Hugging Face's logo

tytodd
/
arbor-test-2

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
tytodd commited on
Commit
fa190a1
·
verified ·
1 Parent(s): 8d3df29

model_checkpoint_test

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. model_checkpoint_test/added_tokens.json +5 -0
  3. model_checkpoint_test/chat_template.jinja +6 -0
  4. model_checkpoint_test/config.json +54 -0
  5. model_checkpoint_test/generation_config.json +13 -0
  6. model_checkpoint_test/merges.txt +0 -0
  7. model_checkpoint_test/model.safetensors +3 -0
  8. model_checkpoint_test/optimizer.pt +3 -0
  9. model_checkpoint_test/rng_state.pth +3 -0
  10. model_checkpoint_test/scheduler.pt +3 -0
  11. model_checkpoint_test/special_tokens_map.json +20 -0
  12. model_checkpoint_test/tokenizer.json +3 -0
  13. model_checkpoint_test/tokenizer_config.json +43 -0
  14. model_checkpoint_test/trainer_state.json +57 -0
  15. model_checkpoint_test/training_args.bin +3 -0
  16. model_checkpoint_test/vocab.json +0 -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
  model_checkpoint_best/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  model_checkpoint_best/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ model_checkpoint_test/tokenizer.json filter=lfs diff=lfs merge=lfs -text
model_checkpoint_test/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
model_checkpoint_test/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
model_checkpoint_test/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention"
37
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "max_window_layers": 24,
40
+ "model_type": "qwen2",
41
+ "num_attention_heads": 14,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "pad_token_id": 151643,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.1",
51
+ "use_cache": false,
52
+ "use_sliding_window": false,
53
+ "vocab_size": 151936
54
+ }
model_checkpoint_test/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
model_checkpoint_test/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_checkpoint_test/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4a66417039a9eb5b869ef6d53d124401dc3aa142156af2fa9428735bfaee2d
3
+ size 1976163472
model_checkpoint_test/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65705bd2a8af3869b16af29bb33330b53303d946b96e94318390cba97cc81b2e
3
+ size 3952509771
model_checkpoint_test/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b2d0e7e32c57f217bda640702c9a866cc251489bef3ccf66647c47e2f0ee6b
3
+ size 14645
model_checkpoint_test/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1df6aa405639e3557888fcfe2436bb9a52be8517ae5231728aa34d0c5e37aa
3
+ size 1465
model_checkpoint_test/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
model_checkpoint_test/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
model_checkpoint_test/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "<|im_end|>",
36
+ "errors": "replace",
37
+ "extra_special_tokens": {},
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
model_checkpoint_test/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": "/home/paperspace/.arbor/storage/grpo:qwen2-0.5b-instruct:masked-penguin:20251027/checkpoints/model_checkpoint_best",
5
+ "epoch": 0.20634920634920634,
6
+ "eval_steps": 500,
7
+ "global_step": 13,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.0,
19
+ "completions/max_length": 4.0,
20
+ "completions/max_terminated_length": 4.0,
21
+ "completions/mean_length": 4.0,
22
+ "completions/mean_terminated_length": 4.0,
23
+ "completions/min_length": 4.0,
24
+ "completions/min_terminated_length": 4.0,
25
+ "epoch": 0.15873015873015872,
26
+ "grad_norm": 0.0,
27
+ "kl": 0.0,
28
+ "learning_rate": 9e-07,
29
+ "loss": 0.0,
30
+ "num_tokens": 4960.0,
31
+ "reward": -1.0,
32
+ "reward_std": 0.0,
33
+ "step": 10
34
+ }
35
+ ],
36
+ "logging_steps": 10,
37
+ "max_steps": 500,
38
+ "num_input_tokens_seen": 6448,
39
+ "num_train_epochs": 8,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "TrainerControl": {
43
+ "args": {
44
+ "should_epoch_stop": false,
45
+ "should_evaluate": false,
46
+ "should_log": false,
47
+ "should_save": false,
48
+ "should_training_stop": false
49
+ },
50
+ "attributes": {}
51
+ }
52
+ },
53
+ "total_flos": 0.0,
54
+ "train_batch_size": 8,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
model_checkpoint_test/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37311d79cdb8b23fae81f9e99e135d4bd44ca29b020b3838b33e13d534c37262
3
+ size 7633
model_checkpoint_test/vocab.json ADDED
The diff for this file is too large to render. See raw diff