Hugging Face's logo

mantika
/
gemma-text-to-sql

Transformers
TensorBoard
Safetensors
Generated from Trainer
sft
trl
Model card Files
xet
 Metrics Community
mantika commited on
Commit
65be6ee
·
verified ·
1 Parent(s): f4e0479

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. README.md +3 -3
  2. adapter_config.json +8 -8
  3. adapter_model.safetensors +2 -2
  4. runs/Jul09_12-56-56_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752065826.pomelo-gpu2.c.sherloq-454319.internal.7362.0 +3 -0
  5. runs/Jul09_13-00-48_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066058.pomelo-gpu2.c.sherloq-454319.internal.7925.0 +3 -0
  6. runs/Jul09_13-05-10_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066320.pomelo-gpu2.c.sherloq-454319.internal.8391.0 +3 -0
  7. runs/Jul09_13-06-37_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066406.pomelo-gpu2.c.sherloq-454319.internal.8568.0 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: google/gemma-3-1b-pt
3
  library_name: transformers
4
  model_name: gemma-text-to-sql
5
  tags:
@@ -11,7 +11,7 @@ licence: license
11
 
12
  # Model Card for gemma-text-to-sql
13
 
14
- This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -34,7 +34,7 @@ This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
- - TRL: 0.19.0
38
  - Transformers: 4.53.1
39
  - Pytorch: 2.7.1+cu128
40
  - Datasets: 3.6.0
 
1
  ---
2
+ base_model: google/gemma-3-1b-it
3
  library_name: transformers
4
  model_name: gemma-text-to-sql
5
  tags:
 
11
 
12
  # Model Card for gemma-text-to-sql
13
 
14
+ This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
34
 
35
  ### Framework versions
36
 
37
+ - TRL: 0.19.1
38
  - Transformers: 4.53.1
39
  - Pytorch: 2.7.1+cu128
40
  - Datasets: 3.6.0
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-3-1b-pt",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
@@ -13,7 +13,7 @@
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
- "lora_alpha": 16,
17
  "lora_bias": false,
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
@@ -24,17 +24,17 @@
24
  ],
25
  "peft_type": "LORA",
26
  "qalora_group_size": 16,
27
- "r": 16,
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
31
- "v_proj",
 
32
  "k_proj",
33
  "down_proj",
34
- "q_proj",
35
- "up_proj",
36
- "gate_proj",
37
- "o_proj"
38
  ],
39
  "task_type": "CAUSAL_LM",
40
  "trainable_token_indices": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-3-1b-it",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 64,
17
  "lora_bias": false,
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
 
24
  ],
25
  "peft_type": "LORA",
26
  "qalora_group_size": 16,
27
+ "r": 64,
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
31
+ "gate_proj",
32
+ "q_proj",
33
  "k_proj",
34
  "down_proj",
35
+ "o_proj",
36
+ "v_proj",
37
+ "up_proj"
 
38
  ],
39
  "task_type": "CAUSAL_LM",
40
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f58deaf4dd7952bb0a69dbf8b9db19a18e2fab345dd6ed98b5d8958178659ff3
3
- size 1260191096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff6c9f6e17352e342ef83d933b0fe22d0ef90be472a361f40450ce23436f65c
3
+ size 1416740712
runs/Jul09_12-56-56_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752065826.pomelo-gpu2.c.sherloq-454319.internal.7362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62357accd8593662240447424fae4ecd6483f35ebb52c4dd9ed2d25457aec74
3
+ size 9695
runs/Jul09_13-00-48_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066058.pomelo-gpu2.c.sherloq-454319.internal.7925.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb62c6c381a4567cbcd847de0fc7c674e371cedef8df6f380ef636896077b92d
3
+ size 6779
runs/Jul09_13-05-10_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066320.pomelo-gpu2.c.sherloq-454319.internal.8391.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4008ed5603761155634a2ab1c35a1e2a40c13833818e4a0d8680e347971df485
3
+ size 8724
runs/Jul09_13-06-37_pomelo-gpu2.c.sherloq-454319.internal/events.out.tfevents.1752066406.pomelo-gpu2.c.sherloq-454319.internal.8568.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2485d80775ef93665c5a99982989f2869d3541fd04bf67e19e72f9e5072b8fba
3
+ size 26988
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:577fa39ca5cff5b576e7e82971f3b87733d2298f7a14bc1fcb5d203f9c861787
3
  size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a435969ef12c36172e43fcdd634b74294d9f89290d5c192566c466c69bf0a927
3
  size 6225