Fill-Mask
PEFT
Safetensors
Transformers
modernbert
lora
dapt
sft
heitorrosa commited on
Commit
2a57597
·
verified ·
1 Parent(s): 4d8318c

chore: nest checkpoint-4000 under dapt/

Browse files
dapt/checkpoint-4000/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Itau-Unibanco/NorBERTo-base
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:Itau-Unibanco/NorBERTo-base
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 0.20.0
dapt/checkpoint-4000/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Itau-Unibanco/NorBERTo-base",
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": 0.05,
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": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "Wo",
35
+ "Wqkv",
36
+ "Wi"
37
+ ],
38
+ "target_parameters": null,
39
+ "task_type": "FEATURE_EXTRACTION",
40
+ "trainable_token_indices": null,
41
+ "use_bdlora": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false,
45
+ "velora_config": null
46
+ }
dapt/checkpoint-4000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a49181543ca0af729f789595b4728b7a133122e8bbdf7cb7596267fe2161056
3
+ size 13538528
dapt/checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c8fea432e63a3a36f8a23dd44dea9a86821857e9d9dd0d7031d45aefcda66e
3
+ size 27184331
dapt/checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388e0482ac2b7b222ca0b6538430ec6603eeabdc5b27336aed91db0ef8ce8bca
3
+ size 14645
dapt/checkpoint-4000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8915edf20e9ecb0995f5a55ba5cf97f225b6e90abd7deeccf9b146ba27aa1444
3
+ size 1383
dapt/checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcee9a5ebde381b985266391900b5d75040d04b0b33fd9a9c02f1c30c408d640
3
+ size 1465
dapt/checkpoint-4000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dapt/checkpoint-4000/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "[CLS]",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "[SEP]",
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_token": "[PAD]",
15
+ "padding_side": "right",
16
+ "tokenizer_class": "TokenizersBackend",
17
+ "truncation_side": "right",
18
+ "unk_token": "[UNK]"
19
+ }
dapt/checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,658 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.6877653000913438,
6
+ "eval_steps": 500,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008597066251141797,
14
+ "grad_norm": 0.3461540639400482,
15
+ "learning_rate": 4.9000000000000005e-06,
16
+ "loss": 0.7137960815429687,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.017194132502283594,
21
+ "grad_norm": 0.23365077376365662,
22
+ "learning_rate": 9.900000000000002e-06,
23
+ "loss": 0.6752699279785156,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.025791198753425393,
28
+ "grad_norm": 0.18823082745075226,
29
+ "learning_rate": 1.49e-05,
30
+ "loss": 0.6456453704833984,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.03438826500456719,
35
+ "grad_norm": 0.23714424669742584,
36
+ "learning_rate": 1.9900000000000003e-05,
37
+ "loss": 0.6078555679321289,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.04298533125570899,
42
+ "grad_norm": 0.16429093480110168,
43
+ "learning_rate": 2.4900000000000002e-05,
44
+ "loss": 0.6051961135864258,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.051582397506850786,
49
+ "grad_norm": 0.16205623745918274,
50
+ "learning_rate": 2.9900000000000002e-05,
51
+ "loss": 0.5889498901367187,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.06017946375799259,
56
+ "grad_norm": 0.1743771731853485,
57
+ "learning_rate": 3.49e-05,
58
+ "loss": 0.5702997970581055,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.06877653000913438,
63
+ "grad_norm": 0.15920504927635193,
64
+ "learning_rate": 3.99e-05,
65
+ "loss": 0.5728500747680664,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.07737359626027618,
70
+ "grad_norm": 0.18150873482227325,
71
+ "learning_rate": 4.49e-05,
72
+ "loss": 0.5552708053588867,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.08597066251141798,
77
+ "grad_norm": 0.2273012101650238,
78
+ "learning_rate": 4.99e-05,
79
+ "loss": 0.5470176696777344,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.08597066251141798,
84
+ "eval_loss": 0.5438547134399414,
85
+ "eval_runtime": 361.1497,
86
+ "eval_samples_per_second": 5.206,
87
+ "eval_steps_per_second": 1.301,
88
+ "step": 500
89
+ },
90
+ {
91
+ "epoch": 0.09456772876255978,
92
+ "grad_norm": 0.1610037386417389,
93
+ "learning_rate": 4.970209143968872e-05,
94
+ "loss": 0.5506169891357422,
95
+ "step": 550
96
+ },
97
+ {
98
+ "epoch": 0.10316479501370157,
99
+ "grad_norm": 0.18427467346191406,
100
+ "learning_rate": 4.9398103112840474e-05,
101
+ "loss": 0.538709716796875,
102
+ "step": 600
103
+ },
104
+ {
105
+ "epoch": 0.11176186126484337,
106
+ "grad_norm": 0.17865458130836487,
107
+ "learning_rate": 4.9094114785992216e-05,
108
+ "loss": 0.5439010620117187,
109
+ "step": 650
110
+ },
111
+ {
112
+ "epoch": 0.12035892751598518,
113
+ "grad_norm": 0.20380577445030212,
114
+ "learning_rate": 4.879012645914397e-05,
115
+ "loss": 0.5345694732666015,
116
+ "step": 700
117
+ },
118
+ {
119
+ "epoch": 0.12895599376712696,
120
+ "grad_norm": 0.21836704015731812,
121
+ "learning_rate": 4.8486138132295725e-05,
122
+ "loss": 0.5367267608642579,
123
+ "step": 750
124
+ },
125
+ {
126
+ "epoch": 0.13755306001826875,
127
+ "grad_norm": 0.21373888850212097,
128
+ "learning_rate": 4.818214980544747e-05,
129
+ "loss": 0.5393967819213867,
130
+ "step": 800
131
+ },
132
+ {
133
+ "epoch": 0.14615012626941057,
134
+ "grad_norm": 0.17039674520492554,
135
+ "learning_rate": 4.787816147859923e-05,
136
+ "loss": 0.5188388061523438,
137
+ "step": 850
138
+ },
139
+ {
140
+ "epoch": 0.15474719252055236,
141
+ "grad_norm": 0.1947856992483139,
142
+ "learning_rate": 4.7574173151750976e-05,
143
+ "loss": 0.5279138565063477,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 0.16334425877169417,
148
+ "grad_norm": 0.1957385241985321,
149
+ "learning_rate": 4.7270184824902724e-05,
150
+ "loss": 0.5388415908813476,
151
+ "step": 950
152
+ },
153
+ {
154
+ "epoch": 0.17194132502283596,
155
+ "grad_norm": 0.19011224806308746,
156
+ "learning_rate": 4.696619649805448e-05,
157
+ "loss": 0.527779426574707,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 0.17194132502283596,
162
+ "eval_loss": 0.5264737010002136,
163
+ "eval_runtime": 349.4761,
164
+ "eval_samples_per_second": 5.379,
165
+ "eval_steps_per_second": 1.345,
166
+ "step": 1000
167
+ },
168
+ {
169
+ "epoch": 0.18053839127397775,
170
+ "grad_norm": 0.17350342869758606,
171
+ "learning_rate": 4.6662208171206227e-05,
172
+ "loss": 0.5216117858886719,
173
+ "step": 1050
174
+ },
175
+ {
176
+ "epoch": 0.18913545752511957,
177
+ "grad_norm": 0.17218773066997528,
178
+ "learning_rate": 4.635821984435798e-05,
179
+ "loss": 0.5192420196533203,
180
+ "step": 1100
181
+ },
182
+ {
183
+ "epoch": 0.19773252377626135,
184
+ "grad_norm": 0.1787382811307907,
185
+ "learning_rate": 4.605423151750973e-05,
186
+ "loss": 0.5193338394165039,
187
+ "step": 1150
188
+ },
189
+ {
190
+ "epoch": 0.20632959002740314,
191
+ "grad_norm": 0.17407308518886566,
192
+ "learning_rate": 4.575024319066148e-05,
193
+ "loss": 0.529417610168457,
194
+ "step": 1200
195
+ },
196
+ {
197
+ "epoch": 0.21492665627854496,
198
+ "grad_norm": 0.18545730412006378,
199
+ "learning_rate": 4.544625486381323e-05,
200
+ "loss": 0.5278170394897461,
201
+ "step": 1250
202
+ },
203
+ {
204
+ "epoch": 0.22352372252968675,
205
+ "grad_norm": 0.19537468254566193,
206
+ "learning_rate": 4.514226653696498e-05,
207
+ "loss": 0.5204765319824218,
208
+ "step": 1300
209
+ },
210
+ {
211
+ "epoch": 0.23212078878082854,
212
+ "grad_norm": 0.2441568374633789,
213
+ "learning_rate": 4.4838278210116735e-05,
214
+ "loss": 0.5202705001831055,
215
+ "step": 1350
216
+ },
217
+ {
218
+ "epoch": 0.24071785503197035,
219
+ "grad_norm": 0.23745512962341309,
220
+ "learning_rate": 4.453428988326849e-05,
221
+ "loss": 0.5292264556884766,
222
+ "step": 1400
223
+ },
224
+ {
225
+ "epoch": 0.24931492128311214,
226
+ "grad_norm": 0.1980402022600174,
227
+ "learning_rate": 4.423030155642023e-05,
228
+ "loss": 0.5218988800048828,
229
+ "step": 1450
230
+ },
231
+ {
232
+ "epoch": 0.25791198753425393,
233
+ "grad_norm": 0.2273419052362442,
234
+ "learning_rate": 4.3926313229571986e-05,
235
+ "loss": 0.5181735992431641,
236
+ "step": 1500
237
+ },
238
+ {
239
+ "epoch": 0.25791198753425393,
240
+ "eval_loss": 0.5230017304420471,
241
+ "eval_runtime": 375.9124,
242
+ "eval_samples_per_second": 5.001,
243
+ "eval_steps_per_second": 1.25,
244
+ "step": 1500
245
+ },
246
+ {
247
+ "epoch": 0.26650905378539574,
248
+ "grad_norm": 0.1970907747745514,
249
+ "learning_rate": 4.362232490272374e-05,
250
+ "loss": 0.5135591125488281,
251
+ "step": 1550
252
+ },
253
+ {
254
+ "epoch": 0.2751061200365375,
255
+ "grad_norm": 0.2051905244588852,
256
+ "learning_rate": 4.331833657587549e-05,
257
+ "loss": 0.5052785873413086,
258
+ "step": 1600
259
+ },
260
+ {
261
+ "epoch": 0.2837031862876793,
262
+ "grad_norm": 0.19686760008335114,
263
+ "learning_rate": 4.301434824902724e-05,
264
+ "loss": 0.5177907943725586,
265
+ "step": 1650
266
+ },
267
+ {
268
+ "epoch": 0.29230025253882114,
269
+ "grad_norm": 0.20986631512641907,
270
+ "learning_rate": 4.271035992217899e-05,
271
+ "loss": 0.5072374725341797,
272
+ "step": 1700
273
+ },
274
+ {
275
+ "epoch": 0.3008973187899629,
276
+ "grad_norm": 0.2033650428056717,
277
+ "learning_rate": 4.240637159533074e-05,
278
+ "loss": 0.5099851989746094,
279
+ "step": 1750
280
+ },
281
+ {
282
+ "epoch": 0.3094943850411047,
283
+ "grad_norm": 0.20672816038131714,
284
+ "learning_rate": 4.2102383268482494e-05,
285
+ "loss": 0.5082115936279297,
286
+ "step": 1800
287
+ },
288
+ {
289
+ "epoch": 0.31809145129224653,
290
+ "grad_norm": 0.1826789379119873,
291
+ "learning_rate": 4.179839494163424e-05,
292
+ "loss": 0.5152957153320312,
293
+ "step": 1850
294
+ },
295
+ {
296
+ "epoch": 0.32668851754338835,
297
+ "grad_norm": 0.24080227315425873,
298
+ "learning_rate": 4.1494406614785997e-05,
299
+ "loss": 0.516766014099121,
300
+ "step": 1900
301
+ },
302
+ {
303
+ "epoch": 0.3352855837945301,
304
+ "grad_norm": 0.18921689689159393,
305
+ "learning_rate": 4.1190418287937745e-05,
306
+ "loss": 0.5188713455200196,
307
+ "step": 1950
308
+ },
309
+ {
310
+ "epoch": 0.3438826500456719,
311
+ "grad_norm": 0.21723054349422455,
312
+ "learning_rate": 4.088642996108949e-05,
313
+ "loss": 0.508725471496582,
314
+ "step": 2000
315
+ },
316
+ {
317
+ "epoch": 0.3438826500456719,
318
+ "eval_loss": 0.5111244916915894,
319
+ "eval_runtime": 375.1647,
320
+ "eval_samples_per_second": 5.011,
321
+ "eval_steps_per_second": 1.253,
322
+ "step": 2000
323
+ },
324
+ {
325
+ "epoch": 0.35247971629681374,
326
+ "grad_norm": 0.2504056692123413,
327
+ "learning_rate": 4.058244163424125e-05,
328
+ "loss": 0.5189783477783203,
329
+ "step": 2050
330
+ },
331
+ {
332
+ "epoch": 0.3610767825479555,
333
+ "grad_norm": 0.20812708139419556,
334
+ "learning_rate": 4.0278453307393e-05,
335
+ "loss": 0.5200382995605469,
336
+ "step": 2100
337
+ },
338
+ {
339
+ "epoch": 0.3696738487990973,
340
+ "grad_norm": 0.21136048436164856,
341
+ "learning_rate": 3.997446498054475e-05,
342
+ "loss": 0.5042448806762695,
343
+ "step": 2150
344
+ },
345
+ {
346
+ "epoch": 0.37827091505023913,
347
+ "grad_norm": 0.2592664957046509,
348
+ "learning_rate": 3.96704766536965e-05,
349
+ "loss": 0.511298828125,
350
+ "step": 2200
351
+ },
352
+ {
353
+ "epoch": 0.3868679813013809,
354
+ "grad_norm": 0.20483101904392242,
355
+ "learning_rate": 3.936648832684825e-05,
356
+ "loss": 0.5088952255249023,
357
+ "step": 2250
358
+ },
359
+ {
360
+ "epoch": 0.3954650475525227,
361
+ "grad_norm": 0.2416965663433075,
362
+ "learning_rate": 3.90625e-05,
363
+ "loss": 0.5220498275756836,
364
+ "step": 2300
365
+ },
366
+ {
367
+ "epoch": 0.4040621138036645,
368
+ "grad_norm": 0.2950873374938965,
369
+ "learning_rate": 3.8758511673151756e-05,
370
+ "loss": 0.5161582946777343,
371
+ "step": 2350
372
+ },
373
+ {
374
+ "epoch": 0.4126591800548063,
375
+ "grad_norm": 0.22417296469211578,
376
+ "learning_rate": 3.8454523346303504e-05,
377
+ "loss": 0.5022587966918945,
378
+ "step": 2400
379
+ },
380
+ {
381
+ "epoch": 0.4212562463059481,
382
+ "grad_norm": 0.24061641097068787,
383
+ "learning_rate": 3.815053501945525e-05,
384
+ "loss": 0.5108227157592773,
385
+ "step": 2450
386
+ },
387
+ {
388
+ "epoch": 0.4298533125570899,
389
+ "grad_norm": 0.21841247379779816,
390
+ "learning_rate": 3.7846546692607006e-05,
391
+ "loss": 0.5098703002929688,
392
+ "step": 2500
393
+ },
394
+ {
395
+ "epoch": 0.4298533125570899,
396
+ "eval_loss": 0.5066602826118469,
397
+ "eval_runtime": 366.5148,
398
+ "eval_samples_per_second": 5.129,
399
+ "eval_steps_per_second": 1.282,
400
+ "step": 2500
401
+ },
402
+ {
403
+ "epoch": 0.4384503788082317,
404
+ "grad_norm": 0.2083503156900406,
405
+ "learning_rate": 3.7542558365758754e-05,
406
+ "loss": 0.49932518005371096,
407
+ "step": 2550
408
+ },
409
+ {
410
+ "epoch": 0.4470474450593735,
411
+ "grad_norm": 0.21678738296031952,
412
+ "learning_rate": 3.723857003891051e-05,
413
+ "loss": 0.5064985275268554,
414
+ "step": 2600
415
+ },
416
+ {
417
+ "epoch": 0.4556445113105153,
418
+ "grad_norm": 0.24412305653095245,
419
+ "learning_rate": 3.6934581712062264e-05,
420
+ "loss": 0.5066806411743164,
421
+ "step": 2650
422
+ },
423
+ {
424
+ "epoch": 0.46424157756165707,
425
+ "grad_norm": 0.26758745312690735,
426
+ "learning_rate": 3.6630593385214005e-05,
427
+ "loss": 0.5179504013061523,
428
+ "step": 2700
429
+ },
430
+ {
431
+ "epoch": 0.4728386438127989,
432
+ "grad_norm": 0.2602377235889435,
433
+ "learning_rate": 3.632660505836576e-05,
434
+ "loss": 0.4992792510986328,
435
+ "step": 2750
436
+ },
437
+ {
438
+ "epoch": 0.4814357100639407,
439
+ "grad_norm": 0.2009514719247818,
440
+ "learning_rate": 3.602261673151751e-05,
441
+ "loss": 0.5105620574951172,
442
+ "step": 2800
443
+ },
444
+ {
445
+ "epoch": 0.49003277631508246,
446
+ "grad_norm": 0.21059006452560425,
447
+ "learning_rate": 3.571862840466926e-05,
448
+ "loss": 0.508187255859375,
449
+ "step": 2850
450
+ },
451
+ {
452
+ "epoch": 0.4986298425662243,
453
+ "grad_norm": 0.2044428288936615,
454
+ "learning_rate": 3.541464007782102e-05,
455
+ "loss": 0.5071085739135742,
456
+ "step": 2900
457
+ },
458
+ {
459
+ "epoch": 0.5072269088173661,
460
+ "grad_norm": 0.2184259295463562,
461
+ "learning_rate": 3.511065175097276e-05,
462
+ "loss": 0.5003342056274414,
463
+ "step": 2950
464
+ },
465
+ {
466
+ "epoch": 0.5158239750685079,
467
+ "grad_norm": 0.22149892151355743,
468
+ "learning_rate": 3.480666342412451e-05,
469
+ "loss": 0.5028779983520508,
470
+ "step": 3000
471
+ },
472
+ {
473
+ "epoch": 0.5158239750685079,
474
+ "eval_loss": 0.5020000338554382,
475
+ "eval_runtime": 346.4065,
476
+ "eval_samples_per_second": 5.427,
477
+ "eval_steps_per_second": 1.357,
478
+ "step": 3000
479
+ },
480
+ {
481
+ "epoch": 0.5244210413196496,
482
+ "grad_norm": 0.25263792276382446,
483
+ "learning_rate": 3.450267509727627e-05,
484
+ "loss": 0.4868510818481445,
485
+ "step": 3050
486
+ },
487
+ {
488
+ "epoch": 0.5330181075707915,
489
+ "grad_norm": 0.1957710087299347,
490
+ "learning_rate": 3.4198686770428016e-05,
491
+ "loss": 0.5041673660278321,
492
+ "step": 3100
493
+ },
494
+ {
495
+ "epoch": 0.5416151738219332,
496
+ "grad_norm": 0.2603848874568939,
497
+ "learning_rate": 3.389469844357977e-05,
498
+ "loss": 0.5014479827880859,
499
+ "step": 3150
500
+ },
501
+ {
502
+ "epoch": 0.550212240073075,
503
+ "grad_norm": 0.17874036729335785,
504
+ "learning_rate": 3.359071011673152e-05,
505
+ "loss": 0.505292739868164,
506
+ "step": 3200
507
+ },
508
+ {
509
+ "epoch": 0.5588093063242169,
510
+ "grad_norm": 0.24125388264656067,
511
+ "learning_rate": 3.328672178988327e-05,
512
+ "loss": 0.514274787902832,
513
+ "step": 3250
514
+ },
515
+ {
516
+ "epoch": 0.5674063725753586,
517
+ "grad_norm": 0.22477301955223083,
518
+ "learning_rate": 3.298273346303502e-05,
519
+ "loss": 0.5066662979125977,
520
+ "step": 3300
521
+ },
522
+ {
523
+ "epoch": 0.5760034388265004,
524
+ "grad_norm": 0.23808450996875763,
525
+ "learning_rate": 3.267874513618677e-05,
526
+ "loss": 0.49730167388916013,
527
+ "step": 3350
528
+ },
529
+ {
530
+ "epoch": 0.5846005050776423,
531
+ "grad_norm": 0.2184080332517624,
532
+ "learning_rate": 3.2374756809338524e-05,
533
+ "loss": 0.5056488800048828,
534
+ "step": 3400
535
+ },
536
+ {
537
+ "epoch": 0.593197571328784,
538
+ "grad_norm": 0.25470733642578125,
539
+ "learning_rate": 3.207076848249028e-05,
540
+ "loss": 0.4887243270874023,
541
+ "step": 3450
542
+ },
543
+ {
544
+ "epoch": 0.6017946375799258,
545
+ "grad_norm": 0.2762533128261566,
546
+ "learning_rate": 3.176678015564202e-05,
547
+ "loss": 0.4995370101928711,
548
+ "step": 3500
549
+ },
550
+ {
551
+ "epoch": 0.6017946375799258,
552
+ "eval_loss": 0.5056677460670471,
553
+ "eval_runtime": 348.3925,
554
+ "eval_samples_per_second": 5.396,
555
+ "eval_steps_per_second": 1.349,
556
+ "step": 3500
557
+ },
558
+ {
559
+ "epoch": 0.6103917038310677,
560
+ "grad_norm": 0.2317754477262497,
561
+ "learning_rate": 3.1462791828793775e-05,
562
+ "loss": 0.5123172760009765,
563
+ "step": 3550
564
+ },
565
+ {
566
+ "epoch": 0.6189887700822094,
567
+ "grad_norm": 0.22287645936012268,
568
+ "learning_rate": 3.115880350194553e-05,
569
+ "loss": 0.5003259658813477,
570
+ "step": 3600
571
+ },
572
+ {
573
+ "epoch": 0.6275858363333513,
574
+ "grad_norm": 0.20770233869552612,
575
+ "learning_rate": 3.085481517509728e-05,
576
+ "loss": 0.4997048187255859,
577
+ "step": 3650
578
+ },
579
+ {
580
+ "epoch": 0.6361829025844931,
581
+ "grad_norm": 0.22887976467609406,
582
+ "learning_rate": 3.055082684824903e-05,
583
+ "loss": 0.493292350769043,
584
+ "step": 3700
585
+ },
586
+ {
587
+ "epoch": 0.6447799688356348,
588
+ "grad_norm": 0.24185964465141296,
589
+ "learning_rate": 3.0246838521400777e-05,
590
+ "loss": 0.4899324417114258,
591
+ "step": 3750
592
+ },
593
+ {
594
+ "epoch": 0.6533770350867767,
595
+ "grad_norm": 0.2602291703224182,
596
+ "learning_rate": 2.994285019455253e-05,
597
+ "loss": 0.5039303207397461,
598
+ "step": 3800
599
+ },
600
+ {
601
+ "epoch": 0.6619741013379185,
602
+ "grad_norm": 0.26305103302001953,
603
+ "learning_rate": 2.9638861867704283e-05,
604
+ "loss": 0.49886848449707033,
605
+ "step": 3850
606
+ },
607
+ {
608
+ "epoch": 0.6705711675890602,
609
+ "grad_norm": 0.2317502647638321,
610
+ "learning_rate": 2.9334873540856035e-05,
611
+ "loss": 0.5039469909667968,
612
+ "step": 3900
613
+ },
614
+ {
615
+ "epoch": 0.6791682338402021,
616
+ "grad_norm": 0.28173670172691345,
617
+ "learning_rate": 2.9030885214007786e-05,
618
+ "loss": 0.492442626953125,
619
+ "step": 3950
620
+ },
621
+ {
622
+ "epoch": 0.6877653000913438,
623
+ "grad_norm": 0.2428692728281021,
624
+ "learning_rate": 2.872689688715953e-05,
625
+ "loss": 0.49990890502929686,
626
+ "step": 4000
627
+ },
628
+ {
629
+ "epoch": 0.6877653000913438,
630
+ "eval_loss": 0.5016358494758606,
631
+ "eval_runtime": 347.7511,
632
+ "eval_samples_per_second": 5.406,
633
+ "eval_steps_per_second": 1.352,
634
+ "step": 4000
635
+ }
636
+ ],
637
+ "logging_steps": 50,
638
+ "max_steps": 8724,
639
+ "num_input_tokens_seen": 0,
640
+ "num_train_epochs": 2,
641
+ "save_steps": 500,
642
+ "stateful_callbacks": {
643
+ "TrainerControl": {
644
+ "args": {
645
+ "should_epoch_stop": false,
646
+ "should_evaluate": false,
647
+ "should_log": false,
648
+ "should_save": true,
649
+ "should_training_stop": false
650
+ },
651
+ "attributes": {}
652
+ }
653
+ },
654
+ "total_flos": 1.809069886309947e+17,
655
+ "train_batch_size": 2,
656
+ "trial_name": null,
657
+ "trial_params": null
658
+ }
dapt/checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526d6f5586cc12f8c3c2decff856ac271e872bdfd30bb3aeb82e6bca21f6e912
3
+ size 5265