Hugging Face's logo

SeragAmin
/
test

Safetensors
Model card Files
xet
Community
SeragAmin commited on
Commit
c372777
·
verified ·
1 Parent(s): 2b5765e

Upload checkpoint for batch5

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. checkpointbatch5/added_tokens.json +3 -0
  3. checkpointbatch5/config.json +62 -0
  4. checkpointbatch5/generation_config.json +13 -0
  5. checkpointbatch5/model.safetensors +3 -0
  6. checkpointbatch5/optimizer.pt +3 -0
  7. checkpointbatch5/rng_state.pth +3 -0
  8. checkpointbatch5/scheduler.pt +3 -0
  9. checkpointbatch5/special_tokens_map.json +33 -0
  10. checkpointbatch5/tokenizer.json +3 -0
  11. checkpointbatch5/tokenizer.model +3 -0
  12. checkpointbatch5/tokenizer_config.json +0 -0
  13. checkpointbatch5/trainer_state.json +33 -0
  14. checkpointbatch5/training_args.bin +3 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpointbatch2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  checkpointbatch4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpointbatch2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  checkpointbatch4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpointbatch5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpointbatch5/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
checkpointbatch5/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 1152,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 6912,
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
+ "sliding_attention",
44
+ "sliding_attention"
45
+ ],
46
+ "max_position_embeddings": 32768,
47
+ "model_type": "gemma3_text",
48
+ "num_attention_heads": 4,
49
+ "num_hidden_layers": 26,
50
+ "num_key_value_heads": 1,
51
+ "pad_token_id": 0,
52
+ "query_pre_attn_scalar": 256,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_local_base_freq": 10000,
55
+ "rope_scaling": null,
56
+ "rope_theta": 1000000,
57
+ "sliding_window": 512,
58
+ "torch_dtype": "bfloat16",
59
+ "transformers_version": "4.54.0",
60
+ "use_cache": true,
61
+ "vocab_size": 262144
62
+ }
checkpointbatch5/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": "4.54.0"
13
+ }
checkpointbatch5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835611f46cca7c812dda9d95dbd4e750ce59342540aa006c9cad4f6506fd6dca
3
+ size 1999811208
checkpointbatch5/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abf1beb199c3822ce0ed40872653b34a91d03a748107fcec1720b02edefbd2a
3
+ size 3999829471
checkpointbatch5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
3
+ size 14645
checkpointbatch5/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c9fe42b478cc55f02b86aff1cc7af6bbab56dc2db2bb5752e36fe22f201e4e
3
+ size 1465
checkpointbatch5/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
+ }
checkpointbatch5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
checkpointbatch5/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
checkpointbatch5/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpointbatch5/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.803681282321512e-05,
6
+ "eval_steps": 500,
7
+ "global_step": 5,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 5,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 171514936688640.0,
30
+ "train_batch_size": 4,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpointbatch5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983bce4ae9b3994ac53f16399bf91c1d3fe1e51992c2439ac8fe222a85ee9914
3
+ size 5777