Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +30 -0
- trainer_state-opt-gptq-QLORA-super_glue-multirc-sequence_classification.json +2262 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2
|
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 0.10.0
|
adapter_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2",
|
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 |
+
],
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 8,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"q_proj",
|
26 |
+
"fc1",
|
27 |
+
"fc2",
|
28 |
+
"v_proj",
|
29 |
+
"k_proj",
|
30 |
+
"out_proj"
|
31 |
+
],
|
32 |
+
"task_type": "SEQ_CLS",
|
33 |
+
"use_dora": false,
|
34 |
+
"use_rslora": false
|
35 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c8390209e0de19acf0615d7cd5cdf97230a08bb49ef5976b199198e7eac6d1
|
3 |
+
size 75566824
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "</s>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
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_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "</s>",
|
23 |
+
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "</s>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 1000000000000000019884624838656,
|
27 |
+
"pad_token": "</s>",
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "</s>"
|
30 |
+
}
|
trainer_state-opt-gptq-QLORA-super_glue-multirc-sequence_classification.json
ADDED
@@ -0,0 +1,2262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 26.392181396484375,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 1.2683,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.016,
|
20 |
+
"eval_exact_match": 0.14285714285714285,
|
21 |
+
"eval_f1_a": 0.544,
|
22 |
+
"eval_f1_m": 0.5331374974232117,
|
23 |
+
"eval_loss": 0.9992128610610962,
|
24 |
+
"eval_runtime": 12.4039,
|
25 |
+
"eval_samples_per_second": 20.155,
|
26 |
+
"eval_steps_per_second": 2.58,
|
27 |
+
"step": 1
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.032,
|
31 |
+
"grad_norm": 19.146682739257812,
|
32 |
+
"learning_rate": 5e-05,
|
33 |
+
"loss": 1.0276,
|
34 |
+
"step": 2
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.032,
|
38 |
+
"eval_exact_match": 0.12244897959183673,
|
39 |
+
"eval_f1_a": 0.5344129554655871,
|
40 |
+
"eval_f1_m": 0.5208925994640281,
|
41 |
+
"eval_loss": 0.9813457131385803,
|
42 |
+
"eval_runtime": 12.2968,
|
43 |
+
"eval_samples_per_second": 20.331,
|
44 |
+
"eval_steps_per_second": 2.602,
|
45 |
+
"step": 2
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.048,
|
49 |
+
"grad_norm": 25.024534225463867,
|
50 |
+
"learning_rate": 4.959016393442623e-05,
|
51 |
+
"loss": 1.1935,
|
52 |
+
"step": 3
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.048,
|
56 |
+
"eval_exact_match": 0.04081632653061224,
|
57 |
+
"eval_f1_a": 0.4979253112033195,
|
58 |
+
"eval_f1_m": 0.4637011514562535,
|
59 |
+
"eval_loss": 0.9183418154716492,
|
60 |
+
"eval_runtime": 12.5058,
|
61 |
+
"eval_samples_per_second": 19.991,
|
62 |
+
"eval_steps_per_second": 2.559,
|
63 |
+
"step": 3
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.064,
|
67 |
+
"grad_norm": 18.022754669189453,
|
68 |
+
"learning_rate": 4.918032786885246e-05,
|
69 |
+
"loss": 0.9304,
|
70 |
+
"step": 4
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.064,
|
74 |
+
"eval_exact_match": 0.04081632653061224,
|
75 |
+
"eval_f1_a": 0.43243243243243246,
|
76 |
+
"eval_f1_m": 0.42084400859911064,
|
77 |
+
"eval_loss": 0.8643535375595093,
|
78 |
+
"eval_runtime": 12.5036,
|
79 |
+
"eval_samples_per_second": 19.994,
|
80 |
+
"eval_steps_per_second": 2.559,
|
81 |
+
"step": 4
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08,
|
85 |
+
"grad_norm": 17.011953353881836,
|
86 |
+
"learning_rate": 4.8770491803278687e-05,
|
87 |
+
"loss": 1.0187,
|
88 |
+
"step": 5
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.08,
|
92 |
+
"eval_exact_match": 0.04081632653061224,
|
93 |
+
"eval_f1_a": 0.44131455399061037,
|
94 |
+
"eval_f1_m": 0.435791589363018,
|
95 |
+
"eval_loss": 0.8290175795555115,
|
96 |
+
"eval_runtime": 12.501,
|
97 |
+
"eval_samples_per_second": 19.998,
|
98 |
+
"eval_steps_per_second": 2.56,
|
99 |
+
"step": 5
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.096,
|
103 |
+
"grad_norm": 9.931246757507324,
|
104 |
+
"learning_rate": 4.836065573770492e-05,
|
105 |
+
"loss": 0.781,
|
106 |
+
"step": 6
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.096,
|
110 |
+
"eval_exact_match": 0.04081632653061224,
|
111 |
+
"eval_f1_a": 0.44761904761904764,
|
112 |
+
"eval_f1_m": 0.44164457990988604,
|
113 |
+
"eval_loss": 0.803396463394165,
|
114 |
+
"eval_runtime": 12.603,
|
115 |
+
"eval_samples_per_second": 19.837,
|
116 |
+
"eval_steps_per_second": 2.539,
|
117 |
+
"step": 6
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.112,
|
121 |
+
"grad_norm": 34.31171417236328,
|
122 |
+
"learning_rate": 4.795081967213115e-05,
|
123 |
+
"loss": 1.2274,
|
124 |
+
"step": 7
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.112,
|
128 |
+
"eval_exact_match": 0.04081632653061224,
|
129 |
+
"eval_f1_a": 0.416243654822335,
|
130 |
+
"eval_f1_m": 0.42698010606173864,
|
131 |
+
"eval_loss": 0.7892948985099792,
|
132 |
+
"eval_runtime": 12.5071,
|
133 |
+
"eval_samples_per_second": 19.989,
|
134 |
+
"eval_steps_per_second": 2.559,
|
135 |
+
"step": 7
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.128,
|
139 |
+
"grad_norm": 19.665807723999023,
|
140 |
+
"learning_rate": 4.754098360655738e-05,
|
141 |
+
"loss": 1.0631,
|
142 |
+
"step": 8
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.128,
|
146 |
+
"eval_exact_match": 0.04081632653061224,
|
147 |
+
"eval_f1_a": 0.3734939759036145,
|
148 |
+
"eval_f1_m": 0.44151661996800046,
|
149 |
+
"eval_loss": 0.779171884059906,
|
150 |
+
"eval_runtime": 12.401,
|
151 |
+
"eval_samples_per_second": 20.16,
|
152 |
+
"eval_steps_per_second": 2.58,
|
153 |
+
"step": 8
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.144,
|
157 |
+
"grad_norm": 6.531087875366211,
|
158 |
+
"learning_rate": 4.713114754098361e-05,
|
159 |
+
"loss": 0.6823,
|
160 |
+
"step": 9
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.144,
|
164 |
+
"eval_exact_match": 0.0,
|
165 |
+
"eval_f1_a": 0.24657534246575338,
|
166 |
+
"eval_f1_m": 0.38393596199718655,
|
167 |
+
"eval_loss": 0.7732793092727661,
|
168 |
+
"eval_runtime": 12.3963,
|
169 |
+
"eval_samples_per_second": 20.167,
|
170 |
+
"eval_steps_per_second": 2.581,
|
171 |
+
"step": 9
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.16,
|
175 |
+
"grad_norm": 9.769821166992188,
|
176 |
+
"learning_rate": 4.672131147540984e-05,
|
177 |
+
"loss": 0.6971,
|
178 |
+
"step": 10
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.16,
|
182 |
+
"eval_exact_match": 0.0,
|
183 |
+
"eval_f1_a": 0.24827586206896554,
|
184 |
+
"eval_f1_m": 0.38636550524305635,
|
185 |
+
"eval_loss": 0.7666972875595093,
|
186 |
+
"eval_runtime": 12.3966,
|
187 |
+
"eval_samples_per_second": 20.167,
|
188 |
+
"eval_steps_per_second": 2.581,
|
189 |
+
"step": 10
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.176,
|
193 |
+
"grad_norm": 18.875186920166016,
|
194 |
+
"learning_rate": 4.631147540983607e-05,
|
195 |
+
"loss": 0.8232,
|
196 |
+
"step": 11
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.176,
|
200 |
+
"eval_exact_match": 0.0,
|
201 |
+
"eval_f1_a": 0.2028985507246377,
|
202 |
+
"eval_f1_m": 0.37477658396025737,
|
203 |
+
"eval_loss": 0.7616797089576721,
|
204 |
+
"eval_runtime": 12.293,
|
205 |
+
"eval_samples_per_second": 20.337,
|
206 |
+
"eval_steps_per_second": 2.603,
|
207 |
+
"step": 11
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.192,
|
211 |
+
"grad_norm": 12.508312225341797,
|
212 |
+
"learning_rate": 4.59016393442623e-05,
|
213 |
+
"loss": 0.4358,
|
214 |
+
"step": 12
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.192,
|
218 |
+
"eval_exact_match": 0.0,
|
219 |
+
"eval_f1_a": 0.2142857142857143,
|
220 |
+
"eval_f1_m": 0.37786431255819003,
|
221 |
+
"eval_loss": 0.7548164129257202,
|
222 |
+
"eval_runtime": 12.2924,
|
223 |
+
"eval_samples_per_second": 20.338,
|
224 |
+
"eval_steps_per_second": 2.603,
|
225 |
+
"step": 12
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.208,
|
229 |
+
"grad_norm": 13.73599624633789,
|
230 |
+
"learning_rate": 4.549180327868853e-05,
|
231 |
+
"loss": 0.7875,
|
232 |
+
"step": 13
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.208,
|
236 |
+
"eval_exact_match": 0.0,
|
237 |
+
"eval_f1_a": 0.21582733812949637,
|
238 |
+
"eval_f1_m": 0.37958707958707955,
|
239 |
+
"eval_loss": 0.7478398680686951,
|
240 |
+
"eval_runtime": 12.293,
|
241 |
+
"eval_samples_per_second": 20.337,
|
242 |
+
"eval_steps_per_second": 2.603,
|
243 |
+
"step": 13
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.224,
|
247 |
+
"grad_norm": 17.087984085083008,
|
248 |
+
"learning_rate": 4.508196721311476e-05,
|
249 |
+
"loss": 0.9012,
|
250 |
+
"step": 14
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.224,
|
254 |
+
"eval_exact_match": 0.0,
|
255 |
+
"eval_f1_a": 0.2377622377622378,
|
256 |
+
"eval_f1_m": 0.38485918843061695,
|
257 |
+
"eval_loss": 0.7398672103881836,
|
258 |
+
"eval_runtime": 12.294,
|
259 |
+
"eval_samples_per_second": 20.335,
|
260 |
+
"eval_steps_per_second": 2.603,
|
261 |
+
"step": 14
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.24,
|
265 |
+
"grad_norm": 17.19772720336914,
|
266 |
+
"learning_rate": 4.467213114754098e-05,
|
267 |
+
"loss": 0.8344,
|
268 |
+
"step": 15
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.24,
|
272 |
+
"eval_exact_match": 0.0,
|
273 |
+
"eval_f1_a": 0.24657534246575338,
|
274 |
+
"eval_f1_m": 0.38393596199718655,
|
275 |
+
"eval_loss": 0.7301445603370667,
|
276 |
+
"eval_runtime": 12.3925,
|
277 |
+
"eval_samples_per_second": 20.173,
|
278 |
+
"eval_steps_per_second": 2.582,
|
279 |
+
"step": 15
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.256,
|
283 |
+
"grad_norm": 9.059144973754883,
|
284 |
+
"learning_rate": 4.426229508196721e-05,
|
285 |
+
"loss": 0.6957,
|
286 |
+
"step": 16
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.256,
|
290 |
+
"eval_exact_match": 0.02040816326530612,
|
291 |
+
"eval_f1_a": 0.3184713375796179,
|
292 |
+
"eval_f1_m": 0.4192099850263115,
|
293 |
+
"eval_loss": 0.7225546836853027,
|
294 |
+
"eval_runtime": 12.2951,
|
295 |
+
"eval_samples_per_second": 20.333,
|
296 |
+
"eval_steps_per_second": 2.603,
|
297 |
+
"step": 16
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.272,
|
301 |
+
"grad_norm": 4.891639709472656,
|
302 |
+
"learning_rate": 4.3852459016393444e-05,
|
303 |
+
"loss": 0.6085,
|
304 |
+
"step": 17
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.272,
|
308 |
+
"eval_exact_match": 0.061224489795918366,
|
309 |
+
"eval_f1_a": 0.3878787878787879,
|
310 |
+
"eval_f1_m": 0.4543832318142042,
|
311 |
+
"eval_loss": 0.7196054458618164,
|
312 |
+
"eval_runtime": 12.2946,
|
313 |
+
"eval_samples_per_second": 20.334,
|
314 |
+
"eval_steps_per_second": 2.603,
|
315 |
+
"step": 17
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.288,
|
319 |
+
"grad_norm": 11.897939682006836,
|
320 |
+
"learning_rate": 4.3442622950819674e-05,
|
321 |
+
"loss": 0.7777,
|
322 |
+
"step": 18
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.288,
|
326 |
+
"eval_exact_match": 0.04081632653061224,
|
327 |
+
"eval_f1_a": 0.3976608187134503,
|
328 |
+
"eval_f1_m": 0.4537870592792561,
|
329 |
+
"eval_loss": 0.7144648432731628,
|
330 |
+
"eval_runtime": 12.3977,
|
331 |
+
"eval_samples_per_second": 20.165,
|
332 |
+
"eval_steps_per_second": 2.581,
|
333 |
+
"step": 18
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.304,
|
337 |
+
"grad_norm": 11.019088745117188,
|
338 |
+
"learning_rate": 4.3032786885245904e-05,
|
339 |
+
"loss": 0.6732,
|
340 |
+
"step": 19
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.304,
|
344 |
+
"eval_exact_match": 0.04081632653061224,
|
345 |
+
"eval_f1_a": 0.39285714285714285,
|
346 |
+
"eval_f1_m": 0.4570021548412905,
|
347 |
+
"eval_loss": 0.7114218473434448,
|
348 |
+
"eval_runtime": 12.3988,
|
349 |
+
"eval_samples_per_second": 20.163,
|
350 |
+
"eval_steps_per_second": 2.581,
|
351 |
+
"step": 19
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.32,
|
355 |
+
"grad_norm": 9.549395561218262,
|
356 |
+
"learning_rate": 4.262295081967213e-05,
|
357 |
+
"loss": 0.7477,
|
358 |
+
"step": 20
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 0.32,
|
362 |
+
"eval_exact_match": 0.04081632653061224,
|
363 |
+
"eval_f1_a": 0.4046242774566474,
|
364 |
+
"eval_f1_m": 0.4577005477515681,
|
365 |
+
"eval_loss": 0.709179699420929,
|
366 |
+
"eval_runtime": 12.4018,
|
367 |
+
"eval_samples_per_second": 20.158,
|
368 |
+
"eval_steps_per_second": 2.58,
|
369 |
+
"step": 20
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.336,
|
373 |
+
"grad_norm": 6.315933704376221,
|
374 |
+
"learning_rate": 4.2213114754098365e-05,
|
375 |
+
"loss": 0.6196,
|
376 |
+
"step": 21
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.336,
|
380 |
+
"eval_exact_match": 0.04081632653061224,
|
381 |
+
"eval_f1_a": 0.4069767441860465,
|
382 |
+
"eval_f1_m": 0.4574949710153791,
|
383 |
+
"eval_loss": 0.7092265486717224,
|
384 |
+
"eval_runtime": 12.2969,
|
385 |
+
"eval_samples_per_second": 20.33,
|
386 |
+
"eval_steps_per_second": 2.602,
|
387 |
+
"step": 21
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.352,
|
391 |
+
"grad_norm": 13.465363502502441,
|
392 |
+
"learning_rate": 4.1803278688524595e-05,
|
393 |
+
"loss": 0.8407,
|
394 |
+
"step": 22
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.352,
|
398 |
+
"eval_exact_match": 0.04081632653061224,
|
399 |
+
"eval_f1_a": 0.4333333333333333,
|
400 |
+
"eval_f1_m": 0.4608648720893619,
|
401 |
+
"eval_loss": 0.7104062438011169,
|
402 |
+
"eval_runtime": 12.3998,
|
403 |
+
"eval_samples_per_second": 20.162,
|
404 |
+
"eval_steps_per_second": 2.581,
|
405 |
+
"step": 22
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.368,
|
409 |
+
"grad_norm": 5.6240763664245605,
|
410 |
+
"learning_rate": 4.1393442622950826e-05,
|
411 |
+
"loss": 0.6945,
|
412 |
+
"step": 23
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.368,
|
416 |
+
"eval_exact_match": 0.04081632653061224,
|
417 |
+
"eval_f1_a": 0.4175824175824176,
|
418 |
+
"eval_f1_m": 0.4523820850351463,
|
419 |
+
"eval_loss": 0.7099843621253967,
|
420 |
+
"eval_runtime": 12.5009,
|
421 |
+
"eval_samples_per_second": 19.999,
|
422 |
+
"eval_steps_per_second": 2.56,
|
423 |
+
"step": 23
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.384,
|
427 |
+
"grad_norm": 11.571455001831055,
|
428 |
+
"learning_rate": 4.098360655737705e-05,
|
429 |
+
"loss": 0.7534,
|
430 |
+
"step": 24
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.384,
|
434 |
+
"eval_exact_match": 0.04081632653061224,
|
435 |
+
"eval_f1_a": 0.42774566473988435,
|
436 |
+
"eval_f1_m": 0.4625007645415809,
|
437 |
+
"eval_loss": 0.7112500071525574,
|
438 |
+
"eval_runtime": 12.505,
|
439 |
+
"eval_samples_per_second": 19.992,
|
440 |
+
"eval_steps_per_second": 2.559,
|
441 |
+
"step": 24
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.4,
|
445 |
+
"grad_norm": 9.693904876708984,
|
446 |
+
"learning_rate": 4.057377049180328e-05,
|
447 |
+
"loss": 0.6428,
|
448 |
+
"step": 25
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.4,
|
452 |
+
"eval_exact_match": 0.02040816326530612,
|
453 |
+
"eval_f1_a": 0.32258064516129026,
|
454 |
+
"eval_f1_m": 0.42786660784860053,
|
455 |
+
"eval_loss": 0.7106679677963257,
|
456 |
+
"eval_runtime": 12.5005,
|
457 |
+
"eval_samples_per_second": 19.999,
|
458 |
+
"eval_steps_per_second": 2.56,
|
459 |
+
"step": 25
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.416,
|
463 |
+
"grad_norm": 5.713263034820557,
|
464 |
+
"learning_rate": 4.016393442622951e-05,
|
465 |
+
"loss": 0.649,
|
466 |
+
"step": 26
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.416,
|
470 |
+
"eval_exact_match": 0.0,
|
471 |
+
"eval_f1_a": 0.2638888888888889,
|
472 |
+
"eval_f1_m": 0.4046327255510929,
|
473 |
+
"eval_loss": 0.7118203043937683,
|
474 |
+
"eval_runtime": 12.4034,
|
475 |
+
"eval_samples_per_second": 20.156,
|
476 |
+
"eval_steps_per_second": 2.58,
|
477 |
+
"step": 26
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.432,
|
481 |
+
"grad_norm": 7.6466965675354,
|
482 |
+
"learning_rate": 3.975409836065574e-05,
|
483 |
+
"loss": 0.7344,
|
484 |
+
"step": 27
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.432,
|
488 |
+
"eval_exact_match": 0.0,
|
489 |
+
"eval_f1_a": 0.18045112781954886,
|
490 |
+
"eval_f1_m": 0.3727819799248371,
|
491 |
+
"eval_loss": 0.7153554558753967,
|
492 |
+
"eval_runtime": 12.4059,
|
493 |
+
"eval_samples_per_second": 20.152,
|
494 |
+
"eval_steps_per_second": 2.579,
|
495 |
+
"step": 27
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.448,
|
499 |
+
"grad_norm": 12.54140567779541,
|
500 |
+
"learning_rate": 3.934426229508197e-05,
|
501 |
+
"loss": 0.5762,
|
502 |
+
"step": 28
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.448,
|
506 |
+
"eval_exact_match": 0.0,
|
507 |
+
"eval_f1_a": 0.13846153846153844,
|
508 |
+
"eval_f1_m": 0.3607012601910561,
|
509 |
+
"eval_loss": 0.7164726853370667,
|
510 |
+
"eval_runtime": 12.4987,
|
511 |
+
"eval_samples_per_second": 20.002,
|
512 |
+
"eval_steps_per_second": 2.56,
|
513 |
+
"step": 28
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.464,
|
517 |
+
"grad_norm": 7.025119781494141,
|
518 |
+
"learning_rate": 3.89344262295082e-05,
|
519 |
+
"loss": 0.6606,
|
520 |
+
"step": 29
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.464,
|
524 |
+
"eval_exact_match": 0.0,
|
525 |
+
"eval_f1_a": 0.11111111111111112,
|
526 |
+
"eval_f1_m": 0.35377706194032715,
|
527 |
+
"eval_loss": 0.719851553440094,
|
528 |
+
"eval_runtime": 12.599,
|
529 |
+
"eval_samples_per_second": 19.843,
|
530 |
+
"eval_steps_per_second": 2.54,
|
531 |
+
"step": 29
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.48,
|
535 |
+
"grad_norm": 16.650728225708008,
|
536 |
+
"learning_rate": 3.8524590163934424e-05,
|
537 |
+
"loss": 0.6886,
|
538 |
+
"step": 30
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.48,
|
542 |
+
"eval_exact_match": 0.0,
|
543 |
+
"eval_f1_a": 0.05454545454545454,
|
544 |
+
"eval_f1_m": 0.3549857455469701,
|
545 |
+
"eval_loss": 0.7235468626022339,
|
546 |
+
"eval_runtime": 12.5049,
|
547 |
+
"eval_samples_per_second": 19.992,
|
548 |
+
"eval_steps_per_second": 2.559,
|
549 |
+
"step": 30
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.496,
|
553 |
+
"grad_norm": 9.604567527770996,
|
554 |
+
"learning_rate": 3.8114754098360655e-05,
|
555 |
+
"loss": 0.6693,
|
556 |
+
"step": 31
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.496,
|
560 |
+
"eval_exact_match": 0.0,
|
561 |
+
"eval_f1_a": 0.03773584905660377,
|
562 |
+
"eval_f1_m": 0.3570682452135034,
|
563 |
+
"eval_loss": 0.730707049369812,
|
564 |
+
"eval_runtime": 12.6051,
|
565 |
+
"eval_samples_per_second": 19.833,
|
566 |
+
"eval_steps_per_second": 2.539,
|
567 |
+
"step": 31
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.512,
|
571 |
+
"grad_norm": 10.662591934204102,
|
572 |
+
"learning_rate": 3.7704918032786885e-05,
|
573 |
+
"loss": 0.8203,
|
574 |
+
"step": 32
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 0.512,
|
578 |
+
"eval_exact_match": 0.0,
|
579 |
+
"eval_f1_a": 0.019230769230769232,
|
580 |
+
"eval_f1_m": 0.35394517780472173,
|
581 |
+
"eval_loss": 0.7325780987739563,
|
582 |
+
"eval_runtime": 12.5102,
|
583 |
+
"eval_samples_per_second": 19.984,
|
584 |
+
"eval_steps_per_second": 2.558,
|
585 |
+
"step": 32
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.528,
|
589 |
+
"grad_norm": 5.810702323913574,
|
590 |
+
"learning_rate": 3.729508196721312e-05,
|
591 |
+
"loss": 0.6831,
|
592 |
+
"step": 33
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.528,
|
596 |
+
"eval_exact_match": 0.0,
|
597 |
+
"eval_f1_a": 0.019230769230769232,
|
598 |
+
"eval_f1_m": 0.35394517780472173,
|
599 |
+
"eval_loss": 0.7296562790870667,
|
600 |
+
"eval_runtime": 12.5052,
|
601 |
+
"eval_samples_per_second": 19.992,
|
602 |
+
"eval_steps_per_second": 2.559,
|
603 |
+
"step": 33
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.544,
|
607 |
+
"grad_norm": 6.527573585510254,
|
608 |
+
"learning_rate": 3.6885245901639346e-05,
|
609 |
+
"loss": 0.6942,
|
610 |
+
"step": 34
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.544,
|
614 |
+
"eval_exact_match": 0.0,
|
615 |
+
"eval_f1_a": 0.019230769230769232,
|
616 |
+
"eval_f1_m": 0.35394517780472173,
|
617 |
+
"eval_loss": 0.7321445345878601,
|
618 |
+
"eval_runtime": 12.6062,
|
619 |
+
"eval_samples_per_second": 19.831,
|
620 |
+
"eval_steps_per_second": 2.538,
|
621 |
+
"step": 34
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.56,
|
625 |
+
"grad_norm": 15.23520565032959,
|
626 |
+
"learning_rate": 3.6475409836065576e-05,
|
627 |
+
"loss": 0.7819,
|
628 |
+
"step": 35
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.56,
|
632 |
+
"eval_exact_match": 0.0,
|
633 |
+
"eval_f1_a": 0.019417475728155338,
|
634 |
+
"eval_f1_m": 0.3550274288869728,
|
635 |
+
"eval_loss": 0.7335781455039978,
|
636 |
+
"eval_runtime": 12.6066,
|
637 |
+
"eval_samples_per_second": 19.831,
|
638 |
+
"eval_steps_per_second": 2.538,
|
639 |
+
"step": 35
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.576,
|
643 |
+
"grad_norm": 12.970118522644043,
|
644 |
+
"learning_rate": 3.6065573770491806e-05,
|
645 |
+
"loss": 0.5959,
|
646 |
+
"step": 36
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.576,
|
650 |
+
"eval_exact_match": 0.0,
|
651 |
+
"eval_f1_a": 0.0,
|
652 |
+
"eval_f1_m": 0.3489535707722984,
|
653 |
+
"eval_loss": 0.7367480397224426,
|
654 |
+
"eval_runtime": 12.5014,
|
655 |
+
"eval_samples_per_second": 19.998,
|
656 |
+
"eval_steps_per_second": 2.56,
|
657 |
+
"step": 36
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.592,
|
661 |
+
"grad_norm": 9.984509468078613,
|
662 |
+
"learning_rate": 3.5655737704918037e-05,
|
663 |
+
"loss": 0.5692,
|
664 |
+
"step": 37
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.592,
|
668 |
+
"eval_exact_match": 0.0,
|
669 |
+
"eval_f1_a": 0.0,
|
670 |
+
"eval_f1_m": 0.3489535707722984,
|
671 |
+
"eval_loss": 0.7453652620315552,
|
672 |
+
"eval_runtime": 12.4005,
|
673 |
+
"eval_samples_per_second": 20.16,
|
674 |
+
"eval_steps_per_second": 2.581,
|
675 |
+
"step": 37
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.608,
|
679 |
+
"grad_norm": 9.310087203979492,
|
680 |
+
"learning_rate": 3.524590163934427e-05,
|
681 |
+
"loss": 0.8538,
|
682 |
+
"step": 38
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.608,
|
686 |
+
"eval_exact_match": 0.0,
|
687 |
+
"eval_f1_a": 0.0,
|
688 |
+
"eval_f1_m": 0.35077572820670067,
|
689 |
+
"eval_loss": 0.7506445050239563,
|
690 |
+
"eval_runtime": 12.5041,
|
691 |
+
"eval_samples_per_second": 19.993,
|
692 |
+
"eval_steps_per_second": 2.559,
|
693 |
+
"step": 38
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.624,
|
697 |
+
"grad_norm": 17.32353401184082,
|
698 |
+
"learning_rate": 3.483606557377049e-05,
|
699 |
+
"loss": 0.7333,
|
700 |
+
"step": 39
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.624,
|
704 |
+
"eval_exact_match": 0.0,
|
705 |
+
"eval_f1_a": 0.0,
|
706 |
+
"eval_f1_m": 0.35077572820670067,
|
707 |
+
"eval_loss": 0.7485976815223694,
|
708 |
+
"eval_runtime": 12.605,
|
709 |
+
"eval_samples_per_second": 19.833,
|
710 |
+
"eval_steps_per_second": 2.539,
|
711 |
+
"step": 39
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.64,
|
715 |
+
"grad_norm": 9.058735847473145,
|
716 |
+
"learning_rate": 3.442622950819672e-05,
|
717 |
+
"loss": 0.4784,
|
718 |
+
"step": 40
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.64,
|
722 |
+
"eval_exact_match": 0.0,
|
723 |
+
"eval_f1_a": 0.0,
|
724 |
+
"eval_f1_m": 0.35077572820670067,
|
725 |
+
"eval_loss": 0.7543515563011169,
|
726 |
+
"eval_runtime": 12.4985,
|
727 |
+
"eval_samples_per_second": 20.002,
|
728 |
+
"eval_steps_per_second": 2.56,
|
729 |
+
"step": 40
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.656,
|
733 |
+
"grad_norm": 15.80337142944336,
|
734 |
+
"learning_rate": 3.401639344262295e-05,
|
735 |
+
"loss": 0.8348,
|
736 |
+
"step": 41
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.656,
|
740 |
+
"eval_exact_match": 0.0,
|
741 |
+
"eval_f1_a": 0.0,
|
742 |
+
"eval_f1_m": 0.35077572820670067,
|
743 |
+
"eval_loss": 0.7519648671150208,
|
744 |
+
"eval_runtime": 12.4002,
|
745 |
+
"eval_samples_per_second": 20.161,
|
746 |
+
"eval_steps_per_second": 2.581,
|
747 |
+
"step": 41
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.672,
|
751 |
+
"grad_norm": 18.595117568969727,
|
752 |
+
"learning_rate": 3.360655737704918e-05,
|
753 |
+
"loss": 0.8212,
|
754 |
+
"step": 42
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.672,
|
758 |
+
"eval_exact_match": 0.0,
|
759 |
+
"eval_f1_a": 0.0,
|
760 |
+
"eval_f1_m": 0.35077572820670067,
|
761 |
+
"eval_loss": 0.7456523180007935,
|
762 |
+
"eval_runtime": 12.5047,
|
763 |
+
"eval_samples_per_second": 19.992,
|
764 |
+
"eval_steps_per_second": 2.559,
|
765 |
+
"step": 42
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.688,
|
769 |
+
"grad_norm": 9.790151596069336,
|
770 |
+
"learning_rate": 3.319672131147541e-05,
|
771 |
+
"loss": 0.9515,
|
772 |
+
"step": 43
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.688,
|
776 |
+
"eval_exact_match": 0.0,
|
777 |
+
"eval_f1_a": 0.0,
|
778 |
+
"eval_f1_m": 0.3489535707722984,
|
779 |
+
"eval_loss": 0.7356074452400208,
|
780 |
+
"eval_runtime": 12.5029,
|
781 |
+
"eval_samples_per_second": 19.995,
|
782 |
+
"eval_steps_per_second": 2.559,
|
783 |
+
"step": 43
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.704,
|
787 |
+
"grad_norm": 19.172956466674805,
|
788 |
+
"learning_rate": 3.2786885245901635e-05,
|
789 |
+
"loss": 0.8488,
|
790 |
+
"step": 44
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.704,
|
794 |
+
"eval_exact_match": 0.0,
|
795 |
+
"eval_f1_a": 0.019230769230769232,
|
796 |
+
"eval_f1_m": 0.35394517780472173,
|
797 |
+
"eval_loss": 0.7283183336257935,
|
798 |
+
"eval_runtime": 12.6008,
|
799 |
+
"eval_samples_per_second": 19.84,
|
800 |
+
"eval_steps_per_second": 2.54,
|
801 |
+
"step": 44
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.72,
|
805 |
+
"grad_norm": 10.353903770446777,
|
806 |
+
"learning_rate": 3.237704918032787e-05,
|
807 |
+
"loss": 0.6007,
|
808 |
+
"step": 45
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.72,
|
812 |
+
"eval_exact_match": 0.0,
|
813 |
+
"eval_f1_a": 0.019230769230769232,
|
814 |
+
"eval_f1_m": 0.35394517780472173,
|
815 |
+
"eval_loss": 0.7258906364440918,
|
816 |
+
"eval_runtime": 12.4066,
|
817 |
+
"eval_samples_per_second": 20.15,
|
818 |
+
"eval_steps_per_second": 2.579,
|
819 |
+
"step": 45
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.736,
|
823 |
+
"grad_norm": 10.669143676757812,
|
824 |
+
"learning_rate": 3.19672131147541e-05,
|
825 |
+
"loss": 0.8167,
|
826 |
+
"step": 46
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.736,
|
830 |
+
"eval_exact_match": 0.0,
|
831 |
+
"eval_f1_a": 0.019230769230769232,
|
832 |
+
"eval_f1_m": 0.35394517780472173,
|
833 |
+
"eval_loss": 0.7255585789680481,
|
834 |
+
"eval_runtime": 12.6073,
|
835 |
+
"eval_samples_per_second": 19.83,
|
836 |
+
"eval_steps_per_second": 2.538,
|
837 |
+
"step": 46
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.752,
|
841 |
+
"grad_norm": 12.651082992553711,
|
842 |
+
"learning_rate": 3.155737704918033e-05,
|
843 |
+
"loss": 0.7909,
|
844 |
+
"step": 47
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.752,
|
848 |
+
"eval_exact_match": 0.0,
|
849 |
+
"eval_f1_a": 0.019047619047619046,
|
850 |
+
"eval_f1_m": 0.35264647650602043,
|
851 |
+
"eval_loss": 0.7224531173706055,
|
852 |
+
"eval_runtime": 12.5046,
|
853 |
+
"eval_samples_per_second": 19.993,
|
854 |
+
"eval_steps_per_second": 2.559,
|
855 |
+
"step": 47
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.768,
|
859 |
+
"grad_norm": 16.77728843688965,
|
860 |
+
"learning_rate": 3.114754098360656e-05,
|
861 |
+
"loss": 0.7277,
|
862 |
+
"step": 48
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 0.768,
|
866 |
+
"eval_exact_match": 0.0,
|
867 |
+
"eval_f1_a": 0.037383177570093455,
|
868 |
+
"eval_f1_m": 0.3553675649413946,
|
869 |
+
"eval_loss": 0.7222617268562317,
|
870 |
+
"eval_runtime": 12.5048,
|
871 |
+
"eval_samples_per_second": 19.992,
|
872 |
+
"eval_steps_per_second": 2.559,
|
873 |
+
"step": 48
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.784,
|
877 |
+
"grad_norm": 9.990218162536621,
|
878 |
+
"learning_rate": 3.073770491803279e-05,
|
879 |
+
"loss": 0.6484,
|
880 |
+
"step": 49
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.784,
|
884 |
+
"eval_exact_match": 0.0,
|
885 |
+
"eval_f1_a": 0.018867924528301886,
|
886 |
+
"eval_f1_m": 0.35094579623391153,
|
887 |
+
"eval_loss": 0.7233593463897705,
|
888 |
+
"eval_runtime": 12.3979,
|
889 |
+
"eval_samples_per_second": 20.165,
|
890 |
+
"eval_steps_per_second": 2.581,
|
891 |
+
"step": 49
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.8,
|
895 |
+
"grad_norm": 19.805315017700195,
|
896 |
+
"learning_rate": 3.0327868852459017e-05,
|
897 |
+
"loss": 0.7366,
|
898 |
+
"step": 50
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.8,
|
902 |
+
"eval_exact_match": 0.0,
|
903 |
+
"eval_f1_a": 0.05454545454545454,
|
904 |
+
"eval_f1_m": 0.35851045213290117,
|
905 |
+
"eval_loss": 0.7192890644073486,
|
906 |
+
"eval_runtime": 12.394,
|
907 |
+
"eval_samples_per_second": 20.171,
|
908 |
+
"eval_steps_per_second": 2.582,
|
909 |
+
"step": 50
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.816,
|
913 |
+
"grad_norm": 6.260676860809326,
|
914 |
+
"learning_rate": 2.9918032786885248e-05,
|
915 |
+
"loss": 0.6544,
|
916 |
+
"step": 51
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.816,
|
920 |
+
"eval_exact_match": 0.0,
|
921 |
+
"eval_f1_a": 0.07207207207207207,
|
922 |
+
"eval_f1_m": 0.3631490108530924,
|
923 |
+
"eval_loss": 0.7178593873977661,
|
924 |
+
"eval_runtime": 12.399,
|
925 |
+
"eval_samples_per_second": 20.163,
|
926 |
+
"eval_steps_per_second": 2.581,
|
927 |
+
"step": 51
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.832,
|
931 |
+
"grad_norm": 6.211192607879639,
|
932 |
+
"learning_rate": 2.9508196721311478e-05,
|
933 |
+
"loss": 0.5797,
|
934 |
+
"step": 52
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.832,
|
938 |
+
"eval_exact_match": 0.0,
|
939 |
+
"eval_f1_a": 0.07142857142857144,
|
940 |
+
"eval_f1_m": 0.36225194873154054,
|
941 |
+
"eval_loss": 0.7176406383514404,
|
942 |
+
"eval_runtime": 12.2942,
|
943 |
+
"eval_samples_per_second": 20.335,
|
944 |
+
"eval_steps_per_second": 2.603,
|
945 |
+
"step": 52
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.848,
|
949 |
+
"grad_norm": 19.603347778320312,
|
950 |
+
"learning_rate": 2.9098360655737705e-05,
|
951 |
+
"loss": 0.613,
|
952 |
+
"step": 53
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.848,
|
956 |
+
"eval_exact_match": 0.0,
|
957 |
+
"eval_f1_a": 0.08928571428571429,
|
958 |
+
"eval_f1_m": 0.36680547343812653,
|
959 |
+
"eval_loss": 0.719406247138977,
|
960 |
+
"eval_runtime": 12.2965,
|
961 |
+
"eval_samples_per_second": 20.331,
|
962 |
+
"eval_steps_per_second": 2.602,
|
963 |
+
"step": 53
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.864,
|
967 |
+
"grad_norm": 7.0200042724609375,
|
968 |
+
"learning_rate": 2.8688524590163935e-05,
|
969 |
+
"loss": 0.7246,
|
970 |
+
"step": 54
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.864,
|
974 |
+
"eval_exact_match": 0.0,
|
975 |
+
"eval_f1_a": 0.03773584905660377,
|
976 |
+
"eval_f1_m": 0.35666626624009584,
|
977 |
+
"eval_loss": 0.7230820059776306,
|
978 |
+
"eval_runtime": 12.3942,
|
979 |
+
"eval_samples_per_second": 20.171,
|
980 |
+
"eval_steps_per_second": 2.582,
|
981 |
+
"step": 54
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.88,
|
985 |
+
"grad_norm": 7.6928791999816895,
|
986 |
+
"learning_rate": 2.8278688524590162e-05,
|
987 |
+
"loss": 0.723,
|
988 |
+
"step": 55
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.88,
|
992 |
+
"eval_exact_match": 0.0,
|
993 |
+
"eval_f1_a": 0.019230769230769232,
|
994 |
+
"eval_f1_m": 0.35394517780472173,
|
995 |
+
"eval_loss": 0.7283515334129333,
|
996 |
+
"eval_runtime": 12.4051,
|
997 |
+
"eval_samples_per_second": 20.153,
|
998 |
+
"eval_steps_per_second": 2.58,
|
999 |
+
"step": 55
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.896,
|
1003 |
+
"grad_norm": 9.09825611114502,
|
1004 |
+
"learning_rate": 2.7868852459016392e-05,
|
1005 |
+
"loss": 0.526,
|
1006 |
+
"step": 56
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.896,
|
1010 |
+
"eval_exact_match": 0.0,
|
1011 |
+
"eval_f1_a": 0.019230769230769232,
|
1012 |
+
"eval_f1_m": 0.35394517780472173,
|
1013 |
+
"eval_loss": 0.736648440361023,
|
1014 |
+
"eval_runtime": 12.5063,
|
1015 |
+
"eval_samples_per_second": 19.99,
|
1016 |
+
"eval_steps_per_second": 2.559,
|
1017 |
+
"step": 56
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.912,
|
1021 |
+
"grad_norm": 12.663421630859375,
|
1022 |
+
"learning_rate": 2.7459016393442626e-05,
|
1023 |
+
"loss": 0.7038,
|
1024 |
+
"step": 57
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.912,
|
1028 |
+
"eval_exact_match": 0.0,
|
1029 |
+
"eval_f1_a": 0.0,
|
1030 |
+
"eval_f1_m": 0.3489535707722984,
|
1031 |
+
"eval_loss": 0.7481816411018372,
|
1032 |
+
"eval_runtime": 12.4036,
|
1033 |
+
"eval_samples_per_second": 20.155,
|
1034 |
+
"eval_steps_per_second": 2.58,
|
1035 |
+
"step": 57
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.928,
|
1039 |
+
"grad_norm": 15.922131538391113,
|
1040 |
+
"learning_rate": 2.7049180327868856e-05,
|
1041 |
+
"loss": 0.7805,
|
1042 |
+
"step": 58
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.928,
|
1046 |
+
"eval_exact_match": 0.0,
|
1047 |
+
"eval_f1_a": 0.0,
|
1048 |
+
"eval_f1_m": 0.35077572820670067,
|
1049 |
+
"eval_loss": 0.7556718587875366,
|
1050 |
+
"eval_runtime": 12.4053,
|
1051 |
+
"eval_samples_per_second": 20.153,
|
1052 |
+
"eval_steps_per_second": 2.58,
|
1053 |
+
"step": 58
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.944,
|
1057 |
+
"grad_norm": 15.116573333740234,
|
1058 |
+
"learning_rate": 2.6639344262295087e-05,
|
1059 |
+
"loss": 0.7645,
|
1060 |
+
"step": 59
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.944,
|
1064 |
+
"eval_exact_match": 0.0,
|
1065 |
+
"eval_f1_a": 0.0,
|
1066 |
+
"eval_f1_m": 0.35077572820670067,
|
1067 |
+
"eval_loss": 0.7615898251533508,
|
1068 |
+
"eval_runtime": 12.301,
|
1069 |
+
"eval_samples_per_second": 20.324,
|
1070 |
+
"eval_steps_per_second": 2.601,
|
1071 |
+
"step": 59
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.96,
|
1075 |
+
"grad_norm": 16.11196517944336,
|
1076 |
+
"learning_rate": 2.6229508196721314e-05,
|
1077 |
+
"loss": 0.802,
|
1078 |
+
"step": 60
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 0.96,
|
1082 |
+
"eval_exact_match": 0.0,
|
1083 |
+
"eval_f1_a": 0.0,
|
1084 |
+
"eval_f1_m": 0.35077572820670067,
|
1085 |
+
"eval_loss": 0.762087881565094,
|
1086 |
+
"eval_runtime": 12.4045,
|
1087 |
+
"eval_samples_per_second": 20.154,
|
1088 |
+
"eval_steps_per_second": 2.58,
|
1089 |
+
"step": 60
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.976,
|
1093 |
+
"grad_norm": 11.784616470336914,
|
1094 |
+
"learning_rate": 2.5819672131147544e-05,
|
1095 |
+
"loss": 0.7266,
|
1096 |
+
"step": 61
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.976,
|
1100 |
+
"eval_exact_match": 0.0,
|
1101 |
+
"eval_f1_a": 0.0,
|
1102 |
+
"eval_f1_m": 0.35077572820670067,
|
1103 |
+
"eval_loss": 0.7605761885643005,
|
1104 |
+
"eval_runtime": 12.5067,
|
1105 |
+
"eval_samples_per_second": 19.989,
|
1106 |
+
"eval_steps_per_second": 2.559,
|
1107 |
+
"step": 61
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.992,
|
1111 |
+
"grad_norm": 5.855625152587891,
|
1112 |
+
"learning_rate": 2.540983606557377e-05,
|
1113 |
+
"loss": 0.6895,
|
1114 |
+
"step": 62
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.992,
|
1118 |
+
"eval_exact_match": 0.0,
|
1119 |
+
"eval_f1_a": 0.0,
|
1120 |
+
"eval_f1_m": 0.35077572820670067,
|
1121 |
+
"eval_loss": 0.7616230249404907,
|
1122 |
+
"eval_runtime": 12.4021,
|
1123 |
+
"eval_samples_per_second": 20.158,
|
1124 |
+
"eval_steps_per_second": 2.58,
|
1125 |
+
"step": 62
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 1.008,
|
1129 |
+
"grad_norm": 12.561187744140625,
|
1130 |
+
"learning_rate": 2.5e-05,
|
1131 |
+
"loss": 0.8057,
|
1132 |
+
"step": 63
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 1.008,
|
1136 |
+
"eval_exact_match": 0.0,
|
1137 |
+
"eval_f1_a": 0.0,
|
1138 |
+
"eval_f1_m": 0.35077572820670067,
|
1139 |
+
