casualprogrammer commited on
Commit
96287f6
·
verified ·
1 Parent(s): 60d1051

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ checkpoint-10498/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-15747/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ eval_results.csv filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/mbart-large-50
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:facebook/mbart-large-50
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ Shadow Finetuned mBart model.
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "facebook/mbart-large-50",
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": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "fc2",
34
+ "v_proj",
35
+ "k_proj",
36
+ "fc1",
37
+ "q_proj",
38
+ "out_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "SEQ_2_SEQ_LM",
42
+ "trainable_token_indices": null,
43
+ "use_bdlora": null,
44
+ "use_dora": false,
45
+ "use_qalora": false,
46
+ "use_rslora": true
47
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed68740976110a5a8e1053342ac6e2d75a14dec2906e0301b8c532ebcf022fc8
3
+ size 34656568
checkpoint-10498/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/mbart-large-50
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:facebook/mbart-large-50
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.19.1
checkpoint-10498/adapter_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "facebook/mbart-large-50",
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": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "fc2",
34
+ "v_proj",
35
+ "k_proj",
36
+ "fc1",
37
+ "q_proj",
38
+ "out_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "SEQ_2_SEQ_LM",
42
+ "trainable_token_indices": null,
43
+ "use_bdlora": null,
44
+ "use_dora": false,
45
+ "use_qalora": false,
46
+ "use_rslora": true
47
+ }
checkpoint-10498/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c9edac52dbc8a736b2369447671d20b894bb6e686ae5b8e73064effc64b7ed
3
+ size 34656568
checkpoint-10498/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526e7ea4d278f947167e312366109d266ca501948ee3617a01bc7e9f033565e5
3
+ size 69534499
checkpoint-10498/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51894895cf8a158ae2a50fa2be81d92c976b676a8fe0d6df2ab7c1ae8f7885c8
3
+ size 14645
checkpoint-10498/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b00d9659f55457724182e658e7a0fa30e01786cc1462a3deaabb49c966d80b
3
+ size 1465
checkpoint-10498/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
3
+ size 17109919
checkpoint-10498/tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "mask_token": "<mask>",
64
+ "model_max_length": 1024,
65
+ "pad_token": "<pad>",
66
+ "sep_token": "</s>",
67
+ "src_lang": "en_XX",
68
+ "tgt_lang": "en_XX",
69
+ "tokenizer_class": "MBart50Tokenizer",
70
+ "unk_id": 0,
71
+ "unk_token": "<unk>"
72
+ }
checkpoint-10498/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 10498,
3
+ "best_metric": 4.745133399963379,
4
+ "best_model_checkpoint": "./output/mbart-large-first/checkpoint-10498",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 10498,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 2.2508127689361572,
15
+ "learning_rate": 2.1358242354377162e-05,
16
+ "loss": 5.126435169198895,
17
+ "step": 5249
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 4.782848834991455,
22
+ "eval_rouge1": 0.2626519199005293,
23
+ "eval_rouge2": 0.11815344657319395,
24
+ "eval_rougeL": 0.20149220585189942,
25
+ "eval_rougeLsum": 0.20168022656710616,
26
+ "eval_runtime": 950.7747,
27
+ "eval_samples_per_second": 4.129,
28
+ "eval_steps_per_second": 4.129,
29
+ "step": 5249
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 3.800706148147583,
34
+ "learning_rate": 1.0680138333220317e-05,
35
+ "loss": 4.756629238902648,
36
+ "step": 10498
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_loss": 4.745133399963379,
41
+ "eval_rouge1": 0.2812791287016354,
42
+ "eval_rouge2": 0.13410717394395671,
43
+ "eval_rougeL": 0.22017424943243102,
44
+ "eval_rougeLsum": 0.22024249247836936,
45
+ "eval_runtime": 1136.965,
46
+ "eval_samples_per_second": 3.453,
47
+ "eval_steps_per_second": 3.453,
48
+ "step": 10498
49
+ }
50
+ ],
51
+ "logging_steps": 500,
52
+ "max_steps": 15747,
53
+ "num_input_tokens_seen": 0,
54
+ "num_train_epochs": 3,
55
+ "save_steps": 500,
56
+ "stateful_callbacks": {
57
+ "TrainerControl": {
58
+ "args": {
59
+ "should_epoch_stop": false,
60
+ "should_evaluate": false,
61
+ "should_log": false,
62
+ "should_save": true,
63
+ "should_training_stop": false
64
+ },
65
+ "attributes": {}
66
+ }
67
+ },
68
+ "total_flos": 1.3984655533827686e+17,
69
+ "train_batch_size": 1,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-10498/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15395dac053d64b4ff5c7d8b1bc15520dd512987b04f2d911cff1824280c5d00
3
+ size 7121
checkpoint-15747/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/mbart-large-50
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:facebook/mbart-large-50
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.19.1
checkpoint-15747/adapter_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "facebook/mbart-large-50",
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": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "fc2",
34
+ "v_proj",
35
+ "k_proj",
36
+ "fc1",
37
+ "q_proj",
38
+ "out_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "SEQ_2_SEQ_LM",
42
+ "trainable_token_indices": null,
43
+ "use_bdlora": null,
44
+ "use_dora": false,
45
+ "use_qalora": false,
46
+ "use_rslora": true
47
+ }
checkpoint-15747/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed68740976110a5a8e1053342ac6e2d75a14dec2906e0301b8c532ebcf022fc8
3
+ size 34656568
checkpoint-15747/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:305ca4d383e476beef6df746808ae0814a697f6cab16044cb37e5ef5c5dc34bc
3
+ size 69534499
checkpoint-15747/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d023c4e30fdefc45ca1bf32f69519b0d60e1112f468c3efcbb6d37783055e54d
3
+ size 14645
checkpoint-15747/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb765421b6da16525ba35cdf6df6969c34d19f525e5a77208c1e65c6ddab5de0
3
+ size 1465
checkpoint-15747/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
3
+ size 17109919
checkpoint-15747/tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "mask_token": "<mask>",
64
+ "model_max_length": 1024,
65
+ "pad_token": "<pad>",
66
+ "sep_token": "</s>",
67
+ "src_lang": "en_XX",
68
+ "tgt_lang": "en_XX",
69
+ "tokenizer_class": "MBart50Tokenizer",
70
+ "unk_id": 0,
71
+ "unk_token": "<unk>"
72
+ }
checkpoint-15747/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 15747,
3
+ "best_metric": 4.732922554016113,
4
+ "best_model_checkpoint": "./output/mbart-large-first/checkpoint-15747",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 15747,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 2.2508127689361572,
15
+ "learning_rate": 2.1358242354377162e-05,
16
+ "loss": 5.126435169198895,
17
+ "step": 5249
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 4.782848834991455,
22
+ "eval_rouge1": 0.2626519199005293,
23
+ "eval_rouge2": 0.11815344657319395,
24
+ "eval_rougeL": 0.20149220585189942,
25
+ "eval_rougeLsum": 0.20168022656710616,
26
+ "eval_runtime": 950.7747,
27
+ "eval_samples_per_second": 4.129,
28
+ "eval_steps_per_second": 4.129,
29
+ "step": 5249
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 3.800706148147583,
34
+ "learning_rate": 1.0680138333220317e-05,
35
+ "loss": 4.756629238902648,
36
+ "step": 10498
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_loss": 4.745133399963379,
41
+ "eval_rouge1": 0.2812791287016354,
42
+ "eval_rouge2": 0.13410717394395671,
43
+ "eval_rougeL": 0.22017424943243102,
44
+ "eval_rougeLsum": 0.22024249247836936,
45
+ "eval_runtime": 1136.965,
46
+ "eval_samples_per_second": 3.453,
47
+ "eval_steps_per_second": 3.453,
48
+ "step": 10498
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "grad_norm": 3.2896928787231445,
53
+ "learning_rate": 2.034312063470536e-09,
54
+ "loss": 4.713336022337588,
55
+ "step": 15747
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_loss": 4.732922554016113,
60
+ "eval_rouge1": 0.28348414256505183,
61
+ "eval_rouge2": 0.13573693703550854,
62
+ "eval_rougeL": 0.2211924448035419,
63
+ "eval_rougeLsum": 0.22134620876521682,
64
+ "eval_runtime": 937.6713,
65
+ "eval_samples_per_second": 4.187,
66
+ "eval_steps_per_second": 4.187,
67
+ "step": 15747
68
+ }
69
+ ],
70
+ "logging_steps": 500,
71
+ "max_steps": 15747,
72
+ "num_input_tokens_seen": 0,
73
+ "num_train_epochs": 3,
74
+ "save_steps": 500,
75
+ "stateful_callbacks": {
76
+ "TrainerControl": {
77
+ "args": {
78
+ "should_epoch_stop": false,
79
+ "should_evaluate": false,
80
+ "should_log": false,
81
+ "should_save": true,
82
+ "should_training_stop": true
83
+ },
84
+ "attributes": {}
85
+ }
86
+ },
87
+ "total_flos": 2.097698330074153e+17,
88
+ "train_batch_size": 1,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-15747/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15395dac053d64b4ff5c7d8b1bc15520dd512987b04f2d911cff1824280c5d00
3
+ size 7121
eval_results.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f03ad6105b04dd845462d153ba6eeb909d474375f0cb400307cb7e9020d435
3
+ size 60244331
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "max_time": 30,
10
+ "num_beams": 2,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "5.5.0",
13
+ "use_cache": true
14
+ }
meta_config.json ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "facebook/mbart-large-50",
3
+ "dataset_path": null,
4
+ "training_args": {
5
+ "output_dir": "./output/mbart-large-first",
6
+ "per_device_train_batch_size": 1,
7
+ "num_train_epochs": 3,
8
+ "max_steps": -1,
9
+ "learning_rate": 3e-05,
10
+ "lr_scheduler_type": "linear",
11
+ "lr_scheduler_kwargs": null,
12
+ "warmup_steps": 1000,
13
+ "optim": "adamw_torch_fused",
14
+ "optim_args": null,
15
+ "weight_decay": 0.01,
16
+ "adam_beta1": 0.9,
17
+ "adam_beta2": 0.999,
18
+ "adam_epsilon": 1e-08,
19
+ "optim_target_modules": null,
20
+ "gradient_accumulation_steps": 1,
21
+ "average_tokens_across_devices": true,
22
+ "max_grad_norm": 1.0,
23
+ "label_smoothing_factor": 0.0,
24
+ "bf16": true,
25
+ "fp16": false,
26
+ "bf16_full_eval": false,
27
+ "fp16_full_eval": false,
28
+ "tf32": null,
29
+ "gradient_checkpointing": false,
30
+ "gradient_checkpointing_kwargs": null,
31
+ "torch_compile": false,
32
+ "torch_compile_backend": null,
33
+ "torch_compile_mode": null,
34
+ "use_liger_kernel": false,
35
+ "liger_kernel_config": null,
36
+ "use_cache": false,
37
+ "neftune_noise_alpha": null,
38
+ "torch_empty_cache_steps": null,
39
+ "auto_find_batch_size": false,
40
+ "logging_strategy": "epoch",
41
+ "logging_steps": 500,
42
+ "logging_first_step": false,
43
+ "log_on_each_node": true,
44
+ "logging_nan_inf_filter": true,
45
+ "include_num_input_tokens_seen": "no",
46
+ "log_level": "passive",
47
+ "log_level_replica": "warning",
48
+ "disable_tqdm": false,
49
+ "report_to": [],
50
+ "run_name": null,
51
+ "project": "huggingface",
52
+ "trackio_space_id": "trackio",
53
+ "eval_strategy": "epoch",
54
+ "eval_steps": null,
55
+ "eval_delay": 0,
56
+ "per_device_eval_batch_size": 1,
57
+ "prediction_loss_only": false,
58
+ "eval_on_start": false,
59
+ "eval_do_concat_batches": true,
60
+ "eval_use_gather_object": false,
61
+ "eval_accumulation_steps": null,
62
+ "include_for_metrics": [],
63
+ "batch_eval_metrics": false,
64
+ "save_only_model": false,
65
+ "save_strategy": "epoch",
66
+ "save_steps": 500,
67
+ "save_on_each_node": false,
68
+ "save_total_limit": 2,
69
+ "enable_jit_checkpoint": false,
70
+ "push_to_hub": false,
71
+ "hub_token": "<HUB_TOKEN>",
72
+ "hub_private_repo": null,
73
+ "hub_model_id": null,
74
+ "hub_strategy": "every_save",
75
+ "hub_always_push": false,
76
+ "hub_revision": null,
77
+ "load_best_model_at_end": true,
78
+ "metric_for_best_model": "eval_loss",
79
+ "greater_is_better": false,
80
+ "ignore_data_skip": false,
81
+ "restore_callback_states_from_checkpoint": false,
82
+ "full_determinism": false,
83
+ "seed": 42,
84
+ "data_seed": null,
85
+ "use_cpu": false,
86
+ "accelerator_config": {
87
+ "split_batches": false,
88
+ "dispatch_batches": null,
89
+ "even_batches": true,
90
+ "use_seedable_sampler": true,
91
+ "non_blocking": false,
92
+ "gradient_accumulation_kwargs": null
93
+ },
94
+ "parallelism_config": null,
95
+ "dataloader_drop_last": false,
96
+ "dataloader_num_workers": 0,
97
+ "dataloader_pin_memory": true,
98
+ "dataloader_persistent_workers": false,
99
+ "dataloader_prefetch_factor": null,
100
+ "remove_unused_columns": true,
101
+ "label_names": null,
102
+ "train_sampling_strategy": "random",
103
+ "length_column_name": "length",
104
+ "ddp_find_unused_parameters": null,
105
+ "ddp_bucket_cap_mb": null,
106
+ "ddp_broadcast_buffers": null,
107
+ "ddp_backend": null,
108
+ "ddp_timeout": 1800,
109
+ "fsdp": [],
110
+ "fsdp_config": {
111
+ "min_num_params": 0,
112
+ "xla": false,
113
+ "xla_fsdp_v2": false,
114
+ "xla_fsdp_grad_ckpt": false
115
+ },
116
+ "deepspeed": null,
117
+ "debug": [],
118
+ "skip_memory_metrics": true,
119
+ "do_train": false,
120
+ "do_eval": true,
121
+ "do_predict": false,
122
+ "resume_from_checkpoint": null,
123
+ "warmup_ratio": null,
124
+ "logging_dir": null,
125
+ "local_rank": -1,
126
+ "sortish_sampler": false,
127
+ "predict_with_generate": true,
128
+ "generation_max_length": null,
129
+ "generation_num_beams": null,
130
+ "generation_config": {
131
+ "max_length": 200,
132
+ "max_new_tokens": null,
133
+ "min_length": null,
134
+ "min_new_tokens": null,
135
+ "early_stopping": true,
136
+ "max_time": 30,
137
+ "stop_strings": null,
138
+ "do_sample": null,
139
+ "num_beams": 2,
140
+ "use_cache": true,
141
+ "cache_implementation": null,
142
+ "cache_config": null,
143
+ "temperature": null,
144
+ "top_k": null,
145
+ "top_p": null,
146
+ "min_p": null,
147
+ "top_h": null,
148
+ "typical_p": null,
149
+ "epsilon_cutoff": null,
150
+ "eta_cutoff": null,
151
+ "repetition_penalty": null,
152
+ "encoder_repetition_penalty": null,
153
+ "length_penalty": null,
154
+ "no_repeat_ngram_size": null,
155
+ "bad_words_ids": null,
156
+ "renormalize_logits": null,
157
+ "forced_bos_token_id": null,
158
+ "forced_eos_token_id": 2,
159
+ "remove_invalid_values": null,
160
+ "exponential_decay_length_penalty": null,
161
+ "suppress_tokens": null,
162
+ "begin_suppress_tokens": null,
163
+ "sequence_bias": null,
164
+ "token_healing": null,
165
+ "guidance_scale": null,
166
+ "watermarking_config": null,
167
+ "num_return_sequences": null,
168
+ "output_attentions": null,
169
+ "output_hidden_states": null,
170
+ "output_scores": null,
171
+ "output_logits": null,
172
+ "return_dict_in_generate": null,
173
+ "pad_token_id": 1,
174
+ "bos_token_id": 0,
175
+ "eos_token_id": 2,
176
+ "encoder_no_repeat_ngram_size": null,
177
+ "decoder_start_token_id": 2,
178
+ "is_assistant": null,
179
+ "num_assistant_tokens": null,
180
+ "num_assistant_tokens_schedule": null,
181
+ "assistant_confidence_threshold": null,
182
+ "prompt_lookup_num_tokens": null,
183
+ "max_matching_ngram_size": null,
184
+ "assistant_early_exit": null,
185
+ "assistant_lookbehind": null,
186
+ "target_lookbehind": null,
187
+ "compile_config": null,
188
+ "disable_compile": null,
189
+ "continuous_batching_config": null,
190
+ "low_memory": null,
191
+ "penalty_alpha": null,
192
+ "dola_layers": null,
193
+ "diversity_penalty": null,
194
+ "num_beam_groups": null,
195
+ "constraints": null,
196
+ "force_words_ids": null,
197
+ "prefill_chunk_size": null,
198
+ "_from_model_config": true,
199
+ "transformers_version": "5.5.0"
200
+ }
201
+ },
202
+ "INPUT_COL": "combined_text",
203
+ "LABEL_COL": "summary",
204
+ "columns_to_keep": [
205
+ "combined_text",
206
+ "summary"
207
+ ],
208
+ "run_cfg": {
209
+ "model_name": "facebook/mbart-large-50",
210
+ "output_dir": "./output/mbart-large-first",
211
+ "LM_type": "seq2seq",
212
+ "input_col_name": "combined_text",
213
+ "label_col_name": "summary",
214
+ "input_text_max_length": 1024,
215
+ "summary_text_max_length": 256,
216
+ "pad_to_multiple_of_input_text": 1024,
217
+ "pad_to_multiple_of_summary_text": 1,
218
+ "batch_max_tokens": 16384,
219
+ "batch_max_tokens_multiplier": 0.8,
220
+ "hyperparameter_search": false,
221
+ "objective_is_loss": false,
222
+ "bf16": true,
223
+ "gradient_accumulation_steps": 1,
224
+ "num_train_epochs": 3,
225
+ "learning_rate": 3e-05,
226
+ "weight_decay": 0.01,
227
+ "max_grad_norm": 1.0,
228
+ "lr_scheduler_type": "cosine",
229
+ "target_modules": "all-linear",
230
+ "training_optim": "adamw_torch_fused",
231
+ "peft_gradient_checkpointing": false,
232
+ "own_bartled_underlying_model": null,
233
+ "selector_name": "first"
234
+ }
235
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
3
+ size 17109919
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "mask_token": "<mask>",
64
+ "model_max_length": 1024,
65
+ "pad_token": "<pad>",
66
+ "sep_token": "</s>",
67
+ "src_lang": "en_XX",
68
+ "tgt_lang": "en_XX",
69
+ "tokenizer_class": "MBart50Tokenizer",
70
+ "unk_id": 0,
71
+ "unk_token": "<unk>"
72
+ }