Hugging Face's logo

jefson08
/
indictrans-en-ne-checkpoint-1B

Text2Text Generation
Transformers
TensorBoard
Safetensors
IndicTrans
Generated from Trainer
custom_code
Model card Files Metrics Community
jefson08 commited on
Commit
92ece5c
·
verified ·
1 Parent(s): 7eaaa4e

Training in progress, step 1000

Browse files
Files changed (12) hide show
  1. config.json +46 -0
  2. model.safetensors +3 -0
  3. runs/Aug25_05-13-29_ip-10-192-11-185/events.out.tfevents.1724562810.ip-10-192-11-185.4259.0 +3 -0
  4. runs/Aug25_05-20-42_ip-10-192-11-185/events.out.tfevents.1724563243.ip-10-192-11-185.12802.0 +3 -0
  5. runs/Aug25_05-22-20_ip-10-192-11-185/events.out.tfevents.1724563340.ip-10-192-11-185.14365.0 +3 -0
  6. runs/Aug25_13-44-28_ip-10-192-11-185/events.out.tfevents.1724593468.ip-10-192-11-185.273580.0 +3 -0
  7. runs/Aug25_13-45-39_ip-10-192-11-185/events.out.tfevents.1724593540.ip-10-192-11-185.275675.0 +3 -0
  8. runs/Aug25_13-46-36_ip-10-192-11-185/events.out.tfevents.1724593596.ip-10-192-11-185.277007.0 +3 -0
  9. runs/Aug25_13-48-35_ip-10-192-11-185/events.out.tfevents.1724593715.ip-10-192-11-185.279336.0 +3 -0
  10. runs/Aug26_07-48-38_ip-10-192-11-38/events.out.tfevents.1724658519.ip-10-192-11-38.2862.0 +3 -0
  11. runs/Aug26_07-49-43_ip-10-192-11-38/events.out.tfevents.1724658584.ip-10-192-11-38.8568.0 +3 -0
  12. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indictrans-en-ne-checkpoint-1B/checkpoint-3000",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "IndicTransForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attn_implementation": null,
10
+ "auto_map": {
11
+ "AutoConfig": "configuration_indictrans.IndicTransConfig",
12
+ "AutoModelForSeq2SeqLM": "modeling_indictrans.IndicTransForConditionalGeneration"
13
+ },
14
+ "bos_token_id": 0,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_embed_dim": 1024,
17
+ "decoder_ffn_dim": 8192,
18
+ "decoder_layerdrop": 0,
19
+ "decoder_layers": 18,
20
+ "decoder_normalize_before": true,
21
+ "decoder_start_token_id": 2,
22
+ "decoder_vocab_size": 122672,
23
+ "dropout": 0.2,
24
+ "encoder_attention_heads": 16,
25
+ "encoder_embed_dim": 1024,
26
+ "encoder_ffn_dim": 8192,
27
+ "encoder_layerdrop": 0,
28
+ "encoder_layers": 18,
29
+ "encoder_normalize_before": true,
30
+ "encoder_vocab_size": 32322,
31
+ "eos_token_id": 2,
32
+ "init_std": 0.02,
33
+ "is_encoder_decoder": true,
34
+ "layernorm_embedding": false,
35
+ "max_source_positions": 256,
36
+ "max_target_positions": 256,
37
+ "model_type": "IndicTrans",
38
+ "num_hidden_layers": 18,
39
+ "pad_token_id": 1,
40
+ "scale_embedding": true,
41
+ "share_decoder_input_output_embed": false,
42
+ "tokenizer_class": "IndicTransTokenizer",
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.44.2",
45
+ "use_cache": true
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359873d00ef1879160f5919f94b170e255f2f438999e290088a754a3c4400ad7
3
+ size 2231178416
runs/Aug25_05-13-29_ip-10-192-11-185/events.out.tfevents.1724562810.ip-10-192-11-185.4259.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06697ddb9996c0d7a0c5d5c411f33e46f9b88cb8803300d20a254e47c079f15e
3
+ size 12024
runs/Aug25_05-20-42_ip-10-192-11-185/events.out.tfevents.1724563243.ip-10-192-11-185.12802.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5afb96f355dea401e97736077432f294404e472bf5d70d5ee2cfaeb54f3202e
3
+ size 5795
runs/Aug25_05-22-20_ip-10-192-11-185/events.out.tfevents.1724563340.ip-10-192-11-185.14365.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccdfbdc62f484bab91eac3f3ebbab54fda020fd87092a18aaf303d8b0c3d5286
3
+ size 132839
runs/Aug25_13-44-28_ip-10-192-11-185/events.out.tfevents.1724593468.ip-10-192-11-185.273580.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3fddcbc407f06c87c9efaf189751e93b0fa25ddea59d01e47cc4991096bf8b
3
+ size 5815
runs/Aug25_13-45-39_ip-10-192-11-185/events.out.tfevents.1724593540.ip-10-192-11-185.275675.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3304c1bd3aa739a76b4f7cf9bc9580cf7e9e434b34d40bbb5394fe55635e6e4b
3
+ size 5815
runs/Aug25_13-46-36_ip-10-192-11-185/events.out.tfevents.1724593596.ip-10-192-11-185.277007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0915935c4aabe0e87ebde6140a88f59f979567199de1ee9260eca85c3448a04
3
+ size 5814
runs/Aug25_13-48-35_ip-10-192-11-185/events.out.tfevents.1724593715.ip-10-192-11-185.279336.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a420eaabc7e1b9d149f3ec69244e6ac8b7dc61dffc0fce14748d1102663fa66
3
+ size 5814
runs/Aug26_07-48-38_ip-10-192-11-38/events.out.tfevents.1724658519.ip-10-192-11-38.2862.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2585432f977dd27ef6e8c70c8ad1587b1d1cb8b0d84f8eb41bcce51a1d92b2fa
3
+ size 5827
runs/Aug26_07-49-43_ip-10-192-11-38/events.out.tfevents.1724658584.ip-10-192-11-38.8568.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2f5bdad3ea276d59b5f0aa0c6dbe78ebd4d590784227e5718eba3faab8659a
3
+ size 48199
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582f83e0ec85126c8a4d959b3684b3a8c8f9b412acb70cadf72f7d23bd4e8678
3
+ size 5368