.4917314632117423e-08,
|
1545 |
+
"logits/chosen": 5831.240234375,
|
1546 |
+
"logits/rejected": 5222.7080078125,
|
1547 |
+
"logps/chosen": -248.1968994140625,
|
1548 |
+
"logps/rejected": -230.4774932861328,
|
1549 |
+
"loss": 1.6229,
|
1550 |
+
"rewards/accuracies": 0.783333420753479,
|
1551 |
+
"rewards/chosen": -0.018525028601288795,
|
1552 |
+
"rewards/margins": 4.307133674621582,
|
1553 |
+
"rewards/rejected": -4.325658798217773,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 11.450889100406535,
|
1559 |
+
"learning_rate": 3.232348258026552e-08,
|
1560 |
+
"logits/chosen": 6223.50048828125,
|
1561 |
+
"logits/rejected": 5888.0341796875,
|
1562 |
+
"logps/chosen": -231.3888702392578,
|
1563 |
+
"logps/rejected": -237.2459259033203,
|
1564 |
+
"loss": 1.6228,
|
1565 |
+
"rewards/accuracies": 0.7833333611488342,
|
1566 |
+
"rewards/chosen": 0.0547012984752655,
|
1567 |
+
"rewards/margins": 4.181652545928955,
|
1568 |
+
"rewards/rejected": -4.126951217651367,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 11.896899452824945,
|
1574 |
+
"learning_rate": 2.9818079203753654e-08,
|
1575 |
+
"logits/chosen": 5537.16064453125,
|
1576 |
+
"logits/rejected": 5094.0849609375,
|
1577 |
+
"logps/chosen": -220.12808227539062,
|
1578 |
+
"logps/rejected": -212.80624389648438,
|
1579 |
+
"loss": 1.6234,
|
1580 |
+
"rewards/accuracies": 0.6666666865348816,
|
1581 |
+
"rewards/chosen": -0.038040757179260254,
|
1582 |
+
"rewards/margins": 3.5793395042419434,
|
1583 |
+
"rewards/rejected": -3.617380142211914,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 12.623914170332412,
|
1589 |
+
"learning_rate": 2.740298720192245e-08,
|
1590 |
+
"logits/chosen": 5572.4052734375,
|
1591 |
+
"logits/rejected": 5124.4365234375,
|
1592 |
+
"logps/chosen": -237.76119995117188,
|
1593 |
+
"logps/rejected": -219.5039825439453,
|
1594 |
+
"loss": 1.6226,
|
1595 |
+
"rewards/accuracies": 0.6916667222976685,
|
1596 |
+
"rewards/chosen": -0.2121574878692627,
|
1597 |
+
"rewards/margins": 3.454202175140381,
|
1598 |
+
"rewards/rejected": -3.6663596630096436,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 11.913054191421269,
|
1604 |
+
"learning_rate": 2.5080021409126655e-08,
|
1605 |
+
"logits/chosen": 6892.4423828125,
|
1606 |
+
"logits/rejected": 5450.9912109375,
|
1607 |
+
"logps/chosen": -261.4605407714844,
|
1608 |
+
"logps/rejected": -224.04019165039062,
|
1609 |
+
"loss": 1.6228,
|
1610 |
+
"rewards/accuracies": 0.6916667222976685,
|
1611 |
+
"rewards/chosen": -0.4351968765258789,
|
1612 |
+
"rewards/margins": 3.5411152839660645,
|
1613 |
+
"rewards/rejected": -3.9763119220733643,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 11.445993088464819,
|
1619 |
+
"learning_rate": 2.2850927430967287e-08,
|
1620 |
+
"logits/chosen": 5742.19580078125,
|
1621 |
+
"logits/rejected": 5310.591796875,
|
1622 |
+
"logps/chosen": -225.3037567138672,
|
1623 |
+
"logps/rejected": -197.18203735351562,
|
1624 |
+
"loss": 1.624,
|
1625 |
+
"rewards/accuracies": 0.7333333492279053,
|
1626 |
+
"rewards/chosen": -0.027328431606292725,
|
1627 |
+
"rewards/margins": 4.017100811004639,
|
1628 |
+
"rewards/rejected": -4.044428825378418,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 11.059510886657053,
|
1634 |
+
"learning_rate": 2.0717380332546768e-08,
|
1635 |
+
"logits/chosen": 6291.6181640625,
|
1636 |
+
"logits/rejected": 4913.92919921875,
|
1637 |
+
"logps/chosen": -266.40643310546875,
|
1638 |
+
"logps/rejected": -206.01705932617188,
|
1639 |
+
"loss": 1.6219,
|
1640 |
+
"rewards/accuracies": 0.8166667222976685,
|
1641 |
+
"rewards/chosen": 0.1874084770679474,
|
1642 |
+
"rewards/margins": 5.219174385070801,
|
1643 |
+
"rewards/rejected": -5.031765937805176,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 11.093065022674237,
|
1649 |
+
"learning_rate": 1.8680983379731618e-08,
|
1650 |
+
"logits/chosen": 6390.0458984375,
|
1651 |
+
"logits/rejected": 4830.373046875,
|
1652 |
+
"logps/chosen": -228.0162353515625,
|
1653 |
+
"logps/rejected": -217.597900390625,
|
1654 |
+
"loss": 1.6244,
|
1655 |
+
"rewards/accuracies": 0.7333334684371948,
|
1656 |
+
"rewards/chosen": -0.5020327568054199,
|
1657 |
+
"rewards/margins": 4.1861772537231445,
|
1658 |
+
"rewards/rejected": -4.688210487365723,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 11.004461382075167,
|
1664 |
+
"learning_rate": 1.6743266834369856e-08,
|
1665 |
+
"logits/chosen": 6145.6806640625,
|
1666 |
+
"logits/rejected": 5110.62548828125,
|
1667 |
+
"logps/chosen": -239.3874053955078,
|
1668 |
+
"logps/rejected": -194.05117797851562,
|
1669 |
+
"loss": 1.6246,
|
1670 |
+
"rewards/accuracies": 0.6916667222976685,
|
1671 |
+
"rewards/chosen": -0.8312684893608093,
|
1672 |
+
"rewards/margins": 3.724156141281128,
|
1673 |
+
"rewards/rejected": -4.555424690246582,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 11.169359353898571,
|
1679 |
+
"learning_rate": 1.4905686804366853e-08,
|
1680 |
+
"logits/chosen": 6507.7529296875,
|
1681 |
+
"logits/rejected": 5290.05908203125,
|
1682 |
+
"logps/chosen": -265.2042236328125,
|
1683 |
+
"logps/rejected": -227.3978729248047,
|
1684 |
+
"loss": 1.6229,
|
1685 |
+
"rewards/accuracies": 0.7083333730697632,
|
1686 |
+
"rewards/chosen": -0.6048145294189453,
|
1687 |
+
"rewards/margins": 4.526320457458496,
|
1688 |
+
"rewards/rejected": -5.131134986877441,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 10.36627141349426,
|
1694 |
+
"learning_rate": 1.3169624149485037e-08,
|
1695 |
+
"logits/chosen": 6368.01416015625,
|
1696 |
+
"logits/rejected": 5209.26611328125,
|
1697 |
+
"logps/chosen": -246.00863647460938,
|
1698 |
+
"logps/rejected": -221.8163604736328,
|
1699 |
+
"loss": 1.6232,
|
1700 |
+
"rewards/accuracies": 0.699999988079071,
|
1701 |
+
"rewards/chosen": -0.8775882720947266,
|
1702 |
+
"rewards/margins": 4.164261817932129,
|
1703 |
+
"rewards/rejected": -5.041850566864014,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 11.689309702253437,
|
1709 |
+
"learning_rate": 1.1536383443688968e-08,
|
1710 |
+
"logits/chosen": 5779.93896484375,
|
1711 |
+
"logits/rejected": 4615.59326171875,
|
1712 |
+
"logps/chosen": -234.68215942382812,
|
1713 |
+
"logps/rejected": -184.45750427246094,
|
1714 |
+
"loss": 1.6232,
|
1715 |
+
"rewards/accuracies": 0.7333333492279053,
|
1716 |
+
"rewards/chosen": 0.10495586693286896,
|
1717 |
+
"rewards/margins": 4.333970546722412,
|
1718 |
+
"rewards/rejected": -4.2290143966674805,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 11.69568286023684,
|
1724 |
+
"learning_rate": 1.0007191994816272e-08,
|
1725 |
+
"logits/chosen": 6343.60009765625,
|
1726 |
+
"logits/rejected": 5211.26416015625,
|
1727 |
+
"logps/chosen": -258.3962097167969,
|
1728 |
+
"logps/rejected": -225.07742309570312,
|
1729 |
+
"loss": 1.6226,
|
1730 |
+
"rewards/accuracies": 0.7250000238418579,
|
1731 |
+
"rewards/chosen": -0.7535941004753113,
|
1732 |
+
"rewards/margins": 3.4583687782287598,
|
1733 |
+
"rewards/rejected": -4.211962699890137,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 12.01611350837566,
|
1739 |
+
"learning_rate": 8.583198922310031e-09,
|
1740 |
+
"logits/chosen": 5625.16796875,
|
1741 |
+
"logits/rejected": 5218.8232421875,
|
1742 |
+
"logps/chosen": -227.22756958007812,
|
1743 |
+
"logps/rejected": -223.5425262451172,
|
1744 |
+
"loss": 1.623,
|
1745 |
+
"rewards/accuracies": 0.7166666984558105,
|
1746 |
+
"rewards/chosen": -0.24080140888690948,
|
1747 |
+
"rewards/margins": 3.7667922973632812,
|
1748 |
+
"rewards/rejected": -4.007594108581543,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 11.149096309955521,
|
1754 |
+
"learning_rate": 7.2654742937067916e-09,
|
1755 |
+
"logits/chosen": 5776.7119140625,
|
1756 |
+
"logits/rejected": 4638.9755859375,
|
1757 |
+
"logps/chosen": -228.9247283935547,
|
1758 |
+
"logps/rejected": -199.80224609375,
|
1759 |
+
"loss": 1.624,
|
1760 |
+
"rewards/accuracies": 0.7083333134651184,
|
1761 |
+
"rewards/chosen": -0.35184532403945923,
|
1762 |
+
"rewards/margins": 3.520703077316284,
|
1763 |
+
"rewards/rejected": -3.8725483417510986,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 11.730310171305202,
|
1769 |
+
"learning_rate": 6.0550083205280325e-09,
|
1770 |
+
"logits/chosen": 6331.5869140625,
|
1771 |
+
"logits/rejected": 6107.18408203125,
|
1772 |
+
"logps/chosen": -243.18026733398438,
|
1773 |
+
"logps/rejected": -251.1663360595703,
|
1774 |
+
"loss": 1.6231,
|
1775 |
+
"rewards/accuracies": 0.6666666865348816,
|
1776 |
+
"rewards/chosen": -0.2250463217496872,
|
1777 |
+
"rewards/margins": 4.151488780975342,
|
1778 |
+
"rewards/rejected": -4.376535415649414,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 12.532143717176293,
|
1784 |
+
"learning_rate": 4.952710614180567e-09,
|
1785 |
+
"logits/chosen": 5591.78173828125,
|
1786 |
+
"logits/rejected": 5125.27197265625,
|
1787 |
+
"logps/chosen": -240.2451629638672,
|
1788 |
+
"logps/rejected": -220.843505859375,
|
1789 |
+
"loss": 1.6247,
|
1790 |
+
"rewards/accuracies": 0.7416667342185974,
|
1791 |
+
"rewards/chosen": -0.33638685941696167,
|
1792 |
+
"rewards/margins": 3.716320753097534,
|
1793 |
+
"rewards/rejected": -4.052707672119141,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 11.073947353465151,
|
1799 |
+
"learning_rate": 3.959409502423744e-09,
|
1800 |
+
"logits/chosen": 6082.80712890625,
|
1801 |
+
"logits/rejected": 5334.0517578125,
|
1802 |
+
"logps/chosen": -250.0338897705078,
|
1803 |
+
"logps/rejected": -221.93896484375,
|
1804 |
+
"loss": 1.6231,
|
1805 |
+
"rewards/accuracies": 0.6750000715255737,
|
1806 |
+
"rewards/chosen": -1.1701091527938843,
|
1807 |
+
"rewards/margins": 3.618891477584839,
|
1808 |
+
"rewards/rejected": -4.789000511169434,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 11.478913045969124,
|
1814 |
+
"learning_rate": 3.075851406917995e-09,
|
1815 |
+
"logits/chosen": 6255.9599609375,
|
1816 |
+
"logits/rejected": 5368.0625,
|
1817 |
+
"logps/chosen": -256.30841064453125,
|
1818 |
+
"logps/rejected": -224.0297393798828,
|
1819 |
+
"loss": 1.6228,
|
1820 |
+
"rewards/accuracies": 0.7416666746139526,
|
1821 |
+
"rewards/chosen": -0.6638107299804688,
|
1822 |
+
"rewards/margins": 4.6817946434021,
|
1823 |
+
"rewards/rejected": -5.345605373382568,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 11.772570086955174,
|
1829 |
+
"learning_rate": 2.3027002823221064e-09,
|
1830 |
+
"logits/chosen": 5870.1064453125,
|
1831 |
+
"logits/rejected": 5151.9208984375,
|
1832 |
+
"logps/chosen": -240.24136352539062,
|
1833 |
+
"logps/rejected": -222.8927764892578,
|
1834 |
+
"loss": 1.6242,
|
1835 |
+
"rewards/accuracies": 0.7916667461395264,
|
1836 |
+
"rewards/chosen": -0.034066688269376755,
|
1837 |
+
"rewards/margins": 4.694322109222412,
|
1838 |
+
"rewards/rejected": -4.728388786315918,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 11.341650876448142,
|
1844 |
+
"learning_rate": 1.6405371173608073e-09,
|
1845 |
+
"logits/chosen": 7316.70556640625,
|
1846 |
+
"logits/rejected": 5417.42626953125,
|
1847 |
+
"logps/chosen": -297.10943603515625,
|
1848 |
+
"logps/rejected": -250.65249633789062,
|
1849 |
+
"loss": 1.6226,
|
1850 |
+
"rewards/accuracies": 0.7249999642372131,
|
1851 |
+
"rewards/chosen": -0.27967390418052673,
|
1852 |
+
"rewards/margins": 5.194223880767822,
|
1853 |
+
"rewards/rejected": -5.4738969802856445,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 12.25958376489255,
|
1859 |
+
"learning_rate": 1.0898594982375387e-09,
|
1860 |
+
"logits/chosen": 6507.357421875,
|
1861 |
+
"logits/rejected": 5199.5634765625,
|
1862 |
+
"logps/chosen": -260.1299133300781,
|
1863 |
+
"logps/rejected": -217.67202758789062,
|
1864 |
+
"loss": 1.6232,
|
1865 |
+
"rewards/accuracies": 0.7416666746139526,
|
1866 |
+
"rewards/chosen": 0.43730440735816956,
|
1867 |
+
"rewards/margins": 5.117526054382324,
|
1868 |
+
"rewards/rejected": -4.680222511291504,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 12.320721462602215,
|
1874 |
+
"learning_rate": 6.510812347205185e-10,
|
1875 |
+
"logits/chosen": 5608.94189453125,
