Training in progress, epoch 1, checkpoint
Browse files- checkpoint-126/README.md +219 -0
- checkpoint-126/adapter_config.json +28 -0
- checkpoint-126/adapter_model.safetensors +3 -0
- checkpoint-126/optimizer.pt +3 -0
- checkpoint-126/rng_state.pth +3 -0
- checkpoint-126/scheduler.pt +3 -0
- checkpoint-126/trainer_state.json +823 -0
- checkpoint-126/training_args.bin +3 -0
checkpoint-126/README.md
ADDED
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: yentinglin/Taiwan-LLM-7B-v2.0-chat
|
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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
+
## Training procedure
|
202 |
+
|
203 |
+
|
204 |
+
The following `bitsandbytes` quantization config was used during training:
|
205 |
+
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: False
|
207 |
+
- load_in_4bit: True
|
208 |
+
- llm_int8_threshold: 6.0
|
209 |
+
- llm_int8_skip_modules: None
|
210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
+
- llm_int8_has_fp16_weight: False
|
212 |
+
- bnb_4bit_quant_type: nf4
|
213 |
+
- bnb_4bit_use_double_quant: True
|
214 |
+
- bnb_4bit_compute_dtype: float16
|
215 |
+
|
216 |
+
### Framework versions
|
217 |
+
|
218 |
+
|
219 |
+
- PEFT 0.6.0
|
checkpoint-126/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 4,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"down_proj",
|
20 |
+
"o_proj",
|
21 |
+
"k_proj",
|
22 |
+
"up_proj",
|
23 |
+
"v_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"q_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-126/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af22ad5df74625210713ef368d0b02c7f058adca19bded43a1f2e84795a71ec9
|
3 |
+
size 40036040
|
checkpoint-126/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3d39892cb0e6c164834644982c11eeeae410662780f6379a691fe1399c9880c
|
3 |
+
size 80218053
|
checkpoint-126/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cd71f7eb73f30bec98c585c9720ca9b3062fbbfa7f2d0655d840524ceb405b6
|
3 |
+
size 14575
|
checkpoint-126/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc28c2798df4d985bf5e974db0962dc19ccd75c172c3e2c7b01514ef56d473c3
|
3 |
+
size 627
|
checkpoint-126/trainer_state.json
ADDED
@@ -0,0 +1,823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0161290322580645,
|
5 |
+
"eval_steps": 25,
|
6 |
+
"global_step": 126,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 0.0,
|
14 |
+
"loss": 4.0553,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"eval_loss": 4.052073955535889,
|
20 |
+
"eval_runtime": 57.3905,
|
21 |
+
"eval_samples_per_second": 4.356,
|
22 |
+
"eval_steps_per_second": 4.356,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.02,
|
27 |
+
"learning_rate": 2e-05,
|
28 |
+
"loss": 4.3696,
|
29 |
+
"step": 2
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.02,
|
33 |
+
"learning_rate": 4e-05,
|
34 |
+
"loss": 4.2401,
|
35 |
+
"step": 3
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.03,
|
39 |
+
"learning_rate": 6e-05,
|
40 |
+
"loss": 4.3077,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.04,
|
45 |
+
"learning_rate": 8e-05,
|
46 |
+
"loss": 4.0741,
|
47 |
+
"step": 5
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.05,
|
51 |
+
"learning_rate": 0.0001,
|
52 |
+
"loss": 4.1673,
|
53 |
+
"step": 6
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.06,
|
57 |
+
"learning_rate": 0.00012,
|
58 |
+
"loss": 3.9378,
|
59 |
+
"step": 7
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.06,
|
63 |
+
"learning_rate": 0.00014,
|
64 |
+
"loss": 4.0167,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.07,
|
69 |
+
"learning_rate": 0.00016,
|
70 |
+
"loss": 3.5818,
|
71 |
+
"step": 9
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.08,
|
75 |
+
"learning_rate": 0.00018,
|
76 |
+
"loss": 3.9022,
|
77 |
+
"step": 10
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.09,
|
81 |
+
"learning_rate": 0.0002,
|
82 |
+
"loss": 3.7906,
|
83 |
+
"step": 11
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.1,
|
87 |
+
"learning_rate": 0.0001999979107245606,
|
88 |
+
"loss": 3.6776,
|
89 |
+
"step": 12
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.1,
|
93 |
+
"learning_rate": 0.00019999164298554375,
|
94 |
+
"loss": 3.4291,
|
95 |
+
"step": 13
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.11,
|
99 |
+
"learning_rate": 0.00019998119704485014,
|
100 |
+
"loss": 3.6101,
|
101 |
+
"step": 14
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.12,
|
105 |
+
"learning_rate": 0.00019996657333896877,
|
106 |
+
"loss": 3.5537,
|
107 |
+
"step": 15
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.13,
|
111 |
+
"learning_rate": 0.00019994777247895855,
|
112 |
+
"loss": 3.386,
|
113 |
+
"step": 16
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.14,
|
117 |
+
"learning_rate": 0.00019992479525042303,
|
118 |
+
"loss": 3.6359,
|
119 |
+
"step": 17
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.15,
|
123 |
+
"learning_rate": 0.00019989764261347736,
|
124 |
+
"loss": 3.6132,
|
125 |
+
"step": 18
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.15,
|
129 |
+
"learning_rate": 0.00019986631570270832,
|
130 |
+
"loss": 3.4794,
|
131 |
+
"step": 19
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.16,
|
135 |
+
"learning_rate": 0.00019983081582712685,
|
136 |
+
"loss": 3.2395,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.17,
|
141 |
+
"learning_rate": 0.00019979114447011323,
|
142 |
+
"loss": 3.2974,
|
143 |
+
"step": 21
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.18,
|
147 |
+
"learning_rate": 0.00019974730328935534,
|
148 |
+
"loss": 3.2698,
|
149 |
+
"step": 22
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.19,
|
153 |
+
"learning_rate": 0.0001996992941167792,
|
154 |
+
"loss": 3.3091,
|
155 |
+
"step": 23
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.19,
|
159 |
+
"learning_rate": 0.00019964711895847258,
|
160 |
+
"loss": 3.2017,
|
161 |
+
"step": 24
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.2,
|
165 |
+
"learning_rate": 0.00019959077999460095,
|
166 |
+
"loss": 3.2469,
|
167 |
+
"step": 25
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.2,
|
171 |
+
"eval_loss": 3.0720062255859375,
|
172 |
+
"eval_runtime": 61.8274,
|
173 |
+
"eval_samples_per_second": 4.044,
|
174 |
+
"eval_steps_per_second": 4.044,
|
175 |
+
"step": 25
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 0.21,
|
179 |
+
"learning_rate": 0.00019953027957931658,
|
180 |
+
"loss": 3.1102,
|
181 |
+
"step": 26
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.22,
|
185 |
+
"learning_rate": 0.00019946562024066014,
|
186 |
+
"loss": 3.1641,
|
187 |
+
"step": 27
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 0.23,
|
191 |
+
"learning_rate": 0.00019939680468045499,
|
192 |
+
"loss": 2.9779,
|
193 |
+
"step": 28
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.23,
|
197 |
+
"learning_rate": 0.00019932383577419432,
|
198 |
+
"loss": 3.104,
|
199 |
+
"step": 29
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.24,
|
203 |
+
"learning_rate": 0.00019924671657092096,
|
204 |
+
"loss": 2.7981,
|
205 |
+
"step": 30
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.25,
|
209 |
+
"learning_rate": 0.00019916545029310012,
|
210 |
+
"loss": 2.7673,
|
211 |
+
"step": 31
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.26,
|
215 |
+
"learning_rate": 0.00019908004033648453,
|
216 |
+
"loss": 2.8478,
|
217 |
+
"step": 32
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.27,
|
221 |
+
"learning_rate": 0.00019899049026997272,
|
222 |
+
"loss": 2.7539,
|
223 |
+
"step": 33
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 0.27,
|
227 |
+
"learning_rate": 0.00019889680383545973,
|
228 |
+
"loss": 2.726,
|
229 |
+
"step": 34
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.28,
|
233 |
+
"learning_rate": 0.00019879898494768093,
|
234 |
+
"loss": 2.81,
|
235 |
+
"step": 35
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.29,
|
239 |
+
"learning_rate": 0.00019869703769404828,
|
240 |
+
"loss": 2.6177,
|
241 |
+
"step": 36
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.3,
|
245 |
+
"learning_rate": 0.00019859096633447965,
|
246 |
+
"loss": 2.6046,
|
247 |
+
"step": 37
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.31,
|
251 |
+
"learning_rate": 0.00019848077530122083,
|
252 |
+
"loss": 2.5004,
|
253 |
+
"step": 38
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 0.31,
|
257 |
+
"learning_rate": 0.0001983664691986601,
|
258 |
+
"loss": 2.4993,
|
259 |
+
"step": 39
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 0.32,
|
263 |
+
"learning_rate": 0.00019824805280313623,
|
264 |
+
"loss": 2.2775,
|
265 |
+
"step": 40
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.33,
|
269 |
+
"learning_rate": 0.00019812553106273847,
|
270 |
+
"loss": 2.3306,
|
271 |
+
"step": 41
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.34,
|
275 |
+
"learning_rate": 0.00019799890909710013,
|
276 |
+
"loss": 2.236,
|
277 |
+
"step": 42
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.35,
|
281 |
+
"learning_rate": 0.00019786819219718443,
|
282 |
+
"loss": 2.2798,
|
283 |
+
"step": 43
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.35,
|
287 |
+
"learning_rate": 0.0001977333858250636,
|
288 |
+
"loss": 2.2178,
|
289 |
+
"step": 44
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.36,
|
293 |
+
"learning_rate": 0.00019759449561369038,
|
294 |
+
"loss": 1.9915,
|
295 |
+
"step": 45
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.37,
|
299 |
+
"learning_rate": 0.00019745152736666302,
|
300 |
+
"loss": 2.3066,
|
301 |
+
"step": 46
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.38,
|
305 |
+
"learning_rate": 0.00019730448705798239,
|
306 |
+
"loss": 2.1409,
|
307 |
+
"step": 47
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.39,
|
311 |
+
"learning_rate": 0.00019715338083180269,
|
312 |
+
"loss": 1.9976,
|
313 |
+
"step": 48
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.4,
|
317 |
+
"learning_rate": 0.00019699821500217434,
|
318 |
+
"loss": 2.1843,
|
319 |
+
"step": 49
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.4,
|
323 |
+
"learning_rate": 0.0001968389960527806,
|
324 |
+
"loss": 2.1539,
|
325 |
+
"step": 50
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.4,
|
329 |
+
"eval_loss": 1.9486372470855713,
|
330 |
+
"eval_runtime": 61.7944,
|
331 |
+
"eval_samples_per_second": 4.046,
|
332 |
+
"eval_steps_per_second": 4.046,
|
333 |
+
"step": 50
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.41,
|
337 |
+
"learning_rate": 0.0001966757306366662,
|
338 |
+
"loss": 2.2096,
|
339 |
+
"step": 51
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.42,
|
343 |
+
"learning_rate": 0.00019650842557595967,
|
344 |
+
"loss": 2.0241,
|
345 |
+
"step": 52
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.43,
|
349 |
+
"learning_rate": 0.00019633708786158806,
|
350 |
+
"loss": 1.8814,
|
351 |
+
"step": 53
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.44,
|
355 |
+
"learning_rate": 0.00019616172465298492,
|
356 |
+
"loss": 1.9953,
|
357 |
+
"step": 54
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.44,
|
361 |
+
"learning_rate": 0.00019598234327779118,
|
362 |
+
"loss": 1.9807,
|
363 |
+
"step": 55
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.45,
|
367 |
+
"learning_rate": 0.0001957989512315489,
|
368 |
+
"loss": 1.9743,
|
369 |
+
"step": 56
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.46,
|
373 |
+
"learning_rate": 0.00019561155617738797,
|
374 |
+
"loss": 1.867,
|
375 |
+
"step": 57
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.47,
|
379 |
+
"learning_rate": 0.00019542016594570615,
|
380 |
+
"loss": 1.8289,
|
381 |
+
"step": 58
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.48,
|
385 |
+
"learning_rate": 0.00019522478853384155,
|
386 |
+
"loss": 1.9712,
|
387 |
+
"step": 59
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.48,
|
391 |
+
"learning_rate": 0.00019502543210573881,
|
392 |
+
"loss": 1.6946,
|
393 |
+
"step": 60
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.49,
|
397 |
+
"learning_rate": 0.00019482210499160765,
|
398 |
+
"loss": 1.8674,
|
399 |
+
"step": 61
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.5,
|
403 |
+
"learning_rate": 0.00019461481568757506,
|
404 |
+
"loss": 1.6849,
|
405 |
+
"step": 62
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.51,
|
409 |
+
"learning_rate": 0.00019440357285533,
|
410 |
+
"loss": 1.7003,
|
411 |
+
"step": 63
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.52,
|
415 |
+
"learning_rate": 0.00019418838532176173,
|
416 |
+
"loss": 1.7021,
|
417 |
+
"step": 64
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.52,
|
421 |
+
"learning_rate": 0.00019396926207859084,
|
422 |
+
"loss": 1.8302,
|
423 |
+
"step": 65
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.53,
|
427 |
+
"learning_rate": 0.0001937462122819935,
|
428 |
+
"loss": 1.8549,
|
429 |
+
"step": 66
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.54,
|
433 |
+
"learning_rate": 0.000193519245252219,
|
434 |
+
"loss": 1.8946,
|
435 |
+
"step": 67
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.55,
|
439 |
+
"learning_rate": 0.0001932883704732001,
|
440 |
+
"loss": 1.799,
|
441 |
+
"step": 68
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.56,
|
445 |
+
"learning_rate": 0.00019305359759215685,
|
446 |
+
"loss": 1.7541,
|
447 |
+
"step": 69
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.56,
|
451 |
+
"learning_rate": 0.00019281493641919368,
|
452 |
+
"loss": 1.7145,
|
453 |
+
"step": 70
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.57,
|
457 |
+
"learning_rate": 0.00019257239692688907,
|
458 |
+
"loss": 1.8254,
|
459 |
+
"step": 71
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.58,
|
463 |
+
"learning_rate": 0.00019232598924987903,
|
464 |
+
"loss": 1.6161,
|
465 |
+
"step": 72
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.59,
|
469 |
+
"learning_rate": 0.00019207572368443385,
|
470 |
+
"loss": 1.5698,
|
471 |
+
"step": 73
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.6,
|
475 |
+
"learning_rate": 0.00019182161068802741,
|
476 |
+
"loss": 1.8155,
|
477 |
+
"step": 74
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.6,
|
481 |
+
"learning_rate": 0.0001915636608789006,
|
482 |
+
"loss": 1.6997,
|
483 |
+
"step": 75
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.6,
|
487 |
+
"eval_loss": 1.6153544187545776,
|
488 |
+
"eval_runtime": 61.8069,
|
489 |
+
"eval_samples_per_second": 4.045,
|
490 |
+
"eval_steps_per_second": 4.045,
|
491 |
+
"step": 75
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.61,
|
495 |
+
"learning_rate": 0.00019130188503561741,
|
496 |
+
"loss": 1.6507,
|
497 |
+
"step": 76
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.62,
|
501 |
+
"learning_rate": 0.0001910362940966147,
|
502 |
+
"loss": 1.6035,
|
503 |
+
"step": 77
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.63,
|
507 |
+
"learning_rate": 0.00019076689915974488,
|
508 |
+
"loss": 1.4493,
|
509 |
+
"step": 78
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.64,
|
513 |
+
"learning_rate": 0.00019049371148181253,
|
514 |
+
"loss": 1.5494,
|
515 |
+
"step": 79
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.65,
|
519 |
+
"learning_rate": 0.0001902167424781038,
|
520 |
+
"loss": 1.5386,
|
521 |
+
"step": 80
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.65,
|
525 |
+
"learning_rate": 0.00018993600372190932,
|
526 |
+
"loss": 1.467,
|
527 |
+
"step": 81
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.66,
|
531 |
+
"learning_rate": 0.00018965150694404094,
|
532 |
+
"loss": 1.6658,
|
533 |
+
"step": 82
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.67,
|
537 |
+
"learning_rate": 0.00018936326403234125,
|
538 |
+
"loss": 1.6175,
|
539 |
+
"step": 83
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.68,
|
543 |
+
"learning_rate": 0.00018907128703118695,
|
544 |
+
"loss": 1.6551,
|
545 |
+
"step": 84
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.69,
|
549 |
+
"learning_rate": 0.00018877558814098561,
|
550 |
+
"loss": 1.409,
|
551 |
+
"step": 85
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.69,
|
555 |
+
"learning_rate": 0.00018847617971766577,
|
556 |
+
"loss": 1.4879,
|
557 |
+
"step": 86
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.7,
|
561 |
+
"learning_rate": 0.0001881730742721608,
|
562 |
+
"loss": 1.3067,
|
563 |
+
"step": 87
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.71,
|
567 |
+
"learning_rate": 0.00018786628446988593,
|
568 |
+
"loss": 1.6869,
|
569 |
+
"step": 88
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.72,
|
573 |
+
"learning_rate": 0.0001875558231302091,
|
574 |
+
"loss": 1.5962,
|
575 |
+
"step": 89
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.73,
|
579 |
+
"learning_rate": 0.00018724170322591537,
|
580 |
+
"loss": 1.3352,
|
581 |
+
"step": 90
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.73,
|
585 |
+
"learning_rate": 0.00018692393788266479,
|
586 |
+
"loss": 1.5016,
|
587 |
+
"step": 91
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.74,
|
591 |
+
"learning_rate": 0.00018660254037844388,
|
592 |
+
"loss": 1.6951,
|
593 |
+
"step": 92
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.75,
|
597 |
+
"learning_rate": 0.00018627752414301086,
|
598 |
+
"loss": 1.5388,
|
599 |
+
"step": 93
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.76,
|
603 |
+
"learning_rate": 0.00018594890275733453,
|
604 |
+
"loss": 1.3656,
|
605 |
+
"step": 94
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.77,
|
609 |
+
"learning_rate": 0.00018561668995302667,
|
610 |
+
"loss": 1.4599,
|
611 |
+
"step": 95
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.77,
|
615 |
+
"learning_rate": 0.0001852808996117683,
|
616 |
+
"loss": 1.3428,
|
617 |
+
"step": 96
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.78,
|
621 |
+
"learning_rate": 0.00018494154576472976,
|
622 |
+
"loss": 1.2147,
|
623 |
+
"step": 97
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 0.79,
|
627 |
+
"learning_rate": 0.0001845986425919841,
|
628 |
+
"loss": 1.4761,
|
629 |
+
"step": 98
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.8,
|
633 |
+
"learning_rate": 0.00018425220442191495,
|
634 |
+
"loss": 1.4571,
|
635 |
+
"step": 99
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.81,
|
639 |
+
"learning_rate": 0.00018390224573061747,
|
640 |
+
"loss": 1.5076,
|
641 |
+
"step": 100
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.81,
|
645 |
+
"eval_loss": 1.49380362033844,
|
646 |
+
"eval_runtime": 61.7975,
|
647 |
+
"eval_samples_per_second": 4.045,
|
648 |
+
"eval_steps_per_second": 4.045,
|
649 |
+
"step": 100
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.81,
|
653 |
+
"learning_rate": 0.00018354878114129367,
|
654 |
+
"loss": 1.3776,
|
655 |
+
"step": 101
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.82,
|
659 |
+
"learning_rate": 0.00018319182542364117,
|
660 |
+
"loss": 1.437,
|
661 |
+
"step": 102
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.83,
|
665 |
+
"learning_rate": 0.00018283139349323634,
|
666 |
+
"loss": 1.3558,
|
667 |
+
"step": 103
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.84,
|
671 |
+
"learning_rate": 0.0001824675004109107,
|
672 |
+
"loss": 1.4502,
|
673 |
+
"step": 104
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.85,
|
677 |
+
"learning_rate": 0.00018210016138212187,
|
678 |
+
"loss": 1.3451,
|
679 |
+
"step": 105
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.85,
|
683 |
+
"learning_rate": 0.00018172939175631808,
|
684 |
+
"loss": 1.403,
|
685 |
+
"step": 106
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.86,
|
689 |
+
"learning_rate": 0.00018135520702629675,
|
690 |
+
"loss": 1.1523,
|
691 |
+
"step": 107
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.87,
|
695 |
+
"learning_rate": 0.00018097762282755727,
|
696 |
+
"loss": 1.2302,
|
697 |
+
"step": 108
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.88,
|
701 |
+
"learning_rate": 0.00018059665493764743,
|
702 |
+
"loss": 1.4151,
|
703 |
+
"step": 109
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.89,
|
707 |
+
"learning_rate": 0.0001802123192755044,
|
708 |
+
"loss": 1.4853,
|
709 |
+
"step": 110
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.9,
|
713 |
+
"learning_rate": 0.0001798246319007893,
|
714 |
+
"loss": 1.2571,
|
715 |
+
"step": 111
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.9,
|
719 |
+
"learning_rate": 0.0001794336090132164,
|
720 |
+
"loss": 1.3594,
|
721 |
+
"step": 112
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.91,
|
725 |
+
"learning_rate": 0.00017903926695187595,
|
726 |
+
"loss": 1.3997,
|
727 |
+
"step": 113
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.92,
|
731 |
+
"learning_rate": 0.00017864162219455163,
|
732 |
+
"loss": 1.5718,
|
733 |
+
"step": 114
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.93,
|
737 |
+
"learning_rate": 0.00017824069135703198,
|
738 |
+
"loss": 1.314,
|
739 |
+
"step": 115
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.94,
|
743 |
+
"learning_rate": 0.00017783649119241602,
|
744 |
+
"loss": 1.3595,
|
745 |
+
"step": 116
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.94,
|
749 |
+
"learning_rate": 0.00017742903859041325,
|
750 |
+
"loss": 1.4467,
|
751 |
+
"step": 117
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.95,
|
755 |
+
"learning_rate": 0.00017701835057663798,
|
756 |
+
"loss": 1.2837,
|
757 |
+
"step": 118
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.96,
|
761 |
+
"learning_rate": 0.0001766044443118978,
|
762 |
+
"loss": 1.2669,
|
763 |
+
"step": 119
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.97,
|
767 |
+
"learning_rate": 0.00017618733709147662,
|
768 |
+
"loss": 1.3115,
|
769 |
+
"step": 120
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.98,
|
773 |
+
"learning_rate": 0.0001757670463444118,
|
774 |
+
"loss": 1.1836,
|
775 |
+
"step": 121
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.98,
|
779 |
+
"learning_rate": 0.00017534358963276607,
|
780 |
+
"loss": 1.6092,
|
781 |
+
"step": 122
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.99,
|
785 |
+
"learning_rate": 0.00017491698465089362,
|
786 |
+
"loss": 1.2288,
|
787 |
+
"step": 123
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 1.0,
|
791 |
+
"learning_rate": 0.00017448724922470058,
|
792 |
+
"loss": 1.2305,
|
793 |
+
"step": 124
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 1.01,
|
797 |
+
"learning_rate": 0.00017405440131090048,
|
798 |
+
"loss": 1.3794,
|
799 |
+
"step": 125
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 1.01,
|
803 |
+
"eval_loss": 1.4039632081985474,
|
804 |
+
"eval_runtime": 61.7879,
|
805 |
+
"eval_samples_per_second": 4.046,
|
806 |
+
"eval_steps_per_second": 4.046,
|
807 |
+
"step": 125
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 1.02,
|
811 |
+
"learning_rate": 0.00017361845899626355,
|
812 |
+
"loss": 1.2283,
|
813 |
+
"step": 126
|
814 |
+
}
|
815 |
+
],
|
816 |
+
"logging_steps": 1,
|
817 |
+
"max_steps": 496,
|
818 |
+
"num_train_epochs": 4,
|
819 |
+
"save_steps": 500,
|
820 |
+
"total_flos": 4.12261207202857e+16,
|
821 |
+
"trial_name": null,
|
822 |
+
"trial_params": null
|
823 |
+
}
|
checkpoint-126/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29182789cc886c4cb1e203599999900c580a72f92286132414128006e2d749f4
|
3 |
+
size 4603
|