Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- runs/Mar22_15-22-17_HAL/events.out.tfevents.1742675082.HAL.6738.0 +3 -0
- runs/Mar22_15-27-06_HAL/events.out.tfevents.1742675246.HAL.8956.0 +3 -0
- runs/Mar22_15-29-29_HAL/events.out.tfevents.1742675388.HAL.9109.0 +3 -0
- runs/Mar22_15-30-49_HAL/events.out.tfevents.1742675470.HAL.9338.0 +3 -0
- runs/Mar22_15-31-57_HAL/events.out.tfevents.1742675535.HAL.9469.0 +3 -0
- runs/Mar22_15-33-06_HAL/events.out.tfevents.1742675653.HAL.9563.0 +3 -0
- runs/Mar22_15-37-12_HAL/events.out.tfevents.1742675879.HAL.9881.0 +3 -0
- runs/Mar22_15-39-20_HAL/events.out.tfevents.1742675968.HAL.10089.0 +3 -0
- runs/Mar22_16-40-08_HAL/events.out.tfevents.1742679614.HAL.11651.0 +3 -0
- runs/Mar22_16-42-58_HAL/events.out.tfevents.1742679784.HAL.12058.0 +3 -0
- runs/Mar22_16-44-19_HAL/events.out.tfevents.1742679872.HAL.12216.0 +3 -0
- runs/Mar22_16-48-17_HAL/events.out.tfevents.1742680103.HAL.12306.0 +3 -0
- runs/Mar22_16-52-55_HAL/events.out.tfevents.1742680383.HAL.12675.0 +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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-3-1b-pt",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 2,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"lm_head"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 2,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"down_proj",
|
29 |
+
"v_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"k_proj",
|
32 |
+
"up_proj",
|
33 |
+
"q_proj",
|
34 |
+
"o_proj"
|
35 |
+
],
|
36 |
+
"task_type": "CAUSAL_LM",
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26b3c5f7462d9dff490fa61d9152dde0dd37f5b6721260e4c3c0b50af4f736e6
|
3 |
+
size 1214532048
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image_soft_token>": 262144
|
3 |
+
}
|
runs/Mar22_15-22-17_HAL/events.out.tfevents.1742675082.HAL.6738.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e687d1dbb33128b67bdd1fdb2f2449d854bf231d942754c4a514b5edff4d5b5d
|
3 |
+
size 12194
|
runs/Mar22_15-27-06_HAL/events.out.tfevents.1742675246.HAL.8956.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd268db3a420924c4621de54a24ca27754bab776010fa1118526de556c67d32c
|
3 |
+
size 6141
|
runs/Mar22_15-29-29_HAL/events.out.tfevents.1742675388.HAL.9109.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1194e3494aa2e4903330606ba28178a3f2a283c7e91143e8f60c3fe20fbd96d
|
3 |
+
size 6141
|
runs/Mar22_15-30-49_HAL/events.out.tfevents.1742675470.HAL.9338.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8424385c9febcd2eabb9550221ffcb9e0f90202d2c0282393fea179ccd4fddc6
|
3 |
+
size 6141
|
runs/Mar22_15-31-57_HAL/events.out.tfevents.1742675535.HAL.9469.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378711bfd363cb1433bdcfcc67ab0a3c17cca3096e42a408f4c3c50c803654b6
|
3 |
+
size 6141
|
runs/Mar22_15-33-06_HAL/events.out.tfevents.1742675653.HAL.9563.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf926fc266eef6352b37397aa375d95180b1c618ae6063a5732d3d01bc52c029
|
3 |
+
size 6141
|
runs/Mar22_15-37-12_HAL/events.out.tfevents.1742675879.HAL.9881.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f908fb6a9013c6210a2d14b6a8c732189ff5a10fed63f088d7873e719fa22a3
|
3 |
+
size 6141
|
runs/Mar22_15-39-20_HAL/events.out.tfevents.1742675968.HAL.10089.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4586db2d4350503f8c1985c636043c12392420008b42c5244ebd233443d9b26e
|
3 |
+
size 6141
|
runs/Mar22_16-40-08_HAL/events.out.tfevents.1742679614.HAL.11651.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a1650183d7a59e9555cc52bd6ea7c5917548850c83de71282e03436f6cdd5ce
|
3 |
+
size 6141
|
runs/Mar22_16-42-58_HAL/events.out.tfevents.1742679784.HAL.12058.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c03372ec3693407e8d09900e84bc38675cde695e0164f7c09e01c08bce953cca
|
3 |
+
size 6142
|
runs/Mar22_16-44-19_HAL/events.out.tfevents.1742679872.HAL.12216.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e9037d1403ef239c82c7b73b1fee760308847109c8ec48cacb1e3534965e035
|
3 |
+
size 6142
|
runs/Mar22_16-48-17_HAL/events.out.tfevents.1742680103.HAL.12306.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9ad0cda804bbf69dee4aca7074fc96a185aea3cab326d8d53ea7344bd9dd1b2
|
3 |
+
size 6143
|
runs/Mar22_16-52-55_HAL/events.out.tfevents.1742680383.HAL.12675.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eef41e373867fedd9658853e40ca3060498136e8eae6bf0109a99e4efb502f40
|
3 |
+
size 8303
|
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 sha256:81387968f455d9456f07e52444b51bc71b3117f9656d10f5581e49c89ad9e831
|
3 |
+
size 5624
|