Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- trainer_state-llama2-bf16-QLORA-super_glue-multirc-sequence_classification.json +2274 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
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": [
|
18 |
+
"score",
|
19 |
+
"classifier",
|
20 |
+
"score"
|
21 |
+
],
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 8,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"v_proj",
|
31 |
+
"down_proj",
|
32 |
+
"up_proj",
|
33 |
+
"gate_proj"
|
34 |
+
],
|
35 |
+
"task_type": "SEQ_CLS",
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:727982e8273d0271acd46532614026188f94d2fc251d82d84245782812615e8e
|
3 |
+
size 40052968
|
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": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|
trainer_state-llama2-bf16-QLORA-super_glue-multirc-sequence_classification.json
ADDED
@@ -0,0 +1,2274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.984,
|
5 |
+
"eval_steps": 1,
|
6 |
+
"global_step": 124,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016,
|
13 |
+
"grad_norm": 52.25,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 1.2424,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.016,
|
20 |
+
"eval_exact_match": 0.02040816326530612,
|
21 |
+
"eval_f1_a": 0.5754985754985755,
|
22 |
+
"eval_f1_m": 0.30537274516866364,
|
23 |
+
"eval_loss": 1.8040205240249634,
|
24 |
+
"eval_runtime": 12.5246,
|
25 |
+
"eval_samples_per_second": 19.961,
|
26 |
+
"eval_steps_per_second": 2.555,
|
27 |
+
"step": 1
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.032,
|
31 |
+
"grad_norm": 74.5,
|
32 |
+
"learning_rate": 5e-05,
|
33 |
+
"loss": 1.5616,
|
34 |
+
"step": 2
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.032,
|
38 |
+
"eval_exact_match": 0.02040816326530612,
|
39 |
+
"eval_f1_a": 0.5754985754985755,
|
40 |
+
"eval_f1_m": 0.30537274516866364,
|
41 |
+
"eval_loss": 1.6737734079360962,
|
42 |
+
"eval_runtime": 12.5202,
|
43 |
+
"eval_samples_per_second": 19.968,
|
44 |
+
"eval_steps_per_second": 2.556,
|
45 |
+
"step": 2
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.048,
|
49 |
+
"grad_norm": 81.5,
|
50 |
+
"learning_rate": 4.959016393442623e-05,
|
51 |
+
"loss": 1.9327,
|
52 |
+
"step": 3
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.048,
|
56 |
+
"eval_exact_match": 0.02040816326530612,
|
57 |
+
"eval_f1_a": 0.5798816568047337,
|
58 |
+
"eval_f1_m": 0.3293744237621789,
|
59 |
+
"eval_loss": 1.0940678119659424,
|
60 |
+
"eval_runtime": 12.4172,
|
61 |
+
"eval_samples_per_second": 20.133,
|
62 |
+
"eval_steps_per_second": 2.577,
|
63 |
+
"step": 3
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.064,
|
67 |
+
"grad_norm": 24.5,
|
68 |
+
"learning_rate": 4.918032786885246e-05,
|
69 |
+
"loss": 0.7502,
|
70 |
+
"step": 4
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.064,
|
74 |
+
"eval_exact_match": 0.04081632653061224,
|
75 |
+
"eval_f1_a": 0.326797385620915,
|
76 |
+
"eval_f1_m": 0.40487871139131637,
|
77 |
+
"eval_loss": 0.7598310708999634,
|
78 |
+
"eval_runtime": 12.5191,
|
79 |
+
"eval_samples_per_second": 19.969,
|
80 |
+
"eval_steps_per_second": 2.556,
|
81 |
+
"step": 4
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08,
|
85 |
+
"grad_norm": 43.5,
|
86 |
+
"learning_rate": 4.8770491803278687e-05,
|
87 |
+
"loss": 1.2439,
|
88 |
+
"step": 5
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.08,
|
92 |
+
"eval_exact_match": 0.0,
|
93 |
+
"eval_f1_a": 0.11475409836065575,
|
94 |
+
"eval_f1_m": 0.3452577201376722,
|
95 |
+
"eval_loss": 0.8241621255874634,
|
96 |
+
"eval_runtime": 12.412,
|
97 |
+
"eval_samples_per_second": 20.142,
|
98 |
+
"eval_steps_per_second": 2.578,
|
99 |
+
"step": 5
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.096,
|
103 |
+
"grad_norm": 21.625,
|
104 |
+
"learning_rate": 4.836065573770492e-05,
|
105 |
+
"loss": 0.9487,
|
106 |
+
"step": 6
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.096,
|
110 |
+
"eval_exact_match": 0.02040816326530612,
|
111 |
+
"eval_f1_a": 0.05555555555555556,
|
112 |
+
"eval_f1_m": 0.35745697213284255,
|
113 |
+
"eval_loss": 0.8299877643585205,
|
114 |
+
"eval_runtime": 12.4102,
|
115 |
+
"eval_samples_per_second": 20.145,
|
116 |
+
"eval_steps_per_second": 2.579,
|
117 |
+
"step": 6
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.112,
|
121 |
+
"grad_norm": 114.0,
|
122 |
+
"learning_rate": 4.795081967213115e-05,
|
123 |
+
"loss": 1.9374,
|
124 |
+
"step": 7
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.112,
|
128 |
+
"eval_exact_match": 0.0,
|
129 |
+
"eval_f1_a": 0.08620689655172413,
|
130 |
+
"eval_f1_m": 0.3505331636484098,
|
131 |
+
"eval_loss": 0.7635751962661743,
|
132 |
+
"eval_runtime": 12.5057,
|
133 |
+
"eval_samples_per_second": 19.991,
|
134 |
+
"eval_steps_per_second": 2.559,
|
135 |
+
"step": 7
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.128,
|
139 |
+
"grad_norm": 49.25,
|
140 |
+
"learning_rate": 4.754098360655738e-05,
|
141 |
+
"loss": 0.9383,
|
142 |
+
"step": 8
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.128,
|
146 |
+
"eval_exact_match": 0.12244897959183673,
|
147 |
+
"eval_f1_a": 0.37499999999999994,
|
148 |
+
"eval_f1_m": 0.4638421102706817,
|
149 |
+
"eval_loss": 0.7212109565734863,
|
150 |
+
"eval_runtime": 12.5257,
|
151 |
+
"eval_samples_per_second": 19.959,
|
152 |
+
"eval_steps_per_second": 2.555,
|
153 |
+
"step": 8
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.144,
|
157 |
+
"grad_norm": 10.375,
|
158 |
+
"learning_rate": 4.713114754098361e-05,
|
159 |
+
"loss": 0.6205,
|
160 |
+
"step": 9
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.144,
|
164 |
+
"eval_exact_match": 0.04081632653061224,
|
165 |
+
"eval_f1_a": 0.46413502109704646,
|
166 |
+
"eval_f1_m": 0.39599618069005815,
|
167 |
+
"eval_loss": 0.7557714581489563,
|
168 |
+
"eval_runtime": 12.5194,
|
169 |
+
"eval_samples_per_second": 19.969,
|
170 |
+
"eval_steps_per_second": 2.556,
|
171 |
+
"step": 9
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.16,
|
175 |
+
"grad_norm": 11.8125,
|
176 |
+
"learning_rate": 4.672131147540984e-05,
|
177 |
+
"loss": 0.9441,
|
178 |
+
"step": 10
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.16,
|
182 |
+
"eval_exact_match": 0.02040816326530612,
|
183 |
+
"eval_f1_a": 0.5454545454545455,
|
184 |
+
"eval_f1_m": 0.3639190741231557,
|
185 |
+
"eval_loss": 0.8026367425918579,
|
186 |
+
"eval_runtime": 12.4166,
|
187 |
+
"eval_samples_per_second": 20.134,
|
188 |
+
"eval_steps_per_second": 2.577,
|
189 |
+
"step": 10
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.176,
|
193 |
+
"grad_norm": 32.25,
|
194 |
+
"learning_rate": 4.631147540983607e-05,
|
195 |
+
"loss": 0.9161,
|
196 |
+
"step": 11
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.176,
|
200 |
+
"eval_exact_match": 0.02040816326530612,
|
201 |
+
"eval_f1_a": 0.5608108108108107,
|
202 |
+
"eval_f1_m": 0.36614026563006147,
|
203 |
+
"eval_loss": 0.8101338148117065,
|
204 |
+
"eval_runtime": 12.5325,
|
205 |
+
"eval_samples_per_second": 19.948,
|
206 |
+
"eval_steps_per_second": 2.553,
|
207 |
+
"step": 11
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.192,
|
211 |
+
"grad_norm": 36.25,
|
212 |
+
"learning_rate": 4.59016393442623e-05,
|
213 |
+
"loss": 0.8093,
|
214 |
+
"step": 12
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.192,
|
218 |
+
"eval_exact_match": 0.02040816326530612,
|
219 |
+
"eval_f1_a": 0.5429553264604812,
|
220 |
+
"eval_f1_m": 0.35214683275907754,
|
221 |
+
"eval_loss": 0.7952831983566284,
|
222 |
+
"eval_runtime": 12.4346,
|
223 |
+
"eval_samples_per_second": 20.105,
|
224 |
+
"eval_steps_per_second": 2.573,
|
225 |
+
"step": 12
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.208,
|
229 |
+
"grad_norm": 11.0,
|
230 |
+
"learning_rate": 4.549180327868853e-05,
|
231 |
+
"loss": 0.6146,
|
232 |
+
"step": 13
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.208,
|
236 |
+
"eval_exact_match": 0.02040816326530612,
|
237 |
+
"eval_f1_a": 0.5441696113074205,
|
238 |
+
"eval_f1_m": 0.3687700621374089,
|
239 |
+
"eval_loss": 0.7707070112228394,
|
240 |
+
"eval_runtime": 12.5246,
|
241 |
+
"eval_samples_per_second": 19.961,
|
242 |
+
"eval_steps_per_second": 2.555,
|
243 |
+
"step": 13
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.224,
|
247 |
+
"grad_norm": 14.625,
|
248 |
+
"learning_rate": 4.508196721311476e-05,
|
249 |
+
"loss": 0.7804,
|
250 |
+
"step": 14
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.224,
|
254 |
+
"eval_exact_match": 0.02040816326530612,
|
255 |
+
"eval_f1_a": 0.5376344086021505,
|
256 |
+
"eval_f1_m": 0.36071490867409234,
|
257 |
+
"eval_loss": 0.7593163847923279,
|
258 |
+
"eval_runtime": 12.5202,
|
259 |
+
"eval_samples_per_second": 19.968,
|
260 |
+
"eval_steps_per_second": 2.556,
|
261 |
+
"step": 14
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.24,
|
265 |
+
"grad_norm": 12.6875,
|
266 |
+
"learning_rate": 4.467213114754098e-05,
|
267 |
+
"loss": 0.75,
|
268 |
+
"step": 15
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.24,
|
272 |
+
"eval_exact_match": 0.0,
|
273 |
+
"eval_f1_a": 0.5300353356890458,
|
274 |
+
"eval_f1_m": 0.3416269105044615,
|
275 |
+
"eval_loss": 0.7546816468238831,
|
276 |
+
"eval_runtime": 12.53,
|
277 |
+
"eval_samples_per_second": 19.952,
|
278 |
+
"eval_steps_per_second": 2.554,
|
279 |
+
"step": 15
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.256,
|
283 |
+
"grad_norm": 10.4375,
|
284 |
+
"learning_rate": 4.426229508196721e-05,
|
285 |
+
"loss": 0.9339,
|
286 |
+
"step": 16
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.256,
|
290 |
+
"eval_exact_match": 0.0,
|
291 |
+
"eval_f1_a": 0.5454545454545454,
|
292 |
+
"eval_f1_m": 0.3630654492899391,
|
293 |
+
"eval_loss": 0.7366230487823486,
|
294 |
+
"eval_runtime": 12.5191,
|
295 |
+
"eval_samples_per_second": 19.97,
|
296 |
+
"eval_steps_per_second": 2.556,
|
297 |
+
"step": 16
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.272,
|
301 |
+
"grad_norm": 36.75,
|
302 |
+
"learning_rate": 4.3852459016393444e-05,
|
303 |
+
"loss": 0.6286,
|
304 |
+
"step": 17
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.272,
|
308 |
+
"eval_exact_match": 0.02040816326530612,
|
309 |
+
"eval_f1_a": 0.528,
|
310 |
+
"eval_f1_m": 0.38775957602488215,
|
311 |
+
"eval_loss": 0.712777316570282,
|
312 |
+
"eval_runtime": 12.5294,
|
313 |
+
"eval_samples_per_second": 19.953,
|
314 |
+
"eval_steps_per_second": 2.554,
|
315 |
+
"step": 17
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.288,
|
319 |
+
"grad_norm": 31.75,
|
320 |
+
"learning_rate": 4.3442622950819674e-05,
|
321 |
+
"loss": 0.7253,
|
322 |
+
"step": 18
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.288,
|
326 |
+
"eval_exact_match": 0.02040816326530612,
|
327 |
+
"eval_f1_a": 0.5301204819277109,
|
328 |
+
"eval_f1_m": 0.39053531502511096,
|
329 |
+
"eval_loss": 0.7025195360183716,
|
330 |
+
"eval_runtime": 12.5183,
|
331 |
+
"eval_samples_per_second": 19.971,
|
332 |
+
"eval_steps_per_second": 2.556,
|
333 |
+
"step": 18
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.304,
|
337 |
+
"grad_norm": 22.0,
|
338 |
+
"learning_rate": 4.3032786885245904e-05,
|
339 |
+
"loss": 0.5984,
|
340 |
+
"step": 19
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.304,
|
344 |
+
"eval_exact_match": 0.04081632653061224,
|
345 |
+
"eval_f1_a": 0.5045045045045046,
|
346 |
+
"eval_f1_m": 0.4079482875401243,
|
347 |
+
"eval_loss": 0.6883164048194885,
|
348 |
+
"eval_runtime": 12.5119,
|
349 |
+
"eval_samples_per_second": 19.981,
|
350 |
+
"eval_steps_per_second": 2.558,
|
351 |
+
"step": 19
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.32,
|
355 |
+
"grad_norm": 24.75,
|
356 |
+
"learning_rate": 4.262295081967213e-05,
|
357 |
+
"loss": 0.6453,
|
358 |
+
"step": 20
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 0.32,
|
362 |
+
"eval_exact_match": 0.04081632653061224,
|
363 |
+
"eval_f1_a": 0.4931506849315069,
|
364 |
+
"eval_f1_m": 0.4012221905079048,
|
365 |
+
"eval_loss": 0.6845566630363464,
|
366 |
+
"eval_runtime": 12.5289,
|
367 |
+
"eval_samples_per_second": 19.954,
|
368 |
+
"eval_steps_per_second": 2.554,
|
369 |
+
"step": 20
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.336,
|
373 |
+
"grad_norm": 8.3125,
|
374 |
+
"learning_rate": 4.2213114754098365e-05,
|
375 |
+
"loss": 0.58,
|
376 |
+
"step": 21
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.336,
|
380 |
+
"eval_exact_match": 0.02040816326530612,
|
381 |
+
"eval_f1_a": 0.4859813084112149,
|
382 |
+
"eval_f1_m": 0.4041376424029486,
|
383 |
+
"eval_loss": 0.6770976781845093,
|
384 |
+
"eval_runtime": 12.4164,
|
385 |
+
"eval_samples_per_second": 20.135,
|
386 |
+
"eval_steps_per_second": 2.577,
|
387 |
+
"step": 21
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.352,
|
391 |
+
"grad_norm": 28.625,
|
392 |
+
"learning_rate": 4.1803278688524595e-05,
|
393 |
+
"loss": 0.6812,
|
394 |
+
"step": 22
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.352,
|
398 |
+
"eval_exact_match": 0.0,
|
399 |
+
"eval_f1_a": 0.509090909090909,
|
400 |
+
"eval_f1_m": 0.40605698156718567,
|
401 |
+
"eval_loss": 0.6734863519668579,
|
402 |
+
"eval_runtime": 12.5159,
|
403 |
+
"eval_samples_per_second": 19.975,
|
404 |
+
"eval_steps_per_second": 2.557,
|
405 |
+
"step": 22
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.368,
|
409 |
+
"grad_norm": 18.25,
|
410 |
+
"learning_rate": 4.1393442622950826e-05,
|
411 |
+
"loss": 0.4762,
|
412 |
+
"step": 23
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.368,
|
416 |
+
"eval_exact_match": 0.02040816326530612,
|
417 |
+
"eval_f1_a": 0.4976076555023924,
|
418 |
+
"eval_f1_m": 0.4171717738044269,
|
419 |
+
"eval_loss": 0.6683046817779541,
|
420 |
+
"eval_runtime": 12.5214,
|
421 |
+
"eval_samples_per_second": 19.966,
|
422 |
+
"eval_steps_per_second": 2.556,
|
423 |
+
"step": 23
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.384,
|
427 |
+
"grad_norm": 9.125,
|
428 |
+
"learning_rate": 4.098360655737705e-05,
|
429 |
+
"loss": 0.6075,
|
430 |
+
"step": 24
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.384,
|
434 |
+
"eval_exact_match": 0.02040816326530612,
|
435 |
+
"eval_f1_a": 0.48756218905472637,
|
436 |
+
"eval_f1_m": 0.41513432878979106,
|
437 |
+
"eval_loss": 0.6622753739356995,
|
438 |
+
"eval_runtime": 12.4157,
|
439 |
+
"eval_samples_per_second": 20.136,
|
440 |
+
"eval_steps_per_second": 2.577,
|
441 |
+
"step": 24
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.4,
|
445 |
+
"grad_norm": 10.1875,
|
446 |
+
"learning_rate": 4.057377049180328e-05,
|
447 |
+
"loss": 0.6313,
|
448 |
+
"step": 25
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.4,
|
452 |
+
"eval_exact_match": 0.04081632653061224,
|
453 |
+
"eval_f1_a": 0.48087431693989074,
|
454 |
+
"eval_f1_m": 0.4350705716852176,
|
455 |
+
"eval_loss": 0.6575761437416077,
|
456 |
+
"eval_runtime": 12.5232,
|
457 |
+
"eval_samples_per_second": 19.963,
|
458 |
+
"eval_steps_per_second": 2.555,
|
459 |
+
"step": 25
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.416,
|
463 |
+
"grad_norm": 14.0,
|
464 |
+
"learning_rate": 4.016393442622951e-05,
|
465 |
+
"loss": 0.6486,
|
466 |
+
"step": 26
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.416,
|
470 |
+
"eval_exact_match": 0.04081632653061224,
|
471 |
+
"eval_f1_a": 0.4606741573033708,
|
472 |
+
"eval_f1_m": 0.44082196315089484,
|
473 |
+
"eval_loss": 0.6529648303985596,
|
474 |
+
"eval_runtime": 12.5257,
|
475 |
+
"eval_samples_per_second": 19.959,
|
476 |
+
"eval_steps_per_second": 2.555,
|
477 |
+
"step": 26
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.432,
|
481 |
+
"grad_norm": 14.9375,
|
482 |
+
"learning_rate": 3.975409836065574e-05,
|
483 |
+
"loss": 0.8356,
|
484 |
+
"step": 27
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.432,
|
488 |
+
"eval_exact_match": 0.04081632653061224,
|
489 |
+
"eval_f1_a": 0.44311377245508976,
|
490 |
+
"eval_f1_m": 0.4505972219057453,
|
491 |
+
"eval_loss": 0.6500390768051147,
|
492 |
+
"eval_runtime": 12.5271,
|
493 |
+
"eval_samples_per_second": 19.957,
|
494 |
+
"eval_steps_per_second": 2.554,
|
495 |
+
"step": 27
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.448,
|
499 |
+
"grad_norm": 9.125,
|
500 |
+
"learning_rate": 3.934426229508197e-05,
|
501 |
+
"loss": 0.6429,
|
502 |
+
"step": 28
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.448,
|
506 |
+
"eval_exact_match": 0.061224489795918366,
|
507 |
+
"eval_f1_a": 0.43636363636363634,
|
508 |
+
"eval_f1_m": 0.4468071344421886,
|
509 |
+
"eval_loss": 0.6493672132492065,
|
510 |
+
"eval_runtime": 12.5212,
|
511 |
+
"eval_samples_per_second": 19.966,
|
512 |
+
"eval_steps_per_second": 2.556,
|
513 |
+
"step": 28
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.464,
|
517 |
+
"grad_norm": 15.8125,
|
518 |
+
"learning_rate": 3.89344262295082e-05,
|
519 |
+
"loss": 0.6248,
|
520 |
+
"step": 29
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.464,
|
524 |
+
"eval_exact_match": 0.10204081632653061,
|
525 |
+
"eval_f1_a": 0.38926174496644295,
|
526 |
+
"eval_f1_m": 0.4801647632079804,
|
527 |
+
"eval_loss": 0.6509453058242798,
|
528 |
+
"eval_runtime": 12.535,
|
529 |
+
"eval_samples_per_second": 19.944,
|
530 |
+
"eval_steps_per_second": 2.553,
|
531 |
+
"step": 29
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.48,
|
535 |
+
"grad_norm": 24.5,
|
536 |
+
"learning_rate": 3.8524590163934424e-05,
|
537 |
+
"loss": 0.4855,
|
538 |
+
"step": 30
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.48,
|
542 |
+
"eval_exact_match": 0.061224489795918366,
|
543 |
+
"eval_f1_a": 0.3283582089552239,
|
544 |
+
"eval_f1_m": 0.46286459638800564,
|
545 |
+
"eval_loss": 0.6590214967727661,
|
546 |
+
"eval_runtime": 12.5171,
|
547 |
+
"eval_samples_per_second": 19.973,
|
548 |
+
"eval_steps_per_second": 2.557,
|
549 |
+
"step": 30
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.496,
|
553 |
+
"grad_norm": 31.375,
|
554 |
+
"learning_rate": 3.8114754098360655e-05,
|
555 |
+
"loss": 0.7308,
|
556 |
+
"step": 31
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.496,
|
560 |
+
"eval_exact_match": 0.02040816326530612,
|
561 |
+
"eval_f1_a": 0.30534351145038163,
|
562 |
+
"eval_f1_m": 0.4485788821022914,
|
563 |
+
"eval_loss": 0.6624687314033508,
|
564 |
+
"eval_runtime": 12.4214,
|
565 |
+
"eval_samples_per_second": 20.127,
|
566 |
+
"eval_steps_per_second": 2.576,
|
567 |
+
"step": 31
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.512,
|
571 |
+
"grad_norm": 28.125,
|
572 |
+
"learning_rate": 3.7704918032786885e-05,
|
573 |
+
"loss": 0.7749,
|
574 |
+
"step": 32
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 0.512,
|
578 |
+
"eval_exact_match": 0.04081632653061224,
|
579 |
+
"eval_f1_a": 0.31007751937984496,
|
580 |
+
"eval_f1_m": 0.4561152299747737,
|
581 |
+
"eval_loss": 0.6629375219345093,
|
582 |
+
"eval_runtime": 12.5333,
|
583 |
+
"eval_samples_per_second": 19.947,
|
584 |
+
"eval_steps_per_second": 2.553,
|
585 |
+
"step": 32
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.528,
|
589 |
+
"grad_norm": 25.125,
|
590 |
+
"learning_rate": 3.729508196721312e-05,
|
591 |
+
"loss": 0.7449,
|
592 |
+
"step": 33
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.528,
|
596 |
+
"eval_exact_match": 0.04081632653061224,
|
597 |
+
"eval_f1_a": 0.34782608695652173,
|
598 |
+
"eval_f1_m": 0.45786965468838214,
|
599 |
+
"eval_loss": 0.6554140448570251,
|
600 |
+
"eval_runtime": 12.5362,
|
601 |
+
"eval_samples_per_second": 19.942,
|
602 |
+
"eval_steps_per_second": 2.553,
|
603 |
+
"step": 33
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.544,
|
607 |
+
"grad_norm": 12.1875,
|
608 |
+
"learning_rate": 3.6885245901639346e-05,
|
609 |
+
"loss": 0.7871,
|
610 |
+
"step": 34
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.544,
|
614 |
+
"eval_exact_match": 0.02040816326530612,
|
615 |
+
"eval_f1_a": 0.3382352941176471,
|
616 |
+
"eval_f1_m": 0.4546140667389167,
|
617 |
+
"eval_loss": 0.6557744145393372,
|
618 |
+
"eval_runtime": 12.5339,
|
619 |
+
"eval_samples_per_second": 19.946,
|
620 |
+
"eval_steps_per_second": 2.553,
|
621 |
+
"step": 34
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.56,
|
625 |
+
"grad_norm": 10.5625,
|
626 |
+
"learning_rate": 3.6475409836065576e-05,
|
627 |
+
"loss": 0.4428,
|
628 |
+
"step": 35
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.56,
|
632 |
+
"eval_exact_match": 0.02040816326530612,
|
633 |
+
"eval_f1_a": 0.2900763358778626,
|
634 |
+
"eval_f1_m": 0.4422134787981126,
|
635 |
+
"eval_loss": 0.6567177772521973,
|
636 |
+
"eval_runtime": 12.5258,
|
637 |
+
"eval_samples_per_second": 19.959,
|
638 |
+
"eval_steps_per_second": 2.555,
|
639 |
+
"step": 35
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.576,
|
643 |
+
"grad_norm": 37.75,
|
644 |
+
"learning_rate": 3.6065573770491806e-05,
|
645 |
+
"loss": 0.8155,
|
646 |
+
"step": 36
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.576,
|
650 |
+
"eval_exact_match": 0.02040816326530612,
|
651 |
+
"eval_f1_a": 0.3333333333333333,
|
652 |
+
"eval_f1_m": 0.4582583816077213,
|
653 |
+
"eval_loss": 0.6531835794448853,
|
654 |
+
"eval_runtime": 12.5226,
|
655 |
+
"eval_samples_per_second": 19.964,
|
656 |
+
"eval_steps_per_second": 2.555,
|
657 |
+
"step": 36
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.592,
|
661 |
+
"grad_norm": 6.53125,
|
662 |
+
"learning_rate": 3.5655737704918037e-05,
|
663 |
+
"loss": 0.6122,
|
664 |
+
"step": 37
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.592,
|
668 |
+
"eval_exact_match": 0.02040816326530612,
|
669 |
+
"eval_f1_a": 0.3230769230769231,
|
670 |
+
"eval_f1_m": 0.45850133593230824,
|
671 |
+
"eval_loss": 0.6510556936264038,
|
672 |
+
"eval_runtime": 12.5321,
|
673 |
+
"eval_samples_per_second": 19.949,
|
674 |
+
"eval_steps_per_second": 2.553,
|
675 |
+
"step": 37
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.608,
|
679 |
+
"grad_norm": 20.0,
|
680 |
+
"learning_rate": 3.524590163934427e-05,
|
681 |
+
"loss": 0.6843,
|
682 |
+
"step": 38
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.608,
|
686 |
+
"eval_exact_match": 0.02040816326530612,
|
687 |
+
"eval_f1_a": 0.3382352941176471,
|
688 |
+
"eval_f1_m": 0.4538476562786286,
|
689 |
+
"eval_loss": 0.6473007798194885,
|
690 |
+
"eval_runtime": 12.4172,
|
691 |
+
"eval_samples_per_second": 20.133,
|
692 |
+
"eval_steps_per_second": 2.577,
|
693 |
+
"step": 38
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.624,
|
697 |
+
"grad_norm": 22.25,
|
698 |
+
"learning_rate": 3.483606557377049e-05,
|
699 |
+
"loss": 0.6606,
|
700 |
+
"step": 39
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.624,
|
704 |
+
"eval_exact_match": 0.061224489795918366,
|
705 |
+
"eval_f1_a": 0.42580645161290326,
|
706 |
+
"eval_f1_m": 0.48005761412123965,
|
707 |
+
"eval_loss": 0.6421992182731628,
|
708 |
+
"eval_runtime": 12.5309,
|
709 |
+
"eval_samples_per_second": 19.951,
|
710 |
+
"eval_steps_per_second": 2.554,
|
711 |
+
"step": 39
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.64,
|
715 |
+
"grad_norm": 19.5,
|
716 |
+
"learning_rate": 3.442622950819672e-05,
|
717 |
+
"loss": 0.6284,
|
718 |
+
"step": 40
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.64,
|
722 |
+
"eval_exact_match": 0.08163265306122448,
|
723 |
+
"eval_f1_a": 0.4331210191082803,
|
724 |
+
"eval_f1_m": 0.4849652914778965,
|
725 |
+
"eval_loss": 0.6393261551856995,
|
726 |
+
"eval_runtime": 12.4078,
|
727 |
+
"eval_samples_per_second": 20.149,
|
728 |
+
"eval_steps_per_second": 2.579,
|
729 |
+
"step": 40
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.656,
|
733 |
+
"grad_norm": 24.0,
|
734 |
+
"learning_rate": 3.401639344262295e-05,
|
735 |
+
"loss": 0.6525,
|
736 |
+
"step": 41
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.656,
|
740 |
+
"eval_exact_match": 0.10204081632653061,
|
741 |
+
"eval_f1_a": 0.45977011494252873,
|
742 |
+
"eval_f1_m": 0.4644901883497321,
|
743 |
+
"eval_loss": 0.6380175948143005,
|
744 |
+
"eval_runtime": 12.5392,
|
745 |
+
"eval_samples_per_second": 19.938,
|
746 |
+
"eval_steps_per_second": 2.552,
|
747 |
+
"step": 41
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.672,
|
751 |
+
"grad_norm": 26.875,
|
752 |
+
"learning_rate": 3.360655737704918e-05,
|
753 |
+
"loss": 0.7537,
|
754 |
+
"step": 42
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.672,
|
758 |
+
"eval_exact_match": 0.08163265306122448,
|
759 |
+
"eval_f1_a": 0.4816753926701571,
|
760 |
+
"eval_f1_m": 0.4603846000604704,
|
761 |
+
"eval_loss": 0.6373457312583923,
|
762 |
+
"eval_runtime": 12.5124,
|
763 |
+
"eval_samples_per_second": 19.98,
|
764 |
+
"eval_steps_per_second": 2.557,
|
765 |
+
"step": 42
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.688,
|
769 |
+
"grad_norm": 8.5625,
|
770 |
+
"learning_rate": 3.319672131147541e-05,
|
771 |
+
"loss": 0.6196,
|
772 |
+
"step": 43
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.688,
|
776 |
+
"eval_exact_match": 0.08163265306122448,
|
777 |
+
"eval_f1_a": 0.5118483412322276,
|
778 |
+
"eval_f1_m": 0.4378736642842286,
|
779 |
+
"eval_loss": 0.641525387763977,
|
780 |
+
"eval_runtime": 12.5135,
|
781 |
+
"eval_samples_per_second": 19.978,
|
782 |
+
"eval_steps_per_second": 2.557,
|
783 |
+
"step": 43
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.704,
|
787 |
+
"grad_norm": 11.5625,
|
788 |
+
"learning_rate": 3.2786885245901635e-05,
|
789 |
+
"loss": 0.7105,
|
790 |
+
"step": 44
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.704,
|
794 |
+
"eval_exact_match": 0.08163265306122448,
|
795 |
+
"eval_f1_a": 0.5407725321888414,
|
796 |
+
"eval_f1_m": 0.42079032079032075,
|
797 |
+
"eval_loss": 0.6511328220367432,
|
798 |
+
"eval_runtime": 12.5196,
|
799 |
+
"eval_samples_per_second": 19.969,
|
800 |
+
"eval_steps_per_second": 2.556,
|
801 |
+
"step": 44
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.72,
|
805 |
+
"grad_norm": 41.75,
|
806 |
+
"learning_rate": 3.237704918032787e-05,
|
807 |
+
"loss": 0.7902,
|
808 |
+
"step": 45
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.72,
|
812 |
+
"eval_exact_match": 0.061224489795918366,
|
813 |
+
"eval_f1_a": 0.5338983050847457,
|
814 |
+
"eval_f1_m": 0.4120925559701069,
|
815 |
+
"eval_loss": 0.6530937552452087,
|
816 |
+
"eval_runtime": 12.5207,
|
817 |
+
"eval_samples_per_second": 19.967,
|
818 |
+
"eval_steps_per_second": 2.556,
|
819 |
+
"step": 45
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.736,
|
823 |
+
"grad_norm": 30.25,
|
824 |
+
"learning_rate": 3.19672131147541e-05,
|
825 |
+
"loss": 0.621,
|
826 |
+
"step": 46
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.736,
|
830 |
+
"eval_exact_match": 0.061224489795918366,
|
831 |
+
"eval_f1_a": 0.5423728813559323,
|
832 |
+
"eval_f1_m": 0.4205959573306511,
|
833 |
+
"eval_loss": 0.6510214805603027,
|
834 |
+
"eval_runtime": 12.5251,
|
835 |
+
"eval_samples_per_second": 19.96,
|
836 |
+
"eval_steps_per_second": 2.555,
|
837 |
+
"step": 46
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.752,
|
841 |
+
"grad_norm": 13.0,
|
842 |
+
"learning_rate": 3.155737704918033e-05,
|
843 |
+
"loss": 0.8848,
|
844 |
+
"step": 47
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.752,
|
848 |
+
"eval_exact_match": 0.061224489795918366,
|
849 |
+
"eval_f1_a": 0.5485232067510549,
|
850 |
+
"eval_f1_m": 0.42849197287972796,
|
851 |
+
"eval_loss": 0.6499238014221191,
|
852 |
+
"eval_runtime": 12.5214,
|
853 |
+
"eval_samples_per_second": 19.966,
|
854 |
+
"eval_steps_per_second": 2.556,
|
855 |
+
"step": 47
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.768,
|
859 |
+
"grad_norm": 51.25,
|
860 |
+
"learning_rate": 3.114754098360656e-05,
|
861 |
+
"loss": 0.876,
|
862 |
+
"step": 48
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 0.768,
|
866 |
+
"eval_exact_match": 0.08163265306122448,
|
867 |
+
"eval_f1_a": 0.5391304347826087,
|
868 |
+
"eval_f1_m": 0.4377896479937296,
|
869 |
+
"eval_loss": 0.6470175981521606,
|
870 |
+
"eval_runtime": 12.5243,
|
871 |
+
"eval_samples_per_second": 19.961,
|
872 |
+
"eval_steps_per_second": 2.555,
|
873 |
+
"step": 48
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.784,
|
877 |
+
"grad_norm": 41.25,
|
878 |
+
"learning_rate": 3.073770491803279e-05,
|
879 |
+
"loss": 0.7048,
|
880 |
+
"step": 49
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.784,
|
884 |
+
"eval_exact_match": 0.08163265306122448,
|
885 |
+
"eval_f1_a": 0.5302325581395348,
|
886 |
+
"eval_f1_m": 0.4584981911512524,
|
887 |
+
"eval_loss": 0.6386250257492065,
|
888 |
+
"eval_runtime": 12.5286,
|
889 |
+
"eval_samples_per_second": 19.954,
|
890 |
+
"eval_steps_per_second": 2.554,
|
891 |
+
"step": 49
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.8,
|
895 |
+
"grad_norm": 17.625,
|
896 |
+
"learning_rate": 3.0327868852459017e-05,
|
897 |
+
"loss": 0.8217,
|
898 |
+
"step": 50
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.8,
|
902 |
+
"eval_exact_match": 0.061224489795918366,
|
903 |
+
"eval_f1_a": 0.5258215962441315,
|
904 |
+
"eval_f1_m": 0.45543696666145644,
|
905 |
+
"eval_loss": 0.6384491920471191,
|
906 |
+
"eval_runtime": 12.5207,
|
907 |
+
"eval_samples_per_second": 19.967,
|
908 |
+
"eval_steps_per_second": 2.556,
|
909 |
+
"step": 50
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.816,
|
913 |
+
"grad_norm": 24.0,
|
914 |
+
"learning_rate": 2.9918032786885248e-05,
|
915 |
+
"loss": 0.6093,
|
916 |
+
"step": 51
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.816,
|
920 |
+
"eval_exact_match": 0.08163265306122448,
|
921 |
+
"eval_f1_a": 0.5125628140703518,
|
922 |
+
"eval_f1_m": 0.48412188718311155,
|
923 |
+
"eval_loss": 0.6337217092514038,
|
924 |
+
"eval_runtime": 12.519,
|
925 |
+
"eval_samples_per_second": 19.97,
|
926 |
+
"eval_steps_per_second": 2.556,
|
927 |
+
"step": 51
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.832,
|
931 |
+
"grad_norm": 28.5,
|
932 |
+
"learning_rate": 2.9508196721311478e-05,
|
933 |
+
"loss": 0.5875,
|
934 |
+
"step": 52
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.832,
|
938 |
+
"eval_exact_match": 0.08163265306122448,
|
939 |
+
"eval_f1_a": 0.4444444444444445,
|
940 |
+
"eval_f1_m": 0.4678045310698371,
|
941 |
+
"eval_loss": 0.6313378810882568,
|
942 |
+
"eval_runtime": 12.5146,
|
943 |
+
"eval_samples_per_second": 19.977,
|
944 |
+
"eval_steps_per_second": 2.557,
|
945 |
+
"step": 52
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.848,
|
949 |
+
"grad_norm": 46.25,
|
950 |
+
"learning_rate": 2.9098360655737705e-05,
|
951 |
+
"loss": 0.5525,
|
952 |
+
"step": 53
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.848,
|
956 |
+
"eval_exact_match": 0.061224489795918366,
|
957 |
+
"eval_f1_a": 0.380952380952381,
|
958 |
+
"eval_f1_m": 0.48287293938554443,
|
959 |
+
"eval_loss": 0.6318368911743164,
|
960 |
+
"eval_runtime": 12.5161,
|
961 |
+
"eval_samples_per_second": 19.974,
|
962 |
+
"eval_steps_per_second": 2.557,
|
963 |
+
"step": 53
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.864,
|
967 |
+
"grad_norm": 17.625,
|
968 |
+
"learning_rate": 2.8688524590163935e-05,
|
969 |
+
"loss": 0.632,
|
970 |
+
"step": 54
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.864,
|
974 |
+
"eval_exact_match": 0.02040816326530612,
|
975 |
+
"eval_f1_a": 0.2992125984251968,
|
976 |
+
"eval_f1_m": 0.4569305710962373,
|
977 |
+
"eval_loss": 0.6356464624404907,
|
978 |
+
"eval_runtime": 12.5236,
|
979 |
+
"eval_samples_per_second": 19.962,
|
980 |
+
"eval_steps_per_second": 2.555,
|
981 |
+
"step": 54
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.88,
|
985 |
+
"grad_norm": 8.875,
|
986 |
+
"learning_rate": 2.8278688524590162e-05,
|
987 |
+
"loss": 0.5346,
|
988 |
+
"step": 55
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.88,
|
992 |
+
"eval_exact_match": 0.0,
|
993 |
+
"eval_f1_a": 0.24999999999999997,
|
994 |
+
"eval_f1_m": 0.4310802309601829,
|
995 |
+
"eval_loss": 0.6434394717216492,
|
996 |
+
"eval_runtime": 12.5233,
|
997 |
+
"eval_samples_per_second": 19.963,
|
998 |
+
"eval_steps_per_second": 2.555,
|
999 |
+
"step": 55
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.896,
|
1003 |
+
"grad_norm": 11.25,
|
1004 |
+
"learning_rate": 2.7868852459016392e-05,
|
1005 |
+
"loss": 0.4656,
|
1006 |
+
"step": 56
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.896,
|
1010 |
+
"eval_exact_match": 0.0,
|
1011 |
+
"eval_f1_a": 0.11009174311926605,
|
1012 |
+
"eval_f1_m": 0.38233843987145305,
|
1013 |
+
"eval_loss": 0.655026376247406,
|
1014 |
+
"eval_runtime": 12.5245,
|
1015 |
+
"eval_samples_per_second": 19.961,
|
1016 |
+
"eval_steps_per_second": 2.555,
|
1017 |
+
"step": 56
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.912,
|
1021 |
+
"grad_norm": 5.96875,
|
1022 |
+
"learning_rate": 2.7459016393442626e-05,
|
1023 |
+
"loss": 0.6506,
|
1024 |
+
"step": 57
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.912,
|
1028 |
+
"eval_exact_match": 0.0,
|
1029 |
+
"eval_f1_a": 0.05714285714285714,
|
1030 |
+
"eval_f1_m": 0.3669373443683168,
|
1031 |
+
"eval_loss": 0.6712407469749451,
|
1032 |
+
"eval_runtime": 12.5217,
|
1033 |
+
"eval_samples_per_second": 19.965,
|
1034 |
+
"eval_steps_per_second": 2.556,
|
1035 |
+
"step": 57
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.928,
|
1039 |
+
"grad_norm": 47.75,
|
1040 |
+
"learning_rate": 2.7049180327868856e-05,
|
1041 |
+
"loss": 0.9128,
|
1042 |
+
"step": 58
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.928,
|
1046 |
+
"eval_exact_match": 0.0,
|
1047 |
+
"eval_f1_a": 0.038461538461538464,
|
1048 |
+
"eval_f1_m": 0.35922759380142344,
|
1049 |
+
"eval_loss": 0.6825835108757019,
|
1050 |
+
"eval_runtime": 12.5246,
|
1051 |
+
"eval_samples_per_second": 19.961,
|
1052 |
+
"eval_steps_per_second": 2.555,
|
1053 |
+
"step": 58
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.944,
|
1057 |
+
"grad_norm": 47.25,
|
1058 |
+
"learning_rate": 2.6639344262295087e-05,
|
1059 |
+
"loss": 0.8041,
|
1060 |
+
"step": 59
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.944,
|
1064 |
+
"eval_exact_match": 0.0,
|
1065 |
+
"eval_f1_a": 0.038461538461538464,
|
1066 |
+
"eval_f1_m": 0.35922759380142344,
|
1067 |
+
"eval_loss": 0.6874199509620667,
|
1068 |
+
"eval_runtime": 12.5257,
|
1069 |
+
"eval_samples_per_second": 19.959,
|
1070 |
+
"eval_steps_per_second": 2.555,
|
1071 |
+
"step": 59
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.96,
|
1075 |
+
"grad_norm": 34.0,
|
1076 |
+
"learning_rate": 2.6229508196721314e-05,
|
1077 |
+
"loss": 0.7979,
|
1078 |
+
"step": 60
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 0.96,
|
1082 |
+
"eval_exact_match": 0.0,
|
1083 |
+
"eval_f1_a": 0.038461538461538464,
|
1084 |
+
"eval_f1_m": 0.35922759380142344,
|
1085 |
+
"eval_loss": 0.6864975690841675,
|
1086 |
+
"eval_runtime": 12.5253,
|
1087 |
+
"eval_samples_per_second": 19.96,
|
1088 |
+
"eval_steps_per_second": 2.555,
|
1089 |
+
"step": 60
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.976,
|
1093 |
+
"grad_norm": 27.0,
|
1094 |
+
"learning_rate": 2.5819672131147544e-05,
|
1095 |
+
"loss": 0.626,
|
1096 |
+
"step": 61
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.976,
|
1100 |
+
"eval_exact_match": 0.0,
|
1101 |
+
"eval_f1_a": 0.038461538461538464,
|
1102 |
+
"eval_f1_m": 0.35922759380142344,
|
1103 |
+
"eval_loss": 0.6805967092514038,
|
1104 |
+
"eval_runtime": 12.5272,
|
1105 |
+
"eval_samples_per_second": 19.957,
|
1106 |
+
"eval_steps_per_second": 2.554,
|
1107 |
+
"step": 61
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.992,
|
1111 |
+
"grad_norm": 13.1875,
|
1112 |
+
"learning_rate": 2.540983606557377e-05,
|
1113 |
+
"loss": 0.5989,
|
1114 |
+
"step": 62
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.992,
|
1118 |
+
"eval_exact_match": 0.0,
|
1119 |
+
"eval_f1_a": 0.05714285714285714,
|
1120 |
+
"eval_f1_m": 0.3673908591075459,
|
1121 |
+
"eval_loss": 0.6689673066139221,
|
1122 |
+
"eval_runtime": 12.5192,
|
1123 |
+
"eval_samples_per_second": 19.969,
|
1124 |
+
"eval_steps_per_second": 2.556,
|
1125 |
+
"step": 62
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 1.008,
|
1129 |
+
"grad_norm": 38.25,
|
1130 |
+
"learning_rate": 2.5e-05,
|
1131 |
+
"loss": 0.6907,
|
1132 |
+
"step": 63
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 1.008,
|
1136 |
+
"eval_exact_match": 0.0,
|
1137 |
+
"eval_f1_a": 0.1272727272727273,
|
1138 |
+
"eval_f1_m": 0.3914323804779987,
|
1139 |
+
"eval_loss": 0.6558759808540344,
|
1140 |
+
"eval_runtime": 12.5213,
|
1141 |
+
"eval_samples_per_second": 19.966,
|
1142 |
+
"eval_steps_per_second": 2.556,
|
1143 |
+
"step": 63
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.024,
|
1147 |
+
"grad_norm": 20.375,
|
1148 |
+
"learning_rate": 2.459016393442623e-05,
|
1149 |
+
"loss": 0.5757,
|
1150 |
+
"step": 64
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.024,
|
1154 |
+
"eval_exact_match": 0.0,
|
1155 |
+
"eval_f1_a": 0.23333333333333334,
|
1156 |
+
"eval_f1_m": 0.426488394225489,
|
1157 |
+
"eval_loss": 0.6442788243293762,
|
1158 |
+
"eval_runtime": 12.5203,
|
1159 |
+
"eval_samples_per_second": 19.968,
|
1160 |
+
"eval_steps_per_second": 2.556,
|
1161 |
+
"step": 64
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.04,
|
1165 |
+
"grad_norm": 36.5,
|
1166 |
+
"learning_rate": 2.418032786885246e-05,
|
1167 |
+
"loss": 0.5626,
|
1168 |
+
"step": 65
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 1.04,
|
1172 |
+
"eval_exact_match": 0.02040816326530612,
|
1173 |
+
"eval_f1_a": 0.2677165354330709,
|
1174 |
+
"eval_f1_m": 0.4416973349446338,
|
1175 |
+
"eval_loss": 0.6316845417022705,
|
1176 |
+
"eval_runtime": 12.5217,
|
1177 |
+
"eval_samples_per_second": 19.965,
|
1178 |
+
"eval_steps_per_second": 2.556,
|
1179 |
+
"step": 65
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.056,
|
1183 |
+
"grad_norm": 33.0,
|
1184 |
+
"learning_rate": 2.377049180327869e-05,
|
1185 |
+
"loss": 0.6962,
|
1186 |
+
"step": 66
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 1.056,
|
1190 |
+
"eval_exact_match": 0.061224489795918366,
|
1191 |
+
"eval_f1_a": 0.3973509933774835,
|
1192 |
+
"eval_f1_m": 0.46887548559217224,
|
1193 |
+
"eval_loss": 0.6250205039978027,
|
1194 |
+
"eval_runtime": 12.5299,
|
1195 |
+
"eval_samples_per_second": 19.952,
|
1196 |
+
"eval_steps_per_second": 2.554,
|
1197 |
+
"step": 66
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.072,
|
1201 |
+
"grad_norm": 10.25,
|
1202 |
+
"learning_rate": 2.336065573770492e-05,
|
1203 |
+
"loss": 0.5543,
|
1204 |
+
"step": 67
|
1205 |
+
},
|
1206 |
+
{
|
1207 |
+
"epoch": 1.072,
|
1208 |
+
"eval_exact_match": 0.10204081632653061,
|
1209 |
+
"eval_f1_a": 0.5082872928176796,
|
1210 |
+
"eval_f1_m": 0.5018395736583011,
|
1211 |
+
"eval_loss": 0.6262060403823853,
|
1212 |
+
"eval_runtime": 12.5279,
|
1213 |
+
"eval_samples_per_second": 19.955,
|
1214 |
+
"eval_steps_per_second": 2.554,
|
1215 |
+
"step": 67
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.088,
|
1219 |
+
"grad_norm": 32.25,
|
1220 |
+
"learning_rate": 2.295081967213115e-05,
|
1221 |
+
"loss": 0.5034,
|
1222 |
+
"step": 68
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 1.088,
|
1226 |
+
"eval_exact_match": 0.061224489795918366,
|
1227 |
+
"eval_f1_a": 0.5471698113207547,
|
1228 |
+
"eval_f1_m": 0.4798306568714732,
|
1229 |
+
"eval_loss": 0.6319238543510437,
|
1230 |
+
"eval_runtime": 12.4294,
|
1231 |
+
"eval_samples_per_second": 20.114,
|
1232 |
+
"eval_steps_per_second": 2.575,
|
1233 |
+
"step": 68
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.104,
|
1237 |
+
"grad_norm": 44.0,
|
1238 |
+
"learning_rate": 2.254098360655738e-05,
|
1239 |
+
"loss": 0.6685,
|
1240 |
+
"step": 69
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 1.104,
|
1244 |
+
"eval_exact_match": 0.08163265306122448,
|
1245 |
+
"eval_f1_a": 0.5650224215246638,
|
1246 |
+
"eval_f1_m": 0.47513240727526446,
|
1247 |
+
"eval_loss": 0.6369560360908508,
|
1248 |
+
"eval_runtime": 12.5288,
|
1249 |
+
"eval_samples_per_second": 19.954,
|
1250 |
+
"eval_steps_per_second": 2.554,
|
1251 |
+
"step": 69
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.12,
|
1255 |
+
"grad_norm": 20.5,
|
1256 |
+
"learning_rate": 2.2131147540983607e-05,
|
1257 |
+
"loss": 0.7279,
|
1258 |
+
"step": 70
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 1.12,
|
1262 |
+
"eval_exact_match": 0.08163265306122448,
|
1263 |
+
"eval_f1_a": 0.5663716814159292,
|
1264 |
+
"eval_f1_m": 0.46904937466161956,
|
1265 |
+
"eval_loss": 0.6388349533081055,
|
1266 |
+
"eval_runtime": 12.5241,
|
1267 |
+
"eval_samples_per_second": 19.961,
|
1268 |
+
"eval_steps_per_second": 2.555,
|
1269 |
+
"step": 70
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.1360000000000001,
|
1273 |
+
"grad_norm": 26.75,
|
1274 |
+
"learning_rate": 2.1721311475409837e-05,
|
1275 |
+
"loss": 0.6486,
|
1276 |
+
"step": 71
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.1360000000000001,
|
1280 |
+
"eval_exact_match": 0.10204081632653061,
|
1281 |
+
"eval_f1_a": 0.5826086956521739,
|
1282 |
+
"eval_f1_m": 0.4729702836845694,
|
1283 |
+
"eval_loss": 0.6392431855201721,
|
1284 |
+
"eval_runtime": 12.5238,
|
1285 |
+
"eval_samples_per_second": 19.962,
|
1286 |
+
"eval_steps_per_second": 2.555,
|
1287 |
+
"step": 71
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.152,
|
1291 |
+
"grad_norm": 4.875,
|
1292 |
+
"learning_rate": 2.1311475409836064e-05,
|
1293 |
+
"loss": 0.7069,
|
1294 |
+
"step": 72
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.152,
|
1298 |
+
"eval_exact_match": 0.08163265306122448,
|
1299 |
+
"eval_f1_a": 0.5836909871244634,
|
1300 |
+
"eval_f1_m": 0.47516055373198224,
|
1301 |
+
"eval_loss": 0.6390937566757202,
|
1302 |
+
"eval_runtime": 12.4268,
|
1303 |
+
"eval_samples_per_second": 20.118,
|
1304 |
+
"eval_steps_per_second": 2.575,
|
1305 |
+
"step": 72
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.168,
|
1309 |
+
"grad_norm": 7.375,
|
1310 |
+
"learning_rate": 2.0901639344262298e-05,
|
1311 |
+
"loss": 0.597,
|
1312 |
+
"step": 73
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.168,
|
1316 |
+
"eval_exact_match": 0.08163265306122448,
|
1317 |
+
"eval_f1_a": 0.5872340425531916,
|
1318 |
+
"eval_f1_m": 0.47219651097202114,
|
1319 |
+
"eval_loss": 0.6382343769073486,
|
1320 |
+
"eval_runtime": 12.5204,
|
1321 |
+
"eval_samples_per_second": 19.967,
|
1322 |
+
"eval_steps_per_second": 2.556,
|
1323 |
+
"step": 73
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.184,
|
1327 |
+
"grad_norm": 6.03125,
|
1328 |
+
"learning_rate": 2.0491803278688525e-05,
|
1329 |
+
"loss": 0.5629,
|
1330 |
+
"step": 74
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 1.184,
|
1334 |
+
"eval_exact_match": 0.08163265306122448,
|
1335 |
+
"eval_f1_a": 0.6050420168067226,
|
1336 |
+
"eval_f1_m": 0.4974637607290668,
|
1337 |
+
"eval_loss": 0.6368105411529541,
|
1338 |
+
"eval_runtime": 12.4204,
|
1339 |
+
"eval_samples_per_second": 20.128,
|
1340 |
+
"eval_steps_per_second": 2.576,
|
1341 |
+
"step": 74
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.2,
|
1345 |
+
"grad_norm": 12.5625,
|
1346 |
+
"learning_rate": 2.0081967213114755e-05,
|
1347 |
+
"loss": 0.4962,
|
1348 |
+
"step": 75
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 1.2,
|
1352 |
+
"eval_exact_match": 0.08163265306122448,
|
1353 |
+
"eval_f1_a": 0.5983606557377048,
|
1354 |
+
"eval_f1_m": 0.48530426489610157,
|
1355 |
+
"eval_loss": 0.6430624723434448,
|
1356 |
+
"eval_runtime": 12.5269,
|
1357 |
+
"eval_samples_per_second": 19.957,
|
1358 |
+
"eval_steps_per_second": 2.555,
|
1359 |
+
"step": 75
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.216,
|
1363 |
+
"grad_norm": 33.5,
|
1364 |
+
"learning_rate": 1.9672131147540985e-05,
|
1365 |
+
"loss": 0.6281,
|
1366 |
+
"step": 76
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 1.216,
|
1370 |
+
"eval_exact_match": 0.08163265306122448,
|
1371 |
+
"eval_f1_a": 0.6040816326530611,
|
1372 |
+
"eval_f1_m": 0.4916509227733717,
|
1373 |
+
"eval_loss": 0.6421269774436951,
|
1374 |
+
"eval_runtime": 12.5178,
|
1375 |
+
"eval_samples_per_second": 19.972,
|
1376 |
+
"eval_steps_per_second": 2.556,
|
1377 |
+
"step": 76
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.232,
|
1381 |
+
"grad_norm": 8.375,
|
1382 |
+
"learning_rate": 1.9262295081967212e-05,
|
1383 |
+
"loss": 0.5854,
|
1384 |
+
"step": 77
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 1.232,
|
1388 |
+
"eval_exact_match": 0.08163265306122448,
|
1389 |
+
"eval_f1_a": 0.5901639344262296,
|
1390 |
+
"eval_f1_m": 0.4785052249337963,
|
1391 |
+
"eval_loss": 0.640457034111023,
|
1392 |
+
"eval_runtime": 12.5109,
|
1393 |
+
"eval_samples_per_second": 19.983,
|
1394 |
+
"eval_steps_per_second": 2.558,
|
1395 |
+
"step": 77
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.248,
|
1399 |
+
"grad_norm": 14.25,
|
1400 |
+
"learning_rate": 1.8852459016393442e-05,
|
1401 |
+
"loss": 0.6745,
|
1402 |
+
"step": 78
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 1.248,
|
1406 |
+
"eval_exact_match": 0.08163265306122448,
|
1407 |
+
"eval_f1_a": 0.5934959349593495,
|
1408 |
+
"eval_f1_m": 0.4793091828806114,
|
1409 |
+
"eval_loss": 0.6414687633514404,
|
1410 |
+
"eval_runtime": 12.5277,
|
1411 |
+
"eval_samples_per_second": 19.956,
|
1412 |
+
"eval_steps_per_second": 2.554,
|
1413 |
+
"step": 78
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.264,
|
1417 |
+
"grad_norm": 15.1875,
|
1418 |
+
"learning_rate": 1.8442622950819673e-05,
|
1419 |
+
"loss": 0.5662,
|
1420 |
+
"step": 79
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.264,
|
1424 |
+
"eval_exact_match": 0.08163265306122448,
|
1425 |
+
"eval_f1_a": 0.5967741935483871,
|
1426 |
+
"eval_f1_m": 0.48058251272536984,
|
1427 |
+
"eval_loss": 0.6460214853286743,
|
1428 |
+
"eval_runtime": 12.5159,
|
1429 |
+
"eval_samples_per_second": 19.975,
|
1430 |
+
"eval_steps_per_second": 2.557,
|
1431 |
+
"step": 79
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.28,
|
1435 |
+
"grad_norm": 55.25,
|
1436 |
+
"learning_rate": 1.8032786885245903e-05,
|
1437 |
+
"loss": 0.679,
|
1438 |
+
"step": 80
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.28,
|
1442 |
+
"eval_exact_match": 0.08163265306122448,
|
1443 |
+
"eval_f1_a": 0.6007905138339921,
|
1444 |
+
"eval_f1_m": 0.4773567135812034,
|
1445 |
+
"eval_loss": 0.6468359231948853,
|
1446 |
+
"eval_runtime": 12.5291,
|
1447 |
+
"eval_samples_per_second": 19.953,
|
1448 |
+
"eval_steps_per_second": 2.554,
|
1449 |
+
"step": 80
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.296,
|
1453 |
+
"grad_norm": 7.21875,
|
1454 |
+
"learning_rate": 1.7622950819672133e-05,
|
1455 |
+
"loss": 0.5867,
|
1456 |
+
"step": 81
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 1.296,
|
1460 |
+
"eval_exact_match": 0.08163265306122448,
|
1461 |
+
"eval_f1_a": 0.6007905138339921,
|
1462 |
+
"eval_f1_m": 0.4778103982185614,
|
1463 |
+
"eval_loss": 0.6476621031761169,
|
1464 |
+
"eval_runtime": 12.5295,
|
1465 |
+
"eval_samples_per_second": 19.953,
|
1466 |
+
"eval_steps_per_second": 2.554,
|
1467 |
+
"step": 81
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.312,
|
1471 |
+
"grad_norm": 8.125,
|
1472 |
+
"learning_rate": 1.721311475409836e-05,
|
1473 |
+
"loss": 0.5129,
|
1474 |
+
"step": 82
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.312,
|
1478 |
+
"eval_exact_match": 0.08163265306122448,
|
1479 |
+
"eval_f1_a": 0.6007905138339921,
|
1480 |
+
"eval_f1_m": 0.47502746686420155,
|
1481 |
+
"eval_loss": 0.6478710770606995,
|
1482 |
+
"eval_runtime": 12.5269,
|
1483 |
+
"eval_samples_per_second": 19.957,
|
1484 |
+
"eval_steps_per_second": 2.554,
|
1485 |
+
"step": 82
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.328,
|
1489 |
+
"grad_norm": 41.25,
|
1490 |
+
"learning_rate": 1.680327868852459e-05,
|
1491 |
+
"loss": 0.6594,
|
1492 |
+
"step": 83
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 1.328,
|
1496 |
+
"eval_exact_match": 0.08163265306122448,
|
1497 |
+
"eval_f1_a": 0.5952380952380952,
|
1498 |
+
"eval_f1_m": 0.4711932058870834,
|
1499 |
+
"eval_loss": 0.6437314748764038,
|
1500 |
+
"eval_runtime": 12.4098,
|
1501 |
+
"eval_samples_per_second": 20.145,
|
1502 |
+
"eval_steps_per_second": 2.579,
|
1503 |
+
"step": 83
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.3439999999999999,
|
1507 |
+
"grad_norm": 12.3125,
|
1508 |
+
"learning_rate": 1.6393442622950818e-05,
|
1509 |
+
"loss": 0.5754,
|
1510 |
+
"step": 84
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.3439999999999999,
|
1514 |
+
"eval_exact_match": 0.08163265306122448,
|
1515 |
+
"eval_f1_a": 0.5910931174089069,
|
1516 |
+
"eval_f1_m": 0.4749946765252888,
|
1517 |
+
"eval_loss": 0.6412422060966492,
|
1518 |
+
"eval_runtime": 12.4226,
|
1519 |
+
"eval_samples_per_second": 20.125,
|
1520 |
+
"eval_steps_per_second": 2.576,
|
1521 |
+
"step": 84
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.3599999999999999,
|
1525 |
+
"grad_norm": 12.0625,
|
1526 |
+
"learning_rate": 1.598360655737705e-05,
|
1527 |
+
"loss": 0.5544,
|
1528 |
+
"step": 85
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.3599999999999999,
|
1532 |
+
"eval_exact_match": 0.08163265306122448,
|
1533 |
+
"eval_f1_a": 0.5887096774193548,
|
1534 |
+
"eval_f1_m": 0.47564113890644494,
|
1535 |
+
"eval_loss": 0.639517605304718,
|
1536 |
+
"eval_runtime": 12.5196,
|
1537 |
+
"eval_samples_per_second": 19.969,
|
1538 |
+
"eval_steps_per_second": 2.556,
|
1539 |
+
"step": 85
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.376,
|
1543 |
+
"grad_norm": 13.1875,
|
1544 |
+
"learning_rate": 1.557377049180328e-05,
|
1545 |
+
"loss": 0.6295,
|
1546 |
+
"step": 86
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.376,
|
1550 |
+
"eval_exact_match": 0.061224489795918366,
|
1551 |
+
"eval_f1_a": 0.5726141078838174,
|
1552 |
+
"eval_f1_m": 0.4691413461821626,
|
1553 |
+
"eval_loss": 0.6366972923278809,
|
1554 |
+
"eval_runtime": 12.5166,
|
1555 |
+
"eval_samples_per_second": 19.973,
|
1556 |
+
"eval_steps_per_second": 2.557,
|
1557 |
+
"step": 86
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.392,
|
1561 |
+
"grad_norm": 5.875,
|
1562 |
+
"learning_rate": 1.5163934426229509e-05,
|
1563 |
+
"loss": 0.6123,
|
1564 |
+
"step": 87
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.392,
|
1568 |
+
"eval_exact_match": 0.061224489795918366,
|
1569 |
+
"eval_f1_a": 0.5690376569037656,
|
1570 |
+
"eval_f1_m": 0.46367544020605245,
|
1571 |
+
"eval_loss": 0.6347695589065552,
|
1572 |
+
"eval_runtime": 12.5135,
|
1573 |
+
"eval_samples_per_second": 19.978,
|
1574 |
+
"eval_steps_per_second": 2.557,
|
1575 |
+
"step": 87
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.408,
|
1579 |
+
"grad_norm": 41.75,
|
1580 |
+
"learning_rate": 1.4754098360655739e-05,
|
1581 |
+
"loss": 0.6,
|
1582 |
+
"step": 88
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 1.408,
|
1586 |
+
"eval_exact_match": 0.061224489795918366,
|
1587 |
+
"eval_f1_a": 0.5702127659574467,
|
1588 |
+
"eval_f1_m": 0.4770136326258776,
|
1589 |
+
"eval_loss": 0.6304101347923279,
|
1590 |
+
"eval_runtime": 12.4096,
|
1591 |
+
"eval_samples_per_second": 20.146,
|
1592 |
+
"eval_steps_per_second": 2.579,
|
1593 |
+
"step": 88
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.424,
|
1597 |
+
"grad_norm": 52.5,
|
1598 |
+
"learning_rate": 1.4344262295081968e-05,
|
1599 |
+
"loss": 0.6655,
|
1600 |
+
"step": 89
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 1.424,
|
1604 |
+
"eval_exact_match": 0.061224489795918366,
|
1605 |
+
"eval_f1_a": 0.5663716814159292,
|
1606 |
+
"eval_f1_m": 0.4777696226675817,
|
1607 |
+
"eval_loss": 0.6252734661102295,
|
1608 |
+
"eval_runtime": 12.52,
|
1609 |
+
"eval_samples_per_second": 19.968,
|
1610 |
+
"eval_steps_per_second": 2.556,
|
1611 |
+
"step": 89
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.44,
|
1615 |
+
"grad_norm": 7.5625,
|
1616 |
+
"learning_rate": 1.3934426229508196e-05,
|
1617 |
+
"loss": 0.5784,
|
1618 |
+
"step": 90
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 1.44,
|
1622 |
+
"eval_exact_match": 0.08163265306122448,
|
1623 |
+
"eval_f1_a": 0.5610859728506787,
|
1624 |
+
"eval_f1_m": 0.4947867325418346,
|
1625 |
+
"eval_loss": 0.6227597594261169,
|
1626 |
+
"eval_runtime": 12.5093,
|
1627 |
+
"eval_samples_per_second": 19.985,
|
1628 |
+
"eval_steps_per_second": 2.558,
|
1629 |
+
"step": 90
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.456,
|
1633 |
+
"grad_norm": 9.375,
|
1634 |
+
"learning_rate": 1.3524590163934428e-05,
|
1635 |
+
"loss": 0.5715,
|
1636 |
+
"step": 91
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 1.456,
|
1640 |
+
"eval_exact_match": 0.08163265306122448,
|
1641 |
+
"eval_f1_a": 0.5781990521327014,
|
1642 |
+
"eval_f1_m": 0.520756964124311,
|
1643 |
+
"eval_loss": 0.6186211109161377,
|
1644 |
+
"eval_runtime": 12.7601,
|
1645 |
+
"eval_samples_per_second": 19.592,
|
1646 |
+
"eval_steps_per_second": 2.508,
|
1647 |
+
"step": 91
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.472,
|
1651 |
+
"grad_norm": 7.21875,
|
1652 |
+
"learning_rate": 1.3114754098360657e-05,
|
1653 |
+
"loss": 0.6274,
|
1654 |
+
"step": 92
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 1.472,
|
1658 |
+
"eval_exact_match": 0.08163265306122448,
|
1659 |
+
"eval_f1_a": 0.5603864734299516,
|
1660 |
+
"eval_f1_m": 0.51300422933076,
|
1661 |
+
"eval_loss": 0.6171249747276306,
|
1662 |
+
"eval_runtime": 12.9738,
|
1663 |
+
"eval_samples_per_second": 19.27,
|
1664 |
+
"eval_steps_per_second": 2.467,
|
1665 |
+
"step": 92
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.488,
|
1669 |
+
"grad_norm": 30.0,
|
1670 |
+
"learning_rate": 1.2704918032786885e-05,
|
1671 |
+
"loss": 0.7038,
|
1672 |
+
"step": 93
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 1.488,
|
1676 |
+
"eval_exact_match": 0.08163265306122448,
|
1677 |
+
"eval_f1_a": 0.5784313725490196,
|
1678 |
+
"eval_f1_m": 0.5305293346109673,
|
1679 |
+
"eval_loss": 0.6147861480712891,
|
1680 |
+
"eval_runtime": 13.3609,
|
1681 |
+
"eval_samples_per_second": 18.711,
|
1682 |
+
"eval_steps_per_second": 2.395,
|
1683 |
+
"step": 93
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.504,
|
1687 |
+
"grad_norm": 6.6875,
|
1688 |
+
"learning_rate": 1.2295081967213116e-05,
|
1689 |
+
"loss": 0.5364,
|
1690 |
+
"step": 94
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.504,
|
1694 |
+
"eval_exact_match": 0.08163265306122448,
|
1695 |
+
"eval_f1_a": 0.5771144278606964,
|
1696 |
+
"eval_f1_m": 0.5379805568581079,
|
1697 |
+
"eval_loss": 0.6129326224327087,
|
1698 |
+
"eval_runtime": 13.0415,
|
1699 |
+
"eval_samples_per_second": 19.17,
|
1700 |
+
"eval_steps_per_second": 2.454,
|
1701 |
+
"step": 94
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.52,
|
1705 |
+
"grad_norm": 27.75,
|
1706 |
+
"learning_rate": 1.1885245901639344e-05,
|
1707 |
+
"loss": 0.4883,
|
1708 |
+
"step": 95
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.52,
|
1712 |
+
"eval_exact_match": 0.08163265306122448,
|
1713 |
+
"eval_f1_a": 0.5612244897959184,
|
1714 |
+
"eval_f1_m": 0.53111536989088,
|
1715 |
+
"eval_loss": 0.6093867421150208,
|
1716 |
+
"eval_runtime": 12.5993,
|
1717 |
+
"eval_samples_per_second": 19.842,
|
1718 |
+
"eval_steps_per_second": 2.54,
|
1719 |
+
"step": 95
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.536,
|
1723 |
+
"grad_norm": 23.0,
|
1724 |
+
"learning_rate": 1.1475409836065575e-05,
|
1725 |
+
"loss": 0.4918,
|
1726 |
+
"step": 96
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.536,
|
1730 |
+
"eval_exact_match": 0.08163265306122448,
|
1731 |
+
"eval_f1_a": 0.5567010309278351,
|
1732 |
+
"eval_f1_m": 0.526410154471379,
|
1733 |
+
"eval_loss": 0.6084589958190918,
|
1734 |
+
"eval_runtime": 12.6824,
|
1735 |
+
"eval_samples_per_second": 19.712,
|
1736 |
+
"eval_steps_per_second": 2.523,
|
1737 |
+
"step": 96
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.552,
|
1741 |
+
"grad_norm": 5.71875,
|
1742 |
+
"learning_rate": 1.1065573770491803e-05,
|
1743 |
+
"loss": 0.5881,
|
1744 |
+
"step": 97
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 1.552,
|
1748 |
+
"eval_exact_match": 0.10204081632653061,
|
1749 |
+
"eval_f1_a": 0.5502645502645503,
|
1750 |
+
"eval_f1_m": 0.5260332071556562,
|
1751 |
+
"eval_loss": 0.6075829863548279,
|
1752 |
+
"eval_runtime": 12.5867,
|
1753 |
+
"eval_samples_per_second": 19.862,
|
1754 |
+
"eval_steps_per_second": 2.542,
|
1755 |
+
"step": 97
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 1.568,
|
1759 |
+
"grad_norm": 18.0,
|
1760 |
+
"learning_rate": 1.0655737704918032e-05,
|
1761 |
+
"loss": 0.4614,
|
1762 |
+
"step": 98
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.568,
|
1766 |
+
"eval_exact_match": 0.10204081632653061,
|
1767 |
+
"eval_f1_a": 0.5608465608465608,
|
1768 |
+
"eval_f1_m": 0.5355139475037434,
|
1769 |
+
"eval_loss": 0.6062441468238831,
|
1770 |
+
"eval_runtime": 12.567,
|
1771 |
+
"eval_samples_per_second": 19.893,
|
1772 |
+
"eval_steps_per_second": 2.546,
|
1773 |
+
"step": 98
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.584,
|
1777 |
+
"grad_norm": 22.625,
|
1778 |
+
"learning_rate": 1.0245901639344262e-05,
|
1779 |
+
"loss": 0.5693,
|
1780 |
+
"step": 99
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.584,
|
1784 |
+
"eval_exact_match": 0.10204081632653061,
|
1785 |
+
"eval_f1_a": 0.5608465608465608,
|
1786 |
+
"eval_f1_m": 0.5325499047437824,
|
1787 |
+
"eval_loss": 0.6053320169448853,
|
1788 |
+
"eval_runtime": 12.573,
|
1789 |
+
"eval_samples_per_second": 19.884,
|
1790 |
+
"eval_steps_per_second": 2.545,
|
1791 |
+
"step": 99
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.6,
|
1795 |
+
"grad_norm": 22.5,
|
1796 |
+
"learning_rate": 9.836065573770493e-06,
|
1797 |
+
"loss": 0.5239,
|
1798 |
+
"step": 100
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 1.6,
|
1802 |
+
"eval_exact_match": 0.08163265306122448,
|
1803 |
+
"eval_f1_a": 0.5531914893617021,
|
1804 |
+
"eval_f1_m": 0.5152986752476547,
|
1805 |
+
"eval_loss": 0.6034590005874634,
|
1806 |
+
"eval_runtime": 12.5763,
|
1807 |
+
"eval_samples_per_second": 19.879,
|
1808 |
+
"eval_steps_per_second": 2.544,
|
1809 |
+
"step": 100
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.616,
|
1813 |
+
"grad_norm": 17.25,
|
1814 |
+
"learning_rate": 9.426229508196721e-06,
|
1815 |
+
"loss": 0.4434,
|
1816 |
+
"step": 101
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.616,
|
1820 |
+
"eval_exact_match": 0.10204081632653061,
|
1821 |
+
"eval_f1_a": 0.5405405405405405,
|
1822 |
+
"eval_f1_m": 0.5147288369227145,
|
1823 |
+
"eval_loss": 0.602425754070282,
|
1824 |
+
"eval_runtime": 12.5712,
|
1825 |
+
"eval_samples_per_second": 19.887,
|
1826 |
+
"eval_steps_per_second": 2.546,
|
1827 |
+
"step": 101
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.6320000000000001,
|
1831 |
+
"grad_norm": 31.875,
|
1832 |
+
"learning_rate": 9.016393442622952e-06,
|
1833 |
+
"loss": 0.6336,
|
1834 |
+
"step": 102
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.6320000000000001,
|
1838 |
+
"eval_exact_match": 0.10204081632653061,
|
1839 |
+
"eval_f1_a": 0.53551912568306,
|
1840 |
+
"eval_f1_m": 0.5188104695757757,
|
1841 |
+
"eval_loss": 0.6012207269668579,
|
1842 |
+
"eval_runtime": 12.5726,
|
1843 |
+
"eval_samples_per_second": 19.885,
|
1844 |
+
"eval_steps_per_second": 2.545,
|
1845 |
+
"step": 102
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.6480000000000001,
|
1849 |
+
"grad_norm": 10.875,
|
1850 |
+
"learning_rate": 8.60655737704918e-06,
|
1851 |
+
"loss": 0.5441,
|
1852 |
+
"step": 103
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 1.6480000000000001,
|
1856 |
+
"eval_exact_match": 0.10204081632653061,
|
1857 |
+
"eval_f1_a": 0.5363128491620112,
|
1858 |
+
"eval_f1_m": 0.5246980627082668,
|
1859 |
+
"eval_loss": 0.6005741953849792,
|
1860 |
+
"eval_runtime": 12.5894,
|
1861 |
+
"eval_samples_per_second": 19.858,
|
1862 |
+
"eval_steps_per_second": 2.542,
|
1863 |
+
"step": 103
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 1.6640000000000001,
|
1867 |
+
"grad_norm": 16.25,
|
1868 |
+
"learning_rate": 8.196721311475409e-06,
|
1869 |
+
"loss": 0.4561,
|
1870 |
+
"step": 104
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 1.6640000000000001,
|
1874 |
+
"eval_exact_match": 0.10204081632653061,
|
1875 |
+
"eval_f1_a": 0.5202312138728324,
|
1876 |
+
"eval_f1_m": 0.5224427233430835,
|
1877 |
+
"eval_loss": 0.5999111533164978,
|
1878 |
+
"eval_runtime": 12.4649,
|
1879 |
+
"eval_samples_per_second": 20.056,
|
1880 |
+
"eval_steps_per_second": 2.567,
|
1881 |
+
"step": 104
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 1.6800000000000002,
|
1885 |
+
"grad_norm": 12.4375,
|
1886 |
+
"learning_rate": 7.78688524590164e-06,
|
1887 |
+
"loss": 0.6999,
|
1888 |
+
"step": 105
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 1.6800000000000002,
|
1892 |
+
"eval_exact_match": 0.10204081632653061,
|
1893 |
+
"eval_f1_a": 0.5207100591715976,
|
1894 |
+
"eval_f1_m": 0.5320394191642691,
|
1895 |
+
"eval_loss": 0.5994404554367065,
|
1896 |
+
"eval_runtime": 12.5816,
|
1897 |
+
"eval_samples_per_second": 19.87,
|
1898 |
+
"eval_steps_per_second": 2.543,
|
1899 |
+
"step": 105
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.696,
|
1903 |
+
"grad_norm": 4.53125,
|
1904 |
+
"learning_rate": 7.3770491803278695e-06,
|
1905 |
+
"loss": 0.4781,
|
1906 |
+
"step": 106
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.696,
|
1910 |
+
"eval_exact_match": 0.12244897959183673,
|
1911 |
+
"eval_f1_a": 0.524390243902439,
|
1912 |
+
"eval_f1_m": 0.5555706498383567,
|
1913 |
+
"eval_loss": 0.5982089638710022,
|
1914 |
+
"eval_runtime": 12.4629,
|
1915 |
+
"eval_samples_per_second": 20.06,
|
1916 |
+
"eval_steps_per_second": 2.568,
|
1917 |
+
"step": 106
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 1.712,
|
1921 |
+
"grad_norm": 9.3125,
|
1922 |
+
"learning_rate": 6.967213114754098e-06,
|
1923 |
+
"loss": 0.4955,
|
1924 |
+
"step": 107
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.712,
|
1928 |
+
"eval_exact_match": 0.10204081632653061,
|
1929 |
+
"eval_f1_a": 0.5000000000000001,
|
1930 |
+
"eval_f1_m": 0.5406607298263958,
|
1931 |
+
"eval_loss": 0.5973047018051147,
|
1932 |
+
"eval_runtime": 12.4809,
|
1933 |
+
"eval_samples_per_second": 20.031,
|
1934 |
+
"eval_steps_per_second": 2.564,
|
1935 |
+
"step": 107
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.728,
|
1939 |
+
"grad_norm": 15.9375,
|
1940 |
+
"learning_rate": 6.557377049180328e-06,
|
1941 |
+
"loss": 0.7169,
|
1942 |
+
"step": 108
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.728,
|
1946 |
+
"eval_exact_match": 0.10204081632653061,
|
1947 |
+
"eval_f1_a": 0.5061728395061729,
|
1948 |
+
"eval_f1_m": 0.5354615072802346,
|
1949 |
+
"eval_loss": 0.5978144407272339,
|
1950 |
+
"eval_runtime": 12.4727,
|
1951 |
+
"eval_samples_per_second": 20.044,
|
1952 |
+
"eval_steps_per_second": 2.566,
|
1953 |
+
"step": 108
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 1.744,
|
1957 |
+
"grad_norm": 8.3125,
|
1958 |
+
"learning_rate": 6.147540983606558e-06,
|
1959 |
+
"loss": 0.5559,
|
1960 |
+
"step": 109
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.744,
|
1964 |
+
"eval_exact_match": 0.10204081632653061,
|
1965 |
+
"eval_f1_a": 0.5185185185185185,
|
1966 |
+
"eval_f1_m": 0.538548896081909,
|
1967 |
+
"eval_loss": 0.5964921712875366,
|
1968 |
+
"eval_runtime": 12.4816,
|
1969 |
+
"eval_samples_per_second": 20.029,
|
1970 |
+
"eval_steps_per_second": 2.564,
|
1971 |
+
"step": 109
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 1.76,
|
1975 |
+
"grad_norm": 14.25,
|
1976 |
+
"learning_rate": 5.737704918032787e-06,
|
1977 |
+
"loss": 0.5697,
|
1978 |
+
"step": 110
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 1.76,
|
1982 |
+
"eval_exact_match": 0.10204081632653061,
|
1983 |
+
"eval_f1_a": 0.49382716049382713,
|
1984 |
+
"eval_f1_m": 0.5282943547049189,
|
1985 |
+
"eval_loss": 0.5966972708702087,
|
1986 |
+
"eval_runtime": 12.4667,
|
1987 |
+
"eval_samples_per_second": 20.053,
|
1988 |
+
"eval_steps_per_second": 2.567,
|
1989 |
+
"step": 110
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.776,
|
1993 |
+
"grad_norm": 8.375,
|
1994 |
+
"learning_rate": 5.327868852459016e-06,
|
1995 |
+
"loss": 0.4283,
|
1996 |
+
"step": 111
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 1.776,
|
2000 |
+
"eval_exact_match": 0.10204081632653061,
|
2001 |
+
"eval_f1_a": 0.5031446540880504,
|
2002 |
+
"eval_f1_m": 0.5433442707752428,
|
2003 |
+
"eval_loss": 0.5960127115249634,
|
2004 |
+
"eval_runtime": 12.4773,
|
2005 |
+
"eval_samples_per_second": 20.036,
|
2006 |
+
"eval_steps_per_second": 2.565,
|
2007 |
+
"step": 111
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 1.792,
|
2011 |
+
"grad_norm": 16.75,
|
2012 |
+
"learning_rate": 4.918032786885246e-06,
|
2013 |
+
"loss": 0.6258,
|
2014 |
+
"step": 112
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 1.792,
|
2018 |
+
"eval_exact_match": 0.10204081632653061,
|
2019 |
+
"eval_f1_a": 0.4774193548387097,
|
2020 |
+
"eval_f1_m": 0.5284177007466322,
|
2021 |
+
"eval_loss": 0.5976787209510803,
|
2022 |
+
"eval_runtime": 12.4731,
|
2023 |
+
"eval_samples_per_second": 20.043,
|
2024 |
+
"eval_steps_per_second": 2.566,
|
2025 |
+
"step": 112
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 1.808,
|
2029 |
+
"grad_norm": 7.96875,
|
2030 |
+
"learning_rate": 4.508196721311476e-06,
|
2031 |
+
"loss": 0.5256,
|
2032 |
+
"step": 113
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 1.808,
|
2036 |
+
"eval_exact_match": 0.10204081632653061,
|
2037 |
+
"eval_f1_a": 0.4615384615384615,
|
2038 |
+
"eval_f1_m": 0.5200843674132989,
|
2039 |
+
"eval_loss": 0.5962343811988831,
|
2040 |
+
"eval_runtime": 12.5684,
|
2041 |
+
"eval_samples_per_second": 19.891,
|
2042 |
+
"eval_steps_per_second": 2.546,
|
2043 |
+
"step": 113
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 1.8239999999999998,
|
2047 |
+
"grad_norm": 15.125,
|
2048 |
+
"learning_rate": 4.098360655737704e-06,
|
2049 |
+
"loss": 0.5736,
|
2050 |
+
"step": 114
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 1.8239999999999998,
|
2054 |
+
"eval_exact_match": 0.10204081632653061,
|
2055 |
+
"eval_f1_a": 0.4675324675324675,
|
2056 |
+
"eval_f1_m": 0.5306153330463053,
|
2057 |
+
"eval_loss": 0.5951288938522339,
|
2058 |
+
"eval_runtime": 12.5788,
|
2059 |
+
"eval_samples_per_second": 19.875,
|
2060 |
+
"eval_steps_per_second": 2.544,
|
2061 |
+
"step": 114
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.8399999999999999,
|
2065 |
+
"grad_norm": 20.25,
|
2066 |
+
"learning_rate": 3.6885245901639347e-06,
|
2067 |
+
"loss": 0.366,
|
2068 |
+
"step": 115
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.8399999999999999,
|
2072 |
+
"eval_exact_match": 0.10204081632653061,
|
2073 |
+
"eval_f1_a": 0.4645161290322581,
|
2074 |
+
"eval_f1_m": 0.5248462721752035,
|
2075 |
+
"eval_loss": 0.594918966293335,
|
2076 |
+
"eval_runtime": 12.4723,
|
2077 |
+
"eval_samples_per_second": 20.044,
|
2078 |
+
"eval_steps_per_second": 2.566,
|
2079 |
+
"step": 115
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.8559999999999999,
|
2083 |
+
"grad_norm": 21.125,
|
2084 |
+
"learning_rate": 3.278688524590164e-06,
|
2085 |
+
"loss": 0.5082,
|
2086 |
+
"step": 116
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 1.8559999999999999,
|
2090 |
+
"eval_exact_match": 0.10204081632653061,
|
2091 |
+
"eval_f1_a": 0.48051948051948046,
|
2092 |
+
"eval_f1_m": 0.5353904898622783,
|
2093 |
+
"eval_loss": 0.5939072370529175,
|
2094 |
+
"eval_runtime": 12.5855,
|
2095 |
+
"eval_samples_per_second": 19.864,
|
2096 |
+
"eval_steps_per_second": 2.543,
|
2097 |
+
"step": 116
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 1.8719999999999999,
|
2101 |
+
"grad_norm": 11.75,
|
2102 |
+
"learning_rate": 2.8688524590163937e-06,
|
2103 |
+
"loss": 0.5421,
|
2104 |
+
"step": 117
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 1.8719999999999999,
|
2108 |
+
"eval_exact_match": 0.10204081632653061,
|
2109 |
+
"eval_f1_a": 0.47435897435897434,
|
2110 |
+
"eval_f1_m": 0.5267037684204547,
|
2111 |
+
"eval_loss": 0.5957451462745667,
|
2112 |
+
"eval_runtime": 12.479,
|
2113 |
+
"eval_samples_per_second": 20.034,
|
2114 |
+
"eval_steps_per_second": 2.564,
|
2115 |
+
"step": 117
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 1.888,
|
2119 |
+
"grad_norm": 8.0,
|
2120 |
+
"learning_rate": 2.459016393442623e-06,
|
2121 |
+
"loss": 0.62,
|
2122 |
+
"step": 118
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.888,
|
2126 |
+
"eval_exact_match": 0.10204081632653061,
|
2127 |
+
"eval_f1_a": 0.4705882352941176,
|
2128 |
+
"eval_f1_m": 0.5307986531275845,
|
2129 |
+
"eval_loss": 0.5949638485908508,
|
2130 |
+
"eval_runtime": 12.4749,
|
2131 |
+
"eval_samples_per_second": 20.04,
|
2132 |
+
"eval_steps_per_second": 2.565,
|
2133 |
+
"step": 118
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 1.904,
|
2137 |
+
"grad_norm": 11.375,
|
2138 |
+
"learning_rate": 2.049180327868852e-06,
|
2139 |
+
"loss": 0.6126,
|
2140 |
+
"step": 119
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.904,
|
2144 |
+
"eval_exact_match": 0.10204081632653061,
|
2145 |
+
"eval_f1_a": 0.4774193548387097,
|
2146 |
+
"eval_f1_m": 0.5340785365095088,
|
2147 |
+
"eval_loss": 0.5944355726242065,
|
2148 |
+
"eval_runtime": 12.5766,
|
2149 |
+
"eval_samples_per_second": 19.878,
|
2150 |
+
"eval_steps_per_second": 2.544,
|
2151 |
+
"step": 119
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.92,
|
2155 |
+
"grad_norm": 13.3125,
|
2156 |
+
"learning_rate": 1.639344262295082e-06,
|
2157 |
+
"loss": 0.527,
|
2158 |
+
"step": 120
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.92,
|
2162 |
+
"eval_exact_match": 0.10204081632653061,
|
2163 |
+
"eval_f1_a": 0.484076433121019,
|
2164 |
+
"eval_f1_m": 0.5245061361207819,
|
2165 |
+
"eval_loss": 0.5951045155525208,
|
2166 |
+
"eval_runtime": 12.4733,
|
2167 |
+
"eval_samples_per_second": 20.043,
|
2168 |
+
"eval_steps_per_second": 2.565,
|
2169 |
+
"step": 120
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 1.936,
|
2173 |
+
"grad_norm": 14.9375,
|
2174 |
+
"learning_rate": 1.2295081967213116e-06,
|
2175 |
+
"loss": 0.5308,
|
2176 |
+
"step": 121
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.936,
|
2180 |
+
"eval_exact_match": 0.10204081632653061,
|
2181 |
+
"eval_f1_a": 0.484076433121019,
|
2182 |
+
"eval_f1_m": 0.5301669718836584,
|
2183 |
+
"eval_loss": 0.5943300724029541,
|
2184 |
+
"eval_runtime": 12.5706,
|
2185 |
+
"eval_samples_per_second": 19.888,
|
2186 |
+
"eval_steps_per_second": 2.546,
|
2187 |
+
"step": 121
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.952,
|
2191 |
+
"grad_norm": 5.1875,
|
2192 |
+
"learning_rate": 8.19672131147541e-07,
|
2193 |
+
"loss": 0.5002,
|
2194 |
+
"step": 122
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.952,
|
2198 |
+
"eval_exact_match": 0.10204081632653061,
|
2199 |
+
"eval_f1_a": 0.4774193548387097,
|
2200 |
+
"eval_f1_m": 0.5352071697809991,
|
2201 |
+
"eval_loss": 0.5943408012390137,
|
2202 |
+
"eval_runtime": 12.4681,
|
2203 |
+
"eval_samples_per_second": 20.051,
|
2204 |
+
"eval_steps_per_second": 2.567,
|
2205 |
+
"step": 122
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 1.968,
|
2209 |
+
"grad_norm": 10.5625,
|
2210 |
+
"learning_rate": 4.098360655737705e-07,
|
2211 |
+
"loss": 0.4733,
|
2212 |
+
"step": 123
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 1.968,
|
2216 |
+
"eval_exact_match": 0.10204081632653061,
|
2217 |
+
"eval_f1_a": 0.4903225806451614,
|
2218 |
+
"eval_f1_m": 0.5415129388418702,
|
2219 |
+
"eval_loss": 0.5952519774436951,
|
2220 |
+
"eval_runtime": 12.4602,
|
2221 |
+
"eval_samples_per_second": 20.064,
|
2222 |
+
"eval_steps_per_second": 2.568,
|
2223 |
+
"step": 123
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 1.984,
|
2227 |
+
"grad_norm": 17.625,
|
2228 |
+
"learning_rate": 0.0,
|
2229 |
+
"loss": 0.4085,
|
2230 |
+
"step": 124
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 1.984,
|
2234 |
+
"eval_exact_match": 0.10204081632653061,
|
2235 |
+
"eval_f1_a": 0.484076433121019,
|
2236 |
+
"eval_f1_m": 0.5301669718836584,
|
2237 |
+
"eval_loss": 0.5949286818504333,
|
2238 |
+
"eval_runtime": 12.5825,
|
2239 |
+
"eval_samples_per_second": 19.869,
|
2240 |
+
"eval_steps_per_second": 2.543,
|
2241 |
+
"step": 124
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 1.984,
|
2245 |
+
"step": 124,
|
2246 |
+
"total_flos": 4.246810864386048e+16,
|
2247 |
+
"train_loss": 0.6719285288164693,
|
2248 |
+
"train_runtime": 1910.309,
|
2249 |
+
"train_samples_per_second": 1.047,
|
2250 |
+
"train_steps_per_second": 0.065
|
2251 |
+
}
|
2252 |
+
],
|
2253 |
+
"logging_steps": 1,
|
2254 |
+
"max_steps": 124,
|
2255 |
+
"num_input_tokens_seen": 0,
|
2256 |
+
"num_train_epochs": 2,
|
2257 |
+
"save_steps": 500,
|
2258 |
+
"stateful_callbacks": {
|
2259 |
+
"TrainerControl": {
|
2260 |
+
"args": {
|
2261 |
+
"should_epoch_stop": false,
|
2262 |
+
"should_evaluate": false,
|
2263 |
+
"should_log": false,
|
2264 |
+
"should_save": false,
|
2265 |
+
"should_training_stop": false
|
2266 |
+
},
|
2267 |
+
"attributes": {}
|
2268 |
+
}
|
2269 |
+
},
|
2270 |
+
"total_flos": 4.246810864386048e+16,
|
2271 |
+
"train_batch_size": 2,
|
2272 |
+
"trial_name": null,
|
2273 |
+
"trial_params": null
|
2274 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be09513a8356c1102fab14897baebb8cf27876dcdb1444e096644535499fc186
|
3 |
+
size 5176
|