Hugging Face's logo

eabybabu
/
chatbot_model

Safetensors
gpt2
Model card Files
xet
 Community
eabybabu commited on
Commit
859e405
·
1 Parent(s): b6beeae

Upload trained chatbot model

Browse files
Files changed (25) hide show
  1. checkpoint-2000/config.json +39 -0
  2. checkpoint-2000/generation_config.json +6 -0
  3. checkpoint-2000/model.safetensors +3 -0
  4. checkpoint-2000/optimizer.pt +3 -0
  5. checkpoint-2000/rng_state.pth +3 -0
  6. checkpoint-2000/scheduler.pt +3 -0
  7. checkpoint-2000/trainer_state.json +77 -0
  8. checkpoint-2000/training_args.bin +3 -0
  9. checkpoint-2247/config.json +39 -0
  10. checkpoint-2247/generation_config.json +6 -0
  11. checkpoint-2247/model.safetensors +3 -0
  12. checkpoint-2247/optimizer.pt +3 -0
  13. checkpoint-2247/rng_state.pth +3 -0
  14. checkpoint-2247/scheduler.pt +3 -0
  15. checkpoint-2247/trainer_state.json +77 -0
  16. checkpoint-2247/training_args.bin +3 -0
  17. config.json +39 -0
  18. generation_config.json +6 -0
  19. merges.txt +0 -0
  20. model.safetensors +3 -0
  21. special_tokens_map.json +6 -0
  22. tokenizer.json +0 -0
  23. tokenizer_config.json +21 -0
  24. training_args.bin +3 -0
  25. vocab.json +0 -0
checkpoint-2000/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": "4.49.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-2000/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": "4.49.0"
6
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6f4d69e47a444929c66c67fdb01a4109762a602042bdf6b208f00c6e9ad756
3
+ size 497774208
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e753dbdd5cf298993ba140fa170338986cdaf1dbe7720885c17dcd2348d1605
3
+ size 995638202
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba46a308d03ed7f92ec63c0883d68587f27335022700ab441d1d4a1ef9beee93
3
+ size 13990
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e777dbfe469f407038f89173dc589b1aeb19386d5795bc3d5cd6bef473a27c6d
3
+ size 1064
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.67022696929239,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6675567423230975,
13
+ "grad_norm": 26.4691104888916,
14
+ "learning_rate": 3.887405429461504e-05,
15
+ "loss": 3.0221,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 2.436640501022339,
21
+ "eval_runtime": 397.2989,
22
+ "eval_samples_per_second": 0.423,
23
+ "eval_steps_per_second": 0.053,
24
+ "step": 749
25
+ },
26
+ {
27
+ "epoch": 1.335113484646195,
28
+ "grad_norm": 52.74542999267578,
29
+ "learning_rate": 2.774810858923009e-05,
30
+ "loss": 2.3297,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_loss": 2.2850723266601562,
36
+ "eval_runtime": 382.014,
37
+ "eval_samples_per_second": 0.44,
38
+ "eval_steps_per_second": 0.055,
39
+ "step": 1498
40
+ },
41
+ {
42
+ "epoch": 2.0026702269692924,
43
+ "grad_norm": 24.449501037597656,
44
+ "learning_rate": 1.6622162883845125e-05,
45
+ "loss": 1.9653,
46
+ "step": 1500
47
+ },
48
+ {
49
+ "epoch": 2.67022696929239,
50
+ "grad_norm": 30.147035598754883,
51
+ "learning_rate": 5.4962171784601695e-06,
52
+ "loss": 1.6578,
53
+ "step": 2000
54
+ }
55
+ ],
56
+ "logging_steps": 500,
57
+ "max_steps": 2247,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 3,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "TrainerControl": {
63
+ "args": {
64
+ "should_epoch_stop": false,
65
+ "should_evaluate": false,
66
+ "should_log": false,
67
+ "should_save": true,
68
+ "should_training_stop": false
69
+ },
70
+ "attributes": {}
71
+ }
72
+ },
73
+ "total_flos": 2090336256000000.0,
74
+ "train_batch_size": 2,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55a53c06dd42d123aaa6ab992fe860b8215e040cf3c4737d58ed301d3161750
3
+ size 5240
checkpoint-2247/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": "4.49.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-2247/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": "4.49.0"
6
+ }
checkpoint-2247/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bcf9723eea6b763bbd1130bff1e619afc7f07c51656fee0851c69219a4d05c
3
+ size 497774208
checkpoint-2247/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfae24edc060ea8b6b7ea9226b4a2bd87d795f8f9a444d09934c1810d6df3e8
3
+ size 995638202
checkpoint-2247/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea2efab5e1b0312a39c7bea30c45799c98ede47ee97e386913dbbcaaca855d0
3
+ size 13990
checkpoint-2247/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc26ff9336644f67ae4ce815786a8df061597a2066308d5ed6bb79aa2d0f8b56
3
+ size 1064
checkpoint-2247/trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2247,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6675567423230975,
13
+ "grad_norm": 26.4691104888916,
14
+ "learning_rate": 3.887405429461504e-05,
15
+ "loss": 3.0221,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 2.436640501022339,
21
+ "eval_runtime": 397.2989,
22
+ "eval_samples_per_second": 0.423,
23
+ "eval_steps_per_second": 0.053,
24
+ "step": 749
25
+ },
26
+ {
27
+ "epoch": 1.335113484646195,
28
+ "grad_norm": 52.74542999267578,
29
+ "learning_rate": 2.774810858923009e-05,
30
+ "loss": 2.3297,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_loss": 2.2850723266601562,
36
+ "eval_runtime": 382.014,
37
+ "eval_samples_per_second": 0.44,
38
+ "eval_steps_per_second": 0.055,
39
+ "step": 1498
40
+ },
41
+ {
42
+ "epoch": 2.0026702269692924,
43
+ "grad_norm": 24.449501037597656,
44
+ "learning_rate": 1.6622162883845125e-05,
45
+ "loss": 1.9653,
46
+ "step": 1500
47
+ },
48
+ {
49
+ "epoch": 2.67022696929239,
50
+ "grad_norm": 30.147035598754883,
51
+ "learning_rate": 5.4962171784601695e-06,
52
+ "loss": 1.6578,
53
+ "step": 2000
54
+ }
55
+ ],
56
+ "logging_steps": 500,
57
+ "max_steps": 2247,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 3,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "TrainerControl": {
63
+ "args": {
64
+ "should_epoch_stop": false,
65
+ "should_evaluate": false,
66
+ "should_log": false,
67
+ "should_save": true,
68
+ "should_training_stop": true
69
+ },
70
+ "attributes": {}
71
+ }
72
+ },
73
+ "total_flos": 2348492783616000.0,
74
+ "train_batch_size": 2,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
checkpoint-2247/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55a53c06dd42d123aaa6ab992fe860b8215e040cf3c4737d58ed301d3161750
3
+ size 5240
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": "4.49.0",
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": "4.49.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bcf9723eea6b763bbd1130bff1e619afc7f07c51656fee0851c69219a4d05c
3
+ size 497774208
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55a53c06dd42d123aaa6ab992fe860b8215e040cf3c4737d58ed301d3161750
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff