Hugging Face's logo

unreservedusername
/
SmolVLM2-500M-Video-Instruct-video-feedback

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
smolvlm
Generated from Trainer
Model card Files
xet
 Metrics Community
unreservedusername commited on
Commit
ee178b9
·
verified ·
1 Parent(s): eae7604

End of training

Browse files
Files changed (13) hide show
  1. README.md +56 -0
  2. config.json +142 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. model_.safetensors +3 -0
  6. runs/Feb22_08-25-11_svr-traning/events.out.tfevents.1740230716.svr-traning.230468.0 +3 -0
  7. runs/Feb26_05-25-44_svr-traning/events.out.tfevents.1740565551.svr-traning.2616956.0 +3 -0
  8. runs/Feb26_05-30-39_svr-traning/events.out.tfevents.1740565844.svr-traning.2616956.1 +3 -0
  9. runs/Feb26_05-48-20_svr-traning/events.out.tfevents.1740566906.svr-traning.2616956.2 +3 -0
  10. runs/Feb27_16-40-06_svr-traning/events.out.tfevents.1740692410.svr-traning.3958905.0 +3 -0
  11. runs/Feb28_00-34-17_svr-traning/events.out.tfevents.1740720862.svr-traning.3550345.0 +3 -0
  12. runs/Feb28_00-34-17_svr-traning/events.out.tfevents.1740734446.svr-traning.3550345.1 +3 -0
  13. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: SmolVLM2-500M-Video-Instruct-video-feedback
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # SmolVLM2-500M-Video-Instruct-video-feedback
16
+
17
+ This model is a fine-tuned version of [HuggingFaceTB/SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0133
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 50
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.50.0.dev0
54
+ - Pytorch 2.6.0+cu124
55
+ - Datasets 3.2.0
56
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
3
+ "architectures": [
4
+ "SmolVLMForConditionalGeneration"
5
+ ],
6
+ "image_token_id": 49190,
7
+ "model_type": "smolvlm",
8
+ "pad_token_id": 128002,
9
+ "scale_factor": 4,
10
+ "text_config": {
11
+ "_flash_attn_2_enabled": true,
12
+ "_name_or_path": "None",
13
+ "architectures": [
14
+ "VLlama3ForCausalLM"
15
+ ],
16
+ "head_dim": 64,
17
+ "hidden_size": 960,
18
+ "intermediate_size": 2560,
19
+ "is_llama_config": true,
20
+ "max_position_embeddings": 8192,
21
+ "model_type": "llama",
22
+ "neftune_noise_alpha": 0.0,
23
+ "num_attention_heads": 15,
24
+ "num_key_value_heads": 5,
25
+ "pad_token_id": 2,
26
+ "perceiver_config": {
27
+ "_attn_implementation_autoset": false,
28
+ "_name_or_path": "",
29
+ "add_cross_attention": false,
30
+ "architectures": null,
31
+ "attention_dropout": 0.0,
32
+ "bad_words_ids": null,
33
+ "begin_suppress_tokens": null,
34
+ "bos_token_id": null,
35
+ "chunk_size_feed_forward": 0,
36
+ "cross_attention_hidden_size": null,
37
+ "decoder_start_token_id": null,
38
+ "diversity_penalty": 0.0,
39
+ "do_sample": false,
40
+ "early_stopping": false,
41
+ "encoder_no_repeat_ngram_size": 0,
42
+ "eos_token_id": null,
43
+ "exponential_decay_length_penalty": null,
44
+ "finetuning_task": null,
45
+ "forced_bos_token_id": null,
46
+ "forced_eos_token_id": null,
47
+ "hidden_act": "silu",
48
+ "id2label": {
49
+ "0": "LABEL_0",
50
+ "1": "LABEL_1"
51
+ },
52
+ "is_decoder": false,
53
+ "is_encoder_decoder": false,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1
57
+ },
58
+ "length_penalty": 1.0,
59
+ "max_length": 20,
60
+ "min_length": 0,
61
+ "model_type": "vllama3",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 1,
65
+ "num_key_value_heads": 1,
66
+ "num_return_sequences": 1,
67
+ "output_attentions": false,
68
+ "output_hidden_states": false,
69
+ "output_scores": false,
70
+ "pad_token_id": null,
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "qk_layer_norms_perceiver": false,
75
+ "remove_invalid_values": false,
76
+ "repetition_penalty": 1.0,
77
+ "resampler_depth": 6,
78
+ "resampler_head_dim": 96,
79
+ "resampler_n_heads": 16,
80
+ "resampler_n_latents": 64,
81
+ "return_dict": true,
82
+ "return_dict_in_generate": false,
83
+ "sep_token_id": null,
84
+ "suppress_tokens": null,
85
+ "task_specific_params": null,
86
+ "temperature": 1.0,
87
+ "tf_legacy_loss": false,
88
+ "tie_encoder_decoder": false,
89
+ "tie_word_embeddings": true,
90
+ "tokenizer_class": null,
91
+ "top_k": 50,
92
+ "top_p": 1.0,
93
+ "torch_dtype": null,
94
+ "torchscript": false,
95
+ "transformers_version": "4.46.0",
96
+ "typical_p": 1.0,
97
+ "use_bfloat16": false
98
+ },
99
+ "pixel_shuffle_factor": 4,
100
+ "qk_layer_norms": false,
101
+ "rms_norm_eps": 1e-05,
102
+ "rope_interleaved": false,
103
+ "rope_theta": 100000,
104
+ "torch_dtype": "bfloat16",
105
+ "transformers.js_config": {
106
+ "kv_cache_dtype": {
107
+ "fp16": "float16",
108
+ "q4f16": "float16"
109
+ }
110
+ },
111
+ "use_resampler": false,
112
+ "vocab_size": 49280
113
+ },
114
+ "tie_word_embeddings": false,
115
+ "torch_dtype": "bfloat16",
116
+ "transformers.js_config": {
117
+ "kv_cache_dtype": {
118
+ "fp16": "float16",
119
+ "q4f16": "float16"
120
+ }
121
+ },
122
+ "transformers_version": "4.50.0.dev0",
123
+ "use_cache": false,
124
+ "use_reentrant_checkpointing": false,
125
+ "vision_config": {
126
+ "hidden_size": 768,
127
+ "image_size": 512,
128
+ "max_image_size": {
129
+ "longest_edge": 512
130
+ },
131
+ "model_type": "smolvlm_vision",
132
+ "num_attention_heads": 12,
133
+ "patch_size": 16,
134
+ "size": {
135
+ "longest_edge": 2048
136
+ },
137
+ "tie_word_embeddings": false,
138
+ "torch_dtype": "bfloat16",
139
+ "use_base_siglip": false
140
+ },
141
+ "vocab_size": 49280
142
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 49279,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.50.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3318537421ff2d80c7e8a2180c0cad672f7f49f3acb726cd82c05ba71fd71f
3
+ size 1015025832
model_.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3318537421ff2d80c7e8a2180c0cad672f7f49f3acb726cd82c05ba71fd71f
3
+ size 1015025832
runs/Feb22_08-25-11_svr-traning/events.out.tfevents.1740230716.svr-traning.230468.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4602d454f6763fdcd8d18fd9ef01a269fbb4b4667dbe001106e5e833f77dd109
3
+ size 17147
runs/Feb26_05-25-44_svr-traning/events.out.tfevents.1740565551.svr-traning.2616956.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de401fbdb87fb6a6dc9cfcffdd1593ce9b4690d579699429661c36913bed8ef
3
+ size 8373
runs/Feb26_05-30-39_svr-traning/events.out.tfevents.1740565844.svr-traning.2616956.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f242030886711a3fb571380d11337899686aa7f2bcd4c6cf5df5137c1c4ff27
3
+ size 8721
runs/Feb26_05-48-20_svr-traning/events.out.tfevents.1740566906.svr-traning.2616956.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef668a34475a39dcaf02d0328b6819f71d88fc9c57bc32a86c3d39abfa63381d
3
+ size 8889
runs/Feb27_16-40-06_svr-traning/events.out.tfevents.1740692410.svr-traning.3958905.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed574d030111678f6291928a9342b99c0a0fbc70a11b590bc4c4200fc8ce131
3
+ size 636544
runs/Feb28_00-34-17_svr-traning/events.out.tfevents.1740720862.svr-traning.3550345.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca95f5957773f40d9d236ea5679beea79b47700c174aeeba61967b437a05e1bb
3
+ size 399758
runs/Feb28_00-34-17_svr-traning/events.out.tfevents.1740734446.svr-traning.3550345.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806ce63442b543daca6513ae2113b5eb34f53e43d3fbbd0d3a64f09f872aaaeb
3
+ size 640
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c20ce4f3648b8515586ebb6bcf802edb280dde2cd70d82bac13f57507806d6
3
+ size 5432