Hugging Face's logo

flax-community
/
t5-base-dutch-demo

Text2Text Generation
Transformers
PyTorch
JAX
TensorBoard
Safetensors
t5
summarization
seq2seq
text-generation
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
1
yhavinga commited on
Commit
a9310ca
•
1 Parent(s): 20560fb

Add log and ckpt dir

Browse files
Files changed (15) hide show
  1. output/ckpt-9999/config.json +58 -0
  2. output/ckpt-9999/flax_model.msgpack +3 -0
  3. output/ckpt-9999/opt_state.msgpack +3 -0
  4. output/ckpt-9999/training_state.json +1 -0
  5. output/config.json +58 -0
  6. output/events.out.tfevents.1626477704.t1v-n-0e7426e8-w-0.83817.3.v2 +3 -0
  7. output/events.out.tfevents.1626504033.t1v-n-0e7426e8-w-0.89661.3.v2 +3 -0
  8. output/events.out.tfevents.1626504547.t1v-n-0e7426e8-w-0.93479.3.v2 +3 -0
  9. output/events.out.tfevents.1626505238.t1v-n-0e7426e8-w-0.95128.3.v2 +3 -0
  10. output/events.out.tfevents.1626506421.t1v-n-0e7426e8-w-0.96635.3.v2 +3 -0
  11. output/events.out.tfevents.1626507299.t1v-n-0e7426e8-w-0.98584.3.v2 +3 -0
  12. output/events.out.tfevents.1626508342.t1v-n-0e7426e8-w-0.101251.3.v2 +3 -0
  13. output/flax_model.msgpack +3 -0
  14. output/opt_state.msgpack +3 -0
  15. output/training_state.json +1 -0
output/ckpt-9999/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "n_positions": 512,
19
+ "num_decoder_layers": 12,
20
+ "num_heads": 12,
21
+ "num_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_num_buckets": 32,
25
+ "task_specific_params": {
26
+ "summarization": {
27
+ "early_stopping": true,
28
+ "length_penalty": 2.0,
29
+ "max_length": 200,
30
+ "min_length": 30,
31
+ "no_repeat_ngram_size": 3,
32
+ "num_beams": 4,
33
+ "prefix": "summarize: "
34
+ },
35
+ "translation_en_to_de": {
36
+ "early_stopping": true,
37
+ "max_length": 300,
38
+ "num_beams": 4,
39
+ "prefix": "translate English to German: "
40
+ },
41
+ "translation_en_to_fr": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to French: "
46
+ },
47
+ "translation_en_to_ro": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to Romanian: "
52
+ }
53
+ },
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.9.0.dev0",
56
+ "use_cache": true,
57
+ "vocab_size": 32103
58
+ }
output/ckpt-9999/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8299c056e5ca07f93db2db052d61cb941710e0925c62486ee0c9775116e0a6bf
3
+ size 891548548
output/ckpt-9999/opt_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c912197fd24feea06a22802e5bfbd9935100bb392a8d1966e230891aeaec658
3
+ size 1783097336
output/ckpt-9999/training_state.json ADDED
@@ -0,0 +1 @@
 
1
+ {"step": 10000}
output/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "n_positions": 512,
19
+ "num_decoder_layers": 12,
20
+ "num_heads": 12,
21
+ "num_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_num_buckets": 32,
25
+ "task_specific_params": {
26
+ "summarization": {
27
+ "early_stopping": true,
28
+ "length_penalty": 2.0,
29
+ "max_length": 200,
30
+ "min_length": 30,
31
+ "no_repeat_ngram_size": 3,
32
+ "num_beams": 4,
33
+ "prefix": "summarize: "
34
+ },
35
+ "translation_en_to_de": {
36
+ "early_stopping": true,
37
+ "max_length": 300,
38
+ "num_beams": 4,
39
+ "prefix": "translate English to German: "
40
+ },
41
+ "translation_en_to_fr": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to French: "
46
+ },
47
+ "translation_en_to_ro": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to Romanian: "
52
+ }
53
+ },
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.9.0.dev0",
56
+ "use_cache": true,
57
+ "vocab_size": 32103
58
+ }
output/events.out.tfevents.1626477704.t1v-n-0e7426e8-w-0.83817.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091b61fc500aae0368d977c5c0fd73632a32aabebdc0e7fba4129f26b6c8abdf
3
+ size 6630102
output/events.out.tfevents.1626504033.t1v-n-0e7426e8-w-0.89661.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3b9f725bfa1e9befedd29c8c0319001a6ddc3597c6dfa30c754913531f26bc
3
+ size 40
output/events.out.tfevents.1626504547.t1v-n-0e7426e8-w-0.93479.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3bd0981ae5d2bb0ac2ffef88a1eac66f198c1a58e207b37e216a9997428160
3
+ size 40
output/events.out.tfevents.1626505238.t1v-n-0e7426e8-w-0.95128.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b26b65cf4c438d4270d906ca1ed332fbe65f924ae82a22289dda08f95d5919f
3
+ size 40
output/events.out.tfevents.1626506421.t1v-n-0e7426e8-w-0.96635.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a031810dfc4c6e7c52913e5261afc3fa3d5cf5a68695b76bbffd177b065e27
3
+ size 40
output/events.out.tfevents.1626507299.t1v-n-0e7426e8-w-0.98584.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4874aada340bc85728ebb4b7f8329a0eb6618a19f0b646abb1f1b5f2e9fc84fe
3
+ size 40
output/events.out.tfevents.1626508342.t1v-n-0e7426e8-w-0.101251.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed227170f48707b46db61d657803869c0be10d350b75f29b0844a6ef8a9e0cd3
3
+ size 40
output/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8299c056e5ca07f93db2db052d61cb941710e0925c62486ee0c9775116e0a6bf
3
+ size 891548548
output/opt_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c912197fd24feea06a22802e5bfbd9935100bb392a8d1966e230891aeaec658
3
+ size 1783097336
output/training_state.json ADDED
@@ -0,0 +1 @@
 
1
+ {"step": 10000}