Andyrasika commited on
Commit
e09c46d
·
1 Parent(s): 02f3007

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. checkpoint-10/config.json +39 -0
  2. checkpoint-10/generation_config.json +6 -0
  3. checkpoint-10/optimizer.pt +3 -0
  4. checkpoint-10/pytorch_model.bin +3 -0
  5. checkpoint-10/rng_state.pth +3 -0
  6. checkpoint-10/scheduler.pt +3 -0
  7. checkpoint-10/trainer_state.json +39 -0
  8. checkpoint-10/training_args.bin +3 -0
  9. checkpoint-20/config.json +39 -0
  10. checkpoint-20/generation_config.json +6 -0
  11. checkpoint-20/optimizer.pt +3 -0
  12. checkpoint-20/pytorch_model.bin +3 -0
  13. checkpoint-20/rng_state.pth +3 -0
  14. checkpoint-20/scheduler.pt +3 -0
  15. checkpoint-20/trainer_state.json +59 -0
  16. checkpoint-20/training_args.bin +3 -0
  17. checkpoint-30/config.json +39 -0
  18. checkpoint-30/generation_config.json +6 -0
  19. checkpoint-30/optimizer.pt +3 -0
  20. checkpoint-30/pytorch_model.bin +3 -0
  21. checkpoint-30/rng_state.pth +3 -0
  22. checkpoint-30/scheduler.pt +3 -0
  23. checkpoint-30/trainer_state.json +79 -0
  24. checkpoint-30/training_args.bin +3 -0
  25. checkpoint-40/config.json +39 -0
  26. checkpoint-40/generation_config.json +6 -0
  27. checkpoint-40/optimizer.pt +3 -0
  28. checkpoint-40/pytorch_model.bin +3 -0
  29. checkpoint-40/rng_state.pth +3 -0
  30. checkpoint-40/scheduler.pt +3 -0
  31. checkpoint-40/trainer_state.json +99 -0
  32. checkpoint-40/training_args.bin +3 -0
  33. checkpoint-50/config.json +39 -0
  34. checkpoint-50/generation_config.json +6 -0
  35. checkpoint-50/optimizer.pt +3 -0
  36. checkpoint-50/pytorch_model.bin +3 -0
  37. checkpoint-50/rng_state.pth +3 -0
  38. checkpoint-50/scheduler.pt +3 -0
  39. checkpoint-50/trainer_state.json +119 -0
  40. checkpoint-50/training_args.bin +3 -0
  41. runs/Sep29_04-53-15_5b6467461428/events.out.tfevents.1695963195.5b6467461428.3940.3 +3 -0
checkpoint-10/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./math_book",
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": "4.33.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-10/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": "4.33.3"
6
+ }
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4f3e8d356ede8ddfa6f845f7fedbf97742e58a7649f56f60a98063d4745a89
3
+ size 995641861
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c335e6984bd50e8ea18c94230c137305a44415b5999220e41a0bb64231864e
3
+ size 497807197
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62328148c8e4c0ce2bb0650f6c47af0c53d9f3345dec0c8e4e46294c02b4f424
3
+ size 14575
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbc54c2481c4ea53212b7d37539c1f37bd31b035ecca9d298f9ed7383571b40
3
+ size 627
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.6543781757354736,
3
+ "best_model_checkpoint": "./math_english_to_latex/checkpoint-10",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 4.5e-05,
14
+ "loss": 4.017,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.3664,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 1.6543781757354736,
26
+ "eval_runtime": 0.0554,
27
+ "eval_samples_per_second": 180.399,
28
+ "eval_steps_per_second": 18.04,
29
+ "step": 10
30
+ }
31
+ ],
32
+ "logging_steps": 5,
33
+ "max_steps": 50,
34
+ "num_train_epochs": 5,
35
+ "save_steps": 500,
36
+ "total_flos": 694056960000.0,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
3
+ size 4027
checkpoint-20/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./math_book",
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": "4.33.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-20/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": "4.33.3"
6
+ }
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1b7667f4b02de4be732f087c72e0b013cf844de2b11f677650711381c2deb5
3
+ size 995641861
checkpoint-20/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcc43425abb1dea14dd8311262f4c9b53cdfd4bc4644a96742e23c0213e8bba
3
+ size 497807197
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057c645c56f68344ed12cf18ea084316d300ef23ef187596b39adcec82bbd233
3
+ size 14575
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218685351f80f0f57d14c858d13411acae1cf38e48ed96475c40a18dd6651ff9
3
+ size 627
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9639002084732056,
3
+ "best_model_checkpoint": "./math_english_to_latex/checkpoint-20",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 4.5e-05,
14
+ "loss": 4.017,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.3664,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 1.6543781757354736,
26
+ "eval_runtime": 0.0554,
