momergul commited on
Commit
e88b58f
1 Parent(s): 93e2cad

Upload 432 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. r0_full/run/checkpoints/acc/README.md +202 -0
  2. r0_full/run/checkpoints/acc/adapter_config.json +29 -0
  3. r0_full/run/checkpoints/acc/adapter_model.safetensors +3 -0
  4. r0_full/run/checkpoints/acc/best_optimizer.pt +3 -0
  5. r0_full/run/checkpoints/acc/best_scheduler.pt +3 -0
  6. r0_full/run/checkpoints/acc/saved_metrics.pth +3 -0
  7. r0_full/run/logging/epoch_0_train_metrics.pth +3 -0
  8. r0_full/run/logging/epoch_0_val_metrics.pth +3 -0
  9. r0_full/run/logging/epoch_10_train_metrics.pth +3 -0
  10. r0_full/run/logging/epoch_10_val_metrics.pth +3 -0
  11. r0_full/run/logging/epoch_11_train_metrics.pth +3 -0
  12. r0_full/run/logging/epoch_11_val_metrics.pth +3 -0
  13. r0_full/run/logging/epoch_12_train_metrics.pth +3 -0
  14. r0_full/run/logging/epoch_12_val_metrics.pth +3 -0
  15. r0_full/run/logging/epoch_1_train_metrics.pth +3 -0
  16. r0_full/run/logging/epoch_1_val_metrics.pth +3 -0
  17. r0_full/run/logging/epoch_2_train_metrics.pth +3 -0
  18. r0_full/run/logging/epoch_2_val_metrics.pth +3 -0
  19. r0_full/run/logging/epoch_3_train_metrics.pth +3 -0
  20. r0_full/run/logging/epoch_3_val_metrics.pth +3 -0
  21. r0_full/run/logging/epoch_4_train_metrics.pth +3 -0
  22. r0_full/run/logging/epoch_4_val_metrics.pth +3 -0
  23. r0_full/run/logging/epoch_5_train_metrics.pth +3 -0
  24. r0_full/run/logging/epoch_5_val_metrics.pth +3 -0
  25. r0_full/run/logging/epoch_6_train_metrics.pth +3 -0
  26. r0_full/run/logging/epoch_6_val_metrics.pth +3 -0
  27. r0_full/run/logging/epoch_7_train_metrics.pth +3 -0
  28. r0_full/run/logging/epoch_7_val_metrics.pth +3 -0
  29. r0_full/run/logging/epoch_8_train_metrics.pth +3 -0
  30. r0_full/run/logging/epoch_8_val_metrics.pth +3 -0
  31. r0_full/run/logging/epoch_9_train_metrics.pth +3 -0
  32. r0_full/run/logging/epoch_9_val_metrics.pth +3 -0
  33. r0_full/run/logging/exp_cfg.yaml +62 -0
  34. r0_no_ji/run/checkpoints/acc/README.md +202 -0
  35. r0_no_ji/run/checkpoints/acc/adapter_config.json +29 -0
  36. r0_no_ji/run/checkpoints/acc/adapter_model.safetensors +3 -0
  37. r0_no_ji/run/checkpoints/acc/best_optimizer.pt +3 -0
  38. r0_no_ji/run/checkpoints/acc/best_scheduler.pt +3 -0
  39. r0_no_ji/run/checkpoints/acc/saved_metrics.pth +3 -0
  40. r0_no_ji/run/logging/epoch_0_train_metrics.pth +3 -0
  41. r0_no_ji/run/logging/epoch_0_val_metrics.pth +3 -0
  42. r0_no_ji/run/logging/epoch_10_train_metrics.pth +3 -0
  43. r0_no_ji/run/logging/epoch_10_val_metrics.pth +3 -0
  44. r0_no_ji/run/logging/epoch_11_train_metrics.pth +3 -0
  45. r0_no_ji/run/logging/epoch_11_val_metrics.pth +3 -0
  46. r0_no_ji/run/logging/epoch_12_train_metrics.pth +3 -0
  47. r0_no_ji/run/logging/epoch_12_val_metrics.pth +3 -0
  48. r0_no_ji/run/logging/epoch_13_train_metrics.pth +3 -0
  49. r0_no_ji/run/logging/epoch_13_val_metrics.pth +3 -0
  50. r0_no_ji/run/logging/epoch_14_train_metrics.pth +3 -0
r0_full/run/checkpoints/acc/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: HuggingFaceM4/idefics2-8b
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
r0_full/run/checkpoints/acc/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Idefics2ForConditionalGeneration",
5
+ "parent_library": "transformers.models.idefics2.modeling_idefics2"
6
+ },
7
+ "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": "(.*(vision_model|modality_projection|perceiver_resampler).*(out_proj|fc1|fc2|down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$)|(.*(k_proj|q_proj|v_proj).*$)",
26
+ "task_type": null,
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
r0_full/run/checkpoints/acc/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d023b55d9d4642dabc2fa070ac45d29e75596408b54a37190667467432cafcac
3
+ size 45771496
r0_full/run/checkpoints/acc/best_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9befa6f3041c71a73a61664b0060dd600d6ce1d58a0d699aa82d8b9d6cc963
3
+ size 91855438
r0_full/run/checkpoints/acc/best_scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64a691c6993fec11fb1484fbc2db955ce092b96ef7c35a038fb0756354926cd
3
+ size 1084
r0_full/run/checkpoints/acc/saved_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0563b720d0a3c5c852603683dedf11945686ad74408aa3089542112afd963961
3
+ size 1208
r0_full/run/logging/epoch_0_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0644574bbd56621f65dbbdbf175d93fabd6675ca14ed192a72ba2361fea53d5
3
+ size 1304
r0_full/run/logging/epoch_0_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a223a06a0e8fa0631a44c59df301d2fa4c71396909112c732eddf4b7e79d8798
3
+ size 1360
r0_full/run/logging/epoch_10_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7efb0e1717789d7f47c39f1097b80392522b434f427750a47d9cc0c038235b
3
+ size 1372
r0_full/run/logging/epoch_10_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2e0e7456ec0d42bad5fcffef505114c5b39d6116d993494324d9dfe53f1924
3
+ size 1364
r0_full/run/logging/epoch_11_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6322bccb60963c3fdb82a5bd0c0fc217b268b8da4114da058cc2f45ee4bae94
3
+ size 1372
r0_full/run/logging/epoch_11_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cf996968b473736b33fe49cc4d00dbb7eb486adb8832384b13c79764b85044
3
+ size 1364
r0_full/run/logging/epoch_12_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6df0d274ae212c414a339497f89874f21ece4be908920254e00533e84e05834
3
+ size 1372
r0_full/run/logging/epoch_12_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068aa2d20e190525108bde73f327df4a742bdda219983a832afc5b70c6ddd5a8
3
+ size 1364
r0_full/run/logging/epoch_1_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95bb69a41dac5c0c4d1040a2515efb333e647ae09db072f5fca7250009b11d4
3
+ size 1304
r0_full/run/logging/epoch_1_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d634f030d0362824b84dbf0e2c17c6dd32fce7dc600b55e695d5da11cafe8e7
3
+ size 1360
r0_full/run/logging/epoch_2_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eeef3179763c22891f9c76e7dea5b42be064568ff5d3579fb94d10c7a92fa09
3
+ size 1304
r0_full/run/logging/epoch_2_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9486129408fef603bd1d4551a732fef8603300593a57cd8a2bfd3586769c22a5
3
+ size 1360
r0_full/run/logging/epoch_3_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51715b87284bc30ba0512cb4c3403c75f0cba4e484344b825ce64855324863f
3
+ size 1304
r0_full/run/logging/epoch_3_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab987bce9c4667e7686042f874c8f3dfe66e17be066d844e928799a1f8f2674
3
+ size 1360
r0_full/run/logging/epoch_4_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69424abb4cf5dfede751827bf78be45e27e578cd6b85f635763c584e76d9111
3
+ size 1304
r0_full/run/logging/epoch_4_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff95f67f1b5b0abac2ea2e6c678cabe195c4343a379be5626c7c96d3e6ecbc6
3
+ size 1360
r0_full/run/logging/epoch_5_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0a1ce65f98e6628143a511160da8e16153bb414b80d1a9d6d859ebf4034839
3
+ size 1304
r0_full/run/logging/epoch_5_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94962b598a8db586aae684ae42571a0977ff5cb67b1feb8ddd4882ed6def9949
3
+ size 1360
r0_full/run/logging/epoch_6_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb22ee7aadf3f6f23a62aca798d8bdc5ab2fa5f218a7161a64c9ccdcb64e44d2
3
+ size 1304
r0_full/run/logging/epoch_6_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47559d024e0f78b0711a3d9f300fa2ae6cc0f2a458d56514a6e3f107c1ce427
3
+ size 1360
r0_full/run/logging/epoch_7_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e447f121c61d82318ce9234997bf3930866f4fa694c9f0d02c5a28a07249a5cd
3
+ size 1304
r0_full/run/logging/epoch_7_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf2e0dcf1d8baaa667d6e1454dd8e90f039af53bd8d1cb7c3690a3bb2fe6be2
3
+ size 1360
r0_full/run/logging/epoch_8_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a680166cfd144c26895e6fae889a0a69b6ad4c29c866fda59d79c32091a7ff39
3
+ size 1304
r0_full/run/logging/epoch_8_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4f0ee44ced703b7f0e78a33a07c1606b965418079819247c673b0ed24b250c
3
+ size 1360
r0_full/run/logging/epoch_9_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0426d41620491b9738568a334362088bc3a35474c3262f47804c30d3501499ac
3
+ size 1304
r0_full/run/logging/epoch_9_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12233438c63c43840ec7ed37a4f05442a112ea7fa66b278b48437a70f54aa175
3
+ size 1360
r0_full/run/logging/exp_cfg.yaml ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ anno_len_threshold: 40
2
+ base_folder: /home/mog29/compgen_saved_files/experiments/joint_training
3
+ batch_size: 2
4
+ checkpoint_dir: /home/mog29/compgen_saved_files/experiments/joint_training/r1_full/run_i2_half_seed_run/checkpoints
5
+ comprehension_prompt: verbose_instruction
6
+ context_size: 10
7
+ data_dir: /home/mog29/compgen_saved_files/kilogram/dataset
8
+ deployment_round: 1
9
+ evaluation_type: joint
10
+ expdir: /home/mog29/compgen_saved_files/experiments/joint_training/r1_full/run_i2_half_seed_run
11
+ from_scratch: true
12
+ generation_prompt: information_after
13
+ gradient_accumulation_steps: 32
14
+ gradient_clip_norm: 1
15
+ img_dir: /home/mog29/compgen_saved_files/kilogram/dataset/square-black-imgs
16
+ ips_clip: 5
17
+ learning_rate: 0.0001
18
+ listener_filter: ''
19
+ listener_lambda: 0.5
20
+ load_from_checkpoint: false
21
+ logdir: /home/mog29/compgen_saved_files/experiments/joint_training/r1_full/run_i2_half_seed_run/logging
22
+ lora_dropout: 0.05
23
+ lora_r: 16
24
+ lora_subset: vision_resampler
25
+ max_steps: 25
26
+ model_family_name: full
27
+ n_epochs: 15
28
+ name: joint and multitask training defaults
29
+ name_suffix: i2_half_seed_run
30
+ no_lora: false
31
+ no_shuffling: false
32
+ noise_filter: ''
33
+ num_samples: 10
34
+ num_training_steps: 15000
35
+ num_warmup_steps: 0
36
+ num_workers: 4
37
+ only_seed: true
38
+ past_checkpoint_dir: /home/mog29/compgen_saved_files/experiments/joint_training/r0_full/run/checkpoints
39
+ past_logdir: /home/mog29/compgen_saved_files/experiments/joint_training/r0_full/run/logging
40
+ past_name_suffix: ''
41
+ past_round: -1
42
+ patience_cutoff: 5
43
+ ref_strat: no_ips_for_pos
44
+ repetition_penalty: 1
45
+ replacement_family_name: ''
46
+ sampling_type: nucleus
47
+ save_each_epoch: true
48
+ seed: 636171
49
+ shared_parameters: true
50
+ speaker_filter: ''
51
+ speaker_lambda: 0.5
52
+ split_dir: /home/mog29/compgen_saved_files/split_info/
53
+ temperature: 1.0
54
+ test_batch_size: 4
55
+ top_k: 20
56
+ top_p: 0.8
57
+ training_type: multitask
58
+ use_separate_dataloaders: false
59
+ use_wandb: true
60
+ wandb_experiment_name: r0_idefics2_half_seed_run
61
+ wandb_project_name: tangram_continual_learning_final
62
+ weight_decay: 0.1
r0_no_ji/run/checkpoints/acc/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: HuggingFaceM4/idefics2-8b
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
r0_no_ji/run/checkpoints/acc/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Idefics2ForConditionalGeneration",
5
+ "parent_library": "transformers.models.idefics2.modeling_idefics2"
6
+ },
7
+ "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": "(.*(vision_model|modality_projection|perceiver_resampler).*(out_proj|fc1|fc2|down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$)|(.*(k_proj|q_proj|v_proj).*$)",
26
+ "task_type": null,
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
r0_no_ji/run/checkpoints/acc/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862a2297469be301efeb32495428965e37fcf47ceabf27e4554de2badba5c6e9
3
+ size 45771496
r0_no_ji/run/checkpoints/acc/best_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4fe1170d858d50eb3576104f3c0aa20f74f4b9ef6283cb9d1e0280c55e09a5
3
+ size 91855438
r0_no_ji/run/checkpoints/acc/best_scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ac8017b9b42b70c4a55b9611785f5cfde9f8ed5f522088c445b6cbca218bea
3
+ size 1084
r0_no_ji/run/checkpoints/acc/saved_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57f7f289540f6e2aa16d75339a8b439da3813dd7467234a519558cf87f5ab66
3
+ size 1016
r0_no_ji/run/logging/epoch_0_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2097d0fe0dbb9ba891721785112c4782198b5054021d8f122ae860c56cb7cb
3
+ size 1304
r0_no_ji/run/logging/epoch_0_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef5fff0a12fd5752bbd668efc045d249727a8d032a106139c1dd7ced07c8d11
3
+ size 1168
r0_no_ji/run/logging/epoch_10_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a78e8393ec1c3a1152b3f8c88e1dd02dcf2908151bcdc93a83e66a002d4bd18
3
+ size 1372
r0_no_ji/run/logging/epoch_10_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3e8d4166ca75a805a88ef92d7fb989d33bd2732e8a50583a0a6933874f654f
3
+ size 1172
r0_no_ji/run/logging/epoch_11_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05506fbca16d2f9be7ac44e6932a73060f33ec6391bca106f5aa98279120e12a
3
+ size 1372
r0_no_ji/run/logging/epoch_11_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989f7d5f063df7405767b5ebe900868899808f30cd7e0485e008de9e3b2f966c
3
+ size 1172
r0_no_ji/run/logging/epoch_12_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d612b0a72d415f09f1667c4cd1478a9730133cc8d56ff309e3476019cec79ed
3
+ size 1372
r0_no_ji/run/logging/epoch_12_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6828ca6f919834d17ca141760a4f548b5a7f7e5fb2b085ebf719d622f4e466
3
+ size 1172
r0_no_ji/run/logging/epoch_13_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a5a1c905f0e6876d6c200d6a35d2c1701b39fbea038e344f0287dba528430b
3
+ size 1372
r0_no_ji/run/logging/epoch_13_val_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb47cc85a160012bcf6c6995ebb2c44012d2a09613f720ea749f11e1aa638430
3
+ size 1172
r0_no_ji/run/logging/epoch_14_train_metrics.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3991d41558369b53de69e2be77ccc4e23c8e5b774993eaf5ee980affbe29ad
3
+ size 1372