Upload 8 files
Browse files- README.md +218 -1
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2857 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,220 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
4 |
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
## Training procedure
|
203 |
+
|
204 |
+
|
205 |
+
The following `bitsandbytes` quantization config was used during training:
|
206 |
+
- quant_method: bitsandbytes
|
207 |
+
- load_in_8bit: True
|
208 |
+
- load_in_4bit: False
|
209 |
+
- llm_int8_threshold: 6.0
|
210 |
+
- llm_int8_skip_modules: None
|
211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
+
- llm_int8_has_fp16_weight: False
|
213 |
+
- bnb_4bit_quant_type: fp4
|
214 |
+
- bnb_4bit_use_double_quant: False
|
215 |
+
- bnb_4bit_compute_dtype: float32
|
216 |
+
|
217 |
+
### Framework versions
|
218 |
+
|
219 |
+
|
220 |
+
- PEFT 0.6.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 0.8,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 32,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"up_proj",
|
20 |
+
"gate_proj",
|
21 |
+
"o_proj",
|
22 |
+
"down_proj",
|
23 |
+
"q_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2de6d2e236f495fca0d167075fb88bad181af6671ed843057bdc70b1b934257
|
3 |
+
size 335604696
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a101ca94bfdcd83f449a829ad9b3b45e88ac7b76862d52e2c7f0a2be8191f4aa
|
3 |
+
size 168624735
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70587b635f67bcf3147c2f1366d716c9547d1e551565af06d2cb77235c23324
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a96b935a7dd4194ff9e77e9b75b7462121105ee680aff83805f748b78c6c7f4
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,2857 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9783549783549783,
|
5 |
+
"eval_steps": 58,
|
6 |
+
"global_step": 462,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.2676,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"eval_loss": 1.2198331356048584,
|
20 |
+
"eval_runtime": 81.1297,
|
21 |
+
"eval_samples_per_second": 0.641,
|
22 |
+
"eval_steps_per_second": 0.32,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"learning_rate": 4e-05,
|
28 |
+
"loss": 1.2193,
|
29 |
+
"step": 2
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.01,
|
33 |
+
"learning_rate": 6e-05,
|
34 |
+
"loss": 1.3298,
|
35 |
+
"step": 3
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.02,
|
39 |
+
"learning_rate": 8e-05,
|
40 |
+
"loss": 1.2061,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.02,
|
45 |
+
"learning_rate": 0.0001,
|
46 |
+
"loss": 1.3527,
|
47 |
+
"step": 5
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.03,
|
51 |
+
"learning_rate": 0.00012,
|
52 |
+
"loss": 1.252,
|
53 |
+
"step": 6
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.03,
|
57 |
+
"learning_rate": 0.00014,
|
58 |
+
"loss": 1.1741,
|
59 |
+
"step": 7
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.03,
|
63 |
+
"learning_rate": 0.00016,
|
64 |
+
"loss": 1.1895,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04,
|
69 |
+
"learning_rate": 0.00018,
|
70 |
+
"loss": 1.2515,
|
71 |
+
"step": 9
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.04,
|
75 |
+
"learning_rate": 0.0002,
|
76 |
+
"loss": 1.1743,
|
77 |
+
"step": 10
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.05,
|
81 |
+
"learning_rate": 0.00019999990671452868,
|
82 |
+
"loss": 1.1574,
|
83 |
+
"step": 11
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.05,
|
87 |
+
"learning_rate": 0.00019999962685828874,
|
88 |
+
"loss": 1.1273,
|
89 |
+
"step": 12
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.06,
|
93 |
+
"learning_rate": 0.0001999991604318023,
|
94 |
+
"loss": 1.2415,
|
95 |
+
"step": 13
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.06,
|
99 |
+
"learning_rate": 0.00019999850743593963,
|
100 |
+
"loss": 1.0545,
|
101 |
+
"step": 14
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.06,
|
105 |
+
"learning_rate": 0.00019999766787191895,
|
106 |
+
"loss": 1.2343,
|
107 |
+
"step": 15
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.07,
|
111 |
+
"learning_rate": 0.0001999966417413067,
|
112 |
+
"loss": 1.191,
|
113 |
+
"step": 16
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.07,
|
117 |
+
"learning_rate": 0.00019999542904601734,
|
118 |
+
"loss": 1.1895,
|
119 |
+
"step": 17
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.08,
|
123 |
+
"learning_rate": 0.0001999940297883134,
|
124 |
+
"loss": 1.2189,
|
125 |
+
"step": 18
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.08,
|
129 |
+
"learning_rate": 0.00019999244397080545,
|
130 |
+
"loss": 1.0745,
|
131 |
+
"step": 19
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.09,
|
135 |
+
"learning_rate": 0.0001999906715964522,
|
136 |
+
"loss": 1.0772,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.09,
|
141 |
+
"learning_rate": 0.0001999887126685604,
|
142 |
+
"loss": 1.2113,
|
143 |
+
"step": 21
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.1,
|
147 |
+
"learning_rate": 0.00019998656719078482,
|
148 |
+
"loss": 1.1121,
|
149 |
+
"step": 22
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.1,
|
153 |
+
"learning_rate": 0.00019998423516712829,
|
154 |
+
"loss": 1.1874,
|
155 |
+
"step": 23
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.1,
|
159 |
+
"learning_rate": 0.00019998171660194172,
|
160 |
+
"loss": 1.1595,
|
161 |
+
"step": 24
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.11,
|
165 |
+
"learning_rate": 0.00019997901149992398,
|
166 |
+
"loss": 1.1307,
|
167 |
+
"step": 25
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.11,
|
171 |
+
"learning_rate": 0.00019997611986612203,
|
172 |
+
"loss": 1.0118,
|
173 |
+
"step": 26
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.12,
|
177 |
+
"learning_rate": 0.00019997304170593083,
|
178 |
+
"loss": 1.0629,
|
179 |
+
"step": 27
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.12,
|
183 |
+
"learning_rate": 0.0001999697770250933,
|
184 |
+
"loss": 1.1903,
|
185 |
+
"step": 28
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.13,
|
189 |
+
"learning_rate": 0.0001999663258297004,
|
190 |
+
"loss": 1.1613,
|
191 |
+
"step": 29
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.13,
|
195 |
+
"learning_rate": 0.00019996268812619107,
|
196 |
+
"loss": 1.1202,
|
197 |
+
"step": 30
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.13,
|
201 |
+
"learning_rate": 0.00019995886392135218,
|
202 |
+
"loss": 1.1014,
|
203 |
+
"step": 31
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.14,
|
207 |
+
"learning_rate": 0.00019995485322231863,
|
208 |
+
"loss": 1.1386,
|
209 |
+
"step": 32
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.14,
|
213 |
+
"learning_rate": 0.00019995065603657316,
|
214 |
+
"loss": 1.111,
|
215 |
+
"step": 33
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.15,
|
219 |
+
"learning_rate": 0.00019994627237194653,
|
220 |
+
"loss": 0.966,
|
221 |
+
"step": 34
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.15,
|
225 |
+
"learning_rate": 0.0001999417022366174,
|
226 |
+
"loss": 1.0894,
|
227 |
+
"step": 35
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.16,
|
231 |
+
"learning_rate": 0.0001999369456391123,
|
232 |
+
"loss": 1.1174,
|
233 |
+
"step": 36
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.16,
|
237 |
+
"learning_rate": 0.00019993200258830568,
|
238 |
+
"loss": 1.1523,
|
239 |
+
"step": 37
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.16,
|
243 |
+
"learning_rate": 0.00019992687309341976,
|
244 |
+
"loss": 1.086,
|
245 |
+
"step": 38
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.17,
|
249 |
+
"learning_rate": 0.00019992155716402475,
|
250 |
+
"loss": 1.1731,
|
251 |
+
"step": 39
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.17,
|
255 |
+
"learning_rate": 0.00019991605481003866,
|
256 |
+
"loss": 1.0819,
|
257 |
+
"step": 40
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.18,
|
261 |
+
"learning_rate": 0.00019991036604172723,
|
262 |
+
"loss": 1.1908,
|
263 |
+
"step": 41
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.18,
|
267 |
+
"learning_rate": 0.00019990449086970403,
|
268 |
+
"loss": 1.137,
|
269 |
+
"step": 42
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.19,
|
273 |
+
"learning_rate": 0.0001998984293049305,
|
274 |
+
"loss": 1.0934,
|
275 |
+
"step": 43
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.19,
|
279 |
+
"learning_rate": 0.00019989218135871571,
|
280 |
+
"loss": 1.1328,
|
281 |
+
"step": 44
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.19,
|
285 |
+
"learning_rate": 0.0001998857470427165,
|
286 |
+
"loss": 1.0891,
|
287 |
+
"step": 45
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.2,
|
291 |
+
"learning_rate": 0.00019987912636893745,
|
292 |
+
"loss": 1.2444,
|
293 |
+
"step": 46
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.2,
|
297 |
+
"learning_rate": 0.0001998723193497308,
|
298 |
+
"loss": 1.1038,
|
299 |
+
"step": 47
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.21,
|
303 |
+
"learning_rate": 0.00019986532599779652,
|
304 |
+
"loss": 1.1226,
|
305 |
+
"step": 48
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.21,
|
309 |
+
"learning_rate": 0.00019985814632618212,
|
310 |
+
"loss": 1.1638,
|
311 |
+
"step": 49
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.22,
|
315 |
+
"learning_rate": 0.0001998507803482828,
|
316 |
+
"loss": 1.0305,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.22,
|
321 |
+
"learning_rate": 0.00019984322807784134,
|
322 |
+
"loss": 1.0989,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.23,
|
327 |
+
"learning_rate": 0.00019983548952894807,
|
328 |
+
"loss": 1.0603,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.23,
|
333 |
+
"learning_rate": 0.0001998275647160409,
|
334 |
+
"loss": 1.0908,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.23,
|
339 |
+
"learning_rate": 0.00019981945365390516,
|
340 |
+
"loss": 1.0206,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.24,
|
345 |
+
"learning_rate": 0.0001998111563576738,
|
346 |
+
"loss": 1.0747,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.24,
|
351 |
+
"learning_rate": 0.00019980267284282717,
|
352 |
+
"loss": 0.9588,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.25,
|
357 |
+
"learning_rate": 0.000199794003125193,
|
358 |
+
"loss": 1.045,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.25,
|
363 |
+
"learning_rate": 0.00019978514722094647,
|
364 |
+
"loss": 1.0878,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.25,
|
369 |
+
"eval_loss": 1.056009292602539,
|
370 |
+
"eval_runtime": 80.995,
|
371 |
+
"eval_samples_per_second": 0.642,
|
372 |
+
"eval_steps_per_second": 0.321,
|
373 |
+
"step": 58
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.26,
|
377 |
+
"learning_rate": 0.00019977610514661018,
|
378 |
+
"loss": 1.1608,
|
379 |
+
"step": 59
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.26,
|
383 |
+
"learning_rate": 0.00019976687691905393,
|
384 |
+
"loss": 1.1301,
|
385 |
+
"step": 60
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.26,
|
389 |
+
"learning_rate": 0.00019975746255549497,
|
390 |
+
"loss": 1.2051,
|
391 |
+
"step": 61
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.27,
|
395 |
+
"learning_rate": 0.00019974786207349775,
|
396 |
+
"loss": 1.2455,
|
397 |
+
"step": 62
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.27,
|
401 |
+
"learning_rate": 0.00019973807549097396,
|
402 |
+
"loss": 1.095,
|
403 |
+
"step": 63
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.28,
|
407 |
+
"learning_rate": 0.00019972810282618256,
|
408 |
+
"loss": 1.0158,
|
409 |
+
"step": 64
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.28,
|
413 |
+
"learning_rate": 0.00019971794409772963,
|
414 |
+
"loss": 1.1211,
|
415 |
+
"step": 65
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.29,
|
419 |
+
"learning_rate": 0.00019970759932456836,
|
420 |
+
"loss": 1.1543,
|
421 |
+
"step": 66
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.29,
|
425 |
+
"learning_rate": 0.00019969706852599915,
|
426 |
+
"loss": 1.0695,
|
427 |
+
"step": 67
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.29,
|
431 |
+
"learning_rate": 0.0001996863517216694,
|
432 |
+
"loss": 1.0116,
|
433 |
+
"step": 68
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.3,
|
437 |
+
"learning_rate": 0.00019967544893157352,
|
438 |
+
"loss": 1.0067,
|
439 |
+
"step": 69
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.3,
|
443 |
+
"learning_rate": 0.00019966436017605297,
|
444 |
+
"loss": 1.0305,
|
445 |
+
"step": 70
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.31,
|
449 |
+
"learning_rate": 0.00019965308547579614,
|
450 |
+
"loss": 1.1282,
|
451 |
+
"step": 71
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.31,
|
455 |
+
"learning_rate": 0.00019964162485183837,
|
456 |
+
"loss": 1.119,
|
457 |
+
"step": 72
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.32,
|
461 |
+
"learning_rate": 0.00019962997832556183,
|
462 |
+
"loss": 1.012,
|
463 |
+
"step": 73
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.32,
|
467 |
+
"learning_rate": 0.00019961814591869557,
|
468 |
+
"loss": 1.077,
|
469 |
+
"step": 74
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.32,
|
473 |
+
"learning_rate": 0.0001996061276533154,
|
474 |
+
"loss": 1.1129,
|
475 |
+
"step": 75
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.33,
|
479 |
+
"learning_rate": 0.00019959392355184389,
|
480 |
+
"loss": 1.2689,
|
481 |
+
"step": 76
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.33,
|
485 |
+
"learning_rate": 0.00019958153363705043,
|
486 |
+
"loss": 1.0738,
|
487 |
+
"step": 77
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.34,
|
491 |
+
"learning_rate": 0.0001995689579320509,
|
492 |
+
"loss": 1.1531,
|
493 |
+
"step": 78
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.34,
|
497 |
+
"learning_rate": 0.00019955619646030802,
|
498 |
+
"loss": 1.1163,
|
499 |
+
"step": 79
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.35,
|
503 |
+
"learning_rate": 0.00019954324924563089,
|
504 |
+
"loss": 1.0968,
|
505 |
+
"step": 80
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.35,
|
509 |
+
"learning_rate": 0.00019953011631217531,
|
510 |
+
"loss": 1.1209,
|
511 |
+
"step": 81
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.35,
|
515 |
+
"learning_rate": 0.00019951679768444346,
|
516 |
+
"loss": 0.9869,
|
517 |
+
"step": 82
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 0.36,
|
521 |
+
"learning_rate": 0.0001995032933872841,
|
522 |
+
"loss": 1.1093,
|
523 |
+
"step": 83
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.36,
|
527 |
+
"learning_rate": 0.0001994896034458923,
|
528 |
+
"loss": 1.0699,
|
529 |
+
"step": 84
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.37,
|
533 |
+
"learning_rate": 0.00019947572788580947,
|
534 |
+
"loss": 1.0447,
|
535 |
+
"step": 85
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.37,
|
539 |
+
"learning_rate": 0.00019946166673292344,
|
540 |
+
"loss": 1.2151,
|
541 |
+
"step": 86
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.38,
|
545 |
+
"learning_rate": 0.0001994474200134682,
|
546 |
+
"loss": 1.0636,
|
547 |
+
"step": 87
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.38,
|
551 |
+
"learning_rate": 0.00019943298775402398,
|
552 |
+
"loss": 1.1213,
|
553 |
+
"step": 88
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 0.39,
|
557 |
+
"learning_rate": 0.00019941836998151722,
|
558 |
+
"loss": 1.1241,
|
559 |
+
"step": 89
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 0.39,
|
563 |
+
"learning_rate": 0.00019940356672322037,
|
564 |
+
"loss": 1.062,
|
565 |
+
"step": 90
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.39,
|
569 |
+
"learning_rate": 0.00019938857800675205,
|
570 |
+
"loss": 1.1219,
|
571 |
+
"step": 91
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.4,
|
575 |
+
"learning_rate": 0.00019937340386007687,
|
576 |
+
"loss": 1.1362,
|
577 |
+
"step": 92
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.4,
|
581 |
+
"learning_rate": 0.00019935804431150538,
|
582 |
+
"loss": 1.0821,
|
583 |
+
"step": 93
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.41,
|
587 |
+
"learning_rate": 0.00019934249938969396,
|
588 |
+
"loss": 1.0587,
|
589 |
+
"step": 94
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.41,
|
593 |
+
"learning_rate": 0.000199326769123645,
|
594 |
+
"loss": 0.9533,
|
595 |
+
"step": 95
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 0.42,
|
599 |
+
"learning_rate": 0.00019931085354270658,
|
600 |
+
"loss": 1.1371,
|
601 |
+
"step": 96
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.42,
|
605 |
+
"learning_rate": 0.00019929475267657255,
|
606 |
+
"loss": 1.069,
|
607 |
+
"step": 97
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.42,
|
611 |
+
"learning_rate": 0.0001992784665552824,
|
612 |
+
"loss": 1.1461,
|
613 |
+
"step": 98
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.43,
|
617 |
+
"learning_rate": 0.00019926199520922135,
|
618 |
+
"loss": 1.0291,
|
619 |
+
"step": 99
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.43,
|
623 |
+
"learning_rate": 0.00019924533866912017,
|
624 |
+
"loss": 1.0241,
|
625 |
+
"step": 100
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.44,
|
629 |
+
"learning_rate": 0.00019922849696605508,
|
630 |
+
"loss": 1.0519,
|
631 |
+
"step": 101
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.44,
|
635 |
+
"learning_rate": 0.0001992114701314478,
|
636 |
+
"loss": 1.0983,
|
637 |
+
"step": 102
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.45,
|
641 |
+
"learning_rate": 0.00019919425819706548,
|
642 |
+
"loss": 1.0108,
|
643 |
+
"step": 103
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.45,
|
647 |
+
"learning_rate": 0.00019917686119502056,
|
648 |
+
"loss": 1.003,
|
649 |
+
"step": 104
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.45,
|
653 |
+
"learning_rate": 0.00019915927915777084,
|
654 |
+
"loss": 1.0954,
|
655 |
+
"step": 105
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.46,
|
659 |
+
"learning_rate": 0.00019914151211811924,
|
660 |
+
"loss": 1.0077,
|
661 |
+
"step": 106
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.46,
|
665 |
+
"learning_rate": 0.00019912356010921394,
|
666 |
+
"loss": 1.0603,
|
667 |
+
"step": 107
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.47,
|
671 |
+
"learning_rate": 0.00019910542316454812,
|
672 |
+
"loss": 1.0503,
|
673 |
+
"step": 108
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.47,
|
677 |
+
"learning_rate": 0.0001990871013179601,
|
678 |
+
"loss": 1.1574,
|
679 |
+
"step": 109
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.48,
|
683 |
+
"learning_rate": 0.00019906859460363307,
|
684 |
+
"loss": 0.9963,
|
685 |
+
"step": 110
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.48,
|
689 |
+
"learning_rate": 0.00019904990305609523,
|
690 |
+
"loss": 1.0808,
|
691 |
+
"step": 111
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.48,
|
695 |
+
"learning_rate": 0.00019903102671021955,
|
696 |
+
"loss": 1.0106,
|
697 |
+
"step": 112
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.49,
|
701 |
+
"learning_rate": 0.00019901196560122384,
|
702 |
+
"loss": 1.1367,
|
703 |
+
"step": 113
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.49,
|
707 |
+
"learning_rate": 0.00019899271976467055,
|
708 |
+
"loss": 0.9625,
|
709 |
+
"step": 114
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.5,
|
713 |
+
"learning_rate": 0.0001989732892364668,
|
714 |
+
"loss": 0.9833,
|
715 |
+
"step": 115
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.5,
|
719 |
+
"learning_rate": 0.0001989536740528644,
|
720 |
+
"loss": 1.0229,
|
721 |
+
"step": 116
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.5,
|
725 |
+
"eval_loss": 1.026347279548645,
|
726 |
+
"eval_runtime": 80.9197,
|
727 |
+
"eval_samples_per_second": 0.643,
|
728 |
+
"eval_steps_per_second": 0.321,
|
729 |
+
"step": 116
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.51,
|
733 |
+
"learning_rate": 0.00019893387425045948,
|
734 |
+
"loss": 0.9988,
|
735 |
+
"step": 117
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.51,
|
739 |
+
"learning_rate": 0.00019891388986619277,
|
740 |
+
"loss": 1.0638,
|
741 |
+
"step": 118
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.52,
|
745 |
+
"learning_rate": 0.00019889372093734932,
|
746 |
+
"loss": 1.0461,
|
747 |
+
"step": 119
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.52,
|
751 |
+
"learning_rate": 0.0001988733675015585,
|
752 |
+
"loss": 1.0636,
|
753 |
+
"step": 120
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.52,
|
757 |
+
"learning_rate": 0.0001988528295967939,
|
758 |
+
"loss": 1.094,
|
759 |
+
"step": 121
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.53,
|
763 |
+
"learning_rate": 0.00019883210726137326,
|
764 |
+
"loss": 1.1916,
|
765 |
+
"step": 122
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.53,
|
769 |
+
"learning_rate": 0.00019881120053395843,
|
770 |
+
"loss": 1.0594,
|
771 |
+
"step": 123
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.54,
|
775 |
+
"learning_rate": 0.00019879010945355534,
|
776 |
+
"loss": 1.0834,
|
777 |
+
"step": 124
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.54,
|
781 |
+
"learning_rate": 0.00019876883405951377,
|
782 |
+
"loss": 1.0531,
|
783 |
+
"step": 125
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.55,
|
787 |
+
"learning_rate": 0.00019874737439152748,
|
788 |
+
"loss": 0.9958,
|
789 |
+
"step": 126
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.55,
|
793 |
+
"learning_rate": 0.0001987257304896339,
|
794 |
+
"loss": 0.982,
|
795 |
+
"step": 127
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.55,
|
799 |
+
"learning_rate": 0.00019870390239421434,
|
800 |
+
"loss": 1.1186,
|
801 |
+
"step": 128
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.56,
|
805 |
+
"learning_rate": 0.00019868189014599362,
|
806 |
+
"loss": 1.0338,
|
807 |
+
"step": 129
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.56,
|
811 |
+
"learning_rate": 0.0001986596937860402,
|
812 |
+
"loss": 1.0408,
|
813 |
+
"step": 130
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.57,
|
817 |
+
"learning_rate": 0.0001986373133557661,
|
818 |
+
"loss": 1.0467,
|
819 |
+
"step": 131
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.57,
|
823 |
+
"learning_rate": 0.00019861474889692663,
|
824 |
+
"loss": 1.0434,
|
825 |
+
"step": 132
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.58,
|
829 |
+
"learning_rate": 0.00019859200045162055,
|
830 |
+
"loss": 1.0551,
|
831 |
+
"step": 133
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.58,
|
835 |
+
"learning_rate": 0.00019856906806228986,
|
836 |
+
"loss": 0.9985,
|
837 |
+
"step": 134
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.58,
|
841 |
+
"learning_rate": 0.00019854595177171968,
|
842 |
+
"loss": 1.117,
|
843 |
+
"step": 135
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.59,
|
847 |
+
"learning_rate": 0.00019852265162303837,
|
848 |
+
"loss": 1.0807,
|
849 |
+
"step": 136
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.59,
|
853 |
+
"learning_rate": 0.00019849916765971718,
|
854 |
+
"loss": 1.1331,
|
855 |
+
"step": 137
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.6,
|
859 |
+
"learning_rate": 0.00019847549992557038,
|
860 |
+
"loss": 0.9886,
|
861 |
+
"step": 138
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.6,
|
865 |
+
"learning_rate": 0.00019845164846475508,
|
866 |
+
"loss": 1.2248,
|
867 |
+
"step": 139
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.61,
|
871 |
+
"learning_rate": 0.00019842761332177115,
|
872 |
+
"loss": 1.0368,
|
873 |
+
"step": 140
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.61,
|
877 |
+
"learning_rate": 0.00019840339454146123,
|
878 |
+
"loss": 1.0343,
|
879 |
+
"step": 141
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.61,
|
883 |
+
"learning_rate": 0.00019837899216901053,
|
884 |
+
"loss": 1.0199,
|
885 |
+
"step": 142
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.62,
|
889 |
+
"learning_rate": 0.00019835440624994672,
|
890 |
+
"loss": 1.0308,
|
891 |
+
"step": 143
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.62,
|
895 |
+
"learning_rate": 0.00019832963683014007,
|
896 |
+
"loss": 1.1501,
|
897 |
+
"step": 144
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.63,
|
901 |
+
"learning_rate": 0.00019830468395580305,
|
902 |
+
"loss": 0.9705,
|
903 |
+
"step": 145
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.63,
|
907 |
+
"learning_rate": 0.00019827954767349048,
|
908 |
+
"loss": 1.0611,
|
909 |
+
"step": 146
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.64,
|
913 |
+
"learning_rate": 0.00019825422803009942,
|
914 |
+
"loss": 1.0194,
|
915 |
+
"step": 147
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.64,
|
919 |
+
"learning_rate": 0.0001982287250728689,
|
920 |
+
"loss": 1.0197,
|
921 |
+
"step": 148
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.65,
|
925 |
+
"learning_rate": 0.00019820303884938002,
|
926 |
+
"loss": 1.0534,
|
927 |
+
"step": 149
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.65,
|
931 |
+
"learning_rate": 0.00019817716940755586,
|
932 |
+
"loss": 1.0378,
|
933 |
+
"step": 150
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.65,
|
937 |
+
"learning_rate": 0.00019815111679566128,
|
938 |
+
"loss": 1.1537,
|
939 |
+
"step": 151
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.66,
|
943 |
+
"learning_rate": 0.00019812488106230286,
|
944 |
+
"loss": 1.0294,
|
945 |
+
"step": 152
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.66,
|
949 |
+
"learning_rate": 0.00019809846225642884,
|
950 |
+
"loss": 1.0661,
|
951 |
+
"step": 153
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.67,
|
955 |
+
"learning_rate": 0.00019807186042732907,
|
956 |
+
"loss": 0.9441,
|
957 |
+
"step": 154
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.67,
|
961 |
+
"learning_rate": 0.0001980450756246348,
|
962 |
+
"loss": 1.1188,
|
963 |
+
"step": 155
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.68,
|
967 |
+
"learning_rate": 0.00019801810789831873,
|
968 |
+
"loss": 0.9543,
|
969 |
+
"step": 156
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.68,
|
973 |
+
"learning_rate": 0.0001979909572986948,
|
974 |
+
"loss": 1.0754,
|
975 |
+
"step": 157
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.68,
|
979 |
+
"learning_rate": 0.00019796362387641806,
|
980 |
+
"loss": 0.9803,
|
981 |
+
"step": 158
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.69,
|
985 |
+
"learning_rate": 0.00019793610768248482,
|
986 |
+
"loss": 1.1368,
|
987 |
+
"step": 159
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.69,
|
991 |
+
"learning_rate": 0.00019790840876823232,
|
992 |
+
"loss": 0.996,
|
993 |
+
"step": 160
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.7,
|
997 |
+
"learning_rate": 0.00019788052718533857,
|
998 |
+
"loss": 1.1974,
|
999 |
+
"step": 161
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.7,
|
1003 |
+
"learning_rate": 0.0001978524629858226,
|
1004 |
+
"loss": 0.9604,
|
1005 |
+
"step": 162
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.71,
|
1009 |
+
"learning_rate": 0.00019782421622204402,
|
1010 |
+
"loss": 1.0494,
|
1011 |
+
"step": 163
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.71,
|
1015 |
+
"learning_rate": 0.0001977957869467031,
|
1016 |
+
"loss": 1.0568,
|
1017 |
+
"step": 164
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.71,
|
1021 |
+
"learning_rate": 0.00019776717521284058,
|
1022 |
+
"loss": 1.0821,
|
1023 |
+
"step": 165
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.72,
|
1027 |
+
"learning_rate": 0.00019773838107383767,
|
1028 |
+
"loss": 1.0717,
|
1029 |
+
"step": 166
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.72,
|
1033 |
+
"learning_rate": 0.00019770940458341583,
|
1034 |
+
"loss": 1.0897,
|
1035 |
+
"step": 167
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.73,
|
1039 |
+
"learning_rate": 0.0001976802457956368,
|
1040 |
+
"loss": 1.1423,
|
1041 |
+
"step": 168
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.73,
|
1045 |
+
"learning_rate": 0.0001976509047649024,
|
1046 |
+
"loss": 1.0614,
|
1047 |
+
"step": 169
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.74,
|
1051 |
+
"learning_rate": 0.00019762138154595446,
|
1052 |
+
"loss": 1.0298,
|
1053 |
+
"step": 170
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.74,
|
1057 |
+
"learning_rate": 0.00019759167619387476,
|
1058 |
+
"loss": 0.9958,
|
1059 |
+
"step": 171
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.74,
|
1063 |
+
"learning_rate": 0.0001975617887640848,
|
1064 |
+
"loss": 1.0356,
|
1065 |
+
"step": 172
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.75,
|
1069 |
+
"learning_rate": 0.00019753171931234588,
|
1070 |
+
"loss": 0.9921,
|
1071 |
+
"step": 173
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.75,
|
1075 |
+
"learning_rate": 0.00019750146789475885,
|
1076 |
+
"loss": 1.2044,
|
1077 |
+
"step": 174
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.75,
|
1081 |
+
"eval_loss": 1.0114357471466064,
|
1082 |
+
"eval_runtime": 81.1178,
|
1083 |
+
"eval_samples_per_second": 0.641,
|
1084 |
+
"eval_steps_per_second": 0.321,
|
1085 |
+
"step": 174
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 0.76,
|
1089 |
+
"learning_rate": 0.00019747103456776405,
|
1090 |
+
"loss": 0.9703,
|
1091 |
+
"step": 175
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.76,
|
1095 |
+
"learning_rate": 0.00019744041938814127,
|
1096 |
+
"loss": 0.9922,
|
1097 |
+
"step": 176
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 0.77,
|
1101 |
+
"learning_rate": 0.00019740962241300949,
|
1102 |
+
"loss": 1.0438,
|
1103 |
+
"step": 177
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.77,
|
1107 |
+
"learning_rate": 0.00019737864369982693,
|
1108 |
+
"loss": 1.1058,
|
1109 |
+
"step": 178
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.77,
|
1113 |
+
"learning_rate": 0.00019734748330639085,
|
1114 |
+
"loss": 0.9976,
|
1115 |
+
"step": 179
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.78,
|
1119 |
+
"learning_rate": 0.00019731614129083754,
|
1120 |
+
"loss": 1.0805,
|
1121 |
+
"step": 180
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 0.78,
|
1125 |
+
"learning_rate": 0.00019728461771164208,
|
1126 |
+
"loss": 1.094,
|
1127 |
+
"step": 181
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 0.79,
|
1131 |
+
"learning_rate": 0.00019725291262761828,
|
1132 |
+
"loss": 1.0198,
|
1133 |
+
"step": 182
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 0.79,
|
1137 |
+
"learning_rate": 0.00019722102609791861,
|
1138 |
+
"loss": 1.1689,
|
1139 |
+
"step": 183
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 0.8,
|
1143 |
+
"learning_rate": 0.00019718895818203412,
|
1144 |
+
"loss": 0.9169,
|
1145 |
+
"step": 184
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.8,
|
1149 |
+
"learning_rate": 0.00019715670893979414,
|
1150 |
+
"loss": 0.9862,
|
1151 |
+
"step": 185
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.81,
|
1155 |
+
"learning_rate": 0.0001971242784313665,
|
1156 |
+
"loss": 0.9377,
|
1157 |
+
"step": 186
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.81,
|
1161 |
+
"learning_rate": 0.00019709166671725702,
|
1162 |
+
"loss": 1.2023,
|
1163 |
+
"step": 187
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 0.81,
|
1167 |
+
"learning_rate": 0.00019705887385830967,
|
1168 |
+
"loss": 0.9953,
|
1169 |
+
"step": 188
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 0.82,
|
1173 |
+
"learning_rate": 0.00019702589991570647,
|
1174 |
+
"loss": 1.0906,
|
1175 |
+
"step": 189
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 0.82,
|
1179 |
+
"learning_rate": 0.00019699274495096712,
|
1180 |
+
"loss": 1.0964,
|
1181 |
+
"step": 190
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 0.83,
|
1185 |
+
"learning_rate": 0.00019695940902594926,
|
1186 |
+
"loss": 0.9253,
|
1187 |
+
"step": 191
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.83,
|
1191 |
+
"learning_rate": 0.00019692589220284795,
|
1192 |
+
"loss": 1.1055,
|
1193 |
+
"step": 192
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.84,
|
1197 |
+
"learning_rate": 0.0001968921945441959,
|
1198 |
+
"loss": 1.0955,
|
1199 |
+
"step": 193
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.84,
|
1203 |
+
"learning_rate": 0.0001968583161128631,
|
1204 |
+
"loss": 0.9852,
|
1205 |
+
"step": 194
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 0.84,
|
1209 |
+
"learning_rate": 0.00019682425697205693,
|
1210 |
+
"loss": 1.1119,
|
1211 |
+
"step": 195
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 0.85,
|
1215 |
+
"learning_rate": 0.00019679001718532176,
|
1216 |
+
"loss": 1.0639,
|
1217 |
+
"step": 196
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 0.85,
|
1221 |
+
"learning_rate": 0.00019675559681653918,
|
1222 |
+
"loss": 0.9929,
|
1223 |
+
"step": 197
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 0.86,
|
1227 |
+
"learning_rate": 0.0001967209959299275,
|
1228 |
+
"loss": 1.0679,
|
1229 |
+
"step": 198
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.86,
|
1233 |
+
"learning_rate": 0.00019668621459004198,
|
1234 |
+
"loss": 1.0858,
|
1235 |
+
"step": 199
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.87,
|
1239 |
+
"learning_rate": 0.00019665125286177449,
|
1240 |
+
"loss": 1.0464,
|
1241 |
+
"step": 200
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.87,
|
1245 |
+
"learning_rate": 0.00019661611081035342,
|
1246 |
+
"loss": 1.0395,
|
1247 |
+
"step": 201
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 0.87,
|
1251 |
+
"learning_rate": 0.00019658078850134366,
|
1252 |
+
"loss": 1.1564,
|
1253 |
+
"step": 202
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 0.88,
|
1257 |
+
"learning_rate": 0.00019654528600064638,
|
1258 |
+
"loss": 1.0532,
|
1259 |
+
"step": 203
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.88,
|
1263 |
+
"learning_rate": 0.0001965096033744989,
|
1264 |
+
"loss": 1.0791,
|
1265 |
+
"step": 204
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.89,
|
1269 |
+
"learning_rate": 0.0001964737406894747,
|
1270 |
+
"loss": 1.0113,
|
1271 |
+
"step": 205
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.89,
|
1275 |
+
"learning_rate": 0.000196437698012483,
|
1276 |
+
"loss": 0.9027,
|
1277 |
+
"step": 206
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.9,
|
1281 |
+
"learning_rate": 0.00019640147541076907,
|
1282 |
+
"loss": 1.0135,
|
1283 |
+
"step": 207
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.9,
|
1287 |
+
"learning_rate": 0.00019636507295191376,
|
1288 |
+
"loss": 1.05,
|
1289 |
+
"step": 208
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 0.9,
|
1293 |
+
"learning_rate": 0.00019632849070383342,
|
1294 |
+
"loss": 1.0013,
|
1295 |
+
"step": 209
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 0.91,
|
1299 |
+
"learning_rate": 0.00019629172873477995,
|
1300 |
+
"loss": 0.9422,
|
1301 |
+
"step": 210
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.91,
|
1305 |
+
"learning_rate": 0.00019625478711334044,
|
1306 |
+
"loss": 1.0928,
|
1307 |
+
"step": 211
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 0.92,
|
1311 |
+
"learning_rate": 0.00019621766590843727,
|
1312 |
+
"loss": 1.0085,
|
1313 |
+
"step": 212
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.92,
|
1317 |
+
"learning_rate": 0.00019618036518932784,
|
1318 |
+
"loss": 1.1621,
|
1319 |
+
"step": 213
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.93,
|
1323 |
+
"learning_rate": 0.0001961428850256044,
|
1324 |
+
"loss": 0.9738,
|
1325 |
+
"step": 214
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.93,
|
1329 |
+
"learning_rate": 0.0001961052254871941,
|
1330 |
+
"loss": 1.0869,
|
1331 |
+
"step": 215
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 0.94,
|
1335 |
+
"learning_rate": 0.0001960673866443586,
|
1336 |
+
"loss": 1.0263,
|
1337 |
+
"step": 216
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 0.94,
|
1341 |
+
"learning_rate": 0.0001960293685676943,
|
1342 |
+
"loss": 0.9994,
|
1343 |
+
"step": 217
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.94,
|
1347 |
+
"learning_rate": 0.00019599117132813184,
|
1348 |
+
"loss": 1.1272,
|
1349 |
+
"step": 218
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.95,
|
1353 |
+
"learning_rate": 0.00019595279499693614,
|
1354 |
+
"loss": 1.0041,
|
1355 |
+
"step": 219
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.95,
|
1359 |
+
"learning_rate": 0.00019591423964570632,
|
1360 |
+
"loss": 1.0379,
|
1361 |
+
"step": 220
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.96,
|
1365 |
+
"learning_rate": 0.00019587550534637545,
|
1366 |
+
"loss": 1.039,
|
1367 |
+
"step": 221
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.96,
|
1371 |
+
"learning_rate": 0.0001958365921712105,
|
1372 |
+
"loss": 0.9473,
|
1373 |
+
"step": 222
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 0.97,
|
1377 |
+
"learning_rate": 0.00019579750019281208,
|
1378 |
+
"loss": 0.9826,
|
1379 |
+
"step": 223
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 0.97,
|
1383 |
+
"learning_rate": 0.00019575822948411452,
|
1384 |
+
"loss": 1.0042,
|
1385 |
+
"step": 224
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.97,
|
1389 |
+
"learning_rate": 0.00019571878011838555,
|
1390 |
+
"loss": 1.0246,
|
1391 |
+
"step": 225
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.98,
|
1395 |
+
"learning_rate": 0.00019567915216922623,
|
1396 |
+
"loss": 0.9494,
|
1397 |
+
"step": 226
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 0.98,
|
1401 |
+
"learning_rate": 0.00019563934571057074,
|
1402 |
+
"loss": 1.0588,
|
1403 |
+
"step": 227
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.99,
|
1407 |
+
"learning_rate": 0.00019559936081668645,
|
1408 |
+
"loss": 1.044,
|
1409 |
+
"step": 228
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.99,
|
1413 |
+
"learning_rate": 0.00019555919756217348,
|
1414 |
+
"loss": 1.0803,
|
1415 |
+
"step": 229
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 1.0,
|
1419 |
+
"learning_rate": 0.0001955188560219648,
|
1420 |
+
"loss": 1.0251,
|
1421 |
+
"step": 230
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 1.0,
|
1425 |
+
"learning_rate": 0.00019547833627132607,
|
1426 |
+
"loss": 1.0764,
|
1427 |
+
"step": 231
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.0,
|
1431 |
+
"learning_rate": 0.0001954376383858553,
|
1432 |
+
"loss": 1.0182,
|
1433 |
+
"step": 232
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 1.0,
|
1437 |
+
"eval_loss": 1.0018986463546753,
|
1438 |
+
"eval_runtime": 80.9338,
|
1439 |
+
"eval_samples_per_second": 0.643,
|
1440 |
+
"eval_steps_per_second": 0.321,
|
1441 |
+
"step": 232
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.01,
|
1445 |
+
"learning_rate": 0.00019539676244148294,
|
1446 |
+
"loss": 1.081,
|
1447 |
+
"step": 233
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 1.01,
|
1451 |
+
"learning_rate": 0.00019535570851447165,
|
1452 |
+
"loss": 1.07,
|
1453 |
+
"step": 234
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 1.02,
|
1457 |
+
"learning_rate": 0.00019531447668141608,
|
1458 |
+
"loss": 1.0361,
|
1459 |
+
"step": 235
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.02,
|
1463 |
+
"learning_rate": 0.0001952730670192429,
|
1464 |
+
"loss": 1.1156,
|
1465 |
+
"step": 236
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.0,
|
1469 |
+
"learning_rate": 0.00019523147960521047,
|
1470 |
+
"loss": 0.9632,
|
1471 |
+
"step": 237
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.01,
|
1475 |
+
"learning_rate": 0.00019518971451690885,
|
1476 |
+
"loss": 1.033,
|
1477 |
+
"step": 238
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 1.01,
|
1481 |
+
"learning_rate": 0.00019514777183225952,
|
1482 |
+
"loss": 1.0654,
|
1483 |
+
"step": 239
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 1.02,
|
1487 |
+
"learning_rate": 0.00019510565162951537,
|
1488 |
+
"loss": 0.9885,
|
1489 |
+
"step": 240
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.02,
|
1493 |
+
"learning_rate": 0.00019506335398726044,
|
1494 |
+
"loss": 0.959,
|
1495 |
+
"step": 241
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 1.03,
|
1499 |
+
"learning_rate": 0.00019502087898440987,
|
1500 |
+
"loss": 0.9577,
|
1501 |
+
"step": 242
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.03,
|
1505 |
+
"learning_rate": 0.00019497822670020966,
|
1506 |
+
"loss": 1.0313,
|
1507 |
+
"step": 243
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 1.03,
|
1511 |
+
"learning_rate": 0.00019493539721423658,
|
1512 |
+
"loss": 0.9624,
|
1513 |
+
"step": 244
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 1.04,
|
1517 |
+
"learning_rate": 0.00019489239060639798,
|
1518 |
+
"loss": 0.997,
|
1519 |
+
"step": 245
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 1.04,
|
1523 |
+
"learning_rate": 0.00019484920695693174,
|
1524 |
+
"loss": 0.9422,
|
1525 |
+
"step": 246
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 1.05,
|
1529 |
+
"learning_rate": 0.00019480584634640598,
|
1530 |
+
"loss": 0.9803,
|
1531 |
+
"step": 247
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 1.05,
|
1535 |
+
"learning_rate": 0.00019476230885571898,
|
1536 |
+
"loss": 1.0103,
|
1537 |
+
"step": 248
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 1.06,
|
1541 |
+
"learning_rate": 0.00019471859456609907,
|
1542 |
+
"loss": 0.9219,
|
1543 |
+
"step": 249
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 1.06,
|
1547 |
+
"learning_rate": 0.00019467470355910438,
|
1548 |
+
"loss": 0.9467,
|
1549 |
+
"step": 250
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 1.06,
|
1553 |
+
"learning_rate": 0.00019463063591662282,
|
1554 |
+
"loss": 1.0323,
|
1555 |
+
"step": 251
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 1.07,
|
1559 |
+
"learning_rate": 0.00019458639172087181,
|
1560 |
+
"loss": 0.9904,
|
1561 |
+
"step": 252
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 1.07,
|
1565 |
+
"learning_rate": 0.0001945419710543981,
|
1566 |
+
"loss": 0.9563,
|
1567 |
+
"step": 253
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 1.08,
|
1571 |
+
"learning_rate": 0.0001944973740000778,
|
1572 |
+
"loss": 0.9692,
|
1573 |
+
"step": 254
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 1.08,
|
1577 |
+
"learning_rate": 0.00019445260064111607,
|
1578 |
+
"loss": 0.974,
|
1579 |
+
"step": 255
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 1.09,
|
1583 |
+
"learning_rate": 0.00019440765106104694,
|
1584 |
+
"loss": 0.9765,
|
1585 |
+
"step": 256
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 1.09,
|
1589 |
+
"learning_rate": 0.00019436252534373326,
|
1590 |
+
"loss": 1.0195,
|
1591 |
+
"step": 257
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 1.1,
|
1595 |
+
"learning_rate": 0.00019431722357336656,
|
1596 |
+
"loss": 0.984,
|
1597 |
+
"step": 258
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 1.1,
|
1601 |
+
"learning_rate": 0.00019427174583446673,
|
1602 |
+
"loss": 0.9831,
|
1603 |
+
"step": 259
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"epoch": 1.1,
|
1607 |
+
"learning_rate": 0.00019422609221188207,
|
1608 |
+
"loss": 0.9619,
|
1609 |
+
"step": 260
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 1.11,
|
1613 |
+
"learning_rate": 0.0001941802627907889,
|
1614 |
+
"loss": 1.0052,
|
1615 |
+
"step": 261
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 1.11,
|
1619 |
+
"learning_rate": 0.00019413425765669166,
|
1620 |
+
"loss": 0.885,
|
1621 |
+
"step": 262
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 1.12,
|
1625 |
+
"learning_rate": 0.00019408807689542257,
|
1626 |
+
"loss": 0.9341,
|
1627 |
+
"step": 263
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 1.12,
|
1631 |
+
"learning_rate": 0.00019404172059314144,
|
1632 |
+
"loss": 0.9914,
|
1633 |
+
"step": 264
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 1.13,
|
1637 |
+
"learning_rate": 0.00019399518883633573,
|
1638 |
+
"loss": 0.9276,
|
1639 |
+
"step": 265
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 1.13,
|
1643 |
+
"learning_rate": 0.0001939484817118202,
|
1644 |
+
"loss": 1.0014,
|
1645 |
+
"step": 266
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 1.13,
|
1649 |
+
"learning_rate": 0.00019390159930673666,
|
1650 |
+
"loss": 1.1253,
|
1651 |
+
"step": 267
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.14,
|
1655 |
+
"learning_rate": 0.00019385454170855416,
|
1656 |
+
"loss": 0.8932,
|
1657 |
+
"step": 268
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 1.14,
|
1661 |
+
"learning_rate": 0.00019380730900506844,
|
1662 |
+
"loss": 1.0478,
|
1663 |
+
"step": 269
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 1.15,
|
1667 |
+
"learning_rate": 0.00019375990128440204,
|
1668 |
+
"loss": 0.9962,
|
1669 |
+
"step": 270
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 1.15,
|
1673 |
+
"learning_rate": 0.00019371231863500398,
|
1674 |
+
"loss": 0.8538,
|
1675 |
+
"step": 271
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 1.16,
|
1679 |
+
"learning_rate": 0.00019366456114564966,
|
1680 |
+
"loss": 0.8961,
|
1681 |
+
"step": 272
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 1.16,
|
1685 |
+
"learning_rate": 0.0001936166289054407,
|
1686 |
+
"loss": 1.0277,
|
1687 |
+
"step": 273
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"epoch": 1.16,
|
1691 |
+
"learning_rate": 0.00019356852200380463,
|
1692 |
+
"loss": 1.036,
|
1693 |
+
"step": 274
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 1.17,
|
1697 |
+
"learning_rate": 0.0001935202405304951,
|
1698 |
+
"loss": 1.0146,
|
1699 |
+
"step": 275
|
1700 |
+
},
|
1701 |
+
{
|
1702 |
+
"epoch": 1.17,
|
1703 |
+
"learning_rate": 0.0001934717845755912,
|
1704 |
+
"loss": 0.9657,
|
1705 |
+
"step": 276
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 1.18,
|
1709 |
+
"learning_rate": 0.0001934231542294977,
|
1710 |
+
"loss": 1.0322,
|
1711 |
+
"step": 277
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 1.18,
|
1715 |
+
"learning_rate": 0.00019337434958294471,
|
1716 |
+
"loss": 1.0221,
|
1717 |
+
"step": 278
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 1.19,
|
1721 |
+
"learning_rate": 0.0001933253707269875,
|
1722 |
+
"loss": 0.985,
|
1723 |
+
"step": 279
|
1724 |
+
},
|
1725 |
+
{
|
1726 |
+
"epoch": 1.19,
|
1727 |
+
"learning_rate": 0.00019327621775300637,
|
1728 |
+
"loss": 0.9492,
|
1729 |
+
"step": 280
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 1.19,
|
1733 |
+
"learning_rate": 0.00019322689075270652,
|
1734 |
+
"loss": 1.0773,
|
1735 |
+
"step": 281
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 1.2,
|
1739 |
+
"learning_rate": 0.00019317738981811778,
|
1740 |
+
"loss": 1.0923,
|
1741 |
+
"step": 282
|
1742 |
+
},
|
1743 |
+
{
|
1744 |
+
"epoch": 1.2,
|
1745 |
+
"learning_rate": 0.00019312771504159448,
|
1746 |
+
"loss": 0.91,
|
1747 |
+
"step": 283
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 1.21,
|
1751 |
+
"learning_rate": 0.00019307786651581542,
|
1752 |
+
"loss": 0.9786,
|
1753 |
+
"step": 284
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 1.21,
|
1757 |
+
"learning_rate": 0.0001930278443337833,
|
1758 |
+
"loss": 0.9862,
|
1759 |
+
"step": 285
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 1.22,
|
1763 |
+
"learning_rate": 0.00019297764858882514,
|
1764 |
+
"loss": 0.9334,
|
1765 |
+
"step": 286
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 1.22,
|
1769 |
+
"learning_rate": 0.00019292727937459154,
|
1770 |
+
"loss": 0.984,
|
1771 |
+
"step": 287
|
1772 |
+
},
|
1773 |
+
{
|
1774 |
+
"epoch": 1.23,
|
1775 |
+
"learning_rate": 0.00019287673678505682,
|
1776 |
+
"loss": 0.8539,
|
1777 |
+
"step": 288
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 1.23,
|
1781 |
+
"learning_rate": 0.0001928260209145188,
|
1782 |
+
"loss": 0.96,
|
1783 |
+
"step": 289
|
1784 |
+
},
|
1785 |
+
{
|
1786 |
+
"epoch": 1.23,
|
1787 |
+
"learning_rate": 0.00019277513185759844,
|
1788 |
+
"loss": 0.9604,
|
1789 |
+
"step": 290
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 1.23,
|
1793 |
+
"eval_loss": 1.0004881620407104,
|
1794 |
+
"eval_runtime": 80.9806,
|
1795 |
+
"eval_samples_per_second": 0.642,
|
1796 |
+
"eval_steps_per_second": 0.321,
|
1797 |
+
"step": 290
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 1.24,
|
1801 |
+
"learning_rate": 0.0001927240697092401,
|
1802 |
+
"loss": 1.0287,
|
1803 |
+
"step": 291
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 1.24,
|
1807 |
+
"learning_rate": 0.0001926728345647108,
|
1808 |
+
"loss": 0.994,
|
1809 |
+
"step": 292
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.25,
|
1813 |
+
"learning_rate": 0.00019262142651960048,
|
1814 |
+
"loss": 0.9442,
|
1815 |
+
"step": 293
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.25,
|
1819 |
+
"learning_rate": 0.0001925698456698216,
|
1820 |
+
"loss": 1.0317,
|
1821 |
+
"step": 294
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 1.26,
|
1825 |
+
"learning_rate": 0.00019251809211160903,
|
1826 |
+
"loss": 0.9337,
|
1827 |
+
"step": 295
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.26,
|
1831 |
+
"learning_rate": 0.00019246616594151985,
|
1832 |
+
"loss": 0.9683,
|
1833 |
+
"step": 296
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 1.26,
|
1837 |
+
"learning_rate": 0.00019241406725643327,
|
1838 |
+
"loss": 0.9819,
|
1839 |
+
"step": 297
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.27,
|
1843 |
+
"learning_rate": 0.00019236179615355026,
|
1844 |
+
"loss": 0.9556,
|
1845 |
+
"step": 298
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.27,
|
1849 |
+
"learning_rate": 0.0001923093527303935,
|
1850 |
+
"loss": 1.0034,
|
1851 |
+
"step": 299
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.28,
|
1855 |
+
"learning_rate": 0.00019225673708480717,
|
1856 |
+
"loss": 0.9104,
|
1857 |
+
"step": 300
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.28,
|
1861 |
+
"learning_rate": 0.00019220394931495683,
|
1862 |
+
"loss": 0.9555,
|
1863 |
+
"step": 301
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 1.29,
|
1867 |
+
"learning_rate": 0.00019215098951932906,
|
1868 |
+
"loss": 1.0719,
|
1869 |
+
"step": 302
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.29,
|
1873 |
+
"learning_rate": 0.0001920978577967315,
|
1874 |
+
"loss": 0.9801,
|
1875 |
+
"step": 303
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 1.29,
|
1879 |
+
"learning_rate": 0.0001920445542462925,
|
1880 |
+
"loss": 0.9875,
|
1881 |
+
"step": 304
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 1.3,
|
1885 |
+
"learning_rate": 0.0001919910789674609,
|
1886 |
+
"loss": 0.9806,
|
1887 |
+
"step": 305
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 1.3,
|
1891 |
+
"learning_rate": 0.00019193743206000617,
|
1892 |
+
"loss": 1.0391,
|
1893 |
+
"step": 306
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.31,
|
1897 |
+
"learning_rate": 0.00019188361362401776,
|
1898 |
+
"loss": 0.9475,
|
1899 |
+
"step": 307
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.31,
|
1903 |
+
"learning_rate": 0.0001918296237599053,
|
1904 |
+
"loss": 0.9549,
|
1905 |
+
"step": 308
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 1.32,
|
1909 |
+
"learning_rate": 0.00019177546256839812,
|
1910 |
+
"loss": 0.9201,
|
1911 |
+
"step": 309
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 1.32,
|
1915 |
+
"learning_rate": 0.00019172113015054532,
|
1916 |
+
"loss": 0.8709,
|
1917 |
+
"step": 310
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 1.32,
|
1921 |
+
"learning_rate": 0.00019166662660771534,
|
1922 |
+
"loss": 0.9228,
|
1923 |
+
"step": 311
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 1.33,
|
1927 |
+
"learning_rate": 0.00019161195204159604,
|
1928 |
+
"loss": 0.9925,
|
1929 |
+
"step": 312
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.33,
|
1933 |
+
"learning_rate": 0.0001915571065541942,
|
1934 |
+
"loss": 0.9712,
|
1935 |
+
"step": 313
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.34,
|
1939 |
+
"learning_rate": 0.00019150209024783562,
|
1940 |
+
"loss": 0.9587,
|
1941 |
+
"step": 314
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.34,
|
1945 |
+
"learning_rate": 0.0001914469032251647,
|
1946 |
+
"loss": 1.0361,
|
1947 |
+
"step": 315
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 1.35,
|
1951 |
+
"learning_rate": 0.0001913915455891444,
|
1952 |
+
"loss": 1.0425,
|
1953 |
+
"step": 316
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 1.35,
|
1957 |
+
"learning_rate": 0.000191336017443056,
|
1958 |
+
"loss": 0.9597,
|
1959 |
+
"step": 317
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 1.35,
|
1963 |
+
"learning_rate": 0.00019128031889049883,
|
1964 |
+
"loss": 0.9656,
|
1965 |
+
"step": 318
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 1.36,
|
1969 |
+
"learning_rate": 0.00019122445003539026,
|
1970 |
+
"loss": 0.946,
|
1971 |
+
"step": 319
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 1.36,
|
1975 |
+
"learning_rate": 0.00019116841098196536,
|
1976 |
+
"loss": 0.9749,
|
1977 |
+
"step": 320
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.37,
|
1981 |
+
"learning_rate": 0.00019111220183477666,
|
1982 |
+
"loss": 0.9431,
|
1983 |
+
"step": 321
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.37,
|
1987 |
+
"learning_rate": 0.00019105582269869412,
|
1988 |
+
"loss": 0.9995,
|
1989 |
+
"step": 322
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.38,
|
1993 |
+
"learning_rate": 0.0001909992736789048,
|
1994 |
+
"loss": 1.032,
|
1995 |
+
"step": 323
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 1.38,
|
1999 |
+
"learning_rate": 0.00019094255488091283,
|
2000 |
+
"loss": 1.0638,
|
2001 |
+
"step": 324
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 1.39,
|
2005 |
+
"learning_rate": 0.00019088566641053885,
|
2006 |
+
"loss": 1.0164,
|
2007 |
+
"step": 325
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 1.39,
|
2011 |
+
"learning_rate": 0.00019082860837392037,
|
2012 |
+
"loss": 1.0147,
|
2013 |
+
"step": 326
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 1.39,
|
2017 |
+
"learning_rate": 0.00019077138087751104,
|
2018 |
+
"loss": 1.0552,
|
2019 |
+
"step": 327
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.4,
|
2023 |
+
"learning_rate": 0.00019071398402808074,
|
2024 |
+
"loss": 0.9179,
|
2025 |
+
"step": 328
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 1.4,
|
2029 |
+
"learning_rate": 0.0001906564179327153,
|
2030 |
+
"loss": 1.0738,
|
2031 |
+
"step": 329
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 1.41,
|
2035 |
+
"learning_rate": 0.0001905986826988164,
|
2036 |
+
"loss": 0.9954,
|
2037 |
+
"step": 330
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 1.41,
|
2041 |
+
"learning_rate": 0.00019054077843410106,
|
2042 |
+
"loss": 0.9737,
|
2043 |
+
"step": 331
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 1.42,
|
2047 |
+
"learning_rate": 0.00019048270524660196,
|
2048 |
+
"loss": 0.9321,
|
2049 |
+
"step": 332
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 1.42,
|
2053 |
+
"learning_rate": 0.00019042446324466674,
|
2054 |
+
"loss": 1.034,
|
2055 |
+
"step": 333
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 1.42,
|
2059 |
+
"learning_rate": 0.00019036605253695802,
|
2060 |
+
"loss": 0.9852,
|
2061 |
+
"step": 334
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.43,
|
2065 |
+
"learning_rate": 0.00019030747323245327,
|
2066 |
+
"loss": 1.0359,
|
2067 |
+
"step": 335
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 1.43,
|
2071 |
+
"learning_rate": 0.0001902487254404444,
|
2072 |
+
"loss": 1.0103,
|
2073 |
+
"step": 336
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 1.44,
|
2077 |
+
"learning_rate": 0.00019018980927053777,
|
2078 |
+
"loss": 0.9564,
|
2079 |
+
"step": 337
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.44,
|
2083 |
+
"learning_rate": 0.00019013072483265377,
|
2084 |
+
"loss": 0.8988,
|
2085 |
+
"step": 338
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 1.45,
|
2089 |
+
"learning_rate": 0.00019007147223702687,
|
2090 |
+
"loss": 0.9197,
|
2091 |
+
"step": 339
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 1.45,
|
2095 |
+
"learning_rate": 0.00019001205159420513,
|
2096 |
+
"loss": 1.0789,
|
2097 |
+
"step": 340
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 1.45,
|
2101 |
+
"learning_rate": 0.0001899524630150502,
|
2102 |
+
"loss": 1.0591,
|
2103 |
+
"step": 341
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 1.46,
|
2107 |
+
"learning_rate": 0.0001898927066107371,
|
2108 |
+
"loss": 0.9553,
|
2109 |
+
"step": 342
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.46,
|
2113 |
+
"learning_rate": 0.00018983278249275388,
|
2114 |
+
"loss": 0.8957,
|
2115 |
+
"step": 343
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 1.47,
|
2119 |
+
"learning_rate": 0.00018977269077290155,
|
2120 |
+
"loss": 0.9349,
|
2121 |
+
"step": 344
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 1.47,
|
2125 |
+
"learning_rate": 0.00018971243156329378,
|
2126 |
+
"loss": 0.9705,
|
2127 |
+
"step": 345
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 1.48,
|
2131 |
+
"learning_rate": 0.0001896520049763568,
|
2132 |
+
"loss": 0.8995,
|
2133 |
+
"step": 346
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 1.48,
|
2137 |
+
"learning_rate": 0.000189591411124829,
|
2138 |
+
"loss": 0.9242,
|
2139 |
+
"step": 347
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 1.48,
|
2143 |
+
"learning_rate": 0.00018953065012176093,
|
2144 |
+
"loss": 1.0026,
|
2145 |
+
"step": 348
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.48,
|
2149 |
+
"eval_loss": 0.9947116374969482,
|
2150 |
+
"eval_runtime": 81.016,
|
2151 |
+
"eval_samples_per_second": 0.642,
|
2152 |
+
"eval_steps_per_second": 0.321,
|
2153 |
+
"step": 348
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 1.49,
|
2157 |
+
"learning_rate": 0.00018946972208051495,
|
2158 |
+
"loss": 1.0078,
|
2159 |
+
"step": 349
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 1.49,
|
2163 |
+
"learning_rate": 0.00018940862711476513,
|
2164 |
+
"loss": 0.9399,
|
2165 |
+
"step": 350
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 1.5,
|
2169 |
+
"learning_rate": 0.00018934736533849687,
|
2170 |
+
"loss": 0.9266,
|
2171 |
+
"step": 351
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 1.5,
|
2175 |
+
"learning_rate": 0.00018928593686600684,
|
2176 |
+
"loss": 1.0301,
|
2177 |
+
"step": 352
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 1.51,
|
2181 |
+
"learning_rate": 0.00018922434181190272,
|
2182 |
+
"loss": 0.9463,
|
2183 |
+
"step": 353
|
2184 |
+
},
|
2185 |
+
{
|
2186 |
+
"epoch": 1.51,
|
2187 |
+
"learning_rate": 0.00018916258029110305,
|
2188 |
+
"loss": 0.9941,
|
2189 |
+
"step": 354
|
2190 |
+
},
|
2191 |
+
{
|
2192 |
+
"epoch": 1.52,
|
2193 |
+
"learning_rate": 0.0001891006524188368,
|
2194 |
+
"loss": 1.0061,
|
2195 |
+
"step": 355
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 1.52,
|
2199 |
+
"learning_rate": 0.00018903855831064342,
|
2200 |
+
"loss": 0.9129,
|
2201 |
+
"step": 356
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 1.52,
|
2205 |
+
"learning_rate": 0.00018897629808237247,
|
2206 |
+
"loss": 1.0232,
|
2207 |
+
"step": 357
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 1.53,
|
2211 |
+
"learning_rate": 0.00018891387185018346,
|
2212 |
+
"loss": 0.9164,
|
2213 |
+
"step": 358
|
2214 |
+
},
|
2215 |
+
{
|
2216 |
+
"epoch": 1.53,
|
2217 |
+
"learning_rate": 0.00018885127973054558,
|
2218 |
+
"loss": 1.031,
|
2219 |
+
"step": 359
|
2220 |
+
},
|
2221 |
+
{
|
2222 |
+
"epoch": 1.54,
|
2223 |
+
"learning_rate": 0.0001887885218402375,
|
2224 |
+
"loss": 0.9675,
|
2225 |
+
"step": 360
|
2226 |
+
},
|
2227 |
+
{
|
2228 |
+
"epoch": 1.54,
|
2229 |
+
"learning_rate": 0.00018872559829634733,
|
2230 |
+
"loss": 1.1264,
|
2231 |
+
"step": 361
|
2232 |
+
},
|
2233 |
+
{
|
2234 |
+
"epoch": 1.55,
|
2235 |
+
"learning_rate": 0.000188662509216272,
|
2236 |
+
"loss": 0.9705,
|
2237 |
+
"step": 362
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 1.55,
|
2241 |
+
"learning_rate": 0.00018859925471771742,
|
2242 |
+
"loss": 0.9431,
|
2243 |
+
"step": 363
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 1.55,
|
2247 |
+
"learning_rate": 0.00018853583491869818,
|
2248 |
+
"loss": 0.9657,
|
2249 |
+
"step": 364
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 1.56,
|
2253 |
+
"learning_rate": 0.0001884722499375371,
|
2254 |
+
"loss": 1.0047,
|
2255 |
+
"step": 365
|
2256 |
+
},
|
2257 |
+
{
|
2258 |
+
"epoch": 1.56,
|
2259 |
+
"learning_rate": 0.00018840849989286532,
|
2260 |
+
"loss": 1.0543,
|
2261 |
+
"step": 366
|
2262 |
+
},
|
2263 |
+
{
|
2264 |
+
"epoch": 1.57,
|
2265 |
+
"learning_rate": 0.0001883445849036219,
|
2266 |
+
"loss": 0.9618,
|
2267 |
+
"step": 367
|
2268 |
+
},
|
2269 |
+
{
|
2270 |
+
"epoch": 1.57,
|
2271 |
+
"learning_rate": 0.00018828050508905365,
|
2272 |
+
"loss": 0.9136,
|
2273 |
+
"step": 368
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 1.58,
|
2277 |
+
"learning_rate": 0.00018821626056871485,
|
2278 |
+
"loss": 0.9688,
|
2279 |
+
"step": 369
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 1.58,
|
2283 |
+
"learning_rate": 0.00018815185146246716,
|
2284 |
+
"loss": 1.0479,
|
2285 |
+
"step": 370
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 1.58,
|
2289 |
+
"learning_rate": 0.00018808727789047924,
|
2290 |
+
"loss": 1.0292,
|
2291 |
+
"step": 371
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 1.59,
|
2295 |
+
"learning_rate": 0.00018802253997322657,
|
2296 |
+
"loss": 0.8738,
|
2297 |
+
"step": 372
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 1.59,
|
2301 |
+
"learning_rate": 0.0001879576378314913,
|
2302 |
+
"loss": 1.0127,
|
2303 |
+
"step": 373
|
2304 |
+
},
|
2305 |
+
{
|
2306 |
+
"epoch": 1.6,
|
2307 |
+
"learning_rate": 0.00018789257158636203,
|
2308 |
+
"loss": 1.02,
|
2309 |
+
"step": 374
|
2310 |
+
},
|
2311 |
+
{
|
2312 |
+
"epoch": 1.6,
|
2313 |
+
"learning_rate": 0.0001878273413592334,
|
2314 |
+
"loss": 0.9951,
|
2315 |
+
"step": 375
|
2316 |
+
},
|
2317 |
+
{
|
2318 |
+
"epoch": 1.61,
|
2319 |
+
"learning_rate": 0.0001877619472718061,
|
2320 |
+
"loss": 1.0025,
|
2321 |
+
"step": 376
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 1.61,
|
2325 |
+
"learning_rate": 0.00018769638944608646,
|
2326 |
+
"loss": 0.9847,
|
2327 |
+
"step": 377
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 1.61,
|
2331 |
+
"learning_rate": 0.00018763066800438636,
|
2332 |
+
"loss": 0.9779,
|
2333 |
+
"step": 378
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 1.62,
|
2337 |
+
"learning_rate": 0.00018756478306932294,
|
2338 |
+
"loss": 1.0122,
|
2339 |
+
"step": 379
|
2340 |
+
},
|
2341 |
+
{
|
2342 |
+
"epoch": 1.62,
|
2343 |
+
"learning_rate": 0.00018749873476381828,
|
2344 |
+
"loss": 0.9998,
|
2345 |
+
"step": 380
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 1.63,
|
2349 |
+
"learning_rate": 0.00018743252321109935,
|
2350 |
+
"loss": 0.9515,
|
2351 |
+
"step": 381
|
2352 |
+
},
|
2353 |
+
{
|
2354 |
+
"epoch": 1.63,
|
2355 |
+
"learning_rate": 0.00018736614853469768,
|
2356 |
+
"loss": 1.0467,
|
2357 |
+
"step": 382
|
2358 |
+
},
|
2359 |
+
{
|
2360 |
+
"epoch": 1.64,
|
2361 |
+
"learning_rate": 0.00018729961085844915,
|
2362 |
+
"loss": 1.0071,
|
2363 |
+
"step": 383
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 1.64,
|
2367 |
+
"learning_rate": 0.0001872329103064937,
|
2368 |
+
"loss": 1.0,
|
2369 |
+
"step": 384
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 1.65,
|
2373 |
+
"learning_rate": 0.00018716604700327514,
|
2374 |
+
"loss": 0.9072,
|
2375 |
+
"step": 385
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 1.65,
|
2379 |
+
"learning_rate": 0.00018709902107354103,
|
2380 |
+
"loss": 0.912,
|
2381 |
+
"step": 386
|
2382 |
+
},
|
2383 |
+
{
|
2384 |
+
"epoch": 1.65,
|
2385 |
+
"learning_rate": 0.00018703183264234227,
|
2386 |
+
"loss": 0.9476,
|
2387 |
+
"step": 387
|
2388 |
+
},
|
2389 |
+
{
|
2390 |
+
"epoch": 1.66,
|
2391 |
+
"learning_rate": 0.0001869644818350329,
|
2392 |
+
"loss": 0.9964,
|
2393 |
+
"step": 388
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"epoch": 1.66,
|
2397 |
+
"learning_rate": 0.00018689696877727006,
|
2398 |
+
"loss": 1.0276,
|
2399 |
+
"step": 389
|
2400 |
+
},
|
2401 |
+
{
|
2402 |
+
"epoch": 1.67,
|
2403 |
+
"learning_rate": 0.00018682929359501338,
|
2404 |
+
"loss": 0.9049,
|
2405 |
+
"step": 390
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 1.67,
|
2409 |
+
"learning_rate": 0.00018676145641452515,
|
2410 |
+
"loss": 0.9695,
|
2411 |
+
"step": 391
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 1.68,
|
2415 |
+
"learning_rate": 0.00018669345736236983,
|
2416 |
+
"loss": 0.9078,
|
2417 |
+
"step": 392
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 1.68,
|
2421 |
+
"learning_rate": 0.00018662529656541388,
|
2422 |
+
"loss": 0.9674,
|
2423 |
+
"step": 393
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 1.68,
|
2427 |
+
"learning_rate": 0.00018655697415082556,
|
2428 |
+
"loss": 0.9606,
|
2429 |
+
"step": 394
|
2430 |
+
},
|
2431 |
+
{
|
2432 |
+
"epoch": 1.69,
|
2433 |
+
"learning_rate": 0.0001864884902460746,
|
2434 |
+
"loss": 0.8688,
|
2435 |
+
"step": 395
|
2436 |
+
},
|
2437 |
+
{
|
2438 |
+
"epoch": 1.69,
|
2439 |
+
"learning_rate": 0.00018641984497893213,
|
2440 |
+
"loss": 1.0021,
|
2441 |
+
"step": 396
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 1.7,
|
2445 |
+
"learning_rate": 0.00018635103847747023,
|
2446 |
+
"loss": 0.9592,
|
2447 |
+
"step": 397
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 1.7,
|
2451 |
+
"learning_rate": 0.00018628207087006184,
|
2452 |
+
"loss": 0.8933,
|
2453 |
+
"step": 398
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 1.71,
|
2457 |
+
"learning_rate": 0.0001862129422853805,
|
2458 |
+
"loss": 0.9368,
|
2459 |
+
"step": 399
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 1.71,
|
2463 |
+
"learning_rate": 0.0001861436528524,
|
2464 |
+
"loss": 1.0112,
|
2465 |
+
"step": 400
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 1.71,
|
2469 |
+
"learning_rate": 0.0001860742027003944,
|
2470 |
+
"loss": 1.0098,
|
2471 |
+
"step": 401
|
2472 |
+
},
|
2473 |
+
{
|
2474 |
+
"epoch": 1.72,
|
2475 |
+
"learning_rate": 0.00018600459195893738,
|
2476 |
+
"loss": 0.8526,
|
2477 |
+
"step": 402
|
2478 |
+
},
|
2479 |
+
{
|
2480 |
+
"epoch": 1.72,
|
2481 |
+
"learning_rate": 0.00018593482075790244,
|
2482 |
+
"loss": 0.9283,
|
2483 |
+
"step": 403
|
2484 |
+
},
|
2485 |
+
{
|
2486 |
+
"epoch": 1.73,
|
2487 |
+
"learning_rate": 0.00018586488922746233,
|
2488 |
+
"loss": 0.9405,
|
2489 |
+
"step": 404
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 1.73,
|
2493 |
+
"learning_rate": 0.00018579479749808897,
|
2494 |
+
"loss": 0.9386,
|
2495 |
+
"step": 405
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 1.74,
|
2499 |
+
"learning_rate": 0.0001857245457005532,
|
2500 |
+
"loss": 0.9265,
|
2501 |
+
"step": 406
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 1.74,
|
2505 |
+
"eval_loss": 0.9922024607658386,
|
2506 |
+
"eval_runtime": 81.0283,
|
2507 |
+
"eval_samples_per_second": 0.642,
|
2508 |
+
"eval_steps_per_second": 0.321,
|
2509 |
+
"step": 406
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 1.74,
|
2513 |
+
"learning_rate": 0.0001856541339659244,
|
2514 |
+
"loss": 0.9656,
|
2515 |
+
"step": 407
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 1.74,
|
2519 |
+
"learning_rate": 0.00018558356242557043,
|
2520 |
+
"loss": 0.9213,
|
2521 |
+
"step": 408
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 1.75,
|
2525 |
+
"learning_rate": 0.00018551283121115729,
|
2526 |
+
"loss": 0.9558,
|
2527 |
+
"step": 409
|
2528 |
+
},
|
2529 |
+
{
|
2530 |
+
"epoch": 1.75,
|
2531 |
+
"learning_rate": 0.00018544194045464886,
|
2532 |
+
"loss": 1.0537,
|
2533 |
+
"step": 410
|
2534 |
+
},
|
2535 |
+
{
|
2536 |
+
"epoch": 1.76,
|
2537 |
+
"learning_rate": 0.00018537089028830672,
|
2538 |
+
"loss": 1.0134,
|
2539 |
+
"step": 411
|
2540 |
+
},
|
2541 |
+
{
|
2542 |
+
"epoch": 1.76,
|
2543 |
+
"learning_rate": 0.0001852996808446898,
|
2544 |
+
"loss": 1.0515,
|
2545 |
+
"step": 412
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 1.77,
|
2549 |
+
"learning_rate": 0.00018522831225665422,
|
2550 |
+
"loss": 0.9971,
|
2551 |
+
"step": 413
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 1.77,
|
2555 |
+
"learning_rate": 0.00018515678465735308,
|
2556 |
+
"loss": 0.9434,
|
2557 |
+
"step": 414
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 1.77,
|
2561 |
+
"learning_rate": 0.00018508509818023608,
|
2562 |
+
"loss": 0.9541,
|
2563 |
+
"step": 415
|
2564 |
+
},
|
2565 |
+
{
|
2566 |
+
"epoch": 1.78,
|
2567 |
+
"learning_rate": 0.0001850132529590493,
|
2568 |
+
"loss": 1.0231,
|
2569 |
+
"step": 416
|
2570 |
+
},
|
2571 |
+
{
|
2572 |
+
"epoch": 1.78,
|
2573 |
+
"learning_rate": 0.00018494124912783516,
|
2574 |
+
"loss": 0.895,
|
2575 |
+
"step": 417
|
2576 |
+
},
|
2577 |
+
{
|
2578 |
+
"epoch": 1.79,
|
2579 |
+
"learning_rate": 0.00018486908682093173,
|
2580 |
+
"loss": 1.0275,
|
2581 |
+
"step": 418
|
2582 |
+
},
|
2583 |
+
{
|
2584 |
+
"epoch": 1.79,
|
2585 |
+
"learning_rate": 0.00018479676617297303,
|
2586 |
+
"loss": 0.9956,
|
2587 |
+
"step": 419
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 1.8,
|
2591 |
+
"learning_rate": 0.00018472428731888837,
|
2592 |
+
"loss": 0.9154,
|
2593 |
+
"step": 420
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 1.8,
|
2597 |
+
"learning_rate": 0.00018465165039390215,
|
2598 |
+
"loss": 1.091,
|
2599 |
+
"step": 421
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 1.81,
|
2603 |
+
"learning_rate": 0.00018457885553353385,
|
2604 |
+
"loss": 0.9218,
|
2605 |
+
"step": 422
|
2606 |
+
},
|
2607 |
+
{
|
2608 |
+
"epoch": 1.81,
|
2609 |
+
"learning_rate": 0.00018450590287359748,
|
2610 |
+
"loss": 0.9878,
|
2611 |
+
"step": 423
|
2612 |
+
},
|
2613 |
+
{
|
2614 |
+
"epoch": 1.81,
|
2615 |
+
"learning_rate": 0.00018443279255020152,
|
2616 |
+
"loss": 0.9075,
|
2617 |
+
"step": 424
|
2618 |
+
},
|
2619 |
+
{
|
2620 |
+
"epoch": 1.82,
|
2621 |
+
"learning_rate": 0.00018435952469974856,
|
2622 |
+
"loss": 0.9818,
|
2623 |
+
"step": 425
|
2624 |
+
},
|
2625 |
+
{
|
2626 |
+
"epoch": 1.82,
|
2627 |
+
"learning_rate": 0.00018428609945893518,
|
2628 |
+
"loss": 0.9162,
|
2629 |
+
"step": 426
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 1.83,
|
2633 |
+
"learning_rate": 0.0001842125169647515,
|
2634 |
+
"loss": 0.9931,
|
2635 |
+
"step": 427
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 1.83,
|
2639 |
+
"learning_rate": 0.00018413877735448108,
|
2640 |
+
"loss": 0.984,
|
2641 |
+
"step": 428
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 1.84,
|
2645 |
+
"learning_rate": 0.0001840648807657006,
|
2646 |
+
"loss": 0.9306,
|
2647 |
+
"step": 429
|
2648 |
+
},
|
2649 |
+
{
|
2650 |
+
"epoch": 1.84,
|
2651 |
+
"learning_rate": 0.00018399082733627965,
|
2652 |
+
"loss": 0.9698,
|
2653 |
+
"step": 430
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 1.84,
|
2657 |
+
"learning_rate": 0.00018391661720438038,
|
2658 |
+
"loss": 0.9633,
|
2659 |
+
"step": 431
|
2660 |
+
},
|
2661 |
+
{
|
2662 |
+
"epoch": 1.85,
|
2663 |
+
"learning_rate": 0.00018384225050845735,
|
2664 |
+
"loss": 1.0766,
|
2665 |
+
"step": 432
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 1.85,
|
2669 |
+
"learning_rate": 0.00018376772738725722,
|
2670 |
+
"loss": 0.9762,
|
2671 |
+
"step": 433
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 1.86,
|
2675 |
+
"learning_rate": 0.00018369304797981843,
|
2676 |
+
"loss": 0.989,
|
2677 |
+
"step": 434
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 1.86,
|
2681 |
+
"learning_rate": 0.0001836182124254711,
|
2682 |
+
"loss": 0.9703,
|
2683 |
+
"step": 435
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 1.87,
|
2687 |
+
"learning_rate": 0.00018354322086383662,
|
2688 |
+
"loss": 0.9834,
|
2689 |
+
"step": 436
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 1.87,
|
2693 |
+
"learning_rate": 0.00018346807343482745,
|
2694 |
+
"loss": 0.9891,
|
2695 |
+
"step": 437
|
2696 |
+
},
|
2697 |
+
{
|
2698 |
+
"epoch": 1.87,
|
2699 |
+
"learning_rate": 0.00018339277027864682,
|
2700 |
+
"loss": 0.9947,
|
2701 |
+
"step": 438
|
2702 |
+
},
|
2703 |
+
{
|
2704 |
+
"epoch": 1.88,
|
2705 |
+
"learning_rate": 0.0001833173115357886,
|
2706 |
+
"loss": 0.9875,
|
2707 |
+
"step": 439
|
2708 |
+
},
|
2709 |
+
{
|
2710 |
+
"epoch": 1.88,
|
2711 |
+
"learning_rate": 0.00018324169734703683,
|
2712 |
+
"loss": 0.9665,
|
2713 |
+
"step": 440
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 1.89,
|
2717 |
+
"learning_rate": 0.00018316592785346564,
|
2718 |
+
"loss": 0.8935,
|
2719 |
+
"step": 441
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 1.89,
|
2723 |
+
"learning_rate": 0.00018309000319643892,
|
2724 |
+
"loss": 1.0179,
|
2725 |
+
"step": 442
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 1.9,
|
2729 |
+
"learning_rate": 0.00018301392351760992,
|
2730 |
+
"loss": 0.951,
|
2731 |
+
"step": 443
|
2732 |
+
},
|
2733 |
+
{
|
2734 |
+
"epoch": 1.9,
|
2735 |
+
"learning_rate": 0.00018293768895892134,
|
2736 |
+
"loss": 0.9589,
|
2737 |
+
"step": 444
|
2738 |
+
},
|
2739 |
+
{
|
2740 |
+
"epoch": 1.9,
|
2741 |
+
"learning_rate": 0.0001828612996626046,
|
2742 |
+
"loss": 0.9594,
|
2743 |
+
"step": 445
|
2744 |
+
},
|
2745 |
+
{
|
2746 |
+
"epoch": 1.91,
|
2747 |
+
"learning_rate": 0.00018278475577118,
|
2748 |
+
"loss": 0.9288,
|
2749 |
+
"step": 446
|
2750 |
+
},
|
2751 |
+
{
|
2752 |
+
"epoch": 1.91,
|
2753 |
+
"learning_rate": 0.00018270805742745617,
|
2754 |
+
"loss": 1.0545,
|
2755 |
+
"step": 447
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 1.92,
|
2759 |
+
"learning_rate": 0.00018263120477453,
|
2760 |
+
"loss": 0.9885,
|
2761 |
+
"step": 448
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 1.92,
|
2765 |
+
"learning_rate": 0.0001825541979557861,
|
2766 |
+
"loss": 0.9119,
|
2767 |
+
"step": 449
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 1.93,
|
2771 |
+
"learning_rate": 0.00018247703711489686,
|
2772 |
+
"loss": 0.9624,
|
2773 |
+
"step": 450
|
2774 |
+
},
|
2775 |
+
{
|
2776 |
+
"epoch": 1.93,
|
2777 |
+
"learning_rate": 0.00018239972239582203,
|
2778 |
+
"loss": 1.1076,
|
2779 |
+
"step": 451
|
2780 |
+
},
|
2781 |
+
{
|
2782 |
+
"epoch": 1.94,
|
2783 |
+
"learning_rate": 0.00018232225394280836,
|
2784 |
+
"loss": 0.9937,
|
2785 |
+
"step": 452
|
2786 |
+
},
|
2787 |
+
{
|
2788 |
+
"epoch": 1.94,
|
2789 |
+
"learning_rate": 0.0001822446319003895,
|
2790 |
+
"loss": 1.0366,
|
2791 |
+
"step": 453
|
2792 |
+
},
|
2793 |
+
{
|
2794 |
+
"epoch": 1.94,
|
2795 |
+
"learning_rate": 0.0001821668564133856,
|
2796 |
+
"loss": 0.9735,
|
2797 |
+
"step": 454
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 1.95,
|
2801 |
+
"learning_rate": 0.00018208892762690317,
|
2802 |
+
"loss": 0.9755,
|
2803 |
+
"step": 455
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 1.95,
|
2807 |
+
"learning_rate": 0.00018201084568633463,
|
2808 |
+
"loss": 1.0696,
|
2809 |
+
"step": 456
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 1.96,
|
2813 |
+
"learning_rate": 0.00018193261073735822,
|
2814 |
+
"loss": 1.0793,
|
2815 |
+
"step": 457
|
2816 |
+
},
|
2817 |
+
{
|
2818 |
+
"epoch": 1.96,
|
2819 |
+
"learning_rate": 0.0001818542229259376,
|
2820 |
+
"loss": 1.0016,
|
2821 |
+
"step": 458
|
2822 |
+
},
|
2823 |
+
{
|
2824 |
+
"epoch": 1.97,
|
2825 |
+
"learning_rate": 0.00018177568239832165,
|
2826 |
+
"loss": 1.0114,
|
2827 |
+
"step": 459
|
2828 |
+
},
|
2829 |
+
{
|
2830 |
+
"epoch": 1.97,
|
2831 |
+
"learning_rate": 0.0001816969893010442,
|
2832 |
+
"loss": 0.8932,
|
2833 |
+
"step": 460
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 1.97,
|
2837 |
+
"learning_rate": 0.0001816181437809237,
|
2838 |
+
"loss": 0.9821,
|
2839 |
+
"step": 461
|
2840 |
+
},
|
2841 |
+
{
|
2842 |
+
"epoch": 1.98,
|
2843 |
+
"learning_rate": 0.00018153914598506297,
|
2844 |
+
"loss": 1.0272,
|
2845 |
+
"step": 462
|
2846 |
+
}
|
2847 |
+
],
|
2848 |
+
"logging_steps": 1,
|
2849 |
+
"max_steps": 2310,
|
2850 |
+
"num_input_tokens_seen": 0,
|
2851 |
+
"num_train_epochs": 10,
|
2852 |
+
"save_steps": 231,
|
2853 |
+
"total_flos": 3.2675073228590285e+17,
|
2854 |
+
"train_batch_size": 2,
|
2855 |
+
"trial_name": null,
|
2856 |
+
"trial_params": null
|
2857 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82927ffe90b51593899088c9819d8f99d2c3cee85ff954cf955874f0579b430b
|
3 |
+
size 4731
|