27
+ "eval_samples_per_second": 180.399,
28
+ "eval_steps_per_second": 18.04,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 1.5,
33
+ "learning_rate": 3.5e-05,
34
+ "loss": 1.5286,
35
+ "step": 15
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "learning_rate": 3e-05,
40
+ "loss": 1.1415,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_loss": 0.9639002084732056,
46
+ "eval_runtime": 0.0432,
47
+ "eval_samples_per_second": 231.663,
48
+ "eval_steps_per_second": 23.166,
49
+ "step": 20
50
+ }
51
+ ],
52
+ "logging_steps": 5,
53
+ "max_steps": 50,
54
+ "num_train_epochs": 5,
55
+ "save_steps": 500,
56
+ "total_flos": 1412610048000.0,
57
+ "trial_name": null,
58
+ "trial_params": null
59
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
3
+ size 4027
checkpoint-30/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./math_book",
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": "4.33.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-30/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": "4.33.3"
6
+ }
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68e06dc6b13221fcecfabefc480e582e077d12787eb3924b4b868a29c1c9a51
3
+ size 995641861
checkpoint-30/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614ddbf13abcd71e5f5d73eab2c13f9495ce3ae76f5421fd0ad0e3601d35ee27
3
+ size 497807197
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17aecbce0613ea0c67554a9c2289b172a9e286beca6035c8c06f4bfef55b9b70
3
+ size 14575
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8948c2ceacdd0aa40c8e2cda98255fcdabc97f46c055f4ac17431041ab0b3492
3
+ size 627
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9328243136405945,
3
+ "best_model_checkpoint": "./math_english_to_latex/checkpoint-30",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 4.5e-05,
14
+ "loss": 4.017,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.3664,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 1.6543781757354736,
26
+ "eval_runtime": 0.0554,
27
+ "eval_samples_per_second": 180.399,
28
+ "eval_steps_per_second": 18.04,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 1.5,
33
+ "learning_rate": 3.5e-05,
34
+ "loss": 1.5286,
35
+ "step": 15
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "learning_rate": 3e-05,
40
+ "loss": 1.1415,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_loss": 0.9639002084732056,
46
+ "eval_runtime": 0.0432,
47
+ "eval_samples_per_second": 231.663,
48
+ "eval_steps_per_second": 23.166,
49
+ "step": 20
50
+ },
51
+ {
52
+ "epoch": 2.5,
53
+ "learning_rate": 2.5e-05,
54
+ "loss": 1.0088,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "learning_rate": 2e-05,
60
+ "loss": 0.8763,
61
+ "step": 30
62
+ },
63
+ {
64
+ "epoch": 3.0,
65
+ "eval_loss": 0.9328243136405945,
66
+ "eval_runtime": 0.0558,
67
+ "eval_samples_per_second": 179.081,
68
+ "eval_steps_per_second": 17.908,
69
+ "step": 30
70
+ }
71
+ ],
72
+ "logging_steps": 5,
73
+ "max_steps": 50,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 2104625664000.0,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
3
+ size 4027
checkpoint-40/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./math_book",
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": "4.33.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-40/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": "4.33.3"
6
+ }
checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3453d46a769b00834686d59fb20cb1c28d3a6e2b3ad5672ad85359cf7895f8
3
+ size 995641861
checkpoint-40/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775f950a6d635bf980bbe63af2b91b6ff92e9f7347fb7f90a8fc276e946cb0ee
3
+ size 497807197
checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d6249fe5dbe9ed1bdc4e1e9d80fa12fbc07191f47a1e57dc947f3569fdc481
3
+ size 14575
checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d499424d0de0fd41d728ede1e4893a9a720923ec53cfd9bdd2b1d9dc3ef04c
3
+ size 627
checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8390220403671265,
3
+ "best_model_checkpoint": "./math_english_to_latex/checkpoint-40",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 4.5e-05,
14
+ "loss": 4.017,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.3664,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 1.6543781757354736,
26
+ "eval_runtime": 0.0554,
27
+ "eval_samples_per_second": 180.399,
28
+ "eval_steps_per_second": 18.04,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 1.5,
33
+ "learning_rate": 3.5e-05,
34
+ "loss": 1.5286,
35
+ "step": 15
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "learning_rate": 3e-05,
40
+ "loss": 1.1415,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_loss": 0.9639002084732056,
46
+ "eval_runtime": 0.0432,
47
+ "eval_samples_per_second": 231.663,
48
+ "eval_steps_per_second": 23.166,
49
+ "step": 20
50
+ },
51
+ {
52
+ "epoch": 2.5,
53
+ "learning_rate": 2.5e-05,
54
+ "loss": 1.0088,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "learning_rate": 2e-05,
60
+ "loss": 0.8763,
61
+ "step": 30
62
+ },
63
+ {
64
+ "epoch": 3.0,
65
+ "eval_loss": 0.9328243136405945,
66
+ "eval_runtime": 0.0558,
67
+ "eval_samples_per_second": 179.081,
68
+ "eval_steps_per_second": 17.908,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 3.5,
73
+ "learning_rate": 1.5e-05,
74
+ "loss": 0.7908,
75
+ "step": 35
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "learning_rate": 1e-05,
80
+ "loss": 0.7064,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 4.0,
85
+ "eval_loss": 0.8390220403671265,
86
+ "eval_runtime": 0.0587,
87
+ "eval_samples_per_second": 170.325,
88
+ "eval_steps_per_second": 17.032,
89
+ "step": 40
90
+ }
91
+ ],
92
+ "logging_steps": 5,
93
+ "max_steps": 50,
94
+ "num_train_epochs": 5,
95
+ "save_steps": 500,
96
+ "total_flos": 2821137408000.0,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
3
+ size 4027
checkpoint-50/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./math_book",
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": "4.33.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-50/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": "4.33.3"
6
+ }
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2589c0138c8106a780a99c8ce6a96448b92015473973706d98a0a4863ca1fb6c
3
+ size 995641861
checkpoint-50/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55534c9559377760090a8313f92652a5e9dfb16a1f0b54e7dcdcc6759c75e34
3
+ size 497807197
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd6c953ef6c5d1b59c7873d17cbf35f053273ce2e932635048554e043bf5520
3
+ size 14575
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0056b270b78cdea3e106b2ed4ba29feeb330610d33a86c55b973dc5c9fa3140
3
+ size 627
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8027936816215515,
3
+ "best_model_checkpoint": "./math_english_to_latex/checkpoint-50",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 4.5e-05,
14
+ "loss": 4.017,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.3664,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 1.6543781757354736,
26
+ "eval_runtime": 0.0554,
27
+ "eval_samples_per_second": 180.399,
28
+ "eval_steps_per_second": 18.04,
29
+ "step": 10
30
+ },
31
+ {
32
+ "epoch": 1.5,
33
+ "learning_rate": 3.5e-05,
34
+ "loss": 1.5286,
35
+ "step": 15
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "learning_rate": 3e-05,
40
+ "loss": 1.1415,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_loss": 0.9639002084732056,
46
+ "eval_runtime": 0.0432,
47
+ "eval_samples_per_second": 231.663,
48
+ "eval_steps_per_second": 23.166,
49
+ "step": 20
50
+ },
51
+ {
52
+ "epoch": 2.5,
53
+ "learning_rate": 2.5e-05,
54
+ "loss": 1.0088,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "learning_rate": 2e-05,
60
+ "loss": 0.8763,
61
+ "step": 30
62
+ },
63
+ {
64
+ "epoch": 3.0,
65
+ "eval_loss": 0.9328243136405945,
66
+ "eval_runtime": 0.0558,
67
+ "eval_samples_per_second": 179.081,
68
+ "eval_steps_per_second": 17.908,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 3.5,
73
+ "learning_rate": 1.5e-05,
74
+ "loss": 0.7908,
75
+ "step": 35
76
+ },
77
+ {
78
+ "epoch": 4.0,
79
+ "learning_rate": 1e-05,
80
+ "loss": 0.7064,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 4.0,
85
+ "eval_loss": 0.8390220403671265,
86
+ "eval_runtime": 0.0587,
87
+ "eval_samples_per_second": 170.325,
88
+ "eval_steps_per_second": 17.032,
89
+ "step": 40
90
+ },
91
+ {
92
+ "epoch": 4.5,
93
+ "learning_rate": 5e-06,
94
+ "loss": 0.7189,
95
+ "step": 45
96
+ },
97
+ {
98
+ "epoch": 5.0,
99
+ "learning_rate": 0.0,
100
+ "loss": 0.6468,
101
+ "step": 50
102
+ },
103
+ {
104
+ "epoch": 5.0,
105
+ "eval_loss": 0.8027936816215515,
106
+ "eval_runtime": 0.045,
107
+ "eval_samples_per_second": 222.202,
108
+ "eval_steps_per_second": 22.22,
109
+ "step": 50
110
+ }
111
+ ],
112
+ "logging_steps": 5,
113
+ "max_steps": 50,
114
+ "num_train_epochs": 5,
115
+ "save_steps": 500,
116
+ "total_flos": 3529483776000.0,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
3
+ size 4027
runs/Sep29_04-53-15_5b6467461428/events.out.tfevents.1695963195.5b6467461428.3940.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ecf37153b98806ea96d1342c2f524c5b8c35d50e4c4b54d3396929d292b21d
3
+ size 8019