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: Ber_shift2-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 |
+
# Ber_shift2-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: 5e-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 2.3.0+cu121
|
59 |
+
- Datasets 2.19.1
|
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": 1.3571216397607346,
|
5 |
+
"train_runtime": 13426.8072,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.553,
|
8 |
+
"train_steps_per_second": 0.095
|
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 sha256:37ba19860dc64a46d11736342726cb8c9e27c68e7c29164779956ac8b6011bf6
|
3 |
+
size 4943162336
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b04c16d9eb7eb28a8d121dff935884750bf94c33ab849e567e9b763b2950895
|
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:d0e5b7eeb2975db5ded0bcb6ca8e9ccf0a0fbfd8c965a0c47cfd6e569451ec7c
|
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": 1.3571216397607346,
|
5 |
+
"train_runtime": 13426.8072,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.553,
|
8 |
+
"train_steps_per_second": 0.095
|
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": 0.03268135007860773,
|
14 |
+
"learning_rate": 3.90625e-09,
|
15 |
+
"logits/chosen": 5914.52099609375,
|
16 |
+
"logits/rejected": 2785.021484375,
|
17 |
+
"logps/chosen": -0.6567006707191467,
|
18 |
+
"logps/rejected": -0.778023362159729,
|
19 |
+
"loss": 1.3863,
|
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": 0.030196865520322073,
|
29 |
+
"learning_rate": 3.9062499999999997e-08,
|
30 |
+
"logits/chosen": 4973.7216796875,
|
31 |
+
"logits/rejected": 4328.291015625,
|
32 |
+
"logps/chosen": -0.7547220587730408,
|
33 |
+
"logps/rejected": -0.8142147064208984,
|
34 |
+
"loss": 1.3863,
|
35 |
+
"rewards/accuracies": 0.4351852238178253,
|
36 |
+
"rewards/chosen": 0.00014649056538473815,
|
37 |
+
"rewards/margins": 0.00016151672753039747,
|
38 |
+
"rewards/rejected": -1.5026165783638135e-05,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015698587127158554,
|
43 |
+
"grad_norm": 0.03515484842658268,
|
44 |
+
"learning_rate": 7.812499999999999e-08,
|
45 |
+
"logits/chosen": 6084.4482421875,
|
46 |
+
"logits/rejected": 4834.47021484375,
|
47 |
+
"logps/chosen": -0.6600744128227234,
|
48 |
+
"logps/rejected": -0.7692333459854126,
|
49 |
+
"loss": 1.3863,
|
50 |
+
"rewards/accuracies": 0.4666667580604553,
|
51 |
+
"rewards/chosen": 6.742794357705861e-05,
|
52 |
+
"rewards/margins": 1.602613519935403e-05,
|
53 |
+
"rewards/rejected": 5.140181019669399e-05,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.023547880690737835,
|
58 |
+
"grad_norm": 0.031197105041082272,
|
59 |
+
"learning_rate": 1.1718749999999999e-07,
|
60 |
+
"logits/chosen": 6085.9990234375,
|
61 |
+
"logits/rejected": 5106.2900390625,
|
62 |
+
"logps/chosen": -0.7124911546707153,
|
63 |
+
"logps/rejected": -0.7892431020736694,
|
64 |
+
"loss": 1.3863,
|
65 |
+
"rewards/accuracies": 0.6333333253860474,
|
66 |
+
"rewards/chosen": 9.94208239717409e-05,
|
67 |
+
"rewards/margins": 0.0004724114260170609,
|
68 |
+
"rewards/rejected": -0.00037299064570106566,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03139717425431711,
|
73 |
+
"grad_norm": 0.02997164386237047,
|
74 |
+
"learning_rate": 1.5624999999999999e-07,
|
75 |
+
"logits/chosen": 5314.44580078125,
|
76 |
+
"logits/rejected": 4349.19580078125,
|
77 |
+
"logps/chosen": -0.7033883929252625,
|
78 |
+
"logps/rejected": -0.7918646931648254,
|
79 |
+
"loss": 1.3863,
|
80 |
+
"rewards/accuracies": 0.6416667103767395,
|
81 |
+
"rewards/chosen": 0.001075960579328239,
|
82 |
+
"rewards/margins": 0.0015331318136304617,
|
83 |
+
"rewards/rejected": -0.0004571711760945618,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.03924646781789639,
|
88 |
+
"grad_norm": 0.03082303956618271,
|
89 |
+
"learning_rate": 1.9531249999999998e-07,
|
90 |
+
"logits/chosen": 6431.498046875,
|
91 |
+
"logits/rejected": 5048.09912109375,
|
92 |
+
"logps/chosen": -0.7465437650680542,
|
93 |
+
"logps/rejected": -0.8175977468490601,
|
94 |
+
"loss": 1.3863,
|
95 |
+
"rewards/accuracies": 0.75,
|
96 |
+
"rewards/chosen": 0.0019261162960901856,
|
97 |
+
"rewards/margins": 0.004134190734475851,
|
98 |
+
"rewards/rejected": -0.0022080740891397,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04709576138147567,
|
103 |
+
"grad_norm": 0.029348201524489196,
|
104 |
+
"learning_rate": 2.3437499999999998e-07,
|
105 |
+
"logits/chosen": 5498.6728515625,
|
106 |
+
"logits/rejected": 4572.8447265625,
|
107 |
+
"logps/chosen": -0.684872567653656,
|
108 |
+
"logps/rejected": -0.8479803800582886,
|
109 |
+
"loss": 1.3863,
|
110 |
+
"rewards/accuracies": 0.699999988079071,
|
111 |
+
"rewards/chosen": 0.002722438657656312,
|
112 |
+
"rewards/margins": 0.006867048796266317,
|
113 |
+
"rewards/rejected": -0.004144609440118074,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.054945054945054944,
|
118 |
+
"grad_norm": 0.029933985172415266,
|
119 |
+
"learning_rate": 2.734375e-07,
|
120 |
+
"logits/chosen": 5221.7255859375,
|
121 |
+
"logits/rejected": 4945.2509765625,
|
122 |
+
"logps/chosen": -0.6324489116668701,
|
123 |
+
"logps/rejected": -0.7256419658660889,
|
124 |
+
"loss": 1.3863,
|
125 |
+
"rewards/accuracies": 0.675000011920929,
|
126 |
+
"rewards/chosen": 0.003583890153095126,
|
127 |
+
"rewards/margins": 0.01209492888301611,
|
128 |
+
"rewards/rejected": -0.008511039428412914,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.06279434850863422,
|
133 |
+
"grad_norm": 0.0421303895483361,
|
134 |
+
"learning_rate": 3.1249999999999997e-07,
|
135 |
+
"logits/chosen": 5823.1435546875,
|
136 |
+
"logits/rejected": 5312.83642578125,
|
137 |
+
"logps/chosen": -0.6347643733024597,
|
138 |
+
"logps/rejected": -0.7057794332504272,
|
139 |
+
"loss": 1.3862,
|
140 |
+
"rewards/accuracies": 0.6166667342185974,
|
141 |
+
"rewards/chosen": -0.005841313861310482,
|
142 |
+
"rewards/margins": 0.016323894262313843,
|
143 |
+
"rewards/rejected": -0.02216520719230175,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0706436420722135,
|
148 |
+
"grad_norm": 0.052609413699091494,
|
149 |
+
"learning_rate": 3.5156249999999997e-07,
|
150 |
+
"logits/chosen": 6123.3955078125,
|
151 |
+
"logits/rejected": 5257.037109375,
|
152 |
+
"logps/chosen": -0.6579065322875977,
|
153 |
+
"logps/rejected": -0.7939826846122742,
|
154 |
+
"loss": 1.3862,
|
155 |
+
"rewards/accuracies": 0.7583333253860474,
|
156 |
+
"rewards/chosen": -0.019795957952737808,
|
157 |
+
"rewards/margins": 0.05933200195431709,
|
158 |
+
"rewards/rejected": -0.0791279524564743,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07849293563579278,
|
163 |
+
"grad_norm": 0.06474882431499306,
|
164 |
+
"learning_rate": 3.9062499999999997e-07,
|
165 |
+
"logits/chosen": 6086.119140625,
|
166 |
+
"logits/rejected": 5854.5458984375,
|
167 |
+
"logps/chosen": -0.7721215486526489,
|
168 |
+
"logps/rejected": -0.9403657913208008,
|
169 |
+
"loss": 1.386,
|
170 |
+
"rewards/accuracies": 0.6500000953674316,
|
171 |
+
"rewards/chosen": -0.11592841148376465,
|
172 |
+
"rewards/margins": 0.09634516388177872,
|
173 |
+
"rewards/rejected": -0.21227355301380157,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08634222919937205,
|
178 |
+
"grad_norm": 0.2514412569708036,
|
179 |
+
"learning_rate": 4.2968749999999996e-07,
|
180 |
+
"logits/chosen": 6355.8857421875,
|
181 |
+
"logits/rejected": 5154.1103515625,
|
182 |
+
"logps/chosen": -1.2314940690994263,
|
183 |
+
"logps/rejected": -1.771580696105957,
|
184 |
+
"loss": 1.3853,
|
185 |
+
"rewards/accuracies": 0.7083333730697632,
|
186 |
+
"rewards/chosen": -0.6742404699325562,
|
187 |
+
"rewards/margins": 0.3862757086753845,
|
188 |
+
"rewards/rejected": -1.0605162382125854,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.09419152276295134,
|
193 |
+
"grad_norm": 0.4065982432993292,
|
194 |
+
"learning_rate": 4.6874999999999996e-07,
|
195 |
+
"logits/chosen": 5716.19189453125,
|
196 |
+
"logits/rejected": 4568.13134765625,
|
197 |
+
"logps/chosen": -3.0005619525909424,
|
198 |
+
"logps/rejected": -4.118376731872559,
|
199 |
+
"loss": 1.3839,
|
200 |
+
"rewards/accuracies": 0.6333333253860474,
|
201 |
+
"rewards/chosen": -2.4058868885040283,
|
202 |
+
"rewards/margins": 0.977187991142273,
|
203 |
+
"rewards/rejected": -3.3830745220184326,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.10204081632653061,
|
208 |
+
"grad_norm": 0.6207662485091842,
|
209 |
+
"learning_rate": 4.999962424962166e-07,
|
210 |
+
"logits/chosen": 6246.6572265625,
|
211 |
+
"logits/rejected": 5490.064453125,
|
212 |
+
"logps/chosen": -4.607759475708008,
|
213 |
+
"logps/rejected": -6.540151119232178,
|
214 |
+
"loss": 1.3829,
|
215 |
+
"rewards/accuracies": 0.6916666626930237,
|
216 |
+
"rewards/chosen": -4.007367134094238,
|
217 |
+
"rewards/margins": 1.8176984786987305,
|
218 |
+
"rewards/rejected": -5.825065612792969,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.10989010989010989,
|
223 |
+
"grad_norm": 1.6726707215948637,
|
224 |
+
"learning_rate": 4.998647417232375e-07,
|
225 |
+
"logits/chosen": 6259.673828125,
|
226 |
+
"logits/rejected": 5075.4140625,
|
227 |
+
"logps/chosen": -6.643527984619141,
|
228 |
+
"logps/rejected": -9.528350830078125,
|
229 |
+
"loss": 1.3806,
|
230 |
+
"rewards/accuracies": 0.6416667103767395,
|
231 |
+
"rewards/chosen": -6.045531272888184,
|
232 |
+
"rewards/margins": 2.7727363109588623,
|
233 |
+
"rewards/rejected": -8.818267822265625,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.11773940345368916,
|
238 |
+
"grad_norm": 1.8074740604257467,
|
239 |
+
"learning_rate": 4.995454786965036e-07,
|
240 |
+
