axrafTic commited on
Commit
27eba2a
·
verified ·
1 Parent(s): 53b6f8e

Deploy QLoRA Approach B (Schema-Linking Text-to-SQL Qwen2.5-Coder-3B)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ language:
6
+ - fr
7
+ tags:
8
+ - text2sql
9
+ - text-to-sql
10
+ - lora
11
+ - qlora
12
+ - schema-linking
13
+ - qwen2.5-coder
14
+ - french
15
+ ---
16
+
17
+ # Text-to-SQL Prospect Model (Approach B: Schema-Linking)
18
+
19
+ Fine-tuned QLoRA adapter for **Qwen2.5-Coder-3B-Instruct** designed to generate SQL queries in French for the `companies` database schema.
20
+
21
+ ## Model Details
22
+ - **Base Model**: `Qwen/Qwen2.5-Coder-3B-Instruct` / `unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit`
23
+ - **Method**: QLoRA Fine-Tuning (`r=32`, `alpha=64`, target modules: all linear layers)
24
+ - **Task**: Text-to-SQL (French natural language questions -> SQLite / Postgres SQL queries)
25
+ - **Approach**: Schema-Linking with column annotations (`SCHEMA_B`)
26
+
27
+ ## Prompt Structure (ChatML)
28
+
29
+ ```text
30
+ <|im_start|>system
31
+ Tu es un analyste de données expert en SQL. Transforme la question de l'utilisateur en une requête SQL valide et exécutable. Ne génère que le code SQL, sans explication.<|im_end|>
32
+ <|im_start|>user
33
+ Base de données:
34
+ [SCHEMA]
35
+ Table: companies (Profils d'entreprises françaises)
36
+ Colonnes:
37
+ - id (UUID identifiant unique)
38
+ - name (Nom commercial de l'entreprise)
39
+ - rating (Note Google Maps de 0 à 5)
40
+ - reviews (Nombre total d'avis Google)
41
+ - is_spending_on_ads (1 si l'entreprise paie pour des annonces, 0 sinon)
42
+ - description (Description textuelle de l'activité)
43
+ - website (URL du site web, NULL si absent)
44
+ - address (Adresse postale complète)
45
+ - ville (ex: 'Paris', 'Lyon', 'Marseille')
46
+ - secteur (ex: 'Informatique', 'Finance', 'Santé')
47
+ - region (ex: 'Ile-de-France', 'Auvergne-Rhone-Alpes')
48
+ - codeAPE (Code NAF d'activité économique)
49
+ - siren (Identifiant unique entreprise à 9 chiffres)
50
+ - siret (Identifiant unique établissement à 14 chiffres)
51
+
52
+ Question: Lister les entreprises à Paris avec une note supérieure à 4.
53
+ SQL:<|im_end|>
54
+ <|im_start|>assistant
55
+ ```
56
+
57
+ ## How to Load in Python
58
+
59
+ ```python
60
+ import torch
61
+ from transformers import AutoTokenizer, AutoModelForCausalLM
62
+ from peft import PeftModel
63
+
64
+ base_model_id = "Qwen/Qwen2.5-Coder-3B-Instruct"
65
+ adapter_id = "axrafTic/text2sqlProspeciton"
66
+
67
+ tokenizer = AutoTokenizer.from_pretrained(adapter_id)
68
+ base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.float16, device_map="auto")
69
+ model = PeftModel.from_pretrained(base_model, adapter_id)
70
+ ```
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 32,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "down_proj",
38
+ "v_proj",
39
+ "k_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cead126e0899a24d04249ec488b177987eee31b3173df05f6f413144abffc05
3
+ size 239536272
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|PAD_TOKEN|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49c1b786ba7cd9c539085ebc8eb83025f6b16a7ce910a34b35957768c4b52a7
3
+ size 11422185
tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
207
+ "clean_up_tokenization_spaces": false,
208
+ "eos_token": "<|im_end|>",
209
+ "errors": "replace",
210
+ "model_max_length": 131072,
211
+ "pad_token": "<|PAD_TOKEN|>",
212
+ "padding_side": "right",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
+ "unk_token": null
216
+ }
trainer_state.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.041570067405700684,
3
+ "best_model_checkpoint": "./sql_lora_approach_b/checkpoint-34",
4
+ "epoch": 2.9565217391304346,
5
+ "eval_steps": 500,
6
+ "global_step": 34,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08695652173913043,
13
+ "grad_norm": 1.1549581289291382,
14
+ "learning_rate": 6.666666666666667e-05,
15
+ "loss": 1.7303,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.17391304347826086,
20
+ "grad_norm": 1.1289726495742798,
21
+ "learning_rate": 0.00013333333333333334,
22
+ "loss": 1.7252,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.2608695652173913,
27
+ "grad_norm": 0.934922993183136,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.597,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.34782608695652173,
34
+ "grad_norm": 0.8451507091522217,
35
+ "learning_rate": 0.00019981755542233177,
36
+ "loss": 1.3325,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.43478260869565216,
41
+ "grad_norm": 0.9650647640228271,
42
+ "learning_rate": 0.0001992708874098054,
43
+ "loss": 1.038,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.5217391304347826,
48
+ "grad_norm": 1.6881967782974243,
49
+ "learning_rate": 0.00019836199069471437,
50
+ "loss": 0.7972,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.6086956521739131,
55
+ "grad_norm": 0.9939894080162048,
56
+ "learning_rate": 0.0001970941817426052,
57
+ "loss": 0.5526,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.6956521739130435,
62
+ "grad_norm": 0.9496100544929504,
63
+ "learning_rate": 0.00019547208665085457,
64
+ "loss": 0.3339,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.782608695652174,
69
+ "grad_norm": 0.7385075688362122,
70
+ "learning_rate": 0.0001935016242685415,
71
+ "loss": 0.1994,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.8695652173913043,
76
+ "grad_norm": 0.5156198740005493,
77
+ "learning_rate": 0.00019118998459920902,
78
+ "loss": 0.0954,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.9565217391304348,
83
+ "grad_norm": 0.3693973124027252,
84
+ "learning_rate": 0.000188545602565321,
85
+ "loss": 0.06,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.9565217391304348,
90
+ "eval_loss": 0.06161738932132721,
91
+ "eval_runtime": 16.8375,
92
+ "eval_samples_per_second": 0.535,
93
+ "eval_steps_per_second": 0.535,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 1.0434782608695652,
98
+ "grad_norm": 0.3475421965122223,
99
+ "learning_rate": 0.00018557812723014476,
100
+ "loss": 0.0668,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 1.1304347826086956,
105
+ "grad_norm": 0.2272304743528366,
106
+ "learning_rate": 0.00018229838658936564,
107
+ "loss": 0.0472,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 1.2173913043478262,
112
+ "grad_norm": 0.18348968029022217,
113
+ "learning_rate": 0.00017871834806090501,
114
+ "loss": 0.0408,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 1.3043478260869565,
119
+ "grad_norm": 0.1996564120054245,
120
+ "learning_rate": 0.00017485107481711012,
121
+ "loss": 0.0533,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 1.391304347826087,
126
+ "grad_norm": 0.17511172592639923,
127
+ "learning_rate": 0.00017071067811865476,
128
+ "loss": 0.042,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 1.4782608695652173,
133
+ "grad_norm": 0.14677977561950684,
134
+ "learning_rate": 0.00016631226582407952,
135
+ "loss": 0.0318,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 1.5652173913043477,
140
+ "grad_norm": 0.19209422171115875,
141
+ "learning_rate": 0.00016167188726285434,
142
+ "loss": 0.0478,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 1.6521739130434783,
147
+ "grad_norm": 0.222362220287323,
148
+ "learning_rate": 0.00015680647467311557,
149
