Upload folder using huggingface_hub
Browse files- checkpoint-2000/README.md +204 -0
- checkpoint-2000/adapter_config.json +32 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +517 -0
- checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
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 0.7.2.dev0
|
checkpoint-2000/adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 512,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 256,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"down_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"up_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8269fc8ac200b1a02b613c536022f3500a85942512ab8a0c973cabc92dcb3f7
|
3 |
+
size 2684416208
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a443c41e494ebcf2eb6780b03969c5a2a5c965a3bfee501655c7ecc0395db4f
|
3 |
+
size 1345338004
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca4e6c6053c9f2f3d9b9c86661233aa79eacafb8baa8da6952fd2fcc0e3a44eb
|
3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:060f08e16fc6cb5f425a93304e0c1350910914c5e1c3834a68bb41682a437609
|
3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.1908211708068848,
|
3 |
+
"best_model_checkpoint": "output/mistral_squad/checkpoint-1000",
|
4 |
+
"epoch": 0.4910385465259023,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2.5e-05,
|
14 |
+
"loss": 2.1039,
|
15 |
+
"step": 25
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 5e-05,
|
20 |
+
"loss": 1.9227,
|
21 |
+
"step": 50
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 7.500000000000001e-05,
|
26 |
+
"loss": 1.8559,
|
27 |
+
"step": 75
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.02,
|
31 |
+
"learning_rate": 0.0001,
|
32 |
+
"loss": 1.8136,
|
33 |
+
"step": 100
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03,
|
37 |
+
"learning_rate": 9.937075257991442e-05,
|
38 |
+
"loss": 1.795,
|
39 |
+
"step": 125
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04,
|
43 |
+
"learning_rate": 9.874150515982885e-05,
|
44 |
+
"loss": 1.7844,
|
45 |
+
"step": 150
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.04,
|
49 |
+
"learning_rate": 9.811225773974327e-05,
|
50 |
+
"loss": 1.7486,
|
51 |
+
"step": 175
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.05,
|
55 |
+
"learning_rate": 9.74830103196577e-05,
|
56 |
+
"loss": 1.719,
|
57 |
+
"step": 200
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.06,
|
61 |
+
"learning_rate": 9.685376289957212e-05,
|
62 |
+
"loss": 1.7017,
|
63 |
+
"step": 225
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.06,
|
67 |
+
"learning_rate": 9.622451547948655e-05,
|
68 |
+
"loss": 1.6495,
|
69 |
+
"step": 250
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.07,
|
73 |
+
"learning_rate": 9.559526805940097e-05,
|
74 |
+
"loss": 1.5982,
|
75 |
+
"step": 275
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.07,
|
79 |
+
"learning_rate": 9.496602063931538e-05,
|
80 |
+
"loss": 1.5912,
|
81 |
+
"step": 300
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08,
|
85 |
+
"learning_rate": 9.43367732192298e-05,
|
86 |
+
"loss": 1.5603,
|
87 |
+
"step": 325
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.09,
|
91 |
+
"learning_rate": 9.370752579914423e-05,
|
92 |
+
"loss": 1.5453,
|
93 |
+
"step": 350
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.09,
|
97 |
+
"learning_rate": 9.307827837905865e-05,
|
98 |
+
"loss": 1.4757,
|
99 |
+
"step": 375
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.1,
|
103 |
+
"learning_rate": 9.244903095897306e-05,
|
104 |
+
"loss": 1.4421,
|
105 |
+
"step": 400
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.1,
|
109 |
+
"learning_rate": 9.18197835388875e-05,
|
110 |
+
"loss": 1.3738,
|
111 |
+
"step": 425
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.11,
|
115 |
+
"learning_rate": 9.119053611880191e-05,
|
116 |
+
"loss": 1.3607,
|
117 |
+
"step": 450
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.12,
|
121 |
+
"learning_rate": 9.056128869871634e-05,
|
122 |
+
"loss": 1.354,
|
123 |
+
"step": 475
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.12,
|
127 |
+
"learning_rate": 8.993204127863076e-05,
|
128 |
+
"loss": 1.3505,
|
129 |
+
"step": 500
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.13,
|
133 |
+
"learning_rate": 8.930279385854519e-05,
|
134 |
+
"loss": 1.3025,
|
135 |
+
"step": 525
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.14,
|
139 |
+
"learning_rate": 8.867354643845961e-05,
|
140 |
+
"loss": 1.2577,
|
141 |
+
"step": 550
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.14,
|
145 |
+
"learning_rate": 8.804429901837403e-05,
|
146 |
+
"loss": 1.3072,
|
147 |
+
"step": 575
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.15,
|
151 |
+
"learning_rate": 8.741505159828846e-05,
|
152 |
+
"loss": 1.2621,
|
153 |
+
"step": 600
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.15,
|
157 |
+
"learning_rate": 8.678580417820287e-05,
|
158 |
+
"loss": 1.213,
|
159 |
+
"step": 625
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.16,
|
163 |
+
"learning_rate": 8.615655675811729e-05,
|
164 |
+
"loss": 1.1523,
|
165 |
+
"step": 650
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.17,
|
169 |
+
"learning_rate": 8.552730933803171e-05,
|
170 |
+
"loss": 1.1324,
|
171 |
+
"step": 675
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.17,
|
175 |
+
"learning_rate": 8.489806191794614e-05,
|
176 |
+
"loss": 1.1531,
|
177 |
+
"step": 700
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.18,
|
181 |
+
"learning_rate": 8.426881449786056e-05,
|
182 |
+
"loss": 1.0632,
|
183 |
+
"step": 725
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.18,
|
187 |
+
"learning_rate": 8.363956707777499e-05,
|
188 |
+
"loss": 1.1238,
|
189 |
+
"step": 750
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.19,
|
193 |
+
"learning_rate": 8.30103196576894e-05,
|
194 |
+
"loss": 1.1197,
|
195 |
+
"step": 775
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.2,
|
199 |
+
"learning_rate": 8.238107223760383e-05,
|
200 |
+
"loss": 1.04,
|
201 |
+
"step": 800
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.2,
|
205 |
+
"learning_rate": 8.175182481751825e-05,
|
206 |
+
"loss": 1.1003,
|
207 |
+
"step": 825
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.21,
|
211 |
+
"learning_rate": 8.112257739743267e-05,
|
212 |
+
"loss": 1.0161,
|
213 |
+
"step": 850
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.21,
|
217 |
+
"learning_rate": 8.04933299773471e-05,
|
218 |
+
"loss": 0.972,
|
219 |
+
"step": 875
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.22,
|
223 |
+
"learning_rate": 7.986408255726152e-05,
|
224 |
+
"loss": 0.9713,
|
225 |
+
"step": 900
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.23,
|
229 |
+
"learning_rate": 7.923483513717595e-05,
|
230 |
+
"loss": 0.9788,
|
231 |
+
"step": 925
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.23,
|
235 |
+
"learning_rate": 7.860558771709036e-05,
|
236 |
+
"loss": 0.9189,
|
237 |
+
"step": 950
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.24,
|
241 |
+
"learning_rate": 7.79763402970048e-05,
|
242 |
+
"loss": 0.9001,
|
243 |
+
"step": 975
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.25,
|
247 |
+
"learning_rate": 7.734709287691921e-05,
|
248 |
+
"loss": 0.8809,
|
249 |
+
"step": 1000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.25,
|
253 |
+
"eval_loss": 2.1908211708068848,
|
254 |
+
"eval_runtime": 596.3037,
|
255 |
+
"eval_samples_per_second": 19.911,
|
256 |
+
"eval_steps_per_second": 0.624,
|
257 |
+
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.25,
|
261 |
+
"learning_rate": 7.671784545683363e-05,
|
262 |
+
"loss": 0.8418,
|
263 |
+
"step": 1025
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.26,
|
267 |
+
"learning_rate": 7.608859803674805e-05,
|
268 |
+
"loss": 0.8633,
|
269 |
+
"step": 1050
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.26,
|
273 |
+
"learning_rate": 7.545935061666248e-05,
|
274 |
+
"loss": 0.8767,
|
275 |
+
"step": 1075
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.27,
|
279 |
+
"learning_rate": 7.48301031965769e-05,
|
280 |
+
"loss": 0.8018,
|
281 |
+
"step": 1100
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.28,
|
285 |
+
"learning_rate": 7.420085577649131e-05,
|
286 |
+
"loss": 0.817,
|
287 |
+
"step": 1125
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.28,
|
291 |
+
"learning_rate": 7.357160835640574e-05,
|
292 |
+
"loss": 0.7738,
|
293 |
+
"step": 1150
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.29,
|
297 |
+
"learning_rate": 7.294236093632016e-05,
|
298 |
+
"loss": 0.7264,
|
299 |
+
"step": 1175
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.29,
|
303 |
+
"learning_rate": 7.231311351623459e-05,
|
304 |
+
"loss": 0.8269,
|
305 |
+
"step": 1200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.3,
|
309 |
+
"learning_rate": 7.168386609614901e-05,
|
310 |
+
"loss": 0.7176,
|
311 |
+
"step": 1225
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.31,
|
315 |
+
"learning_rate": 7.105461867606344e-05,
|
316 |
+
"loss": 0.7344,
|
317 |
+
"step": 1250
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.31,
|
321 |
+
"learning_rate": 7.042537125597786e-05,
|
322 |
+
"loss": 0.7132,
|
323 |
+
"step": 1275
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.32,
|
327 |
+
"learning_rate": 6.979612383589229e-05,
|
328 |
+
"loss": 0.6838,
|
329 |
+
"step": 1300
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.33,
|
333 |
+
"learning_rate": 6.91668764158067e-05,
|
334 |
+
"loss": 0.7343,
|
335 |
+
"step": 1325
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.33,
|
339 |
+
"learning_rate": 6.853762899572112e-05,
|
340 |
+
"loss": 0.6807,
|
341 |
+
"step": 1350
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.34,
|
345 |
+
"learning_rate": 6.790838157563554e-05,
|
346 |
+
"loss": 0.6712,
|
347 |
+
"step": 1375
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.34,
|
351 |
+
"learning_rate": 6.727913415554995e-05,
|
352 |
+
"loss": 0.6808,
|
353 |
+
"step": 1400
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.35,
|
357 |
+
"learning_rate": 6.664988673546439e-05,
|
358 |
+
"loss": 0.6305,
|
359 |
+
"step": 1425
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.36,
|
363 |
+
"learning_rate": 6.60206393153788e-05,
|
364 |
+
"loss": 0.645,
|
365 |
+
"step": 1450
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.36,
|
369 |
+
"learning_rate": 6.539139189529323e-05,
|
370 |
+
"loss": 0.6229,
|
371 |
+
"step": 1475
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.37,
|
375 |
+
"learning_rate": 6.476214447520765e-05,
|
376 |
+
"loss": 0.5976,
|
377 |
+
"step": 1500
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.37,
|
381 |
+
"learning_rate": 6.413289705512208e-05,
|
382 |
+
"loss": 0.6214,
|
383 |
+
"step": 1525
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.38,
|
387 |
+
"learning_rate": 6.35036496350365e-05,
|
388 |
+
"loss": 0.5981,
|
389 |
+
"step": 1550
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.39,
|
393 |
+
"learning_rate": 6.287440221495093e-05,
|
394 |
+
"loss": 0.564,
|
395 |
+
"step": 1575
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.39,
|
399 |
+
"learning_rate": 6.224515479486535e-05,
|
400 |
+
"loss": 0.5757,
|
401 |
+
"step": 1600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.4,
|
405 |
+
"learning_rate": 6.161590737477976e-05,
|
406 |
+
"loss": 0.5611,
|
407 |
+
"step": 1625
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.41,
|
411 |
+
"learning_rate": 6.0986659954694194e-05,
|
412 |
+
"loss": 0.5462,
|
413 |
+
"step": 1650
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.41,
|
417 |
+
"learning_rate": 6.035741253460862e-05,
|
418 |
+
"loss": 0.5172,
|
419 |
+
"step": 1675
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.42,
|
423 |
+
"learning_rate": 5.9728165114523035e-05,
|
424 |
+
"loss": 0.5087,
|
425 |
+
"step": 1700
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.42,
|
429 |
+
"learning_rate": 5.909891769443746e-05,
|
430 |
+
"loss": 0.5148,
|
431 |
+
"step": 1725
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.43,
|
435 |
+
"learning_rate": 5.8469670274351876e-05,
|
436 |
+
"loss": 0.5247,
|
437 |
+
"step": 1750
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.44,
|
441 |
+
"learning_rate": 5.784042285426629e-05,
|
442 |
+
"loss": 0.5356,
|
443 |
+
"step": 1775
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.44,
|
447 |
+
"learning_rate": 5.721117543418072e-05,
|
448 |
+
"loss": 0.4837,
|
449 |
+
"step": 1800
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.45,
|
453 |
+
"learning_rate": 5.658192801409514e-05,
|
454 |
+
"loss": 0.533,
|
455 |
+
"step": 1825
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.45,
|
459 |
+
"learning_rate": 5.5952680594009565e-05,
|
460 |
+
"loss": 0.485,
|
461 |
+
"step": 1850
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.46,
|
465 |
+
"learning_rate": 5.532343317392399e-05,
|
466 |
+
"loss": 0.4728,
|
467 |
+
"step": 1875
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.47,
|
471 |
+
"learning_rate": 5.469418575383841e-05,
|
472 |
+
"loss": 0.4873,
|
473 |
+
"step": 1900
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.47,
|
477 |
+
"learning_rate": 5.406493833375284e-05,
|
478 |
+
"loss": 0.4693,
|
479 |
+
"step": 1925
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.48,
|
483 |
+
"learning_rate": 5.343569091366726e-05,
|
484 |
+
"loss": 0.4951,
|
485 |
+
"step": 1950
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.48,
|
489 |
+
"learning_rate": 5.280644349358168e-05,
|
490 |
+
"loss": 0.4445,
|
491 |
+
"step": 1975
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.49,
|
495 |
+
"learning_rate": 5.21771960734961e-05,
|
496 |
+
"loss": 0.4423,
|
497 |
+
"step": 2000
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.49,
|
501 |
+
"eval_loss": 2.3274576663970947,
|
502 |
+
"eval_runtime": 596.4629,
|
503 |
+
"eval_samples_per_second": 19.906,
|
504 |
+
"eval_steps_per_second": 0.624,
|
505 |
+
"step": 2000
|
506 |
+
}
|
507 |
+
],
|
508 |
+
"logging_steps": 25,
|
509 |
+
"max_steps": 4073,
|
510 |
+
"num_input_tokens_seen": 0,
|
511 |
+
"num_train_epochs": 1,
|
512 |
+
"save_steps": 1000,
|
513 |
+
"total_flos": 7.64977027743744e+17,
|
514 |
+
"train_batch_size": 32,
|
515 |
+
"trial_name": null,
|
516 |
+
"trial_params": null
|
517 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff6a825d8ea4b1626b273bb958f42ff6bf9d9b91b276eed2c5bb04dbe7000b4
|
3 |
+
size 4664
|