"logits/chosen": 6712.15234375,
|
241 |
+
"logits/rejected": 5173.9384765625,
|
242 |
+
"logps/chosen": -5.438518047332764,
|
243 |
+
"logps/rejected": -10.787275314331055,
|
244 |
+
"loss": 1.3787,
|
245 |
+
"rewards/accuracies": 0.6583333015441895,
|
246 |
+
"rewards/chosen": -4.854126453399658,
|
247 |
+
"rewards/margins": 5.265545845031738,
|
248 |
+
"rewards/rejected": -10.119672775268555,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.12558869701726844,
|
253 |
+
"grad_norm": 3.1308973590524034,
|
254 |
+
"learning_rate": 4.990386933279972e-07,
|
255 |
+
"logits/chosen": 5863.80517578125,
|
256 |
+
"logits/rejected": 4384.7138671875,
|
257 |
+
"logps/chosen": -9.97611141204834,
|
258 |
+
"logps/rejected": -14.926114082336426,
|
259 |
+
"loss": 1.3759,
|
260 |
+
"rewards/accuracies": 0.6666666865348816,
|
261 |
+
"rewards/chosen": -9.367152214050293,
|
262 |
+
"rewards/margins": 4.869722843170166,
|
263 |
+
"rewards/rejected": -14.236875534057617,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.13343799058084774,
|
268 |
+
"grad_norm": 4.1177149352808,
|
269 |
+
"learning_rate": 4.983447664444096e-07,
|
270 |
+
"logits/chosen": 6553.7626953125,
|
271 |
+
"logits/rejected": 5106.4052734375,
|
272 |
+
"logps/chosen": -12.286310195922852,
|
273 |
+
"logps/rejected": -20.12063980102539,
|
274 |
+
"loss": 1.3774,
|
275 |
+
"rewards/accuracies": 0.6499999761581421,
|
276 |
+
"rewards/chosen": -11.659884452819824,
|
277 |
+
"rewards/margins": 7.752722263336182,
|
278 |
+
"rewards/rejected": -19.412609100341797,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.141287284144427,
|
283 |
+
"grad_norm": 3.8730928565663554,
|
284 |
+
"learning_rate": 4.97464219500968e-07,
|
285 |
+
"logits/chosen": 5846.3642578125,
|
286 |
+
"logits/rejected": 4395.67578125,
|
287 |
+
"logps/chosen": -6.325826644897461,
|
288 |
+
"logps/rejected": -14.793339729309082,
|
289 |
+
"loss": 1.3709,
|
290 |
+
"rewards/accuracies": 0.6666666269302368,
|
291 |
+
"rewards/chosen": -5.696617603302002,
|
292 |
+
"rewards/margins": 8.336694717407227,
|
293 |
+
"rewards/rejected": -14.03331184387207,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.14913657770800628,
|
298 |
+
"grad_norm": 6.602624193673466,
|
299 |
+
"learning_rate": 4.963977141895843e-07,
|
300 |
+
"logits/chosen": 5749.099609375,
|
301 |
+
"logits/rejected": 4122.6748046875,
|
302 |
+
"logps/chosen": -13.3460111618042,
|
303 |
+
"logps/rejected": -30.625717163085938,
|
304 |
+
"loss": 1.3673,
|
305 |
+
"rewards/accuracies": 0.8083332777023315,
|
306 |
+
"rewards/chosen": -12.694738388061523,
|
307 |
+
"rewards/margins": 17.16573143005371,
|
308 |
+
"rewards/rejected": -29.860469818115234,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.15698587127158556,
|
313 |
+
"grad_norm": 5.197411313874128,
|
314 |
+
"learning_rate": 4.951460519416227e-07,
|
315 |
+
"logits/chosen": 6093.1865234375,
|
316 |
+
"logits/rejected": 4876.7451171875,
|
317 |
+
"logps/chosen": -9.102602005004883,
|
318 |
+
"logps/rejected": -26.314044952392578,
|
319 |
+
"loss": 1.3625,
|
320 |
+
"rewards/accuracies": 0.7583333849906921,
|
321 |
+
"rewards/chosen": -8.488224983215332,
|
322 |
+
"rewards/margins": 17.09214210510254,
|
323 |
+
"rewards/rejected": -25.580366134643555,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16483516483516483,
|
328 |
+
"grad_norm": 9.618320681230124,
|
329 |
+
"learning_rate": 4.937101733256606e-07,
|
330 |
+
"logits/chosen": 5406.921875,
|
331 |
+
"logits/rejected": 4192.8603515625,
|
332 |
+
"logps/chosen": -14.340167045593262,
|
333 |
+
"logps/rejected": -33.15205383300781,
|
334 |
+
"loss": 1.357,
|
335 |
+
"rewards/accuracies": 0.6333333253860474,
|
336 |
+
"rewards/chosen": -13.77330207824707,
|
337 |
+
"rewards/margins": 18.675561904907227,
|
338 |
+
"rewards/rejected": -32.44886016845703,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.1726844583987441,
|
343 |
+
"grad_norm": 7.375553630744227,
|
344 |
+
"learning_rate": 4.920911573406924e-07,
|
345 |
+
"logits/chosen": 6773.37255859375,
|
346 |
+
"logits/rejected": 5361.48046875,
|
347 |
+
"logps/chosen": -11.12817668914795,
|
348 |
+
"logps/rejected": -28.294403076171875,
|
349 |
+
"loss": 1.3615,
|
350 |
+
"rewards/accuracies": 0.7166666388511658,
|
351 |
+
"rewards/chosen": -10.548368453979492,
|
352 |
+
"rewards/margins": 17.09095573425293,
|
353 |
+
"rewards/rejected": -27.639324188232422,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.18053375196232338,
|
358 |
+
"grad_norm": 8.615349191502917,
|
359 |
+
"learning_rate": 4.902902206053098e-07,
|
360 |
+
"logits/chosen": 5996.9853515625,
|
361 |
+
"logits/rejected": 4782.43798828125,
|
362 |
+
"logps/chosen": -18.20733070373535,
|
363 |
+
"logps/rejected": -41.948974609375,
|
364 |
+
"loss": 1.3626,
|
365 |
+
"rewards/accuracies": 0.7166666984558105,
|
366 |
+
"rewards/chosen": -17.62150001525879,
|
367 |
+
"rewards/margins": 23.599395751953125,
|
368 |
+
"rewards/rejected": -41.22089385986328,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.18838304552590268,
|
373 |
+
"grad_norm": 6.3641054961132175,
|
374 |
+
"learning_rate": 4.883087164434672e-07,
|
375 |
+
"logits/chosen": 5568.8056640625,
|
376 |
+
"logits/rejected": 3895.72412109375,
|
377 |
+
"logps/chosen": -7.421477317810059,
|
378 |
+
"logps/rejected": -30.459941864013672,
|
379 |
+
"loss": 1.3562,
|
380 |
+
"rewards/accuracies": 0.7583333253860474,
|
381 |
+
"rewards/chosen": -6.827574729919434,
|
382 |
+
"rewards/margins": 22.909481048583984,
|
383 |
+
"rewards/rejected": -29.7370548248291,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.19623233908948196,
|
388 |
+
"grad_norm": 25.511536310895185,
|
389 |
+
"learning_rate": 4.861481338675183e-07,
|
390 |
+
"logits/chosen": 6335.380859375,
|
391 |
+
"logits/rejected": 4804.142578125,
|
392 |
+
"logps/chosen": -14.736673355102539,
|
393 |
+
"logps/rejected": -40.67548370361328,
|
394 |
+
"loss": 1.3621,
|
395 |
+
"rewards/accuracies": 0.6666666269302368,
|
396 |
+
"rewards/chosen": -14.16309642791748,
|
397 |
+
"rewards/margins": 25.803043365478516,
|
398 |
+
"rewards/rejected": -39.96613693237305,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.20408163265306123,
|
403 |
+
"grad_norm": 8.643358672198618,
|
404 |
+
"learning_rate": 4.838100964592904e-07,
|
405 |
+
"logits/chosen": 6742.24365234375,
|
406 |
+
"logits/rejected": 5024.3515625,
|
407 |
+
"logps/chosen": -8.986857414245605,
|
408 |
+
"logps/rejected": -24.885251998901367,
|
409 |
+
"loss": 1.3711,
|
410 |
+
"rewards/accuracies": 0.7083333730697632,
|
411 |
+
"rewards/chosen": -8.32063102722168,
|
412 |
+
"rewards/margins": 15.831449508666992,
|
413 |
+
"rewards/rejected": -24.152080535888672,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2119309262166405,
|
418 |
+
"grad_norm": 6.0870160275581044,
|
419 |
+
"learning_rate": 4.812963611500339e-07,
|
420 |
+
"logits/chosen": 6522.9189453125,
|
421 |
+
"logits/rejected": 5658.826171875,
|
422 |
+
"logps/chosen": -11.388198852539062,
|
423 |
+
"logps/rejected": -31.324010848999023,
|
424 |
+
"loss": 1.3595,
|
425 |
+
"rewards/accuracies": 0.7083333134651184,
|
426 |
+
"rewards/chosen": -10.788042068481445,
|
427 |
+
"rewards/margins": 19.862857818603516,
|
428 |
+
"rewards/rejected": -30.650897979736328,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.21978021978021978,
|
433 |
+
"grad_norm": 8.557241921021467,
|
434 |
+
"learning_rate": 4.786088169001671e-07,
|
435 |
+
"logits/chosen": 5661.5009765625,
|
436 |
+
"logits/rejected": 4401.69482421875,
|
437 |
+
"logps/chosen": -8.053993225097656,
|
438 |
+
"logps/rejected": -32.422542572021484,
|
439 |
+
"loss": 1.3579,
|
440 |
+
"rewards/accuracies": 0.7166666984558105,
|
441 |
+
"rewards/chosen": -7.461718559265137,
|
442 |
+
"rewards/margins": 24.201175689697266,
|
443 |
+
"rewards/rejected": -31.662893295288086,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.22762951334379905,
|
448 |
+
"grad_norm": 9.481317515747005,
|
449 |
+
"learning_rate": 4.7574948327980567e-07,
|
450 |
+
"logits/chosen": 7745.7158203125,
|
451 |
+
"logits/rejected": 4650.02880859375,
|
452 |
+
"logps/chosen": -12.464855194091797,
|
453 |
+
"logps/rejected": -40.86915969848633,
|
454 |
+
"loss": 1.3604,
|
455 |
+
"rewards/accuracies": 0.7749999761581421,
|
456 |
+
"rewards/chosen": -11.852567672729492,
|
457 |
+
"rewards/margins": 28.29081153869629,
|
458 |
+
"rewards/rejected": -40.14337921142578,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.23547880690737832,
|
463 |
+
"grad_norm": 8.835805617844823,
|
464 |
+
"learning_rate": 4.727205089511466e-07,
|
465 |
+
"logits/chosen": 5531.8173828125,
|
466 |
+
"logits/rejected": 4774.9970703125,
|
467 |
+
"logps/chosen": -10.429524421691895,
|
468 |
+
"logps/rejected": -26.804691314697266,
|
469 |
+
"loss": 1.3651,
|
470 |
+
"rewards/accuracies": 0.6916666626930237,
|
471 |
+
"rewards/chosen": -9.819427490234375,
|
472 |
+
"rewards/margins": 16.315807342529297,
|
473 |
+
"rewards/rejected": -26.13523292541504,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.24332810047095763,
|
478 |
+
"grad_norm": 15.454604782065125,
|
479 |
+
"learning_rate": 4.6952417005384247e-07,
|
480 |
+
"logits/chosen": 6384.7763671875,
|
481 |
+
"logits/rejected": 5284.7490234375,
|
482 |
+
"logps/chosen": -7.295445442199707,
|
483 |
+
"logps/rejected": -19.249813079833984,
|
484 |
+
"loss": 1.3664,
|
485 |
+
"rewards/accuracies": 0.7083333730697632,
|
486 |
+
"rewards/chosen": -6.720705509185791,
|
487 |
+
"rewards/margins": 11.84199333190918,
|
488 |
+
"rewards/rejected": -18.56269645690918,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.25117739403453687,
|
493 |
+
"grad_norm": 11.201402261813897,
|
494 |
+
"learning_rate": 4.661628684945851e-07,
|
495 |
+
"logits/chosen": 6445.9931640625,
|
496 |
+
"logits/rejected": 4742.51123046875,
|
497 |
+
"logps/chosen": -10.060206413269043,
|
498 |
+
"logps/rejected": -35.663307189941406,
|
499 |
+
"loss": 1.3585,
|
500 |
+
"rewards/accuracies": 0.675000011920929,
|
501 |
+
"rewards/chosen": -9.450899124145508,
|
502 |
+
"rewards/margins": 25.444076538085938,
|
503 |
+
"rewards/rejected": -34.89497375488281,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.25902668759811615,
|
508 |
+
"grad_norm": 14.088756180907868,
|
509 |
+
"learning_rate": 4.626391301421782e-07,
|
510 |
+
"logits/chosen": 6144.3173828125,
|
511 |
+
"logits/rejected": 5099.60986328125,
|
512 |
+
"logps/chosen": -11.769998550415039,
|
513 |
+
"logps/rejected": -26.48116683959961,
|
514 |
+
"loss": 1.3667,
|
515 |
+
"rewards/accuracies": 0.6833333373069763,
|
516 |
+
"rewards/chosen": -11.127023696899414,
|
517 |
+
"rewards/margins": 14.672645568847656,
|
518 |
+
"rewards/rejected": -25.799671173095703,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.2668759811616955,
|
523 |
+
"grad_norm": 7.090474377137257,
|
524 |
+
"learning_rate": 4.5895560292945996e-07,
|
525 |
+
"logits/chosen": 6591.3095703125,
|
526 |
+
"logits/rejected": 6281.44970703125,
|
527 |
+
"logps/chosen": -8.332866668701172,
|
528 |
+
"logps/rejected": -23.061569213867188,
|
529 |
+
"loss": 1.3574,
|
530 |
+
"rewards/accuracies": 0.7083333730697632,
|
531 |
+
"rewards/chosen": -7.750649929046631,
|
532 |
+
"rewards/margins": 14.612638473510742,
|
533 |
+
"rewards/rejected": -22.3632869720459,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.27472527472527475,
|
538 |
+
"grad_norm": 11.8517335767745,
|
539 |
+
"learning_rate": 4.5511505486349865e-07,
|
540 |
+
"logits/chosen": 6811.2880859375,
|
541 |
+
"logits/rejected": 5612.2724609375,
|
542 |
+
"logps/chosen": -12.734210014343262,
|
543 |
+
"logps/rejected": -46.445518493652344,
|
544 |
+
"loss": 1.3473,
|
545 |
+
"rewards/accuracies": 0.7249999642372131,
|
546 |
+
"rewards/chosen": -12.119455337524414,
|
547 |
+
"rewards/margins": 33.59000015258789,
|
548 |
+
"rewards/rejected": -45.70945358276367,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.282574568288854,
|
553 |
+
"grad_norm": 17.10556818380673,
|
554 |
+
"learning_rate": 4.5112037194555876e-07,
|
555 |
+
"logits/chosen": 6228.7158203125,
|
556 |
+
"logits/rejected": 5359.6708984375,
|
557 |
+
"logps/chosen": -16.61972999572754,
|
558 |
+
"logps/rejected": -51.56354522705078,
|
559 |
+
"loss": 1.3582,
|
560 |
+
"rewards/accuracies": 0.7500000596046448,
|
561 |
+
"rewards/chosen": -16.05486488342285,
|
562 |
+
"rewards/margins": 34.75627517700195,
|
563 |
+
"rewards/rejected": -50.81113815307617,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2904238618524333,
|
568 |
+
"grad_norm": 12.277205892634896,
|
569 |
+
"learning_rate": 4.4697455600239863e-07,
|
570 |
+
"logits/chosen": 5767.1728515625,
|
571 |
+
"logits/rejected": 5032.4482421875,
|
572 |
+
"logps/chosen": -8.446660041809082,
|
573 |
+
"logps/rejected": -22.16537857055664,
|
574 |
+
"loss": 1.3678,
|
575 |
+
"rewards/accuracies": 0.625,
|
576 |
+
"rewards/chosen": -7.765728950500488,
|
577 |
+
"rewards/margins": 13.689413070678711,
|
578 |
+
"rewards/rejected": -21.455141067504883,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.29827315541601257,
|
583 |
+
"grad_norm": 18.240138504142248,
|
584 |
+
"learning_rate": 4.426807224305315e-07,
|
585 |
+
"logits/chosen": 7020.58203125,
|
586 |
+
"logits/rejected": 4838.7958984375,
|
587 |
+
"logps/chosen": -8.1710205078125,
|
588 |
+
"logps/rejected": -42.699180603027344,
|
589 |
+
"loss": 1.36,
|
590 |
+
"rewards/accuracies": 0.7666667103767395,
|
591 |
+
"rewards/chosen": -7.526429653167725,
|
592 |
+
"rewards/margins": 34.454978942871094,
|
593 |
+
"rewards/rejected": -41.98141098022461,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.30612244897959184,
|
598 |
+
"grad_norm": 9.573222554347216,
|
599 |
+
"learning_rate": 4.3824209785514326e-07,
|
600 |
+
"logits/chosen": 6994.20703125,
|
601 |
+
"logits/rejected": 4667.099609375,
|
602 |
+
"logps/chosen": -10.061126708984375,
|
603 |
+
"logps/rejected": -38.28179168701172,
|
604 |
+
"loss": 1.354,
|
605 |
+
"rewards/accuracies": 0.6916667222976685,
|
606 |
+
"rewards/chosen": -9.435959815979004,
|
607 |
+
"rewards/margins": 28.09332847595215,
|
608 |
+
"rewards/rejected": -37.52928924560547,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.3139717425431711,
|
613 |
+
"grad_norm": 6.6100886548986475,
|
614 |
+
"learning_rate": 4.3366201770542687e-07,
|
615 |
+
"logits/chosen": 5962.6591796875,
|
616 |
+
"logits/rejected": 5447.56884765625,
|
617 |
+
"logps/chosen": -10.098733901977539,
|
618 |
+
"logps/rejected": -31.517467498779297,
|
619 |
+
"loss": 1.3655,
|
620 |
+
"rewards/accuracies": 0.7249999642372131,
|
621 |
+
"rewards/chosen": -9.449263572692871,
|
622 |
+
"rewards/margins": 21.30449867248535,
|
623 |
+
"rewards/rejected": -30.753765106201172,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.3218210361067504,
|
628 |
+
"grad_norm": 30.548099506436554,
|
629 |
+
"learning_rate": 4.2894392370815567e-07,
|
630 |
+
"logits/chosen": 6273.9775390625,
|
631 |
+
"logits/rejected": 4478.13330078125,
|
632 |
+
"logps/chosen": -14.873064041137695,
|
633 |
+
"logps/rejected": -59.72370147705078,
|
634 |
+
"loss": 1.3447,
|
635 |
+
"rewards/accuracies": 0.7583333253860474,
|
636 |
+
"rewards/chosen": -14.206558227539062,
|
637 |
+
"rewards/margins": 44.70840072631836,
|
638 |
+
"rewards/rejected": -58.91496658325195,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.32967032967032966,
|
643 |
+
"grad_norm": 11.996768365493867,
|
644 |
+
"learning_rate": 4.2409136130137845e-07,
|
645 |
+
"logits/chosen": 5747.73681640625,
|
646 |
+
"logits/rejected": 4370.01708984375,
|
647 |
+
"logps/chosen": -21.314987182617188,
|
648 |
+
"logps/rejected": -54.006263732910156,
|
649 |
+
"loss": 1.3593,
|
650 |
+
"rewards/accuracies": 0.699999988079071,
|
651 |
+
"rewards/chosen": -20.65334701538086,
|
652 |
+
"rewards/margins": 32.607086181640625,
|
653 |
+
"rewards/rejected": -53.26043701171875,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.33751962323390894,
|
658 |
+
"grad_norm": 10.590905912907617,
|
659 |
+
"learning_rate": 4.1910797697018017e-07,
|
660 |
+
"logits/chosen": 5875.6357421875,
|
661 |
+
"logits/rejected": 4011.819091796875,
|
662 |
+
"logps/chosen": -11.717180252075195,
|
663 |
+
"logps/rejected": -46.7780647277832,
|
664 |
+
"loss": 1.3438,
|
665 |
+
"rewards/accuracies": 0.7916666865348816,
|
666 |
+
"rewards/chosen": -11.10181999206543,
|
667 |
+
"rewards/margins": 34.92017364501953,
|
668 |
+
"rewards/rejected": -46.02199172973633,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3453689167974882,
|
673 |
+
"grad_norm": 14.453344590210275,
|
674 |
+
"learning_rate": 4.1399751550651084e-07,
|
675 |
+
"logits/chosen": 6271.8125,
|
676 |
+
"logits/rejected": 5575.626953125,
|
677 |
+
"logps/chosen": -13.031234741210938,
|
678 |
+
"logps/rejected": -36.1110725402832,
|
679 |
+
"loss": 1.3582,
|
680 |
+
"rewards/accuracies": 0.7250000238418579,
|
681 |
+
"rewards/chosen": -12.423306465148926,
|
682 |
+
"rewards/margins": 22.96180534362793,
|
683 |
+
"rewards/rejected": -35.385108947753906,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3532182103610675,
|
688 |
+
"grad_norm": 11.608919477063516,
|
689 |
+
"learning_rate": 4.087638171951401e-07,
|
690 |
+
"logits/chosen": 7476.86572265625,
|
691 |
+
"logits/rejected": 4706.1162109375,
|
692 |
+
"logps/chosen": -6.023161888122559,
|
693 |
+
"logps/rejected": -37.36185836791992,
|
694 |
+
"loss": 1.3562,
|
695 |
+
"rewards/accuracies": 0.7749999761581421,
|
696 |
+
"rewards/chosen": -5.43270206451416,
|
697 |
+
"rewards/margins": 31.197275161743164,
|
698 |
+
"rewards/rejected": -36.629974365234375,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.36106750392464676,
|
703 |
+
"grad_norm": 26.28345054484464,
|
704 |
+
"learning_rate": 4.034108149278543e-07,
|
705 |
+
"logits/chosen": 7570.7451171875,
|
706 |
+
"logits/rejected": 5338.115234375,
|
707 |
+
"logps/chosen": -12.235418319702148,
|
708 |
+
"logps/rejected": -36.413673400878906,
|
709 |
+
"loss": 1.3609,
|
710 |
+
"rewards/accuracies": 0.7916667461395264,
|
711 |
+
"rewards/chosen": -11.572993278503418,
|
712 |
+
"rewards/margins": 24.130626678466797,
|
713 |
+
"rewards/rejected": -35.70362091064453,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.36891679748822603,
|
718 |
+
"grad_norm": 9.755625997424268,
|
719 |
+
"learning_rate": 3.979425312480629e-07,
|
720 |
+
"logits/chosen": 6442.072265625,
|
721 |
+
"logits/rejected": 5090.69287109375,
|
722 |
+
"logps/chosen": -11.879281997680664,
|
723 |
+
"logps/rejected": -36.57582092285156,
|
724 |
+
"loss": 1.3581,
|
725 |
+
"rewards/accuracies": 0.7749999761581421,
|
726 |
+
"rewards/chosen": -11.22594165802002,
|
727 |
+
"rewards/margins": 24.602800369262695,
|
728 |
+
"rewards/rejected": -35.82874298095703,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.37676609105180536,
|
733 |
+
"grad_norm": 13.488032723757092,
|
734 |
+
"learning_rate": 3.923630753280357e-07,
|
735 |
+
"logits/chosen": 7082.0048828125,
|
736 |
+
"logits/rejected": 5317.03369140625,
|
737 |
+
"logps/chosen": -10.345157623291016,
|
738 |
+
"logps/rejected": -40.309444427490234,
|
739 |
+
"loss": 1.3518,
|
740 |
+
"rewards/accuracies": 0.7916667461395264,
|
741 |
+
"rewards/chosen": -9.730131149291992,
|
742 |
+
"rewards/margins": 29.90970230102539,
|
743 |
+
"rewards/rejected": -39.63983154296875,