"eval_loss": 0.7573671936988831,
|
1140 |
+
"eval_runtime": 12.5096,
|
1141 |
+
"eval_samples_per_second": 19.985,
|
1142 |
+
"eval_steps_per_second": 2.558,
|
1143 |
+
"step": 63
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.024,
|
1147 |
+
"grad_norm": 10.385027885437012,
|
1148 |
+
"learning_rate": 2.459016393442623e-05,
|
1149 |
+
"loss": 0.7454,
|
1150 |
+
"step": 64
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.024,
|
1154 |
+
"eval_exact_match": 0.0,
|
1155 |
+
"eval_f1_a": 0.0,
|
1156 |
+
"eval_f1_m": 0.3489535707722984,
|
1157 |
+
"eval_loss": 0.7491288781166077,
|
1158 |
+
"eval_runtime": 12.4029,
|
1159 |
+
"eval_samples_per_second": 20.157,
|
1160 |
+
"eval_steps_per_second": 2.58,
|
1161 |
+
"step": 64
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.04,
|
1165 |
+
"grad_norm": 15.67496395111084,
|
1166 |
+
"learning_rate": 2.418032786885246e-05,
|
1167 |
+
"loss": 0.877,
|
1168 |
+
"step": 65
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 1.04,
|
1172 |
+
"eval_exact_match": 0.0,
|
1173 |
+
"eval_f1_a": 0.019417475728155338,
|
1174 |
+
"eval_f1_m": 0.3550274288869728,
|
1175 |
+
"eval_loss": 0.7429726719856262,
|
1176 |
+
"eval_runtime": 12.4019,
|
1177 |
+
"eval_samples_per_second": 20.158,
|
1178 |
+
"eval_steps_per_second": 2.58,
|
1179 |
+
"step": 65
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.056,
|
1183 |
+
"grad_norm": 14.67371654510498,
|
1184 |
+
"learning_rate": 2.377049180327869e-05,
|
1185 |
+
"loss": 0.7684,
|
1186 |
+
"step": 66
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 1.056,
|
1190 |
+
"eval_exact_match": 0.0,
|
1191 |
+
"eval_f1_a": 0.019230769230769232,
|
1192 |
+
"eval_f1_m": 0.35394517780472173,
|
1193 |
+
"eval_loss": 0.7341777086257935,
|
1194 |
+
"eval_runtime": 12.3064,
|
1195 |
+
"eval_samples_per_second": 20.315,
|
1196 |
+
"eval_steps_per_second": 2.6,
|
1197 |
+
"step": 66
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.072,
|
1201 |
+
"grad_norm": 11.17091178894043,
|
1202 |
+
"learning_rate": 2.336065573770492e-05,
|
1203 |
+
"loss": 0.6712,
|
1204 |
+
"step": 67
|
1205 |
+
},
|
1206 |
+
{
|
1207 |
+
"epoch": 1.072,
|
1208 |
+
"eval_exact_match": 0.0,
|
1209 |
+
"eval_f1_a": 0.03669724770642201,
|
1210 |
+
"eval_f1_m": 0.34935849464660995,
|
1211 |
+
"eval_loss": 0.724734365940094,
|
1212 |
+
"eval_runtime": 12.4001,
|
1213 |
+
"eval_samples_per_second": 20.161,
|
1214 |
+
"eval_steps_per_second": 2.581,
|
1215 |
+
"step": 67
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.088,
|
1219 |
+
"grad_norm": 7.933443546295166,
|
1220 |
+
"learning_rate": 2.295081967213115e-05,
|
1221 |
+
"loss": 0.545,
|
1222 |
+
"step": 68
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 1.088,
|
1226 |
+
"eval_exact_match": 0.0,
|
1227 |
+
"eval_f1_a": 0.1,
|
1228 |
+
"eval_f1_m": 0.35936518130395684,
|
1229 |
+
"eval_loss": 0.7180312275886536,
|
1230 |
+
"eval_runtime": 12.6064,
|
1231 |
+
"eval_samples_per_second": 19.831,
|
1232 |
+
"eval_steps_per_second": 2.538,
|
1233 |
+
"step": 68
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.104,
|
1237 |
+
"grad_norm": 6.20879602432251,
|
1238 |
+
"learning_rate": 2.254098360655738e-05,
|
1239 |
+
"loss": 0.5563,
|
1240 |
+
"step": 69
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 1.104,
|
1244 |
+
"eval_exact_match": 0.0,
|
1245 |
+
"eval_f1_a": 0.15503875968992248,
|
1246 |
+
"eval_f1_m": 0.3728975672853224,
|
1247 |
+
"eval_loss": 0.7145351767539978,
|
1248 |
+
"eval_runtime": 12.3015,
|
1249 |
+
"eval_samples_per_second": 20.323,
|
1250 |
+
"eval_steps_per_second": 2.601,
|
1251 |
+
"step": 69
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.12,
|
1255 |
+
"grad_norm": 5.216189861297607,
|
1256 |
+
"learning_rate": 2.2131147540983607e-05,
|
1257 |
+
"loss": 0.5797,
|
1258 |
+
"step": 70
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 1.12,
|
1262 |
+
"eval_exact_match": 0.0,
|
1263 |
+
"eval_f1_a": 0.2222222222222222,
|
1264 |
+
"eval_f1_m": 0.3975035168912719,
|
1265 |
+
"eval_loss": 0.7122148275375366,
|
1266 |
+
"eval_runtime": 12.2962,
|
1267 |
+
"eval_samples_per_second": 20.331,
|
1268 |
+
"eval_steps_per_second": 2.602,
|
1269 |
+
"step": 70
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.1360000000000001,
|
1273 |
+
"grad_norm": 4.51043701171875,
|
1274 |
+
"learning_rate": 2.1721311475409837e-05,
|
1275 |
+
"loss": 0.7785,
|
1276 |
+
"step": 71
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.1360000000000001,
|
1280 |
+
"eval_exact_match": 0.0,
|
1281 |
+
"eval_f1_a": 0.2571428571428571,
|
1282 |
+
"eval_f1_m": 0.4030671709243137,
|
1283 |
+
"eval_loss": 0.7087773680686951,
|
1284 |
+
"eval_runtime": 12.2926,
|
1285 |
+
"eval_samples_per_second": 20.337,
|
1286 |
+
"eval_steps_per_second": 2.603,
|
1287 |
+
"step": 71
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.152,
|
1291 |
+
"grad_norm": 9.325611114501953,
|
1292 |
+
"learning_rate": 2.1311475409836064e-05,
|
1293 |
+
"loss": 0.757,
|
1294 |
+
"step": 72
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.152,
|
1298 |
+
"eval_exact_match": 0.0,
|
1299 |
+
"eval_f1_a": 0.3013698630136986,
|
1300 |
+
"eval_f1_m": 0.4158932903830863,
|
1301 |
+
"eval_loss": 0.7072968482971191,
|
1302 |
+
"eval_runtime": 12.3042,
|
1303 |
+
"eval_samples_per_second": 20.318,
|
1304 |
+
"eval_steps_per_second": 2.601,
|
1305 |
+
"step": 72
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.168,
|
1309 |
+
"grad_norm": 15.549028396606445,
|
1310 |
+
"learning_rate": 2.0901639344262298e-05,
|
1311 |
+
"loss": 0.85,
|
1312 |
+
"step": 73
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.168,
|
1316 |
+
"eval_exact_match": 0.0,
|
1317 |
+
"eval_f1_a": 0.3013698630136986,
|
1318 |
+
"eval_f1_m": 0.4126730412444698,
|
1319 |
+
"eval_loss": 0.7068906426429749,
|
1320 |
+
"eval_runtime": 12.3976,
|
1321 |
+
"eval_samples_per_second": 20.165,
|
1322 |
+
"eval_steps_per_second": 2.581,
|
1323 |
+
"step": 73
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.184,
|
1327 |
+
"grad_norm": 7.413804531097412,
|
1328 |
+
"learning_rate": 2.0491803278688525e-05,
|
1329 |
+
"loss": 0.6694,
|
1330 |
+
"step": 74
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 1.184,
|
1334 |
+
"eval_exact_match": 0.02040816326530612,
|
1335 |
+
"eval_f1_a": 0.32258064516129026,
|
1336 |
+
"eval_f1_m": 0.41783029895274804,
|
1337 |
+
"eval_loss": 0.7051249742507935,
|
1338 |
+
"eval_runtime": 12.3988,
|
1339 |
+
"eval_samples_per_second": 20.163,
|
1340 |
+
"eval_steps_per_second": 2.581,
|
1341 |
+
"step": 74
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.2,
|
1345 |
+
"grad_norm": 13.059216499328613,
|
1346 |
+
"learning_rate": 2.0081967213114755e-05,
|
1347 |
+
"loss": 0.7654,
|
1348 |
+
"step": 75
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 1.2,
|
1352 |
+
"eval_exact_match": 0.02040816326530612,
|
1353 |
+
"eval_f1_a": 0.3658536585365854,
|
1354 |
+
"eval_f1_m": 0.4367546285913633,
|
1355 |
+
"eval_loss": 0.7052109241485596,
|
1356 |
+
"eval_runtime": 12.3021,
|
1357 |
+
"eval_samples_per_second": 20.322,
|
1358 |
+
"eval_steps_per_second": 2.601,
|
1359 |
+
"step": 75
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.216,
|
1363 |
+
"grad_norm": 18.173431396484375,
|
1364 |
+
"learning_rate": 1.9672131147540985e-05,
|
1365 |
+
"loss": 0.7874,
|
1366 |
+
"step": 76
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 1.216,
|
1370 |
+
"eval_exact_match": 0.02040816326530612,
|
1371 |
+
"eval_f1_a": 0.393063583815029,
|
1372 |
+
"eval_f1_m": 0.4441113308460247,
|
1373 |
+
"eval_loss": 0.7044414281845093,
|
1374 |
+
"eval_runtime": 12.3005,
|
1375 |
+
"eval_samples_per_second": 20.324,
|
1376 |
+
"eval_steps_per_second": 2.602,
|
1377 |
+
"step": 76
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.232,
|
1381 |
+
"grad_norm": 5.066444396972656,
|
1382 |
+
"learning_rate": 1.9262295081967212e-05,
|
1383 |
+
"loss": 0.585,
|
1384 |
+
"step": 77
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 1.232,
|
1388 |
+
"eval_exact_match": 0.02040816326530612,
|
1389 |
+
"eval_f1_a": 0.4067796610169491,
|
1390 |
+
"eval_f1_m": 0.44523701921661113,
|
1391 |
+
"eval_loss": 0.7045234441757202,
|
1392 |
+
"eval_runtime": 12.4024,
|
1393 |
+
"eval_samples_per_second": 20.157,
|
1394 |
+
"eval_steps_per_second": 2.58,
|
1395 |
+
"step": 77
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.248,
|
1399 |
+
"grad_norm": 15.81064224243164,
|
1400 |
+
"learning_rate": 1.8852459016393442e-05,
|
1401 |
+
"loss": 0.7125,
|
1402 |
+
"step": 78
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 1.248,
|
1406 |
+
"eval_exact_match": 0.02040816326530612,
|
1407 |
+
"eval_f1_a": 0.4347826086956522,
|
1408 |
+
"eval_f1_m": 0.45324236421175196,
|
1409 |
+
"eval_loss": 0.7049570083618164,
|
1410 |
+
"eval_runtime": 12.2997,
|
1411 |
+
"eval_samples_per_second": 20.326,
|
1412 |
+
"eval_steps_per_second": 2.602,
|
1413 |
+
"step": 78
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.264,
|
1417 |
+
"grad_norm": 15.786576271057129,
|
1418 |
+
"learning_rate": 1.8442622950819673e-05,
|
1419 |
+
"loss": 0.674,
|
1420 |
+
"step": 79
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.264,
|
1424 |
+
"eval_exact_match": 0.04081632653061224,
|
1425 |
+
"eval_f1_a": 0.45263157894736844,
|
1426 |
+
"eval_f1_m": 0.45977191742497864,
|
1427 |
+
"eval_loss": 0.7056093811988831,
|
1428 |
+
"eval_runtime": 12.297,
|
1429 |
+
"eval_samples_per_second": 20.33,
|
1430 |
+
"eval_steps_per_second": 2.602,
|
1431 |
+
"step": 79
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.28,
|
1435 |
+
"grad_norm": 20.205602645874023,
|
1436 |
+
"learning_rate": 1.8032786885245903e-05,
|
1437 |
+
"loss": 0.7886,
|
1438 |
+
"step": 80
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.28,
|
1442 |
+
"eval_exact_match": 0.04081632653061224,
|
1443 |
+
"eval_f1_a": 0.450261780104712,
|
1444 |
+
"eval_f1_m": 0.45734237417910883,
|
1445 |
+
"eval_loss": 0.706125020980835,
|
1446 |
+
"eval_runtime": 12.2957,
|
1447 |
+
"eval_samples_per_second": 20.332,
|
1448 |
+
"eval_steps_per_second": 2.603,
|
1449 |
+
"step": 80
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.296,
|
1453 |
+
"grad_norm": 7.352344036102295,
|
1454 |
+
"learning_rate": 1.7622950819672133e-05,
|
1455 |
+
"loss": 0.521,
|
1456 |
+
"step": 81
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 1.296,
|
1460 |
+
"eval_exact_match": 0.04081632653061224,
|
1461 |
+
"eval_f1_a": 0.44329896907216493,
|
1462 |
+
"eval_f1_m": 0.44956970467174556,
|
1463 |
+
"eval_loss": 0.7077500224113464,
|
1464 |
+
"eval_runtime": 12.4027,
|
1465 |
+
"eval_samples_per_second": 20.157,
|
1466 |
+
"eval_steps_per_second": 2.58,
|
1467 |
+
"step": 81
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.312,
|
1471 |
+
"grad_norm": 9.654190063476562,
|
1472 |
+
"learning_rate": 1.721311475409836e-05,
|
1473 |
+
"loss": 0.7754,
|
1474 |
+
"step": 82
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.312,
|
1478 |
+
"eval_exact_match": 0.04081632653061224,
|
1479 |
+
"eval_f1_a": 0.45226130653266333,
|
1480 |
+
"eval_f1_m": 0.45042921930677027,
|
1481 |
+
"eval_loss": 0.7080312371253967,
|
1482 |
+
"eval_runtime": 12.2984,
|
1483 |
+
"eval_samples_per_second": 20.328,
|
1484 |
+
"eval_steps_per_second": 2.602,
|
1485 |
+
"step": 82
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.328,
|
1489 |
+
"grad_norm": 19.156660079956055,
|
1490 |
+
"learning_rate": 1.680327868852459e-05,
|
1491 |
+
"loss": 0.7493,
|
1492 |
+
"step": 83
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 1.328,
|
1496 |
+
"eval_exact_match": 0.04081632653061224,
|
1497 |
+
"eval_f1_a": 0.4577114427860697,
|
1498 |
+
"eval_f1_m": 0.4507745089377742,
|
1499 |
+
"eval_loss": 0.7095780968666077,
|
1500 |
+
"eval_runtime": 12.2981,
|
1501 |
+
"eval_samples_per_second": 20.328,
|
1502 |
+
"eval_steps_per_second": 2.602,
|
1503 |
+
"step": 83
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.3439999999999999,
|
1507 |
+
"grad_norm": 4.014058589935303,
|
1508 |
+
"learning_rate": 1.6393442622950818e-05,
|
1509 |
+
"loss": 0.7076,
|
1510 |
+
"step": 84
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.3439999999999999,
|
1514 |
+
"eval_exact_match": 0.04081632653061224,
|
1515 |
+
"eval_f1_a": 0.45999999999999996,
|
1516 |
+
"eval_f1_m": 0.45553641369967895,
|
1517 |
+
"eval_loss": 0.7096328139305115,
|
1518 |
+
"eval_runtime": 12.298,
|
1519 |
+
"eval_samples_per_second": 20.329,
|
1520 |
+
"eval_steps_per_second": 2.602,
|
1521 |
+
"step": 84
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.3599999999999999,
|
1525 |
+
"grad_norm": 12.296324729919434,
|
1526 |
+
"learning_rate": 1.598360655737705e-05,
|
1527 |
+
"loss": 0.6649,
|
1528 |
+
"step": 85
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.3599999999999999,
|
1532 |
+
"eval_exact_match": 0.04081632653061224,
|
1533 |
+
"eval_f1_a": 0.4577114427860697,
|
1534 |
+
"eval_f1_m": 0.4507745089377742,
|
1535 |
+
"eval_loss": 0.7094843983650208,
|
1536 |
+
"eval_runtime": 12.2932,
|
1537 |
+
"eval_samples_per_second": 20.337,
|
1538 |
+
"eval_steps_per_second": 2.603,
|
1539 |
+
"step": 85
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.376,
|
1543 |
+
"grad_norm": 8.357748985290527,
|
1544 |
+
"learning_rate": 1.557377049180328e-05,
|
1545 |
+
"loss": 0.6199,
|
1546 |
+
"step": 86
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.376,
|
1550 |
+
"eval_exact_match": 0.04081632653061224,
|
1551 |
+
"eval_f1_a": 0.45544554455445546,
|
1552 |
+
"eval_f1_m": 0.44890376063845455,
|
1553 |
+
"eval_loss": 0.7101484537124634,
|
1554 |
+
"eval_runtime": 12.2925,
|
1555 |
+
"eval_samples_per_second": 20.338,
|
1556 |
+
"eval_steps_per_second": 2.603,
|
1557 |
+
"step": 86
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.392,
|
1561 |
+
"grad_norm": 5.569490909576416,
|
1562 |
+
"learning_rate": 1.5163934426229509e-05,
|
1563 |
+
"loss": 0.7666,
|
1564 |
+
"step": 87
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.392,
|
1568 |
+
"eval_exact_match": 0.04081632653061224,
|
1569 |
+
"eval_f1_a": 0.4577114427860697,
|
1570 |
+
"eval_f1_m": 0.4507745089377742,
|
1571 |
+
"eval_loss": 0.7110859155654907,
|
1572 |
+
"eval_runtime": 12.3978,
|
1573 |
+
"eval_samples_per_second": 20.165,
|
1574 |
+
"eval_steps_per_second": 2.581,
|
1575 |
+
"step": 87
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.408,
|
1579 |
+
"grad_norm": 20.458703994750977,
|
1580 |
+
"learning_rate": 1.4754098360655739e-05,
|
1581 |
+
"loss": 0.7505,
|
1582 |
+
"step": 88
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 1.408,
|
1586 |
+
"eval_exact_match": 0.04081632653061224,
|
1587 |
+
"eval_f1_a": 0.4577114427860697,
|
1588 |
+
"eval_f1_m": 0.4507745089377742,
|
1589 |
+
"eval_loss": 0.7112030982971191,
|
1590 |
+
"eval_runtime": 12.4088,
|
1591 |
+
"eval_samples_per_second": 20.147,
|
1592 |
+
"eval_steps_per_second": 2.579,
|
1593 |
+
"step": 88
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.424,
|
1597 |
+
"grad_norm": 17.410215377807617,
|
1598 |
+
"learning_rate": 1.4344262295081968e-05,
|
1599 |
+
"loss": 0.7426,
|
1600 |
+
"step": 89
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 1.424,
|
1604 |
+
"eval_exact_match": 0.04081632653061224,
|
1605 |
+
"eval_f1_a": 0.45,
|
1606 |
+
"eval_f1_m": 0.4473113054745707,
|
1607 |
+
"eval_loss": 0.7114999890327454,
|
1608 |
+
"eval_runtime": 12.4068,
|
1609 |
+
"eval_samples_per_second": 20.15,
|
1610 |
+
"eval_steps_per_second": 2.579,
|
1611 |
+
"step": 89
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.44,
|
1615 |
+
"grad_norm": 12.000615119934082,
|
1616 |
+
"learning_rate": 1.3934426229508196e-05,
|
1617 |
+
"loss": 0.8439,
|
1618 |
+
"step": 90
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 1.44,
|
1622 |
+
"eval_exact_match": 0.04081632653061224,
|
1623 |
+
"eval_f1_a": 0.45,
|
1624 |
+
"eval_f1_m": 0.4473113054745707,
|
1625 |
+
"eval_loss": 0.7099843621253967,
|
1626 |
+
"eval_runtime": 12.3004,
|
1627 |
+
"eval_samples_per_second": 20.325,
|
1628 |
+
"eval_steps_per_second": 2.602,
|
1629 |
+
"step": 90
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.456,
|
1633 |
+
"grad_norm": 9.254725456237793,
|
1634 |
+
"learning_rate": 1.3524590163934428e-05,
|
1635 |
+
"loss": 0.7011,
|
1636 |
+
"step": 91
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 1.456,
|
1640 |
+
"eval_exact_match": 0.04081632653061224,
|
1641 |
+
"eval_f1_a": 0.44102564102564107,
|
1642 |
+
"eval_f1_m": 0.44650038170446327,
|
1643 |
+
"eval_loss": 0.7092187404632568,
|
1644 |
+
"eval_runtime": 12.6142,
|
1645 |
+
"eval_samples_per_second": 19.819,
|
1646 |
+
"eval_steps_per_second": 2.537,
|
1647 |
+
"step": 91
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.472,
|
1651 |
+
"grad_norm": 9.848048210144043,
|
1652 |
+
"learning_rate": 1.3114754098360657e-05,
|
1653 |
+
"loss": 0.689,
|
1654 |
+
"step": 92
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 1.472,
|
1658 |
+
"eval_exact_match": 0.04081632653061224,
|
1659 |
+
"eval_f1_a": 0.45263157894736844,
|
1660 |
+
"eval_f1_m": 0.4581459923296658,
|
1661 |
+
"eval_loss": 0.7082812786102295,
|
1662 |
+
"eval_runtime": 12.4011,
|
1663 |
+
"eval_samples_per_second": 20.159,
|
1664 |
+
"eval_steps_per_second": 2.58,
|
1665 |
+
"step": 92
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.488,
|
1669 |
+
"grad_norm": 17.459680557250977,
|
1670 |
+
"learning_rate": 1.2704918032786885e-05,
|
1671 |
+
"loss": 0.8424,
|
1672 |
+
"step": 93
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 1.488,
|
1676 |
+
"eval_exact_match": 0.04081632653061224,
|
1677 |
+
"eval_f1_a": 0.450261780104712,
|
1678 |
+
"eval_f1_m": 0.45620235773296997,
|
1679 |
+
"eval_loss": 0.7073437571525574,
|
1680 |
+
"eval_runtime": 12.4025,
|
1681 |
+
"eval_samples_per_second": 20.157,
|
1682 |
+
"eval_steps_per_second": 2.58,
|
1683 |
+
"step": 93
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.504,
|
1687 |
+
"grad_norm": 7.91733980178833,
|
1688 |
+
"learning_rate": 1.2295081967213116e-05,
|
1689 |
+
"loss": 0.6224,
|
1690 |
+
"step": 94
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.504,
|
1694 |
+
"eval_exact_match": 0.04081632653061224,
|
1695 |
+
"eval_f1_a": 0.4468085106382979,
|
1696 |
+
"eval_f1_m": 0.4566639709496852,
|
1697 |
+
"eval_loss": 0.7057031393051147,
|
1698 |
+
"eval_runtime": 12.4036,
|
1699 |
+
"eval_samples_per_second": 20.155,
|
1700 |
+
"eval_steps_per_second": 2.58,
|
1701 |
+
"step": 94
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.52,
|
1705 |
+
"grad_norm": 17.14729881286621,
|
1706 |
+
"learning_rate": 1.1885245901639344e-05,
|
1707 |
+
"loss": 0.5743,
|
1708 |
+
"step": 95
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.52,
|
1712 |
+
"eval_exact_match": 0.04081632653061224,
|
1713 |
+
"eval_f1_a": 0.4491978609625668,
|
1714 |
+
"eval_f1_m": 0.4579678258249688,
|
1715 |
+
"eval_loss": 0.7053046822547913,
|
1716 |
+
"eval_runtime": 12.4028,
|
1717 |
+
"eval_samples_per_second": 20.157,
|
1718 |
+
"eval_steps_per_second": 2.58,
|
1719 |
+
"step": 95
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.536,
|
1723 |
+
"grad_norm": 10.893065452575684,
|
1724 |
+
"learning_rate": 1.1475409836065575e-05,
|
1725 |
+
"loss": 0.7041,
|
1726 |
+
"step": 96
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.536,
|
1730 |
+
"eval_exact_match": 0.04081632653061224,
|
1731 |
+
"eval_f1_a": 0.44324324324324327,
|
1732 |
+
"eval_f1_m": 0.45810145070349156,
|
1733 |
+
"eval_loss": 0.7051210999488831,
|
1734 |
+
"eval_runtime": 12.3907,
|
1735 |
+
"eval_samples_per_second": 20.176,
|
1736 |
+
"eval_steps_per_second": 2.583,
|
1737 |
+
"step": 96
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.552,
|
1741 |
+
"grad_norm": 9.716265678405762,
|
1742 |
+
"learning_rate": 1.1065573770491803e-05,
|
1743 |
+
"loss": 0.6443,
|
1744 |
+
"step": 97
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 1.552,
|
1748 |
+
"eval_exact_match": 0.02040816326530612,
|
1749 |
+
"eval_f1_a": 0.4262295081967213,
|
1750 |
+
"eval_f1_m": 0.4496709356403233,
|
1751 |
+
"eval_loss": 0.7061210870742798,
|
1752 |
+
"eval_runtime": 12.2983,
|
1753 |
+
"eval_samples_per_second": 20.328,
|
1754 |
+
"eval_steps_per_second": 2.602,
|
1755 |
+
"step": 97
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 1.568,
|
1759 |
+
"grad_norm": 17.185867309570312,
|
1760 |
+
"learning_rate": 1.0655737704918032e-05,
|
1761 |
+
"loss": 0.6588,
|
1762 |
+
"step": 98
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.568,
|
1766 |
+
"eval_exact_match": 0.02040816326530612,
|
1767 |
+
"eval_f1_a": 0.430939226519337,
|
1768 |
+
"eval_f1_m": 0.4559391572146673,
|
1769 |
+
"eval_loss": 0.704464852809906,
|
1770 |
+
"eval_runtime": 12.4036,
|
1771 |
+
"eval_samples_per_second": 20.155,
|
1772 |
+
"eval_steps_per_second": 2.58,
|
1773 |
+
"step": 98
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.584,
|
1777 |
+
"grad_norm": 9.352198600769043,
|
1778 |
+
"learning_rate": 1.0245901639344262e-05,
|
1779 |
+
"loss": 0.6669,
|
1780 |
+
"step": 99
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.584,
|
1784 |
+
"eval_exact_match": 0.02040816326530612,
|
1785 |
+
"eval_f1_a": 0.41860465116279066,
|
1786 |
+
"eval_f1_m": 0.45876048721186774,
|
1787 |
+
"eval_loss": 0.7052500247955322,
|
1788 |
+
"eval_runtime": 12.2869,
|
1789 |
+
"eval_samples_per_second": 20.347,
|
1790 |
+
"eval_steps_per_second": 2.604,
|
1791 |
+
"step": 99
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.6,
|
1795 |
+
"grad_norm": 10.983183860778809,
|
1796 |
+
"learning_rate": 9.836065573770493e-06,
|
1797 |
+
"loss": 0.667,
|
1798 |
+
"step": 100
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 1.6,
|
1802 |
+
"eval_exact_match": 0.02040816326530612,
|
1803 |
+
"eval_f1_a": 0.3976608187134503,
|
1804 |
+
"eval_f1_m": 0.44378116214850916,
|
1805 |
+
"eval_loss": 0.7053242325782776,
|
1806 |
+
"eval_runtime": 12.292,
|
1807 |
+
"eval_samples_per_second": 20.338,
|
1808 |
+
"eval_steps_per_second": 2.603,
|
1809 |
+
"step": 100
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.616,
|
1813 |
+
"grad_norm": 8.352677345275879,
|
1814 |
+
"learning_rate": 9.426229508196721e-06,
|
1815 |
+
"loss": 0.6028,
|
1816 |
+
"step": 101
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.616,
|
1820 |
+
"eval_exact_match": 0.02040816326530612,
|
1821 |
+
"eval_f1_a": 0.3780487804878049,
|
1822 |
+
"eval_f1_m": 0.440360093421318,
|
1823 |
+
"eval_loss": 0.7049765586853027,
|
1824 |
+
"eval_runtime": 12.3969,
|
1825 |
+
"eval_samples_per_second": 20.166,
|
1826 |
+
"eval_steps_per_second": 2.581,
|
1827 |
+
"step": 101
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.6320000000000001,
|
1831 |
+
"grad_norm": 18.418481826782227,
|
1832 |
+
"learning_rate": 9.016393442622952e-06,
|
1833 |
+
"loss": 0.7084,
|
1834 |
+
"step": 102
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.6320000000000001,
|
1838 |
+
"eval_exact_match": 0.02040816326530612,
|
1839 |
+
"eval_f1_a": 0.3827160493827161,
|
1840 |
+
"eval_f1_m": 0.4446715982430268,
|
1841 |
+
"eval_loss": 0.7034218907356262,
|
1842 |
+
"eval_runtime": 12.3991,
|
1843 |
+
"eval_samples_per_second": 20.163,
|
1844 |
+
"eval_steps_per_second": 2.581,
|
1845 |
+
"step": 102
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.6480000000000001,
|
1849 |
+
"grad_norm": 10.633659362792969,
|
1850 |
+
"learning_rate": 8.60655737704918e-06,
|
1851 |
+
"loss": 0.6221,
|
1852 |
+
"step": 103
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 1.6480000000000001,
|
1856 |
+
"eval_exact_match": 0.02040816326530612,
|
1857 |
+
"eval_f1_a": 0.33766233766233766,
|
1858 |
+
"eval_f1_m": 0.42304736080246286,
|
1859 |
+
"eval_loss": 0.7042617201805115,
|
1860 |
+
"eval_runtime": 12.2954,
|
1861 |
+
"eval_samples_per_second": 20.333,
|
1862 |
+
"eval_steps_per_second": 2.603,
|
1863 |
+
"step": 103
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 1.6640000000000001,
|
1867 |
+
"grad_norm": 12.377849578857422,
|
1868 |
+
"learning_rate": 8.196721311475409e-06,
|
1869 |
+
"loss": 0.5413,
|
1870 |
+
"step": 104
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 1.6640000000000001,
|
1874 |
+
"eval_exact_match": 0.02040816326530612,
|
1875 |
+
"eval_f1_a": 0.3289473684210526,
|
1876 |
+
"eval_f1_m": 0.4253797223184978,
|
1877 |
+
"eval_loss": 0.7033711075782776,
|
1878 |
+
"eval_runtime": 12.3003,
|
1879 |
+
"eval_samples_per_second": 20.325,
|
1880 |
+
"eval_steps_per_second": 2.602,
|
1881 |
+
"step": 104
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 1.6800000000000002,
|
1885 |
+
"grad_norm": 12.551422119140625,
|
1886 |
+
"learning_rate": 7.78688524590164e-06,
|
1887 |
+
"loss": 0.682,
|
1888 |
+
"step": 105
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 1.6800000000000002,
|
1892 |
+
"eval_exact_match": 0.0,
|
1893 |
+
"eval_f1_a": 0.2953020134228188,
|
1894 |
+
"eval_f1_m": 0.4078515022392573,
|
1895 |
+
"eval_loss": 0.7049804925918579,
|
1896 |
+
"eval_runtime": 12.495,
|
1897 |
+
"eval_samples_per_second": 20.008,
|
1898 |
+
"eval_steps_per_second": 2.561,
|
1899 |
+
"step": 105
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.696,
|
1903 |
+
"grad_norm": 8.237449645996094,
|
1904 |
+
"learning_rate": 7.3770491803278695e-06,
|
1905 |
+
"loss": 0.7448,
|
1906 |
+
"step": 106
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.696,
|
1910 |
+
"eval_exact_match": 0.0,
|
1911 |
+
"eval_f1_a": 0.3013698630136986,
|
1912 |
+
"eval_f1_m": 0.41549131140967865,
|
1913 |
+
"eval_loss": 0.7063398361206055,
|
1914 |
+
"eval_runtime": 12.4967,
|
1915 |
+
"eval_samples_per_second": 20.005,
|
1916 |
+
"eval_steps_per_second": 2.561,
|
1917 |
+
"step": 106
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 1.712,
|
1921 |
+
"grad_norm": 7.336461067199707,
|
1922 |
+
"learning_rate": 6.967213114754098e-06,
|
1923 |
+
"loss": 0.4493,
|
1924 |
+
"step": 107
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.712,
|
1928 |
+
"eval_exact_match": 0.0,
|
1929 |
+
"eval_f1_a": 0.2553191489361702,
|
1930 |
+
"eval_f1_m": 0.4051889720257066,
|
1931 |
+
"eval_loss": 0.7075039148330688,
|
1932 |
+
"eval_runtime": 12.403,
|
1933 |
+
"eval_samples_per_second": 20.156,
|
1934 |
+
"eval_steps_per_second": 2.58,
|
1935 |
+
"step": 107
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.728,
|
1939 |
+
"grad_norm": 8.348127365112305,
|
1940 |
+
"learning_rate": 6.557377049180328e-06,
|
1941 |
+
"loss": 0.8977,
|
1942 |
+
"step": 108
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.728,
|
1946 |
+
"eval_exact_match": 0.0,
|
1947 |
+
"eval_f1_a": 0.2608695652173913,
|
1948 |
+
"eval_f1_m": 0.4141215926930211,
|
1949 |
+
"eval_loss": 0.7066875100135803,
|
1950 |
+
"eval_runtime": 12.3958,
|
1951 |
+
"eval_samples_per_second": 20.168,
|
1952 |
+
"eval_steps_per_second": 2.582,
|
1953 |
+
"step": 108
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 1.744,
|
1957 |
+
"grad_norm": 6.762801170349121,
|
1958 |
+
"learning_rate": 6.147540983606558e-06,
|
1959 |
+
"loss": 0.6888,
|
1960 |
+
"step": 109
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.744,
|
1964 |
+
"eval_exact_match": 0.0,
|
1965 |
+
"eval_f1_a": 0.23529411764705882,
|
1966 |
+
"eval_f1_m": 0.4052051689806791,
|
1967 |
+
"eval_loss": 0.7079609632492065,
|
1968 |
+
"eval_runtime": 12.2957,
|
1969 |
+
"eval_samples_per_second": 20.332,
|
1970 |
+
"eval_steps_per_second": 2.603,
|
1971 |
+
"step": 109
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 1.76,
|
1975 |
+
"grad_norm": 7.54478645324707,
|
1976 |
+
"learning_rate": 5.737704918032787e-06,
|
1977 |
+
"loss": 0.7079,
|
1978 |
+
"step": 110
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 1.76,
|
1982 |
+
"eval_exact_match": 0.0,
|
1983 |
+
"eval_f1_a": 0.196969696969697,
|
1984 |
+
"eval_f1_m": 0.3930353659945496,
|
1985 |
+
"eval_loss": 0.7083203196525574,
|
1986 |
+
"eval_runtime": 12.4001,
|
1987 |
+
"eval_samples_per_second": 20.161,
|
1988 |
+
"eval_steps_per_second": 2.581,
|
1989 |
+
"step": 110
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.776,
|
1993 |
+
"grad_norm": 6.84658145904541,
|
1994 |
+
"learning_rate": 5.327868852459016e-06,
|
1995 |
+
"loss": 0.6766,
|
1996 |
+
"step": 111
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 1.776,
|
2000 |
+
"eval_exact_match": 0.0,
|
2001 |
+
"eval_f1_a": 0.2105263157894737,
|
2002 |
+
"eval_f1_m": 0.39676157176157173,
|
2003 |
+
"eval_loss": 0.7091640830039978,
|
2004 |
+
"eval_runtime": 12.4008,
|
2005 |
+
"eval_samples_per_second": 20.16,
|
2006 |
+
"eval_steps_per_second": 2.58,
|
2007 |
+
"step": 111
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 1.792,
|
2011 |
+
"grad_norm": 16.06954002380371,
|
2012 |
+
"learning_rate": 4.918032786885246e-06,
|
2013 |
+
"loss": 0.6298,
|
2014 |
+
"step": 112
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 1.792,
|
2018 |
+
"eval_exact_match": 0.0,
|
2019 |
+
"eval_f1_a": 0.15748031496062992,
|
2020 |
+
"eval_f1_m": 0.37861616841208684,
|
2021 |
+
"eval_loss": 0.7095195055007935,
|
2022 |
+
"eval_runtime": 12.4951,
|
2023 |
+
"eval_samples_per_second": 20.008,
|
2024 |
+
"eval_steps_per_second": 2.561,
|
2025 |
+
"step": 112
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 1.808,
|
2029 |
+
"grad_norm": 5.902178764343262,
|
2030 |
+
"learning_rate": 4.508196721311476e-06,
|
2031 |
+
"loss": 0.5864,
|
2032 |
+
"step": 113
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 1.808,
|
2036 |
+
"eval_exact_match": 0.0,
|
2037 |
+
"eval_f1_a": 0.15873015873015875,
|
2038 |
+
"eval_f1_m": 0.38075416646845217,
|
2039 |
+
"eval_loss": 0.7111679911613464,
|
2040 |
+
"eval_runtime": 12.4019,
|
2041 |
+
"eval_samples_per_second": 20.158,
|
2042 |
+
"eval_steps_per_second": 2.58,
|
2043 |
+
"step": 113
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 1.8239999999999998,
|
2047 |
+
"grad_norm": 17.344051361083984,
|
2048 |
+
"learning_rate": 4.098360655737704e-06,
|
2049 |
+
"loss": 0.7265,
|
2050 |
+
"step": 114
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 1.8239999999999998,
|
2054 |
+
"eval_exact_match": 0.0,
|
2055 |
+
"eval_f1_a": 0.16,
|
2056 |
+
"eval_f1_m": 0.38211471068613934,
|
2057 |
+
"eval_loss": 0.7119726538658142,
|
2058 |
+
"eval_runtime": 12.3958,
|
2059 |
+
"eval_samples_per_second": 20.168,
|
2060 |
+
"eval_steps_per_second": 2.582,
|
2061 |
+
"step": 114
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.8399999999999999,
|
2065 |
+
"grad_norm": 13.185153007507324,
|
2066 |
+
"learning_rate": 3.6885245901639347e-06,
|
2067 |
+
"loss": 0.5856,
|
2068 |
+
"step": 115
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.8399999999999999,
|
2072 |
+
"eval_exact_match": 0.0,
|
2073 |
+
"eval_f1_a": 0.15873015873015875,
|
2074 |
+
"eval_f1_m": 0.37997671262977384,
|
2075 |
+
"eval_loss": 0.7116367220878601,
|
2076 |
+
"eval_runtime": 12.3902,
|
2077 |
+
"eval_samples_per_second": 20.177,
|
2078 |
+
"eval_steps_per_second": 2.583,
|
2079 |
+
"step": 115
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.8559999999999999,
|
2083 |
+
"grad_norm": 6.701231956481934,
|
2084 |
+
"learning_rate": 3.278688524590164e-06,
|
2085 |
+
"loss": 0.718,
|
2086 |
+
"step": 116
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 1.8559999999999999,
|
2090 |
+
"eval_exact_match": 0.0,
|
2091 |
+
"eval_f1_a": 0.09836065573770492,
|
2092 |
+
"eval_f1_m": 0.361842380975034,
|
2093 |
+
"eval_loss": 0.7136015892028809,
|
2094 |
+
"eval_runtime": 12.294,
|
2095 |
+
"eval_samples_per_second": 20.335,
|
2096 |
+
"eval_steps_per_second": 2.603,
|
2097 |
+
"step": 116
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 1.8719999999999999,
|
2101 |
+
"grad_norm": 11.730875015258789,
|
2102 |
+
"learning_rate": 2.8688524590163937e-06,
|
2103 |
+
"loss": 0.7096,
|
2104 |
+
"step": 117
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 1.8719999999999999,
|
2108 |
+
"eval_exact_match": 0.0,
|
2109 |
+
"eval_f1_a": 0.08333333333333334,
|
2110 |
+
"eval_f1_m": 0.35354549079038877,
|
2111 |
+
"eval_loss": 0.7125195264816284,
|
2112 |
+
"eval_runtime": 12.3992,
|
2113 |
+
"eval_samples_per_second": 20.163,
|
2114 |
+
"eval_steps_per_second": 2.581,
|
2115 |
+
"step": 117
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 1.888,
|
2119 |
+
"grad_norm": 11.764548301696777,
|
2120 |
+
"learning_rate": 2.459016393442623e-06,
|
2121 |
+
"loss": 0.7648,
|
2122 |
+
"step": 118
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.888,
|
2126 |
+
"eval_exact_match": 0.0,
|
2127 |
+
"eval_f1_a": 0.10169491525423728,
|
2128 |
+
"eval_f1_m": 0.36885033900340025,
|
2129 |
+
"eval_loss": 0.7145312428474426,
|
2130 |
+
"eval_runtime": 12.2937,
|
2131 |
+
"eval_samples_per_second": 20.336,
|
2132 |
+
"eval_steps_per_second": 2.603,
|
2133 |
+
"step": 118
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 1.904,
|
2137 |
+
"grad_norm": 7.357093334197998,
|
2138 |
+
"learning_rate": 2.049180327868852e-06,
|
2139 |
+
"loss": 0.66,
|
2140 |
+
"step": 119
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.904,
|
2144 |
+
"eval_exact_match": 0.0,
|
2145 |
+
"eval_f1_a": 0.08403361344537816,
|
2146 |
+
"eval_f1_m": 0.3581008843763946,
|
2147 |
+
"eval_loss": 0.7142617106437683,
|
2148 |
+
"eval_runtime": 12.2932,
|
2149 |
+
"eval_samples_per_second": 20.336,
|
2150 |
+
"eval_steps_per_second": 2.603,
|
2151 |
+
"step": 119
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.92,
|
2155 |
+
"grad_norm": 12.222306251525879,
|
2156 |
+
"learning_rate": 1.639344262295082e-06,
|
2157 |
+
"loss": 0.7134,
|
2158 |
+
"step": 120
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.92,
|
2162 |
+
"eval_exact_match": 0.0,
|
2163 |
+
"eval_f1_a": 0.08620689655172413,
|
2164 |
+
"eval_f1_m": 0.3664693866224478,
|
2165 |
+
"eval_loss": 0.7143398523330688,
|
2166 |
+
"eval_runtime": 12.4037,
|
2167 |
+
"eval_samples_per_second": 20.155,
|
2168 |
+
"eval_steps_per_second": 2.58,
|
2169 |
+
"step": 120
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 1.936,
|
2173 |
+
"grad_norm": 11.94378662109375,
|
2174 |
+
"learning_rate": 1.2295081967213116e-06,
|
2175 |
+
"loss": 0.6269,
|
2176 |
+
"step": 121
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.936,
|
2180 |
+
"eval_exact_match": 0.0,
|
2181 |
+
"eval_f1_a": 0.06837606837606838,
|
2182 |
+
"eval_f1_m": 0.35452724712928796,
|
2183 |
+
"eval_loss": 0.7161992192268372,
|
2184 |
+
"eval_runtime": 12.2894,
|
2185 |
+
"eval_samples_per_second": 20.343,
|
2186 |
+
"eval_steps_per_second": 2.604,
|
2187 |
+
"step": 121
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.952,
|
2191 |
+
"grad_norm": 10.898783683776855,
|
2192 |
+
"learning_rate": 8.19672131147541e-07,
|
2193 |
+
"loss": 0.6692,
|
2194 |
+
"step": 122
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.952,
|
2198 |
+
"eval_exact_match": 0.0,
|
2199 |
+
"eval_f1_a": 0.06779661016949154,
|
2200 |
+
"eval_f1_m": 0.35377437355228475,
|
2201 |
+
"eval_loss": 0.7155507802963257,
|
2202 |
+
"eval_runtime": 12.2897,
|
2203 |
+
"eval_samples_per_second": 20.342,
|
2204 |
+
"eval_steps_per_second": 2.604,
|
2205 |
+
"step": 122
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 1.968,
|
2209 |
+
"grad_norm": 11.34163761138916,
|
2210 |
+
"learning_rate": 4.098360655737705e-07,
|
2211 |
+
"loss": 0.7837,
|
2212 |
+
"step": 123
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 1.968,
|
2216 |
+
"eval_exact_match": 0.0,
|
2217 |
+
"eval_f1_a": 0.06837606837606838,
|
2218 |
+
"eval_f1_m": 0.3542995836363184,
|
2219 |
+
"eval_loss": 0.7164883017539978,
|
2220 |
+
"eval_runtime": 12.3974,
|
2221 |
+
"eval_samples_per_second": 20.166,
|
2222 |
+
"eval_steps_per_second": 2.581,
|
2223 |
+
"step": 123
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 1.984,
|
2227 |
+
"grad_norm": 9.480073928833008,
|
2228 |
+
"learning_rate": 0.0,
|
2229 |
+
"loss": 0.5815,
|
2230 |
+
"step": 124
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 1.984,
|
2234 |
+
"eval_exact_match": 0.0,
|
2235 |
+
"eval_f1_a": 0.053097345132743355,
|
2236 |
+
"eval_f1_m": 0.35416089179594584,
|
2237 |
+
"eval_loss": 0.7167656421661377,
|
2238 |
+
"eval_runtime": 12.2934,
|
2239 |
+
"eval_samples_per_second": 20.336,
|
2240 |
+
"eval_steps_per_second": 2.603,
|
2241 |
+
"step": 124
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 1.984,
|
2245 |
+
"step": 124,
|
2246 |
+
"total_flos": 107566092058624.0,
|
2247 |
+
"train_loss": 0.7248697588520665,
|
2248 |
+
"train_runtime": 2001.1585,
|
2249 |
+
"train_samples_per_second": 0.999,
|
2250 |
+
"train_steps_per_second": 0.062
|
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 |
+
"total_flos": 107566092058624.0,
|
2259 |
+
"train_batch_size": 2,
|
2260 |
+
"trial_name": null,
|
2261 |
+
"trial_params": null
|
2262 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5daa9d904db1c0d816f3e51f5e00ef720b45916ab080defd25795dfb5ee4107
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|