StefanKrsteski
commited on
Commit
•
f26bb25
1
Parent(s):
f454fd6
Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +130 -0
- trainer_state.json +957 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 32,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"o_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7993fddd2e132262392dc91a29d14fdd62deae5c7e814ae974f21c16bf710e59
|
3 |
+
size 142623480
|
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bc0cb4b28b2e810529c5f5be0193dc4744456f3098c3bec842bd8747d1a970
|
3 |
+
size 285320826
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ebe738945bd753e8346f867923ed10d6a05c8e1b8e00be642ff02f901206672
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad2c403835dbb897c4192b2b95bb22e3ddb3d5625f263ca4de9dd1ad53b96369
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
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": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,957 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3783499002456665,
|
3 |
+
"best_model_checkpoint": "../checkpoints/sft/checkpoint-2000",
|
4 |
+
"epoch": 1.8601767167880947,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01550147263990079,
|
13 |
+
"grad_norm": 0.0904994085431099,
|
14 |
+
"learning_rate": 4.9741602067183466e-05,
|
15 |
+
"loss": 2.0913,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03100294527980158,
|
20 |
+
"grad_norm": 0.09595159441232681,
|
21 |
+
"learning_rate": 4.948320413436693e-05,
|
22 |
+
"loss": 1.9736,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04650441791970237,
|
27 |
+
"grad_norm": 0.09749136120080948,
|
28 |
+
"learning_rate": 4.922480620155039e-05,
|
29 |
+
"loss": 1.9502,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06200589055960316,
|
34 |
+
"grad_norm": 0.08286518603563309,
|
35 |
+
"learning_rate": 4.8966408268733855e-05,
|
36 |
+
"loss": 1.9324,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.07750736319950395,
|
41 |
+
"grad_norm": 0.10390572249889374,
|
42 |
+
"learning_rate": 4.870801033591731e-05,
|
43 |
+
"loss": 1.9413,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09300883583940474,
|
48 |
+
"grad_norm": 0.08579128980636597,
|
49 |
+
"learning_rate": 4.8449612403100775e-05,
|
50 |
+
"loss": 1.9437,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.10851030847930554,
|
55 |
+
"grad_norm": 0.11584578454494476,
|
56 |
+
"learning_rate": 4.819121447028424e-05,
|
57 |
+
"loss": 1.939,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.12401178111920633,
|
62 |
+
"grad_norm": 0.1426805555820465,
|
63 |
+
"learning_rate": 4.79328165374677e-05,
|
64 |
+
"loss": 1.9428,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.13951325375910711,
|
69 |
+
"grad_norm": 0.08612250536680222,
|
70 |
+
"learning_rate": 4.7674418604651164e-05,
|
71 |
+
"loss": 1.9212,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.1550147263990079,
|
76 |
+
"grad_norm": 0.08324660360813141,
|
77 |
+
"learning_rate": 4.741602067183463e-05,
|
78 |
+
"loss": 1.9186,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.1550147263990079,
|
83 |
+
"eval_loss": 1.3784544467926025,
|
84 |
+
"eval_runtime": 10.968,
|
85 |
+
"eval_samples_per_second": 32.458,
|
86 |
+
"eval_steps_per_second": 4.103,
|
87 |
+
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.1705161990389087,
|
91 |
+
"grad_norm": 0.09479448199272156,
|
92 |
+
"learning_rate": 4.715762273901809e-05,
|
93 |
+
"loss": 1.9346,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.18601767167880948,
|
98 |
+
"grad_norm": 0.10014442354440689,
|
99 |
+
"learning_rate": 4.6899224806201553e-05,
|
100 |
+
"loss": 1.9093,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.20151914431871026,
|
105 |
+
"grad_norm": 0.08976327627897263,
|
106 |
+
"learning_rate": 4.664082687338501e-05,
|
107 |
+
"loss": 1.935,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.21702061695861108,
|
112 |
+
"grad_norm": 0.10600723326206207,
|
113 |
+
"learning_rate": 4.638242894056848e-05,
|
114 |
+
"loss": 1.9172,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.23252208959851187,
|
119 |
+
"grad_norm": 0.18757325410842896,
|
120 |
+
"learning_rate": 4.6124031007751936e-05,
|
121 |
+
"loss": 1.9177,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.24802356223841265,
|
126 |
+
"grad_norm": 0.10721405595541,
|
127 |
+
"learning_rate": 4.5865633074935406e-05,
|
128 |
+
"loss": 1.9098,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.2635250348783134,
|
133 |
+
"grad_norm": 0.09476891160011292,
|
134 |
+
"learning_rate": 4.560723514211886e-05,
|
135 |
+
"loss": 1.9307,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.27902650751821423,
|
140 |
+
"grad_norm": 0.09466688334941864,
|
141 |
+
"learning_rate": 4.5348837209302326e-05,
|
142 |
+
"loss": 1.9178,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.29452798015811504,
|
147 |
+
"grad_norm": 0.09889288246631622,
|
148 |
+
"learning_rate": 4.509043927648579e-05,
|
149 |
+
"loss": 1.9244,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.3100294527980158,
|
154 |
+
"grad_norm": 0.14233581721782684,
|
155 |
+
"learning_rate": 4.483204134366925e-05,
|
156 |
+
"loss": 1.9153,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.3100294527980158,
|
161 |
+
"eval_loss": 1.411450982093811,
|
162 |
+
"eval_runtime": 10.6228,
|
163 |
+
"eval_samples_per_second": 33.513,
|
164 |
+
"eval_steps_per_second": 4.236,
|
165 |
+
"step": 1000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.3255309254379166,
|
169 |
+
"grad_norm": 0.08776664733886719,
|
170 |
+
"learning_rate": 4.4573643410852715e-05,
|
171 |
+
"loss": 1.9278,
|
172 |
+
"step": 1050
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.3410323980778174,
|
176 |
+
"grad_norm": 0.09803825616836548,
|
177 |
+
"learning_rate": 4.431524547803618e-05,
|
178 |
+
"loss": 1.9199,
|
179 |
+
"step": 1100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.3565338707177182,
|
183 |
+
"grad_norm": 0.13931065797805786,
|
184 |
+
"learning_rate": 4.405684754521964e-05,
|
185 |
+
"loss": 1.9225,
|
186 |
+
"step": 1150
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.37203534335761895,
|
190 |
+
"grad_norm": 0.09357253462076187,
|
191 |
+
"learning_rate": 4.3798449612403104e-05,
|
192 |
+
"loss": 1.9317,
|
193 |
+
"step": 1200
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.38753681599751977,
|
197 |
+
"grad_norm": 0.10508549958467484,
|
198 |
+
"learning_rate": 4.354005167958656e-05,
|
199 |
+
"loss": 1.9255,
|
200 |
+
"step": 1250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.4030382886374205,
|
204 |
+
"grad_norm": 0.10250881314277649,
|
205 |
+
"learning_rate": 4.328165374677003e-05,
|
206 |
+
"loss": 1.9137,
|
207 |
+
"step": 1300
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.41853976127732134,
|
211 |
+
"grad_norm": 0.10409200936555862,
|
212 |
+
"learning_rate": 4.302325581395349e-05,
|
213 |
+
"loss": 1.8974,
|
214 |
+
"step": 1350
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.43404123391722216,
|
218 |
+
"grad_norm": 0.09141243994235992,
|
219 |
+
"learning_rate": 4.276485788113696e-05,
|
220 |
+
"loss": 1.9103,
|
221 |
+
"step": 1400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.4495427065571229,
|
225 |
+
"grad_norm": 0.09040896594524384,
|
226 |
+
"learning_rate": 4.2506459948320413e-05,
|
227 |
+
"loss": 1.9057,
|
228 |
+
"step": 1450
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.46504417919702373,
|
232 |
+
"grad_norm": 0.09726119041442871,
|
233 |
+
"learning_rate": 4.2248062015503877e-05,
|
234 |
+
"loss": 1.9014,
|
235 |
+
"step": 1500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.46504417919702373,
|
239 |
+
"eval_loss": 1.3864915370941162,
|
240 |
+
"eval_runtime": 10.6078,
|
241 |
+
"eval_samples_per_second": 33.56,
|
242 |
+
"eval_steps_per_second": 4.242,
|
243 |
+
"step": 1500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.4805456518369245,
|
247 |
+
"grad_norm": 0.11088709533214569,
|
248 |
+
"learning_rate": 4.198966408268734e-05,
|
249 |
+
"loss": 1.9152,
|
250 |
+
"step": 1550
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.4960471244768253,
|
254 |
+
"grad_norm": 0.11300063878297806,
|
255 |
+
"learning_rate": 4.17312661498708e-05,
|
256 |
+
"loss": 1.9168,
|
257 |
+
"step": 1600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.5115485971167261,
|
261 |
+
"grad_norm": 0.10414065420627594,
|
262 |
+
"learning_rate": 4.1472868217054266e-05,
|
263 |
+
"loss": 1.9172,
|
264 |
+
"step": 1650
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.5270500697566268,
|
268 |
+
"grad_norm": 0.09191906452178955,
|
269 |
+
"learning_rate": 4.121447028423773e-05,
|
270 |
+
"loss": 1.8968,
|
271 |
+
"step": 1700
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.5425515423965277,
|
275 |
+
"grad_norm": 0.10366778820753098,
|
276 |
+
"learning_rate": 4.095607235142119e-05,
|
277 |
+
"loss": 1.8976,
|
278 |
+
"step": 1750
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.5580530150364285,
|
282 |
+
"grad_norm": 0.09124482423067093,
|
283 |
+
"learning_rate": 4.0697674418604655e-05,
|
284 |
+
"loss": 1.8896,
|
285 |
+
"step": 1800
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.5735544876763292,
|
289 |
+
"grad_norm": 0.10119319707155228,
|
290 |
+
"learning_rate": 4.043927648578811e-05,
|
291 |
+
"loss": 1.8881,
|
292 |
+
"step": 1850
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.5890559603162301,
|
296 |
+
"grad_norm": 0.1147024929523468,
|
297 |
+
"learning_rate": 4.018087855297158e-05,
|
298 |
+
"loss": 1.9097,
|
299 |
+
"step": 1900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.6045574329561308,
|
303 |
+
"grad_norm": 0.09813511371612549,
|
304 |
+
"learning_rate": 3.992248062015504e-05,
|
305 |
+
"loss": 1.908,
|
306 |
+
"step": 1950
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.6200589055960316,
|
310 |
+
"grad_norm": 0.10509663820266724,
|
311 |
+
"learning_rate": 3.966408268733851e-05,
|
312 |
+
"loss": 1.9018,
|
313 |
+
"step": 2000
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.6200589055960316,
|
317 |
+
"eval_loss": 1.3783499002456665,
|
318 |
+
"eval_runtime": 10.6185,
|
319 |
+
"eval_samples_per_second": 33.526,
|
320 |
+
"eval_steps_per_second": 4.238,
|
321 |
+
"step": 2000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.6355603782359324,
|
325 |
+
"grad_norm": 0.1106325089931488,
|
326 |
+
"learning_rate": 3.9405684754521964e-05,
|
327 |
+
"loss": 1.8955,
|
328 |
+
"step": 2050
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.6510618508758332,
|
332 |
+
"grad_norm": 0.09004335105419159,
|
333 |
+
"learning_rate": 3.914728682170543e-05,
|
334 |
+
"loss": 1.881,
|
335 |
+
"step": 2100
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.666563323515734,
|
339 |
+
"grad_norm": 0.10601779073476791,
|
340 |
+
"learning_rate": 3.888888888888889e-05,
|
341 |
+
"loss": 1.8996,
|
342 |
+
"step": 2150
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.6820647961556348,
|
346 |
+
"grad_norm": 0.09966927021741867,
|
347 |
+
"learning_rate": 3.8630490956072354e-05,
|
348 |
+
"loss": 1.8806,
|
349 |
+
"step": 2200
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.6975662687955356,
|
353 |
+
"grad_norm": 0.10469923913478851,
|
354 |
+
"learning_rate": 3.837209302325582e-05,
|
355 |
+
"loss": 1.8948,
|
356 |
+
"step": 2250
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.7130677414354364,
|
360 |
+
"grad_norm": 0.10708159953355789,
|
361 |
+
"learning_rate": 3.811369509043928e-05,
|
362 |
+
"loss": 1.8917,
|
363 |
+
"step": 2300
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.7285692140753371,
|
367 |
+
"grad_norm": 0.09772736579179764,
|
368 |
+
"learning_rate": 3.785529715762274e-05,
|
369 |
+
"loss": 1.9049,
|
370 |
+
"step": 2350
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.7440706867152379,
|
374 |
+
"grad_norm": 0.10732176899909973,
|
375 |
+
"learning_rate": 3.7596899224806207e-05,
|
376 |
+
"loss": 1.911,
|
377 |
+
"step": 2400
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.7595721593551388,
|
381 |
+
"grad_norm": 0.10482428967952728,
|
382 |
+
"learning_rate": 3.733850129198966e-05,
|
383 |
+
"loss": 1.8946,
|
384 |
+
"step": 2450
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.7750736319950395,
|
388 |
+
"grad_norm": 0.10157684981822968,
|
389 |
+
"learning_rate": 3.708010335917313e-05,
|
390 |
+
"loss": 1.8859,
|
391 |
+
"step": 2500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.7750736319950395,
|
395 |
+
"eval_loss": 1.3911091089248657,
|
396 |
+
"eval_runtime": 10.6093,
|
397 |
+
"eval_samples_per_second": 33.555,
|
398 |
+
"eval_steps_per_second": 4.242,
|
399 |
+
"step": 2500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.7905751046349403,
|
403 |
+
"grad_norm": 0.10432788729667664,
|
404 |
+
"learning_rate": 3.682170542635659e-05,
|
405 |
+
"loss": 1.894,
|
406 |
+
"step": 2550
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.806076577274841,
|
410 |
+
"grad_norm": 0.10409342497587204,
|
411 |
+
"learning_rate": 3.656330749354005e-05,
|
412 |
+
"loss": 1.8882,
|
413 |
+
"step": 2600
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.8215780499147419,
|
417 |
+
"grad_norm": 0.11120035499334335,
|
418 |
+
"learning_rate": 3.6304909560723515e-05,
|
419 |
+
"loss": 1.8827,
|
420 |
+
"step": 2650
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 0.8370795225546427,
|
424 |
+
"grad_norm": 0.11159931123256683,
|
425 |
+
"learning_rate": 3.604651162790698e-05,
|
426 |
+
"loss": 1.8902,
|
427 |
+
"step": 2700
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.8525809951945434,
|
431 |
+
"grad_norm": 0.09784770011901855,
|
432 |
+
"learning_rate": 3.578811369509044e-05,
|
433 |
+
"loss": 1.8881,
|
434 |
+
"step": 2750
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.8680824678344443,
|
438 |
+
"grad_norm": 0.09907621890306473,
|
439 |
+
"learning_rate": 3.5529715762273905e-05,
|
440 |
+
"loss": 1.9006,
|
441 |
+
"step": 2800
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.8835839404743451,
|
445 |
+
"grad_norm": 0.10387194156646729,
|
446 |
+
"learning_rate": 3.527131782945737e-05,
|
447 |
+
"loss": 1.9085,
|
448 |
+
"step": 2850
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.8990854131142458,
|
452 |
+
"grad_norm": 0.09763891249895096,
|
453 |
+
"learning_rate": 3.5012919896640824e-05,
|
454 |
+
"loss": 1.8904,
|
455 |
+
"step": 2900
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.9145868857541466,
|
459 |
+
"grad_norm": 0.10186181217432022,
|
460 |
+
"learning_rate": 3.4754521963824294e-05,
|
461 |
+
"loss": 1.8732,
|
462 |
+
"step": 2950
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 0.9300883583940475,
|
466 |
+
"grad_norm": 0.11027953773736954,
|
467 |
+
"learning_rate": 3.449612403100775e-05,
|
468 |
+
"loss": 1.8886,
|
469 |
+
"step": 3000
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.9300883583940475,
|
473 |
+
"eval_loss": 1.4133652448654175,
|
474 |
+
"eval_runtime": 10.6201,
|
475 |
+
"eval_samples_per_second": 33.521,
|
476 |
+
"eval_steps_per_second": 4.237,
|
477 |
+
"step": 3000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.9455898310339482,
|
481 |
+
"grad_norm": 0.1076328456401825,
|
482 |
+
"learning_rate": 3.4237726098191214e-05,
|
483 |
+
"loss": 1.9007,
|
484 |
+
"step": 3050
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.961091303673849,
|
488 |
+
"grad_norm": 0.10457822680473328,
|
489 |
+
"learning_rate": 3.397932816537468e-05,
|
490 |
+
"loss": 1.8894,
|
491 |
+
"step": 3100
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.9765927763137499,
|
495 |
+
"grad_norm": 0.1240358054637909,
|
496 |
+
"learning_rate": 3.372093023255814e-05,
|
497 |
+
"loss": 1.8962,
|
498 |
+
"step": 3150
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.9920942489536506,
|
502 |
+
"grad_norm": 0.1087583601474762,
|
503 |
+
"learning_rate": 3.34625322997416e-05,
|
504 |
+
"loss": 1.8849,
|
505 |
+
"step": 3200
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 1.0075957215935514,
|
509 |
+
"grad_norm": 0.10473156720399857,
|
510 |
+
"learning_rate": 3.3204134366925067e-05,
|
511 |
+
"loss": 1.8825,
|
512 |
+
"step": 3250
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.0230971942334521,
|
516 |
+
"grad_norm": 0.11174094676971436,
|
517 |
+
"learning_rate": 3.294573643410852e-05,
|
518 |
+
"loss": 1.8804,
|
519 |
+
"step": 3300
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 1.038598666873353,
|
523 |
+
"grad_norm": 0.10820575803518295,
|
524 |
+
"learning_rate": 3.268733850129199e-05,
|
525 |
+
"loss": 1.874,
|
526 |
+
"step": 3350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.0541001395132537,
|
530 |
+
"grad_norm": 0.11375240236520767,
|
531 |
+
"learning_rate": 3.242894056847545e-05,
|
532 |
+
"loss": 1.892,
|
533 |
+
"step": 3400
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 1.0696016121531546,
|
537 |
+
"grad_norm": 0.10983241349458694,
|
538 |
+
"learning_rate": 3.217054263565892e-05,
|
539 |
+
"loss": 1.8864,
|
540 |
+
"step": 3450
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 1.0851030847930554,
|
544 |
+
"grad_norm": 0.11412903666496277,
|
545 |
+
"learning_rate": 3.1912144702842375e-05,
|
546 |
+
"loss": 1.8841,
|
547 |
+
"step": 3500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 1.0851030847930554,
|
551 |
+
"eval_loss": 1.409255862236023,
|
552 |
+
"eval_runtime": 10.6154,
|
553 |
+
"eval_samples_per_second": 33.536,
|
554 |
+
"eval_steps_per_second": 4.239,
|
555 |
+
"step": 3500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.1006045574329562,
|
559 |
+
"grad_norm": 0.11279023438692093,
|
560 |
+
"learning_rate": 3.1653746770025845e-05,
|
561 |
+
"loss": 1.8809,
|
562 |
+
"step": 3550
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.116106030072857,
|
566 |
+
"grad_norm": 0.12842436134815216,
|
567 |
+
"learning_rate": 3.13953488372093e-05,
|
568 |
+
"loss": 1.8822,
|
569 |
+
"step": 3600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.1316075027127577,
|
573 |
+
"grad_norm": 0.11607849597930908,
|
574 |
+
"learning_rate": 3.1136950904392765e-05,
|
575 |
+
"loss": 1.8677,
|
576 |
+
"step": 3650
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.1471089753526584,
|
580 |
+
"grad_norm": 0.11454817652702332,
|
581 |
+
"learning_rate": 3.087855297157623e-05,
|
582 |
+
"loss": 1.8785,
|
583 |
+
"step": 3700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.1626104479925594,
|
587 |
+
"grad_norm": 0.12619228661060333,
|
588 |
+
"learning_rate": 3.062015503875969e-05,
|
589 |
+
"loss": 1.8735,
|
590 |
+
"step": 3750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.1781119206324602,
|
594 |
+
"grad_norm": 0.12233872711658478,
|
595 |
+
"learning_rate": 3.0361757105943154e-05,
|
596 |
+
"loss": 1.8625,
|
597 |
+
"step": 3800
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.193613393272361,
|
601 |
+
"grad_norm": 0.1316874474287033,
|
602 |
+
"learning_rate": 3.0103359173126618e-05,
|
603 |
+
"loss": 1.8775,
|
604 |
+
"step": 3850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.2091148659122617,
|
608 |
+
"grad_norm": 0.12887555360794067,
|
609 |
+
"learning_rate": 2.9844961240310077e-05,
|
610 |
+
"loss": 1.8868,
|
611 |
+
"step": 3900
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.2246163385521625,
|
615 |
+
"grad_norm": 0.11875531822443008,
|
616 |
+
"learning_rate": 2.9586563307493544e-05,
|
617 |
+
"loss": 1.8645,
|
618 |
+
"step": 3950
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 1.2401178111920632,
|
622 |
+
"grad_norm": 0.11634934693574905,
|
623 |
+
"learning_rate": 2.9328165374677004e-05,
|
624 |
+
"loss": 1.8803,
|
625 |
+
"step": 4000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.2401178111920632,
|
629 |
+
"eval_loss": 1.4193403720855713,
|
630 |
+
"eval_runtime": 10.6141,
|
631 |
+
"eval_samples_per_second": 33.54,
|
632 |
+
"eval_steps_per_second": 4.24,
|
633 |
+
"step": 4000
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.255619283831964,
|
637 |
+
"grad_norm": 0.12749060988426208,
|
638 |
+
"learning_rate": 2.9069767441860467e-05,
|
639 |
+
"loss": 1.8699,
|
640 |
+
"step": 4050
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.271120756471865,
|
644 |
+
"grad_norm": 0.12758812308311462,
|
645 |
+
"learning_rate": 2.881136950904393e-05,
|
646 |
+
"loss": 1.8624,
|
647 |
+
"step": 4100
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.2866222291117655,
|
651 |
+
"grad_norm": 0.11913730949163437,
|
652 |
+
"learning_rate": 2.8552971576227393e-05,
|
653 |
+
"loss": 1.8731,
|
654 |
+
"step": 4150
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.3021237017516665,
|
658 |
+
"grad_norm": 0.11662113666534424,
|
659 |
+
"learning_rate": 2.8294573643410853e-05,
|
660 |
+
"loss": 1.8936,
|
661 |
+
"step": 4200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.3176251743915672,
|
665 |
+
"grad_norm": 0.13116636872291565,
|
666 |
+
"learning_rate": 2.8036175710594316e-05,
|
667 |
+
"loss": 1.8788,
|
668 |
+
"step": 4250
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.333126647031468,
|
672 |
+
"grad_norm": 0.12884733080863953,
|
673 |
+
"learning_rate": 2.777777777777778e-05,
|
674 |
+
"loss": 1.8788,
|
675 |
+
"step": 4300
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.3486281196713688,
|
679 |
+
"grad_norm": 0.12196724116802216,
|
680 |
+
"learning_rate": 2.751937984496124e-05,
|
681 |
+
"loss": 1.8689,
|
682 |
+
"step": 4350
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.3641295923112695,
|
686 |
+
"grad_norm": 0.13119535148143768,
|
687 |
+
"learning_rate": 2.7260981912144705e-05,
|
688 |
+
"loss": 1.8702,
|
689 |
+
"step": 4400
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.3796310649511705,
|
693 |
+
"grad_norm": 0.12181399017572403,
|
694 |
+
"learning_rate": 2.7002583979328165e-05,
|
695 |
+
"loss": 1.8708,
|
696 |
+
"step": 4450
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.395132537591071,
|
700 |
+
"grad_norm": 0.1291220635175705,
|
701 |
+
"learning_rate": 2.674418604651163e-05,
|
702 |
+
"loss": 1.8509,
|
703 |
+
"step": 4500
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.395132537591071,
|
707 |
+
"eval_loss": 1.4268625974655151,
|
708 |
+
"eval_runtime": 10.6177,
|
709 |
+
"eval_samples_per_second": 33.529,
|
710 |
+
"eval_steps_per_second": 4.238,
|
711 |
+
"step": 4500
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 1.410634010230972,
|
715 |
+
"grad_norm": 0.1215544119477272,
|
716 |
+
"learning_rate": 2.648578811369509e-05,
|
717 |
+
"loss": 1.868,
|
718 |
+
"step": 4550
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 1.4261354828708728,
|
722 |
+
"grad_norm": 0.12441984564065933,
|
723 |
+
"learning_rate": 2.622739018087855e-05,
|
724 |
+
"loss": 1.8624,
|
725 |
+
"step": 4600
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 1.4416369555107735,
|
729 |
+
"grad_norm": 0.12983018159866333,
|
730 |
+
"learning_rate": 2.5968992248062018e-05,
|
731 |
+
"loss": 1.875,
|
732 |
+
"step": 4650
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 1.4571384281506743,
|
736 |
+
"grad_norm": 0.14041350781917572,
|
737 |
+
"learning_rate": 2.5710594315245478e-05,
|
738 |
+
"loss": 1.8634,
|
739 |
+
"step": 4700
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 1.472639900790575,
|
743 |
+
"grad_norm": 0.1323089897632599,
|
744 |
+
"learning_rate": 2.5452196382428944e-05,
|
745 |
+
"loss": 1.8701,
|
746 |
+
"step": 4750
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 1.488141373430476,
|
750 |
+
"grad_norm": 0.13671238720417023,
|
751 |
+
"learning_rate": 2.5193798449612404e-05,
|
752 |
+
"loss": 1.8722,
|
753 |
+
"step": 4800
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 1.5036428460703766,
|
757 |
+
"grad_norm": 0.12991730868816376,
|
758 |
+
"learning_rate": 2.4935400516795867e-05,
|
759 |
+
"loss": 1.8548,
|
760 |
+
"step": 4850
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 1.5191443187102776,
|
764 |
+
"grad_norm": 0.12073440849781036,
|
765 |
+
"learning_rate": 2.467700258397933e-05,
|
766 |
+
"loss": 1.8817,
|
767 |
+
"step": 4900
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 1.5346457913501783,
|
771 |
+
"grad_norm": 0.1927834451198578,
|
772 |
+
"learning_rate": 2.441860465116279e-05,
|
773 |
+
"loss": 1.8624,
|
774 |
+
"step": 4950
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 1.550147263990079,
|
778 |
+
"grad_norm": 0.1434555947780609,
|
779 |
+
"learning_rate": 2.4160206718346253e-05,
|
780 |
+
"loss": 1.8571,
|
781 |
+
"step": 5000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 1.550147263990079,
|
785 |
+
"eval_loss": 1.4204214811325073,
|
786 |
+
"eval_runtime": 10.6279,
|
787 |
+
"eval_samples_per_second": 33.497,
|
788 |
+
"eval_steps_per_second": 4.234,
|
789 |
+
"step": 5000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 1.5656487366299798,
|
793 |
+
"grad_norm": 0.1407179832458496,
|
794 |
+
"learning_rate": 2.3901808785529716e-05,
|
795 |
+
"loss": 1.8693,
|
796 |
+
"step": 5050
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 1.5811502092698806,
|
800 |
+
"grad_norm": 0.13802586495876312,
|
801 |
+
"learning_rate": 2.364341085271318e-05,
|
802 |
+
"loss": 1.8653,
|
803 |
+
"step": 5100
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 1.5966516819097816,
|
807 |
+
"grad_norm": 0.13259877264499664,
|
808 |
+
"learning_rate": 2.3385012919896642e-05,
|
809 |
+
"loss": 1.85,
|
810 |
+
"step": 5150
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 1.612153154549682,
|
814 |
+
"grad_norm": 0.14958499372005463,
|
815 |
+
"learning_rate": 2.3131782945736435e-05,
|
816 |
+
"loss": 1.8707,
|
817 |
+
"step": 5200
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 1.627654627189583,
|
821 |
+
"grad_norm": 0.13671304285526276,
|
822 |
+
"learning_rate": 2.2873385012919898e-05,
|
823 |
+
"loss": 1.8642,
|
824 |
+
"step": 5250
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.6431560998294839,
|
828 |
+
"grad_norm": 0.12920096516609192,
|
829 |
+
"learning_rate": 2.261498708010336e-05,
|
830 |
+
"loss": 1.856,
|
831 |
+
"step": 5300
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 1.6586575724693846,
|
835 |
+
"grad_norm": 0.1263495683670044,
|
836 |
+
"learning_rate": 2.235658914728682e-05,
|
837 |
+
"loss": 1.8639,
|
838 |
+
"step": 5350
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 1.6741590451092854,
|
842 |
+
"grad_norm": 0.1388077437877655,
|
843 |
+
"learning_rate": 2.2098191214470284e-05,
|
844 |
+
"loss": 1.8662,
|
845 |
+
"step": 5400
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 1.6896605177491861,
|
849 |
+
"grad_norm": 0.13600564002990723,
|
850 |
+
"learning_rate": 2.1839793281653747e-05,
|
851 |
+
"loss": 1.8667,
|
852 |
+
"step": 5450
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 1.7051619903890871,
|
856 |
+
"grad_norm": 0.1285238116979599,
|
857 |
+
"learning_rate": 2.158139534883721e-05,
|
858 |
+
"loss": 1.8691,
|
859 |
+
"step": 5500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 1.7051619903890871,
|
863 |
+
"eval_loss": 1.4164341688156128,
|
864 |
+
"eval_runtime": 10.618,
|
865 |
+
"eval_samples_per_second": 33.528,
|
866 |
+
"eval_steps_per_second": 4.238,
|
867 |
+
"step": 5500
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 1.7206634630289876,
|
871 |
+
"grad_norm": 0.14896276593208313,
|
872 |
+
"learning_rate": 2.1322997416020673e-05,
|
873 |
+
"loss": 1.8526,
|
874 |
+
"step": 5550
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 1.7361649356688886,
|
878 |
+
"grad_norm": 0.13365153968334198,
|
879 |
+
"learning_rate": 2.1064599483204136e-05,
|
880 |
+
"loss": 1.8592,
|
881 |
+
"step": 5600
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 1.7516664083087892,
|
885 |
+
"grad_norm": 0.1381397843360901,
|
886 |
+
"learning_rate": 2.0806201550387596e-05,
|
887 |
+
"loss": 1.8563,
|
888 |
+
"step": 5650
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 1.7671678809486902,
|
892 |
+
"grad_norm": 0.14912950992584229,
|
893 |
+
"learning_rate": 2.054780361757106e-05,
|
894 |
+
"loss": 1.8562,
|
895 |
+
"step": 5700
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 1.782669353588591,
|
899 |
+
"grad_norm": 0.13218577206134796,
|
900 |
+
"learning_rate": 2.0289405684754523e-05,
|
901 |
+
"loss": 1.8617,
|
902 |
+
"step": 5750
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 1.7981708262284917,
|
906 |
+
"grad_norm": 0.13850583136081696,
|
907 |
+
"learning_rate": 2.0031007751937986e-05,
|
908 |
+
"loss": 1.8563,
|
909 |
+
"step": 5800
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 1.8136722988683927,
|
913 |
+
"grad_norm": 0.13015194237232208,
|
914 |
+
"learning_rate": 1.977260981912145e-05,
|
915 |
+
"loss": 1.8473,
|
916 |
+
"step": 5850
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 1.8291737715082932,
|
920 |
+
"grad_norm": 0.13473467528820038,
|
921 |
+
"learning_rate": 1.9514211886304912e-05,
|
922 |
+
"loss": 1.8549,
|
923 |
+
"step": 5900
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 1.8446752441481942,
|
927 |
+
"grad_norm": 0.13621702790260315,
|
928 |
+
"learning_rate": 1.9255813953488372e-05,
|
929 |
+
"loss": 1.8565,
|
930 |
+
"step": 5950
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 1.8601767167880947,
|
934 |
+
"grad_norm": 0.1430806815624237,
|
935 |
+
"learning_rate": 1.8997416020671835e-05,
|
936 |
+
"loss": 1.8533,
|
937 |
+
"step": 6000
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 1.8601767167880947,
|
941 |
+
"eval_loss": 1.4264311790466309,
|
942 |
+
"eval_runtime": 10.6098,
|
943 |
+
"eval_samples_per_second": 33.554,
|
944 |
+
"eval_steps_per_second": 4.241,
|
945 |
+
"step": 6000
|
946 |
+
}
|
947 |
+
],
|
948 |
+
"logging_steps": 50,
|
949 |
+
"max_steps": 9675,
|
950 |
+
"num_input_tokens_seen": 0,
|
951 |
+
"num_train_epochs": 3,
|
952 |
+
"save_steps": 500,
|
953 |
+
"total_flos": 1.108324190905172e+18,
|
954 |
+
"train_batch_size": 8,
|
955 |
+
"trial_name": null,
|
956 |
+
"trial_params": null
|
957 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e14e697372e7db0ec3de4fbd9c4c3e907b544dd5c741ca6f758b4ceb510e0c3
|
3 |
+
size 5240
|