Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +465 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
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 0.8.2
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
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": 256,
|
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": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"down_proj",
|
24 |
+
"up_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7bbca660990c92ce968c42bc9b09838ec5731619c159f2ac28f718547682fe3
|
3 |
+
size 671149168
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b7e116fbb24a997af5a6b6a8da8096ecdcfd39a747116c9ef526e0fe1c6444d
|
3 |
+
size 1342555602
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93999d5758488ec12683254ba7882b1bb64250d9ed0be7b75005c81b3e98d21c
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca97f12665ba2ec7d2c9ba1872471ab8ddc2efe3256c81ab98d8f1667b9802f3
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3,
|
5 |
+
"eval_steps": 2000,
|
6 |
+
"global_step": 6000,
|
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 |
+
"grad_norm": 12.253900527954102,
|
14 |
+
"learning_rate": 9.8e-07,
|
15 |
+
"loss": 0.3335,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01,
|
20 |
+
"grad_norm": 9.193947792053223,
|
21 |
+
"learning_rate": 9.9010101010101e-07,
|
22 |
+
"loss": 0.2105,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 5.168125152587891,
|
28 |
+
"learning_rate": 9.8e-07,
|
29 |
+
"loss": 0.1618,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02,
|
34 |
+
"grad_norm": 2.163803815841675,
|
35 |
+
"learning_rate": 9.698989898989898e-07,
|
36 |
+
"loss": 0.1418,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.03,
|
41 |
+
"grad_norm": 10.751598358154297,
|
42 |
+
"learning_rate": 9.597979797979797e-07,
|
43 |
+
"loss": 0.1215,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"grad_norm": 7.5342793464660645,
|
49 |
+
"learning_rate": 9.496969696969696e-07,
|
50 |
+
"loss": 0.1142,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04,
|
55 |
+
"grad_norm": 8.430835723876953,
|
56 |
+
"learning_rate": 9.395959595959596e-07,
|
57 |
+
"loss": 0.121,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04,
|
62 |
+
"grad_norm": 1.8440964221954346,
|
63 |
+
"learning_rate": 9.295959595959596e-07,
|
64 |
+
"loss": 0.0969,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04,
|
69 |
+
"grad_norm": 2.699073553085327,
|
70 |
+
"learning_rate": 9.194949494949495e-07,
|
71 |
+
"loss": 0.1024,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.05,
|
76 |
+
"grad_norm": 11.251789093017578,
|
77 |
+
"learning_rate": 9.093939393939394e-07,
|
78 |
+
"loss": 0.0899,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.06,
|
83 |
+
"grad_norm": 7.728929042816162,
|
84 |
+
"learning_rate": 8.992929292929292e-07,
|
85 |
+
"loss": 0.0837,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.06,
|
90 |
+
"grad_norm": 1.7401416301727295,
|
91 |
+
"learning_rate": 8.891919191919191e-07,
|
92 |
+
"loss": 0.0914,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"grad_norm": 3.5504443645477295,
|
98 |
+
"learning_rate": 8.790909090909091e-07,
|
99 |
+
"loss": 0.0754,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07,
|
104 |
+
"grad_norm": 5.9004316329956055,
|
105 |
+
"learning_rate": 8.68989898989899e-07,
|
106 |
+
"loss": 0.0791,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.07,
|
111 |
+
"grad_norm": 2.9171862602233887,
|
112 |
+
"learning_rate": 8.588888888888888e-07,
|
113 |
+
"loss": 0.0866,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.08,
|
118 |
+
"grad_norm": 5.907050132751465,
|
119 |
+
"learning_rate": 8.487878787878787e-07,
|
120 |
+
"loss": 0.0768,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.09,
|
125 |
+
"grad_norm": 4.856807708740234,
|
126 |
+
"learning_rate": 8.386868686868687e-07,
|
127 |
+
"loss": 0.0745,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.09,
|
132 |
+
"grad_norm": 2.4457929134368896,
|
133 |
+
"learning_rate": 8.285858585858585e-07,
|
134 |
+
"loss": 0.0808,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.1,
|
139 |
+
"grad_norm": 3.084287643432617,
|
140 |
+
"learning_rate": 8.184848484848484e-07,
|
141 |
+
"loss": 0.0743,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.1,
|
146 |
+
"grad_norm": 2.936805486679077,
|
147 |
+
"learning_rate": 8.083838383838384e-07,
|
148 |
+
"loss": 0.0675,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.1,
|
153 |
+
"eval_loss": 0.07925247400999069,
|
154 |
+
"eval_runtime": 204.8299,
|
155 |
+
"eval_samples_per_second": 4.882,
|
156 |
+
"eval_steps_per_second": 1.221,
|
157 |
+
"step": 2000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.1,
|
161 |
+
"grad_norm": 13.029026985168457,
|
162 |
+
"learning_rate": 7.982828282828282e-07,
|
163 |
+
"loss": 0.0681,
|
164 |
+
"step": 2100
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.11,
|
168 |
+
"grad_norm": 10.308150291442871,
|
169 |
+
"learning_rate": 7.881818181818182e-07,
|
170 |
+
"loss": 0.0798,
|
171 |
+
"step": 2200
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.12,
|
175 |
+
"grad_norm": 5.64780330657959,
|
176 |
+
"learning_rate": 7.78080808080808e-07,
|
177 |
+
"loss": 0.0648,
|
178 |
+
"step": 2300
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.12,
|
182 |
+
"grad_norm": 6.982935905456543,
|
183 |
+
"learning_rate": 7.679797979797979e-07,
|
184 |
+
"loss": 0.0731,
|
185 |
+
"step": 2400
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.12,
|
189 |
+
"grad_norm": 3.5423080921173096,
|
190 |
+
"learning_rate": 7.578787878787879e-07,
|
191 |
+
"loss": 0.0817,
|
192 |
+
"step": 2500
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.13,
|
196 |
+
"grad_norm": 3.585963249206543,
|
197 |
+
"learning_rate": 7.477777777777778e-07,
|
198 |
+
"loss": 0.072,
|
199 |
+
"step": 2600
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.14,
|
203 |
+
"grad_norm": 7.086956977844238,
|
204 |
+
"learning_rate": 7.376767676767676e-07,
|
205 |
+
"loss": 0.0577,
|
206 |
+
"step": 2700
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.14,
|
210 |
+
"grad_norm": 4.985733509063721,
|
211 |
+
"learning_rate": 7.275757575757575e-07,
|
212 |
+
"loss": 0.0672,
|
213 |
+
"step": 2800
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.14,
|
217 |
+
"grad_norm": 1.4518052339553833,
|
218 |
+
"learning_rate": 7.174747474747475e-07,
|
219 |
+
"loss": 0.0616,
|
220 |
+
"step": 2900
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.15,
|
224 |
+
"grad_norm": 5.120323657989502,
|
225 |
+
"learning_rate": 7.073737373737373e-07,
|
226 |
+
"loss": 0.0625,
|
227 |
+
"step": 3000
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.15,
|
231 |
+
"grad_norm": 1.0982943773269653,
|
232 |
+
"learning_rate": 6.972727272727273e-07,
|
233 |
+
"loss": 0.0666,
|
234 |
+
"step": 3100
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.16,
|
238 |
+
"grad_norm": 1.8519880771636963,
|
239 |
+
"learning_rate": 6.871717171717171e-07,
|
240 |
+
"loss": 0.0786,
|
241 |
+
"step": 3200
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.17,
|
245 |
+
"grad_norm": 3.394327163696289,
|
246 |
+
"learning_rate": 6.77070707070707e-07,
|
247 |
+
"loss": 0.0786,
|
248 |
+
"step": 3300
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.17,
|
252 |
+
"grad_norm": 9.026866912841797,
|
253 |
+
"learning_rate": 6.66969696969697e-07,
|
254 |
+
"loss": 0.0677,
|
255 |
+
"step": 3400
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.17,
|
259 |
+
"grad_norm": 3.718776226043701,
|
260 |
+
"learning_rate": 6.568686868686868e-07,
|
261 |
+
"loss": 0.0576,
|
262 |
+
"step": 3500
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.18,
|
266 |
+
"grad_norm": 0.7873659729957581,
|
267 |
+
"learning_rate": 6.467676767676767e-07,
|
268 |
+
"loss": 0.0559,
|
269 |
+
"step": 3600
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.18,
|
273 |
+
"grad_norm": 5.039899826049805,
|
274 |
+
"learning_rate": 6.366666666666667e-07,
|
275 |
+
"loss": 0.0668,
|
276 |
+
"step": 3700
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.19,
|
280 |
+
"grad_norm": 2.4250056743621826,
|
281 |
+
"learning_rate": 6.266666666666667e-07,
|
282 |
+
"loss": 0.0524,
|
283 |
+
"step": 3800
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.2,
|
287 |
+
"grad_norm": 7.657347202301025,
|
288 |
+
"learning_rate": 6.165656565656565e-07,
|
289 |
+
"loss": 0.0665,
|
290 |
+
"step": 3900
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.2,
|
294 |
+
"grad_norm": 3.9768455028533936,
|
295 |
+
"learning_rate": 6.064646464646465e-07,
|
296 |
+
"loss": 0.0649,
|
297 |
+
"step": 4000
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.2,
|
301 |
+
"eval_loss": 0.06388480961322784,
|
302 |
+
"eval_runtime": 200.3994,
|
303 |
+
"eval_samples_per_second": 4.99,
|
304 |
+
"eval_steps_per_second": 1.248,
|
305 |
+
"step": 4000
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.2,
|
309 |
+
"grad_norm": 6.998288154602051,
|
310 |
+
"learning_rate": 5.963636363636363e-07,
|
311 |
+
"loss": 0.0488,
|
312 |
+
"step": 4100
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.21,
|
316 |
+
"grad_norm": 2.007672071456909,
|
317 |
+
"learning_rate": 5.862626262626262e-07,
|
318 |
+
"loss": 0.0683,
|
319 |
+
"step": 4200
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.21,
|
323 |
+
"grad_norm": 0.5769347548484802,
|
324 |
+
"learning_rate": 5.761616161616162e-07,
|
325 |
+
"loss": 0.0544,
|
326 |
+
"step": 4300
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.22,
|
330 |
+
"grad_norm": 0.005931401159614325,
|
331 |
+
"learning_rate": 5.660606060606061e-07,
|
332 |
+
"loss": 0.0603,
|
333 |
+
"step": 4400
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.23,
|
337 |
+
"grad_norm": 8.401103973388672,
|
338 |
+
"learning_rate": 5.559595959595959e-07,
|
339 |
+
"loss": 0.0531,
|
340 |
+
"step": 4500
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.23,
|
344 |
+
"grad_norm": 3.780881404876709,
|
345 |
+
"learning_rate": 5.459595959595959e-07,
|
346 |
+
"loss": 0.0729,
|
347 |
+
"step": 4600
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.23,
|
351 |
+
"grad_norm": 8.754217147827148,
|
352 |
+
"learning_rate": 5.358585858585858e-07,
|
353 |
+
"loss": 0.0766,
|
354 |
+
"step": 4700
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.24,
|
358 |
+
"grad_norm": 2.9296135902404785,
|
359 |
+
"learning_rate": 5.257575757575757e-07,
|
360 |
+
"loss": 0.0651,
|
361 |
+
"step": 4800
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.24,
|
365 |
+
"grad_norm": 4.884037494659424,
|
366 |
+
"learning_rate": 5.156565656565657e-07,
|
367 |
+
"loss": 0.0623,
|
368 |
+
"step": 4900
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.25,
|
372 |
+
"grad_norm": 1.247363567352295,
|
373 |
+
"learning_rate": 5.055555555555555e-07,
|
374 |
+
"loss": 0.0498,
|
375 |
+
"step": 5000
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.26,
|
379 |
+
"grad_norm": 5.299038887023926,
|
380 |
+
"learning_rate": 4.954545454545454e-07,
|
381 |
+
"loss": 0.0558,
|
382 |
+
"step": 5100
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.26,
|
386 |
+
"grad_norm": 3.8896191120147705,
|
387 |
+
"learning_rate": 4.853535353535353e-07,
|
388 |
+
"loss": 0.0733,
|
389 |
+
"step": 5200
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.27,
|
393 |
+
"grad_norm": 2.1511714458465576,
|
394 |
+
"learning_rate": 4.752525252525252e-07,
|
395 |
+
"loss": 0.0647,
|
396 |
+
"step": 5300
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.27,
|
400 |
+
"grad_norm": 3.958899736404419,
|
401 |
+
"learning_rate": 4.6515151515151513e-07,
|
402 |
+
"loss": 0.0594,
|
403 |
+
"step": 5400
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.28,
|
407 |
+
"grad_norm": 7.097384929656982,
|
408 |
+
"learning_rate": 4.55050505050505e-07,
|
409 |
+
"loss": 0.0623,
|
410 |
+
"step": 5500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.28,
|
414 |
+
"grad_norm": 6.70374870300293,
|
415 |
+
"learning_rate": 4.449494949494949e-07,
|
416 |
+
"loss": 0.0669,
|
417 |
+
"step": 5600
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.28,
|
421 |
+
"grad_norm": 1.3009291887283325,
|
422 |
+
"learning_rate": 4.3484848484848483e-07,
|
423 |
+
"loss": 0.0528,
|
424 |
+
"step": 5700
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.29,
|
428 |
+
"grad_norm": 4.70461368560791,
|
429 |
+
"learning_rate": 4.2474747474747474e-07,
|
430 |
+
"loss": 0.0668,
|
431 |
+
"step": 5800
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.29,
|
435 |
+
"grad_norm": 0.03208538889884949,
|
436 |
+
"learning_rate": 4.1464646464646466e-07,
|
437 |
+
"loss": 0.0641,
|
438 |
+
"step": 5900
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.3,
|
442 |
+
"grad_norm": 0.0016973208403214812,
|
443 |
+
"learning_rate": 4.045454545454545e-07,
|
444 |
+
"loss": 0.064,
|
445 |
+
"step": 6000
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.3,
|
449 |
+
"eval_loss": 0.06021637097001076,
|
450 |
+
"eval_runtime": 200.1582,
|
451 |
+
"eval_samples_per_second": 4.996,
|
452 |
+
"eval_steps_per_second": 1.249,
|
453 |
+
"step": 6000
|
454 |
+
}
|
455 |
+
],
|
456 |
+
"logging_steps": 100,
|
457 |
+
"max_steps": 10000,
|
458 |
+
"num_input_tokens_seen": 0,
|
459 |
+
"num_train_epochs": 1,
|
460 |
+
"save_steps": 2000,
|
461 |
+
"total_flos": 5.65692592029696e+17,
|
462 |
+
"train_batch_size": 4,
|
463 |
+
"trial_name": null,
|
464 |
+
"trial_params": null
|
465 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:736f597104cf9a945e3251bb6da680dfc2d580fce21a952968facdcb3849885c
|
3 |
+
size 4920
|