Hugging Face's logo

mveroe
/
Qwen2.5-1.5B_DS-Qwen-1.5B_0p0_1p0_0p0_sft

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
mveroe commited on
Commit
d282020
·
verified ·
1 Parent(s): d8a0981

Training in progress, epoch 3, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-2250/config.json +59 -0
  2. checkpoint-2250/generation_config.json +6 -0
  3. checkpoint-2250/model.safetensors +3 -0
  4. checkpoint-2250/optimizer.pt +3 -0
  5. checkpoint-2250/rng_state.pth +3 -0
  6. checkpoint-2250/scheduler.pt +3 -0
  7. checkpoint-2250/trainer_state.json +0 -0
  8. checkpoint-2250/training_args.bin +3 -0
checkpoint-2250/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": "4.53.2",
55
+ "use_cache": true,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 151667
59
+ }
checkpoint-2250/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": "4.53.2"
6
+ }
checkpoint-2250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:078f5039db0ab14aa76dbdebecb1983daa787f7f1a40afe920c2936f5d0a4d61
3
+ size 3086640776
checkpoint-2250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accb1db8450c1990099f1be36382f15b664c8049f2763bcd6f30c0437b9f6540
3
+ size 6056651
checkpoint-2250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecc8d19037d27a117a2fd2ffd165ca51167a61228a3907a4352a6c28073eb8e
3
+ size 14645
checkpoint-2250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f393e55181683f501a4ca4b9d0d84036ad322847579ffb4dd26775ea41dd27
3
+ size 1465
checkpoint-2250/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da98c6d17f4216728f21e20cf16cead69b93fd52b151e5750bd308b24b24e81
3
+ size 5969