Training in progress, step 116, checkpoint
Browse files- checkpoint-116/README.md +204 -0
- checkpoint-116/adapter_config.json +40 -0
- checkpoint-116/adapter_model.safetensors +3 -0
- checkpoint-116/optimizer.pt +3 -0
- checkpoint-116/rng_state.pth +3 -0
- checkpoint-116/scheduler.pt +3 -0
- checkpoint-116/trainer_state.json +184 -0
- checkpoint-116/training_args.bin +3 -0
checkpoint-116/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: openai/clip-vit-base-patch32
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.10.0
|
checkpoint-116/adapter_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "CLIPDetails",
|
5 |
+
"parent_library": "clipdetails.models.clipdetails"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "openai/clip-vit-base-patch32",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 8,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"loss_balance"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 8,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"text_projection",
|
29 |
+
"fc1",
|
30 |
+
"q_proj",
|
31 |
+
"out_proj",
|
32 |
+
"v_proj",
|
33 |
+
"k_proj",
|
34 |
+
"fc2",
|
35 |
+
"visual_projection"
|
36 |
+
],
|
37 |
+
"task_type": null,
|
38 |
+
"use_dora": false,
|
39 |
+
"use_rslora": false
|
40 |
+
}
|
checkpoint-116/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c20af6b3fe10d4509efd8b3bdb13aba164a0ea00c75a2d9ea427fa20ceb16f9c
|
3 |
+
size 8962304
|
checkpoint-116/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491bbdad44bbceac5ebef1a3453d85cc003fe9e331e97ae8f78c9d8b498da0b6
|
3 |
+
size 18087162
|
checkpoint-116/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee29b5f560f8f9dc8e0f08328715f8587a023377871f0ca6233f166af5cef7ad
|
3 |
+
size 14244
|
checkpoint-116/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af3633cb0f8b8ce21355952fa00bc5edd57071dceafbcb1b0da971ca5341bb6b
|
3 |
+
size 1064
|
checkpoint-116/trainer_state.json
ADDED
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.7786831855773926,
|
3 |
+
"best_model_checkpoint": "$../logs/03-08-2024T09-55-11-detailclip-b32/checkpoint-116",
|
4 |
+
"epoch": 1.008695652173913,
|
5 |
+
"eval_steps": 58,
|
6 |
+
"global_step": 116,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05217391304347826,
|
13 |
+
"grad_norm": 2.7094666957855225,
|
14 |
+
"learning_rate": 1.2e-05,
|
15 |
+
"loss": 0.7099,
|
16 |
+
"step": 6
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.10434782608695652,
|
20 |
+
"grad_norm": 2.6887893676757812,
|
21 |
+
"learning_rate": 2.4e-05,
|
22 |
+
"loss": 0.6948,
|
23 |
+
"step": 12
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1565217391304348,
|
27 |
+
"grad_norm": 2.56785249710083,
|
28 |
+
"learning_rate": 3.6e-05,
|
29 |
+
"loss": 0.7276,
|
30 |
+
"step": 18
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.20869565217391303,
|
34 |
+
"grad_norm": 2.413269281387329,
|
35 |
+
"learning_rate": 4.8e-05,
|
36 |
+
"loss": 0.5937,
|
37 |
+
"step": 24
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2608695652173913,
|
41 |
+
"grad_norm": 2.0822973251342773,
|
42 |
+
"learning_rate": 6e-05,
|
43 |
+
"loss": 0.4702,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3130434782608696,
|
48 |
+
"grad_norm": 1.9383469820022583,
|
49 |
+
"learning_rate": 7.2e-05,
|
50 |
+
"loss": 0.4579,
|
51 |
+
"step": 36
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3652173913043478,
|
55 |
+
"grad_norm": 1.6925252676010132,
|
56 |
+
"learning_rate": 8.4e-05,
|
57 |
+
"loss": 0.4028,
|
58 |
+
"step": 42
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.41739130434782606,
|
62 |
+
"grad_norm": 1.5693070888519287,
|
63 |
+
"learning_rate": 9.6e-05,
|
64 |
+
"loss": 0.3466,
|
65 |
+
"step": 48
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.46956521739130436,
|
69 |
+
"grad_norm": 1.8624712228775024,
|
70 |
+
"learning_rate": 9.999673735634258e-05,
|
71 |
+
"loss": 0.31,
|
72 |
+
"step": 54
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5043478260869565,
|
76 |
+
"eval_loss": 1.88290536403656,
|
77 |
+
"eval_runtime": 371.0087,
|
78 |
+
"eval_samples_per_second": 6.021,
|
79 |
+
"eval_steps_per_second": 0.049,
|
80 |
+
"step": 58
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.5043478260869565,
|
84 |
+
"neg_increments": 0.40031376906933136,
|
85 |
+
"positive_increments": 0.6000771337979885,
|
86 |
+
"rate_increments": 0.60599292530573,
|
87 |
+
"step": 58
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.5217391304347826,
|
91 |
+
"grad_norm": 1.565119743347168,
|
92 |
+
"learning_rate": 9.997960964140947e-05,
|
93 |
+
"loss": 0.289,
|
94 |
+
"step": 60
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.5739130434782609,
|
98 |
+
"grad_norm": 1.695056438446045,
|
99 |
+
"learning_rate": 9.994780621691156e-05,
|
100 |
+
"loss": 0.2486,
|
101 |
+
"step": 66
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.6260869565217392,
|
105 |
+
"grad_norm": 1.3525909185409546,
|
106 |
+
"learning_rate": 9.990133642141359e-05,
|
107 |
+
"loss": 0.2476,
|
108 |
+
"step": 72
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.6782608695652174,
|
112 |
+
"grad_norm": 1.7046144008636475,
|
113 |
+
"learning_rate": 9.984021390002458e-05,
|
114 |
+
"loss": 0.2677,
|
115 |
+
"step": 78
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.7304347826086957,
|
119 |
+
"grad_norm": 1.199271559715271,
|
120 |
+
"learning_rate": 9.976445660039118e-05,
|
121 |
+
"loss": 0.2425,
|
122 |
+
"step": 84
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.782608695652174,
|
126 |
+
"grad_norm": 1.1520024538040161,
|
127 |
+
"learning_rate": 9.967408676742751e-05,
|
128 |
+
"loss": 0.2444,
|
129 |
+
"step": 90
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.8347826086956521,
|
133 |
+
"grad_norm": 1.023667335510254,
|
134 |
+
"learning_rate": 9.956913093678348e-05,
|
135 |
+
"loss": 0.2127,
|
136 |
+
"step": 96
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.8869565217391304,
|
140 |
+
"grad_norm": 1.418879747390747,
|
141 |
+
"learning_rate": 9.944961992705288e-05,
|
142 |
+
"loss": 0.2375,
|
143 |
+
"step": 102
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.9391304347826087,
|
147 |
+
"grad_norm": 1.6150606870651245,
|
148 |
+
"learning_rate": 9.931558883072403e-05,
|
149 |
+
"loss": 0.2214,
|
150 |
+
"step": 108
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.991304347826087,
|
154 |
+
"grad_norm": 1.3231348991394043,
|
155 |
+
"learning_rate": 9.916707700387547e-05,
|
156 |
+
"loss": 0.2283,
|
157 |
+
"step": 114
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 1.008695652173913,
|
161 |
+
"eval_loss": 1.7786831855773926,
|
162 |
+
"eval_runtime": 352.6788,
|
163 |
+
"eval_samples_per_second": 6.334,
|
164 |
+
"eval_steps_per_second": 0.051,
|
165 |
+
"step": 116
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.008695652173913,
|
169 |
+
"neg_increments": 0.38078110707552626,
|
170 |
+
"positive_increments": 0.6381213280123575,
|
171 |
+
"rate_increments": 0.6405809892973509,
|
172 |
+
"step": 116
|
173 |
+
}
|
174 |
+
],
|
175 |
+
"logging_steps": 6,
|
176 |
+
"max_steps": 1150,
|
177 |
+
"num_input_tokens_seen": 0,
|
178 |
+
"num_train_epochs": 10,
|
179 |
+
"save_steps": 58,
|
180 |
+
"total_flos": 2623924029399750.0,
|
181 |
+
"train_batch_size": 128,
|
182 |
+
"trial_name": null,
|
183 |
+
"trial_params": null
|
184 |
+
}
|
checkpoint-116/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc11c210b8785d6a432d54f322453fc948eaea9f9ea9d9de61c3f5aeeb982050
|
3 |
+
size 5112
|