lewtun HF staff commited on
Commit
b8ea4a9
1 Parent(s): cca3f2b

End of training

Browse files
Files changed (42) hide show
  1. .gitignore +1 -0
  2. all_results.json +14 -0
  3. config.json +39 -0
  4. eval_results.json +9 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. pytorch_model-00001-of-00007.bin +3 -0
  8. pytorch_model-00002-of-00007.bin +3 -0
  9. pytorch_model-00003-of-00007.bin +3 -0
  10. pytorch_model-00004-of-00007.bin +3 -0
  11. pytorch_model-00005-of-00007.bin +3 -0
  12. pytorch_model-00006-of-00007.bin +3 -0
  13. pytorch_model-00007-of-00007.bin +3 -0
  14. pytorch_model.bin.index.json +492 -0
  15. runs/Apr20_12-05-59_ip-26-0-147-94/1681992793.492106/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.1 +3 -0
  16. runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.0 +3 -0
  17. runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992826.ip-26-0-147-94.2699266.2 +3 -0
  18. runs/Apr20_12-22-28_ip-26-0-147-94/1681993752.2594001/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.1 +3 -0
  19. runs/Apr20_12-22-28_ip-26-0-147-94/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.0 +3 -0
  20. runs/Apr20_12-32-13_ip-26-0-147-94/1681994151.4570813/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.1 +3 -0
  21. runs/Apr20_12-32-13_ip-26-0-147-94/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.0 +3 -0
  22. runs/Apr20_12-52-07_ip-26-0-147-94/1681995544.3466527/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.1 +3 -0
  23. runs/Apr20_12-52-07_ip-26-0-147-94/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.0 +3 -0
  24. runs/Apr20_13-03-47_ip-26-0-147-94/1681996046.2437541/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.1 +3 -0
  25. runs/Apr20_13-03-47_ip-26-0-147-94/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.0 +3 -0
  26. runs/Apr20_13-18-36_ip-26-0-147-94/1681997147.8418489/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.1 +3 -0
  27. runs/Apr20_13-18-36_ip-26-0-147-94/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.0 +3 -0
  28. runs/Apr20_13-42-06_ip-26-0-147-94/1681998575.4662077/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.1 +3 -0
  29. runs/Apr20_13-42-06_ip-26-0-147-94/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.0 +3 -0
  30. runs/Apr20_13-58-51_ip-26-0-147-94/1681999524.7086265/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.1 +3 -0
  31. runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.0 +3 -0
  32. runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999553.ip-26-0-147-94.2739528.2 +3 -0
  33. runs/Apr20_14-08-16_ip-26-0-147-94/1681999901.4178648/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.1 +3 -0
  34. runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.0 +3 -0
  35. runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999931.ip-26-0-147-94.2743104.2 +3 -0
  36. special_tokens_map.json +26 -0
  37. tokenizer.json +0 -0
  38. tokenizer_config.json +31 -0
  39. train_results.json +8 -0
  40. trainer_state.json +39 -0
  41. training_args.bin +3 -0
  42. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "eval_loss": 1.1604644060134888,
4
+ "eval_runtime": 6.6615,
5
+ "eval_samples": 226,
6
+ "eval_samples_per_second": 33.926,
7
+ "eval_steps_per_second": 4.353,
8
+ "perplexity": 3.1914150443566505,
9
+ "train_loss": 1.1672077178955078,
10
+ "train_runtime": 23.0652,
11
+ "train_samples": 2066,
12
+ "train_samples_per_second": 2.775,
13
+ "train_steps_per_second": 0.043
14
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/large-model",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 6144,
20
+ "n_head": 48,
21
+ "n_inner": 24576,
22
+ "n_layer": 40,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.28.1",
36
+ "use_cache": false,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "eval_loss": 1.1604644060134888,
4
+ "eval_runtime": 6.6615,
5
+ "eval_samples": 226,
6
+ "eval_samples_per_second": 33.926,
7
+ "eval_steps_per_second": 4.353,
8
+ "perplexity": 3.1914150443566505
9
+ }
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-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91b7fa34533fa0015750f154f9874a62cec710b05b9dc52d19913436cdf6b5d
3
+ size 9904380199
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f7ccb60c90eaf74d330157a2eaeb84a59378c4e52cf7572ccd84cc3f673bbd
3
+ size 9860466003
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8bd5d623820cabf7b36e1e004d416d85f6b2f396701573d88456e2da5d33bd
3
+ size 9854247255
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139dc577299f83cb877620baae06650a740e20ed80d6bcd8bb02f6f8d5f7099d
3
+ size 9860466067
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba94a0596bdfe51787decf6d936b3f0ff7ee781021ef2383d888903d0003ba85
3
+ size 9250267479
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998378a9b38869f87e40eb2b34a12b1ffe03aa583958da2b54009902e8c1fd35
3
+ size 467318397
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6243e8a8f7056b688ad85c180abad904ef7f6ea244ded655ba9aa49378d732d
3
+ size 523795
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,492 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 63277785088
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00007-of-00007.bin",
7
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
8
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
9
+ "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
10
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00007.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00007.bin",
13
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00007.bin",
14
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00007.bin",
15
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
16
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
17
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
18
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
19
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
20
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
21
+ "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
22
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
23
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00007.bin",
24
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00007.bin",
25
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00007.bin",
26
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00007.bin",
27
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
28
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
29
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
30
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
31
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
32
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
33
+ "transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
34
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
35
+ "transformer.h.10.ln_1.bias": "pytorch_model-00002-of-00007.bin",
36
+ "transformer.h.10.ln_1.weight": "pytorch_model-00002-of-00007.bin",
37
+ "transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00007.bin",
38
+ "transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00007.bin",
39
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
40
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
41
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
42
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
43
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
44
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
45
+ "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
46
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
47
+ "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00007.bin",
48
+ "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00007.bin",
49
+ "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00007.bin",
50
+ "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00007.bin",
51
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
52
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
53
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
54
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
55
+ "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
56
+ "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
57
+ "transformer.h.12.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
58
+ "transformer.h.12.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
59
+ "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00007.bin",
60
+ "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00007.bin",
61
+ "transformer.h.12.ln_2.bias": "pytorch_model-00003-of-00007.bin",
62
+ "transformer.h.12.ln_2.weight": "pytorch_model-00003-of-00007.bin",
63
+ "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
64
+ "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
65
+ "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
66
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
67
+ "transformer.h.13.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
68
+ "transformer.h.13.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
69
+ "transformer.h.13.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
70
+ "transformer.h.13.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
71
+ "transformer.h.13.ln_1.bias": "pytorch_model-00003-of-00007.bin",
72
+ "transformer.h.13.ln_1.weight": "pytorch_model-00003-of-00007.bin",
73
+ "transformer.h.13.ln_2.bias": "pytorch_model-00003-of-00007.bin",
74
+ "transformer.h.13.ln_2.weight": "pytorch_model-00003-of-00007.bin",
75
+ "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
76
+ "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
77
+ "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
78
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
79
+ "transformer.h.14.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
80
+ "transformer.h.14.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
81
+ "transformer.h.14.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
82
+ "transformer.h.14.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
83
+ "transformer.h.14.ln_1.bias": "pytorch_model-00003-of-00007.bin",
84
+ "transformer.h.14.ln_1.weight": "pytorch_model-00003-of-00007.bin",
85
+ "transformer.h.14.ln_2.bias": "pytorch_model-00003-of-00007.bin",
86
+ "transformer.h.14.ln_2.weight": "pytorch_model-00003-of-00007.bin",
87
+ "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
88
+ "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
89
+ "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
90
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
91
+ "transformer.h.15.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
92
+ "transformer.h.15.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
93
+ "transformer.h.15.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
94
+ "transformer.h.15.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
95
+ "transformer.h.15.ln_1.bias": "pytorch_model-00003-of-00007.bin",
96
+ "transformer.h.15.ln_1.weight": "pytorch_model-00003-of-00007.bin",
97
+ "transformer.h.15.ln_2.bias": "pytorch_model-00003-of-00007.bin",
98
+ "transformer.h.15.ln_2.weight": "pytorch_model-00003-of-00007.bin",
99
+ "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
100
+ "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
101
+ "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
102
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
103
+ "transformer.h.16.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
104
+ "transformer.h.16.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
105
+ "transformer.h.16.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
106
+ "transformer.h.16.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
107
+ "transformer.h.16.ln_1.bias": "pytorch_model-00003-of-00007.bin",
108
+ "transformer.h.16.ln_1.weight": "pytorch_model-00003-of-00007.bin",
109
+ "transformer.h.16.ln_2.bias": "pytorch_model-00003-of-00007.bin",
110
+ "transformer.h.16.ln_2.weight": "pytorch_model-00003-of-00007.bin",
111
+ "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
112
+ "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
113
+ "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
114
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
115
+ "transformer.h.17.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
116
+ "transformer.h.17.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
117
+ "transformer.h.17.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
118
+ "transformer.h.17.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
119
+ "transformer.h.17.ln_1.bias": "pytorch_model-00003-of-00007.bin",
120
+ "transformer.h.17.ln_1.weight": "pytorch_model-00003-of-00007.bin",
121
+ "transformer.h.17.ln_2.bias": "pytorch_model-00003-of-00007.bin",
122
+ "transformer.h.17.ln_2.weight": "pytorch_model-00003-of-00007.bin",
123
+ "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
124
+ "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
125
+ "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
126
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
127
+ "transformer.h.18.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
128
+ "transformer.h.18.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
129
+ "transformer.h.18.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
130
+ "transformer.h.18.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
131
+ "transformer.h.18.ln_1.bias": "pytorch_model-00003-of-00007.bin",
132
+ "transformer.h.18.ln_1.weight": "pytorch_model-00003-of-00007.bin",
133
+ "transformer.h.18.ln_2.bias": "pytorch_model-00003-of-00007.bin",
134
+ "transformer.h.18.ln_2.weight": "pytorch_model-00003-of-00007.bin",
135
+ "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
136
+ "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
137
+ "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
138
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
139
+ "transformer.h.19.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
140
+ "transformer.h.19.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
141
+ "transformer.h.19.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
142
+ "transformer.h.19.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
143
+ "transformer.h.19.ln_1.bias": "pytorch_model-00004-of-00007.bin",
144
+ "transformer.h.19.ln_1.weight": "pytorch_model-00004-of-00007.bin",
145
+ "transformer.h.19.ln_2.bias": "pytorch_model-00004-of-00007.bin",
146
+ "transformer.h.19.ln_2.weight": "pytorch_model-00004-of-00007.bin",
147
+ "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
148
+ "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
149
+ "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
150
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
151
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
152
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
153
+ "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
154
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
155
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00007.bin",
156
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00007.bin",
157
+ "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00007.bin",
158
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00007.bin",
159
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
160
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
161
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
162
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
163
+ "transformer.h.20.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
164
+ "transformer.h.20.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
165
+ "transformer.h.20.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
166
+ "transformer.h.20.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
167
+ "transformer.h.20.ln_1.bias": "pytorch_model-00004-of-00007.bin",
168
+ "transformer.h.20.ln_1.weight": "pytorch_model-00004-of-00007.bin",
169
+ "transformer.h.20.ln_2.bias": "pytorch_model-00004-of-00007.bin",
170
+ "transformer.h.20.ln_2.weight": "pytorch_model-00004-of-00007.bin",
171
+ "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
172
+ "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
173
+ "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
174
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
175
+ "transformer.h.21.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
176
+ "transformer.h.21.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
177
+ "transformer.h.21.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
178
+ "transformer.h.21.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
179
+ "transformer.h.21.ln_1.bias": "pytorch_model-00004-of-00007.bin",
180
+ "transformer.h.21.ln_1.weight": "pytorch_model-00004-of-00007.bin",
181
+ "transformer.h.21.ln_2.bias": "pytorch_model-00004-of-00007.bin",
182
+ "transformer.h.21.ln_2.weight": "pytorch_model-00004-of-00007.bin",
183
+ "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
184
+ "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
185
+ "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
186
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
187
+ "transformer.h.22.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
188
+ "transformer.h.22.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
189
+ "transformer.h.22.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
190
+ "transformer.h.22.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
191
+ "transformer.h.22.ln_1.bias": "pytorch_model-00004-of-00007.bin",
192
+ "transformer.h.22.ln_1.weight": "pytorch_model-00004-of-00007.bin",
193
+ "transformer.h.22.ln_2.bias": "pytorch_model-00004-of-00007.bin",
194
+ "transformer.h.22.ln_2.weight": "pytorch_model-00004-of-00007.bin",
195
+ "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
196
+ "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
197
+ "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
198
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
199
+ "transformer.h.23.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
200
+ "transformer.h.23.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
201
+ "transformer.h.23.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
202
+ "transformer.h.23.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
203
+ "transformer.h.23.ln_1.bias": "pytorch_model-00004-of-00007.bin",
204
+ "transformer.h.23.ln_1.weight": "pytorch_model-00004-of-00007.bin",
205
+ "transformer.h.23.ln_2.bias": "pytorch_model-00004-of-00007.bin",
206
+ "transformer.h.23.ln_2.weight": "pytorch_model-00004-of-00007.bin",
207
+ "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
208
+ "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
209
+ "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
210
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
211
+ "transformer.h.24.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
212
+ "transformer.h.24.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
213
+ "transformer.h.24.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
214
+ "transformer.h.24.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
215
+ "transformer.h.24.ln_1.bias": "pytorch_model-00004-of-00007.bin",
216
+ "transformer.h.24.ln_1.weight": "pytorch_model-00004-of-00007.bin",
217
+ "transformer.h.24.ln_2.bias": "pytorch_model-00004-of-00007.bin",
218
+ "transformer.h.24.ln_2.weight": "pytorch_model-00004-of-00007.bin",
219
+ "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
220
+ "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
221
+ "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
222
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
223
+ "transformer.h.25.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
224
+ "transformer.h.25.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
225
+ "transformer.h.25.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
226
+ "transformer.h.25.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
227
+ "transformer.h.25.ln_1.bias": "pytorch_model-00004-of-00007.bin",
228
+ "transformer.h.25.ln_1.weight": "pytorch_model-00004-of-00007.bin",
229
+ "transformer.h.25.ln_2.bias": "pytorch_model-00005-of-00007.bin",
230
+ "transformer.h.25.ln_2.weight": "pytorch_model-00005-of-00007.bin",
231
+ "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
232
+ "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
233
+ "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
234
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
235
+ "transformer.h.26.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
236
+ "transformer.h.26.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
237
+ "transformer.h.26.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
238
+ "transformer.h.26.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
239
+ "transformer.h.26.ln_1.bias": "pytorch_model-00005-of-00007.bin",
240
+ "transformer.h.26.ln_1.weight": "pytorch_model-00005-of-00007.bin",
241
+ "transformer.h.26.ln_2.bias": "pytorch_model-00005-of-00007.bin",
242
+ "transformer.h.26.ln_2.weight": "pytorch_model-00005-of-00007.bin",
243
+ "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
244
+ "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
245
+ "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
246
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
247
+ "transformer.h.27.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
248
+ "transformer.h.27.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
249
+ "transformer.h.27.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
250
+ "transformer.h.27.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
251
+ "transformer.h.27.ln_1.bias": "pytorch_model-00005-of-00007.bin",
252
+ "transformer.h.27.ln_1.weight": "pytorch_model-00005-of-00007.bin",
253
+ "transformer.h.27.ln_2.bias": "pytorch_model-00005-of-00007.bin",
254
+ "transformer.h.27.ln_2.weight": "pytorch_model-00005-of-00007.bin",
255
+ "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
256
+ "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
257
+ "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
258
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
259
+ "transformer.h.28.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
260
+ "transformer.h.28.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
261
+ "transformer.h.28.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
262
+ "transformer.h.28.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
263
+ "transformer.h.28.ln_1.bias": "pytorch_model-00005-of-00007.bin",
264
+ "transformer.h.28.ln_1.weight": "pytorch_model-00005-of-00007.bin",
265
+ "transformer.h.28.ln_2.bias": "pytorch_model-00005-of-00007.bin",
266
+ "transformer.h.28.ln_2.weight": "pytorch_model-00005-of-00007.bin",
267
+ "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
268
+ "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
269
+ "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
270
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
271
+ "transformer.h.29.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
272
+ "transformer.h.29.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
273
+ "transformer.h.29.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
274
+ "transformer.h.29.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
275
+ "transformer.h.29.ln_1.bias": "pytorch_model-00005-of-00007.bin",
276
+ "transformer.h.29.ln_1.weight": "pytorch_model-00005-of-00007.bin",
277
+ "transformer.h.29.ln_2.bias": "pytorch_model-00005-of-00007.bin",
278
+ "transformer.h.29.ln_2.weight": "pytorch_model-00005-of-00007.bin",
279
+ "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
280
+ "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
281
+ "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
282
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
283
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
284
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
285
+ "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
286
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
287
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00007.bin",
288
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00007.bin",
289
+ "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00007.bin",
290
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00007.bin",
291
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
292
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
293
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
294
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
295
+ "transformer.h.30.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
296
+ "transformer.h.30.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
297
+ "transformer.h.30.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
298
+ "transformer.h.30.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
299
+ "transformer.h.30.ln_1.bias": "pytorch_model-00005-of-00007.bin",
300
+ "transformer.h.30.ln_1.weight": "pytorch_model-00005-of-00007.bin",
301
+ "transformer.h.30.ln_2.bias": "pytorch_model-00005-of-00007.bin",
302
+ "transformer.h.30.ln_2.weight": "pytorch_model-00005-of-00007.bin",
303
+ "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
304
+ "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
305
+ "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
306
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
307
+ "transformer.h.31.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
308
+ "transformer.h.31.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
309
+ "transformer.h.31.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
310
+ "transformer.h.31.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
311
+ "transformer.h.31.ln_1.bias": "pytorch_model-00005-of-00007.bin",
312
+ "transformer.h.31.ln_1.weight": "pytorch_model-00005-of-00007.bin",
313
+ "transformer.h.31.ln_2.bias": "pytorch_model-00005-of-00007.bin",
314
+ "transformer.h.31.ln_2.weight": "pytorch_model-00005-of-00007.bin",
315
+ "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
316
+ "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
317
+ "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
318
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
319
+ "transformer.h.32.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
320
+ "transformer.h.32.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
321
+ "transformer.h.32.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
322
+ "transformer.h.32.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
323
+ "transformer.h.32.ln_1.bias": "pytorch_model-00006-of-00007.bin",
324
+ "transformer.h.32.ln_1.weight": "pytorch_model-00006-of-00007.bin",
325
+ "transformer.h.32.ln_2.bias": "pytorch_model-00006-of-00007.bin",
326
+ "transformer.h.32.ln_2.weight": "pytorch_model-00006-of-00007.bin",
327
+ "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
328
+ "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
329
+ "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
330
+ "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
331
+ "transformer.h.33.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
332
+ "transformer.h.33.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
333
+ "transformer.h.33.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
334
+ "transformer.h.33.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
335
+ "transformer.h.33.ln_1.bias": "pytorch_model-00006-of-00007.bin",
336
+ "transformer.h.33.ln_1.weight": "pytorch_model-00006-of-00007.bin",
337
+ "transformer.h.33.ln_2.bias": "pytorch_model-00006-of-00007.bin",
338
+ "transformer.h.33.ln_2.weight": "pytorch_model-00006-of-00007.bin",
339
+ "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
340
+ "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
341
+ "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
342
+ "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
343
+ "transformer.h.34.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
344
+ "transformer.h.34.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
345
+ "transformer.h.34.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
346
+ "transformer.h.34.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
347
+ "transformer.h.34.ln_1.bias": "pytorch_model-00006-of-00007.bin",
348
+ "transformer.h.34.ln_1.weight": "pytorch_model-00006-of-00007.bin",
349
+ "transformer.h.34.ln_2.bias": "pytorch_model-00006-of-00007.bin",
350
+ "transformer.h.34.ln_2.weight": "pytorch_model-00006-of-00007.bin",
351
+ "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
352
+ "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
353
+ "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
354
+ "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
355
+ "transformer.h.35.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
356
+ "transformer.h.35.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
357
+ "transformer.h.35.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
358
+ "transformer.h.35.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
359
+ "transformer.h.35.ln_1.bias": "pytorch_model-00006-of-00007.bin",
360
+ "transformer.h.35.ln_1.weight": "pytorch_model-00006-of-00007.bin",
361
+ "transformer.h.35.ln_2.bias": "pytorch_model-00006-of-00007.bin",
362
+ "transformer.h.35.ln_2.weight": "pytorch_model-00006-of-00007.bin",
363
+ "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
364
+ "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
365
+ "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
366
+ "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
367
+ "transformer.h.36.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
368
+ "transformer.h.36.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
369
+ "transformer.h.36.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
370
+ "transformer.h.36.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
371
+ "transformer.h.36.ln_1.bias": "pytorch_model-00006-of-00007.bin",
372
+ "transformer.h.36.ln_1.weight": "pytorch_model-00006-of-00007.bin",
373
+ "transformer.h.36.ln_2.bias": "pytorch_model-00006-of-00007.bin",
374
+ "transformer.h.36.ln_2.weight": "pytorch_model-00006-of-00007.bin",
375
+ "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
376
+ "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
377
+ "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
378
+ "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
379
+ "transformer.h.37.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
380
+ "transformer.h.37.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
381
+ "transformer.h.37.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
382
+ "transformer.h.37.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
383
+ "transformer.h.37.ln_1.bias": "pytorch_model-00006-of-00007.bin",
384
+ "transformer.h.37.ln_1.weight": "pytorch_model-00006-of-00007.bin",
385
+ "transformer.h.37.ln_2.bias": "pytorch_model-00006-of-00007.bin",
386
+ "transformer.h.37.ln_2.weight": "pytorch_model-00006-of-00007.bin",
387
+ "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
388
+ "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
389
+ "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
390
+ "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
391
+ "transformer.h.38.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
392
+ "transformer.h.38.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
393
+ "transformer.h.38.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
394
+ "transformer.h.38.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
395
+ "transformer.h.38.ln_1.bias": "pytorch_model-00006-of-00007.bin",
396
+ "transformer.h.38.ln_1.weight": "pytorch_model-00006-of-00007.bin",
397
+ "transformer.h.38.ln_2.bias": "pytorch_model-00007-of-00007.bin",
398
+ "transformer.h.38.ln_2.weight": "pytorch_model-00007-of-00007.bin",
399
+ "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
400
+ "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
401
+ "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
402
+ "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
403
+ "transformer.h.39.attn.c_attn.bias": "pytorch_model-00007-of-00007.bin",
404
+ "transformer.h.39.attn.c_attn.weight": "pytorch_model-00007-of-00007.bin",
405
+ "transformer.h.39.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
406
+ "transformer.h.39.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
407
+ "transformer.h.39.ln_1.bias": "pytorch_model-00007-of-00007.bin",
408
+ "transformer.h.39.ln_1.weight": "pytorch_model-00007-of-00007.bin",
409
+ "transformer.h.39.ln_2.bias": "pytorch_model-00007-of-00007.bin",
410
+ "transformer.h.39.ln_2.weight": "pytorch_model-00007-of-00007.bin",
411
+ "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
412
+ "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
413
+ "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
414
+ "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
415
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
416
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
417
+ "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
418
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
419
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00007.bin",
420
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00007.bin",
421
+ "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00007.bin",
422
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00007.bin",
423
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
424
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
425
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
426
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
427
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
428
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
429
+ "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
430
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
431
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00007.bin",
432
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00007.bin",
433
+ "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00007.bin",
434
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00007.bin",
435
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
436
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
437
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
438
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
439
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
440
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
441
+ "transformer.h.6.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
442
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
443
+ "transformer.h.6.ln_1.bias": "pytorch_model-00002-of-00007.bin",
444
+ "transformer.h.6.ln_1.weight": "pytorch_model-00002-of-00007.bin",
445
+ "transformer.h.6.ln_2.bias": "pytorch_model-00002-of-00007.bin",
446
+ "transformer.h.6.ln_2.weight": "pytorch_model-00002-of-00007.bin",
447
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
448
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
449
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
450
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
451
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
452
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
453
+ "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
454
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
455
+ "transformer.h.7.ln_1.bias": "pytorch_model-00002-of-00007.bin",
456
+ "transformer.h.7.ln_1.weight": "pytorch_model-00002-of-00007.bin",
457
+ "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00007.bin",
458
+ "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00007.bin",
459
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
460
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
461
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
462
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
463
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
464
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
465
+ "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
466
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
467
+ "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00007.bin",
468
+ "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00007.bin",
469
+ "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00007.bin",
470
+ "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00007.bin",
471
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
472
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
473
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
474
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
475
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
476
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
477
+ "transformer.h.9.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
478
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
479
+ "transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00007.bin",
480
+ "transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00007.bin",
481
+ "transformer.h.9.ln_2.bias": "pytorch_model-00002-of-00007.bin",
482
+ "transformer.h.9.ln_2.weight": "pytorch_model-00002-of-00007.bin",
483
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
484
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
485
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
486
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
487
+ "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
488
+ "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
489
+ "transformer.wpe.weight": "pytorch_model-00001-of-00007.bin",
490
+ "transformer.wte.weight": "pytorch_model-00001-of-00007.bin"
491
+ }
492
+ }
runs/Apr20_12-05-59_ip-26-0-147-94/1681992793.492106/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e79a31260b5140a29d0a117821df6630eae9ad86656f8283d1aeee77ccf956
3
+ size 6456
runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6bcc4fd1cf14059ecd9e1f8b524c88d469825ef62195eefd897dc5e7496c02
3
+ size 5608
runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992826.ip-26-0-147-94.2699266.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa0cfc66b53d1cff94caefea60006c5829bd1f609c974f26dc6aa180a10b4c5
3
+ size 354
runs/Apr20_12-22-28_ip-26-0-147-94/1681993752.2594001/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d5d3dd1ef4e7859d1b200ac671a029c3ebbbb7fd91971aa0850ed44a92237a
3
+ size 6358
runs/Apr20_12-22-28_ip-26-0-147-94/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4802d93484b2208bbfaa76c5e7506001fe4a14e4bd7af580eeae36ca29ff5e5
3
+ size 4715
runs/Apr20_12-32-13_ip-26-0-147-94/1681994151.4570813/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3377f74e3acb9cf012313292279e08882854b461cac6eeaee1cb59b3c0c7f15
3
+ size 6358
runs/Apr20_12-32-13_ip-26-0-147-94/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591844efdc2d12e04caf120e563160528796d7da4db0e3ccd11e3bbe56d89278
3
+ size 4715
runs/Apr20_12-52-07_ip-26-0-147-94/1681995544.3466527/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8082840bb379e3933defeb1e9c3e91dfe3111ade4c429b7b619aea79d281227
3
+ size 6354
runs/Apr20_12-52-07_ip-26-0-147-94/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820c5ed3aa9e3bc995308bc744db6cb71db60f8239790fa72c434ce99c6e13de
3
+ size 4713
runs/Apr20_13-03-47_ip-26-0-147-94/1681996046.2437541/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7bec6c4a2079481ea7096cfc3fb3a3ceca3c0054ee8ab30c5141ab51bfce7c
3
+ size 6352
runs/Apr20_13-03-47_ip-26-0-147-94/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3a847f7bf2d978b80dbe47d1ae60665516ca01471e738e00b544f79254e2e3
3
+ size 4711
runs/Apr20_13-18-36_ip-26-0-147-94/1681997147.8418489/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1569d16ec7d87101f336e9bcd5e834732d0f494a8695ea69a98228e6e74f8b97
3
+ size 6352
runs/Apr20_13-18-36_ip-26-0-147-94/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f971c0f9165af692c177a3193067ba429b51a3d8d6e9279c00852b4211e1d8
3
+ size 4711
runs/Apr20_13-42-06_ip-26-0-147-94/1681998575.4662077/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08296923a32f7833f05ce093f31b14b21df72d0c7ee1e6e6bd032b2aa9d09eb2
3
+ size 6352
runs/Apr20_13-42-06_ip-26-0-147-94/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049cf66784da2de78a3b8f86f964133ebd6b8a8526daadf9151be5783707399a
3
+ size 4711
runs/Apr20_13-58-51_ip-26-0-147-94/1681999524.7086265/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878a08eeea43c6f00e0d91a2d5c76516f93daa120abbac938a78230c1157d559
3
+ size 6456
runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf4f4b4c85e7b03b0c202feac2d16d0a2f485bcedbaa404e81094af4ddc0514
3
+ size 5608
runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999553.ip-26-0-147-94.2739528.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17905abcc4a087ed3cbe8add63a9975dcf53b38255a555ad5391257a87ca88ac
3
+ size 354
runs/Apr20_14-08-16_ip-26-0-147-94/1681999901.4178648/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f2d28077a587885a23d4cc56f4d4453b4bd25f0556949744257301441299ed
3
+ size 6456
runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557304e2bda02bb2f5d27123939cb6a843bd8da1f939e5ad15787592f4847406
3
+ size 5579
runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999931.ip-26-0-147-94.2743104.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b80bf0d31f3752a137fea144911f7b2eceb381a23886b888c7afef4f7b292da
3
+ size 354
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": "<|endoftext|>",
24
+ "eos_token": "<|endoftext|>",
25
+ "unk_token": "<|endoftext|>"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "additional_special_tokens": [
4
+ "<|endoftext|>",
5
+ "<fim_prefix>",
6
+ "<fim_middle>",
7
+ "<fim_suffix>",
8
+ "<fim_pad>",
9
+ "<filename>",
10
+ "<gh_stars>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<empty_output>",
19
+ "<commit_before>",
20
+ "<commit_msg>",
21
+ "<commit_after>",
22
+ "<reponame>"
23
+ ],
24
+ "bos_token": "<|endoftext|>",
25
+ "clean_up_tokenization_spaces": true,
26
+ "eos_token": "<|endoftext|>",
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "<|endoftext|>",
30
+ "vocab_size": 49152
31
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "train_loss": 1.1672077178955078,
4
+ "train_runtime": 23.0652,
5
+ "train_samples": 2066,
6
+ "train_samples_per_second": 2.775,
7
+ "train_steps_per_second": 0.043
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.03088803088803089,
5
+ "global_step": 1,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 2e-05,
13
+ "loss": 1.1672,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "eval_loss": 1.1604644060134888,
19
+ "eval_runtime": 7.2577,
20
+ "eval_samples_per_second": 31.139,
21
+ "eval_steps_per_second": 3.996,
22
+ "step": 1
23
+ },
24
+ {
25
+ "epoch": 0.03,
26
+ "step": 1,
27
+ "total_flos": 745396137623552.0,
28
+ "train_loss": 1.1672077178955078,
29
+ "train_runtime": 23.0652,
30
+ "train_samples_per_second": 2.775,
31
+ "train_steps_per_second": 0.043
32
+ }
33
+ ],
34
+ "max_steps": 1,
35
+ "num_train_epochs": 1,
36
+ "total_flos": 745396137623552.0,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32bed3ec4485de46dd543b055f5efa565847b17ea6fc9e7e52c26ad0abbeefd4
3
+ size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff