Model save
Browse files- README.md +61 -0
- all_results.json +8 -0
- generation_config.json +7 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +261 -0
- train_results.json +8 -0
- trainer_state.json +212 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: google/gemma-7b
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
model-index:
|
11 |
+
- name: gemma-7b-sft-full-dolly-v2
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# gemma-7b-sft-full-dolly-v2
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 8
|
45 |
+
- total_train_batch_size: 32
|
46 |
+
- total_eval_batch_size: 128
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 3
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.39.0.dev0
|
59 |
+
- Pytorch 2.1.2+cu121
|
60 |
+
- Datasets 2.14.6
|
61 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 4.938086860863737,
|
4 |
+
"train_runtime": 252.0914,
|
5 |
+
"train_samples": 15011,
|
6 |
+
"train_samples_per_second": 16.232,
|
7 |
+
"train_steps_per_second": 0.512
|
8 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.39.0.dev0"
|
7 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a266860e774d82834c64ede9bb243040d9f420425635f7ff67a0db593c0c3f84
|
3 |
+
size 4995496656
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b537902fe40fe0b63a4c1d247a28c8516371ebdab650e839115f40f41aa90724
|
3 |
+
size 4982953168
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46c52984decd4e346010b35550c5ca693360e24f27a78fae713df3559b58e554
|
3 |
+
size 4982953200
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e4188b3e0f0891b92164192192d13381df6608640fd8652a269b726dae717b
|
3 |
+
size 2113988336
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 17075361792
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
97 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
106 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
178 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
187 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
196 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
205 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
214 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
232 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
241 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
250 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
259 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
260 |
+
}
|
261 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 4.938086860863737,
|
4 |
+
"train_runtime": 252.0914,
|
5 |
+
"train_samples": 15011,
|
6 |
+
"train_samples_per_second": 16.232,
|
7 |
+
"train_steps_per_second": 0.512
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 129,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 8701.357710303886,
|
14 |
+
"learning_rate": 1.5384615384615387e-06,
|
15 |
+
"loss": 28.3212,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12,
|
20 |
+
"grad_norm": 481.362737716594,
|
21 |
+
"learning_rate": 7.692307692307694e-06,
|
22 |
+
"loss": 22.1134,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23,
|
27 |
+
"grad_norm": 259.4834207727077,
|
28 |
+
"learning_rate": 1.5384615384615387e-05,
|
29 |
+
"loss": 14.8237,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.35,
|
34 |
+
"grad_norm": 131.82252822714617,
|
35 |
+
"learning_rate": 1.998533413851124e-05,
|
36 |
+
"loss": 12.5705,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.47,
|
41 |
+
"grad_norm": 387.9499566391837,
|
42 |
+
"learning_rate": 1.982083682742156e-05,
|
43 |
+
"loss": 13.7286,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.58,
|
48 |
+
"grad_norm": 219.00627726463617,
|
49 |
+
"learning_rate": 1.9476531711828027e-05,
|
50 |
+
"loss": 11.3422,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.7,
|
55 |
+
"grad_norm": 221.35867761333137,
|
56 |
+
"learning_rate": 1.8958722607586883e-05,
|
57 |
+
"loss": 7.7604,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.81,
|
62 |
+
"grad_norm": 43.14746736074378,
|
63 |
+
"learning_rate": 1.827688998156891e-05,
|
64 |
+
"loss": 3.4082,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.93,
|
69 |
+
"grad_norm": 29.64836419071723,
|
70 |
+
"learning_rate": 1.7443517375622706e-05,
|
71 |
+
"loss": 2.9518,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.05,
|
76 |
+
"grad_norm": 21.427062393117673,
|
77 |
+
"learning_rate": 1.647386284781828e-05,
|
78 |
+
"loss": 2.6311,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.16,
|
83 |
+
"grad_norm": 19.158148236389312,
|
84 |
+
"learning_rate": 1.5385679615609045e-05,
|
85 |
+
"loss": 2.4838,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.28,
|
90 |
+
"grad_norm": 14.070587316942852,
|
91 |
+
"learning_rate": 1.4198891015602648e-05,
|
92 |
+
"loss": 2.3473,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.4,
|
97 |
+
"grad_norm": 34.76326434361083,
|
98 |
+
"learning_rate": 1.2935225731039349e-05,
|
99 |
+
"loss": 2.2796,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.51,
|
104 |
+
"grad_norm": 16.17405801850995,
|
105 |
+
"learning_rate": 1.161781996552765e-05,
|
106 |
+
"loss": 2.1971,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.63,
|
111 |
+
"grad_norm": 10.06558936803853,
|
112 |
+
"learning_rate": 1.0270793846761347e-05,
|
113 |
+
"loss": 2.1598,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.74,
|
118 |
+
"grad_norm": 21.625955834057603,
|
119 |
+
"learning_rate": 8.918809815760585e-06,
|
120 |
+
"loss": 2.148,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.86,
|
125 |
+
"grad_norm": 10.59659968673671,
|
126 |
+
"learning_rate": 7.586621087002945e-06,
|
127 |
+
"loss": 2.0663,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.98,
|
132 |
+
"grad_norm": 10.684749100687451,
|
133 |
+
"learning_rate": 6.298618446600856e-06,
|
134 |
+
"loss": 2.079,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.09,
|
139 |
+
"grad_norm": 18.49345747302597,
|
140 |
+
"learning_rate": 5.078383686109927e-06,
|
141 |
+
"loss": 2.0018,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.21,
|
146 |
+
"grad_norm": 14.92738780630304,
|
147 |
+
"learning_rate": 3.948257848062351e-06,
|
148 |
+
"loss": 1.9669,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.33,
|
153 |
+
"grad_norm": 9.352817552145108,
|
154 |
+
"learning_rate": 2.9289321881345257e-06,
|
155 |
+
"loss": 1.9691,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 2.44,
|
160 |
+
"grad_norm": 7.228395436940449,
|
161 |
+
"learning_rate": 2.0390693429435626e-06,
|
162 |
+
"loss": 1.9298,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.56,
|
167 |
+
"grad_norm": 7.290178837796146,
|
168 |
+
"learning_rate": 1.2949616394382802e-06,
|
169 |
+
"loss": 1.9519,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.67,
|
174 |
+
"grad_norm": 6.909179219835438,
|
175 |
+
"learning_rate": 7.102328018320859e-07,
|
176 |
+
"loss": 1.9449,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.79,
|
181 |
+
"grad_norm": 6.799236287899626,
|
182 |
+
"learning_rate": 2.955885174678852e-07,
|
183 |
+
"loss": 1.9203,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.91,
|
188 |
+
"grad_norm": 7.120567007446623,
|
189 |
+
"learning_rate": 5.862042845640403e-08,
|
190 |
+
"loss": 1.9294,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 3.0,
|
195 |
+
"step": 129,
|
196 |
+
"total_flos": 8882126585856.0,
|
197 |
+
"train_loss": 4.938086860863737,
|
198 |
+
"train_runtime": 252.0914,
|
199 |
+
"train_samples_per_second": 16.232,
|
200 |
+
"train_steps_per_second": 0.512
|
201 |
+
}
|
202 |
+
],
|
203 |
+
"logging_steps": 5,
|
204 |
+
"max_steps": 129,
|
205 |
+
"num_input_tokens_seen": 0,
|
206 |
+
"num_train_epochs": 3,
|
207 |
+
"save_steps": 100,
|
208 |
+
"total_flos": 8882126585856.0,
|
209 |
+
"train_batch_size": 4,
|
210 |
+
"trial_name": null,
|
211 |
+
"trial_params": null
|
212 |
+
}
|