initial_commit
Browse files- README.md +202 -3
- adapter_config.json +3 -3
- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +17 -605
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: microsoft/Phi-3-mini-4k-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 0.11.1
|
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"gate_up_proj",
|
25 |
"down_proj",
|
26 |
-
"
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
|
|
24 |
"down_proj",
|
25 |
+
"gate_up_proj",
|
26 |
+
"qkv_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"total_flos": 3.1269503354535936e+16,
|
4 |
+
"train_loss": 0.19359449498793657,
|
5 |
+
"train_runtime": 1514.0603,
|
6 |
+
"train_samples_per_second": 0.448,
|
7 |
+
"train_steps_per_second": 0.112
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"total_flos": 3.1269503354535936e+16,
|
4 |
+
"train_loss": 0.19359449498793657,
|
5 |
+
"train_runtime": 1514.0603,
|
6 |
+
"train_samples_per_second": 0.448,
|
7 |
+
"train_steps_per_second": 0.112
|
8 |
}
|
trainer_state.json
CHANGED
@@ -3,632 +3,44 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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.
|
13 |
"grad_norm": NaN,
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
"grad_norm": NaN,
|
21 |
-
"learning_rate":
|
22 |
"loss": 0.0,
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
"grad_norm": NaN,
|
28 |
-
"learning_rate":
|
29 |
"loss": 0.0,
|
30 |
"step": 150
|
31 |
},
|
32 |
-
{
|
33 |
-
"epoch": 0.045641259698767686,
|
34 |
-
"grad_norm": NaN,
|
35 |
-
"learning_rate": 1.1402508551881415e-06,
|
36 |
-
"loss": 0.0,
|
37 |
-
"step": 200
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 0.057051574623459604,
|
41 |
-
"grad_norm": NaN,
|
42 |
-
"learning_rate": 1.4253135689851768e-06,
|
43 |
-
"loss": 0.0,
|
44 |
-
"step": 250
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.06846188954815152,
|
48 |
-
"grad_norm": NaN,
|
49 |
-
"learning_rate": 1.7103762827822124e-06,
|
50 |
-
"loss": 0.0,
|
51 |
-
"step": 300
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 0.07987220447284345,
|
55 |
-
"grad_norm": NaN,
|
56 |
-
"learning_rate": 1.9954389965792477e-06,
|
57 |
-
"loss": 0.0,
|
58 |
-
"step": 350
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"epoch": 0.09128251939753537,
|
62 |
-
"grad_norm": NaN,
|
63 |
-
"learning_rate": 2.280501710376283e-06,
|
64 |
-
"loss": 0.0,
|
65 |
-
"step": 400
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 0.1026928343222273,
|
69 |
-
"grad_norm": NaN,
|
70 |
-
"learning_rate": 2.5655644241733184e-06,
|
71 |
-
"loss": 0.0,
|
72 |
-
"step": 450
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 0.11410314924691921,
|
76 |
-
"grad_norm": NaN,
|
77 |
-
"learning_rate": 2.8506271379703537e-06,
|
78 |
-
"loss": 0.0,
|
79 |
-
"step": 500
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 0.12551346417161113,
|
83 |
-
"grad_norm": NaN,
|
84 |
-
"learning_rate": 3.135689851767389e-06,
|
85 |
-
"loss": 0.0,
|
86 |
-
"step": 550
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.13692377909630304,
|
90 |
-
"grad_norm": NaN,
|
91 |
-
"learning_rate": 3.4207525655644248e-06,
|
92 |
-
"loss": 0.0,
|
93 |
-
"step": 600
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 0.14833409402099498,
|
97 |
-
"grad_norm": NaN,
|
98 |
-
"learning_rate": 3.70581527936146e-06,
|
99 |
-
"loss": 0.0,
|
100 |
-
"step": 650
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 0.1597444089456869,
|
104 |
-
"grad_norm": NaN,
|
105 |
-
"learning_rate": 3.990877993158495e-06,
|
106 |
-
"loss": 0.0,
|
107 |
-
"step": 700
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"epoch": 0.17115472387037883,
|
111 |
-
"grad_norm": NaN,
|
112 |
-
"learning_rate": 4.27594070695553e-06,
|
113 |
-
"loss": 0.0,
|
114 |
-
"step": 750
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 0.18256503879507074,
|
118 |
-
"grad_norm": NaN,
|
119 |
-
"learning_rate": 4.561003420752566e-06,
|
120 |
-
"loss": 0.0,
|
121 |
-
"step": 800
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 0.19397535371976266,
|
125 |
-
"grad_norm": NaN,
|
126 |
-
"learning_rate": 4.846066134549601e-06,
|
127 |
-
"loss": 0.0,
|
128 |
-
"step": 850
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.2053856686444546,
|
132 |
-
"grad_norm": NaN,
|
133 |
-
"learning_rate": 4.9994687805047495e-06,
|
134 |
-
"loss": 0.0,
|
135 |
-
"step": 900
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"epoch": 0.2167959835691465,
|
139 |
-
"grad_norm": NaN,
|
140 |
-
"learning_rate": 4.994650360888966e-06,
|
141 |
-
"loss": 0.0,
|
142 |
-
"step": 950
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.22820629849383842,
|
146 |
-
"grad_norm": NaN,
|
147 |
-
"learning_rate": 4.984822368325914e-06,
|
148 |
-
"loss": 0.0,
|
149 |
-
"step": 1000
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 0.23961661341853036,
|
153 |
-
"grad_norm": NaN,
|
154 |
-
"learning_rate": 4.970004538665729e-06,
|
155 |
-
"loss": 0.0,
|
156 |
-
"step": 1050
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 0.25102692834322227,
|
160 |
-
"grad_norm": NaN,
|
161 |
-
"learning_rate": 4.950226627981557e-06,
|
162 |
-
"loss": 0.0,
|
163 |
-
"step": 1100
|
164 |
-
},
|
165 |
-
{
|
166 |
-
"epoch": 0.2624372432679142,
|
167 |
-
"grad_norm": NaN,
|
168 |
-
"learning_rate": 4.925528352815589e-06,
|
169 |
-
"loss": 0.0,
|
170 |
-
"step": 1150
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.2738475581926061,
|
174 |
-
"grad_norm": NaN,
|
175 |
-
"learning_rate": 4.895959310423238e-06,
|
176 |
-
"loss": 0.0,
|
177 |
-
"step": 1200
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 0.28525787311729806,
|
181 |
-
"grad_norm": NaN,
|
182 |
-
"learning_rate": 4.861578879175587e-06,
|
183 |
-
"loss": 0.0,
|
184 |
-
"step": 1250
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.29666818804198997,
|
188 |
-
"grad_norm": NaN,
|
189 |
-
"learning_rate": 4.822456099320115e-06,
|
190 |
-
"loss": 0.0,
|
191 |
-
"step": 1300
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 0.3080785029666819,
|
195 |
-
"grad_norm": NaN,
|
196 |
-
"learning_rate": 4.778669534339168e-06,
|
197 |
-
"loss": 0.0,
|
198 |
-
"step": 1350
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"epoch": 0.3194888178913738,
|
202 |
-
"grad_norm": NaN,
|
203 |
-
"learning_rate": 4.730307113184564e-06,
|
204 |
-
"loss": 0.0,
|
205 |
-
"step": 1400
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 0.3308991328160657,
|
209 |
-
"grad_norm": NaN,
|
210 |
-
"learning_rate": 4.67746595370515e-06,
|
211 |
-
"loss": 0.0,
|
212 |
-
"step": 1450
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 0.34230944774075767,
|
216 |
-
"grad_norm": NaN,
|
217 |
-
"learning_rate": 4.620252167621905e-06,
|
218 |
-
"loss": 0.0,
|
219 |
-
"step": 1500
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 0.3537197626654496,
|
223 |
-
"grad_norm": NaN,
|
224 |
-
"learning_rate": 4.558780647442198e-06,
|
225 |
-
"loss": 0.0,
|
226 |
-
"step": 1550
|
227 |
-
},
|
228 |
-
{
|
229 |
-
"epoch": 0.3651300775901415,
|
230 |
-
"grad_norm": NaN,
|
231 |
-
"learning_rate": 4.4931748357411275e-06,
|
232 |
-
"loss": 0.0,
|
233 |
-
"step": 1600
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.3765403925148334,
|
237 |
-
"grad_norm": NaN,
|
238 |
-
"learning_rate": 4.423566477273245e-06,
|
239 |
-
"loss": 0.0,
|
240 |
-
"step": 1650
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 0.3879507074395253,
|
244 |
-
"grad_norm": NaN,
|
245 |
-
"learning_rate": 4.350095354412442e-06,
|
246 |
-
"loss": 0.0,
|
247 |
-
"step": 1700
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 0.3993610223642173,
|
251 |
-
"grad_norm": NaN,
|
252 |
-
"learning_rate": 4.272909006451306e-06,
|
253 |
-
"loss": 0.0,
|
254 |
-
"step": 1750
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.4107713372889092,
|
258 |
-
"grad_norm": NaN,
|
259 |
-
"learning_rate": 4.192162433323576e-06,
|
260 |
-
"loss": 0.0,
|
261 |
-
"step": 1800
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.4221816522136011,
|
265 |
-
"grad_norm": NaN,
|
266 |
-
"learning_rate": 4.10801778434471e-06,
|
267 |
-
"loss": 0.0,
|
268 |
-
"step": 1850
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 0.433591967138293,
|
272 |
-
"grad_norm": NaN,
|
273 |
-
"learning_rate": 4.020644032595583e-06,
|
274 |
-
"loss": 0.0,
|
275 |
-
"step": 1900
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.4450022820629849,
|
279 |
-
"grad_norm": NaN,
|
280 |
-
"learning_rate": 3.930216635603199e-06,
|
281 |
-
"loss": 0.0,
|
282 |
-
"step": 1950
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 0.45641259698767683,
|
286 |
-
"grad_norm": NaN,
|
287 |
-
"learning_rate": 3.836917182999823e-06,
|
288 |
-
"loss": 0.0,
|
289 |
-
"step": 2000
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 0.4678229119123688,
|
293 |
-
"grad_norm": NaN,
|
294 |
-
"learning_rate": 3.7409330318680704e-06,
|
295 |
-
"loss": 0.0,
|
296 |
-
"step": 2050
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.4792332268370607,
|
300 |
-
"grad_norm": NaN,
|
301 |
-
"learning_rate": 3.64245693050422e-06,
|
302 |
-
"loss": 0.0,
|
303 |
-
"step": 2100
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 0.4906435417617526,
|
307 |
-
"grad_norm": NaN,
|
308 |
-
"learning_rate": 3.5416866313553e-06,
|
309 |
-
"loss": 0.0,
|
310 |
-
"step": 2150
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.5020538566864445,
|
314 |
-
"grad_norm": NaN,
|
315 |
-
"learning_rate": 3.4388244939072e-06,
|
316 |
-
"loss": 0.0,
|
317 |
-
"step": 2200
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 0.5134641716111364,
|
321 |
-
"grad_norm": NaN,
|
322 |
-
"learning_rate": 3.3340770783212716e-06,
|
323 |
-
"loss": 0.0,
|
324 |
-
"step": 2250
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"epoch": 0.5248744865358284,
|
328 |
-
"grad_norm": NaN,
|
329 |
-
"learning_rate": 3.227654730635437e-06,
|
330 |
-
"loss": 0.0,
|
331 |
-
"step": 2300
|
332 |
-
},
|
333 |
-
{
|
334 |
-
"epoch": 0.5362848014605203,
|
335 |
-
"grad_norm": NaN,
|
336 |
-
"learning_rate": 3.1197711603627844e-06,
|
337 |
-
"loss": 0.0,
|
338 |
-
"step": 2350
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 0.5476951163852122,
|
342 |
-
"grad_norm": NaN,
|
343 |
-
"learning_rate": 3.0106430113358794e-06,
|
344 |
-
"loss": 0.0,
|
345 |
-
"step": 2400
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 0.5591054313099042,
|
349 |
-
"grad_norm": NaN,
|
350 |
-
"learning_rate": 2.9004894266585893e-06,
|
351 |
-
"loss": 0.0,
|
352 |
-
"step": 2450
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 0.5705157462345961,
|
356 |
-
"grad_norm": NaN,
|
357 |
-
"learning_rate": 2.78953160863906e-06,
|
358 |
-
"loss": 0.0,
|
359 |
-
"step": 2500
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 0.581926061159288,
|
363 |
-
"grad_norm": NaN,
|
364 |
-
"learning_rate": 2.677992374587546e-06,
|
365 |
-
"loss": 0.0,
|
366 |
-
"step": 2550
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 0.5933363760839799,
|
370 |
-
"grad_norm": NaN,
|
371 |
-
"learning_rate": 2.5660957093711147e-06,
|
372 |
-
"loss": 0.0,
|
373 |
-
"step": 2600
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 0.6047466910086718,
|
377 |
-
"grad_norm": NaN,
|
378 |
-
"learning_rate": 2.4540663156237494e-06,
|
379 |
-
"loss": 0.0,
|
380 |
-
"step": 2650
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 0.6161570059333638,
|
384 |
-
"grad_norm": NaN,
|
385 |
-
"learning_rate": 2.3421291625150825e-06,
|
386 |
-
"loss": 0.0,
|
387 |
-
"step": 2700
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"epoch": 0.6275673208580557,
|
391 |
-
"grad_norm": NaN,
|
392 |
-
"learning_rate": 2.2305090339838983e-06,
|
393 |
-
"loss": 0.0,
|
394 |
-
"step": 2750
|
395 |
-
},
|
396 |
-
{
|
397 |
-
"epoch": 0.6389776357827476,
|
398 |
-
"grad_norm": NaN,
|
399 |
-
"learning_rate": 2.119430077343595e-06,
|
400 |
-
"loss": 0.0,
|
401 |
-
"step": 2800
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 0.6503879507074395,
|
405 |
-
"grad_norm": NaN,
|
406 |
-
"learning_rate": 2.009115353166073e-06,
|
407 |
-
"loss": 0.0,
|
408 |
-
"step": 2850
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 0.6617982656321314,
|
412 |
-
"grad_norm": NaN,
|
413 |
-
"learning_rate": 1.8997863873479453e-06,
|
414 |
-
"loss": 0.0,
|
415 |
-
"step": 2900
|
416 |
-
},
|
417 |
-
{
|
418 |
-
"epoch": 0.6732085805568234,
|
419 |
-
"grad_norm": NaN,
|
420 |
-
"learning_rate": 1.7916627262585539e-06,
|
421 |
-
"loss": 0.0,
|
422 |
-
"step": 2950
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 0.6846188954815153,
|
426 |
-
"grad_norm": NaN,
|
427 |
-
"learning_rate": 1.6849614958631432e-06,
|
428 |
-
"loss": 0.0,
|
429 |
-
"step": 3000
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 0.6960292104062072,
|
433 |
-
"grad_norm": NaN,
|
434 |
-
"learning_rate": 1.579896965706499e-06,
|
435 |
-
"loss": 0.0,
|
436 |
-
"step": 3050
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"epoch": 0.7074395253308992,
|
440 |
-
"grad_norm": NaN,
|
441 |
-
"learning_rate": 1.476680118632648e-06,
|
442 |
-
"loss": 0.0,
|
443 |
-
"step": 3100
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 0.7188498402555911,
|
447 |
-
"grad_norm": NaN,
|
448 |
-
"learning_rate": 1.375518227104661e-06,
|
449 |
-
"loss": 0.0,
|
450 |
-
"step": 3150
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 0.730260155180283,
|
454 |
-
"grad_norm": NaN,
|
455 |
-
"learning_rate": 1.276614436975375e-06,
|
456 |
-
"loss": 0.0,
|
457 |
-
"step": 3200
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 0.7416704701049749,
|
461 |
-
"grad_norm": NaN,
|
462 |
-
"learning_rate": 1.180167359544867e-06,
|
463 |
-
"loss": 0.0,
|
464 |
-
"step": 3250
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 0.7530807850296668,
|
468 |
-
"grad_norm": NaN,
|
469 |
-
"learning_rate": 1.0863706727238841e-06,
|
470 |
-
"loss": 0.0,
|
471 |
-
"step": 3300
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 0.7644910999543587,
|
475 |
-
"grad_norm": NaN,
|
476 |
-
"learning_rate": 9.95412732104138e-07,
|
477 |
-
"loss": 0.0,
|
478 |
-
"step": 3350
|
479 |
-
},
|
480 |
-
{
|
481 |
-
"epoch": 0.7759014148790506,
|
482 |
-
"grad_norm": NaN,
|
483 |
-
"learning_rate": 9.074761927164958e-07,
|
484 |
-
"loss": 0.0,
|
485 |
-
"step": 3400
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 0.7873117298037425,
|
489 |
-
"grad_norm": NaN,
|
490 |
-
"learning_rate": 8.227376422366091e-07,
|
491 |
-
"loss": 0.0,
|
492 |
-
"step": 3450
|
493 |
-
},
|
494 |
-
{
|
495 |
-
"epoch": 0.7987220447284346,
|
496 |
-
"grad_norm": NaN,
|
497 |
-
"learning_rate": 7.413672463745617e-07,
|
498 |
-
"loss": 0.0,
|
499 |
-
"step": 3500
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"epoch": 0.8101323596531265,
|
503 |
-
"grad_norm": NaN,
|
504 |
-
"learning_rate": 6.635284071606391e-07,
|
505 |
-
"loss": 0.0,
|
506 |
-
"step": 3550
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 0.8215426745778184,
|
510 |
-
"grad_norm": NaN,
|
511 |
-
"learning_rate": 5.89377434813414e-07,
|
512 |
-
"loss": 0.0,
|
513 |
-
"step": 3600
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 0.8329529895025103,
|
517 |
-
"grad_norm": NaN,
|
518 |
-
"learning_rate": 5.190632338490883e-07,
|
519 |
-
"loss": 0.0,
|
520 |
-
"step": 3650
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 0.8443633044272022,
|
524 |
-
"grad_norm": NaN,
|
525 |
-
"learning_rate": 4.5272700406242626e-07,
|
526 |
-
"loss": 0.0,
|
527 |
-
"step": 3700
|
528 |
-
},
|
529 |
-
{
|
530 |
-
"epoch": 0.8557736193518941,
|
531 |
-
"grad_norm": NaN,
|
532 |
-
"learning_rate": 3.9050195697972776e-07,
|
533 |
-
"loss": 0.0,
|
534 |
-
"step": 3750
|
535 |
-
},
|
536 |
-
{
|
537 |
-
"epoch": 0.867183934276586,
|
538 |
-
"grad_norm": NaN,
|
539 |
-
"learning_rate": 3.325130483532671e-07,
|
540 |
-
"loss": 0.0,
|
541 |
-
"step": 3800
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 0.8785942492012779,
|
545 |
-
"grad_norm": NaN,
|
546 |
-
"learning_rate": 2.788767272343648e-07,
|
547 |
-
"loss": 0.0,
|
548 |
-
"step": 3850
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 0.8900045641259698,
|
552 |
-
"grad_norm": NaN,
|
553 |
-
"learning_rate": 2.2970070212898126e-07,
|
554 |
-
"loss": 0.0,
|
555 |
-
"step": 3900
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 0.9014148790506618,
|
559 |
-
"grad_norm": NaN,
|
560 |
-
"learning_rate": 1.8508372470544045e-07,
|
561 |
-
"loss": 0.0,
|
562 |
-
"step": 3950
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 0.9128251939753537,
|
566 |
-
"grad_norm": NaN,
|
567 |
-
"learning_rate": 1.4511539148860805e-07,
|
568 |
-
"loss": 0.0,
|
569 |
-
"step": 4000
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 0.9242355089000457,
|
573 |
-
"grad_norm": NaN,
|
574 |
-
"learning_rate": 1.0987596393875477e-07,
|
575 |
-
"loss": 0.0,
|
576 |
-
"step": 4050
|
577 |
-
},
|
578 |
-
{
|
579 |
-
"epoch": 0.9356458238247376,
|
580 |
-
"grad_norm": NaN,
|
581 |
-
"learning_rate": 7.943620727641016e-08,
|
582 |
-
"loss": 0.0,
|
583 |
-
"step": 4100
|
584 |
-
},
|
585 |
-
{
|
586 |
-
"epoch": 0.9470561387494295,
|
587 |
-
"grad_norm": NaN,
|
588 |
-
"learning_rate": 5.385724837686124e-08,
|
589 |
-
"loss": 0.0,
|
590 |
-
"step": 4150
|
591 |
-
},
|
592 |
-
{
|
593 |
-
"epoch": 0.9584664536741214,
|
594 |
-
"grad_norm": NaN,
|
595 |
-
"learning_rate": 3.3190453019670835e-08,
|
596 |
-
"loss": 0.0,
|
597 |
-
"step": 4200
|
598 |
-
},
|
599 |
-
{
|
600 |
-
"epoch": 0.9698767685988133,
|
601 |
-
"grad_norm": NaN,
|
602 |
-
"learning_rate": 1.7477322739704038e-08,
|
603 |
-
"loss": 0.0,
|
604 |
-
"step": 4250
|
605 |
-
},
|
606 |
-
{
|
607 |
-
"epoch": 0.9812870835235052,
|
608 |
-
"grad_norm": NaN,
|
609 |
-
"learning_rate": 6.749411486805246e-09,
|
610 |
-
"loss": 0.0,
|
611 |
-
"step": 4300
|
612 |
-
},
|
613 |
-
{
|
614 |
-
"epoch": 0.9926973984481972,
|
615 |
-
"grad_norm": NaN,
|
616 |
-
"learning_rate": 1.028262261483226e-09,
|
617 |
-
"loss": 0.0,
|
618 |
-
"step": 4350
|
619 |
-
},
|
620 |
{
|
621 |
"epoch": 1.0,
|
622 |
-
"step":
|
623 |
-
"total_flos":
|
624 |
-
"train_loss": 0.
|
625 |
-
"train_runtime":
|
626 |
-
"train_samples_per_second": 0.
|
627 |
-
"train_steps_per_second": 0.
|
628 |
}
|
629 |
],
|
630 |
"logging_steps": 50,
|
631 |
-
"max_steps":
|
632 |
"num_input_tokens_seen": 0,
|
633 |
"num_train_epochs": 1,
|
634 |
"save_steps": 500,
|
@@ -638,13 +50,13 @@
|
|
638 |
"should_epoch_stop": false,
|
639 |
"should_evaluate": false,
|
640 |
"should_log": false,
|
641 |
-
"should_save":
|
642 |
"should_training_stop": false
|
643 |
},
|
644 |
"attributes": {}
|
645 |
}
|
646 |
},
|
647 |
-
"total_flos":
|
648 |
"train_batch_size": 4,
|
649 |
"trial_name": null,
|
650 |
"trial_params": null
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 170,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.29411764705882354,
|
13 |
"grad_norm": NaN,
|
14 |
+
"learning_rate": 4.83118057351089e-06,
|
15 |
+
"loss": 0.6582,
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.5882352941176471,
|
20 |
"grad_norm": NaN,
|
21 |
+
"learning_rate": 2.6154586466143495e-06,
|
22 |
"loss": 0.0,
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.8823529411764706,
|
27 |
"grad_norm": NaN,
|
28 |
+
"learning_rate": 2.620917716123444e-07,
|
29 |
"loss": 0.0,
|
30 |
"step": 150
|
31 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{
|
33 |
"epoch": 1.0,
|
34 |
+
"step": 170,
|
35 |
+
"total_flos": 3.1269503354535936e+16,
|
36 |
+
"train_loss": 0.19359449498793657,
|
37 |
+
"train_runtime": 1514.0603,
|
38 |
+
"train_samples_per_second": 0.448,
|
39 |
+
"train_steps_per_second": 0.112
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 50,
|
43 |
+
"max_steps": 170,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
"num_train_epochs": 1,
|
46 |
"save_steps": 500,
|
|
|
50 |
"should_epoch_stop": false,
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
+
"should_save": false,
|
54 |
"should_training_stop": false
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
+
"total_flos": 3.1269503354535936e+16,
|
60 |
"train_batch_size": 4,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4844ff749272ef526f5f855db84ae0970596b037c1465ab89ba72153131c3b54
|
3 |
size 5112
|