Hugging Face's logo

presencesw
/
gemma-3-1b-it_MED_NLI

Text Generation
Transformers
TensorBoard
Safetensors
gemma3_text
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
presencesw commited on
Commit
36fc425
·
verified ·
1 Parent(s): c7ef36b

Training in progress, step 1000

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. config.json +37 -0
  4. model.safetensors +3 -0
  5. runs/Apr13_02-06-24_9e72a503a884/events.out.tfevents.1744510037.9e72a503a884.3411.0 +3 -0
  6. special_tokens_map.json +42 -0
  7. tokenizer.json +3 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +0 -0
  10. trainer_log.jsonl +25 -0
  11. 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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": null,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "eos_token_id": [
11
+ 1,
12
+ 106
13
+ ],
14
+ "final_logit_softcapping": null,
15
+ "head_dim": 256,
16
+ "hidden_activation": "gelu_pytorch_tanh",
17
+ "hidden_size": 1152,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 6912,
20
+ "max_position_embeddings": 32768,
21
+ "model_type": "gemma3_text",
22
+ "num_attention_heads": 4,
23
+ "num_hidden_layers": 26,
24
+ "num_key_value_heads": 1,
25
+ "pad_token_id": 0,
26
+ "query_pre_attn_scalar": 256,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_local_base_freq": 10000,
29
+ "rope_scaling": null,
30
+ "rope_theta": 1000000,
31
+ "sliding_window": 512,
32
+ "sliding_window_pattern": 6,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.50.0",
35
+ "use_cache": false,
36
+ "vocab_size": 262144
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771f4b648d8943b067551a799007180afabb881a378bdd1c84f9c45ef3529796
3
+ size 3999582960
runs/Apr13_02-06-24_9e72a503a884/events.out.tfevents.1744510037.9e72a503a884.3411.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de09e1aef86b2d5892ea3b14a4e01a6142094e7f9715bae2c3b3bd0e52077839
3
+ size 10203
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<end_of_turn>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "boi_token": "<start_of_image>",
12
+ "bos_token": {
13
+ "content": "<bos>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eoi_token": "<end_of_image>",
20
+ "eos_token": {
21
+ "content": "<eos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<image_soft_token>",
28
+ "pad_token": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
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
 
trainer_log.jsonl ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 50, "total_steps": 8503, "loss": 5.0951, "lr": 5.875440658049355e-07, "epoch": 0.005880277549100318, "percentage": 0.59, "elapsed_time": "0:00:54", "remaining_time": "2:34:35"}
2
+ {"current_steps": 100, "total_steps": 8503, "loss": 0.8587, "lr": 1.175088131609871e-06, "epoch": 0.011760555098200636, "percentage": 1.18, "elapsed_time": "0:01:30", "remaining_time": "2:06:11"}
3
+ {"current_steps": 150, "total_steps": 8503, "loss": 0.084, "lr": 1.762632197414806e-06, "epoch": 0.01764083264730095, "percentage": 1.76, "elapsed_time": "0:02:06", "remaining_time": "1:57:11"}
4
+ {"current_steps": 200, "total_steps": 8503, "loss": 0.051, "lr": 2.350176263219742e-06, "epoch": 0.02352111019640127, "percentage": 2.35, "elapsed_time": "0:02:41", "remaining_time": "1:51:54"}
5
+ {"current_steps": 250, "total_steps": 8503, "loss": 0.0592, "lr": 2.937720329024677e-06, "epoch": 0.02940138774550159, "percentage": 2.94, "elapsed_time": "0:03:33", "remaining_time": "1:57:37"}
6
+ {"current_steps": 300, "total_steps": 8503, "loss": 0.0519, "lr": 3.525264394829612e-06, "epoch": 0.0352816652946019, "percentage": 3.53, "elapsed_time": "0:04:08", "remaining_time": "1:53:27"}
7
+ {"current_steps": 350, "total_steps": 8503, "loss": 0.0418, "lr": 4.112808460634548e-06, "epoch": 0.041161942843702226, "percentage": 4.12, "elapsed_time": "0:04:43", "remaining_time": "1:50:13"}
8
+ {"current_steps": 400, "total_steps": 8503, "loss": 0.0665, "lr": 4.700352526439484e-06, "epoch": 0.04704222039280254, "percentage": 4.7, "elapsed_time": "0:05:19", "remaining_time": "1:47:50"}
9
+ {"current_steps": 450, "total_steps": 8503, "loss": 0.052, "lr": 5.287896592244419e-06, "epoch": 0.05292249794190286, "percentage": 5.29, "elapsed_time": "0:06:10", "remaining_time": "1:50:38"}
10
+ {"current_steps": 500, "total_steps": 8503, "loss": 0.0405, "lr": 5.875440658049354e-06, "epoch": 0.05880277549100318, "percentage": 5.88, "elapsed_time": "0:06:46", "remaining_time": "1:48:29"}
11
+ {"current_steps": 550, "total_steps": 8503, "loss": 0.0499, "lr": 6.46298472385429e-06, "epoch": 0.0646830530401035, "percentage": 6.47, "elapsed_time": "0:07:22", "remaining_time": "1:46:43"}
12
+ {"current_steps": 600, "total_steps": 8503, "loss": 0.0444, "lr": 7.050528789659224e-06, "epoch": 0.0705633305892038, "percentage": 7.06, "elapsed_time": "0:07:58", "remaining_time": "1:45:00"}
13
+ {"current_steps": 650, "total_steps": 8503, "loss": 0.0417, "lr": 7.63807285546416e-06, "epoch": 0.07644360813830413, "percentage": 7.64, "elapsed_time": "0:08:50", "remaining_time": "1:46:43"}
14
+ {"current_steps": 700, "total_steps": 8503, "loss": 0.0337, "lr": 8.225616921269097e-06, "epoch": 0.08232388568740445, "percentage": 8.23, "elapsed_time": "0:09:25", "remaining_time": "1:45:08"}
15
+ {"current_steps": 750, "total_steps": 8503, "loss": 0.0314, "lr": 8.81316098707403e-06, "epoch": 0.08820416323650476, "percentage": 8.82, "elapsed_time": "0:10:01", "remaining_time": "1:43:37"}
16
+ {"current_steps": 800, "total_steps": 8503, "loss": 0.0386, "lr": 9.400705052878968e-06, "epoch": 0.09408444078560509, "percentage": 9.41, "elapsed_time": "0:10:37", "remaining_time": "1:42:18"}
17
+ {"current_steps": 850, "total_steps": 8503, "loss": 0.0322, "lr": 9.988249118683903e-06, "epoch": 0.0999647183347054, "percentage": 10.0, "elapsed_time": "0:11:29", "remaining_time": "1:43:25"}
18
+ {"current_steps": 900, "total_steps": 8503, "loss": 0.037, "lr": 9.998988263671598e-06, "epoch": 0.10584499588380572, "percentage": 10.58, "elapsed_time": "0:12:05", "remaining_time": "1:42:09"}
19
+ {"current_steps": 950, "total_steps": 8503, "loss": 0.0328, "lr": 9.995870471854679e-06, "epoch": 0.11172527343290603, "percentage": 11.17, "elapsed_time": "0:12:40", "remaining_time": "1:40:50"}
20
+ {"current_steps": 1000, "total_steps": 8503, "loss": 0.0331, "lr": 9.990647516930925e-06, "epoch": 0.11760555098200635, "percentage": 11.76, "elapsed_time": "0:13:16", "remaining_time": "1:39:39"}
21
+ {"current_steps": 1000, "total_steps": 8503, "eval_loss": 0.03788302466273308, "epoch": 0.11760555098200635, "percentage": 11.76, "elapsed_time": "0:23:36", "remaining_time": "2:57:07"}
22
+ {"current_steps": 1050, "total_steps": 8503, "loss": 0.0359, "lr": 9.983321599752438e-06, "epoch": 0.12348582853110666, "percentage": 12.35, "elapsed_time": "0:25:05", "remaining_time": "2:58:02"}
23
+ {"current_steps": 1100, "total_steps": 8503, "loss": 0.0306, "lr": 9.9738958073189e-06, "epoch": 0.129366106080207, "percentage": 12.94, "elapsed_time": "0:25:41", "remaining_time": "2:52:51"}
24
+ {"current_steps": 1150, "total_steps": 8503, "loss": 0.031, "lr": 9.962374111476778e-06, "epoch": 0.1352463836293073, "percentage": 13.52, "elapsed_time": "0:26:17", "remaining_time": "2:48:07"}
25
+ {"current_steps": 1200, "total_steps": 8503, "loss": 0.0333, "lr": 9.948761367245665e-06, "epoch": 0.1411266611784076, "percentage": 14.11, "elapsed_time": "0:26:54", "remaining_time": "2:43:46"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b410c0a3aa9c6ad87c23be090921bedaa36279bdcab2751bb00e25ef21f95d28
3
+ size 5752