upload
Browse files- README.md +202 -3
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- qwen.tiktoken +0 -0
- special_tokens_map.json +3 -0
- tokenizer_config.json +14 -0
- trainer_state.json +2004 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen-7B-Chat-Int4
|
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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen-7B-Chat-Int4",
|
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": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_attn",
|
24 |
+
"w2",
|
25 |
+
"w1",
|
26 |
+
"c_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ae35d214bd16fb0d2dec40bf7ed31dfab98934e0cb6bd06da11cc5f51e05612
|
3 |
+
size 286302920
|
qwen.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<|endoftext|>"
|
3 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"auto_map": {
|
4 |
+
"AutoTokenizer": [
|
5 |
+
"Qwen/Qwen-7B-Chat-Int4--tokenization_qwen.QWenTokenizer",
|
6 |
+
null
|
7 |
+
]
|
8 |
+
},
|
9 |
+
"clean_up_tokenization_spaces": true,
|
10 |
+
"model_max_length": 512,
|
11 |
+
"pad_token": "<|endoftext|>",
|
12 |
+
"padding_side": "right",
|
13 |
+
"tokenizer_class": "QWenTokenizer"
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2004 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9946949602122017,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 282,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.007073386383731211,
|
13 |
+
"grad_norm": 0.4045802652835846,
|
14 |
+
"learning_rate": 0.0,
|
15 |
+
"loss": 2.592,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.014146772767462422,
|
20 |
+
"grad_norm": 0.4087854325771332,
|
21 |
+
"learning_rate": 0.00018927892607143717,
|
22 |
+
"loss": 2.3663,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.021220159151193633,
|
27 |
+
"grad_norm": 0.391991525888443,
|
28 |
+
"learning_rate": 0.0003,
|
29 |
+
"loss": 2.3427,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.028293545534924844,
|
34 |
+
"grad_norm": 0.47497037053108215,
|
35 |
+
"learning_rate": 0.0003,
|
36 |
+
"loss": 2.4095,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.03536693191865606,
|
41 |
+
"grad_norm": 0.3936399221420288,
|
42 |
+
"learning_rate": 0.0003,
|
43 |
+
"loss": 1.7048,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.042440318302387266,
|
48 |
+
"grad_norm": 0.6155605316162109,
|
49 |
+
"learning_rate": 0.0003,
|
50 |
+
"loss": 1.8204,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04951370468611848,
|
55 |
+
"grad_norm": 0.49080851674079895,
|
56 |
+
"learning_rate": 0.0003,
|
57 |
+
"loss": 1.4646,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.05658709106984969,
|
62 |
+
"grad_norm": 0.5759713053703308,
|
63 |
+
"learning_rate": 0.0003,
|
64 |
+
"loss": 1.4984,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0636604774535809,
|
69 |
+
"grad_norm": 0.5349287390708923,
|
70 |
+
"learning_rate": 0.0003,
|
71 |
+
"loss": 1.3691,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.07073386383731212,
|
76 |
+
"grad_norm": 0.3948557674884796,
|
77 |
+
"learning_rate": 0.0003,
|
78 |
+
"loss": 1.4401,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.07780725022104333,
|
83 |
+
"grad_norm": 0.37507522106170654,
|
84 |
+
"learning_rate": 0.0003,
|
85 |
+
"loss": 1.1852,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.08488063660477453,
|
90 |
+
"grad_norm": 0.32405033707618713,
|
91 |
+
"learning_rate": 0.0003,
|
92 |
+
"loss": 1.051,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.09195402298850575,
|
97 |
+
"grad_norm": 0.4525175392627716,
|
98 |
+
"learning_rate": 0.0003,
|
99 |
+
"loss": 1.2695,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.09902740937223696,
|
104 |
+
"grad_norm": 0.42692625522613525,
|
105 |
+
"learning_rate": 0.0003,
|
106 |
+
"loss": 1.1057,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.10610079575596817,
|
111 |
+
"grad_norm": 0.5049455761909485,
|
112 |
+
"learning_rate": 0.0003,
|
113 |
+
"loss": 1.6851,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.11317418213969938,
|
118 |
+
"grad_norm": 0.38740119338035583,
|
119 |
+
"learning_rate": 0.0003,
|
120 |
+
"loss": 1.2632,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.12024756852343059,
|
125 |
+
"grad_norm": 0.3729807138442993,
|
126 |
+
"learning_rate": 0.0003,
|
127 |
+
"loss": 1.2857,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.1273209549071618,
|
132 |
+
"grad_norm": 0.4548921287059784,
|
133 |
+
"learning_rate": 0.0003,
|
134 |
+
"loss": 1.2233,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.134394341290893,
|
139 |
+
"grad_norm": 0.4324336051940918,
|
140 |
+
"learning_rate": 0.0003,
|
141 |
+
"loss": 1.1058,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.14146772767462423,
|
146 |
+
"grad_norm": 0.5775079727172852,
|
147 |
+
"learning_rate": 0.0003,
|
148 |
+
"loss": 1.0475,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.14854111405835543,
|
153 |
+
"grad_norm": 0.40563157200813293,
|
154 |
+
"learning_rate": 0.0003,
|
155 |
+
"loss": 1.1364,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.15561450044208666,
|
160 |
+
"grad_norm": 0.4697245657444,
|
161 |
+
"learning_rate": 0.0003,
|
162 |
+
"loss": 1.3599,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.16268788682581786,
|
167 |
+
"grad_norm": 0.42879530787467957,
|
168 |
+
"learning_rate": 0.0003,
|
169 |
+
"loss": 1.1086,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.16976127320954906,
|
174 |
+
"grad_norm": 0.42367979884147644,
|
175 |
+
"learning_rate": 0.0003,
|
176 |
+
"loss": 0.9705,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.1768346595932803,
|
181 |
+
"grad_norm": 0.3987770080566406,
|
182 |
+
"learning_rate": 0.0003,
|
183 |
+
"loss": 1.0087,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.1839080459770115,
|
188 |
+
"grad_norm": 0.3194337487220764,
|
189 |
+
"learning_rate": 0.0003,
|
190 |
+
"loss": 0.8143,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.1909814323607427,
|
195 |
+
"grad_norm": 0.3626921474933624,
|
196 |
+
"learning_rate": 0.0003,
|
197 |
+
"loss": 0.9763,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.19805481874447392,
|
202 |
+
"grad_norm": 0.38496437668800354,
|
203 |
+
"learning_rate": 0.0003,
|
204 |
+
"loss": 0.6315,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.20512820512820512,
|
209 |
+
"grad_norm": 0.41984379291534424,
|
210 |
+
"learning_rate": 0.0003,
|
211 |
+
"loss": 1.0303,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.21220159151193635,
|
216 |
+
"grad_norm": 0.4012935161590576,
|
217 |
+
"learning_rate": 0.0003,
|
218 |
+
"loss": 0.9862,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.21927497789566755,
|
223 |
+
"grad_norm": 0.40578627586364746,
|
224 |
+
"learning_rate": 0.0003,
|
225 |
+
"loss": 1.0094,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.22634836427939875,
|
230 |
+
"grad_norm": 0.41153454780578613,
|
231 |
+
"learning_rate": 0.0003,
|
232 |
+
"loss": 0.966,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.23342175066312998,
|
237 |
+
"grad_norm": 0.3835723400115967,
|
238 |
+
"learning_rate": 0.0003,
|
239 |
+
"loss": 0.5704,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.24049513704686118,
|
244 |
+
"grad_norm": 0.4588032066822052,
|
245 |
+
"learning_rate": 0.0003,
|
246 |
+
"loss": 0.8564,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.2475685234305924,
|
251 |
+
"grad_norm": 0.42644572257995605,
|
252 |
+
"learning_rate": 0.0003,
|
253 |
+
"loss": 0.8448,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.2546419098143236,
|
258 |
+
"grad_norm": 0.44491246342658997,
|
259 |
+
"learning_rate": 0.0003,
|
260 |
+
"loss": 1.1484,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.26171529619805484,
|
265 |
+
"grad_norm": 0.44271302223205566,
|
266 |
+
"learning_rate": 0.0003,
|
267 |
+
"loss": 0.7746,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.268788682581786,
|
272 |
+
"grad_norm": 0.4080619215965271,
|
273 |
+
"learning_rate": 0.0003,
|
274 |
+
"loss": 0.5377,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.27586206896551724,
|
279 |
+
"grad_norm": 0.3697488605976105,
|
280 |
+
"learning_rate": 0.0003,
|
281 |
+
"loss": 0.9936,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.28293545534924847,
|
286 |
+
"grad_norm": 0.37987953424453735,
|
287 |
+
"learning_rate": 0.0003,
|
288 |
+
"loss": 0.7066,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.29000884173297964,
|
293 |
+
"grad_norm": 0.5652127861976624,
|
294 |
+
"learning_rate": 0.0003,
|
295 |
+
"loss": 0.8813,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.29708222811671087,
|
300 |
+
"grad_norm": 0.45179855823516846,
|
301 |
+
"learning_rate": 0.0003,
|
302 |
+
"loss": 0.6442,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.3041556145004421,
|
307 |
+
"grad_norm": 0.40251022577285767,
|
308 |
+
"learning_rate": 0.0003,
|
309 |
+
"loss": 0.6876,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.3112290008841733,
|
314 |
+
"grad_norm": 0.3425946831703186,
|
315 |
+
"learning_rate": 0.0003,
|
316 |
+
"loss": 0.4759,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.3183023872679045,
|
321 |
+
"grad_norm": 0.3156929016113281,
|
322 |
+
"learning_rate": 0.0003,
|
323 |
+
"loss": 0.5237,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.3253757736516357,
|
328 |
+
"grad_norm": 0.5097647309303284,
|
329 |
+
"learning_rate": 0.0003,
|
330 |
+
"loss": 1.0965,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.33244916003536695,
|
335 |
+
"grad_norm": 0.4245418906211853,
|
336 |
+
"learning_rate": 0.0003,
|
337 |
+
"loss": 0.717,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.3395225464190981,
|
342 |
+
"grad_norm": 0.36271074414253235,
|
343 |
+
"learning_rate": 0.0003,
|
344 |
+
"loss": 0.925,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.34659593280282935,
|
349 |
+
"grad_norm": 0.3543199300765991,
|
350 |
+
"learning_rate": 0.0003,
|
351 |
+
"loss": 0.52,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.3536693191865606,
|
356 |
+
"grad_norm": 0.4760311245918274,
|
357 |
+
"learning_rate": 0.0003,
|
358 |
+
"loss": 0.6514,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.36074270557029176,
|
363 |
+
"grad_norm": 0.36290043592453003,
|
364 |
+
"learning_rate": 0.0003,
|
365 |
+
"loss": 0.6391,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.367816091954023,
|
370 |
+
"grad_norm": 0.4390805959701538,
|
371 |
+
"learning_rate": 0.0003,
|
372 |
+
"loss": 0.7822,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.3748894783377542,
|
377 |
+
"grad_norm": 0.402041494846344,
|
378 |
+
"learning_rate": 0.0003,
|
379 |
+
"loss": 0.5967,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.3819628647214854,
|
384 |
+
"grad_norm": 0.42580777406692505,
|
385 |
+
"learning_rate": 0.0003,
|
386 |
+
"loss": 0.7591,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.3890362511052166,
|
391 |
+
"grad_norm": 0.4342993199825287,
|
392 |
+
"learning_rate": 0.0003,
|
393 |
+
"loss": 0.9428,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.39610963748894784,
|
398 |
+
"grad_norm": 0.42949816584587097,
|
399 |
+
"learning_rate": 0.0003,
|
400 |
+
"loss": 0.6546,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.40318302387267907,
|
405 |
+
"grad_norm": 0.44655221700668335,
|
406 |
+
"learning_rate": 0.0003,
|
407 |
+
"loss": 0.6999,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.41025641025641024,
|
412 |
+
"grad_norm": 0.38236895203590393,
|
413 |
+
"learning_rate": 0.0003,
|
414 |
+
"loss": 0.5464,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.41732979664014147,
|
419 |
+
"grad_norm": 0.39055347442626953,
|
420 |
+
"learning_rate": 0.0003,
|
421 |
+
"loss": 0.8726,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.4244031830238727,
|
426 |
+
"grad_norm": 0.47743409872055054,
|
427 |
+
"learning_rate": 0.0003,
|
428 |
+
"loss": 0.6839,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.43147656940760387,
|
433 |
+
"grad_norm": 0.5571391582489014,
|
434 |
+
"learning_rate": 0.0003,
|
435 |
+
"loss": 0.6384,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.4385499557913351,
|
440 |
+
"grad_norm": 0.4612606465816498,
|
441 |
+
"learning_rate": 0.0003,
|
442 |
+
"loss": 0.8187,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.44562334217506633,
|
447 |
+
"grad_norm": 0.3999072313308716,
|
448 |
+
"learning_rate": 0.0003,
|
449 |
+
"loss": 0.6792,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.4526967285587975,
|
454 |
+
"grad_norm": 0.4889736771583557,
|
455 |
+
"learning_rate": 0.0003,
|
456 |
+
"loss": 0.7837,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.45977011494252873,
|
461 |
+
"grad_norm": 0.4411163628101349,
|
462 |
+
"learning_rate": 0.0003,
|
463 |
+
"loss": 0.7325,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.46684350132625996,
|
468 |
+
"grad_norm": 0.4137038588523865,
|
469 |
+
"learning_rate": 0.0003,
|
470 |
+
"loss": 0.5974,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.4739168877099912,
|
475 |
+
"grad_norm": 0.4226423501968384,
|
476 |
+
"learning_rate": 0.0003,
|
477 |
+
"loss": 0.6251,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.48099027409372236,
|
482 |
+
"grad_norm": 0.4461803734302521,
|
483 |
+
"learning_rate": 0.0003,
|
484 |
+
"loss": 0.5721,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.4880636604774536,
|
489 |
+
"grad_norm": 0.4135233461856842,
|
490 |
+
"learning_rate": 0.0003,
|
491 |
+
"loss": 0.708,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.4951370468611848,
|
496 |
+
"grad_norm": 0.40338656306266785,
|
497 |
+
"learning_rate": 0.0003,
|
498 |
+
"loss": 0.6943,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.502210433244916,
|
503 |
+
"grad_norm": 0.47266095876693726,
|
504 |
+
"learning_rate": 0.0003,
|
505 |
+
"loss": 0.6883,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.5092838196286472,
|
510 |
+
"grad_norm": 0.45008358359336853,
|
511 |
+
"learning_rate": 0.0003,
|
512 |
+
"loss": 0.6347,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.5163572060123784,
|
517 |
+
"grad_norm": 0.36589792370796204,
|
518 |
+
"learning_rate": 0.0003,
|
519 |
+
"loss": 0.746,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.5234305923961097,
|
524 |
+
"grad_norm": 0.36300450563430786,
|
525 |
+
"learning_rate": 0.0003,
|
526 |
+
"loss": 0.7846,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.5305039787798409,
|
531 |
+
"grad_norm": 0.42305129766464233,
|
532 |
+
"learning_rate": 0.0003,
|
533 |
+
"loss": 0.7909,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.537577365163572,
|
538 |
+
"grad_norm": 0.36807361245155334,
|
539 |
+
"learning_rate": 0.0003,
|
540 |
+
"loss": 0.578,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.5446507515473032,
|
545 |
+
"grad_norm": 0.3479249179363251,
|
546 |
+
"learning_rate": 0.0003,
|
547 |
+
"loss": 0.4358,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.5517241379310345,
|
552 |
+
"grad_norm": 0.4373302161693573,
|
553 |
+
"learning_rate": 0.0003,
|
554 |
+
"loss": 0.8263,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.5587975243147657,
|
559 |
+
"grad_norm": 0.5427613854408264,
|
560 |
+
"learning_rate": 0.0003,
|
561 |
+
"loss": 0.7728,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.5658709106984969,
|
566 |
+
"grad_norm": 0.4510067403316498,
|
567 |
+
"learning_rate": 0.0003,
|
568 |
+
"loss": 0.7188,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.5729442970822282,
|
573 |
+
"grad_norm": 0.3964546322822571,
|
574 |
+
"learning_rate": 0.0003,
|
575 |
+
"loss": 0.6707,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.5800176834659593,
|
580 |
+
"grad_norm": 0.40177956223487854,
|
581 |
+
"learning_rate": 0.0003,
|
582 |
+
"loss": 0.7056,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.5870910698496905,
|
587 |
+
"grad_norm": 0.4081084728240967,
|
588 |
+
"learning_rate": 0.0003,
|
589 |
+
"loss": 0.6588,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.5941644562334217,
|
594 |
+
"grad_norm": 0.3595137298107147,
|
595 |
+
"learning_rate": 0.0003,
|
596 |
+
"loss": 0.6469,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.601237842617153,
|
601 |
+
"grad_norm": 0.40407031774520874,
|
602 |
+
"learning_rate": 0.0003,
|
603 |
+
"loss": 0.6954,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.6083112290008842,
|
608 |
+
"grad_norm": 0.47531482577323914,
|
609 |
+
"learning_rate": 0.0003,
|
610 |
+
"loss": 0.5842,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.6153846153846154,
|
615 |
+
"grad_norm": 0.3669019639492035,
|
616 |
+
"learning_rate": 0.0003,
|
617 |
+
"loss": 0.6278,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.6224580017683466,
|
622 |
+
"grad_norm": 0.3638778030872345,
|
623 |
+
"learning_rate": 0.0003,
|
624 |
+
"loss": 0.4731,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.6295313881520778,
|
629 |
+
"grad_norm": 0.39883217215538025,
|
630 |
+
"learning_rate": 0.0003,
|
631 |
+
"loss": 0.6891,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.636604774535809,
|
636 |
+
"grad_norm": 0.627139687538147,
|
637 |
+
"learning_rate": 0.0003,
|
638 |
+
"loss": 0.58,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.6436781609195402,
|
643 |
+
"grad_norm": 0.5339258313179016,
|
644 |
+
"learning_rate": 0.0003,
|
645 |
+
"loss": 0.6198,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.6507515473032714,
|
650 |
+
"grad_norm": 0.4699147939682007,
|
651 |
+
"learning_rate": 0.0003,
|
652 |
+
"loss": 0.7175,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.6578249336870027,
|
657 |
+
"grad_norm": 0.3144320249557495,
|
658 |
+
"learning_rate": 0.0003,
|
659 |
+
"loss": 0.4438,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.6648983200707339,
|
664 |
+
"grad_norm": 0.47343114018440247,
|
665 |
+
"learning_rate": 0.0003,
|
666 |
+
"loss": 0.7511,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.671971706454465,
|
671 |
+
"grad_norm": 0.43690529465675354,
|
672 |
+
"learning_rate": 0.0003,
|
673 |
+
"loss": 0.4847,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.6790450928381963,
|
678 |
+
"grad_norm": 0.5092759728431702,
|
679 |
+
"learning_rate": 0.0003,
|
680 |
+
"loss": 0.6703,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.6861184792219275,
|
685 |
+
"grad_norm": 0.7045844793319702,
|
686 |
+
"learning_rate": 0.0003,
|
687 |
+
"loss": 0.717,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.6931918656056587,
|
692 |
+
"grad_norm": 0.34709087014198303,
|
693 |
+
"learning_rate": 0.0003,
|
694 |
+
"loss": 0.5597,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.7002652519893899,
|
699 |
+
"grad_norm": 0.39407986402511597,
|
700 |
+
"learning_rate": 0.0003,
|
701 |
+
"loss": 0.5079,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.7073386383731212,
|
706 |
+
"grad_norm": 0.6836314797401428,
|
707 |
+
"learning_rate": 0.0003,
|
708 |
+
"loss": 0.5947,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.7144120247568524,
|
713 |
+
"grad_norm": 0.4487530291080475,
|
714 |
+
"learning_rate": 0.0003,
|
715 |
+
"loss": 0.5638,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.7214854111405835,
|
720 |
+
"grad_norm": 0.34299322962760925,
|
721 |
+
"learning_rate": 0.0003,
|
722 |
+
"loss": 0.4268,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.7285587975243147,
|
727 |
+
"grad_norm": 0.4325425624847412,
|
728 |
+
"learning_rate": 0.0003,
|
729 |
+
"loss": 0.7195,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.735632183908046,
|
734 |
+
"grad_norm": 0.3857167959213257,
|
735 |
+
"learning_rate": 0.0003,
|
736 |
+
"loss": 0.5525,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.7427055702917772,
|
741 |
+
"grad_norm": 0.5439281463623047,
|
742 |
+
"learning_rate": 0.0003,
|
743 |
+
"loss": 0.8488,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.7497789566755084,
|
748 |
+
"grad_norm": 0.5054299831390381,
|
749 |
+
"learning_rate": 0.0003,
|
750 |
+
"loss": 0.5801,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.7568523430592397,
|
755 |
+
"grad_norm": 0.5152317881584167,
|
756 |
+
"learning_rate": 0.0003,
|
757 |
+
"loss": 0.6918,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.7639257294429708,
|
762 |
+
"grad_norm": 0.32669249176979065,
|
763 |
+
"learning_rate": 0.0003,
|
764 |
+
"loss": 0.5322,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.770999115826702,
|
769 |
+
"grad_norm": 0.4302417039871216,
|
770 |
+
"learning_rate": 0.0003,
|
771 |
+
"loss": 0.6439,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.7780725022104332,
|
776 |
+
"grad_norm": 0.4388223886489868,
|
777 |
+
"learning_rate": 0.0003,
|
778 |
+
"loss": 0.6196,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.7851458885941645,
|
783 |
+
"grad_norm": 0.42924442887306213,
|
784 |
+
"learning_rate": 0.0003,
|
785 |
+
"loss": 0.5175,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.7922192749778957,
|
790 |
+
"grad_norm": 0.4361798167228699,
|
791 |
+
"learning_rate": 0.0003,
|
792 |
+
"loss": 0.5342,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.7992926613616269,
|
797 |
+
"grad_norm": 0.4133489429950714,
|
798 |
+
"learning_rate": 0.0003,
|
799 |
+
"loss": 0.5639,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.8063660477453581,
|
804 |
+
"grad_norm": 0.34224194288253784,
|
805 |
+
"learning_rate": 0.0003,
|
806 |
+
"loss": 0.4695,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.8134394341290893,
|
811 |
+
"grad_norm": 0.4219891428947449,
|
812 |
+
"learning_rate": 0.0003,
|
813 |
+
"loss": 0.6307,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.8205128205128205,
|
818 |
+
"grad_norm": 0.44273802638053894,
|
819 |
+
"learning_rate": 0.0003,
|
820 |
+
"loss": 0.5475,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.8275862068965517,
|
825 |
+
"grad_norm": 0.42054426670074463,
|
826 |
+
"learning_rate": 0.0003,
|
827 |
+
"loss": 0.827,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.8346595932802829,
|
832 |
+
"grad_norm": 0.4792965054512024,
|
833 |
+
"learning_rate": 0.0003,
|
834 |
+
"loss": 0.6,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.8417329796640142,
|
839 |
+
"grad_norm": 0.5182773470878601,
|
840 |
+
"learning_rate": 0.0003,
|
841 |
+
"loss": 0.8832,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.8488063660477454,
|
846 |
+
"grad_norm": 0.41087284684181213,
|
847 |
+
"learning_rate": 0.0003,
|
848 |
+
"loss": 0.5825,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.8558797524314765,
|
853 |
+
"grad_norm": 0.36328765749931335,
|
854 |
+
"learning_rate": 0.0003,
|
855 |
+
"loss": 0.4198,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.8629531388152077,
|
860 |
+
"grad_norm": 0.43922775983810425,
|
861 |
+
"learning_rate": 0.0003,
|
862 |
+
"loss": 0.5495,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.870026525198939,
|
867 |
+
"grad_norm": 0.5079771876335144,
|
868 |
+
"learning_rate": 0.0003,
|
869 |
+
"loss": 0.6814,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.8770999115826702,
|
874 |
+
"grad_norm": 0.3167728781700134,
|
875 |
+
"learning_rate": 0.0003,
|
876 |
+
"loss": 0.5706,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.8841732979664014,
|
881 |
+
"grad_norm": 0.45660603046417236,
|
882 |
+
"learning_rate": 0.0003,
|
883 |
+
"loss": 0.7102,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.8912466843501327,
|
888 |
+
"grad_norm": 0.42243629693984985,
|
889 |
+
"learning_rate": 0.0003,
|
890 |
+
"loss": 0.5449,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.8983200707338639,
|
895 |
+
"grad_norm": 0.32169416546821594,
|
896 |
+
"learning_rate": 0.0003,
|
897 |
+
"loss": 0.3933,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.905393457117595,
|
902 |
+
"grad_norm": 0.32228872179985046,
|
903 |
+
"learning_rate": 0.0003,
|
904 |
+
"loss": 0.6444,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.9124668435013262,
|
909 |
+
"grad_norm": 0.47969621419906616,
|
910 |
+
"learning_rate": 0.0003,
|
911 |
+
"loss": 0.7959,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.9195402298850575,
|
916 |
+
"grad_norm": 0.35543474555015564,
|
917 |
+
"learning_rate": 0.0003,
|
918 |
+
"loss": 0.6535,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.9266136162687887,
|
923 |
+
"grad_norm": 0.4273511469364166,
|
924 |
+
"learning_rate": 0.0003,
|
925 |
+
"loss": 0.6058,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.9336870026525199,
|
930 |
+
"grad_norm": 0.3400624692440033,
|
931 |
+
"learning_rate": 0.0003,
|
932 |
+
"loss": 0.6066,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.9407603890362511,
|
937 |
+
"grad_norm": 0.3195785582065582,
|
938 |
+
"learning_rate": 0.0003,
|
939 |
+
"loss": 0.5878,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.9478337754199824,
|
944 |
+
"grad_norm": 0.34657567739486694,
|
945 |
+
"learning_rate": 0.0003,
|
946 |
+
"loss": 0.6462,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.9549071618037135,
|
951 |
+
"grad_norm": 0.4706454873085022,
|
952 |
+
"learning_rate": 0.0003,
|
953 |
+
"loss": 0.8299,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.9619805481874447,
|
958 |
+
"grad_norm": 0.41353291273117065,
|
959 |
+
"learning_rate": 0.0003,
|
960 |
+
"loss": 0.6372,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.969053934571176,
|
965 |
+
"grad_norm": 0.34282562136650085,
|
966 |
+
"learning_rate": 0.0003,
|
967 |
+
"loss": 0.5901,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.9761273209549072,
|
972 |
+
"grad_norm": 0.4154914617538452,
|
973 |
+
"learning_rate": 0.0003,
|
974 |
+
"loss": 0.6213,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.9832007073386384,
|
979 |
+
"grad_norm": 0.2933409810066223,
|
980 |
+
"learning_rate": 0.0003,
|
981 |
+
"loss": 0.4435,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.9902740937223696,
|
986 |
+
"grad_norm": 0.3763149082660675,
|
987 |
+
"learning_rate": 0.0003,
|
988 |
+
"loss": 0.4754,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.9973474801061007,
|
993 |
+
"grad_norm": 0.4369047284126282,
|
994 |
+
"learning_rate": 0.0003,
|
995 |
+
"loss": 0.6313,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 1.004420866489832,
|
1000 |
+
"grad_norm": 0.40332600474357605,
|
1001 |
+
"learning_rate": 0.0003,
|
1002 |
+
"loss": 0.4778,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 1.0114942528735633,
|
1007 |
+
"grad_norm": 0.31336432695388794,
|
1008 |
+
"learning_rate": 0.0003,
|
1009 |
+
"loss": 0.4599,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.0185676392572944,
|
1014 |
+
"grad_norm": 0.3116231858730316,
|
1015 |
+
"learning_rate": 0.0003,
|
1016 |
+
"loss": 0.3823,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.0256410256410255,
|
1021 |
+
"grad_norm": 0.47887638211250305,
|
1022 |
+
"learning_rate": 0.0003,
|
1023 |
+
"loss": 0.4838,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 1.032714412024757,
|
1028 |
+
"grad_norm": 0.3979848325252533,
|
1029 |
+
"learning_rate": 0.0003,
|
1030 |
+
"loss": 0.3765,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.039787798408488,
|
1035 |
+
"grad_norm": 0.3911687433719635,
|
1036 |
+
"learning_rate": 0.0003,
|
1037 |
+
"loss": 0.379,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 1.0468611847922193,
|
1042 |
+
"grad_norm": 0.41035008430480957,
|
1043 |
+
"learning_rate": 0.0003,
|
1044 |
+
"loss": 0.4544,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 1.0539345711759505,
|
1049 |
+
"grad_norm": 0.3448046147823334,
|
1050 |
+
"learning_rate": 0.0003,
|
1051 |
+
"loss": 0.3809,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.0610079575596818,
|
1056 |
+
"grad_norm": 0.3258429765701294,
|
1057 |
+
"learning_rate": 0.0003,
|
1058 |
+
"loss": 0.3027,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.068081343943413,
|
1063 |
+
"grad_norm": 0.4393693208694458,
|
1064 |
+
"learning_rate": 0.0003,
|
1065 |
+
"loss": 0.4825,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 1.075154730327144,
|
1070 |
+
"grad_norm": 0.29749980568885803,
|
1071 |
+
"learning_rate": 0.0003,
|
1072 |
+
"loss": 0.2696,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.0822281167108754,
|
1077 |
+
"grad_norm": 0.3464600741863251,
|
1078 |
+
"learning_rate": 0.0003,
|
1079 |
+
"loss": 0.2812,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.0893015030946065,
|
1084 |
+
"grad_norm": 0.3517362177371979,
|
1085 |
+
"learning_rate": 0.0003,
|
1086 |
+
"loss": 0.4352,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.0963748894783378,
|
1091 |
+
"grad_norm": 0.3475998640060425,
|
1092 |
+
"learning_rate": 0.0003,
|
1093 |
+
"loss": 0.3298,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.103448275862069,
|
1098 |
+
"grad_norm": 0.41514718532562256,
|
1099 |
+
"learning_rate": 0.0003,
|
1100 |
+
"loss": 0.2779,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.1105216622458003,
|
1105 |
+
"grad_norm": 0.38064250349998474,
|
1106 |
+
"learning_rate": 0.0003,
|
1107 |
+
"loss": 0.3552,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 1.1175950486295314,
|
1112 |
+
"grad_norm": 0.48406025767326355,
|
1113 |
+
"learning_rate": 0.0003,
|
1114 |
+
"loss": 0.4691,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.1246684350132625,
|
1119 |
+
"grad_norm": 0.3856564462184906,
|
1120 |
+
"learning_rate": 0.0003,
|
1121 |
+
"loss": 0.3817,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.1317418213969939,
|
1126 |
+
"grad_norm": 0.40879660844802856,
|
1127 |
+
"learning_rate": 0.0003,
|
1128 |
+
"loss": 0.3555,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.138815207780725,
|
1133 |
+
"grad_norm": 0.4073532223701477,
|
1134 |
+
"learning_rate": 0.0003,
|
1135 |
+
"loss": 0.3218,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.1458885941644563,
|
1140 |
+
"grad_norm": 0.5433499217033386,
|
1141 |
+
"learning_rate": 0.0003,
|
1142 |
+
"loss": 0.4749,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.1529619805481874,
|
1147 |
+
"grad_norm": 0.47047749161720276,
|
1148 |
+
"learning_rate": 0.0003,
|
1149 |
+
"loss": 0.3945,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.1600353669319188,
|
1154 |
+
"grad_norm": 0.3000759184360504,
|
1155 |
+
"learning_rate": 0.0003,
|
1156 |
+
"loss": 0.3944,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.16710875331565,
|
1161 |
+
"grad_norm": 0.38655105233192444,
|
1162 |
+
"learning_rate": 0.0003,
|
1163 |
+
"loss": 0.458,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.174182139699381,
|
1168 |
+
"grad_norm": 0.3441111743450165,
|
1169 |
+
"learning_rate": 0.0003,
|
1170 |
+
"loss": 0.3388,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.1812555260831124,
|
1175 |
+
"grad_norm": 0.5380314588546753,
|
1176 |
+
"learning_rate": 0.0003,
|
1177 |
+
"loss": 0.5506,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.1883289124668435,
|
1182 |
+
"grad_norm": 0.2528212070465088,
|
1183 |
+
"learning_rate": 0.0003,
|
1184 |
+
"loss": 0.3144,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.1954022988505748,
|
1189 |
+
"grad_norm": 0.3783420920372009,
|
1190 |
+
"learning_rate": 0.0003,
|
1191 |
+
"loss": 0.5596,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 1.202475685234306,
|
1196 |
+
"grad_norm": 0.3812076449394226,
|
1197 |
+
"learning_rate": 0.0003,
|
1198 |
+
"loss": 0.42,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 1.209549071618037,
|
1203 |
+
"grad_norm": 0.43172749876976013,
|
1204 |
+
"learning_rate": 0.0003,
|
1205 |
+
"loss": 0.4931,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 1.2166224580017684,
|
1210 |
+
"grad_norm": 0.41426223516464233,
|
1211 |
+
"learning_rate": 0.0003,
|
1212 |
+
"loss": 0.2998,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.2236958443854995,
|
1217 |
+
"grad_norm": 0.35829058289527893,
|
1218 |
+
"learning_rate": 0.0003,
|
1219 |
+
"loss": 0.4243,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.2307692307692308,
|
1224 |
+
"grad_norm": 0.4014543294906616,
|
1225 |
+
"learning_rate": 0.0003,
|
1226 |
+
"loss": 0.3049,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.237842617152962,
|
1231 |
+
"grad_norm": 0.3007238507270813,
|
1232 |
+
"learning_rate": 0.0003,
|
1233 |
+
"loss": 0.2005,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.244916003536693,
|
1238 |
+
"grad_norm": 0.3595844507217407,
|
1239 |
+
"learning_rate": 0.0003,
|
1240 |
+
"loss": 0.344,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.2519893899204244,
|
1245 |
+
"grad_norm": 0.34730204939842224,
|
1246 |
+
"learning_rate": 0.0003,
|
1247 |
+
"loss": 0.2573,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.2590627763041558,
|
1252 |
+
"grad_norm": 0.39390042424201965,
|
1253 |
+
"learning_rate": 0.0003,
|
1254 |
+
"loss": 0.3177,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.2661361626878869,
|
1259 |
+
"grad_norm": 0.41631364822387695,
|
1260 |
+
"learning_rate": 0.0003,
|
1261 |
+
"loss": 0.4541,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.273209549071618,
|
1266 |
+
"grad_norm": 0.4117166996002197,
|
1267 |
+
"learning_rate": 0.0003,
|
1268 |
+
"loss": 0.4597,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.2802829354553493,
|
1273 |
+
"grad_norm": 0.46357792615890503,
|
1274 |
+
"learning_rate": 0.0003,
|
1275 |
+
"loss": 0.3166,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.2873563218390804,
|
1280 |
+
"grad_norm": 0.31492120027542114,
|
1281 |
+
"learning_rate": 0.0003,
|
1282 |
+
"loss": 0.2183,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.2944297082228116,
|
1287 |
+
"grad_norm": 0.31738027930259705,
|
1288 |
+
"learning_rate": 0.0003,
|
1289 |
+
"loss": 0.3114,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 1.301503094606543,
|
1294 |
+
"grad_norm": 0.37768757343292236,
|
1295 |
+
"learning_rate": 0.0003,
|
1296 |
+
"loss": 0.2977,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 1.308576480990274,
|
1301 |
+
"grad_norm": 0.45224347710609436,
|
1302 |
+
"learning_rate": 0.0003,
|
1303 |
+
"loss": 0.3788,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 1.3156498673740054,
|
1308 |
+
"grad_norm": 0.42707428336143494,
|
1309 |
+
"learning_rate": 0.0003,
|
1310 |
+
"loss": 0.3065,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.3227232537577365,
|
1315 |
+
"grad_norm": 0.359110027551651,
|
1316 |
+
"learning_rate": 0.0003,
|
1317 |
+
"loss": 0.3916,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 1.3297966401414678,
|
1322 |
+
"grad_norm": 0.4212663173675537,
|
1323 |
+
"learning_rate": 0.0003,
|
1324 |
+
"loss": 0.592,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 1.336870026525199,
|
1329 |
+
"grad_norm": 0.4227355122566223,
|
1330 |
+
"learning_rate": 0.0003,
|
1331 |
+
"loss": 0.4278,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 1.34394341290893,
|
1336 |
+
"grad_norm": 0.45795100927352905,
|
1337 |
+
"learning_rate": 0.0003,
|
1338 |
+
"loss": 0.4068,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 1.3510167992926614,
|
1343 |
+
"grad_norm": 0.47883355617523193,
|
1344 |
+
"learning_rate": 0.0003,
|
1345 |
+
"loss": 0.5285,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 1.3580901856763925,
|
1350 |
+
"grad_norm": 0.36151745915412903,
|
1351 |
+
"learning_rate": 0.0003,
|
1352 |
+
"loss": 0.365,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.3651635720601238,
|
1357 |
+
"grad_norm": 0.38841187953948975,
|
1358 |
+
"learning_rate": 0.0003,
|
1359 |
+
"loss": 0.4783,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 1.372236958443855,
|
1364 |
+
"grad_norm": 0.3572918772697449,
|
1365 |
+
"learning_rate": 0.0003,
|
1366 |
+
"loss": 0.4407,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 1.3793103448275863,
|
1371 |
+
"grad_norm": 0.36447620391845703,
|
1372 |
+
"learning_rate": 0.0003,
|
1373 |
+
"loss": 0.3111,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.3863837312113174,
|
1378 |
+
"grad_norm": 0.31043165922164917,
|
1379 |
+
"learning_rate": 0.0003,
|
1380 |
+
"loss": 0.3809,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 1.3934571175950485,
|
1385 |
+
"grad_norm": 0.4331524670124054,
|
1386 |
+
"learning_rate": 0.0003,
|
1387 |
+
"loss": 0.3464,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 1.4005305039787799,
|
1392 |
+
"grad_norm": 0.5187276005744934,
|
1393 |
+
"learning_rate": 0.0003,
|
1394 |
+
"loss": 0.4041,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.407603890362511,
|
1399 |
+
"grad_norm": 0.3016161322593689,
|
1400 |
+
"learning_rate": 0.0003,
|
1401 |
+
"loss": 0.1315,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 1.4146772767462423,
|
1406 |
+
"grad_norm": 0.3778589069843292,
|
1407 |
+
"learning_rate": 0.0003,
|
1408 |
+
"loss": 0.2563,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.4217506631299734,
|
1413 |
+
"grad_norm": 0.4542739987373352,
|
1414 |
+
"learning_rate": 0.0003,
|
1415 |
+
"loss": 0.3676,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 1.4288240495137048,
|
1420 |
+
"grad_norm": 0.37201106548309326,
|
1421 |
+
"learning_rate": 0.0003,
|
1422 |
+
"loss": 0.4023,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 1.435897435897436,
|
1427 |
+
"grad_norm": 0.3098253607749939,
|
1428 |
+
"learning_rate": 0.0003,
|
1429 |
+
"loss": 0.2013,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 1.442970822281167,
|
1434 |
+
"grad_norm": 0.41762611269950867,
|
1435 |
+
"learning_rate": 0.0003,
|
1436 |
+
"loss": 0.2562,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.4500442086648984,
|
1441 |
+
"grad_norm": 0.3805309534072876,
|
1442 |
+
"learning_rate": 0.0003,
|
1443 |
+
"loss": 0.2091,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 1.4571175950486295,
|
1448 |
+
"grad_norm": 0.30562469363212585,
|
1449 |
+
"learning_rate": 0.0003,
|
1450 |
+
"loss": 0.3204,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 1.4641909814323608,
|
1455 |
+
"grad_norm": 0.40833625197410583,
|
1456 |
+
"learning_rate": 0.0003,
|
1457 |
+
"loss": 0.3828,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 1.471264367816092,
|
1462 |
+
"grad_norm": 0.44443726539611816,
|
1463 |
+
"learning_rate": 0.0003,
|
1464 |
+
"loss": 0.3023,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.4783377541998233,
|
1469 |
+
"grad_norm": 0.3216983675956726,
|
1470 |
+
"learning_rate": 0.0003,
|
1471 |
+
"loss": 0.148,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.4854111405835544,
|
1476 |
+
"grad_norm": 0.49379777908325195,
|
1477 |
+
"learning_rate": 0.0003,
|
1478 |
+
"loss": 0.3597,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.4924845269672855,
|
1483 |
+
"grad_norm": 0.41881895065307617,
|
1484 |
+
"learning_rate": 0.0003,
|
1485 |
+
"loss": 0.3724,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 1.4995579133510168,
|
1490 |
+
"grad_norm": 0.37855106592178345,
|
1491 |
+
"learning_rate": 0.0003,
|
1492 |
+
"loss": 0.2177,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 1.506631299734748,
|
1497 |
+
"grad_norm": 0.4481782615184784,
|
1498 |
+
"learning_rate": 0.0003,
|
1499 |
+
"loss": 0.4668,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 1.513704686118479,
|
1504 |
+
"grad_norm": 0.45132726430892944,
|
1505 |
+
"learning_rate": 0.0003,
|
1506 |
+
"loss": 0.5844,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 1.5207780725022104,
|
1511 |
+
"grad_norm": 0.4039032459259033,
|
1512 |
+
"learning_rate": 0.0003,
|
1513 |
+
"loss": 0.411,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 1.5278514588859418,
|
1518 |
+
"grad_norm": 0.3423170745372772,
|
1519 |
+
"learning_rate": 0.0003,
|
1520 |
+
"loss": 0.3069,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.5349248452696729,
|
1525 |
+
"grad_norm": 0.3927661180496216,
|
1526 |
+
"learning_rate": 0.0003,
|
1527 |
+
"loss": 0.5008,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.541998231653404,
|
1532 |
+
"grad_norm": 0.43571972846984863,
|
1533 |
+
"learning_rate": 0.0003,
|
1534 |
+
"loss": 0.4626,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 1.5490716180371353,
|
1539 |
+
"grad_norm": 0.370449423789978,
|
1540 |
+
"learning_rate": 0.0003,
|
1541 |
+
"loss": 0.2882,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 1.5561450044208665,
|
1546 |
+
"grad_norm": 0.3305343687534332,
|
1547 |
+
"learning_rate": 0.0003,
|
1548 |
+
"loss": 0.2781,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 1.5632183908045976,
|
1553 |
+
"grad_norm": 0.40083616971969604,
|
1554 |
+
"learning_rate": 0.0003,
|
1555 |
+
"loss": 0.2652,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 1.570291777188329,
|
1560 |
+
"grad_norm": 0.38695937395095825,
|
1561 |
+
"learning_rate": 0.0003,
|
1562 |
+
"loss": 0.4565,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.5773651635720602,
|
1567 |
+
"grad_norm": 0.5376386046409607,
|
1568 |
+
"learning_rate": 0.0003,
|
1569 |
+
"loss": 0.4184,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 1.5844385499557914,
|
1574 |
+
"grad_norm": 0.5290461182594299,
|
1575 |
+
"learning_rate": 0.0003,
|
1576 |
+
"loss": 0.3836,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 1.5915119363395225,
|
1581 |
+
"grad_norm": 0.39294925332069397,
|
1582 |
+
"learning_rate": 0.0003,
|
1583 |
+
"loss": 0.446,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.5985853227232538,
|
1588 |
+
"grad_norm": 0.3946995139122009,
|
1589 |
+
"learning_rate": 0.0003,
|
1590 |
+
"loss": 0.3433,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 1.605658709106985,
|
1595 |
+
"grad_norm": 0.3850666880607605,
|
1596 |
+
"learning_rate": 0.0003,
|
1597 |
+
"loss": 0.515,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 1.612732095490716,
|
1602 |
+
"grad_norm": 0.3812507688999176,
|
1603 |
+
"learning_rate": 0.0003,
|
1604 |
+
"loss": 0.4666,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.6198054818744474,
|
1609 |
+
"grad_norm": 0.34343773126602173,
|
1610 |
+
"learning_rate": 0.0003,
|
1611 |
+
"loss": 0.3437,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 1.6268788682581787,
|
1616 |
+
"grad_norm": 0.42423132061958313,
|
1617 |
+
"learning_rate": 0.0003,
|
1618 |
+
"loss": 0.2998,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 1.6339522546419099,
|
1623 |
+
"grad_norm": 0.36676838994026184,
|
1624 |
+
"learning_rate": 0.0003,
|
1625 |
+
"loss": 0.381,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.641025641025641,
|
1630 |
+
"grad_norm": 0.45891061425209045,
|
1631 |
+
"learning_rate": 0.0003,
|
1632 |
+
"loss": 0.4426,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 1.6480990274093723,
|
1637 |
+
"grad_norm": 0.4290439188480377,
|
1638 |
+
"learning_rate": 0.0003,
|
1639 |
+
"loss": 0.3475,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 1.6551724137931034,
|
1644 |
+
"grad_norm": 0.3556974232196808,
|
1645 |
+
"learning_rate": 0.0003,
|
1646 |
+
"loss": 0.328,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.6622458001768345,
|
1651 |
+
"grad_norm": 0.30578428506851196,
|
1652 |
+
"learning_rate": 0.0003,
|
1653 |
+
"loss": 0.2591,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 1.6693191865605659,
|
1658 |
+
"grad_norm": 0.3522488474845886,
|
1659 |
+
"learning_rate": 0.0003,
|
1660 |
+
"loss": 0.416,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 1.6763925729442972,
|
1665 |
+
"grad_norm": 0.3940620720386505,
|
1666 |
+
"learning_rate": 0.0003,
|
1667 |
+
"loss": 0.548,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 1.6834659593280283,
|
1672 |
+
"grad_norm": 0.4076889455318451,
|
1673 |
+
"learning_rate": 0.0003,
|
1674 |
+
"loss": 0.5044,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 1.6905393457117595,
|
1679 |
+
"grad_norm": 0.49337613582611084,
|
1680 |
+
"learning_rate": 0.0003,
|
1681 |
+
"loss": 0.4355,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 1.6976127320954908,
|
1686 |
+
"grad_norm": 0.37077927589416504,
|
1687 |
+
"learning_rate": 0.0003,
|
1688 |
+
"loss": 0.4739,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.704686118479222,
|
1693 |
+
"grad_norm": 0.4110550880432129,
|
1694 |
+
"learning_rate": 0.0003,
|
1695 |
+
"loss": 0.428,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 1.711759504862953,
|
1700 |
+
"grad_norm": 0.49631252884864807,
|
1701 |
+
"learning_rate": 0.0003,
|
1702 |
+
"loss": 0.4227,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 1.7188328912466844,
|
1707 |
+
"grad_norm": 0.3230995535850525,
|
1708 |
+
"learning_rate": 0.0003,
|
1709 |
+
"loss": 0.3451,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 1.7259062776304157,
|
1714 |
+
"grad_norm": 0.36575183272361755,
|
1715 |
+
"learning_rate": 0.0003,
|
1716 |
+
"loss": 0.2817,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 1.7329796640141468,
|
1721 |
+
"grad_norm": 0.4187852740287781,
|
1722 |
+
"learning_rate": 0.0003,
|
1723 |
+
"loss": 0.319,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 1.740053050397878,
|
1728 |
+
"grad_norm": 0.3224227726459503,
|
1729 |
+
"learning_rate": 0.0003,
|
1730 |
+
"loss": 0.3406,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.7471264367816093,
|
1735 |
+
"grad_norm": 0.379561185836792,
|
1736 |
+
"learning_rate": 0.0003,
|
1737 |
+
"loss": 0.3817,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.7541998231653404,
|
1742 |
+
"grad_norm": 0.44703027606010437,
|
1743 |
+
"learning_rate": 0.0003,
|
1744 |
+
"loss": 0.3879,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 1.7612732095490715,
|
1749 |
+
"grad_norm": 0.34053027629852295,
|
1750 |
+
"learning_rate": 0.0003,
|
1751 |
+
"loss": 0.2767,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 1.7683465959328029,
|
1756 |
+
"grad_norm": 0.48519593477249146,
|
1757 |
+
"learning_rate": 0.0003,
|
1758 |
+
