mrm8488 commited on
Commit
27239d1
1 Parent(s): 774bcff

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "seq_length": 2048,
25
+ "skip_bias_add": true,
26
+ "skip_bias_add_qkv": false,
27
+ "slow_but_exact": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.22.1",
30
+ "unk_token_id": 0,
31
+ "use_cache": false,
32
+ "vocab_size": 250880
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1155008f4624e7db0acb97980ee4edce3ddeba7204024679161570fc7a502762
3
+ size 2236955191
runs/Sep27_11-50-57_163646036bff/1664279476.271967/events.out.tfevents.1664279476.163646036bff.68.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554331629e38a2c37d75d002710d137c6966f0cd7adc37f5f047dc99970bb5d7
3
+ size 5548
runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664279476.163646036bff.68.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e6cd6d2f532f7148049ecd92606dc60c973aefc3eccd68386e27310444609b
3
+ size 8146
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ec16c1d2f7cd3fbadcb6fd0f7701b4449c87e76e12b26e1b50a29ab9847d61
3
+ size 3375