Training in progress, epoch 3, checkpoint
Browse files- checkpoint-379/README.md +219 -0
- checkpoint-379/adapter_config.json +28 -0
- checkpoint-379/adapter_model.safetensors +3 -0
- checkpoint-379/optimizer.pt +3 -0
- checkpoint-379/rng_state.pth +3 -0
- checkpoint-379/scheduler.pt +3 -0
- checkpoint-379/trainer_state.json +2421 -0
- checkpoint-379/training_args.bin +3 -0
checkpoint-379/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-379/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-379/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94058099b18b4647a4d20a94b1a4abe758ef86cb8cb2a068e98df47fac66893e
|
3 |
+
size 40036040
|
checkpoint-379/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:210253546aafa90779a51e21f936caa08c6774396d8eda589480362b9e74c8ef
|
3 |
+
size 80218501
|
checkpoint-379/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dffd2cdecf41d109929fd36ee89039ceabfd610fe0b41661f7966676921b14d5
|
3 |
+
size 14575
|
checkpoint-379/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38bf6c374a8dda179bd8f487fe2fb1461b8b291d2d21309894825836dc0d89f5
|
3 |
+
size 627
|
checkpoint-379/trainer_state.json
ADDED
@@ -0,0 +1,2421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0161290322580645,
|
5 |
+
"eval_steps": 25,
|
6 |
+
"global_step": 379,
|
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 |
+
"epoch": 1.0,
|
817 |
+
"learning_rate": 0.00017317944049686124,
|
818 |
+
"loss": 1.2627,
|
819 |
+
"step": 127
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 1.01,
|
823 |
+
"learning_rate": 0.00017273736415730488,
|
824 |
+
"loss": 1.2911,
|
825 |
+
"step": 128
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 1.02,
|
829 |
+
"learning_rate": 0.00017229224844997928,
|
830 |
+
"loss": 1.1225,
|
831 |
+
"step": 129
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 1.03,
|
835 |
+
"learning_rate": 0.00017184411197427077,
|
836 |
+
"loss": 1.3,
|
837 |
+
"step": 130
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 1.03,
|
841 |
+
"learning_rate": 0.00017139297345578994,
|
842 |
+
"loss": 1.1852,
|
843 |
+
"step": 131
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 1.04,
|
847 |
+
"learning_rate": 0.0001709388517455893,
|
848 |
+
"loss": 1.1986,
|
849 |
+
"step": 132
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.05,
|
853 |
+
"learning_rate": 0.00017048176581937563,
|
854 |
+
"loss": 1.3396,
|
855 |
+
"step": 133
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 1.06,
|
859 |
+
"learning_rate": 0.00017002173477671686,
|
860 |
+
"loss": 1.3584,
|
861 |
+
"step": 134
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 1.07,
|
865 |
+
"learning_rate": 0.0001695587778402442,
|
866 |
+
"loss": 1.2763,
|
867 |
+
"step": 135
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 1.07,
|
871 |
+
"learning_rate": 0.0001690929143548488,
|
872 |
+
"loss": 1.3017,
|
873 |
+
"step": 136
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 1.08,
|
877 |
+
"learning_rate": 0.0001686241637868734,
|
878 |
+
"loss": 1.2383,
|
879 |
+
"step": 137
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 1.09,
|
883 |
+
"learning_rate": 0.00016815254572329896,
|
884 |
+
"loss": 1.238,
|
885 |
+
"step": 138
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.1,
|
889 |
+
"learning_rate": 0.00016767807987092621,
|
890 |
+
"loss": 1.2702,
|
891 |
+
"step": 139
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 1.11,
|
895 |
+
"learning_rate": 0.00016720078605555224,
|
896 |
+
"loss": 1.3573,
|
897 |
+
"step": 140
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 1.11,
|
901 |
+
"learning_rate": 0.00016672068422114196,
|
902 |
+
"loss": 1.2863,
|
903 |
+
"step": 141
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 1.12,
|
907 |
+
"learning_rate": 0.0001662377944289948,
|
908 |
+
"loss": 1.2192,
|
909 |
+
"step": 142
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 1.13,
|
913 |
+
"learning_rate": 0.0001657521368569064,
|
914 |
+
"loss": 1.1934,
|
915 |
+
"step": 143
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 1.14,
|
919 |
+
"learning_rate": 0.00016526373179832546,
|
920 |
+
"loss": 1.1558,
|
921 |
+
"step": 144
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 1.15,
|
925 |
+
"learning_rate": 0.00016477259966150588,
|
926 |
+
"loss": 1.3684,
|
927 |
+
"step": 145
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.16,
|
931 |
+
"learning_rate": 0.00016427876096865394,
|
932 |
+
"loss": 1.5386,
|
933 |
+
"step": 146
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.16,
|
937 |
+
"learning_rate": 0.0001637822363550706,
|
938 |
+
"loss": 1.2404,
|
939 |
+
"step": 147
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.17,
|
943 |
+
"learning_rate": 0.00016328304656828952,
|
944 |
+
"loss": 1.2416,
|
945 |
+
"step": 148
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 1.18,
|
949 |
+
"learning_rate": 0.00016278121246720987,
|
950 |
+
"loss": 1.3613,
|
951 |
+
"step": 149
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 1.19,
|
955 |
+
"learning_rate": 0.00016227675502122492,
|
956 |
+
"loss": 1.2755,
|
957 |
+
"step": 150
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.19,
|
961 |
+
"eval_loss": 1.3754363059997559,
|
962 |
+
"eval_runtime": 61.7475,
|
963 |
+
"eval_samples_per_second": 4.049,
|
964 |
+
"eval_steps_per_second": 4.049,
|
965 |
+
"step": 150
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 1.2,
|
969 |
+
"learning_rate": 0.00016176969530934572,
|
970 |
+
"loss": 1.3912,
|
971 |
+
"step": 151
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 1.2,
|
975 |
+
"learning_rate": 0.0001612600545193203,
|
976 |
+
"loss": 1.2778,
|
977 |
+
"step": 152
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 1.21,
|
981 |
+
"learning_rate": 0.00016074785394674837,
|
982 |
+
"loss": 1.2326,
|
983 |
+
"step": 153
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 1.22,
|
987 |
+
"learning_rate": 0.0001602331149941915,
|
988 |
+
"loss": 1.2526,
|
989 |
+
"step": 154
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.23,
|
993 |
+
"learning_rate": 0.00015971585917027862,
|
994 |
+
"loss": 1.1176,
|
995 |
+
"step": 155
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 1.24,
|
999 |
+
"learning_rate": 0.0001591961080888076,
|
1000 |
+
"loss": 1.1617,
|
1001 |
+
"step": 156
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 1.24,
|
1005 |
+
"learning_rate": 0.0001586738834678418,
|
1006 |
+
"loss": 1.2921,
|
1007 |
+
"step": 157
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 1.25,
|
1011 |
+
"learning_rate": 0.00015814920712880267,
|
1012 |
+
"loss": 1.3704,
|
1013 |
+
"step": 158
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 1.26,
|
1017 |
+
"learning_rate": 0.00015762210099555803,
|
1018 |
+
"loss": 1.1412,
|
1019 |
+
"step": 159
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 1.27,
|
1023 |
+
"learning_rate": 0.00015709258709350582,
|
1024 |
+
"loss": 1.1516,
|
1025 |
+
"step": 160
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 1.28,
|
1029 |
+
"learning_rate": 0.00015656068754865387,
|
1030 |
+
"loss": 1.3323,
|
1031 |
+
"step": 161
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.28,
|
1035 |
+
"learning_rate": 0.00015602642458669528,
|
1036 |
+
"loss": 1.2082,
|
1037 |
+
"step": 162
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 1.29,
|
1041 |
+
"learning_rate": 0.0001554898205320797,
|
1042 |
+
"loss": 1.1952,
|
1043 |
+
"step": 163
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 1.3,
|
1047 |
+
"learning_rate": 0.0001549508978070806,
|
1048 |
+
"loss": 1.172,
|
1049 |
+
"step": 164
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 1.31,
|
1053 |
+
"learning_rate": 0.00015440967893085828,
|
1054 |
+
"loss": 1.3049,
|
1055 |
+
"step": 165
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 1.32,
|
1059 |
+
"learning_rate": 0.0001538661865185188,
|
1060 |
+
"loss": 1.1573,
|
1061 |
+
"step": 166
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 1.32,
|
1065 |
+
"learning_rate": 0.00015332044328016914,
|
1066 |
+
"loss": 1.3122,
|
1067 |
+
"step": 167
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 1.33,
|
1071 |
+
"learning_rate": 0.0001527724720199682,
|
1072 |
+
"loss": 1.2487,
|
1073 |
+
"step": 168
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.34,
|
1077 |
+
"learning_rate": 0.00015222229563517385,
|
1078 |
+
"loss": 1.2054,
|
1079 |
+
"step": 169
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 1.35,
|
1083 |
+
"learning_rate": 0.00015166993711518631,
|
1084 |
+
"loss": 1.1871,
|
1085 |
+
"step": 170
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 1.36,
|
1089 |
+
"learning_rate": 0.00015111541954058734,
|
1090 |
+
"loss": 1.1853,
|
1091 |
+
"step": 171
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 1.36,
|
1095 |
+
"learning_rate": 0.0001505587660821759,
|
1096 |
+
"loss": 1.2743,
|
1097 |
+
"step": 172
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 1.37,
|
1101 |
+
"learning_rate": 0.00015000000000000001,
|
1102 |
+
"loss": 1.1493,
|
1103 |
+
"step": 173
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 1.38,
|
1107 |
+
"learning_rate": 0.00014943914464238468,
|
1108 |
+
"loss": 1.2354,
|
1109 |
+
"step": 174
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.39,
|
1113 |
+
"learning_rate": 0.00014887622344495643,
|
1114 |
+
"loss": 1.1913,
|
1115 |
+
"step": 175
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.39,
|
1119 |
+
"eval_loss": 1.3428610563278198,
|
1120 |
+
"eval_runtime": 61.7873,
|
1121 |
+
"eval_samples_per_second": 4.046,
|
1122 |
+
"eval_steps_per_second": 4.046,
|
1123 |
+
"step": 175
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 1.4,
|
1127 |
+
"learning_rate": 0.00014831125992966385,
|
1128 |
+
"loss": 1.2415,
|
1129 |
+
"step": 176
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.41,
|
1133 |
+
"learning_rate": 0.0001477442777037949,
|
1134 |
+
"loss": 1.1343,
|
1135 |
+
"step": 177
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 1.41,
|
1139 |
+
"learning_rate": 0.00014717530045899038,
|
1140 |
+
"loss": 1.325,
|
1141 |
+
"step": 178
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 1.42,
|
1145 |
+
"learning_rate": 0.0001466043519702539,
|
1146 |
+
"loss": 1.3118,
|
1147 |
+
"step": 179
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 1.43,
|
1151 |
+
"learning_rate": 0.0001460314560949586,
|
1152 |
+
"loss": 1.2941,
|
1153 |
+
"step": 180
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 1.44,
|
1157 |
+
"learning_rate": 0.00014545663677185006,
|
1158 |
+
"loss": 1.1848,
|
1159 |
+
"step": 181
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 1.45,
|
1163 |
+
"learning_rate": 0.00014487991802004623,
|
1164 |
+
"loss": 1.1337,
|
1165 |
+
"step": 182
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 1.45,
|
1169 |
+
"learning_rate": 0.00014430132393803352,
|
1170 |
+
"loss": 1.1494,
|
1171 |
+
"step": 183
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.46,
|
1175 |
+
"learning_rate": 0.0001437208787026601,
|
1176 |
+
"loss": 1.2076,
|
1177 |
+
"step": 184
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 1.47,
|
1181 |
+
"learning_rate": 0.00014313860656812536,
|
1182 |
+
"loss": 1.1794,
|
1183 |
+
"step": 185
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 1.48,
|
1187 |
+
"learning_rate": 0.00014255453186496673,
|
1188 |
+
"loss": 1.2402,
|
1189 |
+
"step": 186
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 1.49,
|
1193 |
+
"learning_rate": 0.0001419686789990429,
|
1194 |
+
"loss": 1.2741,
|
1195 |
+
"step": 187
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 1.49,
|
1199 |
+
"learning_rate": 0.00014138107245051392,
|
1200 |
+
"loss": 1.2486,
|
1201 |
+
"step": 188
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 1.5,
|
1205 |
+
"learning_rate": 0.00014079173677281837,
|
1206 |
+
"loss": 1.2796,
|
1207 |
+
"step": 189
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.51,
|
1211 |
+
"learning_rate": 0.0001402006965916474,
|
1212 |
+
"loss": 1.0193,
|
1213 |
+
"step": 190
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.52,
|
1217 |
+
"learning_rate": 0.0001396079766039157,
|
1218 |
+
"loss": 1.1447,
|
1219 |
+
"step": 191
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"epoch": 1.53,
|
1223 |
+
"learning_rate": 0.0001390136015767295,
|
1224 |
+
"loss": 1.0318,
|
1225 |
+
"step": 192
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"epoch": 1.53,
|
1229 |
+
"learning_rate": 0.00013841759634635178,
|
1230 |
+
"loss": 1.1047,
|
1231 |
+
"step": 193
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 1.54,
|
1235 |
+
"learning_rate": 0.00013781998581716427,
|
1236 |
+
"loss": 1.1895,
|
1237 |
+
"step": 194
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 1.55,
|
1241 |
+
"learning_rate": 0.00013722079496062702,
|
1242 |
+
"loss": 1.1119,
|
1243 |
+
"step": 195
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 1.56,
|
1247 |
+
"learning_rate": 0.0001366200488142348,
|
1248 |
+
"loss": 1.0248,
|
1249 |
+
"step": 196
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 1.57,
|
1253 |
+
"learning_rate": 0.00013601777248047105,
|
1254 |
+
"loss": 1.0961,
|
1255 |
+
"step": 197
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.57,
|
1259 |
+
"learning_rate": 0.00013541399112575878,
|
1260 |
+
"loss": 1.2622,
|
1261 |
+
"step": 198
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 1.58,
|
1265 |
+
"learning_rate": 0.00013480872997940905,
|
1266 |
+
"loss": 1.1858,
|
1267 |
+
"step": 199
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 1.59,
|
1271 |
+
"learning_rate": 0.00013420201433256689,
|
1272 |
+
"loss": 1.1458,
|
1273 |
+
"step": 200
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 1.59,
|
1277 |
+
"eval_loss": 1.3336366415023804,
|
1278 |
+
"eval_runtime": 61.796,
|
1279 |
+
"eval_samples_per_second": 4.046,
|
1280 |
+
"eval_steps_per_second": 4.046,
|
1281 |
+
"step": 200
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.6,
|
1285 |
+
"learning_rate": 0.00013359386953715421,
|
1286 |
+
"loss": 1.3068,
|
1287 |
+
"step": 201
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.61,
|
1291 |
+
"learning_rate": 0.00013298432100481079,
|
1292 |
+
"loss": 1.0935,
|
1293 |
+
"step": 202
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 1.61,
|
1297 |
+
"learning_rate": 0.00013237339420583212,
|
1298 |
+
"loss": 1.1904,
|
1299 |
+
"step": 203
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.62,
|
1303 |
+
"learning_rate": 0.00013176111466810532,
|
1304 |
+
"loss": 1.1859,
|
1305 |
+
"step": 204
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.63,
|
1309 |
+
"learning_rate": 0.00013114750797604247,
|
1310 |
+
"loss": 1.1536,
|
1311 |
+
"step": 205
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.64,
|
1315 |
+
"learning_rate": 0.00013053259976951133,
|
1316 |
+
"loss": 1.2067,
|
1317 |
+
"step": 206
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 1.65,
|
1321 |
+
"learning_rate": 0.00012991641574276418,
|
1322 |
+
"loss": 1.2649,
|
1323 |
+
"step": 207
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.66,
|
1327 |
+
"learning_rate": 0.00012991641574276418,
|
1328 |
+
"loss": 1.2189,
|
1329 |
+
"step": 208
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.66,
|
1333 |
+
"learning_rate": 0.00012929898164336408,
|
1334 |
+
"loss": 1.301,
|
1335 |
+
"step": 209
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 1.67,
|
1339 |
+
"learning_rate": 0.00012868032327110904,
|
1340 |
+
"loss": 1.1506,
|
1341 |
+
"step": 210
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.68,
|
1345 |
+
"learning_rate": 0.0001280604664769539,
|
1346 |
+
"loss": 1.1964,
|
1347 |
+
"step": 211
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.69,
|
1351 |
+
"learning_rate": 0.00012743943716193016,
|
1352 |
+
"loss": 1.139,
|
1353 |
+
"step": 212
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.7,
|
1357 |
+
"learning_rate": 0.00012681726127606376,
|
1358 |
+
"loss": 1.2197,
|
1359 |
+
"step": 213
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.7,
|
1363 |
+
"learning_rate": 0.0001261939648172906,
|
1364 |
+
"loss": 1.1713,
|
1365 |
+
"step": 214
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.71,
|
1369 |
+
"learning_rate": 0.0001255695738303704,
|
1370 |
+
"loss": 1.2533,
|
1371 |
+
"step": 215
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.72,
|
1375 |
+
"learning_rate": 0.00012494411440579814,
|
1376 |
+
"loss": 1.1755,
|
1377 |
+
"step": 216
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.73,
|
1381 |
+
"learning_rate": 0.00012431761267871417,
|
1382 |
+
"loss": 0.9834,
|
1383 |
+
"step": 217
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.74,
|
1387 |
+
"learning_rate": 0.00012369009482781192,
|
1388 |
+
"loss": 1.1805,
|
1389 |
+
"step": 218
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.74,
|
1393 |
+
"learning_rate": 0.00012306158707424403,
|
1394 |
+
"loss": 1.0295,
|
1395 |
+
"step": 219
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.75,
|
1399 |
+
"learning_rate": 0.00012243211568052677,
|
1400 |
+
"loss": 1.0861,
|
1401 |
+
"step": 220
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.76,
|
1405 |
+
"learning_rate": 0.0001218017069494426,
|
1406 |
+
"loss": 1.3924,
|
1407 |
+
"step": 221
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 1.77,
|
1411 |
+
"learning_rate": 0.0001211703872229411,
|
1412 |
+
"loss": 1.1034,
|
1413 |
+
"step": 222
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.78,
|
1417 |
+
"learning_rate": 0.0001205381828810382,
|
1418 |
+
"loss": 1.0464,
|
1419 |
+
"step": 223
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.78,
|
1423 |
+
"learning_rate": 0.00011990512034071406,
|
1424 |
+
"loss": 1.1107,
|
1425 |
+
"step": 224
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.79,
|
1429 |
+
"learning_rate": 0.00011927122605480898,
|
1430 |
+
"loss": 1.1568,
|
1431 |
+
"step": 225
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.79,
|
1435 |
+
"eval_loss": 1.31128990650177,
|
1436 |
+
"eval_runtime": 61.808,
|
1437 |
+
"eval_samples_per_second": 4.045,
|
1438 |
+
"eval_steps_per_second": 4.045,
|
1439 |
+
"step": 225
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.8,
|
1443 |
+
"learning_rate": 0.00011863652651091823,
|
1444 |
+
"loss": 1.0532,
|
1445 |
+
"step": 226
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.81,
|
1449 |
+
"learning_rate": 0.00011800104823028515,
|
1450 |
+
"loss": 1.0956,
|
1451 |
+
"step": 227
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 1.82,
|
1455 |
+
"learning_rate": 0.00011736481776669306,
|
1456 |
+
"loss": 1.2576,
|
1457 |
+
"step": 228
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 1.82,
|
1461 |
+
"learning_rate": 0.00011672786170535552,
|
1462 |
+
"loss": 1.081,
|
1463 |
+
"step": 229
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 1.83,
|
1467 |
+
"learning_rate": 0.00011609020666180575,
|
1468 |
+
"loss": 1.097,
|
1469 |
+
"step": 230
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 1.84,
|
1473 |
+
"learning_rate": 0.00011545187928078406,
|
1474 |
+
"loss": 1.1571,
|
1475 |
+
"step": 231
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 1.85,
|
1479 |
+
"learning_rate": 0.0001148129062351249,
|
1480 |
+
"loss": 1.3143,
|
1481 |
+
"step": 232
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 1.86,
|
1485 |
+
"learning_rate": 0.00011417331422464205,
|
1486 |
+
"loss": 1.2877,
|
1487 |
+
"step": 233
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.86,
|
1491 |
+
"learning_rate": 0.00011353312997501313,
|
1492 |
+
"loss": 1.1032,
|
1493 |
+
"step": 234
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 1.87,
|
1497 |
+
"learning_rate": 0.00011289238023666266,
|
1498 |
+
"loss": 1.1401,
|
1499 |
+
"step": 235
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 1.88,
|
1503 |
+
"learning_rate": 0.00011225109178364455,
|
1504 |
+
"loss": 1.2596,
|
1505 |
+
"step": 236
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 1.89,
|
1509 |
+
"learning_rate": 0.00011160929141252303,
|
1510 |
+
"loss": 1.1803,
|
1511 |
+
"step": 237
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 1.9,
|
1515 |
+
"learning_rate": 0.00011096700594125318,
|
1516 |
+
"loss": 1.0706,
|
1517 |
+
"step": 238
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 1.91,
|
1521 |
+
"learning_rate": 0.00011032426220806018,
|
1522 |
+
"loss": 1.1804,
|
1523 |
+
"step": 239
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 1.91,
|
1527 |
+
"learning_rate": 0.00010968108707031792,
|
1528 |
+
"loss": 1.2334,
|
1529 |
+
"step": 240
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.92,
|
1533 |
+
"learning_rate": 0.00010903750740342682,
|
1534 |
+
"loss": 1.1523,
|
1535 |
+
"step": 241
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 1.93,
|
1539 |
+
"learning_rate": 0.00010839355009969068,
|
1540 |
+
"loss": 1.1336,
|
1541 |
+
"step": 242
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 1.94,
|
1545 |
+
"learning_rate": 0.0001077492420671931,
|
1546 |
+
"loss": 1.1287,
|
1547 |
+
"step": 243
|
1548 |
+
},
|
1549 |
+
{
|
1550 |
+
"epoch": 1.95,
|
1551 |
+
"learning_rate": 0.00010710461022867302,
|
1552 |
+
"loss": 1.181,
|
1553 |
+
"step": 244
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 1.95,
|
1557 |
+
"learning_rate": 0.0001064596815203998,
|
1558 |
+
"loss": 1.2882,
|
1559 |
+
"step": 245
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 1.96,
|
1563 |
+
"learning_rate": 0.00010581448289104758,
|
1564 |
+
"loss": 1.0872,
|
1565 |
+
"step": 246
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 1.97,
|
1569 |
+
"learning_rate": 0.00010516904130056946,
|
1570 |
+
"loss": 1.1117,
|
1571 |
+
"step": 247
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.98,
|
1575 |
+
"learning_rate": 0.00010452338371907064,
|
1576 |
+
"loss": 1.1874,
|
1577 |
+
"step": 248
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 1.99,
|
1581 |
+
"learning_rate": 0.0001038775371256817,
|
1582 |
+
"loss": 1.0474,
|
1583 |
+
"step": 249
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 1.99,
|
1587 |
+
"learning_rate": 0.00010323152850743107,
|
1588 |
+
"loss": 1.1845,
|
1589 |
+
"step": 250
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 1.99,
|
1593 |
+
"eval_loss": 1.2912580966949463,
|
1594 |
+
"eval_runtime": 61.8585,
|
1595 |
+
"eval_samples_per_second": 4.041,
|
1596 |
+
"eval_steps_per_second": 4.041,
|
1597 |
+
"step": 250
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 2.0,
|
1601 |
+
"learning_rate": 0.00010258538485811765,
|
1602 |
+
"loss": 1.3517,
|
1603 |
+
"step": 251
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"epoch": 2.01,
|
1607 |
+
"learning_rate": 0.00010193913317718244,
|
1608 |
+
"loss": 1.2637,
|
1609 |
+
"step": 252
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 2.02,
|
1613 |
+
"learning_rate": 0.00010129280046858086,
|
1614 |
+
"loss": 1.1032,
|
1615 |
+
"step": 253
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 2.01,
|
1619 |
+
"learning_rate": 0.00010064641373965393,
|
1620 |
+
"loss": 0.9574,
|
1621 |
+
"step": 254
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 2.02,
|
1625 |
+
"learning_rate": 0.0001,
|
1626 |
+
"loss": 0.8302,
|
1627 |
+
"step": 255
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 2.02,
|
1631 |
+
"learning_rate": 9.935358626034606e-05,
|
1632 |
+
"loss": 1.1663,
|
1633 |
+
"step": 256
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 2.03,
|
1637 |
+
"learning_rate": 9.870719953141917e-05,
|
1638 |
+
"loss": 1.0611,
|
1639 |
+
"step": 257
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 2.04,
|
1643 |
+
"learning_rate": 9.806086682281758e-05,
|
1644 |
+
"loss": 1.1039,
|
1645 |
+
"step": 258
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 2.05,
|
1649 |
+
"learning_rate": 9.741461514188242e-05,
|
1650 |
+
"loss": 1.134,
|
1651 |
+
"step": 259
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 2.06,
|
1655 |
+
"learning_rate": 9.676847149256895e-05,
|
1656 |
+
"loss": 0.8512,
|
1657 |
+
"step": 260
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 2.06,
|
1661 |
+
"learning_rate": 9.612246287431831e-05,
|
1662 |
+
"loss": 1.01,
|
1663 |
+
"step": 261
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 2.07,
|
1667 |
+
"learning_rate": 9.547661628092937e-05,
|
1668 |
+
"loss": 1.1625,
|
1669 |
+
"step": 262
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 2.08,
|
1673 |
+
"learning_rate": 9.483095869943055e-05,
|
1674 |
+
"loss": 1.0704,
|
1675 |
+
"step": 263
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 2.09,
|
1679 |
+
"learning_rate": 9.418551710895243e-05,
|
1680 |
+
"loss": 0.8177,
|
1681 |
+
"step": 264
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 2.1,
|
1685 |
+
"learning_rate": 9.354031847960022e-05,
|
1686 |
+
"loss": 0.9913,
|
1687 |
+
"step": 265
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"epoch": 2.1,
|
1691 |
+
"learning_rate": 9.289538977132703e-05,
|
1692 |
+
"loss": 1.166,
|
1693 |
+
"step": 266
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 2.11,
|
1697 |
+
"learning_rate": 9.225075793280692e-05,
|
1698 |
+
"loss": 1.125,
|
1699 |
+
"step": 267
|
1700 |
+
},
|
1701 |
+
{
|
1702 |
+
"epoch": 2.12,
|
1703 |
+
"learning_rate": 9.160644990030931e-05,
|
1704 |
+
"loss": 0.9657,
|
1705 |
+
"step": 268
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 2.13,
|
1709 |
+
"learning_rate": 9.09624925965732e-05,
|
1710 |
+
"loss": 1.0344,
|
1711 |
+
"step": 269
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 2.14,
|
1715 |
+
"learning_rate": 9.03189129296821e-05,
|
1716 |
+
"loss": 1.0579,
|
1717 |
+
"step": 270
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 2.15,
|
1721 |
+
"learning_rate": 8.967573779193987e-05,
|
1722 |
+
"loss": 1.0357,
|
1723 |
+
"step": 271
|
1724 |
+
},
|
1725 |
+
{
|
1726 |
+
"epoch": 2.15,
|
1727 |
+
"learning_rate": 8.903299405874684e-05,
|
1728 |
+
"loss": 1.1066,
|
1729 |
+
"step": 272
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 2.16,
|
1733 |
+
"learning_rate": 8.839070858747697e-05,
|
1734 |
+
"loss": 0.9976,
|
1735 |
+
"step": 273
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 2.17,
|
1739 |
+
"learning_rate": 8.774890821635548e-05,
|
1740 |
+
"loss": 0.8978,
|
1741 |
+
"step": 274
|
1742 |
+
},
|
1743 |
+
{
|
1744 |
+
"epoch": 2.18,
|
1745 |
+
"learning_rate": 8.710761976333734e-05,
|
1746 |
+
"loss": 1.0132,
|
1747 |
+
"step": 275
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 2.18,
|
1751 |
+
"eval_loss": 1.297065258026123,
|
1752 |
+
"eval_runtime": 61.8107,
|
1753 |
+
"eval_samples_per_second": 4.045,
|
1754 |
+
"eval_steps_per_second": 4.045,
|
1755 |
+
"step": 275
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 2.19,
|
1759 |
+
"learning_rate": 8.646687002498692e-05,
|
1760 |
+
"loss": 0.9386,
|
1761 |
+
"step": 276
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 2.19,
|
1765 |
+
"learning_rate": 8.582668577535797e-05,
|
1766 |
+
"loss": 0.8478,
|
1767 |
+
"step": 277
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 2.2,
|
1771 |
+
"learning_rate": 8.518709376487515e-05,
|
1772 |
+
"loss": 1.0554,
|
1773 |
+
"step": 278
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 2.21,
|
1777 |
+
"learning_rate": 8.454812071921596e-05,
|
1778 |
+
"loss": 1.0435,
|
1779 |
+
"step": 279
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 2.22,
|
1783 |
+
"learning_rate": 8.390979333819426e-05,
|
1784 |
+
"loss": 1.04,
|
1785 |
+
"step": 280
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 2.23,
|
1789 |
+
"learning_rate": 8.327213829464449e-05,
|
1790 |
+
"loss": 1.0513,
|
1791 |
+
"step": 281
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 2.23,
|
1795 |
+
"learning_rate": 8.263518223330697e-05,
|
1796 |
+
"loss": 1.1234,
|
1797 |
+
"step": 282
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 2.24,
|
1801 |
+
"learning_rate": 8.199895176971488e-05,
|
1802 |
+
"loss": 1.0556,
|
1803 |
+
"step": 283
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 2.25,
|
1807 |
+
"learning_rate": 8.13634734890818e-05,
|
1808 |
+
"loss": 0.9852,
|
1809 |
+
"step": 284
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 2.26,
|
1813 |
+
"learning_rate": 8.072877394519102e-05,
|
1814 |
+
"loss": 0.9753,
|
1815 |
+
"step": 285
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 2.27,
|
1819 |
+
"learning_rate": 8.009487965928596e-05,
|
1820 |
+
"loss": 1.1802,
|
1821 |
+
"step": 286
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 2.27,
|
1825 |
+
"learning_rate": 7.94618171189618e-05,
|
1826 |
+
"loss": 0.8883,
|
1827 |
+
"step": 287
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 2.28,
|
1831 |
+
"learning_rate": 7.882961277705895e-05,
|
1832 |
+
"loss": 1.0442,
|
1833 |
+
"step": 288
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 2.29,
|
1837 |
+
"learning_rate": 7.819829305055743e-05,
|
1838 |
+
"loss": 0.9863,
|
1839 |
+
"step": 289
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 2.3,
|
1843 |
+
"learning_rate": 7.756788431947326e-05,
|
1844 |
+
"loss": 1.0352,
|
1845 |
+
"step": 290
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 2.31,
|
1849 |
+
"learning_rate": 7.693841292575598e-05,
|
1850 |
+
"loss": 1.08,
|
1851 |
+
"step": 291
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 2.31,
|
1855 |
+
"learning_rate": 7.630990517218808e-05,
|
1856 |
+
"loss": 1.0916,
|
1857 |
+
"step": 292
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 2.32,
|
1861 |
+
"learning_rate": 7.568238732128585e-05,
|
1862 |
+
"loss": 0.956,
|
1863 |
+
"step": 293
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 2.33,
|
1867 |
+
"learning_rate": 7.505588559420189e-05,
|
1868 |
+
"loss": 1.0018,
|
1869 |
+
"step": 294
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 2.34,
|
1873 |
+
"learning_rate": 7.443042616962965e-05,
|
1874 |
+
"loss": 1.0782,
|
1875 |
+
"step": 295
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 2.35,
|
1879 |
+
"learning_rate": 7.380603518270941e-05,
|
1880 |
+
"loss": 1.098,
|
1881 |
+
"step": 296
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 2.35,
|
1885 |
+
"learning_rate": 7.318273872393625e-05,
|
1886 |
+
"loss": 1.1226,
|
1887 |
+
"step": 297
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 2.36,
|
1891 |
+
"learning_rate": 7.256056283806986e-05,
|
1892 |
+
"loss": 0.9865,
|
1893 |
+
"step": 298
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 2.37,
|
1897 |
+
"learning_rate": 7.193953352304613e-05,
|
1898 |
+
"loss": 0.9185,
|
1899 |
+
"step": 299
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 2.38,
|
1903 |
+
"learning_rate": 7.131967672889101e-05,
|
1904 |
+
"loss": 0.9713,
|
1905 |
+
"step": 300
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 2.38,
|
1909 |
+
"eval_loss": 1.2972489595413208,
|
1910 |
+
"eval_runtime": 61.7846,
|
1911 |
+
"eval_samples_per_second": 4.046,
|
1912 |
+
"eval_steps_per_second": 4.046,
|
1913 |
+
"step": 300
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 2.39,
|
1917 |
+
"learning_rate": 7.070101835663594e-05,
|
1918 |
+
"loss": 1.0547,
|
1919 |
+
"step": 301
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 2.4,
|
1923 |
+
"learning_rate": 7.008358425723585e-05,
|
1924 |
+
"loss": 1.1558,
|
1925 |
+
"step": 302
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 2.4,
|
1929 |
+
"learning_rate": 6.94674002304887e-05,
|
1930 |
+
"loss": 1.0398,
|
1931 |
+
"step": 303
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 2.41,
|
1935 |
+
"learning_rate": 6.885249202395754e-05,
|
1936 |
+
"loss": 0.8272,
|
1937 |
+
"step": 304
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 2.42,
|
1941 |
+
"learning_rate": 6.823888533189469e-05,
|
1942 |
+
"loss": 0.9847,
|
1943 |
+
"step": 305
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 2.43,
|
1947 |
+
"learning_rate": 6.762660579416791e-05,
|
1948 |
+
"loss": 0.919,
|
1949 |
+
"step": 306
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 2.44,
|
1953 |
+
"learning_rate": 6.701567899518924e-05,
|
1954 |
+
"loss": 0.9437,
|
1955 |
+
"step": 307
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 2.44,
|
1959 |
+
"learning_rate": 6.640613046284581e-05,
|
1960 |
+
"loss": 1.0459,
|
1961 |
+
"step": 308
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 2.45,
|
1965 |
+
"learning_rate": 6.579798566743314e-05,
|
1966 |
+
"loss": 0.98,
|
1967 |
+
"step": 309
|
1968 |
+
},
|
1969 |
+
{
|
1970 |
+
"epoch": 2.46,
|
1971 |
+
"learning_rate": 6.519127002059095e-05,
|
1972 |
+
"loss": 1.1745,
|
1973 |
+
"step": 310
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 2.47,
|
1977 |
+
"learning_rate": 6.458600887424125e-05,
|
1978 |
+
"loss": 0.9702,
|
1979 |
+
"step": 311
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 2.48,
|
1983 |
+
"learning_rate": 6.398222751952899e-05,
|
1984 |
+
"loss": 0.9785,
|
1985 |
+
"step": 312
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 2.48,
|
1989 |
+
"learning_rate": 6.337995118576521e-05,
|
1990 |
+
"loss": 0.9573,
|
1991 |
+
"step": 313
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 2.49,
|
1995 |
+
"learning_rate": 6.277920503937303e-05,
|
1996 |
+
"loss": 0.9505,
|
1997 |
+
"step": 314
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 2.5,
|
2001 |
+
"learning_rate": 6.218001418283576e-05,
|
2002 |
+
"loss": 1.0688,
|
2003 |
+
"step": 315
|
2004 |
+
},
|
2005 |
+
{
|
2006 |
+
"epoch": 2.51,
|
2007 |
+
"learning_rate": 6.158240365364823e-05,
|
2008 |
+
"loss": 0.9826,
|
2009 |
+
"step": 316
|
2010 |
+
},
|
2011 |
+
{
|
2012 |
+
"epoch": 2.52,
|
2013 |
+
"learning_rate": 6.098639842327052e-05,
|
2014 |
+
"loss": 0.9873,
|
2015 |
+
"step": 317
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 2.52,
|
2019 |
+
"learning_rate": 6.039202339608432e-05,
|
2020 |
+
"loss": 0.969,
|
2021 |
+
"step": 318
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 2.53,
|
2025 |
+
"learning_rate": 5.979930340835265e-05,
|
2026 |
+
"loss": 1.004,
|
2027 |
+
"step": 319
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 2.54,
|
2031 |
+
"learning_rate": 5.920826322718165e-05,
|
2032 |
+
"loss": 1.0032,
|
2033 |
+
"step": 320
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 2.55,
|
2037 |
+
"learning_rate": 5.861892754948609e-05,
|
2038 |
+
"loss": 1.0514,
|
2039 |
+
"step": 321
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 2.56,
|
2043 |
+
"learning_rate": 5.80313210009571e-05,
|
2044 |
+
"loss": 1.163,
|
2045 |
+
"step": 322
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 2.56,
|
2049 |
+
"learning_rate": 5.744546813503328e-05,
|
2050 |
+
"loss": 1.0799,
|
2051 |
+
"step": 323
|
2052 |
+
},
|
2053 |
+
{
|
2054 |
+
"epoch": 2.57,
|
2055 |
+
"learning_rate": 5.6861393431874675e-05,
|
2056 |
+
"loss": 0.8988,
|
2057 |
+
"step": 324
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 2.58,
|
2061 |
+
"learning_rate": 5.6279121297339924e-05,
|
2062 |
+
"loss": 1.0341,
|
2063 |
+
"step": 325
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 2.58,
|
2067 |
+
"eval_loss": 1.2901266813278198,
|
2068 |
+
"eval_runtime": 61.8384,
|
2069 |
+
"eval_samples_per_second": 4.043,
|
2070 |
+
"eval_steps_per_second": 4.043,
|
2071 |
+
"step": 325
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 2.59,
|
2075 |
+
"learning_rate": 5.5698676061966515e-05,
|
2076 |
+
"loss": 1.1851,
|
2077 |
+
"step": 326
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 2.6,
|
2081 |
+
"learning_rate": 5.5120081979953785e-05,
|
2082 |
+
"loss": 1.0744,
|
2083 |
+
"step": 327
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 2.6,
|
2087 |
+
"learning_rate": 5.4543363228149946e-05,
|
2088 |
+
"loss": 0.9741,
|
2089 |
+
"step": 328
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 2.61,
|
2093 |
+
"learning_rate": 5.3968543905041444e-05,
|
2094 |
+
"loss": 0.9947,
|
2095 |
+
"step": 329
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 2.62,
|
2099 |
+
"learning_rate": 5.339564802974615e-05,
|
2100 |
+
"loss": 1.1458,
|
2101 |
+
"step": 330
|
2102 |
+
},
|
2103 |
+
{
|
2104 |
+
"epoch": 2.63,
|
2105 |
+
"learning_rate": 5.282469954100968e-05,
|
2106 |
+
"loss": 0.8714,
|
2107 |
+
"step": 331
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"epoch": 2.64,
|
2111 |
+
"learning_rate": 5.22557222962051e-05,
|
2112 |
+
"loss": 0.8682,
|
2113 |
+
"step": 332
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 2.65,
|
2117 |
+
"learning_rate": 5.168874007033615e-05,
|
2118 |
+
"loss": 0.9135,
|
2119 |
+
"step": 333
|
2120 |
+
},
|
2121 |
+
{
|
2122 |
+
"epoch": 2.65,
|
2123 |
+
"learning_rate": 5.112377655504359e-05,
|
2124 |
+
"loss": 1.0744,
|
2125 |
+
"step": 334
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 2.66,
|
2129 |
+
"learning_rate": 5.056085535761532e-05,
|
2130 |
+
"loss": 0.9575,
|
2131 |
+
"step": 335
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 2.67,
|
2135 |
+
"learning_rate": 5.000000000000002e-05,
|
2136 |
+
"loss": 1.0823,
|
2137 |
+
"step": 336
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 2.68,
|
2141 |
+
"learning_rate": 4.9441233917824106e-05,
|
2142 |
+
"loss": 0.8986,
|
2143 |
+
"step": 337
|
2144 |
+
},
|
2145 |
+
{
|
2146 |
+
"epoch": 2.69,
|
2147 |
+
"learning_rate": 4.888458045941269e-05,
|
2148 |
+
"loss": 0.9171,
|
2149 |
+
"step": 338
|
2150 |
+
},
|
2151 |
+
{
|
2152 |
+
"epoch": 2.69,
|
2153 |
+
"learning_rate": 4.833006288481371e-05,
|
2154 |
+
"loss": 1.0258,
|
2155 |
+
"step": 339
|
2156 |
+
},
|
2157 |
+
{
|
2158 |
+
"epoch": 2.7,
|
2159 |
+
"learning_rate": 4.777770436482617e-05,
|
2160 |
+
"loss": 1.0722,
|
2161 |
+
"step": 340
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 2.71,
|
2165 |
+
"learning_rate": 4.722752798003184e-05,
|
2166 |
+
"loss": 1.0347,
|
2167 |
+
"step": 341
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 2.72,
|
2171 |
+
"learning_rate": 4.66795567198309e-05,
|
2172 |
+
"loss": 1.034,
|
2173 |
+
"step": 342
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 2.73,
|
2177 |
+
"learning_rate": 4.6133813481481246e-05,
|
2178 |
+
"loss": 0.9559,
|
2179 |
+
"step": 343
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 2.73,
|
2183 |
+
"learning_rate": 4.559032106914173e-05,
|
2184 |
+
"loss": 0.9619,
|
2185 |
+
"step": 344
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 2.74,
|
2189 |
+
"learning_rate": 4.50491021929194e-05,
|
2190 |
+
"loss": 0.9795,
|
2191 |
+
"step": 345
|
2192 |
+
},
|
2193 |
+
{
|
2194 |
+
"epoch": 2.75,
|
2195 |
+
"learning_rate": 4.451017946792032e-05,
|
2196 |
+
"loss": 0.9236,
|
2197 |
+
"step": 346
|
2198 |
+
},
|
2199 |
+
{
|
2200 |
+
"epoch": 2.76,
|
2201 |
+
"learning_rate": 4.397357541330476e-05,
|
2202 |
+
"loss": 0.8438,
|
2203 |
+
"step": 347
|
2204 |
+
},
|
2205 |
+
{
|
2206 |
+
"epoch": 2.77,
|
2207 |
+
"learning_rate": 4.343931245134616e-05,
|
2208 |
+
"loss": 0.9684,
|
2209 |
+
"step": 348
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 2.77,
|
2213 |
+
"learning_rate": 4.2907412906494174e-05,
|
2214 |
+
"loss": 0.9478,
|
2215 |
+
"step": 349
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 2.78,
|
2219 |
+
"learning_rate": 4.2377899004441966e-05,
|
2220 |
+
"loss": 1.0808,
|
2221 |
+
"step": 350
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 2.78,
|
2225 |
+
"eval_loss": 1.2958766222000122,
|
2226 |
+
"eval_runtime": 61.8006,
|
2227 |
+
"eval_samples_per_second": 4.045,
|
2228 |
+
"eval_steps_per_second": 4.045,
|
2229 |
+
"step": 350
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 2.79,
|
2233 |
+
"learning_rate": 4.185079287119733e-05,
|
2234 |
+
"loss": 1.112,
|
2235 |
+
"step": 351
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 2.8,
|
2239 |
+
"learning_rate": 4.132611653215822e-05,
|
2240 |
+
"loss": 0.983,
|
2241 |
+
"step": 352
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 2.81,
|
2245 |
+
"learning_rate": 4.080389191119241e-05,
|
2246 |
+
"loss": 1.1557,
|
2247 |
+
"step": 353
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 2.81,
|
2251 |
+
"learning_rate": 4.028414082972141e-05,
|
2252 |
+
"loss": 0.9879,
|
2253 |
+
"step": 354
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 2.82,
|
2257 |
+
"learning_rate": 3.9766885005808565e-05,
|
2258 |
+
"loss": 0.833,
|
2259 |
+
"step": 355
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 2.83,
|
2263 |
+
"learning_rate": 3.9252146053251636e-05,
|
2264 |
+
"loss": 1.0431,
|
2265 |
+
"step": 356
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 2.84,
|
2269 |
+
"learning_rate": 3.873994548067972e-05,
|
2270 |
+
"loss": 1.0371,
|
2271 |
+
"step": 357
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 2.85,
|
2275 |
+
"learning_rate": 3.8230304690654304e-05,
|
2276 |
+
"loss": 0.9455,
|
2277 |
+
"step": 358
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 2.85,
|
2281 |
+
"learning_rate": 3.772324497877511e-05,
|
2282 |
+
"loss": 0.9356,
|
2283 |
+
"step": 359
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 2.86,
|
2287 |
+
"learning_rate": 3.721878753279017e-05,
|
2288 |
+
"loss": 0.9807,
|
2289 |
+
"step": 360
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 2.87,
|
2293 |
+
"learning_rate": 3.671695343171052e-05,
|
2294 |
+
"loss": 0.9067,
|
2295 |
+
"step": 361
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 2.88,
|
2299 |
+
"learning_rate": 3.621776364492939e-05,
|
2300 |
+
"loss": 0.9393,
|
2301 |
+
"step": 362
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 2.89,
|
2305 |
+
"learning_rate": 3.5721239031346066e-05,
|
2306 |
+
"loss": 0.9856,
|
2307 |
+
"step": 363
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 2.9,
|
2311 |
+
"learning_rate": 3.522740033849411e-05,
|
2312 |
+
"loss": 1.0474,
|
2313 |
+
"step": 364
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 2.9,
|
2317 |
+
"learning_rate": 3.4736268201674574e-05,
|
2318 |
+
"loss": 0.9027,
|
2319 |
+
"step": 365
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 2.91,
|
2323 |
+
"learning_rate": 3.424786314309365e-05,
|
2324 |
+
"loss": 0.9521,
|
2325 |
+
"step": 366
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 2.92,
|
2329 |
+
"learning_rate": 3.376220557100523e-05,
|
2330 |
+
"loss": 0.9211,
|
2331 |
+
"step": 367
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 2.93,
|
2335 |
+
"learning_rate": 3.3279315778858036e-05,
|
2336 |
+
"loss": 0.9576,
|
2337 |
+
"step": 368
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 2.94,
|
2341 |
+
"learning_rate": 3.279921394444776e-05,
|
2342 |
+
"loss": 0.9643,
|
2343 |
+
"step": 369
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 2.94,
|
2347 |
+
"learning_rate": 3.2321920129073816e-05,
|
2348 |
+
"loss": 1.0322,
|
2349 |
+
"step": 370
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 2.95,
|
2353 |
+
"learning_rate": 3.18474542767011e-05,
|
2354 |
+
"loss": 0.9762,
|
2355 |
+
"step": 371
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 2.96,
|
2359 |
+
"learning_rate": 3.137583621312665e-05,
|
2360 |
+
"loss": 1.1331,
|
2361 |
+
"step": 372
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 2.97,
|
2365 |
+
"learning_rate": 3.090708564515124e-05,
|
2366 |
+
"loss": 1.104,
|
2367 |
+
"step": 373
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 2.98,
|
2371 |
+
"learning_rate": 3.04412221597558e-05,
|
2372 |
+
"loss": 0.9667,
|
2373 |
+
"step": 374
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 2.98,
|
2377 |
+
"learning_rate": 2.997826522328315e-05,
|
2378 |
+
"loss": 0.9492,
|
2379 |
+
"step": 375
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 2.98,
|
2383 |
+
"eval_loss": 1.2812517881393433,
|
2384 |
+
"eval_runtime": 61.7806,
|
2385 |
+
"eval_samples_per_second": 4.047,
|
2386 |
+
"eval_steps_per_second": 4.047,
|
2387 |
+
"step": 375
|
2388 |
+
},
|
2389 |
+
{
|
2390 |
+
"epoch": 2.99,
|
2391 |
+
"learning_rate": 2.9518234180624393e-05,
|
2392 |
+
"loss": 1.0619,
|
2393 |
+
"step": 376
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"epoch": 3.0,
|
2397 |
+
"learning_rate": 2.906114825441072e-05,
|
2398 |
+
"loss": 0.9439,
|
2399 |
+
"step": 377
|
2400 |
+
},
|
2401 |
+
{
|
2402 |
+
"epoch": 3.01,
|
2403 |
+
"learning_rate": 2.8607026544210114e-05,
|
2404 |
+
"loss": 0.905,
|
2405 |
+
"step": 378
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 3.02,
|
2409 |
+
"learning_rate": 2.8155888025729273e-05,
|
2410 |
+
"loss": 0.9329,
|
2411 |
+
"step": 379
|
2412 |
+
}
|
2413 |
+
],
|
2414 |
+
"logging_steps": 1,
|
2415 |
+
"max_steps": 496,
|
2416 |
+
"num_train_epochs": 4,
|
2417 |
+
"save_steps": 500,
|
2418 |
+
"total_flos": 1.2351573446570803e+17,
|
2419 |
+
"trial_name": null,
|
2420 |
+
"trial_params": null
|
2421 |
+
}
|
checkpoint-379/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29182789cc886c4cb1e203599999900c580a72f92286132414128006e2d749f4
|
3 |
+
size 4603
|