arhamm40182 commited on
Commit
5250808
1 Parent(s): 7fd6978

Upload 14 files

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: microsoft/phi-2
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "Wqkv",
24
+ "fc2",
25
+ "fc1"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_dora": false,
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1350ab271c68977f15494c37ab5a6863fe7e7cd1a495f02f3c81132eea0cd6
3
+ size 104873776
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdeffab6e4359da77fd5b4860c6c365c6752656b065a2df56b0a8f9896d160ef
3
+ size 209793210
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a902e380560ad6047237cf9cb9aa3d14c42c278517d6349f5f65bc2a1d15a331
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d85fd0dcc980904bdfd3763281a80094639a2b2b63af9676380dd57c838a883
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "return_token_type_ids": false,
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
trainer_state.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.18562874251497,
5
+ "eval_steps": 500,
6
+ "global_step": 600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11976047904191617,
13
+ "grad_norm": 2.8749659061431885,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.4673,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.23952095808383234,
20
+ "grad_norm": 3.4398715496063232,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.0019,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.3592814371257485,
27
+ "grad_norm": 1.9059951305389404,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.0575,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.47904191616766467,
34
+ "grad_norm": 4.149394989013672,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.8164,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.5988023952095808,
41
+ "grad_norm": 1.4866076707839966,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.8684,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.718562874251497,
48
+ "grad_norm": 3.1927452087402344,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.8016,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.8383233532934131,
55
+ "grad_norm": 1.1162314414978027,
56
+ "learning_rate": 0.0002,
57
+ "loss": 0.6809,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.9580838323353293,
62
+ "grad_norm": 2.829102039337158,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.6962,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.0778443113772456,
69
+ "grad_norm": 1.2642532587051392,
70
+ "learning_rate": 0.0002,
71
+ "loss": 0.5769,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.1976047904191618,
76
+ "grad_norm": 1.3799452781677246,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.4128,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.3173652694610778,
83
+ "grad_norm": 2.3143367767333984,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.6441,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.437125748502994,
90
+ "grad_norm": 1.085919976234436,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.393,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.55688622754491,
97
+ "grad_norm": 1.2423957586288452,
98
+ "learning_rate": 0.0002,
99
+ "loss": 0.5582,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.6766467065868262,
104
+ "grad_norm": 1.2964059114456177,
105
+ "learning_rate": 0.0002,
106
+ "loss": 0.4276,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.7964071856287425,
111
+ "grad_norm": 1.8397400379180908,
112
+ "learning_rate": 0.0002,
113
+ "loss": 0.6162,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.9161676646706587,
118
+ "grad_norm": 1.0209627151489258,
119
+ "learning_rate": 0.0002,
120
+ "loss": 0.4565,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.035928143712575,
125
+ "grad_norm": 0.8725757598876953,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.4807,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.155688622754491,
132
+ "grad_norm": 1.1269447803497314,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.3895,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.2754491017964074,
139
+ "grad_norm": 1.528011679649353,
140
+ "learning_rate": 0.0002,
141
+ "loss": 0.3553,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.3952095808383236,
146
+ "grad_norm": 0.8296527862548828,
147
+ "learning_rate": 0.0002,
148
+ "loss": 0.3516,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.5149700598802394,
153
+ "grad_norm": 1.301917552947998,
154
+ "learning_rate": 0.0002,
155
+ "loss": 0.3918,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.6347305389221556,
160
+ "grad_norm": 0.8420801758766174,
161
+ "learning_rate": 0.0002,
162
+ "loss": 0.3497,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.754491017964072,
167
+ "grad_norm": 1.1430580615997314,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.4311,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 2.874251497005988,
174
+ "grad_norm": 0.9065356850624084,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.3551,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 2.9940119760479043,
181
+ "grad_norm": 1.1302285194396973,
182
+ "learning_rate": 0.0002,
183
+ "loss": 0.3513,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.1137724550898205,
188
+ "grad_norm": 0.9960314631462097,
189
+ "learning_rate": 0.0002,
190
+ "loss": 0.3124,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.2335329341317367,
195
+ "grad_norm": 1.680296778678894,
196
+ "learning_rate": 0.0002,
197
+ "loss": 0.3065,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 3.3532934131736525,
202
+ "grad_norm": 1.1697853803634644,
203
+ "learning_rate": 0.0002,
204
+ "loss": 0.3009,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 3.4730538922155687,