|
1876 |
+
"logits/rejected": 5175.58935546875,
|
1877 |
+
"logps/chosen": -232.12710571289062,
|
1878 |
+
"logps/rejected": -239.9905242919922,
|
1879 |
+
"loss": 1.6223,
|
1880 |
+
"rewards/accuracies": 0.6916667222976685,
|
1881 |
+
"rewards/chosen": -0.5330235362052917,
|
1882 |
+
"rewards/margins": 4.260423183441162,
|
1883 |
+
"rewards/rejected": -4.7934465408325195,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 11.623382089715227,
|
1889 |
+
"learning_rate": 3.245320491830683e-10,
|
1890 |
+
"logits/chosen": 5712.59912109375,
|
1891 |
+
"logits/rejected": 4849.1201171875,
|
1892 |
+
"logps/chosen": -230.5782928466797,
|
1893 |
+
"logps/rejected": -193.20933532714844,
|
1894 |
+
"loss": 1.6227,
|
1895 |
+
"rewards/accuracies": 0.75,
|
1896 |
+
"rewards/chosen": -0.2468281090259552,
|
1897 |
+
"rewards/margins": 3.513197660446167,
|
1898 |
+
"rewards/rejected": -3.7600255012512207,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 10.941217530065499,
|
1904 |
+
"learning_rate": 1.1045732883197545e-10,
|
1905 |
+
"logits/chosen": 5392.3876953125,
|
1906 |
+
"logits/rejected": 5146.81103515625,
|
1907 |
+
"logps/chosen": -233.12521362304688,
|
1908 |
+
"logps/rejected": -220.48587036132812,
|
1909 |
+
"loss": 1.6232,
|
1910 |
+
"rewards/accuracies": 0.699999988079071,
|
1911 |
+
"rewards/chosen": -0.9743496775627136,
|
1912 |
+
"rewards/margins": 3.1852924823760986,
|
1913 |
+
"rewards/rejected": -4.159642219543457,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 11.869179900549053,
|
1919 |
+
"learning_rate": 9.017941309813482e-12,
|
1920 |
+
"logits/chosen": 5663.7666015625,
|
1921 |
+
"logits/rejected": 4646.2197265625,
|
1922 |
+
"logps/chosen": -224.53286743164062,
|
1923 |
+
"logps/rejected": -189.52761840820312,
|
1924 |
+
"loss": 1.6221,
|
1925 |
+
"rewards/accuracies": 0.7083333730697632,
|
1926 |
+
"rewards/chosen": -0.044149044901132584,
|
1927 |
+
"rewards/margins": 3.1750922203063965,
|
1928 |
+
"rewards/rejected": -3.2192413806915283,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": 1.6157182269792543,
|
1936 |
+
"train_runtime": 13119.408,
|
1937 |
+
"train_samples_per_second": 4.66,
|
1938 |
+
"train_steps_per_second": 0.097
|
1939 |
+
}
|
1940 |
+
],
|
1941 |
+
"logging_steps": 10,
|
1942 |
+
"max_steps": 1274,
|
1943 |
+
"num_input_tokens_seen": 0,
|
1944 |
+
"num_train_epochs": 1,
|
1945 |
+
"save_steps": 2000,
|
1946 |
+
"stateful_callbacks": {
|
1947 |
+
"TrainerControl": {
|
1948 |
+
"args": {
|
1949 |
+
"should_epoch_stop": false,
|
1950 |
+
"should_evaluate": false,
|
1951 |
+
"should_log": false,
|
1952 |
+
"should_save": false,
|
1953 |
+
"should_training_stop": false
|
1954 |
+
},
|
1955 |
+
"attributes": {}
|
1956 |
+
}
|
1957 |
+
},
|
1958 |
+
"total_flos": 0.0,
|
1959 |
+
"train_batch_size": 6,
|
1960 |
+
"trial_name": null,
|
1961 |
+
"trial_params": null
|
1962 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b69b15a895ae0b24c6ffb659876553c372ae064f1c316c66efeeb8c9ae38efd
|
3 |
+
size 7352
|