"loss": 0.5043,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 1.7754199823165342,
|
1763 |
+
"grad_norm": 0.3466756045818329,
|
1764 |
+
"learning_rate": 0.0003,
|
1765 |
+
"loss": 0.2593,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 1.782493368700265,
|
1770 |
+
"grad_norm": 0.5155137777328491,
|
1771 |
+
"learning_rate": 0.0003,
|
1772 |
+
"loss": 0.3529,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.7895667550839964,
|
1777 |
+
"grad_norm": 0.4184979796409607,
|
1778 |
+
"learning_rate": 0.0003,
|
1779 |
+
"loss": 0.535,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 1.7966401414677278,
|
1784 |
+
"grad_norm": 0.3188352882862091,
|
1785 |
+
"learning_rate": 0.0003,
|
1786 |
+
"loss": 0.2358,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 1.8037135278514589,
|
1791 |
+
"grad_norm": 0.42813432216644287,
|
1792 |
+
"learning_rate": 0.0003,
|
1793 |
+
"loss": 0.374,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.81078691423519,
|
1798 |
+
"grad_norm": 0.40070992708206177,
|
1799 |
+
"learning_rate": 0.0003,
|
1800 |
+
"loss": 0.4326,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.8178603006189213,
|
1805 |
+
"grad_norm": 0.45408982038497925,
|
1806 |
+
"learning_rate": 0.0003,
|
1807 |
+
"loss": 0.4945,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 1.8249336870026527,
|
1812 |
+
"grad_norm": 0.42870137095451355,
|
1813 |
+
"learning_rate": 0.0003,
|
1814 |
+
"loss": 0.4528,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.8320070733863836,
|
1819 |
+
"grad_norm": 0.3272749185562134,
|
1820 |
+
"learning_rate": 0.0003,
|
1821 |
+
"loss": 0.2587,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 1.839080459770115,
|
1826 |
+
"grad_norm": 0.4601209759712219,
|
1827 |
+
"learning_rate": 0.0003,
|
1828 |
+
"loss": 0.5043,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 1.8461538461538463,
|
1833 |
+
"grad_norm": 0.48971623182296753,
|
1834 |
+
"learning_rate": 0.0003,
|
1835 |
+
"loss": 0.4837,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.8532272325375774,
|
1840 |
+
"grad_norm": 0.37702813744544983,
|
1841 |
+
"learning_rate": 0.0003,
|
1842 |
+
"loss": 0.421,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.8603006189213085,
|
1847 |
+
"grad_norm": 0.37648722529411316,
|
1848 |
+
"learning_rate": 0.0003,
|
1849 |
+
"loss": 0.2666,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.8673740053050398,
|
1854 |
+
"grad_norm": 0.5787553787231445,
|
1855 |
+
"learning_rate": 0.0003,
|
1856 |
+
"loss": 0.2987,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.874447391688771,
|
1861 |
+
"grad_norm": 0.4249975085258484,
|
1862 |
+
"learning_rate": 0.0003,
|
1863 |
+
"loss": 0.5577,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 1.881520778072502,
|
1868 |
+
"grad_norm": 0.3846690356731415,
|
1869 |
+
"learning_rate": 0.0003,
|
1870 |
+
"loss": 0.3106,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 1.8885941644562334,
|
1875 |
+
"grad_norm": 0.37595272064208984,
|
1876 |
+
"learning_rate": 0.0003,
|
1877 |
+
"loss": 0.3638,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 1.8956675508399647,
|
1882 |
+
"grad_norm": 0.4609120190143585,
|
1883 |
+
"learning_rate": 0.0003,
|
1884 |
+
"loss": 0.4356,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 1.9027409372236959,
|
1889 |
+
"grad_norm": 0.3405689299106598,
|
1890 |
+
"learning_rate": 0.0003,
|
1891 |
+
"loss": 0.3113,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.909814323607427,
|
1896 |
+
"grad_norm": 0.30769774317741394,
|
1897 |
+
"learning_rate": 0.0003,
|
1898 |
+
"loss": 0.2626,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.9168877099911583,
|
1903 |
+
"grad_norm": 0.36806437373161316,
|
1904 |
+
"learning_rate": 0.0003,
|
1905 |
+
"loss": 0.401,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.9239610963748894,
|
1910 |
+
"grad_norm": 0.45491501688957214,
|
1911 |
+
"learning_rate": 0.0003,
|
1912 |
+
"loss": 0.4295,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 1.9310344827586206,
|
1917 |
+
"grad_norm": 0.3272283971309662,
|
1918 |
+
"learning_rate": 0.0003,
|
1919 |
+
"loss": 0.3143,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 1.938107869142352,
|
1924 |
+
"grad_norm": 0.32763826847076416,
|
1925 |
+
"learning_rate": 0.0003,
|
1926 |
+
"loss": 0.246,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 1.9451812555260832,
|
1931 |
+
"grad_norm": 0.43065381050109863,
|
1932 |
+
"learning_rate": 0.0003,
|
1933 |
+
"loss": 0.3338,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 1.9522546419098143,
|
1938 |
+
"grad_norm": 0.43713968992233276,
|
1939 |
+
"learning_rate": 0.0003,
|
1940 |
+
"loss": 0.3136,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.9593280282935455,
|
1945 |
+
"grad_norm": 0.2735891342163086,
|
1946 |
+
"learning_rate": 0.0003,
|
1947 |
+
"loss": 0.2381,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.9664014146772768,
|
1952 |
+
"grad_norm": 0.3156580626964569,
|
1953 |
+
"learning_rate": 0.0003,
|
1954 |
+
"loss": 0.3336,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 1.973474801061008,
|
1959 |
+
"grad_norm": 0.4958134591579437,
|
1960 |
+
"learning_rate": 0.0003,
|
1961 |
+
"loss": 0.5279,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 1.980548187444739,
|
1966 |
+
"grad_norm": 0.41325512528419495,
|
1967 |
+
"learning_rate": 0.0003,
|
1968 |
+
"loss": 0.3997,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 1.9876215738284704,
|
1973 |
+
"grad_norm": 0.29986992478370667,
|
1974 |
+
"learning_rate": 0.0003,
|
1975 |
+
"loss": 0.2996,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 1.9946949602122017,
|
1980 |
+
"grad_norm": 0.3219819962978363,
|
1981 |
+
"learning_rate": 0.0003,
|
1982 |
+
"loss": 0.2875,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.9946949602122017,
|
1987 |
+
"step": 282,
|
1988 |
+
"total_flos": 1.061363392708608e+16,
|
1989 |
+
"train_loss": 0.5953954255327265,
|
1990 |
+
"train_runtime": 9564.3104,
|
1991 |
+
"train_samples_per_second": 0.473,
|
1992 |
+
"train_steps_per_second": 0.029
|
1993 |
+
}
|
1994 |
+
],
|
1995 |
+
"logging_steps": 1.0,
|
1996 |
+
"max_steps": 282,
|
1997 |
+
"num_input_tokens_seen": 0,
|
1998 |
+
"num_train_epochs": 2,
|
1999 |
+
"save_steps": 1000,
|
2000 |
+
"total_flos": 1.061363392708608e+16,
|
2001 |
+
"train_batch_size": 2,
|
2002 |
+
"trial_name": null,
|
2003 |
+
"trial_params": null
|
2004 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b9703a0f08a877c615f271bc5b1a049eb013ff713b98bd3ca4d9709b6e9a6c
|
3 |
+
size 6648
|