Upload folder using huggingface_hub
Browse files- checkpoint-66/README.md +202 -0
- checkpoint-66/adapter_config.json +31 -0
- checkpoint-66/adapter_model.safetensors +3 -0
- checkpoint-66/optimizer.pt +3 -0
- checkpoint-66/rng_state_0.pth +3 -0
- checkpoint-66/rng_state_1.pth +3 -0
- checkpoint-66/rng_state_2.pth +3 -0
- checkpoint-66/rng_state_3.pth +3 -0
- checkpoint-66/scheduler.pt +3 -0
- checkpoint-66/special_tokens_map.json +30 -0
- checkpoint-66/tokenizer.json +0 -0
- checkpoint-66/tokenizer_config.json +222 -0
- checkpoint-66/trainer_state.json +527 -0
- checkpoint-66/training_args.bin +3 -0
- merged/config.json +30 -0
- merged/generation_config.json +7 -0
- merged/pytorch_model.bin +3 -0
- merged/special_tokens_map.json +30 -0
- merged/tokenizer.json +0 -0
- merged/tokenizer_config.json +222 -0
checkpoint-66/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: EleutherAI/pythia-160m
|
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
|
checkpoint-66/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "EleutherAI/pythia-160m",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"dense",
|
24 |
+
"dense_h_to_4h",
|
25 |
+
"query_key_value",
|
26 |
+
"dense_4h_to_h"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
checkpoint-66/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4aea07c390cb05da57bf54c0e365114211647b9b5695338c4fb5fdfcef594d
|
3 |
+
size 18887640
|
checkpoint-66/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d551662ca0a86ba6fe4a9a0837b1547daae0e696144dcdae8d6dc5f65fca4f79
|
3 |
+
size 9563706
|
checkpoint-66/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49230ad1b6a32270cd00dff0b3f9430d4882beb40d8591d2f783b872e3dc9531
|
3 |
+
size 15024
|
checkpoint-66/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c7f264ff1823f5f0b0ac2c60e609eb3854b728e8a6f3909ea2d9f84061e7cb
|
3 |
+
size 15024
|
checkpoint-66/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03198be8d5f32b01d80de46983690f5d42235d5f074f5f70035f66d9d7d6d72b
|
3 |
+
size 15024
|
checkpoint-66/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e72c79c15c93fbdb57ff6a7612074f99a86c3300da6dbf2d5e85a0f9c86c5e81
|
3 |
+
size 15024
|
checkpoint-66/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a506954e524976b6241592040344d2e00e3c53142510c864270196f96c337e4b
|
3 |
+
size 1064
|
checkpoint-66/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-66/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-66/tokenizer_config.json
ADDED
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50277": {
|
207 |
+
"content": "[PAD]",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
}
|
214 |
+
},
|
215 |
+
"bos_token": "<|endoftext|>",
|
216 |
+
"clean_up_tokenization_spaces": true,
|
217 |
+
"eos_token": "<|endoftext|>",
|
218 |
+
"model_max_length": 1000000000000000019884624838656,
|
219 |
+
"pad_token": "<|endoftext|>",
|
220 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
221 |
+
"unk_token": "<|endoftext|>"
|
222 |
+
}
|
checkpoint-66/trainer_state.json
ADDED
@@ -0,0 +1,527 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9962264150943396,
|
5 |
+
"eval_steps": 17,
|
6 |
+
"global_step": 66,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01509433962264151,
|
13 |
+
"grad_norm": 3.369950532913208,
|
14 |
+
"learning_rate": 6.666666666666667e-05,
|
15 |
+
"loss": 7.2645,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01509433962264151,
|
20 |
+
"eval_loss": 3.149449348449707,
|
21 |
+
"eval_runtime": 61.8077,
|
22 |
+
"eval_samples_per_second": 26.712,
|
23 |
+
"eval_steps_per_second": 3.349,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.03018867924528302,
|
28 |
+
"grad_norm": 3.0387887954711914,
|
29 |
+
"learning_rate": 0.00013333333333333334,
|
30 |
+
"loss": 7.2983,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.045283018867924525,
|
35 |
+
"grad_norm": 2.5631470680236816,
|
36 |
+
"learning_rate": 0.0002,
