Hugging Face's logo

harpertoken
/
harpertokenConvFT

Text Generation
Transformers
Safetensors
English
gpt2
text-generation-inference
conversational-ai
Model card Files
xet
Community
1
Niladri Das 🦊 commited on
Commit
29a3c4e
·
verified ·
1 Parent(s): dd2d947

Upload fine-tuned conversational AI model

Browse files
Files changed (36) hide show
  1. added_tokens.json +3 -0
  2. checkpoint-3000/config.json +39 -0
  3. checkpoint-3000/generation_config.json +6 -0
  4. checkpoint-3000/optimizer.pt +3 -0
  5. checkpoint-3000/pytorch_model.bin +3 -0
  6. checkpoint-3000/rng_state.pth +3 -0
  7. checkpoint-3000/scheduler.pt +3 -0
  8. checkpoint-3000/trainer_state.json +68 -0
  9. checkpoint-3000/training_args.bin +3 -0
  10. checkpoint-3500/config.json +39 -0
  11. checkpoint-3500/generation_config.json +6 -0
  12. checkpoint-3500/optimizer.pt +3 -0
  13. checkpoint-3500/pytorch_model.bin +3 -0
  14. checkpoint-3500/rng_state.pth +3 -0
  15. checkpoint-3500/scheduler.pt +3 -0
  16. checkpoint-3500/trainer_state.json +74 -0
  17. checkpoint-3500/training_args.bin +3 -0
  18. config.json +39 -0
  19. generation_config.json +6 -0
  20. merges.txt +0 -0
  21. pytorch_model.bin +3 -0
  22. runs/Feb23_19-50-33_Niladris-MacBook-Air.local/1740320433.63562/events.out.tfevents.1740320433.Niladris-MacBook-Air.local.15447.1 +3 -0
  23. runs/Feb23_19-50-33_Niladris-MacBook-Air.local/events.out.tfevents.1740320433.Niladris-MacBook-Air.local.15447.0 +3 -0
  24. runs/Feb23_19-55-02_Niladris-MacBook-Air.local/1740320703.005991/events.out.tfevents.1740320703.Niladris-MacBook-Air.local.16330.1 +3 -0
  25. runs/Feb23_19-55-02_Niladris-MacBook-Air.local/events.out.tfevents.1740320703.Niladris-MacBook-Air.local.16330.0 +3 -0
  26. runs/Feb23_19-59-16_Niladris-MacBook-Air.local/1740320956.977622/events.out.tfevents.1740320956.Niladris-MacBook-Air.local.16794.1 +3 -0
  27. runs/Feb23_19-59-16_Niladris-MacBook-Air.local/events.out.tfevents.1740320956.Niladris-MacBook-Air.local.16794.0 +3 -0
  28. runs/Feb23_21-04-45_Niladris-MacBook-Air.local/1740324886.016059/events.out.tfevents.1740324886.Niladris-MacBook-Air.local.20955.1 +3 -0
  29. runs/Feb23_21-04-45_Niladris-MacBook-Air.local/events.out.tfevents.1740324886.Niladris-MacBook-Air.local.20955.0 +3 -0
  30. runs/Feb23_21-08-37_Niladris-MacBook-Air.local/1740325117.034147/events.out.tfevents.1740325117.Niladris-MacBook-Air.local.21268.1 +3 -0
  31. runs/Feb23_21-08-37_Niladris-MacBook-Air.local/events.out.tfevents.1740325117.Niladris-MacBook-Air.local.21268.0 +3 -0
  32. special_tokens_map.json +6 -0
  33. tokenizer.json +0 -0
  34. tokenizer_config.json +9 -0
  35. training_args.bin +3 -0
  36. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
checkpoint-3000/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": "4.28.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-3000/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": "4.28.1"
6
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0276b81ff098c3b14fb29b15314bf3f6990c22ab8311d19928f15f0385c0e7c
3
+ size 995607173
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f92f0404692b5d46667d7e667ca81bbda52cea4d95cdc09fed7a837cb7b91d4
3
+ size 510398653
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc1b860ca2cc776b1b2bf2bb8290ce5e0bb511759efc5a9d1955b2bf4f5fe58
3
+ size 13553
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbdc2e29d939578fc4c0291d4ecc220994406c44a5bfcd16c19948f53978ac12
3
+ size 627
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.4,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.4,
12
+ "learning_rate": 1.7333333333333336e-05,
13
+ "loss": 3.1868,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.8,
18
+ "learning_rate": 1.4666666666666666e-05,
19
+ "loss": 1.9989,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_loss": 1.985045313835144,
25
+ "eval_runtime": 997.7945,
26
+ "eval_samples_per_second": 10.022,
27
+ "eval_steps_per_second": 1.253,
28
+ "step": 1250
29
+ },
30
+ {
31
+ "epoch": 1.2,
32
+ "learning_rate": 1.2e-05,
33
+ "loss": 1.9389,
34
+ "step": 1500
35
+ },
36
+ {
37
+ "epoch": 1.6,
38
+ "learning_rate": 9.333333333333334e-06,
39
+ "loss": 1.8992,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "learning_rate": 6.666666666666667e-06,
45
+ "loss": 1.8668,
46
+ "step": 2500
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 1.9320968389511108,
51
+ "eval_runtime": 1179.2887,
52
+ "eval_samples_per_second": 8.48,
53
+ "eval_steps_per_second": 1.06,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 2.4,
58
+ "learning_rate": 4.000000000000001e-06,
59
+ "loss": 1.8505,
60
+ "step": 3000
61
+ }
62
+ ],
63
+ "max_steps": 3750,
64
+ "num_train_epochs": 3,
65
+ "total_flos": 1567752192000000.0,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3de59169804b003fabfd560ee4510ebdc845ec2aa625b6ef18675e134aa1d3
3
+ size 3579
checkpoint-3500/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": "4.28.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-3500/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": "4.28.1"
6
+ }
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e262cf803f368535170a97fb0a736c037db4638daa20ebe171677b4a8e49cab
3
+ size 995607173
checkpoint-3500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244a093d4758f2930e06904bb5ea2b5a1b80bfdf1f094d458a6c4980c8fb884b
3
+ size 510398653
checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d5bb56406884b635bb14258a2225b6afdb8bc58ac25ffd83159882562e3a84
3
+ size 13553
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d1e37d77ae48420c7f91bbfc458b7c7efd68cd2532a891d8331036a22a914a
3
+ size 627
checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.8,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.4,
12
+ "learning_rate": 1.7333333333333336e-05,
13
+ "loss": 3.1868,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.8,
18
+ "learning_rate": 1.4666666666666666e-05,
19
+ "loss": 1.9989,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_loss": 1.985045313835144,
25
+ "eval_runtime": 997.7945,
26
+ "eval_samples_per_second": 10.022,
27
+ "eval_steps_per_second": 1.253,
28
+ "step": 1250
29
+ },
30
+ {
31
+ "epoch": 1.2,
32
+ "learning_rate": 1.2e-05,
33
+ "loss": 1.9389,
34
+ "step": 1500
35
+ },
36
+ {
37
+ "epoch": 1.6,
38
+ "learning_rate": 9.333333333333334e-06,
39
+ "loss": 1.8992,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "learning_rate": 6.666666666666667e-06,
45
+ "loss": 1.8668,
46
+ "step": 2500
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 1.9320968389511108,
51
+ "eval_runtime": 1179.2887,
52
+ "eval_samples_per_second": 8.48,
53
+ "eval_steps_per_second": 1.06,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 2.4,
58
+ "learning_rate": 4.000000000000001e-06,
59
+ "loss": 1.8505,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 2.8,
64
+ "learning_rate": 1.3333333333333334e-06,
65
+ "loss": 1.8329,
66
+ "step": 3500
67
+ }
68
+ ],
69
+ "max_steps": 3750,
70
+ "num_train_epochs": 3,
71
+ "total_flos": 1829044224000000.0,
72
+ "trial_name": null,
73
+ "trial_params": null
74
+ }
checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3de59169804b003fabfd560ee4510ebdc845ec2aa625b6ef18675e134aa1d3
3
+ size 3579
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": "4.28.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
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": "4.28.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d4469a1f8d8b40db4fe4ded15e67da46a0e62d2f54912821c0286d26d77336
3
+ size 510398653
runs/Feb23_19-50-33_Niladris-MacBook-Air.local/1740320433.63562/events.out.tfevents.1740320433.Niladris-MacBook-Air.local.15447.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79754ebcc32a4406f9958a3e914e15f4aafc32b52771efdced8e306a0e95f32d
3
+ size 5890
runs/Feb23_19-50-33_Niladris-MacBook-Air.local/events.out.tfevents.1740320433.Niladris-MacBook-Air.local.15447.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9c0b6272d5852be44313fd691b3c76afd099f0d6a9eb0420e9a9f11ce86365
3
+ size 3941
runs/Feb23_19-55-02_Niladris-MacBook-Air.local/1740320703.005991/events.out.tfevents.1740320703.Niladris-MacBook-Air.local.16330.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5c6cc80393b78ba66ad8e7e67a26f461aecbdeacf6d0500d51e853c78012af
3
+ size 5890
runs/Feb23_19-55-02_Niladris-MacBook-Air.local/events.out.tfevents.1740320703.Niladris-MacBook-Air.local.16330.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f398c227d56e2bca48a5ea3f5c6be317a066c9a9b29dc7d4078b472b0c810932
3
+ size 4242
runs/Feb23_19-59-16_Niladris-MacBook-Air.local/1740320956.977622/events.out.tfevents.1740320956.Niladris-MacBook-Air.local.16794.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ec83d4ef24483ef60cc4af74650afbd82a7284e195f061ad4589cb76b513c
3
+ size 5890
runs/Feb23_19-59-16_Niladris-MacBook-Air.local/events.out.tfevents.1740320956.Niladris-MacBook-Air.local.16794.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76069675841c1d9a3da74b94125260233f3cde7091e13d2ffe2152f62b2c9f0c
3
+ size 4556
runs/Feb23_21-04-45_Niladris-MacBook-Air.local/1740324886.016059/events.out.tfevents.1740324886.Niladris-MacBook-Air.local.20955.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2783a52b83f290228798b1807054fa49a26565e7db853ec3a88975f554da29
3
+ size 5890
runs/Feb23_21-04-45_Niladris-MacBook-Air.local/events.out.tfevents.1740324886.Niladris-MacBook-Air.local.20955.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554bd899dc3110d81d04708945c6f67b7376ede935473ce95ad346dafb14bff5
3
+ size 4242
runs/Feb23_21-08-37_Niladris-MacBook-Air.local/1740325117.034147/events.out.tfevents.1740325117.Niladris-MacBook-Air.local.21268.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8edc1b86197fa8d08c749fb60c6145d801ca36b616fba9b4f6269b29e3354a0c
3
+ size 5890
runs/Feb23_21-08-37_Niladris-MacBook-Air.local/events.out.tfevents.1740325117.Niladris-MacBook-Air.local.21268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b597dfe8c735753816a7fd747caaaf89a9fc255b094ecba55ce0c4891169e59
3
+ size 6508
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "[PAD]",
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3de59169804b003fabfd560ee4510ebdc845ec2aa625b6ef18675e134aa1d3
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff