Hugging Face's logo

MatanBT
/
mia-target-model

Text Generation
Transformers
Safetensors
gemma3_text
text-generation-inference
Model card Files
xet
Community
MatanBT commited on
Commit
35fbf36
·
verified ·
1 Parent(s): 9ef049b

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. checkpoint-125/added_tokens.json +3 -0
  3. checkpoint-125/config.json +64 -0
  4. checkpoint-125/generation_config.json +13 -0
  5. checkpoint-125/model.safetensors +3 -0
  6. checkpoint-125/optimizer.pt +3 -0
  7. checkpoint-125/rng_state.pth +3 -0
  8. checkpoint-125/scheduler.pt +3 -0
  9. checkpoint-125/special_tokens_map.json +27 -0
  10. checkpoint-125/tokenizer.json +3 -0
  11. checkpoint-125/tokenizer.model +3 -0
  12. checkpoint-125/tokenizer_config.json +0 -0
  13. checkpoint-125/trainer_state.json +118 -0
  14. checkpoint-125/training_args.bin +3 -0
  15. model.safetensors +1 -1
  16. training_args.bin +1 -1
.gitattributes CHANGED
@@ -37,3 +37,4 @@ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-125/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
checkpoint-125/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_local_base_freq": 10000,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000,
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 6,
60
+ "transformers_version": "4.57.1",
61
+ "use_bidirectional_attention": false,
62
+ "use_cache": true,
63
+ "vocab_size": 262144
64
+ }
checkpoint-125/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.1"
13
+ }
checkpoint-125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7843202d2d6a3c5f9c1850f2a10618f12f726b6d3fe2f80fba07558eee57fc6a
3
+ size 1999811208
checkpoint-125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3605d190af6e2bcb2d38534d83c745d67e64dd9ecfff2162571505f8f7772b31
3
+ size 3999834207
checkpoint-125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
3
+ size 14645
checkpoint-125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e1f4356063c53108f9b1037e420f8b280ea03647d8984ddf7070afcc29d44a
3
+ size 1465
checkpoint-125/special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
checkpoint-125/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5eba787198c9cb1d12d0dc4d653f46747749da078219b0b3f4a11b7487eb19
3
+ size 33384832
checkpoint-125/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
checkpoint-125/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-125/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 125,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 9.4375,
15
+ "learning_rate": 4.64e-05,
16
+ "loss": 2.314,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 23.125,
22
+ "learning_rate": 4.24e-05,
23
+ "loss": 1.668,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.2,
28
+ "grad_norm": 6.53125,
29
+ "learning_rate": 3.8400000000000005e-05,
30
+ "loss": 1.5949,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 1.6,
35
+ "grad_norm": 4.59375,
36
+ "learning_rate": 3.4399999999999996e-05,
37
+ "loss": 1.5539,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "grad_norm": 4.4375,
43
+ "learning_rate": 3.04e-05,
44
+ "loss": 1.517,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 2.4,
49
+ "grad_norm": 5.4375,
50
+ "learning_rate": 2.64e-05,
51
+ "loss": 1.3099,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 2.8,
56
+ "grad_norm": 9.5,
57
+ "learning_rate": 2.2400000000000002e-05,
58
+ "loss": 1.3096,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 3.2,
63
+ "grad_norm": 7.0,
64
+ "learning_rate": 1.84e-05,
65
+ "loss": 1.2975,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 3.6,
70
+ "grad_norm": 6.0,
71
+ "learning_rate": 1.44e-05,
72
+ "loss": 1.1199,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "grad_norm": 9.25,
78
+ "learning_rate": 1.04e-05,
79
+ "loss": 1.1435,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 4.4,
84
+ "grad_norm": 8.625,
85
+ "learning_rate": 6.4000000000000006e-06,
86
+ "loss": 1.0673,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 4.8,
91
+ "grad_norm": 10.75,
92
+ "learning_rate": 2.4000000000000003e-06,
93
+ "loss": 0.9403,
94
+ "step": 120
95
+ }
96
+ ],
97
+ "logging_steps": 10,
98
+ "max_steps": 125,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 5,
101
+ "save_steps": 500,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 267992088576000.0,
115
+ "train_batch_size": 4,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc78888f5156497d93538b7861f6887178a080d85e1fd6d2b7949adca962b863
3
+ size 5777
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93e8a7ebfec30f4bbf57a2a15e030efcf88437764c28576a4eef20e778dd03bf
3
  size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7843202d2d6a3c5f9c1850f2a10618f12f726b6d3fe2f80fba07558eee57fc6a
3
  size 1999811208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7391c61484a67ecf78a29d1db8b985014e15fab710d3992820c62a4bbe244937
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc78888f5156497d93538b7861f6887178a080d85e1fd6d2b7949adca962b863
3
  size 5777