Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- runs/Apr21_12-46-38_cluster4/events.out.tfevents.1745228801.cluster4.557450.0 +3 -0
- runs/Apr21_12-47-31_cluster4/events.out.tfevents.1745228856.cluster4.562438.0 +3 -0
- runs/Apr21_12-54-41_cluster4/events.out.tfevents.1745229283.cluster4.599412.0 +3 -0
- runs/Apr21_12-58-29_cluster4/events.out.tfevents.1745229512.cluster4.620690.0 +3 -0
- runs/Apr21_12-59-54_cluster4/events.out.tfevents.1745229597.cluster4.628967.0 +3 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
adapter_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-3-1b-it",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": [
|
22 |
+
"lm_head",
|
23 |
+
"embed_tokens"
|
24 |
+
],
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 16,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"q_proj",
|
31 |
+
"down_proj",
|
32 |
+
"v_proj",
|
33 |
+
"k_proj",
|
34 |
+
"up_proj",
|
35 |
+
"gate_proj",
|
36 |
+
"o_proj"
|
37 |
+
],
|
38 |
+
"task_type": "CAUSAL_LM",
|
39 |
+
"trainable_token_indices": null,
|
40 |
+
"use_dora": false,
|
41 |
+
"use_rslora": false
|
42 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b763442fa98e19f76b2f84ce2e56e93d3d56ae06efb83c8a05e05b51d7481d83
|
3 |
+
size 2468152240
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image_soft_token>": 262144
|
3 |
+
}
|
runs/Apr21_12-46-38_cluster4/events.out.tfevents.1745228801.cluster4.557450.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad41696a62fe779b39560946ddf17bf466f2120041e6002bcd96f823fe0c8202
|
3 |
+
size 6220
|
runs/Apr21_12-47-31_cluster4/events.out.tfevents.1745228856.cluster4.562438.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7b1a37b40670ce58c305c9db740adaadde4954662fbd8d2dd2a387ac0e5b7e4
|
3 |
+
size 6220
|
runs/Apr21_12-54-41_cluster4/events.out.tfevents.1745229283.cluster4.599412.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1ee987918c9afda4a5d3d445a91783dd02d5da34f830d7327cd8a9148cb0520
|
3 |
+
size 6220
|
runs/Apr21_12-58-29_cluster4/events.out.tfevents.1745229512.cluster4.620690.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ffc2ca88c19edf13accea3eac740b247e5832f9ba40eeb1d0628a5b48e897d0
|
3 |
+
size 6222
|
runs/Apr21_12-59-54_cluster4/events.out.tfevents.1745229597.cluster4.628967.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:795551065f484150b2215a46e350e65faf9d2ede9ba535cc9787100927084086
|
3 |
+
size 6222
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"boi_token": "<start_of_image>",
|
3 |
+
"bos_token": {
|
4 |
+
"content": "<bos>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"eoi_token": "<end_of_image>",
|
11 |
+
"eos_token": {
|
12 |
+
"content": "<eos>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"image_token": "<image_soft_token>",
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
3 |
+
size 33384568
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
3 |
+
size 4689074
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:459a041801835540a34030a8d8de27967777e71305697f9f8962cca493b30554
|
3 |
+
size 5688
|