Training in progress, step 25, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +31 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +29 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +124 -0
- last-checkpoint/trainer_state.json +248 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: katuni4ka/tiny-random-falcon-40b
|
3 |
+
library_name: peft
|
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 0.13.2
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "katuni4ka/tiny-random-falcon-40b",
|
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": 64,
|
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 |
+
"query_key_value",
|
24 |
+
"dense_4h_to_h",
|
25 |
+
"dense",
|
26 |
+
"dense_h_to_4h"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb435ae44e1260bf001862b4712cedf6e7ccb6e2947659ca26e077ee9f463da7
|
3 |
+
size 493712
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d672426f8a4e05ea1ed343c9f10c28fb8ba064956e5b138f61d885146b0673
|
3 |
+
size 997038
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ccb34b93699f078ddb82b9a167e79da1e720b4cd2112f0de5c0f8f14e38bd22
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
|
3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>PREFIX<<",
|
12 |
+
">>SUFFIX<<",
|
13 |
+
">>MIDDLE<<"
|
14 |
+
],
|
15 |
+
"eos_token": {
|
16 |
+
"content": "<|endoftext|>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": {
|
23 |
+
"content": "<|endoftext|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": ">>TITLE<<",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": ">>ABSTRACT<<",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": ">>INTRODUCTION<<",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": ">>SUMMARY<<",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": ">>COMMENT<<",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": ">>ANSWER<<",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": ">>QUESTION<<",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": ">>DOMAIN<<",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": ">>PREFIX<<",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": ">>SUFFIX<<",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": ">>MIDDLE<<",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<|endoftext|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
}
|
100 |
+
},
|
101 |
+
"additional_special_tokens": [
|
102 |
+
">>TITLE<<",
|
103 |
+
">>ABSTRACT<<",
|
104 |
+
">>INTRODUCTION<<",
|
105 |
+
">>SUMMARY<<",
|
106 |
+
">>COMMENT<<",
|
107 |
+
">>ANSWER<<",
|
108 |
+
">>QUESTION<<",
|
109 |
+
">>DOMAIN<<",
|
110 |
+
">>PREFIX<<",
|
111 |
+
">>SUFFIX<<",
|
112 |
+
">>MIDDLE<<"
|
113 |
+
],
|
114 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
115 |
+
"clean_up_tokenization_spaces": false,
|
116 |
+
"eos_token": "<|endoftext|>",
|
117 |
+
"model_input_names": [
|
118 |
+
"input_ids",
|
119 |
+
"attention_mask"
|
120 |
+
],
|
121 |
+
"model_max_length": 2048,
|
122 |
+
"pad_token": "<|endoftext|>",
|
123 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
124 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006348668895754857,
|
5 |
+
"eval_steps": 6,
|
6 |
+
"global_step": 25,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0002539467558301943,
|
13 |
+
"grad_norm": 2.3970961570739746,
|
14 |
+
"learning_rate": 1e-05,
|
15 |
+
"loss": 66.6603,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0002539467558301943,
|
20 |
+
"eval_loss": 11.107478141784668,
|
21 |
+
"eval_runtime": 18.8123,
|
22 |
+
"eval_samples_per_second": 264.454,
|
23 |
+
"eval_steps_per_second": 66.127,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0005078935116603886,
|
28 |
+
"grad_norm": 2.4752585887908936,
|
29 |
+
"learning_rate": 2e-05,
|
30 |
+
"loss": 66.6705,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0007618402674905828,
|
35 |
+
"grad_norm": 2.5148186683654785,
|
36 |
+
"learning_rate": 3e-05,
|
37 |
+
"loss": 66.6682,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0010157870233207772,
|
42 |
+
"grad_norm": 2.3080971240997314,
|
43 |
+
"learning_rate": 4e-05,
|
44 |
+
"loss": 66.5837,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0012697337791509713,
|
49 |
+
"grad_norm": 2.354560613632202,
|
50 |
+
"learning_rate": 5e-05,
|
51 |
+
"loss": 66.6436,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.0015236805349811656,
|
56 |
+
"grad_norm": 2.5473434925079346,
|
57 |
+
"learning_rate": 6e-05,
|
58 |
+
"loss": 66.6068,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.0015236805349811656,
|
63 |
+
"eval_loss": 11.101515769958496,
|
64 |
+
"eval_runtime": 18.1722,
|
65 |
+
"eval_samples_per_second": 273.77,
|
66 |
+
"eval_steps_per_second": 68.456,
|
67 |
+
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.00177762729081136,
|
71 |
+
"grad_norm": 2.5556399822235107,
|
72 |
+
"learning_rate": 7e-05,
|
73 |
+
"loss": 66.6045,
|
74 |
+
"step": 7
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.0020315740466415543,
|
78 |
+
"grad_norm": 2.6539461612701416,
|
79 |
+
"learning_rate": 8e-05,
|
80 |
+
"loss": 66.6228,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.0022855208024717484,
|
85 |
+
"grad_norm": 2.602025032043457,
|
86 |
+
"learning_rate": 9e-05,
|
87 |
+
"loss": 66.4995,
|
88 |
+
"step": 9
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.0025394675583019426,
|
92 |
+
"grad_norm": 2.4404804706573486,
|
93 |
+
"learning_rate": 0.0001,
|
94 |
+
"loss": 66.5529,
|
95 |
+
"step": 10
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.002793414314132137,
|
99 |
+
"grad_norm": 2.2321112155914307,
|
100 |
+
"learning_rate": 9.98458666866564e-05,
|
101 |
+
"loss": 66.4916,
|
102 |
+
"step": 11
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.0030473610699623312,
|
106 |
+
"grad_norm": 2.796868085861206,
|
107 |
+
"learning_rate": 9.938441702975689e-05,
|
108 |
+
"loss": 66.4966,
|
109 |
+
"step": 12
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.0030473610699623312,
|
113 |
+
"eval_loss": 11.079522132873535,
|
114 |
+
"eval_runtime": 18.1003,
|
115 |
+
"eval_samples_per_second": 274.858,
|
116 |
+
"eval_steps_per_second": 68.728,
|
117 |
+
"step": 12
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.0033013078257925254,
|
121 |
+
"grad_norm": 2.591143846511841,
|
122 |
+
"learning_rate": 9.861849601988383e-05,
|
123 |
+
"loss": 66.4451,
|
124 |
+
"step": 13
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.00355525458162272,
|
128 |
+
"grad_norm": 2.323777675628662,
|
129 |
+
"learning_rate": 9.755282581475769e-05,
|
130 |
+
"loss": 66.4647,
|
131 |
+
"step": 14
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.003809201337452914,
|
135 |
+
"grad_norm": 2.9256598949432373,
|
136 |
+
"learning_rate": 9.619397662556435e-05,
|
137 |
+
"loss": 66.3829,
|
138 |
+
"step": 15
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.004063148093283109,
|
142 |
+
"grad_norm": 2.4250593185424805,
|
143 |
+
"learning_rate": 9.45503262094184e-05,
|
144 |
+
"loss": 66.4283,
|
145 |
+
"step": 16
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.004317094849113303,
|
149 |
+
"grad_norm": 2.607290029525757,
|
150 |
+
"learning_rate": 9.263200821770461e-05,
|
151 |
+
"loss": 66.2636,
|
152 |
+
"step": 17
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.004571041604943497,
|
156 |
+
"grad_norm": 2.8356802463531494,
|
157 |
+
"learning_rate": 9.045084971874738e-05,
|
158 |
+
"loss": 66.2697,
|
159 |
+
"step": 18
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.004571041604943497,
|
163 |
+
"eval_loss": 11.051901817321777,
|
164 |
+
"eval_runtime": 18.1634,
|
165 |
+
"eval_samples_per_second": 273.902,
|
166 |
+
"eval_steps_per_second": 68.489,
|
167 |
+
"step": 18
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.004824988360773691,
|
171 |
+
"grad_norm": 2.4801783561706543,
|
172 |
+
"learning_rate": 8.802029828000156e-05,
|
173 |
+
"loss": 66.3638,
|
174 |
+
"step": 19
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.005078935116603885,
|
178 |
+
"grad_norm": 2.5052285194396973,
|
179 |
+
"learning_rate": 8.535533905932738e-05,
|
180 |
+
"loss": 66.2984,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.005332881872434079,
|
185 |
+
"grad_norm": 2.5191738605499268,
|
186 |
+
"learning_rate": 8.247240241650918e-05,
|
187 |
+
"loss": 66.3049,
|
188 |
+
"step": 21
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.005586828628264274,
|
192 |
+
"grad_norm": 2.384291887283325,
|
193 |
+
"learning_rate": 7.938926261462366e-05,
|
194 |
+
"loss": 66.2243,
|
195 |
+
"step": 22
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.005840775384094468,
|
199 |
+
"grad_norm": 2.3815808296203613,
|
200 |
+
"learning_rate": 7.612492823579745e-05,
|
201 |
+
"loss": 66.3124,
|
202 |
+
"step": 23
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.0060947221399246625,
|
206 |
+
"grad_norm": 2.601182222366333,
|
207 |
+
"learning_rate": 7.269952498697734e-05,
|
208 |
+
"loss": 66.2157,
|
209 |
+
"step": 24
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.0060947221399246625,
|
213 |
+
"eval_loss": 11.026150703430176,
|
214 |
+
"eval_runtime": 18.1547,
|
215 |
+
"eval_samples_per_second": 274.034,
|
216 |
+
"eval_steps_per_second": 68.522,
|
217 |
+
"step": 24
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.006348668895754857,
|
221 |
+
"grad_norm": 2.959272861480713,
|
222 |
+
"learning_rate": 6.91341716182545e-05,
|
223 |
+
"loss": 66.0543,
|
224 |
+
"step": 25
|
225 |
+
}
|
226 |
+
],
|
227 |
+
"logging_steps": 1,
|
228 |
+
"max_steps": 50,
|
229 |
+
"num_input_tokens_seen": 0,
|
230 |
+
"num_train_epochs": 1,
|
231 |
+
"save_steps": 25,
|
232 |
+
"stateful_callbacks": {
|
233 |
+
"TrainerControl": {
|
234 |
+
"args": {
|
235 |
+
"should_epoch_stop": false,
|
236 |
+
"should_evaluate": false,
|
237 |
+
"should_log": false,
|
238 |
+
"should_save": true,
|
239 |
+
"should_training_stop": false
|
240 |
+
},
|
241 |
+
"attributes": {}
|
242 |
+
}
|
243 |
+
},
|
244 |
+
"total_flos": 3572917862400.0,
|
245 |
+
"train_batch_size": 4,
|
246 |
+
"trial_name": null,
|
247 |
+
"trial_params": null
|
248 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1247e6ed50813d593deabfd533d2a70ffcb96c386789337a3cad83af38aff09
|
3 |
+
size 6776
|