Hugging Face's logo

sunnypsmith
/
berean-pygmalion-6b-v6-AUG8

Text Generation
Transformers
PyTorch
gptj
Inference Endpoints
Model card Files Community
sunnypsmith commited on
Commit
17ad9f4
•
1 Parent(s): 7217287

Update from Suny

Browse files
Files changed (16) hide show
  1. added_tokens.json +145 -0
  2. all_results.json +14 -0
  3. config.json +40 -0
  4. eval_results.json +9 -0
  5. generation_config.json +7 -0
  6. merges.txt +0 -0
  7. pytorch_model-00001-of-00003.bin +3 -0
  8. pytorch_model-00002-of-00003.bin +3 -0
  9. pytorch_model-00003-of-00003.bin +3 -0
  10. pytorch_model.bin.index.json +292 -0
  11. special_tokens_map.json +24 -0
  12. tokenizer_config.json +33 -0
  13. train_results.json +8 -0
  14. trainer_state.json +445 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|extratoken_100|>": 50356,
3
+ "<|extratoken_101|>": 50357,
4
+ "<|extratoken_102|>": 50358,
5
+ "<|extratoken_103|>": 50359,
6
+ "<|extratoken_104|>": 50360,
7
+ "<|extratoken_105|>": 50361,
8
+ "<|extratoken_106|>": 50362,
9
+ "<|extratoken_107|>": 50363,
10
+ "<|extratoken_108|>": 50364,
11
+ "<|extratoken_109|>": 50365,
12
+ "<|extratoken_10|>": 50266,
13
+ "<|extratoken_110|>": 50366,
14
+ "<|extratoken_111|>": 50367,
15
+ "<|extratoken_112|>": 50368,
16
+ "<|extratoken_113|>": 50369,
17
+ "<|extratoken_114|>": 50370,
18
+ "<|extratoken_115|>": 50371,
19
+ "<|extratoken_116|>": 50372,
20
+ "<|extratoken_117|>": 50373,
21
+ "<|extratoken_118|>": 50374,
22
+ "<|extratoken_119|>": 50375,
23
+ "<|extratoken_11|>": 50267,
24
+ "<|extratoken_120|>": 50376,
25
+ "<|extratoken_121|>": 50377,
26
+ "<|extratoken_122|>": 50378,
27
+ "<|extratoken_123|>": 50379,
28
+ "<|extratoken_124|>": 50380,
29
+ "<|extratoken_125|>": 50381,
30
+ "<|extratoken_126|>": 50382,
31
+ "<|extratoken_127|>": 50383,
32
+ "<|extratoken_128|>": 50384,
33
+ "<|extratoken_129|>": 50385,
34
+ "<|extratoken_12|>": 50268,
35
+ "<|extratoken_130|>": 50386,
36
+ "<|extratoken_131|>": 50387,
37
+ "<|extratoken_132|>": 50388,
38
+ "<|extratoken_133|>": 50389,
39
+ "<|extratoken_134|>": 50390,
40
+ "<|extratoken_135|>": 50391,
41
+ "<|extratoken_136|>": 50392,
42
+ "<|extratoken_137|>": 50393,
43
+ "<|extratoken_138|>": 50394,
44
+ "<|extratoken_139|>": 50395,
45
+ "<|extratoken_13|>": 50269,
46
+ "<|extratoken_140|>": 50396,
47
+ "<|extratoken_141|>": 50397,
48
+ "<|extratoken_142|>": 50398,
49
+ "<|extratoken_143|>": 50399,
50
+ "<|extratoken_14|>": 50270,
51
+ "<|extratoken_15|>": 50271,
52
+ "<|extratoken_16|>": 50272,
53
+ "<|extratoken_17|>": 50273,
54
+ "<|extratoken_18|>": 50274,
55
+ "<|extratoken_19|>": 50275,
56
+ "<|extratoken_1|>": 50257,
57
+ "<|extratoken_20|>": 50276,
58
+ "<|extratoken_21|>": 50277,
59
+ "<|extratoken_22|>": 50278,
60
+ "<|extratoken_23|>": 50279,
61
+ "<|extratoken_24|>": 50280,
62
+ "<|extratoken_25|>": 50281,
63
+ "<|extratoken_26|>": 50282,
64
+ "<|extratoken_27|>": 50283,
65
+ "<|extratoken_28|>": 50284,
66
+ "<|extratoken_29|>": 50285,
67
+ "<|extratoken_2|>": 50258,
68
+ "<|extratoken_30|>": 50286,
69
+ "<|extratoken_31|>": 50287,
70
+ "<|extratoken_32|>": 50288,
71
+ "<|extratoken_33|>": 50289,
72
+ "<|extratoken_34|>": 50290,
73
+ "<|extratoken_35|>": 50291,
74
+ "<|extratoken_36|>": 50292,
75
+ "<|extratoken_37|>": 50293,
76
+ "<|extratoken_38|>": 50294,
77
+ "<|extratoken_39|>": 50295,
78
+ "<|extratoken_3|>": 50259,
79
+ "<|extratoken_40|>": 50296,
80
+ "<|extratoken_41|>": 50297,
81
+ "<|extratoken_42|>": 50298,
82
+ "<|extratoken_43|>": 50299,
83
+ "<|extratoken_44|>": 50300,
84
+ "<|extratoken_45|>": 50301,
85
+ "<|extratoken_46|>": 50302,
86
+ "<|extratoken_47|>": 50303,
87
+ "<|extratoken_48|>": 50304,
88
+ "<|extratoken_49|>": 50305,
89
+ "<|extratoken_4|>": 50260,
90
+ "<|extratoken_50|>": 50306,
91
+ "<|extratoken_51|>": 50307,
92
+ "<|extratoken_52|>": 50308,
93
+ "<|extratoken_53|>": 50309,
94
+ "<|extratoken_54|>": 50310,
95
+ "<|extratoken_55|>": 50311,
96
+ "<|extratoken_56|>": 50312,
97
+ "<|extratoken_57|>": 50313,
98
+ "<|extratoken_58|>": 50314,
99
+ "<|extratoken_59|>": 50315,
100
+ "<|extratoken_5|>": 50261,
101
+ "<|extratoken_60|>": 50316,
102
+ "<|extratoken_61|>": 50317,
103
+ "<|extratoken_62|>": 50318,
104
+ "<|extratoken_63|>": 50319,
105
+ "<|extratoken_64|>": 50320,
106
+ "<|extratoken_65|>": 50321,
107
+ "<|extratoken_66|>": 50322,
108
+ "<|extratoken_67|>": 50323,
109
+ "<|extratoken_68|>": 50324,
110
+ "<|extratoken_69|>": 50325,
111
+ "<|extratoken_6|>": 50262,
112
+ "<|extratoken_70|>": 50326,
113
+ "<|extratoken_71|>": 50327,
114
+ "<|extratoken_72|>": 50328,
115
+ "<|extratoken_73|>": 50329,
116
+ "<|extratoken_74|>": 50330,
117
+ "<|extratoken_75|>": 50331,
118
+ "<|extratoken_76|>": 50332,
119
+ "<|extratoken_77|>": 50333,
120
+ "<|extratoken_78|>": 50334,
121
+ "<|extratoken_79|>": 50335,
122
+ "<|extratoken_7|>": 50263,
123
+ "<|extratoken_80|>": 50336,
124
+ "<|extratoken_81|>": 50337,
125
+ "<|extratoken_82|>": 50338,
126
+ "<|extratoken_83|>": 50339,
127
+ "<|extratoken_84|>": 50340,
128
+ "<|extratoken_85|>": 50341,
129
+ "<|extratoken_86|>": 50342,
130
+ "<|extratoken_87|>": 50343,
131
+ "<|extratoken_88|>": 50344,
132
+ "<|extratoken_89|>": 50345,
133
+ "<|extratoken_8|>": 50264,
134
+ "<|extratoken_90|>": 50346,
135
+ "<|extratoken_91|>": 50347,
136
+ "<|extratoken_92|>": 50348,
137
+ "<|extratoken_93|>": 50349,
138
+ "<|extratoken_94|>": 50350,
139
+ "<|extratoken_95|>": 50351,
140
+ "<|extratoken_96|>": 50352,
141
+ "<|extratoken_97|>": 50353,
142
+ "<|extratoken_98|>": 50354,
143
+ "<|extratoken_99|>": 50355,
144
+ "<|extratoken_9|>": 50265
145
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 2.1879360675811768,
4
+ "eval_runtime": 1198.0556,
5
+ "eval_samples": 12571,
6
+ "eval_samples_per_second": 10.493,
7
+ "eval_steps_per_second": 0.164,
8
+ "perplexity": 8.916790456782447,
9
+ "train_loss": 2.0404130036088044,
10
+ "train_runtime": 190042.9753,
11
+ "train_samples": 54906,
12
+ "train_samples_per_second": 0.867,
13
+ "train_steps_per_second": 0.007
14
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PygmalionAI/pygmalion-6b",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gptj",
14
+ "n_embd": 4096,
15
+ "n_head": 16,
16
+ "n_inner": null,
17
+ "n_layer": 28,
18
+ "n_positions": 2048,
19
+ "resid_pdrop": 0.0,
20
+ "rotary_dim": 64,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50,
31
+ "temperature": 1.0
32
+ }
33
+ },
34
+ "tie_word_embeddings": false,
35
+ "tokenizer_class": "GPT2Tokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.31.0",
38
+ "use_cache": false,
39
+ "vocab_size": 50400
40
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 2.1879360675811768,
4
+ "eval_runtime": 1198.0556,
5
+ "eval_samples": 12571,
6
+ "eval_samples_per_second": 10.493,
7
+ "eval_steps_per_second": 0.164,
8
+ "perplexity": 8.916790456782447
9
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.31.0",
6
+ "use_cache": false
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15264a1ca3c53339fadf1d190efedfc262936f1b06d037c3580eab4edb62ee76
3
+ size 9953892678
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1aebdf1b0bd40101e3d35f24971652d29f87fbe1a98991bd4a303a6f20c241
3
+ size 9933594769
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb77948b589524f2715f82d1704c72af89f031021d5519ab9efb1cc85b482299
3
+ size 4316139051
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24203531136
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00003-of-00003.bin",
7
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
8
+ "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
9
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
27
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
28
+ "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
33
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
34
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
35
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
36
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
37
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
38
+ "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
40
+ "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
43
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
44
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
45
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
46
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
47
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
48
+ "transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
49
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
83
+ "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
84
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
104
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
105
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
106
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
107
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
108
+ "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
113
+ "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
114
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
115
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
116
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
117
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
118
+ "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
119
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
123
+ "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
124
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
125
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
126
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
127
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
128
+ "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
129
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
133
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
134
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
135
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
136
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
137
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
138
+ "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
139
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
143
+ "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
144
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
145
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
146
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
147
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
148
+ "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
153
+ "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
154
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
155
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
156
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
157
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
158
+ "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
163
+ "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
164
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
165
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
166
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
167
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
168
+ "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
173
+ "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
174
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
175
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
176
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
177
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
178
+ "transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
179
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
180
+ "transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
183
+ "transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
184
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
185
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
186
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
187
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
188
+ "transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
189
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
193
+ "transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
194
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
195
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
196
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
197
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
198
+ "transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
199
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
203
+ "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
204
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
205
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
206
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
207
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
208
+ "transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
209
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
211
+ "transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
213
+ "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
214
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
215
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
216
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
217
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
218
+ "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
220
+ "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
223
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
224
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
225
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
226
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
227
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
228
+ "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
229
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
230
+ "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
231
+ "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
232
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
233
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
234
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
235
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
236
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
237
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
238
+ "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
239
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
243
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
244
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
245
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
246
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
247
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
248
+ "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
249
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
250
+ "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
251
+ "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
252
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
253
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
254
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
255
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
256
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
257
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
258
+ "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
259
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
261
+ "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
263
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
264
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
265
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
266
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
267
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
268
+ "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
269
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
270
+ "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
273
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
274
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
275
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
276
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
277
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
278
+ "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
279
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
283
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
284
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
285
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
286
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
287
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
288
+ "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
289
+ "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
290
+ "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
291
+ }
292
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.0404130036088044,
4
+ "train_runtime": 190042.9753,
5
+ "train_samples": 54906,
6
+ "train_samples_per_second": 0.867,
7
+ "train_steps_per_second": 0.007
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,445 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 1287,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "eval_loss": 2.3746426105499268,
13
+ "eval_runtime": 1198.5011,
14
+ "eval_samples_per_second": 10.489,
15
+ "eval_steps_per_second": 0.164,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.12,
20
+ "eval_loss": 2.335777521133423,
21
+ "eval_runtime": 1198.5148,
22
+ "eval_samples_per_second": 10.489,
23
+ "eval_steps_per_second": 0.164,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.17,
28
+ "eval_loss": 2.3206024169921875,
29
+ "eval_runtime": 1198.298,
30
+ "eval_samples_per_second": 10.491,
31
+ "eval_steps_per_second": 0.164,
32
+ "step": 75
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "eval_loss": 2.3067309856414795,
37
+ "eval_runtime": 1198.4272,
38
+ "eval_samples_per_second": 10.49,
39
+ "eval_steps_per_second": 0.164,
40
+ "step": 100
41
+ },
42
+ {
43
+ "epoch": 0.29,
44
+ "eval_loss": 2.295646905899048,
45
+ "eval_runtime": 1198.0238,
46
+ "eval_samples_per_second": 10.493,
47
+ "eval_steps_per_second": 0.164,
48
+ "step": 125
49
+ },
50
+ {
51
+ "epoch": 0.35,
52
+ "eval_loss": 2.288886308670044,
53
+ "eval_runtime": 1198.6077,
54
+ "eval_samples_per_second": 10.488,
55
+ "eval_steps_per_second": 0.164,
56
+ "step": 150
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "eval_loss": 2.2820334434509277,
61
+ "eval_runtime": 1197.653,
62
+ "eval_samples_per_second": 10.496,
63
+ "eval_steps_per_second": 0.164,
64
+ "step": 175
65
+ },
66
+ {
67
+ "epoch": 0.47,
68
+ "eval_loss": 2.275322675704956,
69
+ "eval_runtime": 1197.9481,
70
+ "eval_samples_per_second": 10.494,
71
+ "eval_steps_per_second": 0.164,
72
+ "step": 200
73
+ },
74
+ {
75
+ "epoch": 0.52,
76
+ "eval_loss": 2.269848108291626,
77
+ "eval_runtime": 1197.9985,
78
+ "eval_samples_per_second": 10.493,
79
+ "eval_steps_per_second": 0.164,
80
+ "step": 225
81
+ },
82
+ {
83
+ "epoch": 0.58,
84
+ "eval_loss": 2.266172170639038,
85
+ "eval_runtime": 1198.9744,
86
+ "eval_samples_per_second": 10.485,
87
+ "eval_steps_per_second": 0.164,
88
+ "step": 250
89
+ },
90
+ {
91
+ "epoch": 0.64,
92
+ "eval_loss": 2.2608513832092285,
93
+ "eval_runtime": 1198.2986,
94
+ "eval_samples_per_second": 10.491,
95
+ "eval_steps_per_second": 0.164,
96
+ "step": 275
97
+ },
98
+ {
99
+ "epoch": 0.7,
100
+ "eval_loss": 2.256772756576538,
101
+ "eval_runtime": 1198.6541,
102
+ "eval_samples_per_second": 10.488,
103
+ "eval_steps_per_second": 0.164,
104
+ "step": 300
105
+ },
106
+ {
107
+ "epoch": 0.76,
108
+ "eval_loss": 2.2526705265045166,
109
+ "eval_runtime": 1198.4379,
110
+ "eval_samples_per_second": 10.489,
111
+ "eval_steps_per_second": 0.164,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 0.82,
116
+ "eval_loss": 2.2487242221832275,
117
+ "eval_runtime": 1198.434,
118
+ "eval_samples_per_second": 10.49,
119
+ "eval_steps_per_second": 0.164,
120
+ "step": 350
121
+ },
122
+ {
123
+ "epoch": 0.87,
124
+ "eval_loss": 2.2462055683135986,
125
+ "eval_runtime": 1198.2638,
126
+ "eval_samples_per_second": 10.491,
127
+ "eval_steps_per_second": 0.164,
128
+ "step": 375
129
+ },
130
+ {
131
+ "epoch": 0.93,
132
+ "eval_loss": 2.2430307865142822,
133
+ "eval_runtime": 1198.979,
134
+ "eval_samples_per_second": 10.485,
135
+ "eval_steps_per_second": 0.164,
136
+ "step": 400
137
+ },
138
+ {
139
+ "epoch": 0.99,
140
+ "eval_loss": 2.240046501159668,
141
+ "eval_runtime": 1198.9558,
142
+ "eval_samples_per_second": 10.485,
143
+ "eval_steps_per_second": 0.164,
144
+ "step": 425
145
+ },
146
+ {
147
+ "epoch": 1.05,
148
+ "eval_loss": 2.239072799682617,
149
+ "eval_runtime": 1199.2167,
150
+ "eval_samples_per_second": 10.483,
151
+ "eval_steps_per_second": 0.164,
152
+ "step": 450
153
+ },
154
+ {
155
+ "epoch": 1.11,
156
+ "eval_loss": 2.235506296157837,
157
+ "eval_runtime": 1199.5308,
158
+ "eval_samples_per_second": 10.48,
159
+ "eval_steps_per_second": 0.164,
160
+ "step": 475
161
+ },
162
+ {
163
+ "epoch": 1.17,
164
+ "learning_rate": 5e-06,
165
+ "loss": 2.1094,
166
+ "step": 500
167
+ },
168
+ {
169
+ "epoch": 1.17,
170
+ "eval_loss": 2.233208656311035,
171
+ "eval_runtime": 1198.8451,
172
+ "eval_samples_per_second": 10.486,
173
+ "eval_steps_per_second": 0.164,
174
+ "step": 500
175
+ },
176
+ {
177
+ "epoch": 1.22,
178
+ "eval_loss": 2.2311644554138184,
179
+ "eval_runtime": 1198.7414,
180
+ "eval_samples_per_second": 10.487,
181
+ "eval_steps_per_second": 0.164,
182
+ "step": 525
183
+ },
184
+ {
185
+ "epoch": 1.28,
186
+ "eval_loss": 2.2293059825897217,
187
+ "eval_runtime": 1198.5095,
188
+ "eval_samples_per_second": 10.489,
189
+ "eval_steps_per_second": 0.164,
190
+ "step": 550
191
+ },
192
+ {
193
+ "epoch": 1.34,
194
+ "eval_loss": 2.226186990737915,
195
+ "eval_runtime": 1198.3579,
196
+ "eval_samples_per_second": 10.49,
197
+ "eval_steps_per_second": 0.164,
198
+ "step": 575
199
+ },
200
+ {
201
+ "epoch": 1.4,
202
+ "eval_loss": 2.224607467651367,
203
+ "eval_runtime": 1198.8254,
204
+ "eval_samples_per_second": 10.486,
205
+ "eval_steps_per_second": 0.164,
206
+ "step": 600
207
+ },
208
+ {
209
+ "epoch": 1.46,
210
+ "eval_loss": 2.222740888595581,
211
+ "eval_runtime": 1198.8308,
212
+ "eval_samples_per_second": 10.486,
213
+ "eval_steps_per_second": 0.164,
214
+ "step": 625
215
+ },
216
+ {
217
+ "epoch": 1.52,
218
+ "eval_loss": 2.2205824851989746,
219
+ "eval_runtime": 1197.986,
220
+ "eval_samples_per_second": 10.493,
221
+ "eval_steps_per_second": 0.164,
222
+ "step": 650
223
+ },
224
+ {
225
+ "epoch": 1.57,
226
+ "eval_loss": 2.2183074951171875,
227
+ "eval_runtime": 1198.7617,
228
+ "eval_samples_per_second": 10.487,
229
+ "eval_steps_per_second": 0.164,
230
+ "step": 675
231
+ },
232
+ {
233
+ "epoch": 1.63,
234
+ "eval_loss": 2.216313123703003,
235
+ "eval_runtime": 1197.8492,
236
+ "eval_samples_per_second": 10.495,
237
+ "eval_steps_per_second": 0.164,
238
+ "step": 700
239
+ },
240
+ {
241
+ "epoch": 1.69,
242
+ "eval_loss": 2.214667320251465,
243
+ "eval_runtime": 1198.1314,
244
+ "eval_samples_per_second": 10.492,
245
+ "eval_steps_per_second": 0.164,
246
+ "step": 725
247
+ },
248
+ {
249
+ "epoch": 1.75,
250
+ "eval_loss": 2.2129483222961426,
251
+ "eval_runtime": 1198.8701,
252
+ "eval_samples_per_second": 10.486,
253
+ "eval_steps_per_second": 0.164,
254
+ "step": 750
255
+ },
256
+ {
257
+ "epoch": 1.81,
258
+ "eval_loss": 2.2119433879852295,
259
+ "eval_runtime": 1198.3317,
260
+ "eval_samples_per_second": 10.49,
261
+ "eval_steps_per_second": 0.164,
262
+ "step": 775
263
+ },
264
+ {
265
+ "epoch": 1.86,
266
+ "eval_loss": 2.210693836212158,
267
+ "eval_runtime": 1198.0145,
268
+ "eval_samples_per_second": 10.493,
269
+ "eval_steps_per_second": 0.164,
270
+ "step": 800
271
+ },
272
+ {
273
+ "epoch": 1.92,
274
+ "eval_loss": 2.209263801574707,
275
+ "eval_runtime": 1198.6585,
276
+ "eval_samples_per_second": 10.488,
277
+ "eval_steps_per_second": 0.164,
278
+ "step": 825
279
+ },
280
+ {
281
+ "epoch": 1.98,
282
+ "eval_loss": 2.20792293548584,
283
+ "eval_runtime": 1198.1192,
284
+ "eval_samples_per_second": 10.492,
285
+ "eval_steps_per_second": 0.164,
286
+ "step": 850
287
+ },
288
+ {
289
+ "epoch": 2.04,
290
+ "eval_loss": 2.2082931995391846,
291
+ "eval_runtime": 1197.8097,
292
+ "eval_samples_per_second": 10.495,
293
+ "eval_steps_per_second": 0.164,
294
+ "step": 875
295
+ },
296
+ {
297
+ "epoch": 2.1,
298
+ "eval_loss": 2.205972194671631,
299
+ "eval_runtime": 1198.0467,
300
+ "eval_samples_per_second": 10.493,
301
+ "eval_steps_per_second": 0.164,
302
+ "step": 900
303
+ },
304
+ {
305
+ "epoch": 2.16,
306
+ "eval_loss": 2.2038400173187256,
307
+ "eval_runtime": 1197.5865,
308
+ "eval_samples_per_second": 10.497,
309
+ "eval_steps_per_second": 0.164,
310
+ "step": 925
311
+ },
312
+ {
313
+ "epoch": 2.21,
314
+ "eval_loss": 2.2014477252960205,
315
+ "eval_runtime": 1198.4564,
316
+ "eval_samples_per_second": 10.489,
317
+ "eval_steps_per_second": 0.164,
318
+ "step": 950
319
+ },
320
+ {
321
+ "epoch": 2.27,
322
+ "eval_loss": 2.202155113220215,
323
+ "eval_runtime": 1198.0855,
324
+ "eval_samples_per_second": 10.493,
325
+ "eval_steps_per_second": 0.164,
326
+ "step": 975
327
+ },
328
+ {
329
+ "epoch": 2.33,
330
+ "learning_rate": 5e-06,
331
+ "loss": 2.007,
332
+ "step": 1000
333
+ },
334
+ {
335
+ "epoch": 2.33,
336
+ "eval_loss": 2.2006430625915527,
337
+ "eval_runtime": 1198.775,
338
+ "eval_samples_per_second": 10.487,
339
+ "eval_steps_per_second": 0.164,
340
+ "step": 1000
341
+ },
342
+ {
343
+ "epoch": 2.39,
344
+ "eval_loss": 2.1995391845703125,
345
+ "eval_runtime": 1198.5076,
346
+ "eval_samples_per_second": 10.489,
347
+ "eval_steps_per_second": 0.164,
348
+ "step": 1025
349
+ },
350
+ {
351
+ "epoch": 2.45,
352
+ "eval_loss": 2.199397087097168,
353
+ "eval_runtime": 1198.3593,
354
+ "eval_samples_per_second": 10.49,
355
+ "eval_steps_per_second": 0.164,
356
+ "step": 1050
357
+ },
358
+ {
359
+ "epoch": 2.51,
360
+ "eval_loss": 2.19655179977417,
361
+ "eval_runtime": 1198.8863,
362
+ "eval_samples_per_second": 10.486,
363
+ "eval_steps_per_second": 0.164,
364
+ "step": 1075
365
+ },
366
+ {
367
+ "epoch": 2.56,
368
+ "eval_loss": 2.196131467819214,
369
+ "eval_runtime": 1198.1451,
370
+ "eval_samples_per_second": 10.492,
371
+ "eval_steps_per_second": 0.164,
372
+ "step": 1100
373
+ },
374
+ {
375
+ "epoch": 2.62,
376
+ "eval_loss": 2.195343255996704,
377
+ "eval_runtime": 1198.7177,
378
+ "eval_samples_per_second": 10.487,
379
+ "eval_steps_per_second": 0.164,
380
+ "step": 1125
381
+ },
382
+ {
383
+ "epoch": 2.68,
384
+ "eval_loss": 2.194007158279419,
385
+ "eval_runtime": 1199.5879,
386
+ "eval_samples_per_second": 10.479,
387
+ "eval_steps_per_second": 0.164,
388
+ "step": 1150
389
+ },
390
+ {
391
+ "epoch": 2.74,
392
+ "eval_loss": 2.192256212234497,
393
+ "eval_runtime": 1198.4679,
394
+ "eval_samples_per_second": 10.489,
395
+ "eval_steps_per_second": 0.164,
396
+ "step": 1175
397
+ },
398
+ {
399
+ "epoch": 2.8,
400
+ "eval_loss": 2.1922357082366943,
401
+ "eval_runtime": 1198.561,
402
+ "eval_samples_per_second": 10.488,
403
+ "eval_steps_per_second": 0.164,
404
+ "step": 1200
405
+ },
406
+ {
407
+ "epoch": 2.86,
408
+ "eval_loss": 2.190948724746704,
409
+ "eval_runtime": 1198.5536,
410
+ "eval_samples_per_second": 10.488,
411
+ "eval_steps_per_second": 0.164,
412
+ "step": 1225
413
+ },
414
+ {
415
+ "epoch": 2.91,
416
+ "eval_loss": 2.188807487487793,
417
+ "eval_runtime": 1199.0987,
418
+ "eval_samples_per_second": 10.484,
419
+ "eval_steps_per_second": 0.164,
420
+ "step": 1250
421
+ },
422
+ {
423
+ "epoch": 2.97,
424
+ "eval_loss": 2.1877503395080566,
425
+ "eval_runtime": 1199.1927,
426
+ "eval_samples_per_second": 10.483,
427
+ "eval_steps_per_second": 0.164,
428
+ "step": 1275
429
+ },
430
+ {
431
+ "epoch": 3.0,
432
+ "step": 1287,
433
+ "total_flos": 5.915384239745925e+18,
434
+ "train_loss": 2.0404130036088044,
435
+ "train_runtime": 190042.9753,
436
+ "train_samples_per_second": 0.867,
437
+ "train_steps_per_second": 0.007
438
+ }
439
+ ],
440
+ "max_steps": 1287,
441
+ "num_train_epochs": 3,
442
+ "total_flos": 5.915384239745925e+18,
443
+ "trial_name": null,
444
+ "trial_params": null
445
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e903b900047586f4b1b014b6becc2c0082ecf3e51fe48e6be0a5dc775f483ecd
3
+ size 5435
vocab.json ADDED
The diff for this file is too large to render. See raw diff