Hugging Face's logo

DavidLanz
/
uuu_fine_tune_taipower

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
DavidLanz commited on
Commit
f6c9f51
•
1 Parent(s): a00bd1a

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-2400/config.json +39 -0
  2. checkpoint-2400/generation_config.json +6 -0
  3. checkpoint-2400/optimizer.pt +3 -0
  4. checkpoint-2400/pytorch_model.bin +3 -0
  5. checkpoint-2400/rng_state.pth +3 -0
  6. checkpoint-2400/scheduler.pt +3 -0
  7. checkpoint-2400/trainer_state.json +40 -0
  8. checkpoint-2400/training_args.bin +3 -0
  9. config.json +39 -0
  10. generation_config.json +6 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-2400/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
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": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
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
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.29.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-2400/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.29.2"
6
+ }
checkpoint-2400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e9687fe30c08d0fa4b09b585031b67763b3005598ac347b1a0c615b9f47e87
3
+ size 995610735
checkpoint-2400/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd02c88cc75073d3ed6b7b23f9d991643371a56fadb848fc3c27ff9bd79bb48a
3
+ size 510400655
checkpoint-2400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1addc282820a7f75c233d28b32b7773e2eeb7fa4ac89134519a40bd54046bd44
3
+ size 14655
checkpoint-2400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c274dd7600f3eb7039443bd0fd9623073373bede799a0a2c176db891d9208a9b
3
+ size 623
checkpoint-2400/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.572347266881029,
5
+ "global_step": 2400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.54,
12
+ "learning_rate": 5e-05,
13
+ "loss": 3.7701,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.07,
18
+ "learning_rate": 3.9125706829056117e-05,
19
+ "loss": 3.4878,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.61,
24
+ "learning_rate": 2.8251413658112224e-05,
25
+ "loss": 3.1876,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.14,
30
+ "learning_rate": 1.7377120487168335e-05,
31
+ "loss": 3.0536,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 2799,
36
+ "num_train_epochs": 3,
37
+ "total_flos": 313419792384000.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21e45009ca596710dd3d96b3f447ece6734d31191dd4d92ed479ff4b6a4e92c
3
+ size 3887
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
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": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
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
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.29.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.29.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf5a211010cd5e5ccfd926b671dbd73cb5ff71d73aa5b76444910e319542770
3
+ size 510400655
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21e45009ca596710dd3d96b3f447ece6734d31191dd4d92ed479ff4b6a4e92c
3
+ size 3887