Hugging Face's logo

sai1881
/
bloom-560m-pre-train-v2

Text Generation
Transformers
PyTorch
TensorBoard
bloom
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
sai1881 commited on
Commit
dcee415
•
1 Parent(s): 2905029

End of training

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +32 -0
  3. generation_config.json +7 -0
  4. pytorch_model.bin +3 -0
  5. runs/May29_16-52-29_a596f8138a7d/1685379154.6004076/events.out.tfevents.1685379154.a596f8138a7d.31.1 +3 -0
  6. runs/May29_16-52-29_a596f8138a7d/1685381230.7334983/events.out.tfevents.1685381230.a596f8138a7d.31.3 +3 -0
  7. runs/May29_16-52-29_a596f8138a7d/events.out.tfevents.1685379154.a596f8138a7d.31.0 +3 -0
  8. runs/May29_16-52-29_a596f8138a7d/events.out.tfevents.1685381230.a596f8138a7d.31.2 +3 -0
  9. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-560m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_head": 16,
19
+ "n_inner": null,
20
+ "n_layer": 24,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 1,
24
+ "skip_bias_add": true,
25
+ "skip_bias_add_qkv": false,
26
+ "slow_but_exact": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "unk_token_id": 0,
30
+ "use_cache": true,
31
+ "vocab_size": 250880
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.28.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb28d21f66ada18aeda9e43e2e9ee3806b2cacb277275784214d388f00dd7234
3
+ size 2236957537
runs/May29_16-52-29_a596f8138a7d/1685379154.6004076/events.out.tfevents.1685379154.a596f8138a7d.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddd1ef47c43dad6610d5f088fcfe88aec2418eb4ccc470134830ffaf5e9767f
3
+ size 5846
runs/May29_16-52-29_a596f8138a7d/1685381230.7334983/events.out.tfevents.1685381230.a596f8138a7d.31.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578e470699e4a52d6efda8fa3d46dd7ae10dd64126e8fdfde2ec56f8597b8cb4
3
+ size 5846
runs/May29_16-52-29_a596f8138a7d/events.out.tfevents.1685379154.a596f8138a7d.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e2b53cca0c49ca8b2efd176edbd05ed61485a25dbdf8e69ad099a02a31e089
3
+ size 6038
runs/May29_16-52-29_a596f8138a7d/events.out.tfevents.1685381230.a596f8138a7d.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9fda39abcc3a6989cc9e2e1339eb60f7fd67dbec4f80edad65e9e9a6f2ebffa
3
+ size 6038
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3029969ea350278e4f9e734455c267dfb2e81aa183a5090f53a4e4d3fd560d8
3
+ size 3643