209
+ "grad_norm": 1.9219907522201538,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.2802,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 3.592814371257485,
216
+ "grad_norm": 1.384773850440979,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.3419,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 3.712574850299401,
223
+ "grad_norm": 1.3956997394561768,
224
+ "learning_rate": 0.0002,
225
+ "loss": 0.3172,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 3.8323353293413174,
230
+ "grad_norm": 1.058669924736023,
231
+ "learning_rate": 0.0002,
232
+ "loss": 0.3723,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 3.9520958083832336,
237
+ "grad_norm": 1.5626955032348633,
238
+ "learning_rate": 0.0002,
239
+ "loss": 0.325,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 4.07185628742515,
244
+ "grad_norm": 1.2782564163208008,
245
+ "learning_rate": 0.0002,
246
+ "loss": 0.2912,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 4.191616766467066,
251
+ "grad_norm": 1.0916423797607422,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.233,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 4.311377245508982,
258
+ "grad_norm": 0.8613762855529785,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.3058,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 4.431137724550898,
265
+ "grad_norm": 0.6293674111366272,
266
+ "learning_rate": 0.0002,
267
+ "loss": 0.2334,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 4.550898203592815,
272
+ "grad_norm": 1.6042566299438477,
273
+ "learning_rate": 0.0002,
274
+ "loss": 0.3287,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 4.6706586826347305,
279
+ "grad_norm": 0.8140411376953125,
280
+ "learning_rate": 0.0002,
281
+ "loss": 0.2372,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 4.790419161676647,
286
+ "grad_norm": 1.5365833044052124,
287
+ "learning_rate": 0.0002,
288
+ "loss": 0.3266,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 4.910179640718563,
293
+ "grad_norm": 0.9418448805809021,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.2513,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 5.029940119760479,
300
+ "grad_norm": 0.6695829033851624,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.2688,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 5.149700598802395,
307
+ "grad_norm": 0.628887414932251,
308
+ "learning_rate": 0.0002,
309
+ "loss": 0.2149,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 5.269461077844311,
314
+ "grad_norm": 0.964766263961792,
315
+ "learning_rate": 0.0002,
316
+ "loss": 0.2606,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 5.389221556886228,
321
+ "grad_norm": 0.5990360975265503,
322
+ "learning_rate": 0.0002,
323
+ "loss": 0.2364,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 5.508982035928144,
328
+ "grad_norm": 0.8189520835876465,
329
+ "learning_rate": 0.0002,
330
+ "loss": 0.2857,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 5.62874251497006,
335
+ "grad_norm": 0.5583224296569824,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.2414,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 5.748502994011976,
342
+ "grad_norm": 0.7695009708404541,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.2434,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 5.868263473053892,
349
+ "grad_norm": 0.3456665575504303,
350
+ "learning_rate": 0.0002,
351
+ "loss": 0.2597,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 5.9880239520958085,
356
+ "grad_norm": 0.7596808671951294,
357
+ "learning_rate": 0.0002,
358
+ "loss": 0.2983,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 6.107784431137724,
363
+ "grad_norm": 0.9513673782348633,
364
+ "learning_rate": 0.0002,
365
+ "loss": 0.2139,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 6.227544910179641,
370
+ "grad_norm": 1.0958881378173828,
371
+ "learning_rate": 0.0002,
372
+ "loss": 0.2211,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 6.347305389221557,
377
+ "grad_norm": 0.6882690787315369,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.2347,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 6.467065868263473,
384
+ "grad_norm": 1.0562934875488281,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.2276,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 6.586826347305389,
391
+ "grad_norm": 1.1535356044769287,
392
+ "learning_rate": 0.0002,
393
+ "loss": 0.2469,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 6.706586826347305,
398
+ "grad_norm": 0.9436424970626831,
399
+ "learning_rate": 0.0002,
400
+ "loss": 0.2713,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 6.826347305389222,
405
+ "grad_norm": 1.0283164978027344,
406
+ "learning_rate": 0.0002,
407
+ "loss": 0.2449,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 6.946107784431137,
412
+ "grad_norm": 1.3945902585983276,
413
+ "learning_rate": 0.0002,
414
+ "loss": 0.2193,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 7.065868263473054,
419
+ "grad_norm": 0.5662649869918823,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.2415,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 7.18562874251497,
426
+ "grad_norm": 0.4687662720680237,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.1792,
429
+ "step": 600
430
+ }
431
+ ],
432
+ "logging_steps": 10,
433
+ "max_steps": 600,
434
+ "num_input_tokens_seen": 0,
435
+ "num_train_epochs": 8,
436
+ "save_steps": 100,
437
+ "total_flos": 1753733775298560.0,
438
+ "train_batch_size": 1,
439
+ "trial_name": null,
440
+ "trial_params": null
441
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61628cace3d23a0b192a9deedee77f44155861bd679d5aea8149c0bf78beb87c
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff