Upload folder using huggingface_hub
Browse files- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +37 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +733 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-150/README.md +202 -0
- checkpoint-150/adapter_config.json +37 -0
- checkpoint-150/adapter_model.safetensors +3 -0
- checkpoint-150/optimizer.pt +3 -0
- checkpoint-150/rng_state.pth +3 -0
- checkpoint-150/scheduler.pt +3 -0
- checkpoint-150/trainer_state.json +1083 -0
- checkpoint-150/training_args.bin +3 -0
- checkpoint-200/README.md +202 -0
- checkpoint-200/adapter_config.json +37 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +1433 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-250/README.md +202 -0
- checkpoint-250/adapter_config.json +37 -0
- checkpoint-250/adapter_model.safetensors +3 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/trainer_state.json +1783 -0
- checkpoint-250/training_args.bin +3 -0
- checkpoint-50/README.md +202 -0
- checkpoint-50/adapter_config.json +37 -0
- checkpoint-50/adapter_model.safetensors +3 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/trainer_state.json +383 -0
- checkpoint-50/training_args.bin +3 -0
checkpoint-100/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: rinna/llama-3-youko-8b
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": true
|
37 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:402d9ba930e17a9165738bdc9ddaee75f3f8d20a263ad6bf4fde180b4bcd2bfa
|
3 |
+
size 11849545016
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cf5124d409fd3f9cdb0c19cd4fea78d078b6bcb791169e8fcfa4eef0ecaad3b
|
3 |
+
size 2778493596
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9275065a25044785d153dd5dd91f5472b87a85a6b9cfc005f93d96861615f
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6955f63444adde71c8424c079b438f03225134f58369b6493fa8d4f7192856c5
|
3 |
+
size 1064
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.13027618551328818,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013027618551328818,
|
13 |
+
"grad_norm": 14.949752807617188,
|
14 |
+
"learning_rate": 4.0625e-06,
|
15 |
+
"loss": 1.3439,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0026055237102657635,
|
20 |
+
"grad_norm": 15.725403785705566,
|
21 |
+
"learning_rate": 8.125e-06,
|
22 |
+
"loss": 1.3354,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0039082855653986455,
|
27 |
+
"grad_norm": 12.41278076171875,
|
28 |
+
"learning_rate": 1.2187499999999998e-05,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.005211047420531527,
|
34 |
+
"grad_norm": 6.782334327697754,
|
35 |
+
"learning_rate": 1.625e-05,
|
36 |
+
"loss": 1.2634,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.006513809275664409,
|
41 |
+
"grad_norm": 3.730219841003418,
|
42 |
+
"learning_rate": 2.03125e-05,
|
43 |
+
"loss": 1.1704,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.007816571130797291,
|
48 |
+
"grad_norm": 2.547757863998413,
|
49 |
+
"learning_rate": 2.4374999999999996e-05,
|
50 |
+
"loss": 1.165,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.009119332985930172,
|
55 |
+
"grad_norm": 2.4353976249694824,
|
56 |
+
"learning_rate": 2.8437499999999997e-05,
|
57 |
+
"loss": 1.1567,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.010422094841063054,
|
62 |
+
"grad_norm": 2.218895673751831,
|
63 |
+
"learning_rate": 3.25e-05,
|
64 |
+
"loss": 1.0846,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.011724856696195935,
|
69 |
+
"grad_norm": 1.7433233261108398,
|
70 |
+
"learning_rate": 3.6562499999999994e-05,
|
71 |
+
"loss": 0.9816,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.013027618551328817,
|
76 |
+
"grad_norm": 1.6148579120635986,
|
77 |
+
"learning_rate": 4.0625e-05,
|
78 |
+
"loss": 1.0869,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0143303804064617,
|
83 |
+
"grad_norm": 1.5065230131149292,
|
84 |
+
"learning_rate": 4.4687499999999995e-05,
|
85 |
+
"loss": 0.9625,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.015633142261594582,
|
90 |
+
"grad_norm": 1.4786823987960815,
|
91 |
+
"learning_rate": 4.874999999999999e-05,
|
92 |
+
"loss": 1.0489,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.016935904116727463,
|
97 |
+
"grad_norm": 1.2991230487823486,
|
98 |
+
"learning_rate": 5.2812499999999996e-05,
|
99 |
+
"loss": 0.9935,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.018238665971860343,
|
104 |
+
"grad_norm": 1.3199464082717896,
|
105 |
+
"learning_rate": 5.687499999999999e-05,
|
106 |
+
"loss": 1.0188,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.019541427826993224,
|
111 |
+
"grad_norm": 1.2793257236480713,
|
112 |
+
"learning_rate": 6.09375e-05,
|
113 |
+
"loss": 1.0265,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.020844189682126108,
|
118 |
+
"grad_norm": 1.2210655212402344,
|
119 |
+
"learning_rate": 6.5e-05,
|
120 |
+
"loss": 0.9019,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02214695153725899,
|
125 |
+
"grad_norm": 1.3837445974349976,
|
126 |
+
"learning_rate": 6.499971563731688e-05,
|
127 |
+
"loss": 0.9487,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02344971339239187,
|
132 |
+
"grad_norm": 1.2946529388427734,
|
133 |
+
"learning_rate": 6.499886255424368e-05,
|
134 |
+
"loss": 1.0031,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.024752475247524754,
|
139 |
+
"grad_norm": 1.3142110109329224,
|
140 |
+
"learning_rate": 6.499744076570868e-05,
|
141 |
+
"loss": 0.9941,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.026055237102657634,
|
146 |
+
"grad_norm": 1.8206599950790405,
|
147 |
+
"learning_rate": 6.499545029659211e-05,
|
148 |
+
"loss": 0.9767,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.027357998957790515,
|
153 |
+
"grad_norm": 1.2736281156539917,
|
154 |
+
"learning_rate": 6.499289118172568e-05,
|
155 |
+
"loss": 0.9194,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0286607608129234,
|
160 |
+
"grad_norm": 1.8105640411376953,
|
161 |
+
"learning_rate": 6.498976346589196e-05,
|
162 |
+
"loss": 0.9853,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02996352266805628,
|
167 |
+
"grad_norm": 1.4621827602386475,
|
168 |
+
"learning_rate": 6.49860672038236e-05,
|
169 |
+
"loss": 0.9896,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.031266284523189164,
|
174 |
+
"grad_norm": 1.212299108505249,
|
175 |
+
"learning_rate": 6.498180246020238e-05,
|
176 |
+
"loss": 0.9684,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.032569046378322045,
|
181 |
+
"grad_norm": 1.2274290323257446,
|
182 |
+
"learning_rate": 6.49769693096581e-05,
|
183 |
+
"loss": 0.9831,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.033871808233454925,
|
188 |
+
"grad_norm": 1.2909352779388428,
|
189 |
+
"learning_rate": 6.49715678367672e-05,
|
190 |
+
"loss": 0.9971,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.035174570088587806,
|
195 |
+
"grad_norm": 1.2330715656280518,
|
196 |
+
"learning_rate": 6.49655981360514e-05,
|
197 |
+
"loss": 0.9923,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03647733194372069,
|
202 |
+
"grad_norm": 1.2433793544769287,
|
203 |
+
"learning_rate": 6.495906031197591e-05,
|
204 |
+
"loss": 0.9121,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03778009379885357,
|
209 |
+
"grad_norm": 1.2374027967453003,
|
210 |
+
"learning_rate": 6.49519544789477e-05,
|
211 |
+
"loss": 0.9224,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03908285565398645,
|
216 |
+
"grad_norm": 1.2204357385635376,
|
217 |
+
"learning_rate": 6.494428076131346e-05,
|
218 |
+
"loss": 0.919,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.040385617509119336,
|
223 |
+
"grad_norm": 1.1927292346954346,
|
224 |
+
"learning_rate": 6.493603929335744e-05,
|
225 |
+
"loss": 0.9589,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.041688379364252216,
|
230 |
+
"grad_norm": 1.1353641748428345,
|
231 |
+
"learning_rate": 6.492723021929908e-05,
|
232 |
+
"loss": 0.8869,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0429911412193851,
|
237 |
+
"grad_norm": 1.212263822555542,
|
238 |
+
"learning_rate": 6.49178536932905e-05,
|
239 |
+
"loss": 0.8934,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.04429390307451798,
|
244 |
+
"grad_norm": 1.0893241167068481,
|
245 |
+
"learning_rate": 6.49079098794138e-05,
|
246 |
+
"loss": 0.8718,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04559666492965086,
|
251 |
+
"grad_norm": 1.1801607608795166,
|
252 |
+
"learning_rate": 6.489739895167818e-05,
|
253 |
+
"loss": 0.9774,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04689942678478374,
|
258 |
+
"grad_norm": 1.1302330493927002,
|
259 |
+
"learning_rate": 6.488632109401691e-05,
|
260 |
+
"loss": 0.9584,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04820218863991663,
|
265 |
+
"grad_norm": 1.1432682275772095,
|
266 |
+
"learning_rate": 6.487467650028411e-05,
|
267 |
+
"loss": 0.9452,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04950495049504951,
|
272 |
+
"grad_norm": 1.1399481296539307,
|
273 |
+
"learning_rate": 6.486246537425133e-05,
|
274 |
+
"loss": 0.9017,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.05080771235018239,
|
279 |
+
"grad_norm": 1.0911235809326172,
|
280 |
+
"learning_rate": 6.484968792960403e-05,
|
281 |
+
"loss": 0.9036,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.05211047420531527,
|
286 |
+
"grad_norm": 1.071078896522522,
|
287 |
+
"learning_rate": 6.48363443899378e-05,
|
288 |
+
"loss": 0.9273,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.05341323606044815,
|
293 |
+
"grad_norm": 1.053589105606079,
|
294 |
+
"learning_rate": 6.482243498875449e-05,
|
295 |
+
"loss": 0.8847,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05471599791558103,
|
300 |
+
"grad_norm": 1.109771490097046,
|
301 |
+
"learning_rate": 6.480795996945806e-05,
|
302 |
+
"loss": 0.9364,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.05601875977071391,
|
307 |
+
"grad_norm": 1.1093286275863647,
|
308 |
+
"learning_rate": 6.479291958535037e-05,
|
309 |
+
"loss": 0.9088,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.0573215216258468,
|
314 |
+
"grad_norm": 1.0716255903244019,
|
315 |
+
"learning_rate": 6.477731409962675e-05,
|
316 |
+
"loss": 0.8885,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.05862428348097968,
|
321 |
+
"grad_norm": 1.1552095413208008,
|
322 |
+
"learning_rate": 6.476114378537138e-05,
|
323 |
+
"loss": 0.9736,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05992704533611256,
|
328 |
+
"grad_norm": 1.1647394895553589,
|
329 |
+
"learning_rate": 6.474440892555249e-05,
|
330 |
+
"loss": 0.9138,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06122980719124544,
|
335 |
+
"grad_norm": 1.1463412046432495,
|
336 |
+
"learning_rate": 6.472710981301745e-05,
|
337 |
+
"loss": 0.9204,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.06253256904637833,
|
342 |
+
"grad_norm": 1.175421118736267,
|
343 |
+
"learning_rate": 6.470924675048762e-05,
|
344 |
+
"loss": 0.9119,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.06383533090151121,
|
349 |
+
"grad_norm": 1.9249529838562012,
|
350 |
+
"learning_rate": 6.469082005055304e-05,
|
351 |
+
"loss": 0.8639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.06513809275664409,
|
356 |
+
"grad_norm": 1.1802655458450317,
|
357 |
+
"learning_rate": 6.467183003566701e-05,
|
358 |
+
"loss": 0.9352,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.06644085461177697,
|
363 |
+
"grad_norm": 1.1035569906234741,
|
364 |
+
"learning_rate": 6.465227703814038e-05,
|
365 |
+
"loss": 0.9342,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.06774361646690985,
|
370 |
+
"grad_norm": 1.1226942539215088,
|
371 |
+
"learning_rate": 6.463216140013581e-05,
|
372 |
+
"loss": 0.8948,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.06904637832204273,
|
377 |
+
"grad_norm": 1.1143085956573486,
|
378 |
+
"learning_rate": 6.46114834736617e-05,
|
379 |
+
"loss": 0.9577,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.07034914017717561,
|
384 |
+
"grad_norm": 1.1214665174484253,
|
385 |
+
"learning_rate": 6.459024362056608e-05,
|
386 |
+
"loss": 0.9106,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.07165190203230849,
|
391 |
+
"grad_norm": 1.1105942726135254,
|
392 |
+
"learning_rate": 6.45684422125303e-05,
|
393 |
+
"loss": 0.8706,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.07295466388744137,
|
398 |
+
"grad_norm": 1.0562191009521484,
|
399 |
+
"learning_rate": 6.454607963106247e-05,
|
400 |
+
"loss": 0.8278,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.07425742574257425,
|
405 |
+
"grad_norm": 1.1298907995224,
|
406 |
+
"learning_rate": 6.452315626749081e-05,
|
407 |
+
"loss": 0.8883,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.07556018759770713,
|
412 |
+
"grad_norm": 1.133426547050476,
|
413 |
+
"learning_rate": 6.449967252295682e-05,
|
414 |
+
"loss": 0.8868,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.07686294945284002,
|
419 |
+
"grad_norm": 1.09175443649292,
|
420 |
+
"learning_rate": 6.447562880840822e-05,
|
421 |
+
"loss": 0.8486,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.0781657113079729,
|
426 |
+
"grad_norm": 1.1153368949890137,
|
427 |
+
"learning_rate": 6.44510255445918e-05,
|
428 |
+
"loss": 0.9278,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.07946847316310579,
|
433 |
+
"grad_norm": 1.102013349533081,
|
434 |
+
"learning_rate": 6.442586316204601e-05,
|
435 |
+
"loss": 0.8362,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.08077123501823867,
|
440 |
+
"grad_norm": 1.1041877269744873,
|
441 |
+
"learning_rate": 6.44001421010935e-05,
|
442 |
+
"loss": 0.8746,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.08207399687337155,
|
447 |
+
"grad_norm": 1.075576901435852,
|
448 |
+
"learning_rate": 6.437386281183331e-05,
|
449 |
+
"loss": 0.8567,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.08337675872850443,
|
454 |
+
"grad_norm": 1.1472443342208862,
|
455 |
+
"learning_rate": 6.43470257541331e-05,
|
456 |
+
"loss": 0.9023,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.08467952058363731,
|
461 |
+
"grad_norm": 1.1024972200393677,
|
462 |
+
"learning_rate": 6.431963139762104e-05,
|
463 |
+
"loss": 0.8982,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.0859822824387702,
|
468 |
+
"grad_norm": 1.1128768920898438,
|
469 |
+
"learning_rate": 6.42916802216776e-05,
|
470 |
+
"loss": 0.883,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.08728504429390307,
|
475 |
+
"grad_norm": 1.058384895324707,
|
476 |
+
"learning_rate": 6.426317271542717e-05,
|
477 |
+
"loss": 0.8428,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.08858780614903596,
|
482 |
+
"grad_norm": 1.0728991031646729,
|
483 |
+
"learning_rate": 6.423410937772951e-05,
|
484 |
+
"loss": 0.8553,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.08989056800416884,
|
489 |
+
"grad_norm": 1.0956963300704956,
|
490 |
+
"learning_rate": 6.4204490717171e-05,
|
491 |
+
"loss": 0.8894,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.09119332985930172,
|
496 |
+
"grad_norm": 1.0787287950515747,
|
497 |
+
"learning_rate": 6.417431725205575e-05,
|
498 |
+
"loss": 0.9086,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.0924960917144346,
|
503 |
+
"grad_norm": 1.1435580253601074,
|
504 |
+
"learning_rate": 6.414358951039651e-05,
|
505 |
+
"loss": 0.9074,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.09379885356956748,
|
510 |
+
"grad_norm": 1.0396053791046143,
|
511 |
+
"learning_rate": 6.41123080299055e-05,
|
512 |
+
"loss": 0.8553,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.09510161542470036,
|
517 |
+
"grad_norm": 1.0929105281829834,
|
518 |
+
"learning_rate": 6.40804733579849e-05,
|
519 |
+
"loss": 0.8504,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.09640437727983325,
|
524 |
+
"grad_norm": 1.1395248174667358,
|
525 |
+
"learning_rate": 6.404808605171734e-05,
|
526 |
+
"loss": 0.9222,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.09770713913496613,
|
531 |
+
"grad_norm": 1.0281647443771362,
|
532 |
+
"learning_rate": 6.401514667785613e-05,
|
533 |
+
"loss": 0.868,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.09900990099009901,
|
538 |
+
"grad_norm": 1.0565054416656494,
|
539 |
+
"learning_rate": 6.398165581281536e-05,
|
540 |
+
"loss": 0.8302,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.1003126628452319,
|
545 |
+
"grad_norm": 1.0529290437698364,
|
546 |
+
"learning_rate": 6.394761404265977e-05,
|
547 |
+
"loss": 0.8669,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.10161542470036478,
|
552 |
+
"grad_norm": 1.0579882860183716,
|
553 |
+
"learning_rate": 6.391302196309452e-05,
|
554 |
+
"loss": 0.9204,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.10291818655549766,
|
559 |
+
"grad_norm": 1.0531302690505981,
|
560 |
+
"learning_rate": 6.387788017945482e-05,
|
561 |
+
"loss": 0.9202,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.10422094841063054,
|
566 |
+
"grad_norm": 1.0358260869979858,
|
567 |
+
"learning_rate": 6.384218930669521e-05,
|
568 |
+
"loss": 0.8647,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.10552371026576342,
|
573 |
+
"grad_norm": 1.0599216222763062,
|
574 |
+
"learning_rate": 6.380594996937895e-05,
|
575 |
+
"loss": 0.9093,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.1068264721208963,
|
580 |
+
"grad_norm": 1.2026344537734985,
|
581 |
+
"learning_rate": 6.376916280166696e-05,
|
582 |
+
"loss": 0.8731,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.10812923397602918,
|
587 |
+
"grad_norm": 1.1054397821426392,
|
588 |
+
"learning_rate": 6.373182844730677e-05,
|
589 |
+
"loss": 0.8835,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.10943199583116206,
|
594 |
+
"grad_norm": 1.030562162399292,
|
595 |
+
"learning_rate": 6.369394755962129e-05,
|
596 |
+
"loss": 0.8432,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.11073475768629494,
|
601 |
+
"grad_norm": 1.0522128343582153,
|
602 |
+
"learning_rate": 6.365552080149737e-05,
|
603 |
+
"loss": 0.8598,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.11203751954142782,
|
608 |
+
"grad_norm": 1.0692416429519653,
|
609 |
+
"learning_rate": 6.361654884537413e-05,
|
610 |
+
"loss": 0.8812,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.1133402813965607,
|
615 |
+
"grad_norm": 1.1009373664855957,
|
616 |
+
"learning_rate": 6.357703237323127e-05,
|
617 |
+
"loss": 0.8635,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.1146430432516936,
|
622 |
+
"grad_norm": 1.1628373861312866,
|
623 |
+
"learning_rate": 6.353697207657708e-05,
|
624 |
+
"loss": 0.8907,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.11594580510682648,
|
629 |
+
"grad_norm": 1.1273458003997803,
|
630 |
+
"learning_rate": 6.349636865643642e-05,
|
631 |
+
"loss": 0.8445,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.11724856696195936,
|
636 |
+
"grad_norm": 1.0971312522888184,
|
637 |
+
"learning_rate": 6.345522282333835e-05,
|
638 |
+
"loss": 0.8543,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.11855132881709224,
|
643 |
+
"grad_norm": 1.0826351642608643,
|
644 |
+
