Hugging Face's logo

osman93
/
SmolVLM-256M-Instruct-SFT

Transformers
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
Community
osman93 commited on
Commit
d2795b6
·
verified ·
1 Parent(s): 1c2eaf2

Add checkpoint -1 post-trained on curated_deepscaler

Browse files
Files changed (7) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +1 -1
  3. all_results.json +2 -2
  4. tokenizer_config.json +1 -1
  5. train_results.json +2 -2
  6. trainer_state.json +2 -2
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "q_proj",
28
  "down_proj",
29
- "up_proj",
30
  "k_proj",
31
- "v_proj",
32
  "o_proj",
33
- "gate_proj"
 
 
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
 
27
  "down_proj",
 
28
  "k_proj",
29
+ "gate_proj",
30
  "o_proj",
31
+ "q_proj",
32
+ "up_proj",
33
+ "v_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae326e349e94e856f5f2de58502b84e3053bef07e27c2f71f2317357b31c8e7
3
  size 5838888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59591948f8a5adc97ad8214b395f457ebe72fd04954f0e26a74cfef001f093f2
3
  size 5838888
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "total_flos": 0,
3
  "train_loss": 0.0,
4
- "train_runtime": 9995.2935,
5
- "train_samples_per_second": 0.01,
6
  "train_steps_per_second": 0.002
7
  }
 
1
  {
2
  "total_flos": 0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 10851.9382,
5
+ "train_samples_per_second": 0.009,
6
  "train_steps_per_second": 0.002
7
  }
tokenizer_config.json CHANGED
@@ -1206,7 +1206,7 @@
1206
  "eos_token": "<end_of_utterance>",
1207
  "extra_special_tokens": {},
1208
  "legacy": false,
1209
- "model_max_length": 8192,
1210
  "pad_token": "<|im_end|>",
1211
  "processor_class": "Idefics3Processor",
1212
  "tokenizer_class": "GPT2Tokenizer",
 
1206
  "eos_token": "<end_of_utterance>",
1207
  "extra_special_tokens": {},
1208
  "legacy": false,
1209
+ "model_max_length": 16384,
1210
  "pad_token": "<|im_end|>",
1211
  "processor_class": "Idefics3Processor",
1212
  "tokenizer_class": "GPT2Tokenizer",
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "total_flos": 0,
3
  "train_loss": 0.0,
4
- "train_runtime": 9995.2935,
5
- "train_samples_per_second": 0.01,
6
  "train_steps_per_second": 0.002
7
  }
 
1
  {
2
  "total_flos": 0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 10851.9382,
5
+ "train_samples_per_second": 0.009,
6
  "train_steps_per_second": 0.002
7
  }
trainer_state.json CHANGED
@@ -13,8 +13,8 @@
13
  "step": 0,
14
  "total_flos": 0,
15
  "train_loss": 0.0,
16
- "train_runtime": 9995.2935,
17
- "train_samples_per_second": 0.01,
18
  "train_steps_per_second": 0.002
19
  }
20
  ],
 
13
  "step": 0,
14
  "total_flos": 0,
15
  "train_loss": 0.0,
16
+ "train_runtime": 10851.9382,
17
+ "train_samples_per_second": 0.009,
18
  "train_steps_per_second": 0.002
19
  }
20
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:377d7fcf444597f25d679c2c1c7e9f9107437e56579ed16ed0ca3a5e7bbb5a6c
3
  size 6840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f997bd4cbe8bc017809085f990ece8762693b2bf751a586df061b31fd18769
3
  size 6840