+ "loss": 0.0578,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 1.7391304347826086,
154
+ "grad_norm": 0.1985371708869934,
155
+ "learning_rate": 0.00015173378141776568,
156
+ "loss": 0.039,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 1.8260869565217392,
161
+ "grad_norm": 0.19283267855644226,
162
+ "learning_rate": 0.00014647231720437686,
163
+ "loss": 0.0338,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 1.9130434782608696,
168
+ "grad_norm": 0.18836742639541626,
169
+ "learning_rate": 0.0001410412805452757,
170
+ "loss": 0.0367,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 2.0,
175
+ "grad_norm": 0.22117920219898224,
176
+ "learning_rate": 0.00013546048870425356,
177
+ "loss": 0.0562,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 2.0,
182
+ "eval_loss": 0.042378202080726624,
183
+ "eval_runtime": 16.8523,
184
+ "eval_samples_per_second": 0.534,
185
+ "eval_steps_per_second": 0.534,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 2.0869565217391304,
190
+ "grad_norm": 0.08625093847513199,
191
+ "learning_rate": 0.00012975030538552032,
192
+ "loss": 0.0223,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 2.1739130434782608,
197
+ "grad_norm": 0.10370675474405289,
198
+ "learning_rate": 0.0001239315664287558,
199
+ "loss": 0.0292,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 2.260869565217391,
204
+ "grad_norm": 0.15547294914722443,
205
+ "learning_rate": 0.0001180255037813906,
206
+ "loss": 0.0403,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 2.3478260869565215,
211
+ "grad_norm": 0.1734398603439331,
212
+ "learning_rate": 0.0001120536680255323,
213
+ "loss": 0.0341,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 2.4347826086956523,
218
+ "grad_norm": 0.12611858546733856,
219
+ "learning_rate": 0.00010603784974222861,
220
+ "loss": 0.025,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.5217391304347827,
225
+ "grad_norm": 0.11490053683519363,
226
+ "learning_rate": 0.0001,
227
+ "loss": 0.0254,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.608695652173913,
232
+ "grad_norm": 0.11299990862607956,
233
+ "learning_rate": 9.396215025777139e-05,
234
+ "loss": 0.0287,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.6956521739130435,
239
+ "grad_norm": 0.09447255730628967,
240
+ "learning_rate": 8.79463319744677e-05,
241
+ "loss": 0.0226,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.782608695652174,
246
+ "grad_norm": 0.13230058550834656,
247
+ "learning_rate": 8.197449621860943e-05,
248
+ "loss": 0.0277,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.869565217391304,
253
+ "grad_norm": 0.13557763397693634,
254
+ "learning_rate": 7.606843357124426e-05,
255
+ "loss": 0.0325,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.9565217391304346,
260
+ "grad_norm": 0.10920581966638565,
261
+ "learning_rate": 7.024969461447972e-05,
262
+ "loss": 0.0219,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 2.9565217391304346,
267
+ "eval_loss": 0.041570067405700684,
268
+ "eval_runtime": 16.9013,
269
+ "eval_samples_per_second": 0.533,
270
+ "eval_steps_per_second": 0.533,
271
+ "step": 34
272
+ }
273
+ ],
274
+ "logging_steps": 1,
275
+ "max_steps": 55,
276
+ "num_input_tokens_seen": 0,
277
+ "num_train_epochs": 5,
278
+ "save_steps": 500,
279
+ "stateful_callbacks": {
280
+ "TrainerControl": {
281
+ "args": {
282
+ "should_epoch_stop": false,
283
+ "should_evaluate": false,
284
+ "should_log": false,
285
+ "should_save": true,
286
+ "should_training_stop": false
287
+ },
288
+ "attributes": {}
289
+ }
290
+ },
291
+ "total_flos": 1208798594408448.0,
292
+ "train_batch_size": 1,
293
+ "trial_name": null,
294
+ "trial_params": null
295
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff