File size: 4,581 Bytes
1fea908
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
{
 "fixture": "huggingface-mic/codegen2-16B_P-mic",
 "key": "3423601d143b9048dcf2c11dd8eba12db6bc5e3d503ac9f0306e2801c74e81e0",
 "key_fields": {
  "architectures": [
   "CodeGenForCausalLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
   "0": "LABEL_0",
   "1": "LABEL_1"
  },
  "label2id": {
   "LABEL_0": 0,
   "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 51200,
  "n_positions": 2048,
  "n_ctx": 2048,
  "n_embd": 64,
  "n_layer": 2,
  "n_head": 4,
  "rotary_dim": 4,
  "n_inner": null,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.0,
  "embd_pdrop": 0.0,
  "attn_pdrop": 0.0,
  "layer_norm_epsilon": 1e-05,
  "initializer_range": 0.02,
  "use_cache": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "tie_word_embeddings": false,
  "auto_map": {
   "AutoConfig": "configuration_codegen.CodeGenConfig",
   "AutoModel": "modeling_codegen.CodeGenModel",
   "AutoModelForCausalLM": "modeling_codegen.CodeGenForCausalLM"
  },
  "gradient_checkpointing": false,
  "model_type": "codegen",
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
   "text-generation": {
    "do_sample": true,
    "max_length": 50,
    "temperature": 1.0
   }
  },
  "tokenizer_class": "GPT2Tokenizer",
  "output_attentions": false
 },
 "covers": {
  "Salesforce/codegen2-16B_P": "14bcc89999feb32d9ee3c51388aa4d8ac134124d"
 },
 "built_from": {
  "repo": "Salesforce/codegen2-16B_P",
  "revision": "14bcc89999feb32d9ee3c51388aa4d8ac134124d"
 },
 "seed": 17,
 "dtype": "float32",
 "builder": "example/build_fixtures.py",
 "builder_revision": "ca3975c124db193f594adc9eda862d86115e9521",
 "recipe": {
  "seed": 17
 },
 "shrink": "rule",
 "model_class": "CodeGenForCausalLM",
 "parameters": 6704128,
 "missing_parameters": [],
 "serialization": {
  "file": "model.safetensors",
  "source_file": "pytorch_model.bin.index.json",
  "reverted_conversions": []
 },
 "checkpoint_inspection": "parameter headers/indexes; bounded binary fallback",
 "numeric_health_scope": "CPU float32/bfloat16/float16; autocast for low-precision losses",
 "captured": {
  "call": "training step",
  "inputs": [
   "attention_mask",
   "input_ids",
   "labels"
  ],
  "class": "CodeGenForCausalLM"
 },
 "weights": "random",
 "gate": {
  "random": {
   "pass": true,
   "accepted_insensitive": {},
   "threshold": 0.001,
   "deltas": {
    "input_ids:roll_batch": 1.0425515174865723,
    "input_ids:reverse": 1.1702327728271484,
    "attention_mask:all_ones": null
   },
   "weakest": "input_ids:roll_batch",
   "no_perturbation_defined": [],
   "not_a_forward_parameter": []
  }
 },
 "numeric_health": {
  "float32": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "bfloat16": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "float16": {
   "outputs_finite": true,
   "loss_finite": true,
   "unscaled_gradients_finite": true,
   "finite": true
  }
 },
 "copied_unchanged": [
  "added_tokens.json",
  "configuration_codegen.py",
  "merges.txt",
  "modeling_codegen.py",
  "special_tokens_map.json",
  "tokenizer.json",
  "tokenizer_config.json",
  "vocab.json"
 ],
 "environment": {
  "python": "3.11.18",
  "machine": "x86_64",
  "torch": "2.15.0+cpu",
  "transformers": "5.23.0.dev0",
  "tokenizers": "0.23.3"
 },
 "sha256": {
  "added_tokens.json": "b319b4f7c9d7c4d6e1088b9debc8d3c1d23cf3e12b16e1623d2d296a8a9c569b",
  "config.json": "ff9a4a534a1fd802f87cfa9c3d279fd537338e4df59a9bc6caf06a1756309700",
  "configuration_codegen.py": "0d768d7a46b0f831c52ab61311da733901c42a1a717d624d727fd5206b9aaf07",
  "generation_config.json": "5bb7b3dd5e8f3486049935b62cfed42967f1146f1a2ef747d8c75c2d09947c18",
  "merges.txt": "fe36cab26d4f4421ed725e10a2e9ddb7f799449c603a96e7f29b5a3c82a95862",
  "model.safetensors": "021f94aa14de58a0a36ebfc691016a170e96c01964980d15724ce39e1db6f7fb",
  "modeling_codegen.py": "d6e01345b18e5493ccd18d5b2c6fcdd4c75d28a1ba3f09c49a1a498de97e1052",
  "special_tokens_map.json": "6f50ab5a5a509a1c309d6171f339b196a900dc9c99ad0408ff23bb615fdae7ad",
  "tokenizer.json": "e7a5a447b967fe9dd87e3eb3a0bb44a0b7e56015ae04455a5f8d3aa922e54cd1",
  "tokenizer_config.json": "0f7123cb7e1be4e9c2e8770bd3c00f73d75364fb71680d0412d6263e7af2654c",
  "vocab.json": "3ba3c3109ff33976c4bd966589c11ee14fcaa1f4c9e5e154c2ed7f99d80709e7"
 }
}