Hugging Face's logo

yhavinga
/
gpt2-large-dutch

Text Generation
Transformers
PyTorch
JAX
TensorBoard
Safetensors
Dutch
gpt2
gpt2-large
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
yhavinga commited on
Commit
055f129
·
1 Parent(s): d8eaa92

Saving checkpoint and logs at step 360000

Browse files
Files changed (11) hide show
  1. ckpt-360000/config.json +38 -0
  2. ckpt-360000/flax_model.msgpack +3 -0
  3. ckpt-360000/opt_state.msgpack +3 -0
  4. ckpt-360000/training_state.json +1 -0
  5. runs/events.out.tfevents.1641027824.t1v-n-f9cfcc28-w-0.77645.0.v2 +3 -0
  6. runs/events.out.tfevents.1641028749.t1v-n-f9cfcc28-w-0.80857.0.v2 +3 -0
  7. runs/events.out.tfevents.1641031320.t1v-n-f9cfcc28-w-0.85207.0.v2 +3 -0
  8. runs/events.out.tfevents.1641033635.t1v-n-f9cfcc28-w-0.88769.0.v2 +3 -0
  9. runs/events.out.tfevents.1641054222.t1v-n-f9cfcc28-w-0.98674.0.v2 +3 -0
  10. runs/events.out.tfevents.1641055087.t1v-n-f9cfcc28-w-0.110334.0.v2 +3 -0
  11. runs/events.out.tfevents.1641055391.t1v-n-f9cfcc28-w-0.112189.0.v2 +3 -0
ckpt-360000/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/yeb/data/gpt2-large-dutch-2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.0,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.13.0",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
ckpt-360000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e0de2d54eb3b7bc5f13c45c1e8a09a567817e57b530a02d5a48c5ffae1c8ec
3
+ size 3096134690
ckpt-360000/opt_state.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b36d51344c1e080292135b99672910ca9e981c7e6dca2af6127627e5145e10d
3
+ size 5611008
ckpt-360000/training_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"step": 360001}
runs/events.out.tfevents.1641027824.t1v-n-f9cfcc28-w-0.77645.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d605b44ebcfa0fd3d225ad471f2e074ac95dca362f4e2b8c21d0f64e634ab2ce
3
+ size 40
runs/events.out.tfevents.1641028749.t1v-n-f9cfcc28-w-0.80857.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fa173469dc1c82c59b12b6f68508554c7e28c0c9133813ecb215c206397ee6
3
+ size 441483
runs/events.out.tfevents.1641031320.t1v-n-f9cfcc28-w-0.85207.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a7fadc0170fc57bac114f24615fffff20cb7739695e7eb3791e893b33cee61
3
+ size 367914
runs/events.out.tfevents.1641033635.t1v-n-f9cfcc28-w-0.88769.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f09748ea45488ea363401567aa6b2a93771b0383cf9c933b865959a633e760
3
+ size 1619013
runs/events.out.tfevents.1641054222.t1v-n-f9cfcc28-w-0.98674.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231cba331f1db1eca87731face3cc13ff79c93c16454d3eb61a401444ebc65ab
3
+ size 40
runs/events.out.tfevents.1641055087.t1v-n-f9cfcc28-w-0.110334.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acfd659bc685866d4a47dc94a305ef2138f16b9abdbe1bafb46903f2b24c4b69
3
+ size 40
runs/events.out.tfevents.1641055391.t1v-n-f9cfcc28-w-0.112189.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f49cb4b742ac7ebe1f71281334586064571b27c97412cd1d4ddbae2852e08da
3
+ size 53678253