|
744 |
+
"step": 480
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.38461538461538464,
|
748 |
+
"grad_norm": 10.81857496627396,
|
749 |
+
"learning_rate": 3.866766398810424e-07,
|
750 |
+
"logits/chosen": 6680.68359375,
|
751 |
+
"logits/rejected": 5265.3974609375,
|
752 |
+
"logps/chosen": -9.079381942749023,
|
753 |
+
"logps/rejected": -47.32402801513672,
|
754 |
+
"loss": 1.3498,
|
755 |
+
"rewards/accuracies": 0.7666667103767395,
|
756 |
+
"rewards/chosen": -8.535429954528809,
|
757 |
+
"rewards/margins": 38.05257034301758,
|
758 |
+
"rewards/rejected": -46.58799743652344,
|
759 |
+
"step": 490
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.3924646781789639,
|
763 |
+
"grad_norm": 8.225268327717496,
|
764 |
+
"learning_rate": 3.8088749801071496e-07,
|
765 |
+
"logits/chosen": 6926.06640625,
|
766 |
+
"logits/rejected": 4467.6005859375,
|
767 |
+
"logps/chosen": -18.076974868774414,
|
768 |
+
"logps/rejected": -52.8994255065918,
|
769 |
+
"loss": 1.3522,
|
770 |
+
"rewards/accuracies": 0.6916666626930237,
|
771 |
+
"rewards/chosen": -17.428617477416992,
|
772 |
+
"rewards/margins": 34.659934997558594,
|
773 |
+
"rewards/rejected": -52.08855056762695,
|
774 |
+
"step": 500
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4003139717425432,
|
778 |
+
"grad_norm": 8.403224575968139,
|
779 |
+
"learning_rate": 3.75e-07,
|
780 |
+
"logits/chosen": 5711.43994140625,
|
781 |
+
"logits/rejected": 4712.4541015625,
|
782 |
+
"logps/chosen": -10.59355640411377,
|
783 |
+
"logps/rejected": -28.433752059936523,
|
784 |
+
"loss": 1.357,
|
785 |
+
"rewards/accuracies": 0.7416666746139526,
|
786 |
+
"rewards/chosen": -9.983890533447266,
|
787 |
+
"rewards/margins": 17.735435485839844,
|
788 |
+
"rewards/rejected": -27.719324111938477,
|
789 |
+
"step": 510
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.40816326530612246,
|
793 |
+
"grad_norm": 7.859662724135296,
|
794 |
+
"learning_rate": 3.6901857004211443e-07,
|
795 |
+
"logits/chosen": 6058.2236328125,
|
796 |
+
"logits/rejected": 5172.513671875,
|
797 |
+
"logps/chosen": -9.832149505615234,
|
798 |
+
"logps/rejected": -27.763540267944336,
|
799 |
+
"loss": 1.3672,
|
800 |
+
"rewards/accuracies": 0.7083333730697632,
|
801 |
+
"rewards/chosen": -9.129549980163574,
|
802 |
+
"rewards/margins": 17.810230255126953,
|
803 |
+
"rewards/rejected": -26.93977928161621,
|
804 |
+
"step": 520
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.41601255886970173,
|
808 |
+
"grad_norm": 13.018474920832832,
|
809 |
+
"learning_rate": 3.6294770291596076e-07,
|
810 |
+
"logits/chosen": 6869.9970703125,
|
811 |
+
"logits/rejected": 5111.6474609375,
|
812 |
+
"logps/chosen": -6.732565879821777,
|
813 |
+
"logps/rejected": -25.002674102783203,
|
814 |
+
"loss": 1.3553,
|
815 |
+
"rewards/accuracies": 0.6833333373069763,
|
816 |
+
"rewards/chosen": -6.134089469909668,
|
817 |
+
"rewards/margins": 18.133365631103516,
|
818 |
+
"rewards/rejected": -24.2674560546875,
|
819 |
+
"step": 530
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.423861852433281,
|
823 |
+
"grad_norm": 17.461930895857275,
|
824 |
+
"learning_rate": 3.5679196060850034e-07,
|
825 |
+
"logits/chosen": 6209.1474609375,
|
826 |
+
"logits/rejected": 4489.95556640625,
|
827 |
+
"logps/chosen": -17.81626319885254,
|
828 |
+
"logps/rejected": -52.312652587890625,
|
829 |
+
"loss": 1.3616,
|
830 |
+
"rewards/accuracies": 0.7416666746139526,
|
831 |
+
"rewards/chosen": -17.198108673095703,
|
832 |
+
"rewards/margins": 34.41394805908203,
|
833 |
+
"rewards/rejected": -51.61205291748047,
|
834 |
+
"step": 540
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.4317111459968603,
|
838 |
+
"grad_norm": 14.537248039469688,
|
839 |
+
"learning_rate": 3.505559688866229e-07,
|
840 |
+
"logits/chosen": 6301.17724609375,
|
841 |
+
"logits/rejected": 4744.8837890625,
|
842 |
+
"logps/chosen": -10.278491973876953,
|
843 |
+
"logps/rejected": -44.104400634765625,
|
844 |
+
"loss": 1.3482,
|
845 |
+
"rewards/accuracies": 0.7750000357627869,
|
846 |
+
"rewards/chosen": -9.643937110900879,
|
847 |
+
"rewards/margins": 33.664276123046875,
|
848 |
+
"rewards/rejected": -43.30820846557617,
|
849 |
+
"step": 550
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.43956043956043955,
|
853 |
+
"grad_norm": 12.121639720486284,
|
854 |
+
"learning_rate": 3.4424441382108826e-07,
|
855 |
+
"logits/chosen": 5940.2646484375,
|
856 |
+
"logits/rejected": 5123.6513671875,
|
857 |
+
"logps/chosen": -16.82316017150879,
|
858 |
+
"logps/rejected": -34.89044952392578,
|
859 |
+
"loss": 1.3679,
|
860 |
+
"rewards/accuracies": 0.6499999761581421,
|
861 |
+
"rewards/chosen": -16.180652618408203,
|
862 |
+
"rewards/margins": 17.98758316040039,
|
863 |
+
"rewards/rejected": -34.168235778808594,
|
864 |
+
"step": 560
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.4474097331240188,
|
868 |
+
"grad_norm": 9.643273866165796,
|
869 |
+
"learning_rate": 3.378620382651523e-07,
|
870 |
+
"logits/chosen": 6564.9365234375,
|
871 |
+
"logits/rejected": 5344.296875,
|
872 |
+
"logps/chosen": -11.590880393981934,
|
873 |
+
"logps/rejected": -38.3111572265625,
|
874 |
+
"loss": 1.3495,
|
875 |
+
"rewards/accuracies": 0.716666579246521,
|
876 |
+
"rewards/chosen": -10.887467384338379,
|
877 |
+
"rewards/margins": 26.603397369384766,
|
878 |
+
"rewards/rejected": -37.49085998535156,
|
879 |
+
"step": 570
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4552590266875981,
|
883 |
+
"grad_norm": 9.384348098391655,
|
884 |
+
"learning_rate": 3.314136382905234e-07,
|
885 |
+
"logits/chosen": 6624.49072265625,
|
886 |
+
"logits/rejected": 4907.68212890625,
|
887 |
+
"logps/chosen": -9.338412284851074,
|
888 |
+
"logps/rejected": -45.03810119628906,
|
889 |
+
"loss": 1.3524,
|
890 |
+
"rewards/accuracies": 0.7916666269302368,
|
891 |
+
"rewards/chosen": -8.67926025390625,
|
892 |
+
"rewards/margins": 35.5770263671875,
|
893 |
+
"rewards/rejected": -44.25628662109375,
|
894 |
+
"step": 580
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.4631083202511774,
|
898 |
+
"grad_norm": 11.149480684566118,
|
899 |
+
"learning_rate": 3.249040595833274e-07,
|
900 |
+
"logits/chosen": 7035.4873046875,
|
901 |
+
"logits/rejected": 5026.8193359375,
|
902 |
+
"logps/chosen": -11.245471954345703,
|
903 |
+
"logps/rejected": -44.87081527709961,
|
904 |
+
"loss": 1.3472,
|
905 |
+
"rewards/accuracies": 0.7916666865348816,
|
906 |
+
"rewards/chosen": -10.6029691696167,
|
907 |
+
"rewards/margins": 33.520263671875,
|
908 |
+
"rewards/rejected": -44.123233795166016,
|
909 |
+
"step": 590
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.47095761381475665,
|
913 |
+
"grad_norm": 19.526133215761668,
|
914 |
+
"learning_rate": 3.1833819380279023e-07,
|
915 |
+
"logits/chosen": 6805.5771484375,
|
916 |
+
"logits/rejected": 5161.3935546875,
|
917 |
+
"logps/chosen": -8.982612609863281,
|
918 |
+
"logps/rejected": -35.16088104248047,
|
919 |
+
"loss": 1.3532,
|
920 |
+
"rewards/accuracies": 0.7750000357627869,
|
921 |
+
"rewards/chosen": -8.421594619750977,
|
922 |
+
"rewards/margins": 26.0313777923584,
|
923 |
+
"rewards/rejected": -34.45297622680664,
|
924 |
+
"step": 600
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.478806907378336,
|
928 |
+
"grad_norm": 11.018750446737162,
|
929 |
+
"learning_rate": 3.11720974905373e-07,
|
930 |
+
"logits/chosen": 6474.22900390625,
|
931 |
+
"logits/rejected": 5111.5498046875,
|
932 |
+
"logps/chosen": -11.592761993408203,
|
933 |
+
"logps/rejected": -42.404930114746094,
|
934 |
+
"loss": 1.3414,
|
935 |
+
"rewards/accuracies": 0.75,
|
936 |
+
"rewards/chosen": -10.948739051818848,
|
937 |
+
"rewards/margins": 30.717721939086914,
|
938 |
+
"rewards/rejected": -41.666465759277344,
|
939 |
+
"step": 610
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.48665620094191525,
|
943 |
+
"grad_norm": 8.775291118452293,
|
944 |
+
"learning_rate": 3.0505737543712275e-07,
|
945 |
+
"logits/chosen": 5456.4990234375,
|
946 |
+
"logits/rejected": 3857.27294921875,
|
947 |
+
"logps/chosen": -15.486307144165039,
|
948 |
+
"logps/rejected": -48.56859588623047,
|
949 |
+
"loss": 1.3521,
|
950 |
+
"rewards/accuracies": 0.7083333134651184,
|
951 |
+
"rewards/chosen": -14.838460922241211,
|
952 |
+
"rewards/margins": 32.94873809814453,
|
953 |
+
"rewards/rejected": -47.787193298339844,
|
954 |
+
"step": 620
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4945054945054945,
|
958 |
+
"grad_norm": 9.749208955925335,
|
959 |
+
"learning_rate": 2.9835240279702513e-07,
|
960 |
+
"logits/chosen": 7186.5859375,
|
961 |
+
"logits/rejected": 5223.5263671875,
|
962 |
+
"logps/chosen": -8.555147171020508,
|
963 |
+
"logps/rejected": -48.16273880004883,
|
964 |
+
"loss": 1.3394,
|
965 |
+
"rewards/accuracies": 0.7583333253860474,
|
966 |
+
"rewards/chosen": -7.907660007476807,
|
967 |
+
"rewards/margins": 39.55339813232422,
|
968 |
+
"rewards/rejected": -47.461055755615234,
|
969 |
+
"step": 630
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.5023547880690737,
|
973 |
+
"grad_norm": 10.872491616524146,
|
974 |
+
"learning_rate": 2.9161109547416667e-07,
|
975 |
+
"logits/chosen": 6674.87646484375,
|
976 |
+
"logits/rejected": 5399.53564453125,
|
977 |
+
"logps/chosen": -18.24646759033203,
|
978 |
+
"logps/rejected": -34.43614196777344,
|
979 |
+
"loss": 1.3488,
|
980 |
+
"rewards/accuracies": 0.6666666865348816,
|
981 |
+
"rewards/chosen": -17.58979606628418,
|
982 |
+
"rewards/margins": 16.084903717041016,
|
983 |
+
"rewards/rejected": -33.67470169067383,
|
984 |
+
"step": 640
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.5102040816326531,
|
988 |
+
"grad_norm": 10.769277377138156,
|
989 |
+
"learning_rate": 2.848385192615339e-07,
|
990 |
+
"logits/chosen": 5799.63671875,
|
991 |
+
"logits/rejected": 4268.919921875,
|
992 |
+
"logps/chosen": -12.065497398376465,
|
993 |
+
"logps/rejected": -39.761295318603516,
|
994 |
+
"loss": 1.3529,
|
995 |
+
"rewards/accuracies": 0.6750000715255737,
|
996 |
+
"rewards/chosen": -11.4081449508667,
|
997 |
+
"rewards/margins": 27.570276260375977,
|
998 |
+
"rewards/rejected": -38.97842788696289,
|
999 |
+
"step": 650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5180533751962323,
|
1003 |
+
"grad_norm": 12.661156373398873,
|
1004 |
+
"learning_rate": 2.780397634492949e-07,
|
1005 |
+
"logits/chosen": 6555.94775390625,
|
1006 |
+
"logits/rejected": 4259.31787109375,
|
1007 |
+
"logps/chosen": -10.676517486572266,
|
1008 |
+
"logps/rejected": -47.2622184753418,
|
1009 |
+
"loss": 1.3509,
|
1010 |
+
"rewards/accuracies": 0.7416666746139526,
|
1011 |
+
"rewards/chosen": -10.025793075561523,
|
1012 |
+
"rewards/margins": 36.494449615478516,
|
1013 |
+
"rewards/rejected": -46.520240783691406,
|
1014 |
+
"step": 660
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5259026687598116,
|
1018 |
+
"grad_norm": 10.079297684272941,
|
1019 |
+
"learning_rate": 2.71219937000424e-07,
|
1020 |
+
"logits/chosen": 6487.3076171875,
|
1021 |
+
"logits/rejected": 4708.78515625,
|
1022 |
+
"logps/chosen": -9.443751335144043,
|
1023 |
+
"logps/rejected": -38.85082244873047,
|
1024 |
+
"loss": 1.3585,
|
1025 |
+
"rewards/accuracies": 0.7333333492279053,
|
1026 |
+
"rewards/chosen": -8.82435131072998,
|
1027 |
+
"rewards/margins": 29.266210556030273,
|
1028 |
+
"rewards/rejected": -38.09056854248047,
|
1029 |
+
"step": 670
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.533751962323391,
|
1033 |
+
"grad_norm": 9.015834795504192,
|
1034 |
+
"learning_rate": 2.6438416471154273e-07,
|
1035 |
+
"logits/chosen": 6213.49267578125,
|
1036 |
+
"logits/rejected": 4702.8037109375,
|
1037 |
+
"logps/chosen": -9.60643196105957,
|
1038 |
+
"logps/rejected": -42.58051300048828,
|
1039 |
+
"loss": 1.3547,
|
1040 |
+
"rewards/accuracies": 0.7750000357627869,
|
1041 |
+
"rewards/chosen": -8.9835205078125,
|
1042 |
+
"rewards/margins": 32.88523864746094,
|
1043 |
+
"rewards/rejected": -41.8687629699707,
|
1044 |
+
"step": 680
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.5416012558869702,
|
1048 |
+
"grad_norm": 11.295069759751865,
|
1049 |
+
"learning_rate": 2.5753758336186326e-07,
|
1050 |
+
"logits/chosen": 6236.7900390625,
|
1051 |
+
"logits/rejected": 4860.75439453125,
|
1052 |
+
"logps/chosen": -9.005716323852539,
|
1053 |
+
"logps/rejected": -47.84248352050781,
|
1054 |
+
"loss": 1.3411,
|
1055 |
+
"rewards/accuracies": 0.7250000238418579,
|
1056 |
+
"rewards/chosen": -8.415175437927246,
|
1057 |
+
"rewards/margins": 38.613529205322266,
|
1058 |
+
"rewards/rejected": -47.02870178222656,
|
1059 |
+
"step": 690
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.5494505494505495,
|
1063 |
+
"grad_norm": 12.115147537268316,
|
1064 |
+
"learning_rate": 2.5068533785312666e-07,
|
1065 |
+
"logits/chosen": 5841.62890625,
|
1066 |
+
"logits/rejected": 4997.1611328125,
|
1067 |
+
"logps/chosen": -15.859621047973633,
|
1068 |
+
"logps/rejected": -44.61968994140625,
|
1069 |
+
"loss": 1.3585,
|
1070 |
+
"rewards/accuracies": 0.6416667103767395,
|
1071 |
+
"rewards/chosen": -15.210749626159668,
|
1072 |
+
"rewards/margins": 28.713302612304688,
|
1073 |
+
"rewards/rejected": -43.92405319213867,
|
1074 |
+
"step": 700
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.5572998430141287,
|
1078 |
+
"grad_norm": 9.83299305993898,
|
1079 |
+
"learning_rate": 2.4383257734343794e-07,
|
1080 |
+
"logits/chosen": 5929.123046875,
|
1081 |
+
"logits/rejected": 5199.5263671875,
|
1082 |
+
"logps/chosen": -11.007040977478027,
|
1083 |
+
"logps/rejected": -41.53852081298828,
|
1084 |
+
"loss": 1.3444,
|
1085 |
+
"rewards/accuracies": 0.7416666746139526,
|
1086 |
+
"rewards/chosen": -10.386730194091797,
|
1087 |
+
"rewards/margins": 30.414636611938477,
|
1088 |
+
"rewards/rejected": -40.80137252807617,
|
1089 |
+
"step": 710
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.565149136577708,
|
1093 |
+
"grad_norm": 11.047220141739768,
|
1094 |
+
"learning_rate": 2.3698445137790258e-07,
|
1095 |
+
"logits/chosen": 6393.74462890625,
|
1096 |
+
"logits/rejected": 4948.32470703125,
|
1097 |
+
"logps/chosen": -7.117844581604004,
|
1098 |
+
"logps/rejected": -32.42450714111328,
|
1099 |
+
"loss": 1.3619,
|
1100 |
+
"rewards/accuracies": 0.675000011920929,
|
1101 |
+
"rewards/chosen": -6.463726997375488,
|
1102 |
+
"rewards/margins": 25.183258056640625,
|
1103 |
+
"rewards/rejected": -31.646984100341797,
|
1104 |
+
"step": 720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.5729984301412873,
|
1108 |
+
"grad_norm": 11.23974480867259,
|
1109 |
+
"learning_rate": 2.3014610601897157e-07,
|
1110 |
+
"logits/chosen": 6870.53369140625,
|
1111 |
+
"logits/rejected": 4605.583984375,
|
1112 |
+
"logps/chosen": -9.47913932800293,
|
1113 |
+
"logps/rejected": -41.51166534423828,
|
1114 |
+
"loss": 1.3438,
|
1115 |
+
"rewards/accuracies": 0.7416666746139526,
|
1116 |
+
"rewards/chosen": -8.836474418640137,
|
1117 |
+
"rewards/margins": 31.91958236694336,
|
1118 |
+
"rewards/rejected": -40.75605773925781,
|
1119 |
+
"step": 730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5808477237048666,
|
1123 |
+
"grad_norm": 15.559189693273993,
|
1124 |
+
"learning_rate": 2.2332267997940513e-07,
|
1125 |
+
"logits/chosen": 5558.8349609375,
|
1126 |
+
"logits/rejected": 4223.8994140625,
|
1127 |
+
"logps/chosen": -15.262466430664062,
|
1128 |
+
"logps/rejected": -46.9307746887207,
|
1129 |
+
"loss": 1.3578,
|
1130 |
+
"rewards/accuracies": 0.7583333253860474,
|
1131 |
+
"rewards/chosen": -14.636202812194824,
|
1132 |
+
"rewards/margins": 31.5787296295166,
|
1133 |
+
"rewards/rejected": -46.214927673339844,
|
1134 |
+
"step": 740
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.5886970172684458,
|
1138 |
+
"grad_norm": 14.272382010281738,
|
1139 |
+
"learning_rate": 2.1651930076075723e-07,
|
1140 |
+
"logits/chosen": 5937.4658203125,
|
1141 |
+
"logits/rejected": 4661.57470703125,
|
1142 |
+
"logps/chosen": -17.500411987304688,
|
1143 |
+
"logps/rejected": -43.45275115966797,
|
1144 |
+
"loss": 1.3582,
|
1145 |
+
"rewards/accuracies": 0.6916666030883789,
|
1146 |
+
"rewards/chosen": -16.904193878173828,
|
1147 |
+
"rewards/margins": 25.871822357177734,
|
1148 |
+
"rewards/rejected": -42.776023864746094,
|
1149 |
+
"step": 750
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.5965463108320251,
|
1153 |
+
"grad_norm": 8.754492592596351,
|
1154 |
+
"learning_rate": 2.0974108080028692e-07,
|
1155 |
+
"logits/chosen": 6596.6220703125,
|
1156 |
+
"logits/rejected": 4611.462890625,
|
1157 |
+
"logps/chosen": -7.955502510070801,
|
1158 |
+
"logps/rejected": -37.630226135253906,
|
1159 |
+
"loss": 1.3555,
|
1160 |
+
"rewards/accuracies": 0.7166666388511658,
|
1161 |
+
"rewards/chosen": -7.332449913024902,
|
1162 |
+
"rewards/margins": 29.615585327148438,
|
1163 |
+
"rewards/rejected": -36.948036193847656,
|
1164 |
+
"step": 760
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.6043956043956044,
|
1168 |
+
"grad_norm": 10.912459081597383,
|
1169 |
+
"learning_rate": 2.0299311362918773e-07,
|
1170 |
+
"logits/chosen": 6754.17578125,
|
1171 |
+
"logits/rejected": 5320.26806640625,
|
1172 |
+
"logps/chosen": -13.05921745300293,
|
1173 |
+
"logps/rejected": -38.955936431884766,
|
1174 |
+
"loss": 1.3558,
|
1175 |
+
"rewards/accuracies": 0.7250000238418579,
|
1176 |
+
"rewards/chosen": -12.377306938171387,
|
1177 |
+
"rewards/margins": 25.745901107788086,
|
1178 |
+
"rewards/rejected": -38.123207092285156,
|
1179 |
+
"step": 770
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6122448979591837,
|
1183 |
+
"grad_norm": 11.267028059252095,
|
1184 |
+
"learning_rate": 1.962804700450265e-07,
|
1185 |
+
"logits/chosen": 6594.95068359375,
|
1186 |
+
"logits/rejected": 5792.111328125,
|
1187 |
+
"logps/chosen": -11.285120010375977,
|
1188 |
+
"logps/rejected": -36.00288009643555,
|
1189 |
+
"loss": 1.3521,
|
1190 |
+
"rewards/accuracies": 0.7083333730697632,
|
1191 |
+
"rewards/chosen": -10.641828536987305,
|
1192 |
+
"rewards/margins": 24.54639434814453,
|
1193 |
+
"rewards/rejected": -35.1882209777832,
|
1194 |
+
"step": 780
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.6200941915227629,
|
1198 |
+
"grad_norm": 16.889300889632764,
|
1199 |
+
"learning_rate": 1.8960819430126334e-07,
|
1200 |
+
"logits/chosen": 5998.2666015625,
|
1201 |
+
"logits/rejected": 4746.22119140625,
|
1202 |
+
"logps/chosen": -18.8221378326416,
|
1203 |
+
"logps/rejected": -49.53624725341797,
|
1204 |
+
"loss": 1.3518,
|
1205 |
+
"rewards/accuracies": 0.7416666746139526,
|
1206 |
+
"rewards/chosen": -18.138534545898438,
|
1207 |
+
"rewards/margins": 30.649255752563477,
|
1208 |
+
"rewards/rejected": -48.78778839111328,
|
1209 |
+
"step": 790
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.6279434850863422,
|
1213 |
+
"grad_norm": 10.993691880850108,
|
1214 |
+
"learning_rate": 1.8298130031671972e-07,
|
1215 |
+
"logits/chosen": 6008.68994140625,
|
1216 |
+
"logits/rejected": 4658.36669921875,
|
1217 |
+
"logps/chosen": -15.523478507995605,
|
1218 |
+
"logps/rejected": -42.00802230834961,
|
1219 |
+
"loss": 1.3645,
|
1220 |
+
"rewards/accuracies": 0.7500000596046448,
|
1221 |
+
"rewards/chosen": -14.784734725952148,
|
1222 |
+
"rewards/margins": 26.388931274414062,
|
1223 |
+
"rewards/rejected": -41.173667907714844,
|
1224 |
+
"step": 800
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6357927786499215,
|
1228 |
+
"grad_norm": 9.806014319167142,
|
1229 |
+
"learning_rate": 1.7640476790784075e-07,
|
1230 |
+
"logits/chosen": 5616.755859375,
|
1231 |
+
"logits/rejected": 4236.2626953125,
|
1232 |
+
"logps/chosen": -10.850046157836914,
|
1233 |
+
"logps/rejected": -40.791954040527344,
|
1234 |
+
"loss": 1.3535,
|
1235 |
+
"rewards/accuracies": 0.7083333730697632,
|
1236 |
+
"rewards/chosen": -10.169736862182617,
|
1237 |
+
"rewards/margins": 29.735652923583984,
|
1238 |
+
"rewards/rejected": -39.905391693115234,
|
1239 |
+
"step": 810
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.6436420722135008,
|
1243 |
+
"grad_norm": 18.37377243229568,
|
1244 |
+
"learning_rate": 1.6988353904658492e-07,
|
1245 |
+
"logits/chosen": 6082.55322265625,
|
1246 |
+
"logits/rejected": 4100.5595703125,
|
1247 |
+
"logps/chosen": -12.024580001831055,
|
1248 |
+
"logps/rejected": -40.69676208496094,
|
1249 |
+
"loss": 1.3524,
|
1250 |
+
"rewards/accuracies": 0.8166667222976685,
|
1251 |
+
"rewards/chosen": -11.352849006652832,
|
1252 |
+
"rewards/margins": 28.577457427978516,
|
1253 |
+
"rewards/rejected": -39.93030548095703,
|
1254 |
+
"step": 820
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.6514913657770801,
|
1258 |
+
"grad_norm": 16.297609330074813,
|
1259 |
+
"learning_rate": 1.634225141467513e-07,
|
1260 |
+
"logits/chosen": 5812.82275390625,
|
1261 |
+
"logits/rejected": 4317.2626953125,
|
1262 |
+
"logps/chosen": -17.369579315185547,
|
1263 |
+
"logps/rejected": -48.95631408691406,
|
1264 |
+
"loss": 1.3462,
|
1265 |
+
"rewards/accuracies": 0.6750000715255737,
|
1266 |
+
"rewards/chosen": -16.705692291259766,
|
1267 |
+
"rewards/margins": 31.48634910583496,
|
1268 |
+
"rewards/rejected": -48.19204330444336,
|
1269 |
+
"step": 830
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.6593406593406593,
|
1273 |
+
"grad_norm": 9.301450718129091,
|
1274 |
+
"learning_rate": 1.570265483815364e-07,
|
1275 |
+
"logits/chosen": 6524.0634765625,
|
1276 |
+
"logits/rejected": 4608.86181640625,
|
1277 |
+
"logps/chosen": -14.519497871398926,
|
1278 |
+
"logps/rejected": -40.709632873535156,
|
1279 |
+
"loss": 1.3465,
|
1280 |
+
"rewards/accuracies": 0.6833333969116211,
|
1281 |
+
"rewards/chosen": -13.860455513000488,
|
1282 |
+
"rewards/margins": 26.043548583984375,
|
1283 |
+
"rewards/rejected": -39.90399932861328,
|
1284 |
+
"step": 840
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.6671899529042387,
|
1288 |
+
"grad_norm": 9.160256595515714,
|
1289 |
+
"learning_rate": 1.5070044803508691e-07,
|
1290 |
+
"logits/chosen": 6107.046875,
|
1291 |
+
"logits/rejected": 4694.4599609375,
|
1292 |
+
"logps/chosen": -8.90070915222168,
|
1293 |
+
"logps/rejected": -44.73848342895508,
|
1294 |
+
"loss": 1.3408,
|
1295 |
+
"rewards/accuracies": 0.75,
|
1296 |
+
"rewards/chosen": -8.21817398071289,
|
1297 |
+
"rewards/margins": 35.75190353393555,
|
1298 |
+
"rewards/rejected": -43.97007751464844,
|
1299 |
+
"step": 850
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.6750392464678179,
|
1303 |
+
"grad_norm": 27.489286245121285,
|
1304 |
+
"learning_rate": 1.444489668907914e-07,
|
1305 |
+
"logits/chosen": 6378.09033203125,
|
1306 |
+
"logits/rejected": 4609.8115234375,
|
1307 |
+
"logps/chosen": -12.870359420776367,
|
1308 |
+
"logps/rejected": -47.970619201660156,
|
1309 |
+
"loss": 1.3578,
|
1310 |
+
"rewards/accuracies": 0.7250000238418579,
|
1311 |
+
"rewards/chosen": -12.144631385803223,
|
1312 |
+
"rewards/margins": 35.02986526489258,
|
1313 |
+
"rewards/rejected": -47.174495697021484,
|
1314 |
+
"step": 860
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.6828885400313972,
|
1318 |
+
"grad_norm": 9.941621288803526,
|
1319 |
+
"learning_rate": 1.3827680265902232e-07,
|
1320 |
+
"logits/chosen": 6576.61083984375,
|
1321 |
+
"logits/rejected": 4636.0556640625,
|
1322 |
+
"logps/chosen": -10.919339179992676,
|
1323 |
+
"logps/rejected": -39.724056243896484,
|
1324 |
+
"loss": 1.3491,
|
1325 |
+
"rewards/accuracies": 0.7666666507720947,
|
1326 |
+
"rewards/chosen": -10.253345489501953,
|
1327 |
+
"rewards/margins": 28.734447479248047,
|
1328 |
+
"rewards/rejected": -38.98779296875,
|
1329 |
+
"step": 870
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6907378335949764,
|
1333 |
+
"grad_norm": 24.038360075630116,
|
1334 |
+
"learning_rate": 1.3218859344701632e-07,
|
1335 |
+
"logits/chosen": 5705.89697265625,
|
1336 |
+
"logits/rejected": 4821.3330078125,
|
1337 |
+
"logps/chosen": -12.567468643188477,
|
1338 |
+
"logps/rejected": -35.90740966796875,
|
1339 |
+
"loss": 1.3557,
|
1340 |
+
"rewards/accuracies": 0.7500000596046448,
|
1341 |
+
"rewards/chosen": -11.867032051086426,
|
1342 |
+
"rewards/margins": 23.217498779296875,
|
1343 |
+
"rewards/rejected": -35.084529876708984,
|
1344 |
+
"step": 880
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.6985871271585558,
|
1348 |
+
"grad_norm": 14.799566924171229,
|
1349 |
+
"learning_rate": 1.2618891427354172e-07,
|
1350 |
+
"logits/chosen": 6839.7822265625,
|
1351 |
+
"logits/rejected": 4843.2822265625,
|
1352 |
+
"logps/chosen": -10.830427169799805,
|
1353 |
+
"logps/rejected": -46.047332763671875,
|
1354 |
+
"loss": 1.3521,
|
1355 |
+
"rewards/accuracies": 0.7750000357627869,
|
1356 |
+
"rewards/chosen": -10.071599960327148,
|
1357 |
+
"rewards/margins": 35.167415618896484,
|
1358 |
+
"rewards/rejected": -45.239017486572266,
|
1359 |
+
"step": 890
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.706436420722135,
|
1363 |
+
"grad_norm": 12.683033226611311,
|
1364 |
+
"learning_rate": 1.202822736309758e-07,
|
1365 |
+
"logits/chosen": 5786.37744140625,
|
1366 |
+
"logits/rejected": 4521.42529296875,
|
1367 |
+
"logps/chosen": -10.186563491821289,
|
1368 |
+
"logps/rejected": -42.66360092163086,
|
1369 |
+
"loss": 1.3532,
|
1370 |
+
"rewards/accuracies": 0.7333333492279053,
|
1371 |
+
"rewards/chosen": -9.53927993774414,
|
1372 |
+
"rewards/margins": 32.29823303222656,
|
1373 |
+
"rewards/rejected": -41.83751678466797,
|
1374 |
+
"step": 900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.7142857142857143,
|
1378 |
+
"grad_norm": 7.8112818904757555,
|
1379 |
+
"learning_rate": 1.1447311009737299e-07,
|
1380 |
+
"logits/chosen": 5534.1630859375,
|
1381 |
+
"logits/rejected": 4551.8251953125,
|
1382 |
+
"logps/chosen": -13.114629745483398,
|
1383 |
+
"logps/rejected": -46.98776626586914,
|
1384 |
+
"loss": 1.3477,
|
1385 |
+
"rewards/accuracies": 0.7416666746139526,
|
1386 |
+
"rewards/chosen": -12.424124717712402,
|
1387 |
+
"rewards/margins": 33.744571685791016,
|
1388 |
+
"rewards/rejected": -46.1686897277832,
|
1389 |
+
"step": 910
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.7221350078492935,
|
1393 |
+
"grad_norm": 13.48022639064254,
|
1394 |
+
"learning_rate": 1.0876578900107053e-07,
|
1395 |
+
"logits/chosen": 6257.46142578125,
|
1396 |
+
"logits/rejected": 4657.412109375,
|
1397 |
+
"logps/chosen": -9.951969146728516,
|
1398 |
+
"logps/rejected": -37.00797653198242,
|
1399 |
+
"loss": 1.3473,
|
1400 |
+
"rewards/accuracies": 0.7749999761581421,
|
1401 |
+
"rewards/chosen": -9.255838394165039,
|
1402 |
+
"rewards/margins": 26.91226577758789,
|
1403 |
+
"rewards/rejected": -36.1681022644043,
|
1404 |
+
"step": 920
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.7299843014128728,
|
1408 |
+
"grad_norm": 9.203666814948612,
|
1409 |
+
"learning_rate": 1.0316459914033793e-07,
|
1410 |
+
"logits/chosen": 6127.88720703125,
|
1411 |
+
"logits/rejected": 3711.983642578125,
|
1412 |
+
"logps/chosen": -14.189971923828125,
|
1413 |
+
"logps/rejected": -48.925025939941406,
|
1414 |
+
"loss": 1.3439,
|
1415 |
+
"rewards/accuracies": 0.7583333253860474,
|
1416 |
+
"rewards/chosen": -13.459379196166992,
|
1417 |
+
"rewards/margins": 34.6566047668457,
|
1418 |
+
"rewards/rejected": -48.1159782409668,
|
1419 |
+
"step": 930
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.7378335949764521,
|
1423 |
+
"grad_norm": 10.697737816990417,
|
1424 |
+
"learning_rate": 9.767374956053584e-08,
|
1425 |
+
"logits/chosen": 5963.5029296875,
|
1426 |
+
"logits/rejected": 4586.4345703125,
|
1427 |
+
"logps/chosen": -11.35425090789795,
|
1428 |
+
"logps/rejected": -51.100425720214844,
|
1429 |
+
"loss": 1.3422,
|
1430 |
+
"rewards/accuracies": 0.6916666626930237,
|
1431 |
+
"rewards/chosen": -10.636934280395508,
|
1432 |
+
"rewards/margins": 39.55208206176758,
|
1433 |
+
"rewards/rejected": -50.18900680541992,
|
1434 |
+
"step": 940
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7456828885400314,
|
1438 |
+
"grad_norm": 11.783318339337354,
|
1439 |
+
"learning_rate": 9.229736639120561e-08,
|
1440 |
+
"logits/chosen": 6086.76025390625,
|
1441 |
+
"logits/rejected": 5080.07421875,
|
1442 |
+
"logps/chosen": -12.311005592346191,
|
1443 |
+
"logps/rejected": -28.69287109375,
|
1444 |
+
"loss": 1.3568,
|
1445 |
+
"rewards/accuracies": 0.6833332777023315,
|
1446 |
+
"rewards/chosen": -11.60954475402832,
|
1447 |
+
"rewards/margins": 16.351043701171875,
|
1448 |
+
"rewards/rejected": -27.960586547851562,
|
1449 |
+
"step": 950
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.7535321821036107,
|
1453 |
+
"grad_norm": 10.637109859687323,
|
1454 |
+
"learning_rate": 8.70394897454659e-08,
|
1455 |
+
"logits/chosen": 6191.0126953125,
|
1456 |
+
"logits/rejected": 4793.7890625,
|
1457 |
+
"logps/chosen": -6.652519226074219,
|
1458 |
+
"logps/rejected": -37.2434196472168,
|
1459 |
+
"loss": 1.339,
|
1460 |
+
"rewards/accuracies": 0.7166666984558105,
|
1461 |
+
"rewards/chosen": -5.941922187805176,
|
1462 |
+
"rewards/margins": 30.51517677307129,
|
1463 |
+
"rewards/rejected": -36.457096099853516,
|
1464 |
+
"step": 960
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7613814756671899,
|
1468 |
+
"grad_norm": 21.916390858965105,
|
1469 |
+
"learning_rate": 8.19040706840472e-08,
|
1470 |
+
"logits/chosen": 6167.099609375,
|
1471 |
+
"logits/rejected": 4380.296875,
|
1472 |
+
"logps/chosen": -9.31376838684082,
|
1473 |
+
"logps/rejected": -49.45098114013672,
|
1474 |
+
"loss": 1.3427,
|
1475 |
+
"rewards/accuracies": 0.800000011920929,
|
1476 |
+
"rewards/chosen": -8.63332748413086,
|
1477 |
+
"rewards/margins": 39.97867965698242,
|
1478 |
+
"rewards/rejected": -48.61200714111328,
|
1479 |
+
"step": 970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.7692307692307693,
|
1483 |
+
"grad_norm": 15.489524399549873,
|
1484 |
+
"learning_rate": 7.689496824624525e-08,
|
1485 |
+
"logits/chosen": 5892.37158203125,
|
1486 |
+
"logits/rejected": 3848.999267578125,
|
1487 |
+
"logps/chosen": -10.760286331176758,
|
1488 |
+
"logps/rejected": -56.49827194213867,
|
1489 |
+
"loss": 1.3421,
|
1490 |
+
"rewards/accuracies": 0.7916666269302368,
|
1491 |
+
"rewards/chosen": -10.0794677734375,
|
1492 |
+
"rewards/margins": 45.537147521972656,
|
1493 |
+
"rewards/rejected": -55.616615295410156,
|
1494 |
+
"step": 980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.7770800627943485,
|
1498 |
+
"grad_norm": 11.83089798223724,
|
1499 |
+
"learning_rate": 7.201594655002458e-08,
|
1500 |
+
"logits/chosen": 6142.3076171875,
|
1501 |
+
"logits/rejected": 4396.3681640625,
|
1502 |
+
"logps/chosen": -11.698305130004883,
|
1503 |
+
"logps/rejected": -52.2495002746582,
|
1504 |
+
"loss": 1.3418,
|
1505 |
+
"rewards/accuracies": 0.7250000238418579,
|
1506 |
+
"rewards/chosen": -11.031845092773438,
|
1507 |
+
"rewards/margins": 40.371498107910156,
|
1508 |
+
"rewards/rejected": -51.403343200683594,
|
1509 |
+
"step": 990
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.7849293563579278,
|
1513 |
+
"grad_norm": 12.8555278251267,
|
1514 |
+
"learning_rate": 6.727067196345099e-08,
|
1515 |
+
"logits/chosen": 5779.787109375,
|
1516 |
+
"logits/rejected": 4448.8349609375,
|
1517 |
+
"logps/chosen": -12.997045516967773,
|
1518 |
+
"logps/rejected": -34.62881851196289,
|
1519 |
+
"loss": 1.3515,
|
1520 |
+
"rewards/accuracies": 0.6833333373069763,
|
1521 |
+
"rewards/chosen": -12.312833786010742,
|
1522 |
+
"rewards/margins": 21.579345703125,
|
1523 |
+
"rewards/rejected": -33.89217758178711,
|
1524 |
+
"step": 1000
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.792778649921507,
|
1528 |
+
"grad_norm": 12.537447175753579,
|
1529 |
+
"learning_rate": 6.26627103495786e-08,
|
1530 |
+
"logits/chosen": 6107.9267578125,
|
1531 |
+
"logits/rejected": 4406.4130859375,
|
1532 |
+
"logps/chosen": -11.072089195251465,
|
1533 |
+
"logps/rejected": -43.155887603759766,
|
1534 |
+
"loss": 1.3516,
|
1535 |
+
"rewards/accuracies": 0.7083333134651184,
|
1536 |
+
"rewards/chosen": -10.391607284545898,
|
1537 |
+
"rewards/margins": 32.014122009277344,
|
1538 |
+
"rewards/rejected": -42.40572738647461,
|
1539 |
+
"step": 1010
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.8006279434850864,
|
1543 |
+
"grad_norm": 6.910015837764057,
|
1544 |
+
"learning_rate": 5.8195524386862374e-08,
|
1545 |
+
"logits/chosen": 6251.3759765625,
|
1546 |
+
"logits/rejected": 4906.587890625,
|
1547 |
+
"logps/chosen": -8.422673225402832,
|
1548 |
+
"logps/rejected": -39.31324768066406,
|
1549 |
+
"loss": 1.3533,
|
1550 |
+
"rewards/accuracies": 0.7916667461395264,
|
1551 |
+
"rewards/chosen": -7.672184944152832,
|
1552 |
+
"rewards/margins": 30.805267333984375,
|
1553 |
+
"rewards/rejected": -38.477455139160156,
|
1554 |
+
"step": 1020
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.8084772370486656,
|
1558 |
+
"grad_norm": 10.822080025305892,
|
1559 |
+
"learning_rate": 5.38724709671092e-08,
|
1560 |
+
"logits/chosen": 6651.43115234375,
|
1561 |
+
"logits/rejected": 5678.1181640625,
|
1562 |
+
"logps/chosen": -9.612025260925293,
|
1563 |
+
"logps/rejected": -36.233829498291016,
|
1564 |
+
"loss": 1.3491,
|
1565 |
+
"rewards/accuracies": 0.7500001192092896,
|
1566 |
+
"rewards/chosen": -8.941255569458008,
|
1567 |
+
"rewards/margins": 26.474712371826172,
|
1568 |
+
"rewards/rejected": -35.41596603393555,
|
1569 |
+
"step": 1030
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8163265306122449,
|
1573 |
+
"grad_norm": 8.94597165114862,
|
1574 |
+
"learning_rate": 4.969679867292276e-08,
|
1575 |
+
"logits/chosen": 5803.84375,
|
1576 |
+
"logits/rejected": 4507.89404296875,
|
1577 |
+
"logps/chosen": -11.683372497558594,
|
1578 |
+
"logps/rejected": -50.33116149902344,
|
1579 |
+
"loss": 1.3396,
|
1580 |
+
"rewards/accuracies": 0.7000000476837158,
|
1581 |
+
"rewards/chosen": -10.970834732055664,
|
1582 |
+
"rewards/margins": 38.524723052978516,
|
1583 |
+
"rewards/rejected": -49.49555587768555,
|
1584 |
+
"step": 1040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.8241758241758241,
|
1588 |
+
"grad_norm": 15.522644034350902,
|
1589 |
+
"learning_rate": 4.5671645336537416e-08,
|
1590 |
+
"logits/chosen": 5976.689453125,
|
1591 |
+
"logits/rejected": 4534.595703125,
|
1592 |
+
"logps/chosen": -11.027806282043457,
|
1593 |
+
"logps/rejected": -47.25383758544922,
|
1594 |
+
"loss": 1.3436,
|
1595 |
+
"rewards/accuracies": 0.75,
|
1596 |
+
"rewards/chosen": -10.277358055114746,
|
1597 |
+
"rewards/margins": 36.20246505737305,
|
1598 |
+
"rewards/rejected": -46.479827880859375,
|
1599 |
+
"step": 1050
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.8320251177394035,
|
1603 |
+
"grad_norm": 19.227519235685435,
|
1604 |
+
"learning_rate": 4.180003568187776e-08,
|
1605 |
+
"logits/chosen": 7209.6474609375,
|
1606 |
+
"logits/rejected": 5028.30029296875,
|
1607 |
+
"logps/chosen": -14.763595581054688,
|
1608 |
+
"logps/rejected": -42.880470275878906,
|
1609 |
+
"loss": 1.3622,
|
1610 |
+
"rewards/accuracies": 0.6583333611488342,
|
1611 |
+
"rewards/chosen": -14.041421890258789,
|
1612 |
+
"rewards/margins": 28.038188934326172,
|
1613 |
+
"rewards/rejected": -42.079612731933594,
|
1614 |
+
"step": 1060
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.8398744113029827,
|
1618 |
+
"grad_norm": 11.191674738465105,
|
1619 |
+
"learning_rate": 3.8084879051612144e-08,
|
1620 |
+
"logits/chosen": 6095.42529296875,
|
1621 |
+
"logits/rejected": 4858.88671875,
|
1622 |
+
"logps/chosen": -8.86856460571289,
|
1623 |
+
"logps/rejected": -46.186073303222656,
|
1624 |
+
"loss": 1.3464,
|
1625 |
+
"rewards/accuracies": 0.6833333969116211,
|
1626 |
+
"rewards/chosen": -8.155261993408203,
|
1627 |
+
"rewards/margins": 37.2761116027832,
|
1628 |
+
"rewards/rejected": -45.431373596191406,
|
1629 |
+
"step": 1070
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.847723704866562,
|
1633 |
+
"grad_norm": 7.0206188838060735,
|
1634 |
+
"learning_rate": 3.452896722091128e-08,
|
1635 |
+
"logits/chosen": 6701.546875,
|
1636 |
+
"logits/rejected": 4320.4267578125,
|
1637 |
+
"logps/chosen": -9.577341079711914,
|
1638 |
+
"logps/rejected": -46.688411712646484,
|
1639 |
+
"loss": 1.3479,
|
1640 |
+
"rewards/accuracies": 0.824999988079071,
|
1641 |
+
"rewards/chosen": -8.867132186889648,
|
1642 |
+
"rewards/margins": 37.0556640625,
|
1643 |
+
"rewards/rejected": -45.922794342041016,
|
1644 |
+
"step": 1080
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.8555729984301413,
|
1648 |
+
"grad_norm": 12.648028891337141,
|
1649 |
+
"learning_rate": 3.11349722995527e-08,
|
1650 |
+
"logits/chosen": 6607.6318359375,
|
1651 |
+
"logits/rejected": 4307.4677734375,
|
1652 |
+
"logps/chosen": -11.983565330505371,
|
1653 |
+
"logps/rejected": -44.108150482177734,
|
1654 |
+
"loss": 1.3466,
|
1655 |
+
"rewards/accuracies": 0.7416667342185974,
|
1656 |
+
"rewards/chosen": -11.318174362182617,
|
1657 |
+
"rewards/margins": 31.94852638244629,
|
1658 |
+
"rewards/rejected": -43.26670455932617,
|
1659 |
+
"step": 1090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.8634222919937206,
|
1663 |
+
"grad_norm": 16.16520843547699,
|
1664 |
+
"learning_rate": 2.7905444723949762e-08,
|
1665 |
+
"logits/chosen": 6445.07177734375,
|
1666 |
+
"logits/rejected": 4464.13427734375,
|
1667 |
+
"logps/chosen": -14.572372436523438,
|
1668 |
+
"logps/rejected": -57.9854850769043,
|
1669 |
+
"loss": 1.3444,
|
1670 |
+
"rewards/accuracies": 0.7750000357627869,
|
1671 |
+
"rewards/chosen": -13.854543685913086,
|
1672 |
+
"rewards/margins": 43.35486602783203,
|
1673 |
+
"rewards/rejected": -57.20940399169922,
|
1674 |
+
"step": 1100
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8712715855572999,
|
1678 |
+
"grad_norm": 12.082780970830518,
|
1679 |
+
"learning_rate": 2.484281134061142e-08,
|
1680 |
+
"logits/chosen": 6635.34619140625,
|
1681 |
+
"logits/rejected": 4545.72314453125,
|
1682 |
+
"logps/chosen": -15.10521411895752,
|
1683 |
+
"logps/rejected": -54.311370849609375,
|
1684 |
+
"loss": 1.3485,
|
1685 |
+
"rewards/accuracies": 0.7416666746139526,
|
1686 |
+
"rewards/chosen": -14.40710735321045,
|
1687 |
+
"rewards/margins": 39.0588264465332,
|
1688 |
+
"rewards/rejected": -53.4659309387207,
|
1689 |
+
"step": 1110
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.8791208791208791,
|
1693 |
+
"grad_norm": 15.429026565586026,
|
1694 |
+
"learning_rate": 2.194937358247506e-08,
|
1695 |
+
"logits/chosen": 6658.29052734375,
|
1696 |
+
"logits/rejected": 4560.0166015625,
|
1697 |
+
"logps/chosen": -14.397059440612793,
|
1698 |
+
"logps/rejected": -51.39775466918945,
|
1699 |
+
"loss": 1.3472,
|
1700 |
+
"rewards/accuracies": 0.7250000238418579,
|
1701 |
+
"rewards/chosen": -13.709543228149414,
|
1702 |
+
"rewards/margins": 36.796878814697266,
|
1703 |
+
"rewards/rejected": -50.50641632080078,
|
1704 |
+
"step": 1120
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.8869701726844584,
|
1708 |
+
"grad_norm": 19.175151198780238,
|
1709 |
+
"learning_rate": 1.9227305739481612e-08,
|
1710 |
+
"logits/chosen": 6183.2001953125,
|
1711 |
+
"logits/rejected": 3959.198486328125,
|
1712 |
+
"logps/chosen": -8.73318099975586,
|
1713 |
+
"logps/rejected": -47.819435119628906,
|
1714 |
+
"loss": 1.342,
|
1715 |
+
"rewards/accuracies": 0.7583333849906921,
|
1716 |
+
"rewards/chosen": -8.031963348388672,
|
1717 |
+
"rewards/margins": 38.94813919067383,
|
1718 |
+
"rewards/rejected": -46.9801025390625,
|
1719 |
+
"step": 1130
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.8948194662480377,
|
1723 |
+
"grad_norm": 10.620817934538785,
|
1724 |
+
"learning_rate": 1.6678653324693787e-08,
|
1725 |
+
"logits/chosen": 6747.44287109375,
|
1726 |
+
"logits/rejected": 4794.2822265625,
|
1727 |
+
"logps/chosen": -10.389518737792969,
|
1728 |
+
"logps/rejected": -41.45861053466797,
|
1729 |
+
"loss": 1.3374,
|
1730 |
+
"rewards/accuracies": 0.7416666746139526,
|
1731 |
+
"rewards/chosen": -9.669957160949707,
|
1732 |
+
"rewards/margins": 30.935802459716797,
|
1733 |
+
"rewards/rejected": -40.60576629638672,
|
1734 |
+
"step": 1140
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.902668759811617,
|
1738 |
+
"grad_norm": 10.754709061690225,
|
1739 |
+
"learning_rate": 1.4305331537183384e-08,
|
1740 |
+
"logits/chosen": 5942.2294921875,
|
1741 |
+
"logits/rejected": 4849.82177734375,
|
1742 |
+
"logps/chosen": -12.92119312286377,
|
1743 |
+
"logps/rejected": -41.3829345703125,
|
1744 |
+
"loss": 1.3461,
|
1745 |
+
"rewards/accuracies": 0.7083333134651184,
|
1746 |
+
"rewards/chosen": -12.190919876098633,
|
1747 |
+
"rewards/margins": 28.414255142211914,
|
1748 |
+
"rewards/rejected": -40.60517120361328,
|
1749 |
+
"step": 1150
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.9105180533751962,
|
1753 |
+
"grad_norm": 13.557533071090745,
|
1754 |
+
"learning_rate": 1.2109123822844653e-08,
|
1755 |
+
"logits/chosen": 6006.47021484375,
|
1756 |
+
"logits/rejected": 4266.6396484375,
|
1757 |
+
"logps/chosen": -14.5009765625,
|
1758 |
+
"logps/rejected": -38.874107360839844,
|
1759 |
+
"loss": 1.3503,
|
1760 |
+
"rewards/accuracies": 0.7166666984558105,
|
1761 |
+
"rewards/chosen": -13.78251838684082,
|
1762 |
+
"rewards/margins": 24.258342742919922,
|
1763 |
+
"rewards/rejected": -38.040863037109375,
|
1764 |
+
"step": 1160
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.9183673469387755,
|
1768 |
+
"grad_norm": 18.275601434548747,
|
1769 |
+
"learning_rate": 1.0091680534213387e-08,
|
1770 |
+
"logits/chosen": 6534.689453125,
|
1771 |
+
"logits/rejected": 5600.6259765625,
|
1772 |
+
"logps/chosen": -14.446474075317383,
|
1773 |
+
"logps/rejected": -39.4738655090332,
|
1774 |
+
"loss": 1.3455,
|
1775 |
+
"rewards/accuracies": 0.6333333253860474,
|
1776 |
+
"rewards/chosen": -13.775007247924805,
|
1777 |
+
"rewards/margins": 24.918426513671875,
|
1778 |
+
"rewards/rejected": -38.69343566894531,
|
1779 |
+
"step": 1170
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.9262166405023547,
|
1783 |
+
"grad_norm": 18.235577733959495,
|
1784 |
+
"learning_rate": 8.254517690300944e-09,
|
1785 |
+
"logits/chosen": 5951.74609375,
|
1786 |
+
"logits/rejected": 4470.59814453125,
|
1787 |
+
"logps/chosen": -12.159133911132812,
|
1788 |
+
"logps/rejected": -45.7835807800293,
|
1789 |
+
"loss": 1.3548,
|
1790 |
+
"rewards/accuracies": 0.7250000238418579,
|
1791 |
+
"rewards/chosen": -11.42202091217041,
|
1792 |
+
"rewards/margins": 33.510128021240234,
|
1793 |
+
"rewards/rejected": -44.932151794433594,
|
1794 |
+
"step": 1180
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.9340659340659341,
|
1798 |
+
"grad_norm": 10.49720602308573,
|
1799 |
+
"learning_rate": 6.599015837372907e-09,
|
1800 |
+
"logits/chosen": 6310.583984375,
|
1801 |
+
"logits/rejected": 4920.32861328125,
|
1802 |
+
"logps/chosen": -15.357757568359375,
|
1803 |
+
"logps/rejected": -46.599708557128906,
|
1804 |
+
"loss": 1.3385,
|
1805 |
+
"rewards/accuracies": 0.699999988079071,
|
1806 |
+
"rewards/chosen": -14.61291217803955,
|
1807 |
+
"rewards/margins": 31.154321670532227,
|
1808 |
+
"rewards/rejected": -45.767234802246094,
|
1809 |
+
"step": 1190
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.9419152276295133,
|
1813 |
+
"grad_norm": 11.862843010865799,
|
1814 |
+
"learning_rate": 5.126419011529992e-09,
|
1815 |
+
"logits/chosen": 6784.61865234375,
|
1816 |
+
"logits/rejected": 4886.77001953125,
|
1817 |
+
"logps/chosen": -10.652966499328613,
|
1818 |
+
"logps/rejected": -48.49315643310547,
|
1819 |
+
"loss": 1.3506,
|
1820 |
+
"rewards/accuracies": 0.7833333015441895,
|
1821 |
+
"rewards/chosen": -9.923705101013184,
|
1822 |
+
"rewards/margins": 37.731605529785156,
|
1823 |
+
"rewards/rejected": -47.65531539916992,
|
1824 |
+
"step": 1200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.9497645211930926,
|
1828 |
+
"grad_norm": 16.13028833676148,
|
1829 |
+
"learning_rate": 3.837833803870177e-09,
|
1830 |
+
"logits/chosen": 6215.4248046875,
|
1831 |
+
"logits/rejected": 4725.1298828125,
|
1832 |
+
"logps/chosen": -13.33996868133545,
|
1833 |
+
"logps/rejected": -44.714012145996094,
|
1834 |
+
"loss": 1.3548,
|
1835 |
+
"rewards/accuracies": 0.7583333253860474,
|
1836 |
+
"rewards/chosen": -12.622026443481445,
|
1837 |
+
"rewards/margins": 31.248937606811523,
|
1838 |
+
"rewards/rejected": -43.8709602355957,
|
1839 |
+
"step": 1210
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.957613814756672,
|
1843 |
+
"grad_norm": 13.798152810624883,
|
1844 |
+
"learning_rate": 2.734228528934679e-09,
|
1845 |
+
"logits/chosen": 7684.4091796875,
|
1846 |
+
"logits/rejected": 4981.8173828125,
|
1847 |
+
"logps/chosen": -13.918993949890137,
|
1848 |
+
"logps/rejected": -47.229942321777344,
|
1849 |
+
"loss": 1.3582,
|
1850 |
+
"rewards/accuracies": 0.7250000238418579,
|
1851 |
+
"rewards/chosen": -13.145196914672852,
|
1852 |
+
"rewards/margins": 33.178897857666016,
|
1853 |
+
"rewards/rejected": -46.324092864990234,
|
1854 |
+
"step": 1220
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.9654631083202512,
|
1858 |
+
"grad_norm": 10.813489628564165,
|
1859 |
+
"learning_rate": 1.8164324970625645e-09,
|
1860 |
+
"logits/chosen": 6866.75,
|
1861 |
+
"logits/rejected": 4787.5693359375,
|
1862 |
+
"logps/chosen": -11.430197715759277,
|
1863 |
+
"logps/rejected": -42.63923645019531,
|
1864 |
+
"loss": 1.3546,
|
1865 |
+
"rewards/accuracies": 0.7250000238418579,
|
1866 |
+
"rewards/chosen": -10.682231903076172,
|
1867 |
+
"rewards/margins": 31.16469383239746,
|
1868 |
+
"rewards/rejected": -41.846927642822266,
|
1869 |
+
"step": 1230
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.9733124018838305,
|
1873 |
+
"grad_norm": 11.901517103335008,
|
1874 |
+
"learning_rate": 1.0851353912008642e-09,
|
1875 |
+
"logits/chosen": 5887.49462890625,
|
1876 |
+
"logits/rejected": 4629.6220703125,
|
1877 |
+
"logps/chosen": -13.619874954223633,
|
1878 |
+
"logps/rejected": -50.765167236328125,
|
1879 |
+
"loss": 1.34,
|
1880 |
+
"rewards/accuracies": 0.75,
|
1881 |
+
"rewards/chosen": -12.862905502319336,
|
1882 |
+
"rewards/margins": 36.99613571166992,
|
1883 |
+
"rewards/rejected": -49.85904312133789,
|
1884 |
+
"step": 1240
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.9811616954474097,
|
1888 |
+
"grad_norm": 11.112356440700552,
|
1889 |
+
"learning_rate": 5.408867486384471e-10,
|
1890 |
+
"logits/chosen": 6076.89453125,
|
1891 |
+
"logits/rejected": 4519.1474609375,
|
1892 |
+
"logps/chosen": -8.847349166870117,
|
1893 |
+
"logps/rejected": -37.14400863647461,
|
1894 |
+
"loss": 1.3532,
|
1895 |
+
"rewards/accuracies": 0.7749999761581421,
|
1896 |
+
"rewards/chosen": -8.169310569763184,
|
1897 |
+
"rewards/margins": 28.190332412719727,
|
1898 |
+
"rewards/rejected": -36.359649658203125,
|
1899 |
+
"step": 1250
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.989010989010989,
|
1903 |
+
"grad_norm": 10.283870046812526,
|
1904 |
+
"learning_rate": 1.840955480532924e-10,
|
1905 |
+
"logits/chosen": 5829.6083984375,
|
1906 |
+
"logits/rejected": 4635.3076171875,
|
1907 |
+
"logps/chosen": -11.450944900512695,
|
1908 |
+
"logps/rejected": -42.468692779541016,
|
1909 |
+
"loss": 1.3448,
|
1910 |
+
"rewards/accuracies": 0.7666666507720947,
|
1911 |
+
"rewards/chosen": -10.698575019836426,
|
1912 |
+
"rewards/margins": 30.944873809814453,
|
1913 |
+
"rewards/rejected": -41.64345169067383,
|
1914 |
+
"step": 1260
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.9968602825745683,
|
1918 |
+
"grad_norm": 14.458122344024726,
|
1919 |
+
"learning_rate": 1.502990218302247e-11,
|
1920 |
+
"logits/chosen": 5938.97802734375,
|
1921 |
+
"logits/rejected": 4195.7705078125,
|
1922 |
+
"logps/chosen": -12.192282676696777,
|
1923 |
+
"logps/rejected": -46.034873962402344,
|
1924 |
+
"loss": 1.3539,
|
1925 |
+
"rewards/accuracies": 0.6833333373069763,
|
1926 |
+
"rewards/chosen": -11.495050430297852,
|
1927 |
+
"rewards/margins": 33.76050567626953,
|
1928 |
+
"rewards/rejected": -45.255550384521484,
|
1929 |
+
"step": 1270
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.0,
|
1933 |
+
"step": 1274,
|
1934 |
+
"total_flos": 0.0,
|
1935 |
+
"train_loss": 1.3571216397607346,
|
1936 |
+
"train_runtime": 13426.8072,
|
1937 |
+
"train_samples_per_second": 4.553,
|
1938 |
+
"train_steps_per_second": 0.095
|
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 sha256:571e2b8760254b1e81ea05c4fc584fec08b68c07fb3fe09113d0d92f25166a60
|
3 |
+
size 7288
|