|
37 |
+
"loss": 7.4367,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.06037735849056604,
|
42 |
+
"grad_norm": 3.278961181640625,
|
43 |
+
"learning_rate": 0.00019987569212189224,
|
44 |
+
"loss": 7.4776,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.07547169811320754,
|
49 |
+
"grad_norm": 2.087064266204834,
|
50 |
+
"learning_rate": 0.00019950307753654017,
|
51 |
+
"loss": 7.0908,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.09056603773584905,
|
56 |
+
"grad_norm": 2.3598978519439697,
|
57 |
+
"learning_rate": 0.00019888308262251285,
|
58 |
+
"loss": 6.9143,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.10566037735849057,
|
63 |
+
"grad_norm": 1.7771012783050537,
|
64 |
+
"learning_rate": 0.00019801724878485438,
|
65 |
+
"loss": 6.9186,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.12075471698113208,
|
70 |
+
"grad_norm": 2.4985220432281494,
|
71 |
+
"learning_rate": 0.0001969077286229078,
|
72 |
+
"loss": 6.9942,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.13584905660377358,
|
77 |
+
"grad_norm": 12.599207878112793,
|
78 |
+
"learning_rate": 0.0001955572805786141,
|
79 |
+
"loss": 7.7101,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.1509433962264151,
|
84 |
+
"grad_norm": 2.3558859825134277,
|
85 |
+
"learning_rate": 0.00019396926207859084,
|
86 |
+
"loss": 6.779,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.1660377358490566,
|
91 |
+
"grad_norm": 2.0808639526367188,
|
92 |
+
"learning_rate": 0.00019214762118704076,
|
93 |
+
"loss": 6.5311,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.1811320754716981,
|
98 |
+
"grad_norm": 2.708430528640747,
|
99 |
+
"learning_rate": 0.0001900968867902419,
|
100 |
+
"loss": 7.1752,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.19622641509433963,
|
105 |
+
"grad_norm": 2.17210054397583,
|
106 |
+
"learning_rate": 0.00018782215733702286,
|
107 |
+
"loss": 6.6172,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.21132075471698114,
|
112 |
+
"grad_norm": 2.789539098739624,
|
113 |
+
"learning_rate": 0.00018532908816321558,
|
114 |
+
"loss": 6.4962,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.22641509433962265,
|
119 |
+
"grad_norm": 2.58414888381958,
|
120 |
+
"learning_rate": 0.0001826238774315995,
|
121 |
+
"loss": 6.5226,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.24150943396226415,
|
126 |
+
"grad_norm": 3.2796332836151123,
|
127 |
+
"learning_rate": 0.00017971325072229226,
|
128 |
+
"loss": 6.3995,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.25660377358490566,
|
133 |
+
"grad_norm": 4.385023593902588,
|
134 |
+
"learning_rate": 0.0001766044443118978,
|
135 |
+
"loss": 6.4826,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.25660377358490566,
|
140 |
+
"eval_loss": 3.5372278690338135,
|
141 |
+
"eval_runtime": 61.6896,
|
142 |
+
"eval_samples_per_second": 26.763,
|
143 |
+
"eval_steps_per_second": 3.356,
|
144 |
+
"step": 17
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.27169811320754716,
|
148 |
+
"grad_norm": 3.294088840484619,
|
149 |
+
"learning_rate": 0.00017330518718298264,
|
150 |
+
"loss": 6.4608,
|
151 |
+
"step": 18
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.28679245283018867,
|
155 |
+
"grad_norm": 4.093864440917969,
|
156 |
+
"learning_rate": 0.00016982368180860728,
|
157 |
+
"loss": 6.3879,
|
158 |
+
"step": 19
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.3018867924528302,
|
162 |
+
"grad_norm": 5.418688774108887,
|
163 |
+
"learning_rate": 0.00016616858375968595,
|
164 |
+
"loss": 6.3805,
|
165 |
+
"step": 20
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.3169811320754717,
|
169 |
+
"grad_norm": 3.941084384918213,
|
170 |
+
"learning_rate": 0.00016234898018587337,
|
171 |
+
"loss": 6.3663,
|
172 |
+
"step": 21
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.3320754716981132,
|
176 |
+
"grad_norm": 3.4766499996185303,
|
177 |
+
"learning_rate": 0.000158374367223479,
|
178 |
+
"loss": 6.3908,
|
179 |
+
"step": 22
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.3471698113207547,
|
183 |
+
"grad_norm": 2.5574960708618164,
|
184 |
+
"learning_rate": 0.00015425462638657595,
|
185 |
+
"loss": 6.2122,
|
186 |
+
"step": 23
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.3622641509433962,
|
190 |
+
"grad_norm": 4.6637349128723145,
|
191 |
+
"learning_rate": 0.00015000000000000001,
|
192 |
+
"loss": 6.3776,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.37735849056603776,
|
197 |
+
"grad_norm": 2.4422309398651123,
|
198 |
+
"learning_rate": 0.0001456210657353163,
|
199 |
+
"loss": 6.2012,
|
200 |
+
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.39245283018867927,
|
204 |
+
"grad_norm": 2.3416097164154053,
|
205 |
+
"learning_rate": 0.00014112871031306119,
|
206 |
+
"loss": 6.1651,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.4075471698113208,
|
211 |
+
"grad_norm": 3.30576491355896,
|
212 |
+
"learning_rate": 0.00013653410243663952,
|
213 |
+
"loss": 6.2184,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.4226415094339623,
|
218 |
+
"grad_norm": 2.7682509422302246,
|
219 |
+
"learning_rate": 0.00013184866502516845,
|
220 |
+
"loss": 6.2027,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.4377358490566038,
|
225 |
+
"grad_norm": 4.021812438964844,
|
226 |
+
"learning_rate": 0.00012708404681430053,
|
227 |
+
"loss": 6.3386,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.4528301886792453,
|
232 |
+
"grad_norm": 3.3042852878570557,
|
233 |
+
"learning_rate": 0.00012225209339563145,
|
234 |
+
"loss": 6.227,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.4679245283018868,
|
239 |
+
"grad_norm": 3.844247817993164,
|
240 |
+
"learning_rate": 0.00011736481776669306,
|
241 |
+
"loss": 6.2673,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.4830188679245283,
|
246 |
+
"grad_norm": 2.8234848976135254,
|
247 |
+
"learning_rate": 0.00011243437046474853,
|
248 |
+
"loss": 6.1439,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.4981132075471698,
|
253 |
+
"grad_norm": 4.197116374969482,
|
254 |
+
"learning_rate": 0.00010747300935864243,
|
255 |
+
"loss": 6.3007,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.5132075471698113,
|
260 |
+
"grad_norm": 3.342660427093506,
|
261 |
+
"learning_rate": 0.0001024930691738073,
|
262 |
+
"loss": 6.2201,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.5132075471698113,
|
267 |
+
"eval_loss": 3.566420078277588,
|
268 |
+
"eval_runtime": 61.4895,
|
269 |
+
"eval_samples_per_second": 26.85,
|
270 |
+
"eval_steps_per_second": 3.366,
|
271 |
+
"step": 34
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.5283018867924528,
|
275 |
+
"grad_norm": 2.9787464141845703,
|
276 |
+
"learning_rate": 9.750693082619273e-05,
|
277 |
+
"loss": 6.112,
|
278 |
+
"step": 35
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.5433962264150943,
|
282 |
+
"grad_norm": 2.610438585281372,
|
283 |
+
"learning_rate": 9.252699064135758e-05,
|
284 |
+
"loss": 6.0614,
|
285 |
+
"step": 36
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.5584905660377358,
|
289 |
+
"grad_norm": 2.8261501789093018,
|
290 |
+
"learning_rate": 8.756562953525152e-05,
|
291 |
+
"loss": 6.1233,
|
292 |
+
"step": 37
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.5735849056603773,
|
296 |
+
"grad_norm": 2.346614360809326,
|
297 |
+
"learning_rate": 8.263518223330697e-05,
|
298 |
+
"loss": 6.0373,
|
299 |
+
"step": 38
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.5886792452830188,
|
303 |
+
"grad_norm": 3.4609148502349854,
|
304 |
+
"learning_rate": 7.774790660436858e-05,
|
305 |
+
"loss": 6.2116,
|
306 |
+
"step": 39
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.6037735849056604,
|
310 |
+
"grad_norm": 3.320744514465332,
|
311 |
+
"learning_rate": 7.291595318569951e-05,
|
312 |
+
"loss": 6.0184,
|
313 |
+
"step": 40
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.6188679245283019,
|
317 |
+
"grad_norm": 5.637310981750488,
|
318 |
+
"learning_rate": 6.815133497483157e-05,
|
319 |
+
"loss": 6.0733,
|
320 |
+
"step": 41
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.6339622641509434,
|
324 |
+
"grad_norm": 3.282639503479004,
|
325 |
+
"learning_rate": 6.34658975633605e-05,
|
326 |
+
"loss": 6.0873,
|
327 |
+
"step": 42
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.6490566037735849,
|
331 |
+
"grad_norm": 3.5872244834899902,
|
332 |
+
"learning_rate": 5.887128968693887e-05,
|
333 |
+
"loss": 6.1186,
|
334 |
+
"step": 43
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.6641509433962264,
|
338 |
+
"grad_norm": 4.284397602081299,
|
339 |
+
"learning_rate": 5.43789342646837e-05,
|
340 |
+
"loss": 6.0825,
|
341 |
+
"step": 44
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.6792452830188679,
|
345 |
+
"grad_norm": 4.394499778747559,
|
346 |
+
"learning_rate": 5.000000000000002e-05,
|
347 |
+
"loss": 6.1251,
|
348 |
+
"step": 45
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.6943396226415094,
|
352 |
+
"grad_norm": 3.4746081829071045,
|
353 |
+
"learning_rate": 4.574537361342407e-05,
|
354 |
+
"loss": 6.0812,
|
355 |
+
"step": 46
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.7094339622641509,
|
359 |
+
"grad_norm": 3.57454514503479,
|
360 |
+
"learning_rate": 4.1625632776521037e-05,
|
361 |
+
"loss": 6.0712,
|
362 |
+
"step": 47
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.7245283018867924,
|
366 |
+
"grad_norm": 3.51664400100708,
|
367 |
+
"learning_rate": 3.7651019814126654e-05,
|
368 |
+
"loss": 5.964,
|
369 |
+
"step": 48
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.7396226415094339,
|
373 |
+
"grad_norm": 4.315882205963135,
|
374 |
+
"learning_rate": 3.383141624031408e-05,
|
375 |
+
"loss": 6.0406,
|
376 |
+
"step": 49
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.7547169811320755,
|
380 |
+
"grad_norm": 3.73150372505188,
|
381 |
+
"learning_rate": 3.0176318191392726e-05,
|
382 |
+
"loss": 6.0522,
|
383 |
+
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.769811320754717,
|
387 |
+
"grad_norm": 3.529745578765869,
|
388 |
+
"learning_rate": 2.669481281701739e-05,
|
389 |
+
"loss": 5.9788,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.769811320754717,
|
394 |
+
"eval_loss": 3.448855400085449,
|
395 |
+
"eval_runtime": 61.4858,
|
396 |
+
"eval_samples_per_second": 26.852,
|
397 |
+
"eval_steps_per_second": 3.367,
|
398 |
+
"step": 51
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.7849056603773585,
|
402 |
+
"grad_norm": 4.503292560577393,
|
403 |
+
"learning_rate": 2.339555568810221e-05,
|
404 |
+
"loss": 6.1671,
|
405 |
+
"step": 52
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.8,
|
409 |
+
"grad_norm": 3.397348165512085,
|
410 |
+
"learning_rate": 2.0286749277707782e-05,
|
411 |
+
"loss": 6.0209,
|
412 |
+
"step": 53
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.8150943396226416,
|
416 |
+
"grad_norm": 4.6119794845581055,
|
417 |
+
"learning_rate": 1.7376122568400532e-05,
|
418 |
+
"loss": 6.0264,
|
419 |
+
"step": 54
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.8301886792452831,
|
423 |
+
"grad_norm": 3.454331874847412,
|
424 |
+
"learning_rate": 1.467091183678444e-05,
|
425 |
+
"loss": 5.9945,
|
426 |
+
"step": 55
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 0.8452830188679246,
|
430 |
+
"grad_norm": 3.9767298698425293,
|
431 |
+
"learning_rate": 1.2177842662977135e-05,
|
432 |
+
"loss": 5.9584,
|
433 |
+
"step": 56
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.8603773584905661,
|
437 |
+
"grad_norm": 3.5614728927612305,
|
438 |
+
"learning_rate": 9.903113209758096e-06,
|
439 |
+
"loss": 5.9824,
|
440 |
+
"step": 57
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.8754716981132076,
|
444 |
+
"grad_norm": 4.728991985321045,
|
445 |
+
"learning_rate": 7.852378812959227e-06,
|
446 |
+
"loss": 6.1022,
|
447 |
+
"step": 58
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.8905660377358491,
|
451 |
+
"grad_norm": 3.6874423027038574,
|
452 |
+
"learning_rate": 6.030737921409169e-06,
|
453 |
+
"loss": 6.0629,
|
454 |
+
"step": 59
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 0.9056603773584906,
|
458 |
+
"grad_norm": 7.522274017333984,
|
459 |
+
"learning_rate": 4.442719421385922e-06,
|
460 |
+
"loss": 6.1012,
|
461 |
+
"step": 60
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.9207547169811321,
|
465 |
+
"grad_norm": 4.2981977462768555,
|
466 |
+
"learning_rate": 3.092271377092215e-06,
|
467 |
+
"loss": 5.943,
|
468 |
+
"step": 61
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 0.9358490566037736,
|
472 |
+
"grad_norm": 8.979515075683594,
|
473 |
+
"learning_rate": 1.9827512151456173e-06,
|
474 |
+
"loss": 6.0199,
|
475 |
+
"step": 62
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.9509433962264151,
|
479 |
+
"grad_norm": 3.528214931488037,
|
480 |
+
"learning_rate": 1.1169173774871478e-06,
|
481 |
+
"loss": 6.0036,
|
482 |
+
"step": 63
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.9660377358490566,
|
486 |
+
"grad_norm": 4.428744316101074,
|
487 |
+
"learning_rate": 4.969224634598591e-07,
|
488 |
+
"loss": 6.0324,
|
489 |
+
"step": 64
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.9811320754716981,
|
493 |
+
"grad_norm": 4.525725364685059,
|
494 |
+
"learning_rate": 1.2430787810776555e-07,
|
495 |
+
"loss": 6.0756,
|
496 |
+
"step": 65
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.9962264150943396,
|
500 |
+
"grad_norm": 4.799617767333984,
|
501 |
+
"learning_rate": 0.0,
|
502 |
+
"loss": 6.0619,
|
503 |
+
"step": 66
|
504 |
+
}
|
505 |
+
],
|
506 |
+
"logging_steps": 1,
|
507 |
+
"max_steps": 66,
|
508 |
+
"num_input_tokens_seen": 0,
|
509 |
+
"num_train_epochs": 1,
|
510 |
+
"save_steps": 500,
|
511 |
+
"stateful_callbacks": {
|
512 |
+
"TrainerControl": {
|
513 |
+
"args": {
|
514 |
+
"should_epoch_stop": false,
|
515 |
+
"should_evaluate": false,
|
516 |
+
"should_log": false,
|
517 |
+
"should_save": true,
|
518 |
+
"should_training_stop": true
|
519 |
+
},
|
520 |
+
"attributes": {}
|
521 |
+
}
|
522 |
+
},
|
523 |
+
"total_flos": 6664957898784768.0,
|
524 |
+
"train_batch_size": 2,
|
525 |
+
"trial_name": null,
|
526 |
+
"trial_params": null
|
527 |
+
}
|
checkpoint-66/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b28bd5f286cb1830f4cb51aead0257ae27dd2f2bf81db165e1a5eeaadb7ff86
|
3 |
+
size 6200
|
merged/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-160m",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rotary_emb_base": 10000,
|
23 |
+
"rotary_pct": 0.25,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.42.3",
|
27 |
+
"use_cache": false,
|
28 |
+
"use_parallel_residual": true,
|
29 |
+
"vocab_size": 50304
|
30 |
+
}
|
merged/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 0,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
+
}
|
merged/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:247a1237a582861a30efa5ca66117359d75a8ab8c7385d93eeedca98c4333b27
|
3 |
+
size 324694042
|
merged/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
merged/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merged/tokenizer_config.json
ADDED
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50277": {
|
207 |
+
"content": "[PAD]",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
}
|
214 |
+
},
|
215 |
+
"bos_token": "<|endoftext|>",
|
216 |
+
"clean_up_tokenization_spaces": true,
|
217 |
+
"eos_token": "<|endoftext|>",
|
218 |
+
"model_max_length": 1000000000000000019884624838656,
|
219 |
+
"pad_token": "<|endoftext|>",
|
220 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
221 |
+
"unk_token": "<|endoftext|>"
|
222 |
+
}
|