"learning_rate": 6.341353529730374e-05,
|
645 |
+
"loss": 0.8605,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.11985409067222512,
|
650 |
+
"grad_norm": 1.0686413049697876,
|
651 |
+
"learning_rate": 6.337130680783273e-05,
|
652 |
+
"loss": 0.8814,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.121156852527358,
|
657 |
+
"grad_norm": 1.21683931350708,
|
658 |
+
"learning_rate": 6.332853809389189e-05,
|
659 |
+
"loss": 0.8979,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.12245961438249088,
|
664 |
+
"grad_norm": 1.0884461402893066,
|
665 |
+
"learning_rate": 6.328522990390126e-05,
|
666 |
+
"loss": 0.8577,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.12376237623762376,
|
671 |
+
"grad_norm": 1.047310709953308,
|
672 |
+
"learning_rate": 6.324138299572135e-05,
|
673 |
+
"loss": 0.8174,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.12506513809275666,
|
678 |
+
"grad_norm": 1.087296485900879,
|
679 |
+
"learning_rate": 6.319699813663982e-05,
|
680 |
+
"loss": 0.8566,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.12636789994788952,
|
685 |
+
"grad_norm": 1.070327639579773,
|
686 |
+
"learning_rate": 6.315207610335808e-05,
|
687 |
+
"loss": 0.8615,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.12767066180302242,
|
692 |
+
"grad_norm": 1.0299792289733887,
|
693 |
+
"learning_rate": 6.310661768197764e-05,
|
694 |
+
"loss": 0.866,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.12897342365815528,
|
699 |
+
"grad_norm": 1.1011384725570679,
|
700 |
+
"learning_rate": 6.306062366798642e-05,
|
701 |
+
"loss": 0.8775,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.13027618551328818,
|
706 |
+
"grad_norm": 1.0193467140197754,
|
707 |
+
"learning_rate": 6.301409486624481e-05,
|
708 |
+
"loss": 0.8243,
|
709 |
+
"step": 100
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 1,
|
713 |
+
"max_steps": 767,
|
714 |
+
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 1,
|
716 |
+
"save_steps": 50,
|
717 |
+
"stateful_callbacks": {
|
718 |
+
"TrainerControl": {
|
719 |
+
"args": {
|
720 |
+
"should_epoch_stop": false,
|
721 |
+
"should_evaluate": false,
|
722 |
+
"should_log": false,
|
723 |
+
"should_save": true,
|
724 |
+
"should_training_stop": false
|
725 |
+
},
|
726 |
+
"attributes": {}
|
727 |
+
}
|
728 |
+
},
|
729 |
+
"total_flos": 1.5374903328099533e+17,
|
730 |
+
"train_batch_size": 6,
|
731 |
+
"trial_name": null,
|
732 |
+
"trial_params": null
|
733 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c6cdd050f0e9f3e909bcca2e2c0488bdf293a6b22313a332d8541c60d48d06
|
3 |
+
size 5432
|
checkpoint-150/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: rinna/llama-3-youko-8b
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-150/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": true
|
37 |
+
}
|
checkpoint-150/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f90f319b735a22000a285a95a40d44e0e47b277f706deaaa31fec054a39b0a5
|
3 |
+
size 11849545016
|
checkpoint-150/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3d849e8a3e9ba1f43026f3377a4bc2a1321a0c0c2dc65aabd2e49f2f3f5b9a2
|
3 |
+
size 2778493596
|
checkpoint-150/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9275065a25044785d153dd5dd91f5472b87a85a6b9cfc005f93d96861615f
|
3 |
+
size 14244
|
checkpoint-150/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0be33ef84db17996ded51f72659e58534368a1f615ccdd34908ebaa6888cf5dd
|
3 |
+
size 1064
|
checkpoint-150/trainer_state.json
ADDED
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19541427826993227,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 150,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013027618551328818,
|
13 |
+
"grad_norm": 14.949752807617188,
|
14 |
+
"learning_rate": 4.0625e-06,
|
15 |
+
"loss": 1.3439,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0026055237102657635,
|
20 |
+
"grad_norm": 15.725403785705566,
|
21 |
+
"learning_rate": 8.125e-06,
|
22 |
+
"loss": 1.3354,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0039082855653986455,
|
27 |
+
"grad_norm": 12.41278076171875,
|
28 |
+
"learning_rate": 1.2187499999999998e-05,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.005211047420531527,
|
34 |
+
"grad_norm": 6.782334327697754,
|
35 |
+
"learning_rate": 1.625e-05,
|
36 |
+
"loss": 1.2634,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.006513809275664409,
|
41 |
+
"grad_norm": 3.730219841003418,
|
42 |
+
"learning_rate": 2.03125e-05,
|
43 |
+
"loss": 1.1704,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.007816571130797291,
|
48 |
+
"grad_norm": 2.547757863998413,
|
49 |
+
"learning_rate": 2.4374999999999996e-05,
|
50 |
+
"loss": 1.165,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.009119332985930172,
|
55 |
+
"grad_norm": 2.4353976249694824,
|
56 |
+
"learning_rate": 2.8437499999999997e-05,
|
57 |
+
"loss": 1.1567,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.010422094841063054,
|
62 |
+
"grad_norm": 2.218895673751831,
|
63 |
+
"learning_rate": 3.25e-05,
|
64 |
+
"loss": 1.0846,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.011724856696195935,
|
69 |
+
"grad_norm": 1.7433233261108398,
|
70 |
+
"learning_rate": 3.6562499999999994e-05,
|
71 |
+
"loss": 0.9816,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.013027618551328817,
|
76 |
+
"grad_norm": 1.6148579120635986,
|
77 |
+
"learning_rate": 4.0625e-05,
|
78 |
+
"loss": 1.0869,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0143303804064617,
|
83 |
+
"grad_norm": 1.5065230131149292,
|
84 |
+
"learning_rate": 4.4687499999999995e-05,
|
85 |
+
"loss": 0.9625,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.015633142261594582,
|
90 |
+
"grad_norm": 1.4786823987960815,
|
91 |
+
"learning_rate": 4.874999999999999e-05,
|
92 |
+
"loss": 1.0489,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.016935904116727463,
|
97 |
+
"grad_norm": 1.2991230487823486,
|
98 |
+
"learning_rate": 5.2812499999999996e-05,
|
99 |
+
"loss": 0.9935,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.018238665971860343,
|
104 |
+
"grad_norm": 1.3199464082717896,
|
105 |
+
"learning_rate": 5.687499999999999e-05,
|
106 |
+
"loss": 1.0188,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.019541427826993224,
|
111 |
+
"grad_norm": 1.2793257236480713,
|
112 |
+
"learning_rate": 6.09375e-05,
|
113 |
+
"loss": 1.0265,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.020844189682126108,
|
118 |
+
"grad_norm": 1.2210655212402344,
|
119 |
+
"learning_rate": 6.5e-05,
|
120 |
+
"loss": 0.9019,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02214695153725899,
|
125 |
+
"grad_norm": 1.3837445974349976,
|
126 |
+
"learning_rate": 6.499971563731688e-05,
|
127 |
+
"loss": 0.9487,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02344971339239187,
|
132 |
+
"grad_norm": 1.2946529388427734,
|
133 |
+
"learning_rate": 6.499886255424368e-05,
|
134 |
+
"loss": 1.0031,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.024752475247524754,
|
139 |
+
"grad_norm": 1.3142110109329224,
|
140 |
+
"learning_rate": 6.499744076570868e-05,
|
141 |
+
"loss": 0.9941,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.026055237102657634,
|
146 |
+
"grad_norm": 1.8206599950790405,
|
147 |
+
"learning_rate": 6.499545029659211e-05,
|
148 |
+
"loss": 0.9767,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.027357998957790515,
|
153 |
+
"grad_norm": 1.2736281156539917,
|
154 |
+
"learning_rate": 6.499289118172568e-05,
|
155 |
+
"loss": 0.9194,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0286607608129234,
|
160 |
+
"grad_norm": 1.8105640411376953,
|
161 |
+
"learning_rate": 6.498976346589196e-05,
|
162 |
+
"loss": 0.9853,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02996352266805628,
|
167 |
+
"grad_norm": 1.4621827602386475,
|
168 |
+
"learning_rate": 6.49860672038236e-05,
|
169 |
+
"loss": 0.9896,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.031266284523189164,
|
174 |
+
"grad_norm": 1.212299108505249,
|
175 |
+
"learning_rate": 6.498180246020238e-05,
|
176 |
+
"loss": 0.9684,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.032569046378322045,
|
181 |
+
"grad_norm": 1.2274290323257446,
|
182 |
+
"learning_rate": 6.49769693096581e-05,
|
183 |
+
"loss": 0.9831,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.033871808233454925,
|
188 |
+
"grad_norm": 1.2909352779388428,
|
189 |
+
"learning_rate": 6.49715678367672e-05,
|
190 |
+
"loss": 0.9971,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.035174570088587806,
|
195 |
+
"grad_norm": 1.2330715656280518,
|
196 |
+
"learning_rate": 6.49655981360514e-05,
|
197 |
+
"loss": 0.9923,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03647733194372069,
|
202 |
+
"grad_norm": 1.2433793544769287,
|
203 |
+
"learning_rate": 6.495906031197591e-05,
|
204 |
+
"loss": 0.9121,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03778009379885357,
|
209 |
+
"grad_norm": 1.2374027967453003,
|
210 |
+
"learning_rate": 6.49519544789477e-05,
|
211 |
+
"loss": 0.9224,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03908285565398645,
|
216 |
+
"grad_norm": 1.2204357385635376,
|
217 |
+
"learning_rate": 6.494428076131346e-05,
|
218 |
+
"loss": 0.919,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.040385617509119336,
|
223 |
+
"grad_norm": 1.1927292346954346,
|
224 |
+
"learning_rate": 6.493603929335744e-05,
|
225 |
+
"loss": 0.9589,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.041688379364252216,
|
230 |
+
"grad_norm": 1.1353641748428345,
|
231 |
+
"learning_rate": 6.492723021929908e-05,
|
232 |
+
"loss": 0.8869,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0429911412193851,
|
237 |
+
"grad_norm": 1.212263822555542,
|
238 |
+
"learning_rate": 6.49178536932905e-05,
|
239 |
+
"loss": 0.8934,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.04429390307451798,
|
244 |
+
"grad_norm": 1.0893241167068481,
|
245 |
+
"learning_rate": 6.49079098794138e-05,
|
246 |
+
"loss": 0.8718,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04559666492965086,
|
251 |
+
"grad_norm": 1.1801607608795166,
|
252 |
+
"learning_rate": 6.489739895167818e-05,
|
253 |
+
"loss": 0.9774,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04689942678478374,
|
258 |
+
"grad_norm": 1.1302330493927002,
|
259 |
+
"learning_rate": 6.488632109401691e-05,
|
260 |
+
"loss": 0.9584,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04820218863991663,
|
265 |
+
"grad_norm": 1.1432682275772095,
|
266 |
+
"learning_rate": 6.487467650028411e-05,
|
267 |
+
"loss": 0.9452,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04950495049504951,
|
272 |
+
"grad_norm": 1.1399481296539307,
|
273 |
+
"learning_rate": 6.486246537425133e-05,
|
274 |
+
"loss": 0.9017,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.05080771235018239,
|
279 |
+
"grad_norm": 1.0911235809326172,
|
280 |
+
"learning_rate": 6.484968792960403e-05,
|
281 |
+
"loss": 0.9036,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.05211047420531527,
|
286 |
+
"grad_norm": 1.071078896522522,
|
287 |
+
"learning_rate": 6.48363443899378e-05,
|
288 |
+
"loss": 0.9273,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.05341323606044815,
|
293 |
+
"grad_norm": 1.053589105606079,
|
294 |
+
"learning_rate": 6.482243498875449e-05,
|
295 |
+
"loss": 0.8847,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05471599791558103,
|
300 |
+
"grad_norm": 1.109771490097046,
|
301 |
+
"learning_rate": 6.480795996945806e-05,
|
302 |
+
"loss": 0.9364,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.05601875977071391,
|
307 |
+
"grad_norm": 1.1093286275863647,
|
308 |
+
"learning_rate": 6.479291958535037e-05,
|
309 |
+
"loss": 0.9088,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.0573215216258468,
|
314 |
+
"grad_norm": 1.0716255903244019,
|
315 |
+
"learning_rate": 6.477731409962675e-05,
|
316 |
+
"loss": 0.8885,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.05862428348097968,
|
321 |
+
"grad_norm": 1.1552095413208008,
|
322 |
+
"learning_rate": 6.476114378537138e-05,
|
323 |
+
"loss": 0.9736,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05992704533611256,
|
328 |
+
"grad_norm": 1.1647394895553589,
|
329 |
+
"learning_rate": 6.474440892555249e-05,
|
330 |
+
"loss": 0.9138,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06122980719124544,
|
335 |
+
"grad_norm": 1.1463412046432495,
|
336 |
+
"learning_rate": 6.472710981301745e-05,
|
337 |
+
"loss": 0.9204,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.06253256904637833,
|
342 |
+
"grad_norm": 1.175421118736267,
|
343 |
+
"learning_rate": 6.470924675048762e-05,
|
344 |
+
"loss": 0.9119,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.06383533090151121,
|
349 |
+
"grad_norm": 1.9249529838562012,
|
350 |
+
"learning_rate": 6.469082005055304e-05,
|
351 |
+
"loss": 0.8639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.06513809275664409,
|
356 |
+
"grad_norm": 1.1802655458450317,
|
357 |
+
"learning_rate": 6.467183003566701e-05,
|
358 |
+
"loss": 0.9352,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.06644085461177697,
|
363 |
+
"grad_norm": 1.1035569906234741,
|
364 |
+
"learning_rate": 6.465227703814038e-05,
|
365 |
+
"loss": 0.9342,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.06774361646690985,
|
370 |
+
"grad_norm": 1.1226942539215088,
|
371 |
+
"learning_rate": 6.463216140013581e-05,
|
372 |
+
"loss": 0.8948,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.06904637832204273,
|
377 |
+
"grad_norm": 1.1143085956573486,
|
378 |
+
"learning_rate": 6.46114834736617e-05,
|
379 |
+
"loss": 0.9577,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.07034914017717561,
|
384 |
+
"grad_norm": 1.1214665174484253,
|
385 |
+
"learning_rate": 6.459024362056608e-05,
|
386 |
+
"loss": 0.9106,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.07165190203230849,
|
391 |
+
"grad_norm": 1.1105942726135254,
|
392 |
+
"learning_rate": 6.45684422125303e-05,
|
393 |
+
"loss": 0.8706,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.07295466388744137,
|
398 |
+
"grad_norm": 1.0562191009521484,
|
399 |
+
"learning_rate": 6.454607963106247e-05,
|
400 |
+
"loss": 0.8278,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.07425742574257425,
|
405 |
+
"grad_norm": 1.1298907995224,
|
406 |
+
"learning_rate": 6.452315626749081e-05,
|
407 |
+
"loss": 0.8883,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.07556018759770713,
|
412 |
+
"grad_norm": 1.133426547050476,
|
413 |
+
"learning_rate": 6.449967252295682e-05,
|
414 |
+
"loss": 0.8868,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.07686294945284002,
|
419 |
+
"grad_norm": 1.09175443649292,
|
420 |
+
"learning_rate": 6.447562880840822e-05,
|
421 |
+
"loss": 0.8486,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.0781657113079729,
|
426 |
+
"grad_norm": 1.1153368949890137,
|
427 |
+
"learning_rate": 6.44510255445918e-05,
|
428 |
+
"loss": 0.9278,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.07946847316310579,
|
433 |
+
"grad_norm": 1.102013349533081,
|
434 |
+
"learning_rate": 6.442586316204601e-05,
|
435 |
+
"loss": 0.8362,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.08077123501823867,
|
440 |
+
"grad_norm": 1.1041877269744873,
|
441 |
+
"learning_rate": 6.44001421010935e-05,
|
442 |
+
"loss": 0.8746,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.08207399687337155,
|
447 |
+
"grad_norm": 1.075576901435852,
|
448 |
+
"learning_rate": 6.437386281183331e-05,
|
449 |
+
"loss": 0.8567,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.08337675872850443,
|
454 |
+
"grad_norm": 1.1472443342208862,
|
455 |
+
"learning_rate": 6.43470257541331e-05,
|
456 |
+
"loss": 0.9023,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.08467952058363731,
|
461 |
+
"grad_norm": 1.1024972200393677,
|
462 |
+
"learning_rate": 6.431963139762104e-05,
|
463 |
+
"loss": 0.8982,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.0859822824387702,
|
468 |
+
"grad_norm": 1.1128768920898438,
|
469 |
+
"learning_rate": 6.42916802216776e-05,
|
470 |
+
"loss": 0.883,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.08728504429390307,
|
475 |
+
"grad_norm": 1.058384895324707,
|
476 |
+
"learning_rate": 6.426317271542717e-05,
|
477 |
+
"loss": 0.8428,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.08858780614903596,
|
482 |
+
"grad_norm": 1.0728991031646729,
|
483 |
+
"learning_rate": 6.423410937772951e-05,
|
484 |
+
"loss": 0.8553,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.08989056800416884,
|
489 |
+
"grad_norm": 1.0956963300704956,
|
490 |
+
"learning_rate": 6.4204490717171e-05,
|
491 |
+
"loss": 0.8894,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.09119332985930172,
|
496 |
+
"grad_norm": 1.0787287950515747,
|
497 |
+
"learning_rate": 6.417431725205575e-05,
|
498 |
+
"loss": 0.9086,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.0924960917144346,
|
503 |
+
"grad_norm": 1.1435580253601074,
|
504 |
+
"learning_rate": 6.414358951039651e-05,
|
505 |
+
"loss": 0.9074,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.09379885356956748,
|
510 |
+
"grad_norm": 1.0396053791046143,
|
511 |
+
"learning_rate": 6.41123080299055e-05,
|
512 |
+
"loss": 0.8553,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.09510161542470036,
|
517 |
+
"grad_norm": 1.0929105281829834,
|
518 |
+
"learning_rate": 6.40804733579849e-05,
|
519 |
+
"loss": 0.8504,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.09640437727983325,
|
524 |
+
"grad_norm": 1.1395248174667358,
|
525 |
+
"learning_rate": 6.404808605171734e-05,
|
526 |
+
"loss": 0.9222,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.09770713913496613,
|
531 |
+
"grad_norm": 1.0281647443771362,
|
532 |
+
"learning_rate": 6.401514667785613e-05,
|
533 |
+
"loss": 0.868,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.09900990099009901,
|
538 |
+
"grad_norm": 1.0565054416656494,
|
539 |
+
"learning_rate": 6.398165581281536e-05,
|
540 |
+
"loss": 0.8302,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.1003126628452319,
|
545 |
+
"grad_norm": 1.0529290437698364,
|
546 |
+
"learning_rate": 6.394761404265977e-05,
|
547 |
+
"loss": 0.8669,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.10161542470036478,
|
552 |
+
"grad_norm": 1.0579882860183716,
|
553 |
+
"learning_rate": 6.391302196309452e-05,
|
554 |
+
"loss": 0.9204,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.10291818655549766,
|
559 |
+
"grad_norm": 1.0531302690505981,
|
560 |
+
"learning_rate": 6.387788017945482e-05,
|
561 |
+
"loss": 0.9202,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.10422094841063054,
|
566 |
+
"grad_norm": 1.0358260869979858,
|
567 |
+
"learning_rate": 6.384218930669521e-05,
|
568 |
+
"loss": 0.8647,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.10552371026576342,
|
573 |
+
"grad_norm": 1.0599216222763062,
|
574 |
+
"learning_rate": 6.380594996937895e-05,
|
575 |
+
"loss": 0.9093,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.1068264721208963,
|
580 |
+
"grad_norm": 1.2026344537734985,
|
581 |
+
"learning_rate": 6.376916280166696e-05,
|
582 |
+
"loss": 0.8731,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.10812923397602918,
|
587 |
+
"grad_norm": 1.1054397821426392,
|
588 |
+
"learning_rate": 6.373182844730677e-05,
|
589 |
+
"loss": 0.8835,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.10943199583116206,
|
594 |
+
"grad_norm": 1.030562162399292,
|
595 |
+
"learning_rate": 6.369394755962129e-05,
|
596 |
+
"loss": 0.8432,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.11073475768629494,
|
601 |
+
"grad_norm": 1.0522128343582153,
|
602 |
+
"learning_rate": 6.365552080149737e-05,
|
603 |
+
"loss": 0.8598,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.11203751954142782,
|
608 |
+
"grad_norm": 1.0692416429519653,
|
609 |
+
"learning_rate": 6.361654884537413e-05,
|
610 |
+
"loss": 0.8812,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.1133402813965607,
|
615 |
+
"grad_norm": 1.1009373664855957,
|
616 |
+
"learning_rate": 6.357703237323127e-05,
|
617 |
+
"loss": 0.8635,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.1146430432516936,
|
622 |
+
"grad_norm": 1.1628373861312866,
|
623 |
+
"learning_rate": 6.353697207657708e-05,
|
624 |
+
"loss": 0.8907,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.11594580510682648,
|
629 |
+
"grad_norm": 1.1273458003997803,
|
630 |
+
"learning_rate": 6.349636865643642e-05,
|
631 |
+
"loss": 0.8445,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.11724856696195936,
|
636 |
+
"grad_norm": 1.0971312522888184,
|
637 |
+
"learning_rate": 6.345522282333835e-05,
|
638 |
+
"loss": 0.8543,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.11855132881709224,
|
643 |
+
"grad_norm": 1.0826351642608643,
|
644 |
+
"learning_rate": 6.341353529730374e-05,
|
645 |
+
"loss": 0.8605,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.11985409067222512,
|
650 |
+
"grad_norm": 1.0686413049697876,
|
651 |
+
"learning_rate": 6.337130680783273e-05,
|
652 |
+
"loss": 0.8814,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.121156852527358,
|
657 |
+
"grad_norm": 1.21683931350708,
|
658 |
+
"learning_rate": 6.332853809389189e-05,
|
659 |
+
"loss": 0.8979,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.12245961438249088,
|
664 |
+
"grad_norm": 1.0884461402893066,
|
665 |
+
"learning_rate": 6.328522990390126e-05,
|
666 |
+
"loss": 0.8577,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.12376237623762376,
|
671 |
+
"grad_norm": 1.047310709953308,
|
672 |
+
"learning_rate": 6.324138299572135e-05,
|
673 |
+
"loss": 0.8174,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.12506513809275666,
|
678 |
+
"grad_norm": 1.087296485900879,
|
679 |
+
"learning_rate": 6.319699813663982e-05,
|
680 |
+
"loss": 0.8566,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.12636789994788952,
|
685 |
+
"grad_norm": 1.070327639579773,
|
686 |
+
"learning_rate": 6.315207610335808e-05,
|
687 |
+
"loss": 0.8615,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.12767066180302242,
|
692 |
+
"grad_norm": 1.0299792289733887,
|
693 |
+
"learning_rate": 6.310661768197764e-05,
|
694 |
+
"loss": 0.866,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.12897342365815528,
|
699 |
+
"grad_norm": 1.1011384725570679,
|
700 |
+
"learning_rate": 6.306062366798642e-05,
|
701 |
+
"loss": 0.8775,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.13027618551328818,
|
706 |
+
"grad_norm": 1.0193467140197754,
|
707 |
+
"learning_rate": 6.301409486624481e-05,
|
708 |
+
"loss": 0.8243,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.13157894736842105,
|
713 |
+
"grad_norm": 1.0899205207824707,
|
714 |
+
"learning_rate": 6.296703209097159e-05,
|
715 |
+
"loss": 0.8849,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.13288170922355394,
|
720 |
+
"grad_norm": 1.0473856925964355,
|
721 |
+
"learning_rate": 6.291943616572962e-05,
|
722 |
+
"loss": 0.8847,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.1341844710786868,
|
727 |
+
"grad_norm": 0.9922148585319519,
|
728 |
+
"learning_rate": 6.287130792341154e-05,
|
729 |
+
"loss": 0.8157,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.1354872329338197,
|
734 |
+
"grad_norm": 1.0680872201919556,
|
735 |
+
"learning_rate": 6.282264820622511e-05,
|
736 |
+
"loss": 0.8802,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.13678999478895257,
|
741 |
+
"grad_norm": 1.034562587738037,
|
742 |
+
"learning_rate": 6.27734578656785e-05,
|
743 |
+
"loss": 0.8826,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.13809275664408546,
|
748 |
+
"grad_norm": 1.0247395038604736,
|
749 |
+
"learning_rate": 6.272373776256536e-05,
|
750 |
+
"loss": 0.8535,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.13939551849921833,
|
755 |
+
"grad_norm": 1.099061131477356,
|
756 |
+
"learning_rate": 6.267348876694983e-05,
|
757 |
+
"loss": 0.8583,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.14069828035435122,
|
762 |
+
"grad_norm": 1.0081039667129517,
|
763 |
+
"learning_rate": 6.262271175815126e-05,
|
764 |
+
"loss": 0.7988,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.14200104220948412,
|
769 |
+
"grad_norm": 1.1140209436416626,
|
770 |
+
"learning_rate": 6.257140762472879e-05,
|
771 |
+
"loss": 0.8426,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.14330380406461699,
|
776 |
+
"grad_norm": 1.0654839277267456,
|
777 |
+
"learning_rate": 6.251957726446589e-05,
|
778 |
+
"loss": 0.8682,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.14460656591974988,
|
783 |
+
"grad_norm": 1.0632318258285522,
|
784 |
+
"learning_rate": 6.246722158435455e-05,
|
785 |
+
"loss": 0.8379,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.14590932777488275,
|
790 |
+
"grad_norm": 1.0444918870925903,
|
791 |
+
"learning_rate": 6.241434150057953e-05,
|
792 |
+
"loss": 0.8525,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.14721208963001564,
|
797 |
+
"grad_norm": 1.0542877912521362,
|
798 |
+
"learning_rate": 6.236093793850217e-05,
|
799 |
+
"loss": 0.834,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.1485148514851485,
|
804 |
+
"grad_norm": 0.9843441247940063,
|
805 |
+
"learning_rate": 6.230701183264436e-05,
|
806 |
+
"loss": 0.7711,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.1498176133402814,
|
811 |
+
"grad_norm": 1.0625543594360352,
|
812 |
+
"learning_rate": 6.225256412667207e-05,
|
813 |
+
"loss": 0.8169,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.15112037519541427,
|
818 |
+
"grad_norm": 1.0951343774795532,
|
819 |
+
"learning_rate": 6.219759577337887e-05,
|
820 |
+
"loss": 0.9114,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.15242313705054716,
|
825 |
+
"grad_norm": 1.0442739725112915,
|
826 |
+
"learning_rate": 6.214210773466932e-05,
|
827 |
+
"loss": 0.8038,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.15372589890568003,
|
832 |
+
"grad_norm": 1.0549882650375366,
|
833 |
+
"learning_rate": 6.2086100981542e-05,
|
834 |
+
"loss": 0.8677,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.15502866076081293,
|
839 |
+
"grad_norm": 1.0807327032089233,
|
840 |
+
"learning_rate": 6.202957649407264e-05,
|
841 |
+
"loss": 0.8276,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.1563314226159458,
|
846 |
+
"grad_norm": 1.0784152746200562,
|
847 |
+
"learning_rate": 6.197253526139696e-05,
|
848 |
+
"loss": 0.8823,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.1576341844710787,
|
853 |
+
"grad_norm": 1.076708436012268,
|
854 |
+
"learning_rate": 6.191497828169325e-05,
|
855 |
+
"loss": 0.842,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.15893694632621158,
|
860 |
+
"grad_norm": 1.0658226013183594,
|
861 |
+
"learning_rate": 6.185690656216507e-05,
|
862 |
+
"loss": 0.8626,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.16023970818134445,
|
867 |
+
"grad_norm": 1.064942717552185,
|
868 |
+
"learning_rate": 6.179832111902348e-05,
|
869 |
+
"loss": 0.8735,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.16154247003647734,
|
874 |
+
"grad_norm": 1.0782710313796997,
|
875 |
+
"learning_rate": 6.17392229774693e-05,
|
876 |
+
"loss": 0.828,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.1628452318916102,
|
881 |
+
"grad_norm": 1.0276188850402832,
|
882 |
+
"learning_rate": 6.167961317167528e-05,
|
883 |
+
"loss": 0.8475,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.1641479937467431,
|
888 |
+
"grad_norm": 1.1249077320098877,
|
889 |
+
"learning_rate": 6.161949274476778e-05,
|
890 |
+
"loss": 0.9029,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.16545075560187597,
|
895 |
+
"grad_norm": 1.027971863746643,
|
896 |
+
"learning_rate": 6.155886274880874e-05,
|
897 |
+
"loss": 0.8057,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.16675351745700887,
|
902 |
+
"grad_norm": 1.0177087783813477,
|
903 |
+
"learning_rate": 6.14977242447771e-05,
|
904 |
+
"loss": 0.7928,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.16805627931214173,
|
909 |
+
"grad_norm": 1.0410820245742798,
|
910 |
+
"learning_rate": 6.143607830255037e-05,
|
911 |
+
"loss": 0.8222,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.16935904116727463,
|
916 |
+
"grad_norm": 1.086966872215271,
|
917 |
+
"learning_rate": 6.137392600088579e-05,
|
918 |
+
"loss": 0.837,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.1706618030224075,
|
923 |
+
"grad_norm": 1.099645972251892,
|
924 |
+
"learning_rate": 6.131126842740155e-05,
|
925 |
+
"loss": 0.8604,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.1719645648775404,
|
930 |
+
"grad_norm": 1.0512402057647705,
|
931 |
+
"learning_rate": 6.124810667855768e-05,
|
932 |
+
"loss": 0.8524,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.17326732673267325,
|
937 |
+
"grad_norm": 1.0146111249923706,
|
938 |
+
"learning_rate": 6.118444185963691e-05,
|
939 |
+
"loss": 0.7948,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.17457008858780615,
|
944 |
+
"grad_norm": 1.0564138889312744,
|
945 |
+
"learning_rate": 6.112027508472533e-05,
|
946 |
+
"loss": 0.8393,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.17587285044293904,
|
951 |
+
"grad_norm": 1.1982516050338745,
|
952 |
+
"learning_rate": 6.105560747669284e-05,
|
953 |
+
"loss": 0.8326,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.1771756122980719,
|
958 |
+
"grad_norm": 1.0336800813674927,
|
959 |
+
"learning_rate": 6.0990440167173595e-05,
|
960 |
+
"loss": 0.8456,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.1784783741532048,
|
965 |
+
"grad_norm": 1.0412505865097046,
|
966 |
+
"learning_rate": 6.092477429654611e-05,
|
967 |
+
"loss": 0.8026,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.17978113600833767,
|
972 |
+
"grad_norm": 1.0531303882598877,
|
973 |
+
"learning_rate": 6.085861101391333e-05,
|
974 |
+
"loss": 0.8675,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.18108389786347057,
|
979 |
+
"grad_norm": 1.0367439985275269,
|
980 |
+
"learning_rate": 6.0791951477082555e-05,
|
981 |
+
"loss": 0.8328,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.18238665971860343,
|
986 |
+
"grad_norm": 1.057989478111267,
|
987 |
+
"learning_rate": 6.072479685254518e-05,
|
988 |
+
"loss": 0.8129,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.18368942157373633,
|
993 |
+
"grad_norm": 1.1223191022872925,
|
994 |
+
"learning_rate": 6.065714831545621e-05,
|
995 |
+
"loss": 0.8519,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.1849921834288692,
|
1000 |
+
"grad_norm": 1.0480860471725464,
|
1001 |
+
"learning_rate": 6.058900704961377e-05,
|
1002 |
+
"loss": 0.8478,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.1862949452840021,
|
1007 |
+
"grad_norm": 1.0725680589675903,
|
1008 |
+
"learning_rate": 6.0520374247438375e-05,
|
1009 |
+
"loss": 0.8612,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.18759770713913496,
|
1014 |
+
"grad_norm": 1.0441476106643677,
|
1015 |
+
"learning_rate": 6.045125110995204e-05,
|
1016 |
+
"loss": 0.8521,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.18890046899426785,
|
1021 |
+
"grad_norm": 1.0792895555496216,
|
1022 |
+
"learning_rate": 6.0381638846757264e-05,
|
1023 |
+
"loss": 0.8364,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.19020323084940072,
|
1028 |
+
"grad_norm": 1.0203429460525513,
|
1029 |
+
"learning_rate": 6.03115386760159e-05,
|
1030 |
+
"loss": 0.7973,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.1915059927045336,
|
1035 |
+
"grad_norm": 1.0836308002471924,
|
1036 |
+
"learning_rate": 6.024095182442782e-05,
|
1037 |
+
"loss": 0.8719,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.1928087545596665,
|
1042 |
+
"grad_norm": 1.0394123792648315,
|
1043 |
+
"learning_rate": 6.016987952720939e-05,
|
1044 |
+
"loss": 0.8809,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.19411151641479937,
|
1049 |
+
"grad_norm": 1.0890783071517944,
|
1050 |
+
"learning_rate": 6.0098323028071956e-05,
|
1051 |
+
"loss": 0.8996,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.19541427826993227,
|
1056 |
+
"grad_norm": 1.0037873983383179,
|
1057 |
+
"learning_rate": 6.002628357920002e-05,
|
1058 |
+
"loss": 0.8424,
|
1059 |
+
"step": 150
|
1060 |
+
}
|
1061 |
+
],
|
1062 |
+
"logging_steps": 1,
|
1063 |
+
"max_steps": 767,
|
1064 |
+
"num_input_tokens_seen": 0,
|
1065 |
+
"num_train_epochs": 1,
|
1066 |
+
"save_steps": 50,
|
1067 |
+
"stateful_callbacks": {
|
1068 |
+
"TrainerControl": {
|
1069 |
+
"args": {
|
1070 |
+
"should_epoch_stop": false,
|
1071 |
+
"should_evaluate": false,
|
1072 |
+
"should_log": false,
|
1073 |
+
"should_save": true,
|
1074 |
+
"should_training_stop": false
|
1075 |
+
},
|
1076 |
+
"attributes": {}
|
1077 |
+
}
|
1078 |
+
},
|
1079 |
+
"total_flos": 2.3066812323908813e+17,
|
1080 |
+
"train_batch_size": 6,
|
1081 |
+
"trial_name": null,
|
1082 |
+
"trial_params": null
|
1083 |
+
}
|
checkpoint-150/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c6cdd050f0e9f3e909bcca2e2c0488bdf293a6b22313a332d8541c60d48d06
|
3 |
+
size 5432
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: rinna/llama-3-youko-8b
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": true
|
37 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9568e68b993dc58952ac49c55deaf285bd3f7b60e3b229e942adc11a61c60828
|
3 |
+
size 11849545016
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3c4e40238f7a51b8cb66915f5b0ec217ca2859935e74d3c57d5624359ff139
|
3 |
+
size 2778493596
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9275065a25044785d153dd5dd91f5472b87a85a6b9cfc005f93d96861615f
|
3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c7ac6b5803ddfb7950e5b25096836e1cd17097eaf1b7c69af1d693ab99d323
|
3 |
+
size 1064
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,1433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.26055237102657636,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013027618551328818,
|
13 |
+
"grad_norm": 14.949752807617188,
|
14 |
+
"learning_rate": 4.0625e-06,
|
15 |
+
"loss": 1.3439,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0026055237102657635,
|
20 |
+
"grad_norm": 15.725403785705566,
|
21 |
+
"learning_rate": 8.125e-06,
|
22 |
+
"loss": 1.3354,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0039082855653986455,
|
27 |
+
"grad_norm": 12.41278076171875,
|
28 |
+
"learning_rate": 1.2187499999999998e-05,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.005211047420531527,
|
34 |
+
"grad_norm": 6.782334327697754,
|
35 |
+
"learning_rate": 1.625e-05,
|
36 |
+
"loss": 1.2634,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.006513809275664409,
|
41 |
+
"grad_norm": 3.730219841003418,
|
42 |
+
"learning_rate": 2.03125e-05,
|
43 |
+
"loss": 1.1704,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.007816571130797291,
|
48 |
+
"grad_norm": 2.547757863998413,
|
49 |
+
"learning_rate": 2.4374999999999996e-05,
|
50 |
+
"loss": 1.165,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.009119332985930172,
|
55 |
+
"grad_norm": 2.4353976249694824,
|
56 |
+
"learning_rate": 2.8437499999999997e-05,
|
57 |
+
"loss": 1.1567,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.010422094841063054,
|
62 |
+
"grad_norm": 2.218895673751831,
|
63 |
+
"learning_rate": 3.25e-05,
|
64 |
+
"loss": 1.0846,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.011724856696195935,
|
69 |
+
"grad_norm": 1.7433233261108398,
|
70 |
+
"learning_rate": 3.6562499999999994e-05,
|
71 |
+
"loss": 0.9816,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.013027618551328817,
|
76 |
+
"grad_norm": 1.6148579120635986,
|
77 |
+
"learning_rate": 4.0625e-05,
|
78 |
+
"loss": 1.0869,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0143303804064617,
|
83 |
+
"grad_norm": 1.5065230131149292,
|
84 |
+
"learning_rate": 4.4687499999999995e-05,
|
85 |
+
"loss": 0.9625,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.015633142261594582,
|
90 |
+
"grad_norm": 1.4786823987960815,
|
91 |
+
"learning_rate": 4.874999999999999e-05,
|
92 |
+
"loss": 1.0489,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.016935904116727463,
|
97 |
+
"grad_norm": 1.2991230487823486,
|
98 |
+
"learning_rate": 5.2812499999999996e-05,
|
99 |
+
"loss": 0.9935,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.018238665971860343,
|
104 |
+
"grad_norm": 1.3199464082717896,
|
105 |
+
"learning_rate": 5.687499999999999e-05,
|
106 |
+
"loss": 1.0188,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.019541427826993224,
|
111 |
+
"grad_norm": 1.2793257236480713,
|
112 |
+
"learning_rate": 6.09375e-05,
|
113 |
+
"loss": 1.0265,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.020844189682126108,
|
118 |
+
"grad_norm": 1.2210655212402344,
|
119 |
+
"learning_rate": 6.5e-05,
|
120 |
+
"loss": 0.9019,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02214695153725899,
|
125 |
+
"grad_norm": 1.3837445974349976,
|
126 |
+
"learning_rate": 6.499971563731688e-05,
|
127 |
+
"loss": 0.9487,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02344971339239187,
|
132 |
+
"grad_norm": 1.2946529388427734,
|
133 |
+
"learning_rate": 6.499886255424368e-05,
|
134 |
+
"loss": 1.0031,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.024752475247524754,
|
139 |
+
"grad_norm": 1.3142110109329224,
|
140 |
+
"learning_rate": 6.499744076570868e-05,
|
141 |
+
"loss": 0.9941,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.026055237102657634,
|
146 |
+
"grad_norm": 1.8206599950790405,
|
147 |
+
"learning_rate": 6.499545029659211e-05,
|
148 |
+
"loss": 0.9767,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.027357998957790515,
|
153 |
+
"grad_norm": 1.2736281156539917,
|
154 |
+
"learning_rate": 6.499289118172568e-05,
|
155 |
+
"loss": 0.9194,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0286607608129234,
|
160 |
+
"grad_norm": 1.8105640411376953,
|
161 |
+
"learning_rate": 6.498976346589196e-05,
|
162 |
+
"loss": 0.9853,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02996352266805628,
|
167 |
+
"grad_norm": 1.4621827602386475,
|
168 |
+
"learning_rate": 6.49860672038236e-05,
|
169 |
+
"loss": 0.9896,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.031266284523189164,
|
174 |
+
"grad_norm": 1.212299108505249,
|
175 |
+
"learning_rate": 6.498180246020238e-05,
|
176 |
+
"loss": 0.9684,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.032569046378322045,
|
181 |
+
"grad_norm": 1.2274290323257446,
|
182 |
+
"learning_rate": 6.49769693096581e-05,
|
183 |
+
"loss": 0.9831,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.033871808233454925,
|
188 |
+
"grad_norm": 1.2909352779388428,
|
189 |
+
"learning_rate": 6.49715678367672e-05,
|
190 |
+
"loss": 0.9971,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.035174570088587806,
|
195 |
+
"grad_norm": 1.2330715656280518,
|
196 |
+
"learning_rate": 6.49655981360514e-05,
|
197 |
+
"loss": 0.9923,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03647733194372069,
|
202 |
+
"grad_norm": 1.2433793544769287,
|
203 |
+
"learning_rate": 6.495906031197591e-05,
|
204 |
+
"loss": 0.9121,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03778009379885357,
|
209 |
+
"grad_norm": 1.2374027967453003,
|
210 |
+
"learning_rate": 6.49519544789477e-05,
|
211 |
+
"loss": 0.9224,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03908285565398645,
|
216 |
+
"grad_norm": 1.2204357385635376,
|
217 |
+
"learning_rate": 6.494428076131346e-05,
|
218 |
+
"loss": 0.919,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.040385617509119336,
|
223 |
+
"grad_norm": 1.1927292346954346,
|
224 |
+
"learning_rate": 6.493603929335744e-05,
|
225 |
+
"loss": 0.9589,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.041688379364252216,
|
230 |
+
"grad_norm": 1.1353641748428345,
|
231 |
+
"learning_rate": 6.492723021929908e-05,
|
232 |
+
"loss": 0.8869,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0429911412193851,
|
237 |
+
"grad_norm": 1.212263822555542,
|
238 |
+
"learning_rate": 6.49178536932905e-05,
|
239 |
+
"loss": 0.8934,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.04429390307451798,
|
244 |
+
"grad_norm": 1.0893241167068481,
|
245 |
+
"learning_rate": 6.49079098794138e-05,
|
246 |
+
"loss": 0.8718,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04559666492965086,
|
251 |
+
"grad_norm": 1.1801607608795166,
|
252 |
+
"learning_rate": 6.489739895167818e-05,
|
253 |
+
"loss": 0.9774,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04689942678478374,
|
258 |
+
"grad_norm": 1.1302330493927002,
|
259 |
+
"learning_rate": 6.488632109401691e-05,
|
260 |
+
"loss": 0.9584,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04820218863991663,
|
265 |
+
"grad_norm": 1.1432682275772095,
|
266 |
+
"learning_rate": 6.487467650028411e-05,
|
267 |
+
"loss": 0.9452,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04950495049504951,
|
272 |
+
"grad_norm": 1.1399481296539307,
|
273 |
+
"learning_rate": 6.486246537425133e-05,
|
274 |
+
"loss": 0.9017,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.05080771235018239,
|
279 |
+
"grad_norm": 1.0911235809326172,
|
280 |
+
"learning_rate": 6.484968792960403e-05,
|
281 |
+
"loss": 0.9036,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.05211047420531527,
|
286 |
+
"grad_norm": 1.071078896522522,
|
287 |
+
"learning_rate": 6.48363443899378e-05,
|
288 |
+
"loss": 0.9273,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.05341323606044815,
|
293 |
+
"grad_norm": 1.053589105606079,
|
294 |
+
"learning_rate": 6.482243498875449e-05,
|
295 |
+
"loss": 0.8847,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05471599791558103,
|
300 |
+
"grad_norm": 1.109771490097046,
|
301 |
+
"learning_rate": 6.480795996945806e-05,
|
302 |
+
"loss": 0.9364,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.05601875977071391,
|
307 |
+
"grad_norm": 1.1093286275863647,
|
308 |
+
"learning_rate": 6.479291958535037e-05,
|
309 |
+
"loss": 0.9088,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.0573215216258468,
|
314 |
+
"grad_norm": 1.0716255903244019,
|
315 |
+
"learning_rate": 6.477731409962675e-05,
|
316 |
+
"loss": 0.8885,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.05862428348097968,
|
321 |
+
"grad_norm": 1.1552095413208008,
|
322 |
+
"learning_rate": 6.476114378537138e-05,
|
323 |
+
"loss": 0.9736,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05992704533611256,
|
328 |
+
"grad_norm": 1.1647394895553589,
|
329 |
+
"learning_rate": 6.474440892555249e-05,
|
330 |
+
"loss": 0.9138,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06122980719124544,
|
335 |
+
"grad_norm": 1.1463412046432495,
|
336 |
+
"learning_rate": 6.472710981301745e-05,
|
337 |
+
"loss": 0.9204,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.06253256904637833,
|
342 |
+
"grad_norm": 1.175421118736267,
|
343 |
+
"learning_rate": 6.470924675048762e-05,
|
344 |
+
"loss": 0.9119,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.06383533090151121,
|
349 |
+
"grad_norm": 1.9249529838562012,
|
350 |
+
"learning_rate": 6.469082005055304e-05,
|
351 |
+
"loss": 0.8639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.06513809275664409,
|
356 |
+
"grad_norm": 1.1802655458450317,
|
357 |
+
"learning_rate": 6.467183003566701e-05,
|
358 |
+
"loss": 0.9352,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.06644085461177697,
|
363 |
+
"grad_norm": 1.1035569906234741,
|
364 |
+
"learning_rate": 6.465227703814038e-05,
|
365 |
+
"loss": 0.9342,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.06774361646690985,
|
370 |
+
"grad_norm": 1.1226942539215088,
|
371 |
+
"learning_rate": 6.463216140013581e-05,
|
372 |
+
"loss": 0.8948,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.06904637832204273,
|
377 |
+
"grad_norm": 1.1143085956573486,
|
378 |
+
"learning_rate": 6.46114834736617e-05,
|
379 |
+
"loss": 0.9577,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.07034914017717561,
|
384 |
+
"grad_norm": 1.1214665174484253,
|
385 |
+
"learning_rate": 6.459024362056608e-05,
|
386 |
+
"loss": 0.9106,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.07165190203230849,
|
391 |
+
"grad_norm": 1.1105942726135254,
|
392 |
+
"learning_rate": 6.45684422125303e-05,
|
393 |
+
"loss": 0.8706,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.07295466388744137,
|
398 |
+
"grad_norm": 1.0562191009521484,
|
399 |
+
"learning_rate": 6.454607963106247e-05,
|
400 |
+
"loss": 0.8278,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.07425742574257425,
|
405 |
+
"grad_norm": 1.1298907995224,
|
406 |
+
"learning_rate": 6.452315626749081e-05,
|
407 |
+
"loss": 0.8883,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.07556018759770713,
|
412 |
+
"grad_norm": 1.133426547050476,
|
413 |
+
"learning_rate": 6.449967252295682e-05,
|
414 |
+
"loss": 0.8868,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.07686294945284002,
|
419 |
+
"grad_norm": 1.09175443649292,
|
420 |
+
"learning_rate": 6.447562880840822e-05,
|
421 |
+
"loss": 0.8486,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.0781657113079729,
|
426 |
+
"grad_norm": 1.1153368949890137,
|
427 |
+
"learning_rate": 6.44510255445918e-05,
|
428 |
+
"loss": 0.9278,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.07946847316310579,
|
433 |
+
"grad_norm": 1.102013349533081,
|
434 |
+
"learning_rate": 6.442586316204601e-05,
|
435 |
+
"loss": 0.8362,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.08077123501823867,
|
440 |
+
"grad_norm": 1.1041877269744873,
|
441 |
+
"learning_rate": 6.44001421010935e-05,
|
442 |
+
"loss": 0.8746,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.08207399687337155,
|
447 |
+
"grad_norm": 1.075576901435852,
|
448 |
+
"learning_rate": 6.437386281183331e-05,
|
449 |
+
"loss": 0.8567,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.08337675872850443,
|
454 |
+
"grad_norm": 1.1472443342208862,
|
455 |
+
"learning_rate": 6.43470257541331e-05,
|
456 |
+
"loss": 0.9023,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.08467952058363731,
|
461 |
+
"grad_norm": 1.1024972200393677,
|
462 |
+
"learning_rate": 6.431963139762104e-05,
|
463 |
+
"loss": 0.8982,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.0859822824387702,
|
468 |
+
"grad_norm": 1.1128768920898438,
|
469 |
+
"learning_rate": 6.42916802216776e-05,
|
470 |
+
"loss": 0.883,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.08728504429390307,
|
475 |
+
"grad_norm": 1.058384895324707,
|
476 |
+
"learning_rate": 6.426317271542717e-05,
|
477 |
+
"loss": 0.8428,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.08858780614903596,
|
482 |
+
"grad_norm": 1.0728991031646729,
|
483 |
+
"learning_rate": 6.423410937772951e-05,
|
484 |
+
"loss": 0.8553,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.08989056800416884,
|
489 |
+
"grad_norm": 1.0956963300704956,
|
490 |
+
"learning_rate": 6.4204490717171e-05,
|
491 |
+
"loss": 0.8894,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.09119332985930172,
|
496 |
+
"grad_norm": 1.0787287950515747,
|
497 |
+
"learning_rate": 6.417431725205575e-05,
|
498 |
+
"loss": 0.9086,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.0924960917144346,
|
503 |
+
"grad_norm": 1.1435580253601074,
|
504 |
+
"learning_rate": 6.414358951039651e-05,
|
505 |
+
"loss": 0.9074,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.09379885356956748,
|
510 |
+
"grad_norm": 1.0396053791046143,
|
511 |
+
"learning_rate": 6.41123080299055e-05,
|
512 |
+
"loss": 0.8553,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.09510161542470036,
|
517 |
+
"grad_norm": 1.0929105281829834,
|
518 |
+
"learning_rate": 6.40804733579849e-05,
|
519 |
+
"loss": 0.8504,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.09640437727983325,
|
524 |
+
"grad_norm": 1.1395248174667358,
|
525 |
+
"learning_rate": 6.404808605171734e-05,
|
526 |
+
"loss": 0.9222,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.09770713913496613,
|
531 |
+
"grad_norm": 1.0281647443771362,
|
532 |
+
"learning_rate": 6.401514667785613e-05,
|
533 |
+
"loss": 0.868,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.09900990099009901,
|
538 |
+
"grad_norm": 1.0565054416656494,
|
539 |
+
"learning_rate": 6.398165581281536e-05,
|
540 |
+
"loss": 0.8302,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.1003126628452319,
|
545 |
+
"grad_norm": 1.0529290437698364,
|
546 |
+
"learning_rate": 6.394761404265977e-05,
|
547 |
+
"loss": 0.8669,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.10161542470036478,
|
552 |
+
"grad_norm": 1.0579882860183716,
|
553 |
+
"learning_rate": 6.391302196309452e-05,
|
554 |
+
"loss": 0.9204,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.10291818655549766,
|
559 |
+
"grad_norm": 1.0531302690505981,
|
560 |
+
"learning_rate": 6.387788017945482e-05,
|
561 |
+
"loss": 0.9202,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.10422094841063054,
|
566 |
+
"grad_norm": 1.0358260869979858,
|
567 |
+
"learning_rate": 6.384218930669521e-05,
|
568 |
+
"loss": 0.8647,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.10552371026576342,
|
573 |
+
"grad_norm": 1.0599216222763062,
|
574 |
+
"learning_rate": 6.380594996937895e-05,
|
575 |
+
"loss": 0.9093,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.1068264721208963,
|
580 |
+
"grad_norm": 1.2026344537734985,
|
581 |
+
"learning_rate": 6.376916280166696e-05,
|
582 |
+
"loss": 0.8731,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.10812923397602918,
|
587 |
+
"grad_norm": 1.1054397821426392,
|
588 |
+
"learning_rate": 6.373182844730677e-05,
|
589 |
+
"loss": 0.8835,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.10943199583116206,
|
594 |
+
"grad_norm": 1.030562162399292,
|
595 |
+
"learning_rate": 6.369394755962129e-05,
|
596 |
+
"loss": 0.8432,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.11073475768629494,
|
601 |
+
"grad_norm": 1.0522128343582153,
|
602 |
+
"learning_rate": 6.365552080149737e-05,
|
603 |
+
"loss": 0.8598,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.11203751954142782,
|
608 |
+
"grad_norm": 1.0692416429519653,
|
609 |
+
"learning_rate": 6.361654884537413e-05,
|
610 |
+
"loss": 0.8812,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.1133402813965607,
|
615 |
+
"grad_norm": 1.1009373664855957,
|
616 |
+
"learning_rate": 6.357703237323127e-05,
|
617 |
+
"loss": 0.8635,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.1146430432516936,
|
622 |
+
"grad_norm": 1.1628373861312866,
|
623 |
+
"learning_rate": 6.353697207657708e-05,
|
624 |
+
"loss": 0.8907,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.11594580510682648,
|
629 |
+
"grad_norm": 1.1273458003997803,
|
630 |
+
"learning_rate": 6.349636865643642e-05,
|
631 |
+
"loss": 0.8445,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.11724856696195936,
|
636 |
+
"grad_norm": 1.0971312522888184,
|
637 |
+
"learning_rate": 6.345522282333835e-05,
|
638 |
+
"loss": 0.8543,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.11855132881709224,
|
643 |
+
"grad_norm": 1.0826351642608643,
|
644 |
+
"learning_rate": 6.341353529730374e-05,
|
645 |
+
"loss": 0.8605,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.11985409067222512,
|
650 |
+
"grad_norm": 1.0686413049697876,
|
651 |
+
"learning_rate": 6.337130680783273e-05,
|
652 |
+
"loss": 0.8814,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.121156852527358,
|
657 |
+
"grad_norm": 1.21683931350708,
|
658 |
+
"learning_rate": 6.332853809389189e-05,
|
659 |
+
"loss": 0.8979,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.12245961438249088,
|
664 |
+
"grad_norm": 1.0884461402893066,
|
665 |
+
"learning_rate": 6.328522990390126e-05,
|
666 |
+
"loss": 0.8577,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.12376237623762376,
|
671 |
+
"grad_norm": 1.047310709953308,
|
672 |
+
"learning_rate": 6.324138299572135e-05,
|
673 |
+
"loss": 0.8174,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.12506513809275666,
|
678 |
+
"grad_norm": 1.087296485900879,
|
679 |
+
"learning_rate": 6.319699813663982e-05,
|
680 |
+
"loss": 0.8566,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.12636789994788952,
|
685 |
+
"grad_norm": 1.070327639579773,
|
686 |
+
"learning_rate": 6.315207610335808e-05,
|
687 |
+
"loss": 0.8615,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.12767066180302242,
|
692 |
+
"grad_norm": 1.0299792289733887,
|
693 |
+
"learning_rate": 6.310661768197764e-05,
|
694 |
+
"loss": 0.866,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.12897342365815528,
|
699 |
+
"grad_norm": 1.1011384725570679,
|
700 |
+
"learning_rate": 6.306062366798642e-05,
|
701 |
+
"loss": 0.8775,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.13027618551328818,
|
706 |
+
"grad_norm": 1.0193467140197754,
|
707 |
+
"learning_rate": 6.301409486624481e-05,
|
708 |
+
"loss": 0.8243,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.13157894736842105,
|
713 |
+
"grad_norm": 1.0899205207824707,
|
714 |
+
"learning_rate": 6.296703209097159e-05,
|
715 |
+
"loss": 0.8849,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.13288170922355394,
|
720 |
+
"grad_norm": 1.0473856925964355,
|
721 |
+
"learning_rate": 6.291943616572962e-05,
|
722 |
+
"loss": 0.8847,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.1341844710786868,
|
727 |
+
"grad_norm": 0.9922148585319519,
|
728 |
+
"learning_rate": 6.287130792341154e-05,
|
729 |
+
"loss": 0.8157,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.1354872329338197,
|
734 |
+
"grad_norm": 1.0680872201919556,
|
735 |
+
"learning_rate": 6.282264820622511e-05,
|
736 |
+
"loss": 0.8802,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.13678999478895257,
|
741 |
+
"grad_norm": 1.034562587738037,
|
742 |
+
"learning_rate": 6.27734578656785e-05,
|
743 |
+
"loss": 0.8826,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.13809275664408546,
|
748 |
+
"grad_norm": 1.0247395038604736,
|
749 |
+
"learning_rate": 6.272373776256536e-05,
|
750 |
+
"loss": 0.8535,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.13939551849921833,
|
755 |
+
"grad_norm": 1.099061131477356,
|
756 |
+
"learning_rate": 6.267348876694983e-05,
|
757 |
+
"loss": 0.8583,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.14069828035435122,
|
762 |
+
"grad_norm": 1.0081039667129517,
|
763 |
+
"learning_rate": 6.262271175815126e-05,
|
764 |
+
"loss": 0.7988,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.14200104220948412,
|
769 |
+
"grad_norm": 1.1140209436416626,
|
770 |
+
"learning_rate": 6.257140762472879e-05,
|
771 |
+
"loss": 0.8426,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.14330380406461699,
|
776 |
+
"grad_norm": 1.0654839277267456,
|
777 |
+
"learning_rate": 6.251957726446589e-05,
|
778 |
+
"loss": 0.8682,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.14460656591974988,
|
783 |
+
"grad_norm": 1.0632318258285522,
|
784 |
+
"learning_rate": 6.246722158435455e-05,
|
785 |
+
"loss": 0.8379,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.14590932777488275,
|
790 |
+
"grad_norm": 1.0444918870925903,
|
791 |
+
"learning_rate": 6.241434150057953e-05,
|
792 |
+
"loss": 0.8525,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.14721208963001564,
|
797 |
+
"grad_norm": 1.0542877912521362,
|
798 |
+
"learning_rate": 6.236093793850217e-05,
|
799 |
+
"loss": 0.834,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.1485148514851485,
|
804 |
+
"grad_norm": 0.9843441247940063,
|
805 |
+
"learning_rate": 6.230701183264436e-05,
|
806 |
+
"loss": 0.7711,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.1498176133402814,
|
811 |
+
"grad_norm": 1.0625543594360352,
|
812 |
+
"learning_rate": 6.225256412667207e-05,
|
813 |
+
"loss": 0.8169,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.15112037519541427,
|
818 |
+
"grad_norm": 1.0951343774795532,
|
819 |
+
"learning_rate": 6.219759577337887e-05,
|
820 |
+
"loss": 0.9114,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.15242313705054716,
|
825 |
+
"grad_norm": 1.0442739725112915,
|
826 |
+
"learning_rate": 6.214210773466932e-05,
|
827 |
+
"loss": 0.8038,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.15372589890568003,
|
832 |
+
"grad_norm": 1.0549882650375366,
|
833 |
+
"learning_rate": 6.2086100981542e-05,
|
834 |
+
"loss": 0.8677,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.15502866076081293,
|
839 |
+
"grad_norm": 1.0807327032089233,
|
840 |
+
"learning_rate": 6.202957649407264e-05,
|
841 |
+
"loss": 0.8276,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.1563314226159458,
|
846 |
+
"grad_norm": 1.0784152746200562,
|
847 |
+
"learning_rate": 6.197253526139696e-05,
|
848 |
+
"loss": 0.8823,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.1576341844710787,
|
853 |
+
"grad_norm": 1.076708436012268,
|
854 |
+
"learning_rate": 6.191497828169325e-05,
|
855 |
+
"loss": 0.842,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.15893694632621158,
|
860 |
+
"grad_norm": 1.0658226013183594,
|
861 |
+
"learning_rate": 6.185690656216507e-05,
|
862 |
+
"loss": 0.8626,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.16023970818134445,
|
867 |
+
"grad_norm": 1.064942717552185,
|
868 |
+
"learning_rate": 6.179832111902348e-05,
|
869 |
+
"loss": 0.8735,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.16154247003647734,
|
874 |
+
"grad_norm": 1.0782710313796997,
|
875 |
+
"learning_rate": 6.17392229774693e-05,
|
876 |
+
"loss": 0.828,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.1628452318916102,
|
881 |
+
"grad_norm": 1.0276188850402832,
|
882 |
+
"learning_rate": 6.167961317167528e-05,
|
883 |
+
"loss": 0.8475,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.1641479937467431,
|
888 |
+
"grad_norm": 1.1249077320098877,
|
889 |
+
"learning_rate": 6.161949274476778e-05,
|
890 |
+
"loss": 0.9029,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.16545075560187597,
|
895 |
+
"grad_norm": 1.027971863746643,
|
896 |
+
"learning_rate": 6.155886274880874e-05,
|
897 |
+
"loss": 0.8057,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.16675351745700887,
|
902 |
+
"grad_norm": 1.0177087783813477,
|
903 |
+
"learning_rate": 6.14977242447771e-05,
|
904 |
+
"loss": 0.7928,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.16805627931214173,
|
909 |
+
"grad_norm": 1.0410820245742798,
|
910 |
+
"learning_rate": 6.143607830255037e-05,
|
911 |
+
"loss": 0.8222,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.16935904116727463,
|
916 |
+
"grad_norm": 1.086966872215271,
|
917 |
+
"learning_rate": 6.137392600088579e-05,
|
918 |
+
"loss": 0.837,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.1706618030224075,
|
923 |
+
"grad_norm": 1.099645972251892,
|
924 |
+
"learning_rate": 6.131126842740155e-05,
|
925 |
+
"loss": 0.8604,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.1719645648775404,
|
930 |
+
"grad_norm": 1.0512402057647705,
|
931 |
+
"learning_rate": 6.124810667855768e-05,
|
932 |
+
"loss": 0.8524,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.17326732673267325,
|
937 |
+
"grad_norm": 1.0146111249923706,
|
938 |
+
"learning_rate": 6.118444185963691e-05,
|
939 |
+
"loss": 0.7948,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.17457008858780615,
|
944 |
+
"grad_norm": 1.0564138889312744,
|
945 |
+
"learning_rate": 6.112027508472533e-05,
|
946 |
+
"loss": 0.8393,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.17587285044293904,
|
951 |
+
"grad_norm": 1.1982516050338745,
|
952 |
+
"learning_rate": 6.105560747669284e-05,
|
953 |
+
"loss": 0.8326,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.1771756122980719,
|
958 |
+
"grad_norm": 1.0336800813674927,
|
959 |
+
"learning_rate": 6.0990440167173595e-05,
|
960 |
+
"loss": 0.8456,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.1784783741532048,
|
965 |
+
"grad_norm": 1.0412505865097046,
|
966 |
+
"learning_rate": 6.092477429654611e-05,
|
967 |
+
"loss": 0.8026,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.17978113600833767,
|
972 |
+
"grad_norm": 1.0531303882598877,
|
973 |
+
"learning_rate": 6.085861101391333e-05,
|
974 |
+
"loss": 0.8675,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.18108389786347057,
|
979 |
+
"grad_norm": 1.0367439985275269,
|
980 |
+
"learning_rate": 6.0791951477082555e-05,
|
981 |
+
"loss": 0.8328,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.18238665971860343,
|
986 |
+
"grad_norm": 1.057989478111267,
|
987 |
+
"learning_rate": 6.072479685254518e-05,
|
988 |
+
"loss": 0.8129,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.18368942157373633,
|
993 |
+
"grad_norm": 1.1223191022872925,
|
994 |
+
"learning_rate": 6.065714831545621e-05,
|
995 |
+
"loss": 0.8519,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.1849921834288692,
|
1000 |
+
"grad_norm": 1.0480860471725464,
|
1001 |
+
"learning_rate": 6.058900704961377e-05,
|
1002 |
+
"loss": 0.8478,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.1862949452840021,
|
1007 |
+
"grad_norm": 1.0725680589675903,
|
1008 |
+
"learning_rate": 6.0520374247438375e-05,
|
1009 |
+
"loss": 0.8612,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.18759770713913496,
|
1014 |
+
"grad_norm": 1.0441476106643677,
|
1015 |
+
"learning_rate": 6.045125110995204e-05,
|
1016 |
+
"loss": 0.8521,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.18890046899426785,
|
1021 |
+
"grad_norm": 1.0792895555496216,
|
1022 |
+
"learning_rate": 6.0381638846757264e-05,
|
1023 |
+
"loss": 0.8364,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.19020323084940072,
|
1028 |
+
"grad_norm": 1.0203429460525513,
|
1029 |
+
"learning_rate": 6.03115386760159e-05,
|
1030 |
+
"loss": 0.7973,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.1915059927045336,
|
1035 |
+
"grad_norm": 1.0836308002471924,
|
1036 |
+
"learning_rate": 6.024095182442782e-05,
|
1037 |
+
"loss": 0.8719,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.1928087545596665,
|
1042 |
+
"grad_norm": 1.0394123792648315,
|
1043 |
+
"learning_rate": 6.016987952720939e-05,
|
1044 |
+
"loss": 0.8809,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.19411151641479937,
|
1049 |
+
"grad_norm": 1.0890783071517944,
|
1050 |
+
"learning_rate": 6.0098323028071956e-05,
|
1051 |
+
"loss": 0.8996,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.19541427826993227,
|
1056 |
+
"grad_norm": 1.0037873983383179,
|
1057 |
+
"learning_rate": 6.002628357920002e-05,
|
1058 |
+
"loss": 0.8424,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.19671704012506513,
|
1063 |
+
"grad_norm": 1.0470969676971436,
|
1064 |
+
"learning_rate": 5.995376244122935e-05,
|
1065 |
+
"loss": 0.8019,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.19801980198019803,
|
1070 |
+
"grad_norm": 1.0230716466903687,
|
1071 |
+
"learning_rate": 5.988076088322486e-05,
|
1072 |
+
"loss": 0.7927,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.1993225638353309,
|
1077 |
+
"grad_norm": 1.0318727493286133,
|
1078 |
+
"learning_rate": 5.980728018265849e-05,
|
1079 |
+
"loss": 0.803,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.2006253256904638,
|
1084 |
+
"grad_norm": 1.0479062795639038,
|
1085 |
+
"learning_rate": 5.9733321625386824e-05,
|
1086 |
+
"loss": 0.8597,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.20192808754559666,
|
1091 |
+
"grad_norm": 1.025315761566162,
|
1092 |
+
"learning_rate": 5.965888650562853e-05,
|
1093 |
+
"loss": 0.7937,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.20323084940072955,
|
1098 |
+
"grad_norm": 1.0599974393844604,
|
1099 |
+
"learning_rate": 5.958397612594182e-05,
|
1100 |
+
"loss": 0.8628,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.20453361125586242,
|
1105 |
+
"grad_norm": 1.0344469547271729,
|
1106 |
+
"learning_rate": 5.950859179720152e-05,
|
1107 |
+
"loss": 0.8436,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.2058363731109953,
|
1112 |
+
"grad_norm": 1.1034519672393799,
|
1113 |
+
"learning_rate": 5.943273483857627e-05,
|
1114 |
+
"loss": 0.8124,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.20713913496612818,
|
1119 |
+
"grad_norm": 1.0487233400344849,
|
1120 |
+
"learning_rate": 5.935640657750534e-05,
|
1121 |
+
"loss": 0.8337,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.20844189682126107,
|
1126 |
+
"grad_norm": 1.0436427593231201,
|
1127 |
+
"learning_rate": 5.9279608349675444e-05,
|
1128 |
+
"loss": 0.8438,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.20974465867639394,
|
1133 |
+
"grad_norm": 1.0612242221832275,
|
1134 |
+
"learning_rate": 5.920234149899736e-05,
|
1135 |
+
"loss": 0.8735,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.21104742053152684,
|
1140 |
+
"grad_norm": 1.168532371520996,
|
1141 |
+
"learning_rate": 5.912460737758241e-05,
|
1142 |
+
"loss": 0.8422,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.21235018238665973,
|
1147 |
+
"grad_norm": 1.0675426721572876,
|
1148 |
+
"learning_rate": 5.9046407345718805e-05,
|
1149 |
+
"loss": 0.8631,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.2136529442417926,
|
1154 |
+
"grad_norm": 1.048614501953125,
|
1155 |
+
"learning_rate": 5.8967742771847826e-05,
|
1156 |
+
"loss": 0.8473,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.2149557060969255,
|
1161 |
+
"grad_norm": 1.0362776517868042,
|
1162 |
+
"learning_rate": 5.888861503253989e-05,
|
1163 |
+
"loss": 0.8888,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.21625846795205836,
|
1168 |
+
"grad_norm": 0.9976462721824646,
|
1169 |
+
"learning_rate": 5.8809025512470445e-05,
|
1170 |
+
"loss": 0.8079,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.21756122980719125,
|
1175 |
+
"grad_norm": 1.0061395168304443,
|
1176 |
+
"learning_rate": 5.87289756043958e-05,
|
1177 |
+
"loss": 0.7954,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.21886399166232412,
|
1182 |
+
"grad_norm": 1.0533777475357056,
|
1183 |
+
"learning_rate": 5.864846670912864e-05,
|
1184 |
+
"loss": 0.8089,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.22016675351745701,
|
1189 |
+
"grad_norm": 0.9939700365066528,
|
1190 |
+
"learning_rate": 5.856750023551361e-05,
|
1191 |
+
"loss": 0.8176,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.22146951537258988,
|
1196 |
+
"grad_norm": 1.0513004064559937,
|
1197 |
+
"learning_rate": 5.848607760040267e-05,
|
1198 |
+
"loss": 0.8602,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.22277227722772278,
|
1203 |
+
"grad_norm": 1.055511713027954,
|
1204 |
+
"learning_rate": 5.840420022863016e-05,
|
1205 |
+
"loss": 0.8511,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.22407503908285564,
|
1210 |
+
"grad_norm": 1.0215332508087158,
|
1211 |
+
"learning_rate": 5.832186955298808e-05,
|
1212 |
+
"loss": 0.8233,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.22537780093798854,
|
1217 |
+
"grad_norm": 1.018233299255371,
|
1218 |
+
"learning_rate": 5.8239087014200806e-05,
|
1219 |
+
"loss": 0.8354,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.2266805627931214,
|
1224 |
+
"grad_norm": 1.0055863857269287,
|
1225 |
+
"learning_rate": 5.815585406090005e-05,
|
1226 |
+
"loss": 0.8488,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.2279833246482543,
|
1231 |
+
"grad_norm": 1.008152961730957,
|
1232 |
+
"learning_rate": 5.8072172149599394e-05,
|
1233 |
+
"loss": 0.7623,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.2292860865033872,
|
1238 |
+
"grad_norm": 1.0418919324874878,
|
1239 |
+
"learning_rate": 5.7988042744668856e-05,
|
1240 |
+
"loss": 0.8109,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.23058884835852006,
|
1245 |
+
"grad_norm": 1.0832551717758179,
|
1246 |
+
"learning_rate": 5.790346731830927e-05,
|
1247 |
+
"loss": 0.8951,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.23189161021365295,
|
1252 |
+
"grad_norm": 1.0513347387313843,
|
1253 |
+
"learning_rate": 5.7818447350526476e-05,
|
1254 |
+
"loss": 0.8598,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.23319437206878582,
|
1259 |
+
"grad_norm": 0.9888846278190613,
|
1260 |
+
"learning_rate": 5.7732984329105484e-05,
|
1261 |
+
"loss": 0.746,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.23449713392391872,
|
1266 |
+
"grad_norm": 1.0668085813522339,
|
1267 |
+
"learning_rate": 5.764707974958437e-05,
|
1268 |
+
"loss": 0.8039,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.23579989577905158,
|
1273 |
+
"grad_norm": 1.0392318964004517,
|
1274 |
+
"learning_rate": 5.7560735115228195e-05,
|
1275 |
+
"loss": 0.8155,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.23710265763418448,
|
1280 |
+
"grad_norm": 1.052474021911621,
|
1281 |
+
"learning_rate": 5.7473951937002576e-05,
|
1282 |
+
"loss": 0.8215,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.23840541948931734,
|
1287 |
+
"grad_norm": 1.067699670791626,
|
1288 |
+
"learning_rate": 5.738673173354739e-05,
|
1289 |
+
"loss": 0.8259,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.23970818134445024,
|
1294 |
+
"grad_norm": 1.042398452758789,
|
1295 |
+
"learning_rate": 5.729907603115005e-05,
|
1296 |
+
"loss": 0.8086,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.2410109431995831,
|
1301 |
+
"grad_norm": 1.0346574783325195,
|
1302 |
+
"learning_rate": 5.721098636371894e-05,
|
1303 |
+
"loss": 0.8184,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.242313705054716,
|
1308 |
+
"grad_norm": 1.0383342504501343,
|
1309 |
+
"learning_rate": 5.712246427275646e-05,
|
1310 |
+
"loss": 0.8543,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.24361646690984887,
|
1315 |
+
"grad_norm": 1.0456079244613647,
|
1316 |
+
"learning_rate": 5.703351130733211e-05,
|
1317 |
+
"loss": 0.8244,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.24491922876498176,
|
1322 |
+
"grad_norm": 0.9899833798408508,
|
1323 |
+
"learning_rate": 5.694412902405535e-05,
|
1324 |
+
"loss": 0.7916,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.24622199062011466,
|
1329 |
+
"grad_norm": 1.1231224536895752,
|
1330 |
+
"learning_rate": 5.685431898704839e-05,
|
1331 |
+
"loss": 0.7904,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.24752475247524752,
|
1336 |
+
"grad_norm": 1.0400362014770508,
|
1337 |
+
"learning_rate": 5.676408276791882e-05,
|
1338 |
+
"loss": 0.845,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.24882751433038042,
|
1343 |
+
"grad_norm": 1.0910183191299438,
|
1344 |
+
"learning_rate": 5.6673421945732075e-05,
|
1345 |
+
"loss": 0.8293,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.2501302761855133,
|
1350 |
+
"grad_norm": 1.0755969285964966,
|
1351 |
+
"learning_rate": 5.658233810698381e-05,
|
1352 |
+
"loss": 0.83,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.25143303804064615,
|
1357 |
+
"grad_norm": 1.0231711864471436,
|
1358 |
+
"learning_rate": 5.649083284557219e-05,
|
1359 |
+
"loss": 0.8442,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.25273579989577905,
|
1364 |
+
"grad_norm": 1.0368572473526,
|
1365 |
+
"learning_rate": 5.639890776276991e-05,
|
1366 |
+
"loss": 0.8574,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.25403856175091194,
|
1371 |
+
"grad_norm": 1.0136909484863281,
|
1372 |
+
"learning_rate": 5.630656446719626e-05,
|
1373 |
+
"loss": 0.8151,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.25534132360604483,
|
1378 |
+
"grad_norm": 1.0600650310516357,
|
1379 |
+
"learning_rate": 5.621380457478889e-05,
|
1380 |
+
"loss": 0.7792,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.2566440854611777,
|
1385 |
+
"grad_norm": 1.0362857580184937,
|
1386 |
+
"learning_rate": 5.612062970877565e-05,
|
1387 |
+
"loss": 0.8246,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.25794684731631057,
|
1392 |
+
"grad_norm": 1.0172935724258423,
|
1393 |
+
"learning_rate": 5.602704149964604e-05,
|
1394 |
+
"loss": 0.8196,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.25924960917144346,
|
1399 |
+
"grad_norm": 1.0049176216125488,
|
1400 |
+
"learning_rate": 5.5933041585122805e-05,
|
1401 |
+
"loss": 0.8229,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.26055237102657636,
|
1406 |
+
"grad_norm": 1.0751328468322754,
|
1407 |
+
"learning_rate": 5.5838631610133196e-05,
|
1408 |
+
"loss": 0.8456,
|
1409 |
+
"step": 200
|
1410 |
+
}
|
1411 |
+
],
|
1412 |
+
"logging_steps": 1,
|
1413 |
+
"max_steps": 767,
|
1414 |
+
"num_input_tokens_seen": 0,
|
1415 |
+
"num_train_epochs": 1,
|
1416 |
+
"save_steps": 50,
|
1417 |
+
"stateful_callbacks": {
|
1418 |
+
"TrainerControl": {
|
1419 |
+
"args": {
|
1420 |
+
"should_epoch_stop": false,
|
1421 |
+
"should_evaluate": false,
|
1422 |
+
"should_log": false,
|
1423 |
+
"should_save": true,
|
1424 |
+
"should_training_stop": false
|
1425 |
+
},
|
1426 |
+
"attributes": {}
|
1427 |
+
}
|
1428 |
+
},
|
1429 |
+
"total_flos": 3.075293883527332e+17,
|
1430 |
+
"train_batch_size": 6,
|
1431 |
+
"trial_name": null,
|
1432 |
+
"trial_params": null
|
1433 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c6cdd050f0e9f3e909bcca2e2c0488bdf293a6b22313a332d8541c60d48d06
|
3 |
+
size 5432
|
checkpoint-250/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: rinna/llama-3-youko-8b
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-250/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": true
|
37 |
+
}
|
checkpoint-250/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:336c3b39281dff8eabf6d02121a0c0b25690f7a46b3e7215768e08374571fa26
|
3 |
+
size 11849545016
|
checkpoint-250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8a5c59f3746f6c590fa748b282de3739be863c5b8711a96855de88ad726d589
|
3 |
+
size 2778493596
|
checkpoint-250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9275065a25044785d153dd5dd91f5472b87a85a6b9cfc005f93d96861615f
|
3 |
+
size 14244
|
checkpoint-250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dae0fdde9047b87fc6b00649f690350db14657ad1566f1005c7754106e0f1325
|
3 |
+
size 1064
|
checkpoint-250/trainer_state.json
ADDED
@@ -0,0 +1,1783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3256904637832204,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013027618551328818,
|
13 |
+
"grad_norm": 14.949752807617188,
|
14 |
+
"learning_rate": 4.0625e-06,
|
15 |
+
"loss": 1.3439,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0026055237102657635,
|
20 |
+
"grad_norm": 15.725403785705566,
|
21 |
+
"learning_rate": 8.125e-06,
|
22 |
+
"loss": 1.3354,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0039082855653986455,
|
27 |
+
"grad_norm": 12.41278076171875,
|
28 |
+
"learning_rate": 1.2187499999999998e-05,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.005211047420531527,
|
34 |
+
"grad_norm": 6.782334327697754,
|
35 |
+
"learning_rate": 1.625e-05,
|
36 |
+
"loss": 1.2634,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.006513809275664409,
|
41 |
+
"grad_norm": 3.730219841003418,
|
42 |
+
"learning_rate": 2.03125e-05,
|
43 |
+
"loss": 1.1704,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.007816571130797291,
|
48 |
+
"grad_norm": 2.547757863998413,
|
49 |
+
"learning_rate": 2.4374999999999996e-05,
|
50 |
+
"loss": 1.165,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.009119332985930172,
|
55 |
+
"grad_norm": 2.4353976249694824,
|
56 |
+
"learning_rate": 2.8437499999999997e-05,
|
57 |
+
"loss": 1.1567,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.010422094841063054,
|
62 |
+
"grad_norm": 2.218895673751831,
|
63 |
+
"learning_rate": 3.25e-05,
|
64 |
+
"loss": 1.0846,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.011724856696195935,
|
69 |
+
"grad_norm": 1.7433233261108398,
|
70 |
+
"learning_rate": 3.6562499999999994e-05,
|
71 |
+
"loss": 0.9816,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.013027618551328817,
|
76 |
+
"grad_norm": 1.6148579120635986,
|
77 |
+
"learning_rate": 4.0625e-05,
|
78 |
+
"loss": 1.0869,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0143303804064617,
|
83 |
+
"grad_norm": 1.5065230131149292,
|
84 |
+
"learning_rate": 4.4687499999999995e-05,
|
85 |
+
"loss": 0.9625,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.015633142261594582,
|
90 |
+
"grad_norm": 1.4786823987960815,
|
91 |
+
"learning_rate": 4.874999999999999e-05,
|
92 |
+
"loss": 1.0489,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.016935904116727463,
|
97 |
+
"grad_norm": 1.2991230487823486,
|
98 |
+
"learning_rate": 5.2812499999999996e-05,
|
99 |
+
"loss": 0.9935,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.018238665971860343,
|
104 |
+
"grad_norm": 1.3199464082717896,
|
105 |
+
"learning_rate": 5.687499999999999e-05,
|
106 |
+
"loss": 1.0188,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.019541427826993224,
|
111 |
+
"grad_norm": 1.2793257236480713,
|
112 |
+
"learning_rate": 6.09375e-05,
|
113 |
+
"loss": 1.0265,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.020844189682126108,
|
118 |
+
"grad_norm": 1.2210655212402344,
|
119 |
+
"learning_rate": 6.5e-05,
|
120 |
+
"loss": 0.9019,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02214695153725899,
|
125 |
+
"grad_norm": 1.3837445974349976,
|
126 |
+
"learning_rate": 6.499971563731688e-05,
|
127 |
+
"loss": 0.9487,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02344971339239187,
|
132 |
+
"grad_norm": 1.2946529388427734,
|
133 |
+
"learning_rate": 6.499886255424368e-05,
|
134 |
+
"loss": 1.0031,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.024752475247524754,
|
139 |
+
"grad_norm": 1.3142110109329224,
|
140 |
+
"learning_rate": 6.499744076570868e-05,
|
141 |
+
"loss": 0.9941,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.026055237102657634,
|
146 |
+
"grad_norm": 1.8206599950790405,
|
147 |
+
"learning_rate": 6.499545029659211e-05,
|
148 |
+
"loss": 0.9767,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.027357998957790515,
|
153 |
+
"grad_norm": 1.2736281156539917,
|
154 |
+
"learning_rate": 6.499289118172568e-05,
|
155 |
+
"loss": 0.9194,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0286607608129234,
|
160 |
+
"grad_norm": 1.8105640411376953,
|
161 |
+
"learning_rate": 6.498976346589196e-05,
|
162 |
+
"loss": 0.9853,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02996352266805628,
|
167 |
+
"grad_norm": 1.4621827602386475,
|
168 |
+
"learning_rate": 6.49860672038236e-05,
|
169 |
+
"loss": 0.9896,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.031266284523189164,
|
174 |
+
"grad_norm": 1.212299108505249,
|
175 |
+
"learning_rate": 6.498180246020238e-05,
|
176 |
+
"loss": 0.9684,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.032569046378322045,
|
181 |
+
"grad_norm": 1.2274290323257446,
|
182 |
+
"learning_rate": 6.49769693096581e-05,
|
183 |
+
"loss": 0.9831,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.033871808233454925,
|
188 |
+
"grad_norm": 1.2909352779388428,
|
189 |
+
"learning_rate": 6.49715678367672e-05,
|
190 |
+
"loss": 0.9971,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.035174570088587806,
|
195 |
+
"grad_norm": 1.2330715656280518,
|
196 |
+
"learning_rate": 6.49655981360514e-05,
|
197 |
+
"loss": 0.9923,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03647733194372069,
|
202 |
+
"grad_norm": 1.2433793544769287,
|
203 |
+
"learning_rate": 6.495906031197591e-05,
|
204 |
+
"loss": 0.9121,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03778009379885357,
|
209 |
+
"grad_norm": 1.2374027967453003,
|
210 |
+
"learning_rate": 6.49519544789477e-05,
|
211 |
+
"loss": 0.9224,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03908285565398645,
|
216 |
+
"grad_norm": 1.2204357385635376,
|
217 |
+
"learning_rate": 6.494428076131346e-05,
|
218 |
+
"loss": 0.919,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.040385617509119336,
|
223 |
+
"grad_norm": 1.1927292346954346,
|
224 |
+
"learning_rate": 6.493603929335744e-05,
|
225 |
+
"loss": 0.9589,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.041688379364252216,
|
230 |
+
"grad_norm": 1.1353641748428345,
|
231 |
+
"learning_rate": 6.492723021929908e-05,
|
232 |
+
"loss": 0.8869,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0429911412193851,
|
237 |
+
"grad_norm": 1.212263822555542,
|
238 |
+
"learning_rate": 6.49178536932905e-05,
|
239 |
+
"loss": 0.8934,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.04429390307451798,
|
244 |
+
"grad_norm": 1.0893241167068481,
|
245 |
+
"learning_rate": 6.49079098794138e-05,
|
246 |
+
"loss": 0.8718,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04559666492965086,
|
251 |
+
"grad_norm": 1.1801607608795166,
|
252 |
+
"learning_rate": 6.489739895167818e-05,
|
253 |
+
"loss": 0.9774,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04689942678478374,
|
258 |
+
"grad_norm": 1.1302330493927002,
|
259 |
+
"learning_rate": 6.488632109401691e-05,
|
260 |
+
"loss": 0.9584,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04820218863991663,
|
265 |
+
"grad_norm": 1.1432682275772095,
|
266 |
+
"learning_rate": 6.487467650028411e-05,
|
267 |
+
"loss": 0.9452,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04950495049504951,
|
272 |
+
"grad_norm": 1.1399481296539307,
|
273 |
+
"learning_rate": 6.486246537425133e-05,
|
274 |
+
"loss": 0.9017,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.05080771235018239,
|
279 |
+
"grad_norm": 1.0911235809326172,
|
280 |
+
"learning_rate": 6.484968792960403e-05,
|
281 |
+
"loss": 0.9036,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.05211047420531527,
|
286 |
+
"grad_norm": 1.071078896522522,
|
287 |
+
"learning_rate": 6.48363443899378e-05,
|
288 |
+
"loss": 0.9273,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.05341323606044815,
|
293 |
+
"grad_norm": 1.053589105606079,
|
294 |
+
"learning_rate": 6.482243498875449e-05,
|
295 |
+
"loss": 0.8847,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05471599791558103,
|
300 |
+
"grad_norm": 1.109771490097046,
|
301 |
+
"learning_rate": 6.480795996945806e-05,
|
302 |
+
"loss": 0.9364,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.05601875977071391,
|
307 |
+
"grad_norm": 1.1093286275863647,
|
308 |
+
"learning_rate": 6.479291958535037e-05,
|
309 |
+
"loss": 0.9088,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.0573215216258468,
|
314 |
+
"grad_norm": 1.0716255903244019,
|
315 |
+
"learning_rate": 6.477731409962675e-05,
|
316 |
+
"loss": 0.8885,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.05862428348097968,
|
321 |
+
"grad_norm": 1.1552095413208008,
|
322 |
+
"learning_rate": 6.476114378537138e-05,
|
323 |
+
"loss": 0.9736,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05992704533611256,
|
328 |
+
"grad_norm": 1.1647394895553589,
|
329 |
+
"learning_rate": 6.474440892555249e-05,
|
330 |
+
"loss": 0.9138,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06122980719124544,
|
335 |
+
"grad_norm": 1.1463412046432495,
|
336 |
+
"learning_rate": 6.472710981301745e-05,
|
337 |
+
"loss": 0.9204,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.06253256904637833,
|
342 |
+
"grad_norm": 1.175421118736267,
|
343 |
+
"learning_rate": 6.470924675048762e-05,
|
344 |
+
"loss": 0.9119,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.06383533090151121,
|
349 |
+
"grad_norm": 1.9249529838562012,
|
350 |
+
"learning_rate": 6.469082005055304e-05,
|
351 |
+
"loss": 0.8639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.06513809275664409,
|
356 |
+
"grad_norm": 1.1802655458450317,
|
357 |
+
"learning_rate": 6.467183003566701e-05,
|
358 |
+
"loss": 0.9352,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.06644085461177697,
|
363 |
+
"grad_norm": 1.1035569906234741,
|
364 |
+
"learning_rate": 6.465227703814038e-05,
|
365 |
+
"loss": 0.9342,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.06774361646690985,
|
370 |
+
"grad_norm": 1.1226942539215088,
|
371 |
+
"learning_rate": 6.463216140013581e-05,
|
372 |
+
"loss": 0.8948,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.06904637832204273,
|
377 |
+
"grad_norm": 1.1143085956573486,
|
378 |
+
"learning_rate": 6.46114834736617e-05,
|
379 |
+
"loss": 0.9577,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.07034914017717561,
|
384 |
+
"grad_norm": 1.1214665174484253,
|
385 |
+
"learning_rate": 6.459024362056608e-05,
|
386 |
+
"loss": 0.9106,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.07165190203230849,
|
391 |
+
"grad_norm": 1.1105942726135254,
|
392 |
+
"learning_rate": 6.45684422125303e-05,
|
393 |
+
"loss": 0.8706,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.07295466388744137,
|
398 |
+
"grad_norm": 1.0562191009521484,
|
399 |
+
"learning_rate": 6.454607963106247e-05,
|
400 |
+
"loss": 0.8278,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.07425742574257425,
|
405 |
+
"grad_norm": 1.1298907995224,
|
406 |
+
"learning_rate": 6.452315626749081e-05,
|
407 |
+
"loss": 0.8883,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.07556018759770713,
|
412 |
+
"grad_norm": 1.133426547050476,
|
413 |
+
"learning_rate": 6.449967252295682e-05,
|
414 |
+
"loss": 0.8868,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.07686294945284002,
|
419 |
+
"grad_norm": 1.09175443649292,
|
420 |
+
"learning_rate": 6.447562880840822e-05,
|
421 |
+
"loss": 0.8486,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.0781657113079729,
|
426 |
+
"grad_norm": 1.1153368949890137,
|
427 |
+
"learning_rate": 6.44510255445918e-05,
|
428 |
+
"loss": 0.9278,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.07946847316310579,
|
433 |
+
"grad_norm": 1.102013349533081,
|
434 |
+
"learning_rate": 6.442586316204601e-05,
|
435 |
+
"loss": 0.8362,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.08077123501823867,
|
440 |
+
"grad_norm": 1.1041877269744873,
|
441 |
+
"learning_rate": 6.44001421010935e-05,
|
442 |
+
"loss": 0.8746,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.08207399687337155,
|
447 |
+
"grad_norm": 1.075576901435852,
|
448 |
+
"learning_rate": 6.437386281183331e-05,
|
449 |
+
"loss": 0.8567,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.08337675872850443,
|
454 |
+
"grad_norm": 1.1472443342208862,
|
455 |
+
"learning_rate": 6.43470257541331e-05,
|
456 |
+
"loss": 0.9023,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.08467952058363731,
|
461 |
+
"grad_norm": 1.1024972200393677,
|
462 |
+
"learning_rate": 6.431963139762104e-05,
|
463 |
+
"loss": 0.8982,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.0859822824387702,
|
468 |
+
"grad_norm": 1.1128768920898438,
|
469 |
+
"learning_rate": 6.42916802216776e-05,
|
470 |
+
"loss": 0.883,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.08728504429390307,
|
475 |
+
"grad_norm": 1.058384895324707,
|
476 |
+
"learning_rate": 6.426317271542717e-05,
|
477 |
+
"loss": 0.8428,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.08858780614903596,
|
482 |
+
"grad_norm": 1.0728991031646729,
|
483 |
+
"learning_rate": 6.423410937772951e-05,
|
484 |
+
"loss": 0.8553,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.08989056800416884,
|
489 |
+
"grad_norm": 1.0956963300704956,
|
490 |
+
"learning_rate": 6.4204490717171e-05,
|
491 |
+
"loss": 0.8894,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.09119332985930172,
|
496 |
+
"grad_norm": 1.0787287950515747,
|
497 |
+
"learning_rate": 6.417431725205575e-05,
|
498 |
+
"loss": 0.9086,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.0924960917144346,
|
503 |
+
"grad_norm": 1.1435580253601074,
|
504 |
+
"learning_rate": 6.414358951039651e-05,
|
505 |
+
"loss": 0.9074,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.09379885356956748,
|
510 |
+
"grad_norm": 1.0396053791046143,
|
511 |
+
"learning_rate": 6.41123080299055e-05,
|
512 |
+
"loss": 0.8553,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.09510161542470036,
|
517 |
+
"grad_norm": 1.0929105281829834,
|
518 |
+
"learning_rate": 6.40804733579849e-05,
|
519 |
+
"loss": 0.8504,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.09640437727983325,
|
524 |
+
"grad_norm": 1.1395248174667358,
|
525 |
+
"learning_rate": 6.404808605171734e-05,
|
526 |
+
"loss": 0.9222,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.09770713913496613,
|
531 |
+
"grad_norm": 1.0281647443771362,
|
532 |
+
"learning_rate": 6.401514667785613e-05,
|
533 |
+
"loss": 0.868,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.09900990099009901,
|
538 |
+
"grad_norm": 1.0565054416656494,
|
539 |
+
"learning_rate": 6.398165581281536e-05,
|
540 |
+
"loss": 0.8302,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.1003126628452319,
|
545 |
+
"grad_norm": 1.0529290437698364,
|
546 |
+
"learning_rate": 6.394761404265977e-05,
|
547 |
+
"loss": 0.8669,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.10161542470036478,
|
552 |
+
"grad_norm": 1.0579882860183716,
|
553 |
+
"learning_rate": 6.391302196309452e-05,
|
554 |
+
"loss": 0.9204,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.10291818655549766,
|
559 |
+
"grad_norm": 1.0531302690505981,
|
560 |
+
"learning_rate": 6.387788017945482e-05,
|
561 |
+
"loss": 0.9202,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.10422094841063054,
|
566 |
+
"grad_norm": 1.0358260869979858,
|
567 |
+
"learning_rate": 6.384218930669521e-05,
|
568 |
+
"loss": 0.8647,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.10552371026576342,
|
573 |
+
"grad_norm": 1.0599216222763062,
|
574 |
+
"learning_rate": 6.380594996937895e-05,
|
575 |
+
"loss": 0.9093,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.1068264721208963,
|
580 |
+
"grad_norm": 1.2026344537734985,
|
581 |
+
"learning_rate": 6.376916280166696e-05,
|
582 |
+
"loss": 0.8731,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.10812923397602918,
|
587 |
+
"grad_norm": 1.1054397821426392,
|
588 |
+
"learning_rate": 6.373182844730677e-05,
|
589 |
+
"loss": 0.8835,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.10943199583116206,
|
594 |
+
"grad_norm": 1.030562162399292,
|
595 |
+
"learning_rate": 6.369394755962129e-05,
|
596 |
+
"loss": 0.8432,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.11073475768629494,
|
601 |
+
"grad_norm": 1.0522128343582153,
|
602 |
+
"learning_rate": 6.365552080149737e-05,
|
603 |
+
"loss": 0.8598,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.11203751954142782,
|
608 |
+
"grad_norm": 1.0692416429519653,
|
609 |
+
"learning_rate": 6.361654884537413e-05,
|
610 |
+
"loss": 0.8812,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.1133402813965607,
|
615 |
+
"grad_norm": 1.1009373664855957,
|
616 |
+
"learning_rate": 6.357703237323127e-05,
|
617 |
+
"loss": 0.8635,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.1146430432516936,
|
622 |
+
"grad_norm": 1.1628373861312866,
|
623 |
+
"learning_rate": 6.353697207657708e-05,
|
624 |
+
"loss": 0.8907,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.11594580510682648,
|
629 |
+
"grad_norm": 1.1273458003997803,
|
630 |
+
"learning_rate": 6.349636865643642e-05,
|
631 |
+
"loss": 0.8445,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.11724856696195936,
|
636 |
+
"grad_norm": 1.0971312522888184,
|
637 |
+
"learning_rate": 6.345522282333835e-05,
|
638 |
+
"loss": 0.8543,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.11855132881709224,
|
643 |
+
"grad_norm": 1.0826351642608643,
|
644 |
+
"learning_rate": 6.341353529730374e-05,
|
645 |
+
"loss": 0.8605,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.11985409067222512,
|
650 |
+
"grad_norm": 1.0686413049697876,
|
651 |
+
"learning_rate": 6.337130680783273e-05,
|
652 |
+
"loss": 0.8814,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.121156852527358,
|
657 |
+
"grad_norm": 1.21683931350708,
|
658 |
+
"learning_rate": 6.332853809389189e-05,
|
659 |
+
"loss": 0.8979,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.12245961438249088,
|
664 |
+
"grad_norm": 1.0884461402893066,
|
665 |
+
"learning_rate": 6.328522990390126e-05,
|
666 |
+
"loss": 0.8577,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.12376237623762376,
|
671 |
+
"grad_norm": 1.047310709953308,
|
672 |
+
"learning_rate": 6.324138299572135e-05,
|
673 |
+
"loss": 0.8174,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.12506513809275666,
|
678 |
+
"grad_norm": 1.087296485900879,
|
679 |
+
"learning_rate": 6.319699813663982e-05,
|
680 |
+
"loss": 0.8566,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.12636789994788952,
|
685 |
+
"grad_norm": 1.070327639579773,
|
686 |
+
"learning_rate": 6.315207610335808e-05,
|
687 |
+
"loss": 0.8615,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.12767066180302242,
|
692 |
+
"grad_norm": 1.0299792289733887,
|
693 |
+
"learning_rate": 6.310661768197764e-05,
|
694 |
+
"loss": 0.866,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.12897342365815528,
|
699 |
+
"grad_norm": 1.1011384725570679,
|
700 |
+
"learning_rate": 6.306062366798642e-05,
|
701 |
+
"loss": 0.8775,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.13027618551328818,
|
706 |
+
"grad_norm": 1.0193467140197754,
|
707 |
+
"learning_rate": 6.301409486624481e-05,
|
708 |
+
"loss": 0.8243,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.13157894736842105,
|
713 |
+
"grad_norm": 1.0899205207824707,
|
714 |
+
"learning_rate": 6.296703209097159e-05,
|
715 |
+
"loss": 0.8849,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.13288170922355394,
|
720 |
+
"grad_norm": 1.0473856925964355,
|
721 |
+
"learning_rate": 6.291943616572962e-05,
|
722 |
+
"loss": 0.8847,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.1341844710786868,
|
727 |
+
"grad_norm": 0.9922148585319519,
|
728 |
+
"learning_rate": 6.287130792341154e-05,
|
729 |
+
"loss": 0.8157,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.1354872329338197,
|
734 |
+
"grad_norm": 1.0680872201919556,
|
735 |
+
"learning_rate": 6.282264820622511e-05,
|
736 |
+
"loss": 0.8802,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.13678999478895257,
|
741 |
+
"grad_norm": 1.034562587738037,
|
742 |
+
"learning_rate": 6.27734578656785e-05,
|
743 |
+
"loss": 0.8826,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.13809275664408546,
|
748 |
+
"grad_norm": 1.0247395038604736,
|
749 |
+
"learning_rate": 6.272373776256536e-05,
|
750 |
+
"loss": 0.8535,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.13939551849921833,
|
755 |
+
"grad_norm": 1.099061131477356,
|
756 |
+
"learning_rate": 6.267348876694983e-05,
|
757 |
+
"loss": 0.8583,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.14069828035435122,
|
762 |
+
"grad_norm": 1.0081039667129517,
|
763 |
+
"learning_rate": 6.262271175815126e-05,
|
764 |
+
"loss": 0.7988,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.14200104220948412,
|
769 |
+
"grad_norm": 1.1140209436416626,
|
770 |
+
"learning_rate": 6.257140762472879e-05,
|
771 |
+
"loss": 0.8426,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.14330380406461699,
|
776 |
+
"grad_norm": 1.0654839277267456,
|
777 |
+
"learning_rate": 6.251957726446589e-05,
|
778 |
+
"loss": 0.8682,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.14460656591974988,
|
783 |
+
"grad_norm": 1.0632318258285522,
|
784 |
+
"learning_rate": 6.246722158435455e-05,
|
785 |
+
"loss": 0.8379,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.14590932777488275,
|
790 |
+
"grad_norm": 1.0444918870925903,
|
791 |
+
"learning_rate": 6.241434150057953e-05,
|
792 |
+
"loss": 0.8525,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.14721208963001564,
|
797 |
+
"grad_norm": 1.0542877912521362,
|
798 |
+
"learning_rate": 6.236093793850217e-05,
|
799 |
+
"loss": 0.834,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.1485148514851485,
|
804 |
+
"grad_norm": 0.9843441247940063,
|
805 |
+
"learning_rate": 6.230701183264436e-05,
|
806 |
+
"loss": 0.7711,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.1498176133402814,
|
811 |
+
"grad_norm": 1.0625543594360352,
|
812 |
+
"learning_rate": 6.225256412667207e-05,
|
813 |
+
"loss": 0.8169,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.15112037519541427,
|
818 |
+
"grad_norm": 1.0951343774795532,
|
819 |
+
"learning_rate": 6.219759577337887e-05,
|
820 |
+
"loss": 0.9114,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.15242313705054716,
|
825 |
+
"grad_norm": 1.0442739725112915,
|
826 |
+
"learning_rate": 6.214210773466932e-05,
|
827 |
+
"loss": 0.8038,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.15372589890568003,
|
832 |
+
"grad_norm": 1.0549882650375366,
|
833 |
+
"learning_rate": 6.2086100981542e-05,
|
834 |
+
"loss": 0.8677,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.15502866076081293,
|
839 |
+
"grad_norm": 1.0807327032089233,
|
840 |
+
"learning_rate": 6.202957649407264e-05,
|
841 |
+
"loss": 0.8276,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.1563314226159458,
|
846 |
+
"grad_norm": 1.0784152746200562,
|
847 |
+
"learning_rate": 6.197253526139696e-05,
|
848 |
+
"loss": 0.8823,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.1576341844710787,
|
853 |
+
"grad_norm": 1.076708436012268,
|
854 |
+
"learning_rate": 6.191497828169325e-05,
|
855 |
+
"loss": 0.842,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.15893694632621158,
|
860 |
+
"grad_norm": 1.0658226013183594,
|
861 |
+
"learning_rate": 6.185690656216507e-05,
|
862 |
+
"loss": 0.8626,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.16023970818134445,
|
867 |
+
"grad_norm": 1.064942717552185,
|
868 |
+
"learning_rate": 6.179832111902348e-05,
|
869 |
+
"loss": 0.8735,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.16154247003647734,
|
874 |
+
"grad_norm": 1.0782710313796997,
|
875 |
+
"learning_rate": 6.17392229774693e-05,
|
876 |
+
"loss": 0.828,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.1628452318916102,
|
881 |
+
"grad_norm": 1.0276188850402832,
|
882 |
+
"learning_rate": 6.167961317167528e-05,
|
883 |
+
"loss": 0.8475,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.1641479937467431,
|
888 |
+
"grad_norm": 1.1249077320098877,
|
889 |
+
"learning_rate": 6.161949274476778e-05,
|
890 |
+
"loss": 0.9029,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.16545075560187597,
|
895 |
+
"grad_norm": 1.027971863746643,
|
896 |
+
"learning_rate": 6.155886274880874e-05,
|
897 |
+
"loss": 0.8057,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.16675351745700887,
|
902 |
+
"grad_norm": 1.0177087783813477,
|
903 |
+
"learning_rate": 6.14977242447771e-05,
|
904 |
+
"loss": 0.7928,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.16805627931214173,
|
909 |
+
"grad_norm": 1.0410820245742798,
|
910 |
+
"learning_rate": 6.143607830255037e-05,
|
911 |
+
"loss": 0.8222,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.16935904116727463,
|
916 |
+
"grad_norm": 1.086966872215271,
|
917 |
+
"learning_rate": 6.137392600088579e-05,
|
918 |
+
"loss": 0.837,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.1706618030224075,
|
923 |
+
"grad_norm": 1.099645972251892,
|
924 |
+
"learning_rate": 6.131126842740155e-05,
|
925 |
+
"loss": 0.8604,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.1719645648775404,
|
930 |
+
"grad_norm": 1.0512402057647705,
|
931 |
+
"learning_rate": 6.124810667855768e-05,
|
932 |
+
"loss": 0.8524,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.17326732673267325,
|
937 |
+
"grad_norm": 1.0146111249923706,
|
938 |
+
"learning_rate": 6.118444185963691e-05,
|
939 |
+
"loss": 0.7948,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.17457008858780615,
|
944 |
+
"grad_norm": 1.0564138889312744,
|
945 |
+
"learning_rate": 6.112027508472533e-05,
|
946 |
+
"loss": 0.8393,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.17587285044293904,
|
951 |
+
"grad_norm": 1.1982516050338745,
|
952 |
+
"learning_rate": 6.105560747669284e-05,
|
953 |
+
"loss": 0.8326,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.1771756122980719,
|
958 |
+
"grad_norm": 1.0336800813674927,
|
959 |
+
"learning_rate": 6.0990440167173595e-05,
|
960 |
+
"loss": 0.8456,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.1784783741532048,
|
965 |
+
"grad_norm": 1.0412505865097046,
|
966 |
+
"learning_rate": 6.092477429654611e-05,
|
967 |
+
"loss": 0.8026,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.17978113600833767,
|
972 |
+
"grad_norm": 1.0531303882598877,
|
973 |
+
"learning_rate": 6.085861101391333e-05,
|
974 |
+
"loss": 0.8675,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.18108389786347057,
|
979 |
+
"grad_norm": 1.0367439985275269,
|
980 |
+
"learning_rate": 6.0791951477082555e-05,
|
981 |
+
"loss": 0.8328,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.18238665971860343,
|
986 |
+
"grad_norm": 1.057989478111267,
|
987 |
+
"learning_rate": 6.072479685254518e-05,
|
988 |
+
"loss": 0.8129,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.18368942157373633,
|
993 |
+
"grad_norm": 1.1223191022872925,
|
994 |
+
"learning_rate": 6.065714831545621e-05,
|
995 |
+
"loss": 0.8519,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.1849921834288692,
|
1000 |
+
"grad_norm": 1.0480860471725464,
|
1001 |
+
"learning_rate": 6.058900704961377e-05,
|
1002 |
+
"loss": 0.8478,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.1862949452840021,
|
1007 |
+
"grad_norm": 1.0725680589675903,
|
1008 |
+
"learning_rate": 6.0520374247438375e-05,
|
1009 |
+
"loss": 0.8612,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.18759770713913496,
|
1014 |
+
"grad_norm": 1.0441476106643677,
|
1015 |
+
"learning_rate": 6.045125110995204e-05,
|
1016 |
+
"loss": 0.8521,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.18890046899426785,
|
1021 |
+
"grad_norm": 1.0792895555496216,
|
1022 |
+
"learning_rate": 6.0381638846757264e-05,
|
1023 |
+
"loss": 0.8364,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.19020323084940072,
|
1028 |
+
"grad_norm": 1.0203429460525513,
|
1029 |
+
"learning_rate": 6.03115386760159e-05,
|
1030 |
+
"loss": 0.7973,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.1915059927045336,
|
1035 |
+
"grad_norm": 1.0836308002471924,
|
1036 |
+
"learning_rate": 6.024095182442782e-05,
|
1037 |
+
"loss": 0.8719,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.1928087545596665,
|
1042 |
+
"grad_norm": 1.0394123792648315,
|
1043 |
+
"learning_rate": 6.016987952720939e-05,
|
1044 |
+
"loss": 0.8809,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.19411151641479937,
|
1049 |
+
"grad_norm": 1.0890783071517944,
|
1050 |
+
"learning_rate": 6.0098323028071956e-05,
|
1051 |
+
"loss": 0.8996,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.19541427826993227,
|
1056 |
+
"grad_norm": 1.0037873983383179,
|
1057 |
+
"learning_rate": 6.002628357920002e-05,
|
1058 |
+
"loss": 0.8424,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.19671704012506513,
|
1063 |
+
"grad_norm": 1.0470969676971436,
|
1064 |
+
"learning_rate": 5.995376244122935e-05,
|
1065 |
+
"loss": 0.8019,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.19801980198019803,
|
1070 |
+
"grad_norm": 1.0230716466903687,
|
1071 |
+
"learning_rate": 5.988076088322486e-05,
|
1072 |
+
"loss": 0.7927,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.1993225638353309,
|
1077 |
+
"grad_norm": 1.0318727493286133,
|
1078 |
+
"learning_rate": 5.980728018265849e-05,
|
1079 |
+
"loss": 0.803,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.2006253256904638,
|
1084 |
+
"grad_norm": 1.0479062795639038,
|
1085 |
+
"learning_rate": 5.9733321625386824e-05,
|
1086 |
+
"loss": 0.8597,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.20192808754559666,
|
1091 |
+
"grad_norm": 1.025315761566162,
|
1092 |
+
"learning_rate": 5.965888650562853e-05,
|
1093 |
+
"loss": 0.7937,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.20323084940072955,
|
1098 |
+
"grad_norm": 1.0599974393844604,
|
1099 |
+
"learning_rate": 5.958397612594182e-05,
|
1100 |
+
"loss": 0.8628,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.20453361125586242,
|
1105 |
+
"grad_norm": 1.0344469547271729,
|
1106 |
+
"learning_rate": 5.950859179720152e-05,
|
1107 |
+
"loss": 0.8436,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.2058363731109953,
|
1112 |
+
"grad_norm": 1.1034519672393799,
|
1113 |
+
"learning_rate": 5.943273483857627e-05,
|
1114 |
+
"loss": 0.8124,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.20713913496612818,
|
1119 |
+
"grad_norm": 1.0487233400344849,
|
1120 |
+
"learning_rate": 5.935640657750534e-05,
|
1121 |
+
"loss": 0.8337,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.20844189682126107,
|
1126 |
+
"grad_norm": 1.0436427593231201,
|
1127 |
+
"learning_rate": 5.9279608349675444e-05,
|
1128 |
+
"loss": 0.8438,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.20974465867639394,
|
1133 |
+
"grad_norm": 1.0612242221832275,
|
1134 |
+
"learning_rate": 5.920234149899736e-05,
|
1135 |
+
"loss": 0.8735,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.21104742053152684,
|
1140 |
+
"grad_norm": 1.168532371520996,
|
1141 |
+
"learning_rate": 5.912460737758241e-05,
|
1142 |
+
"loss": 0.8422,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.21235018238665973,
|
1147 |
+
"grad_norm": 1.0675426721572876,
|
1148 |
+
"learning_rate": 5.9046407345718805e-05,
|
1149 |
+
"loss": 0.8631,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.2136529442417926,
|
1154 |
+
"grad_norm": 1.048614501953125,
|
1155 |
+
"learning_rate": 5.8967742771847826e-05,
|
1156 |
+
"loss": 0.8473,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.2149557060969255,
|
1161 |
+
"grad_norm": 1.0362776517868042,
|
1162 |
+
"learning_rate": 5.888861503253989e-05,
|
1163 |
+
"loss": 0.8888,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.21625846795205836,
|
1168 |
+
"grad_norm": 0.9976462721824646,
|
1169 |
+
"learning_rate": 5.8809025512470445e-05,
|
1170 |
+
"loss": 0.8079,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.21756122980719125,
|
1175 |
+
"grad_norm": 1.0061395168304443,
|
1176 |
+
"learning_rate": 5.87289756043958e-05,
|
1177 |
+
"loss": 0.7954,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.21886399166232412,
|
1182 |
+
"grad_norm": 1.0533777475357056,
|
1183 |
+
"learning_rate": 5.864846670912864e-05,
|
1184 |
+
"loss": 0.8089,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.22016675351745701,
|
1189 |
+
"grad_norm": 0.9939700365066528,
|
1190 |
+
"learning_rate": 5.856750023551361e-05,
|
1191 |
+
"loss": 0.8176,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.22146951537258988,
|
1196 |
+
"grad_norm": 1.0513004064559937,
|
1197 |
+
"learning_rate": 5.848607760040267e-05,
|
1198 |
+
"loss": 0.8602,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.22277227722772278,
|
1203 |
+
"grad_norm": 1.055511713027954,
|
1204 |
+
"learning_rate": 5.840420022863016e-05,
|
1205 |
+
"loss": 0.8511,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.22407503908285564,
|
1210 |
+
"grad_norm": 1.0215332508087158,
|
1211 |
+
"learning_rate": 5.832186955298808e-05,
|
1212 |
+
"loss": 0.8233,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.22537780093798854,
|
1217 |
+
"grad_norm": 1.018233299255371,
|
1218 |
+
"learning_rate": 5.8239087014200806e-05,
|
1219 |
+
"loss": 0.8354,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.2266805627931214,
|
1224 |
+
"grad_norm": 1.0055863857269287,
|
1225 |
+
"learning_rate": 5.815585406090005e-05,
|
1226 |
+
"loss": 0.8488,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.2279833246482543,
|
1231 |
+
"grad_norm": 1.008152961730957,
|
1232 |
+
"learning_rate": 5.8072172149599394e-05,
|
1233 |
+
"loss": 0.7623,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.2292860865033872,
|
1238 |
+
"grad_norm": 1.0418919324874878,
|
1239 |
+
"learning_rate": 5.7988042744668856e-05,
|
1240 |
+
"loss": 0.8109,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.23058884835852006,
|
1245 |
+
"grad_norm": 1.0832551717758179,
|
1246 |
+
"learning_rate": 5.790346731830927e-05,
|
1247 |
+
"loss": 0.8951,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.23189161021365295,
|
1252 |
+
"grad_norm": 1.0513347387313843,
|
1253 |
+
"learning_rate": 5.7818447350526476e-05,
|
1254 |
+
"loss": 0.8598,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.23319437206878582,
|
1259 |
+
"grad_norm": 0.9888846278190613,
|
1260 |
+
"learning_rate": 5.7732984329105484e-05,
|
1261 |
+
"loss": 0.746,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.23449713392391872,
|
1266 |
+
"grad_norm": 1.0668085813522339,
|
1267 |
+
"learning_rate": 5.764707974958437e-05,
|
1268 |
+
"loss": 0.8039,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.23579989577905158,
|
1273 |
+
"grad_norm": 1.0392318964004517,
|
1274 |
+
"learning_rate": 5.7560735115228195e-05,
|
1275 |
+
"loss": 0.8155,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.23710265763418448,
|
1280 |
+
"grad_norm": 1.052474021911621,
|
1281 |
+
"learning_rate": 5.7473951937002576e-05,
|
1282 |
+
"loss": 0.8215,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.23840541948931734,
|
1287 |
+
"grad_norm": 1.067699670791626,
|
1288 |
+
"learning_rate": 5.738673173354739e-05,
|
1289 |
+
"loss": 0.8259,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.23970818134445024,
|
1294 |
+
"grad_norm": 1.042398452758789,
|
1295 |
+
"learning_rate": 5.729907603115005e-05,
|
1296 |
+
"loss": 0.8086,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.2410109431995831,
|
1301 |
+
"grad_norm": 1.0346574783325195,
|
1302 |
+
"learning_rate": 5.721098636371894e-05,
|
1303 |
+
"loss": 0.8184,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.242313705054716,
|
1308 |
+
"grad_norm": 1.0383342504501343,
|
1309 |
+
"learning_rate": 5.712246427275646e-05,
|
1310 |
+
"loss": 0.8543,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.24361646690984887,
|
1315 |
+
"grad_norm": 1.0456079244613647,
|
1316 |
+
"learning_rate": 5.703351130733211e-05,
|
1317 |
+
"loss": 0.8244,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.24491922876498176,
|
1322 |
+
"grad_norm": 0.9899833798408508,
|
1323 |
+
"learning_rate": 5.694412902405535e-05,
|
1324 |
+
"loss": 0.7916,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.24622199062011466,
|
1329 |
+
"grad_norm": 1.1231224536895752,
|
1330 |
+
"learning_rate": 5.685431898704839e-05,
|
1331 |
+
"loss": 0.7904,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.24752475247524752,
|
1336 |
+
"grad_norm": 1.0400362014770508,
|
1337 |
+
"learning_rate": 5.676408276791882e-05,
|
1338 |
+
"loss": 0.845,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.24882751433038042,
|
1343 |
+
"grad_norm": 1.0910183191299438,
|
1344 |
+
"learning_rate": 5.6673421945732075e-05,
|
1345 |
+
"loss": 0.8293,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.2501302761855133,
|
1350 |
+
"grad_norm": 1.0755969285964966,
|
1351 |
+
"learning_rate": 5.658233810698381e-05,
|
1352 |
+
"loss": 0.83,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.25143303804064615,
|
1357 |
+
"grad_norm": 1.0231711864471436,
|
1358 |
+
"learning_rate": 5.649083284557219e-05,
|
1359 |
+
"loss": 0.8442,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.25273579989577905,
|
1364 |
+
"grad_norm": 1.0368572473526,
|
1365 |
+
"learning_rate": 5.639890776276991e-05,
|
1366 |
+
"loss": 0.8574,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.25403856175091194,
|
1371 |
+
"grad_norm": 1.0136909484863281,
|
1372 |
+
"learning_rate": 5.630656446719626e-05,
|
1373 |
+
"loss": 0.8151,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.25534132360604483,
|
1378 |
+
"grad_norm": 1.0600650310516357,
|
1379 |
+
"learning_rate": 5.621380457478889e-05,
|
1380 |
+
"loss": 0.7792,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.2566440854611777,
|
1385 |
+
"grad_norm": 1.0362857580184937,
|
1386 |
+
"learning_rate": 5.612062970877565e-05,
|
1387 |
+
"loss": 0.8246,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.25794684731631057,
|
1392 |
+
"grad_norm": 1.0172935724258423,
|
1393 |
+
"learning_rate": 5.602704149964604e-05,
|
1394 |
+
"loss": 0.8196,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.25924960917144346,
|
1399 |
+
"grad_norm": 1.0049176216125488,
|
1400 |
+
"learning_rate": 5.5933041585122805e-05,
|
1401 |
+
"loss": 0.8229,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.26055237102657636,
|
1406 |
+
"grad_norm": 1.0751328468322754,
|
1407 |
+
"learning_rate": 5.5838631610133196e-05,
|
1408 |
+
"loss": 0.8456,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.2618551328817092,
|
1413 |
+
"grad_norm": 1.0684475898742676,
|
1414 |
+
"learning_rate": 5.57438132267802e-05,
|
1415 |
+
"loss": 0.8607,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.2631578947368421,
|
1420 |
+
"grad_norm": 1.029704213142395,
|
1421 |
+
"learning_rate": 5.564858809431367e-05,
|
1422 |
+
"loss": 0.7801,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.264460656591975,
|
1427 |
+
"grad_norm": 1.044959306716919,
|
1428 |
+
"learning_rate": 5.5552957879101246e-05,
|
1429 |
+
"loss": 0.8379,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.2657634184471079,
|
1434 |
+
"grad_norm": 1.030415654182434,
|
1435 |
+
"learning_rate": 5.545692425459921e-05,
|
1436 |
+
"loss": 0.8705,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.2670661803022408,
|
1441 |
+
"grad_norm": 1.0018935203552246,
|
1442 |
+
"learning_rate": 5.5360488901323206e-05,
|
1443 |
+
"loss": 0.8122,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.2683689421573736,
|
1448 |
+
"grad_norm": 1.0166568756103516,
|
1449 |
+
"learning_rate": 5.526365350681881e-05,
|
1450 |
+
"loss": 0.8171,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.2696717040125065,
|
1455 |
+
"grad_norm": 1.0195856094360352,
|
1456 |
+
"learning_rate": 5.516641976563204e-05,
|
1457 |
+
"loss": 0.8496,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.2709744658676394,
|
1462 |
+
"grad_norm": 0.985876739025116,
|
1463 |
+
"learning_rate": 5.506878937927966e-05,
|
1464 |
+
"loss": 0.801,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.2722772277227723,
|
1469 |
+
"grad_norm": 1.0150160789489746,
|
1470 |
+
"learning_rate": 5.497076405621944e-05,
|
1471 |
+
"loss": 0.784,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.27357998957790514,
|
1476 |
+
"grad_norm": 1.095823884010315,
|
1477 |
+
"learning_rate": 5.487234551182022e-05,
|
1478 |
+
"loss": 0.8957,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.27488275143303803,
|
1483 |
+
"grad_norm": 1.033151388168335,
|
1484 |
+
"learning_rate": 5.477353546833193e-05,
|
1485 |
+
"loss": 0.8346,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.2761855132881709,
|
1490 |
+
"grad_norm": 0.982230007648468,
|
1491 |
+
"learning_rate": 5.467433565485546e-05,
|
1492 |
+
"loss": 0.7826,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.2774882751433038,
|
1497 |
+
"grad_norm": 0.9829743504524231,
|
1498 |
+
"learning_rate": 5.4574747807312326e-05,
|
1499 |
+
"loss": 0.791,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.27879103699843666,
|
1504 |
+
"grad_norm": 1.0257138013839722,
|
1505 |
+
"learning_rate": 5.4474773668414395e-05,
|
1506 |
+
"loss": 0.8498,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.28009379885356955,
|
1511 |
+
"grad_norm": 1.0054680109024048,
|
1512 |
+
"learning_rate": 5.437441498763332e-05,
|
1513 |
+
"loss": 0.8365,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.28139656070870245,
|
1518 |
+
"grad_norm": 1.0021213293075562,
|
1519 |
+
"learning_rate": 5.427367352116993e-05,
|
1520 |
+
"loss": 0.8313,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.28269932256383534,
|
1525 |
+
"grad_norm": 1.0124083757400513,
|
1526 |
+
"learning_rate": 5.417255103192355e-05,
|
1527 |
+
"loss": 0.81,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.28400208441896824,
|
1532 |
+
"grad_norm": 1.0104458332061768,
|
1533 |
+
"learning_rate": 5.407104928946109e-05,
|
1534 |
+
"loss": 0.7821,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.2853048462741011,
|
1539 |
+
"grad_norm": 1.0982369184494019,
|
1540 |
+
"learning_rate": 5.39691700699861e-05,
|
1541 |
+
"loss": 0.8512,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.28660760812923397,
|
1546 |
+
"grad_norm": 1.0122724771499634,
|
1547 |
+
"learning_rate": 5.386691515630771e-05,
|
1548 |
+
"loss": 0.8634,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.28791036998436687,
|
1553 |
+
"grad_norm": 1.0455682277679443,
|
1554 |
+
"learning_rate": 5.376428633780941e-05,
|
1555 |
+
"loss": 0.8399,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.28921313183949976,
|
1560 |
+
"grad_norm": 0.9880922436714172,
|
1561 |
+
"learning_rate": 5.3661285410417705e-05,
|
1562 |
+
"loss": 0.8044,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.2905158936946326,
|
1567 |
+
"grad_norm": 1.0006861686706543,
|
1568 |
+
"learning_rate": 5.355791417657078e-05,
|
1569 |
+
"loss": 0.7957,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.2918186555497655,
|
1574 |
+
"grad_norm": 1.0367894172668457,
|
1575 |
+
"learning_rate": 5.345417444518687e-05,
|
1576 |
+
"loss": 0.8207,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.2931214174048984,
|
1581 |
+
"grad_norm": 1.0520100593566895,
|
1582 |
+
"learning_rate": 5.335006803163265e-05,
|
1583 |
+
"loss": 0.8586,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.2944241792600313,
|
1588 |
+
"grad_norm": 1.0345007181167603,
|
1589 |
+
"learning_rate": 5.3245596757691435e-05,
|
1590 |
+
"loss": 0.8362,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.2957269411151641,
|
1595 |
+
"grad_norm": 1.0230737924575806,
|
1596 |
+
"learning_rate": 5.3140762451531344e-05,
|
1597 |
+
"loss": 0.8482,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.297029702970297,
|
1602 |
+
"grad_norm": 0.9852018356323242,
|
1603 |
+
"learning_rate": 5.303556694767326e-05,
|
1604 |
+
"loss": 0.8661,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.2983324648254299,
|
1609 |
+
"grad_norm": 0.9801431894302368,
|
1610 |
+
"learning_rate": 5.2930012086958783e-05,
|
1611 |
+
"loss": 0.8702,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.2996352266805628,
|
1616 |
+
"grad_norm": 1.0442442893981934,
|
1617 |
+
"learning_rate": 5.282409971651797e-05,
|
1618 |
+
"loss": 0.8566,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.3009379885356957,
|
1623 |
+
"grad_norm": 1.103188157081604,
|
1624 |
+
"learning_rate": 5.271783168973701e-05,
|
1625 |
+
"loss": 0.8206,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.30224075039082854,
|
1630 |
+
"grad_norm": 1.0066590309143066,
|
1631 |
+
"learning_rate": 5.261120986622583e-05,
|
1632 |
+
"loss": 0.8369,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.30354351224596143,
|
1637 |
+
"grad_norm": 0.9748640060424805,
|
1638 |
+
"learning_rate": 5.250423611178553e-05,
|
1639 |
+
"loss": 0.7792,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.30484627410109433,
|
1644 |
+
"grad_norm": 1.0654217004776,
|
1645 |
+
"learning_rate": 5.239691229837573e-05,
|
1646 |
+
"loss": 0.8242,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.3061490359562272,
|
1651 |
+
"grad_norm": 1.0146901607513428,
|
1652 |
+
"learning_rate": 5.228924030408182e-05,
|
1653 |
+
"loss": 0.8166,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.30745179781136006,
|
1658 |
+
"grad_norm": 1.0119966268539429,
|
1659 |
+
"learning_rate": 5.218122201308209e-05,
|
1660 |
+
"loss": 0.8074,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.30875455966649296,
|
1665 |
+
"grad_norm": 1.0073226690292358,
|
1666 |
+
"learning_rate": 5.207285931561475e-05,
|
1667 |
+
"loss": 0.8292,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.31005732152162585,
|
1672 |
+
"grad_norm": 1.0207470655441284,
|
1673 |
+
"learning_rate": 5.1964154107944876e-05,
|
1674 |
+
"loss": 0.8245,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.31136008337675875,
|
1679 |
+
"grad_norm": 0.9803332090377808,
|
1680 |
+
"learning_rate": 5.185510829233121e-05,
|
1681 |
+
"loss": 0.774,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.3126628452318916,
|
1686 |
+
"grad_norm": 1.0056718587875366,
|
1687 |
+
"learning_rate": 5.174572377699286e-05,
|
1688 |
+
"loss": 0.8308,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.3139656070870245,
|
1693 |
+
"grad_norm": 0.9751390218734741,
|
1694 |
+
"learning_rate": 5.163600247607596e-05,
|
1695 |
+
"loss": 0.7648,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.3152683689421574,
|
1700 |
+
"grad_norm": 1.0351225137710571,
|
1701 |
+
"learning_rate": 5.152594630962008e-05,
|
1702 |
+
"loss": 0.7695,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.31657113079729027,
|
1707 |
+
"grad_norm": 1.0021389722824097,
|
1708 |
+
"learning_rate": 5.1415557203524736e-05,
|
1709 |
+
"loss": 0.8158,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.31787389265242316,
|
1714 |
+
"grad_norm": 1.0016628503799438,
|
1715 |
+
"learning_rate": 5.130483708951561e-05,
|
1716 |
+
"loss": 0.793,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.319176654507556,
|
1721 |
+
"grad_norm": 1.008516788482666,
|
1722 |
+
"learning_rate": 5.119378790511079e-05,
|
1723 |
+
"loss": 0.8143,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.3204794163626889,
|
1728 |
+
"grad_norm": 1.0514389276504517,
|
1729 |
+
"learning_rate": 5.108241159358679e-05,
|
1730 |
+
"loss": 0.7945,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.3217821782178218,
|
1735 |
+
"grad_norm": 0.9676159024238586,
|
1736 |
+
"learning_rate": 5.097071010394469e-05,
|
1737 |
+
"loss": 0.7912,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.3230849400729547,
|
1742 |
+
"grad_norm": 1.0046639442443848,
|
1743 |
+
"learning_rate": 5.085868539087586e-05,
|
1744 |
+
"loss": 0.8136,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.3243877019280875,
|
1749 |
+
"grad_norm": 0.993964433670044,
|
1750 |
+
"learning_rate": 5.074633941472788e-05,
|
1751 |
+
"loss": 0.7893,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.3256904637832204,
|
1756 |
+
"grad_norm": 0.9951984286308289,
|
1757 |
+
"learning_rate": 5.0633674141470194e-05,
|
1758 |
+
"loss": 0.7463,
|
1759 |
+
"step": 250
|
1760 |
+
}
|
1761 |
+
],
|
1762 |
+
"logging_steps": 1,
|
1763 |
+
"max_steps": 767,
|
1764 |
+
"num_input_tokens_seen": 0,
|
1765 |
+
"num_train_epochs": 1,
|
1766 |
+
"save_steps": 50,
|
1767 |
+
"stateful_callbacks": {
|
1768 |
+
"TrainerControl": {
|
1769 |
+
"args": {
|
1770 |
+
"should_epoch_stop": false,
|
1771 |
+
"should_evaluate": false,
|
1772 |
+
"should_log": false,
|
1773 |
+
"should_save": true,
|
1774 |
+
"should_training_stop": false
|
1775 |
+
},
|
1776 |
+
"attributes": {}
|
1777 |
+
}
|
1778 |
+
},
|
1779 |
+
"total_flos": 3.844147471515648e+17,
|
1780 |
+
"train_batch_size": 6,
|
1781 |
+
"trial_name": null,
|
1782 |
+
"trial_params": null
|
1783 |
+
}
|
checkpoint-250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c6cdd050f0e9f3e909bcca2e2c0488bdf293a6b22313a332d8541c60d48d06
|
3 |
+
size 5432
|
checkpoint-50/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: rinna/llama-3-youko-8b
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-50/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj",
|
30 |
+
"v_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": true
|
37 |
+
}
|
checkpoint-50/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e4dfb25fdfdddf57ff64795732d9d471e4a5e72f13154e63f41e170fd6a62ca
|
3 |
+
size 11849545016
|
checkpoint-50/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c35448882ef1bf7fa5d18503afe4dea8eda38d19edc5f98339e052a83d29dcb2
|
3 |
+
size 2778493596
|
checkpoint-50/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9275065a25044785d153dd5dd91f5472b87a85a6b9cfc005f93d96861615f
|
3 |
+
size 14244
|
checkpoint-50/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7473a6fe005d44e9f96a4935dfc6fca3e89dbf0d3271b8df1d4bee2197e0ef21
|
3 |
+
size 1064
|
checkpoint-50/trainer_state.json
ADDED
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06513809275664409,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 50,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0013027618551328818,
|
13 |
+
"grad_norm": 14.949752807617188,
|
14 |
+
"learning_rate": 4.0625e-06,
|
15 |
+
"loss": 1.3439,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0026055237102657635,
|
20 |
+
"grad_norm": 15.725403785705566,
|
21 |
+
"learning_rate": 8.125e-06,
|
22 |
+
"loss": 1.3354,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0039082855653986455,
|
27 |
+
"grad_norm": 12.41278076171875,
|
28 |
+
"learning_rate": 1.2187499999999998e-05,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.005211047420531527,
|
34 |
+
"grad_norm": 6.782334327697754,
|
35 |
+
"learning_rate": 1.625e-05,
|
36 |
+
"loss": 1.2634,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.006513809275664409,
|
41 |
+
"grad_norm": 3.730219841003418,
|
42 |
+
"learning_rate": 2.03125e-05,
|
43 |
+
"loss": 1.1704,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.007816571130797291,
|
48 |
+
"grad_norm": 2.547757863998413,
|
49 |
+
"learning_rate": 2.4374999999999996e-05,
|
50 |
+
"loss": 1.165,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.009119332985930172,
|
55 |
+
"grad_norm": 2.4353976249694824,
|
56 |
+
"learning_rate": 2.8437499999999997e-05,
|
57 |
+
"loss": 1.1567,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.010422094841063054,
|
62 |
+
"grad_norm": 2.218895673751831,
|
63 |
+
"learning_rate": 3.25e-05,
|
64 |
+
"loss": 1.0846,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.011724856696195935,
|
69 |
+
"grad_norm": 1.7433233261108398,
|
70 |
+
"learning_rate": 3.6562499999999994e-05,
|
71 |
+
"loss": 0.9816,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.013027618551328817,
|
76 |
+
"grad_norm": 1.6148579120635986,
|
77 |
+
"learning_rate": 4.0625e-05,
|
78 |
+
"loss": 1.0869,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0143303804064617,
|
83 |
+
"grad_norm": 1.5065230131149292,
|
84 |
+
"learning_rate": 4.4687499999999995e-05,
|
85 |
+
"loss": 0.9625,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.015633142261594582,
|
90 |
+
"grad_norm": 1.4786823987960815,
|
91 |
+
"learning_rate": 4.874999999999999e-05,
|
92 |
+
"loss": 1.0489,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.016935904116727463,
|
97 |
+
"grad_norm": 1.2991230487823486,
|
98 |
+
"learning_rate": 5.2812499999999996e-05,
|
99 |
+
"loss": 0.9935,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.018238665971860343,
|
104 |
+
"grad_norm": 1.3199464082717896,
|
105 |
+
"learning_rate": 5.687499999999999e-05,
|
106 |
+
"loss": 1.0188,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.019541427826993224,
|
111 |
+
"grad_norm": 1.2793257236480713,
|
112 |
+
"learning_rate": 6.09375e-05,
|
113 |
+
"loss": 1.0265,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.020844189682126108,
|
118 |
+
"grad_norm": 1.2210655212402344,
|
119 |
+
"learning_rate": 6.5e-05,
|
120 |
+
"loss": 0.9019,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02214695153725899,
|
125 |
+
"grad_norm": 1.3837445974349976,
|
126 |
+
"learning_rate": 6.499971563731688e-05,
|
127 |
+
"loss": 0.9487,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02344971339239187,
|
132 |
+
"grad_norm": 1.2946529388427734,
|
133 |
+
"learning_rate": 6.499886255424368e-05,
|
134 |
+
"loss": 1.0031,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.024752475247524754,
|
139 |
+
"grad_norm": 1.3142110109329224,
|
140 |
+
"learning_rate": 6.499744076570868e-05,
|
141 |
+
"loss": 0.9941,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.026055237102657634,
|
146 |
+
"grad_norm": 1.8206599950790405,
|
147 |
+
"learning_rate": 6.499545029659211e-05,
|
148 |
+
"loss": 0.9767,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.027357998957790515,
|
153 |
+
"grad_norm": 1.2736281156539917,
|
154 |
+
"learning_rate": 6.499289118172568e-05,
|
155 |
+
"loss": 0.9194,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0286607608129234,
|
160 |
+
"grad_norm": 1.8105640411376953,
|
161 |
+
"learning_rate": 6.498976346589196e-05,
|
162 |
+
"loss": 0.9853,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02996352266805628,
|
167 |
+
"grad_norm": 1.4621827602386475,
|
168 |
+
"learning_rate": 6.49860672038236e-05,
|
169 |
+
"loss": 0.9896,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.031266284523189164,
|
174 |
+
"grad_norm": 1.212299108505249,
|
175 |
+
"learning_rate": 6.498180246020238e-05,
|
176 |
+
"loss": 0.9684,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.032569046378322045,
|
181 |
+
"grad_norm": 1.2274290323257446,
|
182 |
+
"learning_rate": 6.49769693096581e-05,
|
183 |
+
"loss": 0.9831,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.033871808233454925,
|
188 |
+
"grad_norm": 1.2909352779388428,
|
189 |
+
"learning_rate": 6.49715678367672e-05,
|
190 |
+
"loss": 0.9971,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.035174570088587806,
|
195 |
+
"grad_norm": 1.2330715656280518,
|
196 |
+
"learning_rate": 6.49655981360514e-05,
|
197 |
+
"loss": 0.9923,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03647733194372069,
|
202 |
+
"grad_norm": 1.2433793544769287,
|
203 |
+
"learning_rate": 6.495906031197591e-05,
|
204 |
+
"loss": 0.9121,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03778009379885357,
|
209 |
+
"grad_norm": 1.2374027967453003,
|
210 |
+
"learning_rate": 6.49519544789477e-05,
|
211 |
+
"loss": 0.9224,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03908285565398645,
|
216 |
+
"grad_norm": 1.2204357385635376,
|
217 |
+
"learning_rate": 6.494428076131346e-05,
|
218 |
+
"loss": 0.919,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.040385617509119336,
|
223 |
+
"grad_norm": 1.1927292346954346,
|
224 |
+
"learning_rate": 6.493603929335744e-05,
|
225 |
+
"loss": 0.9589,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.041688379364252216,
|
230 |
+
"grad_norm": 1.1353641748428345,
|
231 |
+
"learning_rate": 6.492723021929908e-05,
|
232 |
+
"loss": 0.8869,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.0429911412193851,
|
237 |
+
"grad_norm": 1.212263822555542,
|
238 |
+
"learning_rate": 6.49178536932905e-05,
|
239 |
+
"loss": 0.8934,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.04429390307451798,
|
244 |
+
"grad_norm": 1.0893241167068481,
|
245 |
+
"learning_rate": 6.49079098794138e-05,
|
246 |
+
"loss": 0.8718,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04559666492965086,
|
251 |
+
"grad_norm": 1.1801607608795166,
|
252 |
+
"learning_rate": 6.489739895167818e-05,
|
253 |
+
"loss": 0.9774,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04689942678478374,
|
258 |
+
"grad_norm": 1.1302330493927002,
|
259 |
+
"learning_rate": 6.488632109401691e-05,
|
260 |
+
"loss": 0.9584,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04820218863991663,
|
265 |
+
"grad_norm": 1.1432682275772095,
|
266 |
+
"learning_rate": 6.487467650028411e-05,
|
267 |
+
"loss": 0.9452,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04950495049504951,
|
272 |
+
"grad_norm": 1.1399481296539307,
|
273 |
+
"learning_rate": 6.486246537425133e-05,
|
274 |
+
"loss": 0.9017,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.05080771235018239,
|
279 |
+
"grad_norm": 1.0911235809326172,
|
280 |
+
"learning_rate": 6.484968792960403e-05,
|
281 |
+
"loss": 0.9036,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.05211047420531527,
|
286 |
+
"grad_norm": 1.071078896522522,
|
287 |
+
"learning_rate": 6.48363443899378e-05,
|
288 |
+
"loss": 0.9273,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.05341323606044815,
|
293 |
+
"grad_norm": 1.053589105606079,
|
294 |
+
"learning_rate": 6.482243498875449e-05,
|
295 |
+
"loss": 0.8847,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.05471599791558103,
|
300 |
+
"grad_norm": 1.109771490097046,
|
301 |
+
"learning_rate": 6.480795996945806e-05,
|
302 |
+
"loss": 0.9364,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.05601875977071391,
|
307 |
+
"grad_norm": 1.1093286275863647,
|
308 |
+
"learning_rate": 6.479291958535037e-05,
|
309 |
+
"loss": 0.9088,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.0573215216258468,
|
314 |
+
"grad_norm": 1.0716255903244019,
|
315 |
+
"learning_rate": 6.477731409962675e-05,
|
316 |
+
"loss": 0.8885,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.05862428348097968,
|
321 |
+
"grad_norm": 1.1552095413208008,
|
322 |
+
"learning_rate": 6.476114378537138e-05,
|
323 |
+
"loss": 0.9736,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05992704533611256,
|
328 |
+
"grad_norm": 1.1647394895553589,
|
329 |
+
"learning_rate": 6.474440892555249e-05,
|
330 |
+
"loss": 0.9138,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06122980719124544,
|
335 |
+
"grad_norm": 1.1463412046432495,
|
336 |
+
"learning_rate": 6.472710981301745e-05,
|
337 |
+
"loss": 0.9204,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.06253256904637833,
|
342 |
+
"grad_norm": 1.175421118736267,
|
343 |
+
"learning_rate": 6.470924675048762e-05,
|
344 |
+
"loss": 0.9119,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.06383533090151121,
|
349 |
+
"grad_norm": 1.9249529838562012,
|
350 |
+
"learning_rate": 6.469082005055304e-05,
|
351 |
+
"loss": 0.8639,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.06513809275664409,
|
356 |
+
"grad_norm": 1.1802655458450317,
|
357 |
+
"learning_rate": 6.467183003566701e-05,
|
358 |
+
"loss": 0.9352,
|
359 |
+
"step": 50
|
360 |
+
}
|
361 |
+
],
|
362 |
+
"logging_steps": 1,
|
363 |
+
"max_steps": 767,
|
364 |
+
"num_input_tokens_seen": 0,
|
365 |
+
"num_train_epochs": 1,
|
366 |
+
"save_steps": 50,
|
367 |
+
"stateful_callbacks": {
|
368 |
+
"TrainerControl": {
|
369 |
+
"args": {
|
370 |
+
"should_epoch_stop": false,
|
371 |
+
"should_evaluate": false,
|
372 |
+
"should_log": false,
|
373 |
+
"should_save": true,
|
374 |
+
"should_training_stop": false
|
375 |
+
},
|
376 |
+
"attributes": {}
|
377 |
+
}
|
378 |
+
},
|
379 |
+
"total_flos": 7.689981500994355e+16,
|
380 |
+
"train_batch_size": 6,
|
381 |
+
"trial_name": null,
|
382 |
+
"trial_params": null
|
383 |
+
}
|
checkpoint-50/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c6cdd050f0e9f3e909bcca2e2c0488bdf293a6b22313a332d8541c60d48d06
|
3 |
+
size 5432
|