matis35 commited on
Commit
5330620
·
verified ·
1 Parent(s): 38cf7d1

Upload folder using huggingface_hub

Browse files
.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
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3TextModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "dtype": "float32",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1152,
18
+ "layer_types": [
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 2048,
45
+ "model_type": "gemma3_text",
46
+ "num_attention_heads": 3,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 1,
49
+ "pad_token_id": 0,
50
+ "query_pre_attn_scalar": 256,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_local_base_freq": 10000.0,
53
+ "rope_scaling": null,
54
+ "rope_theta": 1000000.0,
55
+ "sliding_window": 257,
56
+ "transformers_version": "4.57.3",
57
+ "use_bidirectional_attention": true,
58
+ "use_cache": true,
59
+ "vocab_size": 262144
60
+ }
loss_curves.png ADDED
metrics.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_runtime": 1524.2683,
3
+ "train_samples_per_second": 27.678,
4
+ "train_steps_per_second": 0.433,
5
+ "total_flos": 0.0,
6
+ "train_loss": 0.8622043457898226,
7
+ "epoch": 3.0,
8
+ "test_loss": 0.7137625217437744,
9
+ "test_mrr": 0.5474628453925872,
10
+ "test_recall_at_1": 0.3992197659297789,
11
+ "test_recall_at_5": 0.7386215864759428,
12
+ "test_recall_at_10": 0.8387516254876463,
13
+ "test_runtime": 7.5815,
14
+ "test_samples_per_second": 103.146,
15
+ "test_steps_per_second": 1.715,
16
+ "base_model": "google/embeddinggemma-300m",
17
+ "dataset_id": "matis35/cf-synt_V2",
18
+ "output_dir": "./final_merged_model"
19
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c10c68a5260e2c5545d957acb146784a034d712444c642bc21bc04ee1f0335
3
+ size 1211486072
run_metrics/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1db950834f0e8c33f2a03671d5b7db82ab1c579b1436edec22ebe4a802acd22
3
+ size 3280
run_metrics/dataset_info.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "train_runtime": {
6
+ "dtype": "float64",
7
+ "_type": "Value"
8
+ },
9
+ "train_samples_per_second": {
10
+ "dtype": "float64",
11
+ "_type": "Value"
12
+ },
13
+ "train_steps_per_second": {
14
+ "dtype": "float64",
15
+ "_type": "Value"
16
+ },
17
+ "total_flos": {
18
+ "dtype": "float64",
19
+ "_type": "Value"
20
+ },
21
+ "train_loss": {
22
+ "dtype": "float64",
23
+ "_type": "Value"
24
+ },
25
+ "epoch": {
26
+ "dtype": "float64",
27
+ "_type": "Value"
28
+ },
29
+ "test_loss": {
30
+ "dtype": "float64",
31
+ "_type": "Value"
32
+ },
33
+ "test_mrr": {
34
+ "dtype": "float64",
35
+ "_type": "Value"
36
+ },
37
+ "test_recall_at_1": {
38
+ "dtype": "float64",
39
+ "_type": "Value"
40
+ },
41
+ "test_recall_at_5": {
42
+ "dtype": "float64",
43
+ "_type": "Value"
44
+ },
45
+ "test_recall_at_10": {
46
+ "dtype": "float64",
47
+ "_type": "Value"
48
+ },
49
+ "test_runtime": {
50
+ "dtype": "float64",
51
+ "_type": "Value"
52
+ },
53
+ "test_samples_per_second": {
54
+ "dtype": "float64",
55
+ "_type": "Value"
56
+ },
57
+ "test_steps_per_second": {
58
+ "dtype": "float64",
59
+ "_type": "Value"
60
+ },
61
+ "base_model": {
62
+ "dtype": "string",
63
+ "_type": "Value"
64
+ },
65
+ "dataset_id": {
66
+ "dtype": "string",
67
+ "_type": "Value"
68
+ },
69
+ "output_dir": {
70
+ "dtype": "string",
71
+ "_type": "Value"
72
+ }
73
+ },
74
+ "homepage": "",
75
+ "license": ""
76
+ }
run_metrics/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "a95e6b8c3518384b",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
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:d7ae06c2d5423018713138be1af08ead828be6d5aec3dcaf4004830d73339843
3
+ size 33385261
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff