Hugging Face's logo

mveroe
/
Qwen2.5-1.5B_lightr1_3_EN_6144_1p0_0p0_1p0_sft

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
mveroe commited on
Commit
34276b9
·
verified ·
1 Parent(s): ad73c81

Training in progress, epoch 3, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-1941/config.json +59 -0
  2. checkpoint-1941/generation_config.json +6 -0
  3. checkpoint-1941/model.safetensors +3 -0
  4. checkpoint-1941/optimizer.pt +3 -0
  5. checkpoint-1941/rng_state_0.pth +3 -0
  6. checkpoint-1941/rng_state_1.pth +3 -0
  7. checkpoint-1941/rng_state_2.pth +3 -0
  8. checkpoint-1941/rng_state_3.pth +3 -0
  9. checkpoint-1941/scheduler.pt +3 -0
  10. checkpoint-1941/trainer_state.json +0 -0
  11. checkpoint-1941/training_args.bin +3 -0
checkpoint-1941/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
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
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": true,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.55.0",
55
+ "use_cache": true,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 151667
59
+ }
checkpoint-1941/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.0"
6
+ }
checkpoint-1941/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5e34aab5820b80ca4b6010fa2e6736abc669117d9ee69d52201e02f101ae21
3
+ size 3086640776
checkpoint-1941/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8acdf101223e5b51e7b6b3ff795c6bfa8c14fa58da197e277a719fa9a48ef596
3
+ size 6056651
checkpoint-1941/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bcb01918719a25ed943b2f2faf45f650ff504bfa760286758dc145518593380
3
+ size 15365
checkpoint-1941/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e34c5da13614815d740bb91790974fffad60cd4e1e61540d824668f639ceb8c4
3
+ size 15429
checkpoint-1941/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84cf36eb77e76f4d60fcc92f3755828769fe8aab6a2ca29f9573827e93d0c9f5
3
+ size 15429
checkpoint-1941/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5001f16e2075ef4f6a1c0dbc75d9121e1906a36d5ad35279fed02e36a6c7d13
3
+ size 15429
checkpoint-1941/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606b947fa2a22bd58abb61349c014a3ca6139ab83a2e1fbb88504e7259f6e27a
3
+ size 1465
checkpoint-1941/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1941/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9111af7da848affc882008f9b1eed603765d07a949de83eec6f87d1d825dce52
3
+ size 5969