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 +762 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: zephyr-7b-DPOBS128Base-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 |
+
# zephyr-7b-DPOBS128Base-full
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/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: 4
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 4
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 128
|
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": 0.998691442030882,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6349887008187156,
|
5 |
+
"train_runtime": 13807.6715,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.428,
|
8 |
+
"train_steps_per_second": 0.035
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "alignment-handbook/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 sha256:118a4a71a39f2e3ad1444fb53b15f9f6669bf6b0b6e268a679bb9a5266972547
|
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:c556dd707e179bad13b9418a8816820d965e8f8053c49ba44dc2bd9e5d8ff8e2
|
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:cdd838cf12f681078dde6b6eb6069acb3bfa242ada76ed068ad282e01d2e9d3a
|
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": 0.998691442030882,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6349887008187156,
|
5 |
+
"train_runtime": 13807.6715,
|
6 |
+
"train_samples": 61135,
|
7 |
+
"train_samples_per_second": 4.428,
|
8 |
+
"train_steps_per_second": 0.035
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.998691442030882,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 477,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.002093692750588851,
|
13 |
+
"grad_norm": 4.60470009024502,
|
14 |
+
"learning_rate": 1.0416666666666666e-08,
|
15 |
+
"logits/chosen": 5002.53564453125,
|
16 |
+
"logits/rejected": 4591.72021484375,
|
17 |
+
"logps/chosen": -265.6396789550781,
|
18 |
+
"logps/rejected": -206.22401428222656,
|
19 |
+
"loss": 0.6931,
|
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": 0.02093692750588851,
|
28 |
+
"grad_norm": 3.9004836147811037,
|
29 |
+
"learning_rate": 1.0416666666666667e-07,
|
30 |
+
"logits/chosen": 5977.43212890625,
|
31 |
+
"logits/rejected": 5015.40087890625,
|
32 |
+
"logps/chosen": -292.5469970703125,
|
33 |
+
"logps/rejected": -259.3294677734375,
|
34 |
+
"loss": 0.6931,
|
35 |
+
"rewards/accuracies": 0.4618055522441864,
|
36 |
+
"rewards/chosen": 0.00013807312643621117,
|
37 |
+
"rewards/margins": 0.00019646011060103774,
|
38 |
+
"rewards/rejected": -5.838695869897492e-05,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04187385501177702,
|
43 |
+
"grad_norm": 4.409000344379127,
|
44 |
+
"learning_rate": 2.0833333333333333e-07,
|
45 |
+
"logits/chosen": 5877.6181640625,
|
46 |
+
"logits/rejected": 4855.9072265625,
|
47 |
+
"logps/chosen": -290.42059326171875,
|
48 |
+
"logps/rejected": -249.79830932617188,
|
49 |
+
"loss": 0.6926,
|
50 |
+
"rewards/accuracies": 0.6343749761581421,
|
51 |
+
"rewards/chosen": 0.0017289689276367426,
|
52 |
+
"rewards/margins": 0.002378009492531419,
|
53 |
+
"rewards/rejected": -0.000649040739517659,
|
54 |
+
"step": 20
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.06281078251766553,
|
58 |
+
"grad_norm": 4.1115595198104895,
|
59 |
+
"learning_rate": 3.1249999999999997e-07,
|
60 |
+
"logits/chosen": 5644.3134765625,
|
61 |
+
"logits/rejected": 4922.59326171875,
|
62 |
+
"logps/chosen": -270.7469787597656,
|
63 |
+
"logps/rejected": -238.15133666992188,
|
64 |
+
"loss": 0.6907,
|
65 |
+
"rewards/accuracies": 0.581250011920929,
|
66 |
+
"rewards/chosen": 0.014904869720339775,
|
67 |
+
"rewards/margins": 0.008396080695092678,
|
68 |
+
"rewards/rejected": 0.00650878855958581,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.08374771002355404,
|
73 |
+
"grad_norm": 3.9812692815534487,
|
74 |
+
"learning_rate": 4.1666666666666667e-07,
|
75 |
+
"logits/chosen": 5738.85693359375,
|
76 |
+
"logits/rejected": 4991.9970703125,
|
77 |
+
"logps/chosen": -269.1136169433594,
|
78 |
+
"logps/rejected": -256.45672607421875,
|
79 |
+
"loss": 0.6855,
|
80 |
+
"rewards/accuracies": 0.6781250238418579,
|
81 |
+
"rewards/chosen": 0.04843459650874138,
|
82 |
+
"rewards/margins": 0.0284621212631464,
|
83 |
+
"rewards/rejected": 0.01997247338294983,
|
84 |
+
"step": 40
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.10468463752944256,
|
88 |
+
"grad_norm": 4.46544140589733,
|
89 |
+
"learning_rate": 4.999731868769026e-07,
|
90 |
+
"logits/chosen": 6019.5712890625,
|
91 |
+
"logits/rejected": 5225.3515625,
|
92 |
+
"logps/chosen": -276.187744140625,
|
93 |
+
"logps/rejected": -271.6847839355469,
|
94 |
+
"loss": 0.6789,
|
95 |
+
"rewards/accuracies": 0.6812499761581421,
|
96 |
+
"rewards/chosen": 0.02429984137415886,
|
97 |
+
"rewards/margins": 0.0659550279378891,
|
98 |
+
"rewards/rejected": -0.04165518283843994,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.12562156503533106,
|
103 |
+
"grad_norm": 4.993454825378816,
|
104 |
+
"learning_rate": 4.990353313429303e-07,
|
105 |
+
"logits/chosen": 5790.12646484375,
|
106 |
+
"logits/rejected": 4928.04296875,
|
107 |
+
"logps/chosen": -284.0537109375,
|
108 |
+
"logps/rejected": -269.0484313964844,
|
109 |
+
"loss": 0.6716,
|
110 |
+
"rewards/accuracies": 0.6781250238418579,
|
111 |
+
"rewards/chosen": -0.05631242319941521,
|
112 |
+
"rewards/margins": 0.11938270181417465,
|
113 |
+
"rewards/rejected": -0.17569510638713837,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.14655849254121958,
|
118 |
+
"grad_norm": 6.738341247222451,
|
119 |
+
"learning_rate": 4.967625656594781e-07,
|
120 |
+
"logits/chosen": 5591.57421875,
|
121 |
+
"logits/rejected": 5146.23779296875,
|
122 |
+
"logps/chosen": -288.3265380859375,
|
123 |
+
"logps/rejected": -293.3169860839844,
|
124 |
+
"loss": 0.664,
|
125 |
+
"rewards/accuracies": 0.659375011920929,
|
126 |
+
"rewards/chosen": -0.1001863032579422,
|
127 |
+
"rewards/margins": 0.16495101153850555,
|
128 |
+
"rewards/rejected": -0.26513734459877014,
|
129 |
+
"step": 70
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16749542004710807,
|
133 |
+
"grad_norm": 6.195725545958302,
|
134 |
+
"learning_rate": 4.93167072587771e-07,
|
135 |
+
"logits/chosen": 5745.04443359375,
|
136 |
+
"logits/rejected": 4929.4033203125,
|
137 |
+
"logps/chosen": -285.25628662109375,
|
138 |
+
"logps/rejected": -284.0039367675781,
|
139 |
+
"loss": 0.6578,
|
140 |
+
"rewards/accuracies": 0.6781250238418579,
|
141 |
+
"rewards/chosen": -0.09169374406337738,
|
142 |
+
"rewards/margins": 0.2176208794116974,
|
143 |
+
"rewards/rejected": -0.30931463837623596,
|
144 |
+
"step": 80
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.1884323475529966,
|
148 |
+
"grad_norm": 8.253469662871487,
|
149 |
+
"learning_rate": 4.882681251368548e-07,
|
150 |
+
"logits/chosen": 5881.85693359375,
|
151 |
+
"logits/rejected": 4956.69482421875,
|
152 |
+
"logps/chosen": -295.1579895019531,
|
153 |
+
"logps/rejected": -297.10235595703125,
|
154 |
+
"loss": 0.654,
|
155 |
+
"rewards/accuracies": 0.684374988079071,
|
156 |
+
"rewards/chosen": -0.1745041012763977,
|
157 |
+
"rewards/margins": 0.24678310751914978,
|
158 |
+
"rewards/rejected": -0.4212872087955475,
|
159 |
+
"step": 90
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.2093692750588851,
|
163 |
+
"grad_norm": 9.862843851151778,
|
164 |
+
"learning_rate": 4.820919832540181e-07,
|
165 |
+
"logits/chosen": 5971.64794921875,
|
166 |
+
"logits/rejected": 5451.3154296875,
|
167 |
+
"logps/chosen": -310.86712646484375,
|
168 |
+
"logps/rejected": -344.1552734375,
|
169 |
+
"loss": 0.6478,
|
170 |
+
"rewards/accuracies": 0.6875,
|
171 |
+
"rewards/chosen": -0.3099839687347412,
|
172 |
+
"rewards/margins": 0.38641446828842163,
|
173 |
+
"rewards/rejected": -0.6963984370231628,
|
174 |
+
"step": 100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.23030620256477363,
|
178 |
+
"grad_norm": 7.664167361758326,
|
179 |
+
"learning_rate": 4.7467175306295647e-07,
|
180 |
+
"logits/chosen": 6156.85791015625,
|
181 |
+
"logits/rejected": 4974.04296875,
|
182 |
+
"logps/chosen": -305.1463317871094,
|
183 |
+
"logps/rejected": -332.91363525390625,
|
184 |
+
"loss": 0.6379,
|
185 |
+
"rewards/accuracies": 0.7124999761581421,
|
186 |
+
"rewards/chosen": -0.3052375018596649,
|
187 |
+
"rewards/margins": 0.4351824223995209,
|
188 |
+
"rewards/rejected": -0.7404199838638306,
|
189 |
+
"step": 110
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.2512431300706621,
|
193 |
+
"grad_norm": 8.556770009207627,
|
194 |
+
"learning_rate": 4.6604720940421207e-07,
|
195 |
+
"logits/chosen": 5761.1591796875,
|
196 |
+
"logits/rejected": 5308.05224609375,
|
197 |
+
"logps/chosen": -308.85296630859375,
|
198 |
+
"logps/rejected": -346.0533447265625,
|
199 |
+
"loss": 0.6438,
|
200 |
+
"rewards/accuracies": 0.699999988079071,
|
201 |
+
"rewards/chosen": -0.41673964262008667,
|
202 |
+
"rewards/margins": 0.37503576278686523,
|
203 |
+
"rewards/rejected": -0.7917754054069519,
|
204 |
+
"step": 120
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.2721800575765506,
|
208 |
+
"grad_norm": 11.15595897330077,
|
209 |
+
"learning_rate": 4.5626458262912735e-07,
|
210 |
+
"logits/chosen": 5819.66357421875,
|
211 |
+
"logits/rejected": 5165.65771484375,
|
212 |
+
"logps/chosen": -305.6595458984375,
|
213 |
+
"logps/rejected": -344.2333679199219,
|
214 |
+
"loss": 0.6412,
|
215 |
+
"rewards/accuracies": 0.690625011920929,
|
216 |
+
"rewards/chosen": -0.37142214179039,
|
217 |
+
"rewards/margins": 0.38082534074783325,
|
218 |
+
"rewards/rejected": -0.7522474527359009,
|
219 |
+
"step": 130
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.29311698508243916,
|
223 |
+
"grad_norm": 8.207443336589154,
|
224 |
+
"learning_rate": 4.453763107901675e-07,
|
225 |
+
"logits/chosen": 5615.36279296875,
|
226 |
+
"logits/rejected": 4947.9091796875,
|
227 |
+
"logps/chosen": -302.700927734375,
|
228 |
+
"logps/rejected": -326.2046203613281,
|
229 |
+
"loss": 0.6425,
|
230 |
+
"rewards/accuracies": 0.7124999761581421,
|
231 |
+
"rewards/chosen": -0.30796128511428833,
|
232 |
+
"rewards/margins": 0.4427562654018402,
|
233 |
+
"rewards/rejected": -0.7507175207138062,
|
234 |
+
"step": 140
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.31405391258832765,
|
238 |
+
"grad_norm": 11.288023963328941,
|
239 |
+
"learning_rate": 4.3344075855595097e-07,
|
240 |
+
"logits/chosen": 6199.8349609375,
|
241 |
+
"logits/rejected": 5057.89990234375,
|
242 |
+
"logps/chosen": -339.68829345703125,
|
243 |
+
"logps/rejected": -355.90643310546875,
|
244 |
+
"loss": 0.636,
|
245 |
+
"rewards/accuracies": 0.7437499761581421,
|
246 |
+
"rewards/chosen": -0.5057331323623657,
|
247 |
+
"rewards/margins": 0.5384237766265869,
|
248 |
+
"rewards/rejected": -1.044156789779663,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.33499084009421615,
|
253 |
+
"grad_norm": 10.16845225583156,
|
254 |
+
"learning_rate": 4.2052190435769554e-07,
|
255 |
+
"logits/chosen": 5847.75634765625,
|
256 |
+
"logits/rejected": 4841.6728515625,
|
257 |
+
"logps/chosen": -347.44244384765625,
|
258 |
+
"logps/rejected": -371.6456604003906,
|
259 |
+
"loss": 0.6265,
|
260 |
+
"rewards/accuracies": 0.7406250238418579,
|
261 |
+
"rewards/chosen": -0.6284831762313843,
|
262 |
+
"rewards/margins": 0.5241909027099609,
|
263 |
+
"rewards/rejected": -1.1526740789413452,
|
264 |
+
"step": 160
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.3559277676001047,
|
268 |
+
"grad_norm": 12.422675446136871,
|
269 |
+
"learning_rate": 4.0668899744407567e-07,
|
270 |
+
"logits/chosen": 6190.0078125,
|
271 |
+
"logits/rejected": 5228.7177734375,
|
272 |
+
"logps/chosen": -333.79241943359375,
|
273 |
+
"logps/rejected": -341.86968994140625,
|
274 |
+
"loss": 0.6269,
|
275 |
+
"rewards/accuracies": 0.7250000238418579,
|
276 |
+
"rewards/chosen": -0.5147669911384583,
|
277 |
+
"rewards/margins": 0.4974791407585144,
|
278 |
+
"rewards/rejected": -1.012246012687683,
|
279 |
+
"step": 170
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.3768646951059932,
|
283 |
+
"grad_norm": 8.193752614141884,
|
284 |
+
"learning_rate": 3.920161866827889e-07,
|
285 |
+
"logits/chosen": 5827.63427734375,
|
286 |
+
"logits/rejected": 4925.3046875,
|
287 |
+
"logps/chosen": -342.14068603515625,
|
288 |
+
"logps/rejected": -365.3731689453125,
|
289 |
+
"loss": 0.6314,
|
290 |
+
"rewards/accuracies": 0.7437499761581421,
|
291 |
+
"rewards/chosen": -0.548454225063324,
|
292 |
+
"rewards/margins": 0.6054696440696716,
|
293 |
+
"rewards/rejected": -1.1539238691329956,
|
294 |
+
"step": 180
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.39780162261188173,
|
298 |
+
"grad_norm": 11.037520790820944,
|
299 |
+
"learning_rate": 3.765821230985757e-07,
|
300 |
+
"logits/chosen": 5962.33056640625,
|
301 |
+
"logits/rejected": 4930.44091796875,
|
302 |
+
"logps/chosen": -310.32427978515625,
|
303 |
+
"logps/rejected": -358.37774658203125,
|
304 |
+
"loss": 0.6203,
|
305 |
+
"rewards/accuracies": 0.7593749761581421,
|
306 |
+
"rewards/chosen": -0.40572792291641235,
|
307 |
+
"rewards/margins": 0.6992164850234985,
|
308 |
+
"rewards/rejected": -1.1049444675445557,
|
309 |
+
"step": 190
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.4187385501177702,
|
313 |
+
"grad_norm": 9.527716723410062,
|
314 |
+
"learning_rate": 3.604695382782159e-07,
|
315 |
+
"logits/chosen": 5604.3310546875,
|
316 |
+
"logits/rejected": 4814.98828125,
|
317 |
+
"logps/chosen": -303.8848876953125,
|
318 |
+
"logps/rejected": -348.39678955078125,
|
319 |
+
"loss": 0.6349,
|
320 |
+
"rewards/accuracies": 0.7250000238418579,
|
321 |
+
"rewards/chosen": -0.495340496301651,
|
322 |
+
"rewards/margins": 0.5600203275680542,
|
323 |
+
"rewards/rejected": -1.0553607940673828,
|
324 |
+
"step": 200
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.4396754776236587,
|
328 |
+
"grad_norm": 12.016875634198213,
|
329 |
+
"learning_rate": 3.4376480090239047e-07,
|
330 |
+
"logits/chosen": 6233.3984375,
|
331 |
+
"logits/rejected": 5250.013671875,
|
332 |
+
"logps/chosen": -342.68585205078125,
|
333 |
+
"logps/rejected": -369.70904541015625,
|
334 |
+
"loss": 0.63,
|
335 |
+
"rewards/accuracies": 0.7124999761581421,
|
336 |
+
"rewards/chosen": -0.5591845512390137,
|
337 |
+
"rewards/margins": 0.5208701491355896,
|
338 |
+
"rewards/rejected": -1.0800548791885376,
|
339 |
+
"step": 210
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.46061240512954726,
|
343 |
+
"grad_norm": 12.10521639246573,
|
344 |
+
"learning_rate": 3.265574537815398e-07,
|
345 |
+
"logits/chosen": 5601.2353515625,
|
346 |
+
"logits/rejected": 5141.3740234375,
|
347 |
+
"logps/chosen": -329.7219543457031,
|
348 |
+
"logps/rejected": -389.0228271484375,
|
349 |
+
"loss": 0.6191,
|
350 |
+
"rewards/accuracies": 0.778124988079071,
|
351 |
+
"rewards/chosen": -0.5860620737075806,
|
352 |
+
"rewards/margins": 0.7007312178611755,
|
353 |
+
"rewards/rejected": -1.2867933511734009,
|
354 |
+
"step": 220
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.48154933263543576,
|
358 |
+
"grad_norm": 10.132071032109883,
|
359 |
+
"learning_rate": 3.0893973387735683e-07,
|
360 |
+
"logits/chosen": 5776.4091796875,
|
361 |
+
"logits/rejected": 4840.046875,
|
362 |
+
"logps/chosen": -335.4309997558594,
|
363 |
+
"logps/rejected": -385.7275695800781,
|
364 |
+
"loss": 0.619,
|
365 |
+
"rewards/accuracies": 0.7749999761581421,
|
366 |
+
"rewards/chosen": -0.6716222763061523,
|
367 |
+
"rewards/margins": 0.7313363552093506,
|
368 |
+
"rewards/rejected": -1.402958631515503,
|
369 |
+
"step": 230
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.5024862601413242,
|
373 |
+
"grad_norm": 11.646693213650721,
|
374 |
+
"learning_rate": 2.910060778827554e-07,
|
375 |
+
"logits/chosen": 5956.8095703125,
|
376 |
+
"logits/rejected": 4968.13232421875,
|
377 |
+
"logps/chosen": -334.1136779785156,
|
378 |
+
"logps/rejected": -376.6734619140625,
|
379 |
+
"loss": 0.6266,
|
380 |
+
"rewards/accuracies": 0.7281249761581421,
|
381 |
+
"rewards/chosen": -0.6853675246238708,
|
382 |
+
"rewards/margins": 0.5835575461387634,
|
383 |
+
"rewards/rejected": -1.2689251899719238,
|
384 |
+
"step": 240
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.5234231876472127,
|
388 |
+
"grad_norm": 9.693640002493433,
|
389 |
+
"learning_rate": 2.7285261601056697e-07,
|
390 |
+
"logits/chosen": 6025.3310546875,
|
391 |
+
"logits/rejected": 5018.666015625,
|
392 |
+
"logps/chosen": -362.75250244140625,
|
393 |
+
"logps/rejected": -400.90155029296875,
|
394 |
+
"loss": 0.6285,
|
395 |
+
"rewards/accuracies": 0.7250000238418579,
|
396 |
+
"rewards/chosen": -0.7680386304855347,
|
397 |
+
"rewards/margins": 0.6202248334884644,
|
398 |
+
"rewards/rejected": -1.3882635831832886,
|
399 |
+
"step": 250
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.5443601151531012,
|
403 |
+
"grad_norm": 12.110581184936667,
|
404 |
+
"learning_rate": 2.5457665670441937e-07,
|
405 |
+
"logits/chosen": 5841.02197265625,
|
406 |
+
"logits/rejected": 5221.95703125,
|
407 |
+
"logps/chosen": -350.9548034667969,
|
408 |
+
"logps/rejected": -391.574951171875,
|
409 |
+
"loss": 0.6227,
|
410 |
+
"rewards/accuracies": 0.7875000238418579,
|
411 |
+
"rewards/chosen": -0.6488569974899292,
|
412 |
+
"rewards/margins": 0.6560698747634888,
|
413 |
+
"rewards/rejected": -1.304926872253418,
|
414 |
+
"step": 260
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.5652970426589898,
|
418 |
+
"grad_norm": 11.095733736590391,
|
419 |
+
"learning_rate": 2.3627616503391812e-07,
|
420 |
+
"logits/chosen": 5896.1123046875,
|
421 |
+
"logits/rejected": 5345.4794921875,
|
422 |
+
"logps/chosen": -338.3013000488281,
|
423 |
+
"logps/rejected": -395.18365478515625,
|
424 |
+
"loss": 0.6222,
|
425 |
+
"rewards/accuracies": 0.784375011920929,
|
426 |
+
"rewards/chosen": -0.6368743777275085,
|
427 |
+
"rewards/margins": 0.7109971046447754,
|
428 |
+
"rewards/rejected": -1.3478715419769287,
|
429 |
+
"step": 270
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5862339701648783,
|
433 |
+
"grad_norm": 9.899171422824232,
|
434 |
+
"learning_rate": 2.1804923757009882e-07,
|
435 |
+
"logits/chosen": 5956.20751953125,
|
436 |
+
"logits/rejected": 4884.17724609375,
|
437 |
+
"logps/chosen": -336.65655517578125,
|
438 |
+
"logps/rejected": -378.20257568359375,
|
439 |
+
"loss": 0.6209,
|
440 |
+
"rewards/accuracies": 0.737500011920929,
|
441 |
+
"rewards/chosen": -0.5593088269233704,
|
442 |
+
"rewards/margins": 0.7548757791519165,
|
443 |
+
"rewards/rejected": -1.314184546470642,
|
444 |
+
"step": 280
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.6071708976707668,
|
448 |
+
"grad_norm": 14.00097312046503,
|
449 |
+
"learning_rate": 1.9999357655598891e-07,
|
450 |
+
"logits/chosen": 6179.2138671875,
|
451 |
+
"logits/rejected": 5698.1767578125,
|
452 |
+
"logps/chosen": -375.6763000488281,
|
453 |
+
"logps/rejected": -440.81805419921875,
|
454 |
+
"loss": 0.6268,
|
455 |
+
"rewards/accuracies": 0.715624988079071,
|
456 |
+
"rewards/chosen": -0.8424223065376282,
|
457 |
+
"rewards/margins": 0.5865424275398254,
|
458 |
+
"rewards/rejected": -1.4289648532867432,
|
459 |
+
"step": 290
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.6281078251766553,
|
463 |
+
"grad_norm": 14.203557312456628,
|
464 |
+
"learning_rate": 1.8220596619089573e-07,
|
465 |
+
"logits/chosen": 5657.166015625,
|
466 |
+
"logits/rejected": 5264.8466796875,
|
467 |
+
"logps/chosen": -350.72784423828125,
|
468 |
+
"logps/rejected": -411.1917419433594,
|
469 |
+
"loss": 0.6231,
|
470 |
+
"rewards/accuracies": 0.721875011920929,
|
471 |
+
"rewards/chosen": -0.7937782406806946,
|
472 |
+
"rewards/margins": 0.6089503765106201,
|
473 |
+
"rewards/rejected": -1.40272855758667,
|
474 |
+
"step": 300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.6490447526825438,
|
478 |
+
"grad_norm": 10.770674638912404,
|
479 |
+
"learning_rate": 1.647817538357072e-07,
|
480 |
+
"logits/chosen": 6337.3076171875,
|
481 |
+
"logits/rejected": 5510.4892578125,
|
482 |
+
"logps/chosen": -360.8718566894531,
|
483 |
+
"logps/rejected": -397.1591796875,
|
484 |
+
"loss": 0.6192,
|
485 |
+
"rewards/accuracies": 0.765625,
|
486 |
+
"rewards/chosen": -0.7004226446151733,
|
487 |
+
"rewards/margins": 0.5756019353866577,
|
488 |
+
"rewards/rejected": -1.2760246992111206,
|
489 |
+
"step": 310
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.6699816801884323,
|
493 |
+
"grad_norm": 12.586206352705796,
|
494 |
+
"learning_rate": 1.478143389201113e-07,
|
495 |
+
"logits/chosen": 5900.0009765625,
|
496 |
+
"logits/rejected": 5053.62744140625,
|
497 |
+
"logps/chosen": -338.50836181640625,
|
498 |
+
"logps/rejected": -400.8262023925781,
|
499 |
+
"loss": 0.6206,
|
500 |
+
"rewards/accuracies": 0.7437499761581421,
|
501 |
+
"rewards/chosen": -0.666448712348938,
|
502 |
+
"rewards/margins": 0.7436891198158264,
|
503 |
+
"rewards/rejected": -1.4101378917694092,
|
504 |
+
"step": 320
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.6909186076943209,
|
508 |
+
"grad_norm": 11.467937206667434,
|
509 |
+
"learning_rate": 1.3139467229135998e-07,
|
510 |
+
"logits/chosen": 5687.28564453125,
|
511 |
+
"logits/rejected": 5192.236328125,
|
512 |
+
"logps/chosen": -344.19000244140625,
|
513 |
+
"logps/rejected": -401.15484619140625,
|
514 |
+
"loss": 0.6266,
|
515 |
+
"rewards/accuracies": 0.768750011920929,
|
516 |
+
"rewards/chosen": -0.6740574240684509,
|
517 |
+
"rewards/margins": 0.6941967010498047,
|
518 |
+
"rewards/rejected": -1.3682540655136108,
|
519 |
+
"step": 330
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.7118555352002094,
|
523 |
+
"grad_norm": 12.06333657205332,
|
524 |
+
"learning_rate": 1.1561076868822755e-07,
|
525 |
+
"logits/chosen": 5517.1494140625,
|
526 |
+
"logits/rejected": 4742.1181640625,
|
527 |
+
"logps/chosen": -323.6866760253906,
|
528 |
+
"logps/rejected": -374.42169189453125,
|
529 |
+
"loss": 0.6239,
|
530 |
+
"rewards/accuracies": 0.7281249761581421,
|
531 |
+
"rewards/chosen": -0.6611974239349365,
|
532 |
+
"rewards/margins": 0.6709928512573242,
|
533 |
+
"rewards/rejected": -1.3321901559829712,
|
534 |
+
"step": 340
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.7327924627060979,
|
538 |
+
"grad_norm": 11.532722063890231,
|
539 |
+
"learning_rate": 1.0054723495346482e-07,
|
540 |
+
"logits/chosen": 6202.3583984375,
|
541 |
+
"logits/rejected": 4977.18115234375,
|
542 |
+
"logps/chosen": -362.2864990234375,
|
543 |
+
"logps/rejected": -393.2933349609375,
|
544 |
+
"loss": 0.6251,
|
545 |
+
"rewards/accuracies": 0.768750011920929,
|
546 |
+
"rewards/chosen": -0.6137198209762573,
|
547 |
+
"rewards/margins": 0.635828971862793,
|
548 |
+
"rewards/rejected": -1.2495489120483398,
|
549 |
+
"step": 350
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.7537293902119864,
|
553 |
+
"grad_norm": 12.827074983628805,
|
554 |
+
"learning_rate": 8.628481651367875e-08,
|
555 |
+
"logits/chosen": 5883.3125,
|
556 |
+
"logits/rejected": 5070.5986328125,
|
557 |
+
"logps/chosen": -341.68011474609375,
|
558 |
+
"logps/rejected": -390.2152099609375,
|
559 |
+
"loss": 0.6263,
|
560 |
+
"rewards/accuracies": 0.737500011920929,
|
561 |
+
"rewards/chosen": -0.6395655870437622,
|
562 |
+
"rewards/margins": 0.6800642013549805,
|
563 |
+
"rewards/rejected": -1.3196299076080322,
|
564 |
+
"step": 360
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.7746663177178749,
|
568 |
+
"grad_norm": 9.251136847302337,
|
569 |
+
"learning_rate": 7.289996455765748e-08,
|
570 |
+
"logits/chosen": 5781.0732421875,
|
571 |
+
"logits/rejected": 4854.42333984375,
|
572 |
+
"logps/chosen": -352.7303161621094,
|
573 |
+
"logps/rejected": -394.6329345703125,
|
574 |
+
"loss": 0.6134,
|
575 |
+
"rewards/accuracies": 0.778124988079071,
|
576 |
+
"rewards/chosen": -0.639372706413269,
|
577 |
+
"rewards/margins": 0.7373119592666626,
|
578 |
+
"rewards/rejected": -1.376684546470642,
|
579 |
+
"step": 370
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.7956032452237635,
|
583 |
+
"grad_norm": 12.098049848889806,
|
584 |
+
"learning_rate": 6.046442623320145e-08,
|
585 |
+
"logits/chosen": 6060.8408203125,
|
586 |
+
"logits/rejected": 5173.55126953125,
|
587 |
+
"logps/chosen": -345.76519775390625,
|
588 |
+
"logps/rejected": -371.1272888183594,
|
589 |
+
"loss": 0.6248,
|
590 |
+
"rewards/accuracies": 0.753125011920929,
|
591 |
+
"rewards/chosen": -0.6106373071670532,
|
592 |
+
"rewards/margins": 0.5920594334602356,
|
593 |
+
"rewards/rejected": -1.202696681022644,
|
594 |
+
"step": 380
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.816540172729652,
|
598 |
+
"grad_norm": 9.994672177952491,
|
599 |
+
"learning_rate": 4.904486005914027e-08,
|
600 |
+
"logits/chosen": 6291.39501953125,
|
601 |
+
"logits/rejected": 5494.92431640625,
|
602 |
+
"logps/chosen": -351.2883605957031,
|
603 |
+
"logps/rejected": -405.6934814453125,
|
604 |
+
"loss": 0.6161,
|
605 |
+
"rewards/accuracies": 0.7562500238418579,
|
606 |
+
"rewards/chosen": -0.5953892469406128,
|
607 |
+
"rewards/margins": 0.7137786746025085,
|
608 |
+
"rewards/rejected": -1.3091679811477661,
|
609 |
+
"step": 390
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.8374771002355405,
|
613 |
+
"grad_norm": 10.018943299981588,
|
614 |
+
"learning_rate": 3.8702478614051345e-08,
|
615 |
+
"logits/chosen": 5870.2626953125,
|
616 |
+
"logits/rejected": 5131.064453125,
|
617 |
+
"logps/chosen": -352.17132568359375,
|
618 |
+
"logps/rejected": -379.8227233886719,
|
619 |
+
"loss": 0.6228,
|
620 |
+
"rewards/accuracies": 0.75,
|
621 |
+
"rewards/chosen": -0.6126725673675537,
|
622 |
+
"rewards/margins": 0.626976490020752,
|
623 |
+
"rewards/rejected": -1.2396490573883057,
|
624 |
+
"step": 400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.8584140277414289,
|
628 |
+
"grad_norm": 12.50787678673054,
|
629 |
+
"learning_rate": 2.9492720416985e-08,
|
630 |
+
"logits/chosen": 5846.2509765625,
|
631 |
+
"logits/rejected": 5063.88818359375,
|
632 |
+
"logps/chosen": -348.4322814941406,
|
633 |
+
"logps/rejected": -408.62237548828125,
|
634 |
+
"loss": 0.6161,
|
635 |
+
"rewards/accuracies": 0.71875,
|
636 |
+
"rewards/chosen": -0.6656492948532104,
|
637 |
+
"rewards/margins": 0.6094722151756287,
|
638 |
+
"rewards/rejected": -1.2751215696334839,
|
639 |
+
"step": 410
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.8793509552473174,
|
643 |
+
"grad_norm": 13.503737918548683,
|
644 |
+
"learning_rate": 2.1464952759020856e-08,
|
645 |
+
"logits/chosen": 6236.7607421875,
|
646 |
+
"logits/rejected": 5383.3154296875,
|
647 |
+
"logps/chosen": -355.6968994140625,
|
648 |
+
"logps/rejected": -402.67681884765625,
|
649 |
+
"loss": 0.6183,
|
650 |
+
"rewards/accuracies": 0.746874988079071,
|
651 |
+
"rewards/chosen": -0.6371773481369019,
|
652 |
+
"rewards/margins": 0.6647071242332458,
|
653 |
+
"rewards/rejected": -1.3018845319747925,
|
654 |
+
"step": 420
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.9002878827532059,
|
658 |
+
"grad_norm": 12.19770327814421,
|
659 |
+
"learning_rate": 1.4662207078575684e-08,
|
660 |
+
"logits/chosen": 6165.9990234375,
|
661 |
+
"logits/rejected": 4889.5029296875,
|
662 |
+
"logps/chosen": -349.86297607421875,
|
663 |
+
"logps/rejected": -390.2151184082031,
|
664 |
+
"loss": 0.6092,
|
665 |
+
"rewards/accuracies": 0.768750011920929,
|
666 |
+
"rewards/chosen": -0.6226025819778442,
|
667 |
+
"rewards/margins": 0.7049604654312134,
|
668 |
+
"rewards/rejected": -1.3275630474090576,
|
669 |
+
"step": 430
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.9212248102590945,
|
673 |
+
"grad_norm": 11.802179491960299,
|
674 |
+
"learning_rate": 9.12094829893642e-09,
|
675 |
+
"logits/chosen": 5992.05029296875,
|
676 |
+
"logits/rejected": 5618.6328125,
|
677 |
+
"logps/chosen": -338.279541015625,
|
678 |
+
"logps/rejected": -399.9471130371094,
|
679 |
+
"loss": 0.6193,
|
680 |
+
"rewards/accuracies": 0.7437499761581421,
|
681 |
+
"rewards/chosen": -0.5973601937294006,
|
682 |
+
"rewards/margins": 0.6416517496109009,
|
683 |
+
"rewards/rejected": -1.2390120029449463,
|
684 |
+
"step": 440
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.942161737764983,
|
688 |
+
"grad_norm": 15.288231020941236,
|
689 |
+
"learning_rate": 4.8708793644441086e-09,
|
690 |
+
"logits/chosen": 6121.3330078125,
|
691 |
+
"logits/rejected": 5176.08349609375,
|
692 |
+
"logps/chosen": -350.21331787109375,
|
693 |
+
"logps/rejected": -387.7196044921875,
|
694 |
+
"loss": 0.6177,
|
695 |
+
"rewards/accuracies": 0.7906249761581421,
|
696 |
+
"rewards/chosen": -0.598780632019043,
|
697 |
+
"rewards/margins": 0.6639107465744019,
|
698 |
+
"rewards/rejected": -1.2626912593841553,
|
699 |
+
"step": 450
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.9630986652708715,
|
703 |
+
"grad_norm": 14.093283682723904,
|
704 |
+
"learning_rate": 1.9347820230782295e-09,
|
705 |
+
"logits/chosen": 6296.310546875,
|
706 |
+
"logits/rejected": 5237.2060546875,
|
707 |
+
"logps/chosen": -378.281982421875,
|
708 |
+
"logps/rejected": -422.67242431640625,
|
709 |
+
"loss": 0.6236,
|
710 |
+
"rewards/accuracies": 0.753125011920929,
|
711 |
+
"rewards/chosen": -0.652829647064209,
|
712 |
+
"rewards/margins": 0.7167678475379944,
|
713 |
+
"rewards/rejected": -1.3695974349975586,
|
714 |
+
"step": 460
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.98403559277676,
|
718 |
+
"grad_norm": 9.706197753513703,
|
719 |
+
"learning_rate": 3.2839470889836627e-10,
|
720 |
+
"logits/chosen": 5874.50830078125,
|
721 |
+
"logits/rejected": 5139.2998046875,
|
722 |
+
"logps/chosen": -342.42303466796875,
|
723 |
+
"logps/rejected": -391.7164001464844,
|
724 |
+
"loss": 0.6113,
|
725 |
+
"rewards/accuracies": 0.7749999761581421,
|
726 |
+
"rewards/chosen": -0.6158385872840881,
|
727 |
+
"rewards/margins": 0.7232969999313354,
|
728 |
+
"rewards/rejected": -1.3391354084014893,
|
729 |
+
"step": 470
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.998691442030882,
|
733 |
+
"step": 477,
|
734 |
+
"total_flos": 0.0,
|
735 |
+
"train_loss": 0.6349887008187156,
|
736 |
+
"train_runtime": 13807.6715,
|
737 |
+
"train_samples_per_second": 4.428,
|
738 |
+
"train_steps_per_second": 0.035
|
739 |
+
}
|
740 |
+
],
|
741 |
+
"logging_steps": 10,
|
742 |
+
"max_steps": 477,
|
743 |
+
"num_input_tokens_seen": 0,
|
744 |
+
"num_train_epochs": 1,
|
745 |
+
"save_steps": 1000,
|
746 |
+
"stateful_callbacks": {
|
747 |
+
"TrainerControl": {
|
748 |
+
"args": {
|
749 |
+
"should_epoch_stop": false,
|
750 |
+
"should_evaluate": false,
|
751 |
+
"should_log": false,
|
752 |
+
"should_save": false,
|
753 |
+
"should_training_stop": false
|
754 |
+
},
|
755 |
+
"attributes": {}
|
756 |
+
}
|
757 |
+
},
|
758 |
+
"total_flos": 0.0,
|
759 |
+
"train_batch_size": 4,
|
760 |
+
"trial_name": null,
|
761 |
+
"trial_params": null
|
762 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a33c767137d0c36202448a692d7d2d1193a5a2a1630b5c75e469d1e01822bb80
|
3 |
+
size 7288
|