Upload 7 files
Browse files- README.md +202 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2253 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: hishab/titulm-1b-bn-v1
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "hishab/titulm-1b-bn-v1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"out_proj",
|
25 |
+
"up_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a3b4361eea93a0bda321ad452248bbccc466147cd1696128e8396206dc26b99
|
3 |
+
size 37768408
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff09c451a10d4088bb54a29920ab4c7f6bfe1e15f4fa7f70303d92cee153f304
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1da0efa6bd078f65dc649d4e90d30aba6d462a8362459d030146b3c40a5e6c58
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,2253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9664931297302246,
|
3 |
+
"best_model_checkpoint": "./lora_bn_resume/checkpoint-3000",
|
4 |
+
"epoch": 1.9292604501607717,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 3000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.006430868167202572,
|
13 |
+
"grad_norm": 0.7529953718185425,
|
14 |
+
"learning_rate": 2.9999999999999997e-05,
|
15 |
+
"loss": 2.01,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.012861736334405145,
|
20 |
+
"grad_norm": 0.8143910765647888,
|
21 |
+
"learning_rate": 5.9999999999999995e-05,
|
22 |
+
"loss": 1.9794,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01929260450160772,
|
27 |
+
"grad_norm": 0.7554563283920288,
|
28 |
+
"learning_rate": 8.999999999999999e-05,
|
29 |
+
"loss": 1.9687,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02572347266881029,
|
34 |
+
"grad_norm": 0.701172411441803,
|
35 |
+
"learning_rate": 0.00011999999999999999,
|
36 |
+
"loss": 2.0374,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.03215434083601286,
|
41 |
+
"grad_norm": 0.7426002621650696,
|
42 |
+
"learning_rate": 0.00015,
|
43 |
+
"loss": 1.8484,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03858520900321544,
|
48 |
+
"grad_norm": 0.7900332808494568,
|
49 |
+
"learning_rate": 0.00017999999999999998,
|
50 |
+
"loss": 1.91,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04501607717041801,
|
55 |
+
"grad_norm": 0.7825136184692383,
|
56 |
+
"learning_rate": 0.00020999999999999998,
|
57 |
+
"loss": 1.9625,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.05144694533762058,
|
62 |
+
"grad_norm": 0.9338003993034363,
|
63 |
+
"learning_rate": 0.00023999999999999998,
|
64 |
+
"loss": 1.9668,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05787781350482315,
|
69 |
+
"grad_norm": 0.8660485148429871,
|
70 |
+
"learning_rate": 0.00027,
|
71 |
+
"loss": 2.0447,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.06430868167202572,
|
76 |
+
"grad_norm": 0.8631746768951416,
|
77 |
+
"learning_rate": 0.0003,
|
78 |
+
"loss": 2.0347,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0707395498392283,
|
83 |
+
"grad_norm": 0.9202760457992554,
|
84 |
+
"learning_rate": 0.00029934282584884994,
|
85 |
+
"loss": 2.0218,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.07717041800643087,
|
90 |
+
"grad_norm": 0.8508992791175842,
|
91 |
+
"learning_rate": 0.00029868565169769985,
|
92 |
+
"loss": 1.9808,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.08360128617363344,
|
97 |
+
"grad_norm": 0.9962050914764404,
|
98 |
+
"learning_rate": 0.0002980284775465498,
|
99 |
+
"loss": 1.9586,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.09003215434083602,
|
104 |
+
"grad_norm": 0.9159810543060303,
|
105 |
+
"learning_rate": 0.00029737130339539973,
|
106 |
+
"loss": 2.0257,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.09646302250803858,
|
111 |
+
"grad_norm": 0.8135138750076294,
|
112 |
+
"learning_rate": 0.0002967141292442497,
|
113 |
+
"loss": 2.0103,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.10289389067524116,
|
118 |
+
"grad_norm": 0.7933633327484131,
|
119 |
+
"learning_rate": 0.00029605695509309966,
|
120 |
+
"loss": 2.028,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.10932475884244373,
|
125 |
+
"grad_norm": 0.9258368611335754,
|
126 |
+
"learning_rate": 0.00029539978094194957,
|
127 |
+
"loss": 2.0654,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.1157556270096463,
|
132 |
+
"grad_norm": 0.8758969902992249,
|
133 |
+
"learning_rate": 0.00029474260679079954,
|
134 |
+
"loss": 1.9928,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.12218649517684887,
|
139 |
+
"grad_norm": 0.8316165804862976,
|
140 |
+
"learning_rate": 0.00029408543263964945,
|
141 |
+
"loss": 1.9748,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.12861736334405144,
|
146 |
+
"grad_norm": 0.8353763222694397,
|
147 |
+
"learning_rate": 0.0002934282584884994,
|
148 |
+
"loss": 2.0167,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.12861736334405144,
|
153 |
+
"eval_loss": 2.0699551105499268,
|
154 |
+
"eval_runtime": 131.8406,
|
155 |
+
"eval_samples_per_second": 15.17,
|
156 |
+
"eval_steps_per_second": 1.896,
|
157 |
+
"step": 200
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.13504823151125403,
|
161 |
+
"grad_norm": 0.8024882078170776,
|
162 |
+
"learning_rate": 0.0002927710843373494,
|
163 |
+
"loss": 2.1039,
|
164 |
+
"step": 210
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.1414790996784566,
|
168 |
+
"grad_norm": 0.861377477645874,
|
169 |
+
"learning_rate": 0.0002921139101861993,
|
170 |
+
"loss": 2.023,
|
171 |
+
"step": 220
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.14790996784565916,
|
175 |
+
"grad_norm": 0.8247071504592896,
|
176 |
+
"learning_rate": 0.00029145673603504926,
|
177 |
+
"loss": 1.9341,
|
178 |
+
"step": 230
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.15434083601286175,
|
182 |
+
"grad_norm": 0.8182681202888489,
|
183 |
+
"learning_rate": 0.0002907995618838992,
|
184 |
+
"loss": 2.0137,
|
185 |
+
"step": 240
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.1607717041800643,
|
189 |
+
"grad_norm": 0.8556217551231384,
|
190 |
+
"learning_rate": 0.00029014238773274913,
|
191 |
+
"loss": 2.0638,
|
192 |
+
"step": 250
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.16720257234726688,
|
196 |
+
"grad_norm": 0.7721512913703918,
|
197 |
+
"learning_rate": 0.0002894852135815991,
|
198 |
+
"loss": 2.0061,
|
199 |
+
"step": 260
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.17363344051446947,
|
203 |
+
"grad_norm": 0.7948784828186035,
|
204 |
+
"learning_rate": 0.000288828039430449,
|
205 |
+
"loss": 1.9751,
|
206 |
+
"step": 270
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.18006430868167203,
|
210 |
+
"grad_norm": 0.7582404613494873,
|
211 |
+
"learning_rate": 0.000288170865279299,
|
212 |
+
"loss": 2.0254,
|
213 |
+
"step": 280
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.1864951768488746,
|
217 |
+
"grad_norm": 0.9620535969734192,
|
218 |
+
"learning_rate": 0.00028751369112814894,
|
219 |
+
"loss": 1.9978,
|
220 |
+
"step": 290
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.19292604501607716,
|
224 |
+
"grad_norm": 0.7374221682548523,
|
225 |
+
"learning_rate": 0.00028685651697699885,
|
226 |
+
"loss": 2.0631,
|
227 |
+
"step": 300
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.19935691318327975,
|
231 |
+
"grad_norm": 0.794651210308075,
|
232 |
+
"learning_rate": 0.0002861993428258488,
|
233 |
+
"loss": 1.9507,
|
234 |
+
"step": 310
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2057877813504823,
|
238 |
+
"grad_norm": 0.7450920939445496,
|
239 |
+
"learning_rate": 0.00028554216867469873,
|
240 |
+
"loss": 2.0363,
|
241 |
+
"step": 320
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.21221864951768488,
|
245 |
+
"grad_norm": 0.7574348449707031,
|
246 |
+
"learning_rate": 0.0002848849945235487,
|
247 |
+
"loss": 2.0508,
|
248 |
+
"step": 330
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.21864951768488747,
|
252 |
+
"grad_norm": 0.9118533134460449,
|
253 |
+
"learning_rate": 0.00028422782037239866,
|
254 |
+
"loss": 2.0118,
|
255 |
+
"step": 340
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.22508038585209003,
|
259 |
+
"grad_norm": 0.8136394023895264,
|
260 |
+
"learning_rate": 0.0002835706462212486,
|
261 |
+
"loss": 2.1211,
|
262 |
+
"step": 350
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.2315112540192926,
|
266 |
+
"grad_norm": 0.9099079966545105,
|
267 |
+
"learning_rate": 0.00028291347207009854,
|
268 |
+
"loss": 2.0346,
|
269 |
+
"step": 360
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.2379421221864952,
|
273 |
+
"grad_norm": 0.830896258354187,
|
274 |
+
"learning_rate": 0.0002822562979189485,
|
275 |
+
"loss": 2.0494,
|
276 |
+
"step": 370
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.24437299035369775,
|
280 |
+
"grad_norm": 0.789002001285553,
|
281 |
+
"learning_rate": 0.0002815991237677984,
|
282 |
+
"loss": 1.9791,
|
283 |
+
"step": 380
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.2508038585209003,
|
287 |
+
"grad_norm": 0.8194644451141357,
|
288 |
+
"learning_rate": 0.0002809419496166484,
|
289 |
+
"loss": 2.0106,
|
290 |
+
"step": 390
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.2572347266881029,
|
294 |
+
"grad_norm": 0.8226191401481628,
|
295 |
+
"learning_rate": 0.00028028477546549835,
|
296 |
+
"loss": 2.0268,
|
297 |
+
"step": 400
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.2572347266881029,
|
301 |
+
"eval_loss": 2.057727575302124,
|
302 |
+
"eval_runtime": 127.2637,
|
303 |
+
"eval_samples_per_second": 15.715,
|
304 |
+
"eval_steps_per_second": 1.964,
|
305 |
+
"step": 400
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.26366559485530544,
|
309 |
+
"grad_norm": 0.796454668045044,
|
310 |
+
"learning_rate": 0.00027962760131434826,
|
311 |
+
"loss": 2.0376,
|
312 |
+
"step": 410
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.27009646302250806,
|
316 |
+
"grad_norm": 0.8327352404594421,
|
317 |
+
"learning_rate": 0.0002789704271631982,
|
318 |
+
"loss": 2.0481,
|
319 |
+
"step": 420
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.2765273311897106,
|
323 |
+
"grad_norm": 0.8051420450210571,
|
324 |
+
"learning_rate": 0.0002783132530120482,
|
325 |
+
"loss": 1.99,
|
326 |
+
"step": 430
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.2829581993569132,
|
330 |
+
"grad_norm": 0.7519128322601318,
|
331 |
+
"learning_rate": 0.0002776560788608981,
|
332 |
+
"loss": 2.0339,
|
333 |
+
"step": 440
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.28938906752411575,
|
337 |
+
"grad_norm": 0.8251495957374573,
|
338 |
+
"learning_rate": 0.00027699890470974807,
|
339 |
+
"loss": 2.0289,
|
340 |
+
"step": 450
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.2958199356913183,
|
344 |
+
"grad_norm": 0.7058277130126953,
|
345 |
+
"learning_rate": 0.000276341730558598,
|
346 |
+
"loss": 2.0669,
|
347 |
+
"step": 460
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.3022508038585209,
|
351 |
+
"grad_norm": 0.8475114107131958,
|
352 |
+
"learning_rate": 0.00027568455640744795,
|
353 |
+
"loss": 2.0506,
|
354 |
+
"step": 470
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.3086816720257235,
|
358 |
+
"grad_norm": 0.7855744957923889,
|
359 |
+
"learning_rate": 0.0002750273822562979,
|
360 |
+
"loss": 1.97,
|
361 |
+
"step": 480
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.31511254019292606,
|
365 |
+
"grad_norm": 0.727988064289093,
|
366 |
+
"learning_rate": 0.0002743702081051478,
|
367 |
+
"loss": 2.0705,
|
368 |
+
"step": 490
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.3215434083601286,
|
372 |
+
"grad_norm": 0.7662935853004456,
|
373 |
+
"learning_rate": 0.0002737130339539978,
|
374 |
+
"loss": 1.9678,
|
375 |
+
"step": 500
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.3279742765273312,
|
379 |
+
"grad_norm": 0.9171555638313293,
|
380 |
+
"learning_rate": 0.00027305585980284776,
|
381 |
+
"loss": 1.9818,
|
382 |
+
"step": 510
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.33440514469453375,
|
386 |
+
"grad_norm": 0.7959179282188416,
|
387 |
+
"learning_rate": 0.00027239868565169767,
|
388 |
+
"loss": 2.0014,
|
389 |
+
"step": 520
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.3408360128617363,
|
393 |
+
"grad_norm": 0.9359775185585022,
|
394 |
+
"learning_rate": 0.00027174151150054763,
|
395 |
+
"loss": 2.0244,
|
396 |
+
"step": 530
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.34726688102893893,
|
400 |
+
"grad_norm": 0.7740966081619263,
|
401 |
+
"learning_rate": 0.0002710843373493976,
|
402 |
+
"loss": 2.0883,
|
403 |
+
"step": 540
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.3536977491961415,
|
407 |
+
"grad_norm": 0.868601381778717,
|
408 |
+
"learning_rate": 0.0002704271631982475,
|
409 |
+
"loss": 2.0226,
|
410 |
+
"step": 550
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.36012861736334406,
|
414 |
+
"grad_norm": 0.8721134662628174,
|
415 |
+
"learning_rate": 0.0002697699890470975,
|
416 |
+
"loss": 2.0965,
|
417 |
+
"step": 560
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.3665594855305466,
|
421 |
+
"grad_norm": 0.8080394268035889,
|
422 |
+
"learning_rate": 0.00026911281489594744,
|
423 |
+
"loss": 2.0082,
|
424 |
+
"step": 570
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.3729903536977492,
|
428 |
+
"grad_norm": 1.7169413566589355,
|
429 |
+
"learning_rate": 0.00026845564074479735,
|
430 |
+
"loss": 2.039,
|
431 |
+
"step": 580
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.37942122186495175,
|
435 |
+
"grad_norm": 0.8220880031585693,
|
436 |
+
"learning_rate": 0.0002677984665936473,
|
437 |
+
"loss": 2.0696,
|
438 |
+
"step": 590
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.3858520900321543,
|
442 |
+
"grad_norm": 0.7639694213867188,
|
443 |
+
"learning_rate": 0.00026714129244249723,
|
444 |
+
"loss": 2.0014,
|
445 |
+
"step": 600
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.3858520900321543,
|
449 |
+
"eval_loss": 2.0443177223205566,
|
450 |
+
"eval_runtime": 133.8726,
|
451 |
+
"eval_samples_per_second": 14.94,
|
452 |
+
"eval_steps_per_second": 1.867,
|
453 |
+
"step": 600
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.39228295819935693,
|
457 |
+
"grad_norm": 0.817965567111969,
|
458 |
+
"learning_rate": 0.0002664841182913472,
|
459 |
+
"loss": 2.0553,
|
460 |
+
"step": 610
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.3987138263665595,
|
464 |
+
"grad_norm": 0.871166467666626,
|
465 |
+
"learning_rate": 0.00026582694414019716,
|
466 |
+
"loss": 2.0027,
|
467 |
+
"step": 620
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.40514469453376206,
|
471 |
+
"grad_norm": 0.7483948469161987,
|
472 |
+
"learning_rate": 0.00026516976998904707,
|
473 |
+
"loss": 2.0355,
|
474 |
+
"step": 630
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.4115755627009646,
|
478 |
+
"grad_norm": 0.8223303556442261,
|
479 |
+
"learning_rate": 0.00026451259583789704,
|
480 |
+
"loss": 2.0076,
|
481 |
+
"step": 640
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.4180064308681672,
|
485 |
+
"grad_norm": 0.80986088514328,
|
486 |
+
"learning_rate": 0.00026385542168674695,
|
487 |
+
"loss": 2.0781,
|
488 |
+
"step": 650
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.42443729903536975,
|
492 |
+
"grad_norm": 0.7527362704277039,
|
493 |
+
"learning_rate": 0.0002631982475355969,
|
494 |
+
"loss": 1.9727,
|
495 |
+
"step": 660
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.43086816720257237,
|
499 |
+
"grad_norm": 0.7571489810943604,
|
500 |
+
"learning_rate": 0.0002625410733844469,
|
501 |
+
"loss": 2.0205,
|
502 |
+
"step": 670
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.43729903536977494,
|
506 |
+
"grad_norm": 0.7976600527763367,
|
507 |
+
"learning_rate": 0.0002618838992332968,
|
508 |
+
"loss": 2.0505,
|
509 |
+
"step": 680
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.4437299035369775,
|
513 |
+
"grad_norm": 0.8057394623756409,
|
514 |
+
"learning_rate": 0.00026122672508214676,
|
515 |
+
"loss": 2.0351,
|
516 |
+
"step": 690
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.45016077170418006,
|
520 |
+
"grad_norm": 0.8420009016990662,
|
521 |
+
"learning_rate": 0.0002605695509309967,
|
522 |
+
"loss": 1.9655,
|
523 |
+
"step": 700
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.4565916398713826,
|
527 |
+
"grad_norm": 0.853597104549408,
|
528 |
+
"learning_rate": 0.00025991237677984664,
|
529 |
+
"loss": 1.9939,
|
530 |
+
"step": 710
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.4630225080385852,
|
534 |
+
"grad_norm": 0.7588443160057068,
|
535 |
+
"learning_rate": 0.0002592552026286966,
|
536 |
+
"loss": 2.032,
|
537 |
+
"step": 720
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.4694533762057878,
|
541 |
+
"grad_norm": 0.8099080920219421,
|
542 |
+
"learning_rate": 0.0002585980284775465,
|
543 |
+
"loss": 1.9817,
|
544 |
+
"step": 730
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.4758842443729904,
|
548 |
+
"grad_norm": 0.7894070148468018,
|
549 |
+
"learning_rate": 0.0002579408543263965,
|
550 |
+
"loss": 2.0001,
|
551 |
+
"step": 740
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.48231511254019294,
|
555 |
+
"grad_norm": 0.7474116683006287,
|
556 |
+
"learning_rate": 0.00025728368017524644,
|
557 |
+
"loss": 2.0077,
|
558 |
+
"step": 750
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.4887459807073955,
|
562 |
+
"grad_norm": 0.8076878786087036,
|
563 |
+
"learning_rate": 0.00025662650602409636,
|
564 |
+
"loss": 2.0394,
|
565 |
+
"step": 760
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.49517684887459806,
|
569 |
+
"grad_norm": 0.7559667825698853,
|
570 |
+
"learning_rate": 0.0002559693318729463,
|
571 |
+
"loss": 1.9753,
|
572 |
+
"step": 770
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.5016077170418006,
|
576 |
+
"grad_norm": 0.7402215600013733,
|
577 |
+
"learning_rate": 0.00025531215772179623,
|
578 |
+
"loss": 2.0353,
|
579 |
+
"step": 780
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.5080385852090032,
|
583 |
+
"grad_norm": 0.7112523317337036,
|
584 |
+
"learning_rate": 0.0002546549835706462,
|
585 |
+
"loss": 1.989,
|
586 |
+
"step": 790
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.5144694533762058,
|
590 |
+
"grad_norm": 0.7255666255950928,
|
591 |
+
"learning_rate": 0.00025399780941949616,
|
592 |
+
"loss": 1.9912,
|
593 |
+
"step": 800
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.5144694533762058,
|
597 |
+
"eval_loss": 2.0358893871307373,
|
598 |
+
"eval_runtime": 131.9747,
|
599 |
+
"eval_samples_per_second": 15.154,
|
600 |
+
"eval_steps_per_second": 1.894,
|
601 |
+
"step": 800
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.5209003215434084,
|
605 |
+
"grad_norm": 0.7614848613739014,
|
606 |
+
"learning_rate": 0.0002533406352683461,
|
607 |
+
"loss": 1.9507,
|
608 |
+
"step": 810
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.5273311897106109,
|
612 |
+
"grad_norm": 0.7834282517433167,
|
613 |
+
"learning_rate": 0.00025268346111719604,
|
614 |
+
"loss": 2.0572,
|
615 |
+
"step": 820
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.5337620578778135,
|
619 |
+
"grad_norm": 0.8642615079879761,
|
620 |
+
"learning_rate": 0.00025202628696604595,
|
621 |
+
"loss": 1.9766,
|
622 |
+
"step": 830
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.5401929260450161,
|
626 |
+
"grad_norm": 0.7937222123146057,
|
627 |
+
"learning_rate": 0.0002513691128148959,
|
628 |
+
"loss": 1.9718,
|
629 |
+
"step": 840
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.5466237942122186,
|
633 |
+
"grad_norm": 0.7922580242156982,
|
634 |
+
"learning_rate": 0.0002507119386637459,
|
635 |
+
"loss": 2.0098,
|
636 |
+
"step": 850
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.5530546623794212,
|
640 |
+
"grad_norm": 0.7464605569839478,
|
641 |
+
"learning_rate": 0.0002500547645125958,
|
642 |
+
"loss": 1.9529,
|
643 |
+
"step": 860
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.5594855305466238,
|
647 |
+
"grad_norm": 0.7568275332450867,
|
648 |
+
"learning_rate": 0.00024939759036144576,
|
649 |
+
"loss": 1.989,
|
650 |
+
"step": 870
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.5659163987138264,
|
654 |
+
"grad_norm": 0.7011362910270691,
|
655 |
+
"learning_rate": 0.00024874041621029573,
|
656 |
+
"loss": 2.031,
|
657 |
+
"step": 880
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.572347266881029,
|
661 |
+
"grad_norm": 0.7106270790100098,
|
662 |
+
"learning_rate": 0.00024808324205914564,
|
663 |
+
"loss": 2.022,
|
664 |
+
"step": 890
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.5787781350482315,
|
668 |
+
"grad_norm": 0.7415210604667664,
|
669 |
+
"learning_rate": 0.0002474260679079956,
|
670 |
+
"loss": 2.0595,
|
671 |
+
"step": 900
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.5852090032154341,
|
675 |
+
"grad_norm": 0.7313567399978638,
|
676 |
+
"learning_rate": 0.0002467688937568455,
|
677 |
+
"loss": 2.0293,
|
678 |
+
"step": 910
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.5916398713826366,
|
682 |
+
"grad_norm": 0.692523181438446,
|
683 |
+
"learning_rate": 0.0002461117196056955,
|
684 |
+
"loss": 2.0746,
|
685 |
+
"step": 920
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.5980707395498392,
|
689 |
+
"grad_norm": 0.6929277181625366,
|
690 |
+
"learning_rate": 0.00024545454545454545,
|
691 |
+
"loss": 1.955,
|
692 |
+
"step": 930
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.6045016077170418,
|
696 |
+
"grad_norm": 0.7199161648750305,
|
697 |
+
"learning_rate": 0.00024479737130339536,
|
698 |
+
"loss": 2.0454,
|
699 |
+
"step": 940
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.6109324758842444,
|
703 |
+
"grad_norm": 0.767314076423645,
|
704 |
+
"learning_rate": 0.00024414019715224533,
|
705 |
+
"loss": 2.0428,
|
706 |
+
"step": 950
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.617363344051447,
|
710 |
+
"grad_norm": 0.8044443130493164,
|
711 |
+
"learning_rate": 0.00024348302300109526,
|
712 |
+
"loss": 1.9423,
|
713 |
+
"step": 960
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.6237942122186495,
|
717 |
+
"grad_norm": 0.702936589717865,
|
718 |
+
"learning_rate": 0.0002428258488499452,
|
719 |
+
"loss": 1.9271,
|
720 |
+
"step": 970
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.6302250803858521,
|
724 |
+
"grad_norm": 0.7394160032272339,
|
725 |
+
"learning_rate": 0.00024216867469879517,
|
726 |
+
"loss": 1.9674,
|
727 |
+
"step": 980
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.6366559485530546,
|
731 |
+
"grad_norm": 0.7981842160224915,
|
732 |
+
"learning_rate": 0.0002415115005476451,
|
733 |
+
"loss": 1.9932,
|
734 |
+
"step": 990
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.6430868167202572,
|
738 |
+
"grad_norm": 0.871896505355835,
|
739 |
+
"learning_rate": 0.00024085432639649505,
|
740 |
+
"loss": 2.0182,
|
741 |
+
"step": 1000
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.6430868167202572,
|
745 |
+
"eval_loss": 2.024224281311035,
|
746 |
+
"eval_runtime": 130.1041,
|
747 |
+
"eval_samples_per_second": 15.372,
|
748 |
+
"eval_steps_per_second": 1.922,
|
749 |
+
"step": 1000
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 0.6495176848874598,
|
753 |
+
"grad_norm": 0.7123499512672424,
|
754 |
+
"learning_rate": 0.00024019715224534498,
|
755 |
+
"loss": 2.0923,
|
756 |
+
"step": 1010
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.6559485530546624,
|
760 |
+
"grad_norm": 0.7226546406745911,
|
761 |
+
"learning_rate": 0.00023953997809419495,
|
762 |
+
"loss": 2.0035,
|
763 |
+
"step": 1020
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.662379421221865,
|
767 |
+
"grad_norm": 0.7627468109130859,
|
768 |
+
"learning_rate": 0.0002388828039430449,
|
769 |
+
"loss": 1.9667,
|
770 |
+
"step": 1030
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.6688102893890675,
|
774 |
+
"grad_norm": 0.8175467252731323,
|
775 |
+
"learning_rate": 0.00023822562979189483,
|
776 |
+
"loss": 1.948,
|
777 |
+
"step": 1040
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.6752411575562701,
|
781 |
+
"grad_norm": 0.690073549747467,
|
782 |
+
"learning_rate": 0.0002375684556407448,
|
783 |
+
"loss": 2.0498,
|
784 |
+
"step": 1050
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 0.6816720257234726,
|
788 |
+
"grad_norm": 0.9848446249961853,
|
789 |
+
"learning_rate": 0.0002369112814895947,
|
790 |
+
"loss": 1.9874,
|
791 |
+
"step": 1060
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 0.6881028938906752,
|
795 |
+
"grad_norm": 0.7157571315765381,
|
796 |
+
"learning_rate": 0.00023625410733844467,
|
797 |
+
"loss": 2.0488,
|
798 |
+
"step": 1070
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.6945337620578779,
|
802 |
+
"grad_norm": 0.8503302931785583,
|
803 |
+
"learning_rate": 0.00023559693318729464,
|
804 |
+
"loss": 1.9958,
|
805 |
+
"step": 1080
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.7009646302250804,
|
809 |
+
"grad_norm": 0.7864677906036377,
|
810 |
+
"learning_rate": 0.00023493975903614455,
|
811 |
+
"loss": 2.0212,
|
812 |
+
"step": 1090
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.707395498392283,
|
816 |
+
"grad_norm": 1.7837698459625244,
|
817 |
+
"learning_rate": 0.0002342825848849945,
|
818 |
+
"loss": 1.9828,
|
819 |
+
"step": 1100
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.7138263665594855,
|
823 |
+
"grad_norm": 0.7183972001075745,
|
824 |
+
"learning_rate": 0.00023362541073384445,
|
825 |
+
"loss": 2.0652,
|
826 |
+
"step": 1110
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.7202572347266881,
|
830 |
+
"grad_norm": 0.7377676963806152,
|
831 |
+
"learning_rate": 0.0002329682365826944,
|
832 |
+
"loss": 2.0123,
|
833 |
+
"step": 1120
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 0.7266881028938906,
|
837 |
+
"grad_norm": 0.7170071601867676,
|
838 |
+
"learning_rate": 0.00023231106243154436,
|
839 |
+
"loss": 1.9759,
|
840 |
+
"step": 1130
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.7331189710610932,
|
844 |
+
"grad_norm": 0.6442170143127441,
|
845 |
+
"learning_rate": 0.00023165388828039427,
|
846 |
+
"loss": 2.047,
|
847 |
+
"step": 1140
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.7395498392282959,
|
851 |
+
"grad_norm": 0.7356306910514832,
|
852 |
+
"learning_rate": 0.00023099671412924423,
|
853 |
+
"loss": 2.0438,
|
854 |
+
"step": 1150
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.7459807073954984,
|
858 |
+
"grad_norm": 0.7483031153678894,
|
859 |
+
"learning_rate": 0.0002303395399780942,
|
860 |
+
"loss": 2.0274,
|
861 |
+
"step": 1160
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.752411575562701,
|
865 |
+
"grad_norm": 0.7624642848968506,
|
866 |
+
"learning_rate": 0.0002296823658269441,
|
867 |
+
"loss": 1.9938,
|
868 |
+
"step": 1170
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 0.7588424437299035,
|
872 |
+
"grad_norm": 0.7435073256492615,
|
873 |
+
"learning_rate": 0.00022902519167579408,
|
874 |
+
"loss": 1.9848,
|
875 |
+
"step": 1180
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 0.7652733118971061,
|
879 |
+
"grad_norm": 0.7327163219451904,
|
880 |
+
"learning_rate": 0.000228368017524644,
|
881 |
+
"loss": 2.0286,
|
882 |
+
"step": 1190
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.7717041800643086,
|
886 |
+
"grad_norm": 0.8398700952529907,
|
887 |
+
"learning_rate": 0.00022771084337349395,
|
888 |
+
"loss": 1.999,
|
889 |
+
"step": 1200
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.7717041800643086,
|
893 |
+
"eval_loss": 2.0166773796081543,
|
894 |
+
"eval_runtime": 129.989,
|
895 |
+
"eval_samples_per_second": 15.386,
|
896 |
+
"eval_steps_per_second": 1.923,
|
897 |
+
"step": 1200
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.7781350482315113,
|
901 |
+
"grad_norm": 0.6727181673049927,
|
902 |
+
"learning_rate": 0.00022705366922234392,
|
903 |
+
"loss": 2.0044,
|
904 |
+
"step": 1210
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.7845659163987139,
|
908 |
+
"grad_norm": 0.8738404512405396,
|
909 |
+
"learning_rate": 0.00022639649507119383,
|
910 |
+
"loss": 2.0246,
|
911 |
+
"step": 1220
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.7909967845659164,
|
915 |
+
"grad_norm": 0.760010302066803,
|
916 |
+
"learning_rate": 0.0002257393209200438,
|
917 |
+
"loss": 2.0058,
|
918 |
+
"step": 1230
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 0.797427652733119,
|
922 |
+
"grad_norm": 0.701081395149231,
|
923 |
+
"learning_rate": 0.00022508214676889373,
|
924 |
+
"loss": 1.9974,
|
925 |
+
"step": 1240
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.8038585209003215,
|
929 |
+
"grad_norm": 0.7346913814544678,
|
930 |
+
"learning_rate": 0.00022442497261774367,
|
931 |
+
"loss": 2.0884,
|
932 |
+
"step": 1250
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.8102893890675241,
|
936 |
+
"grad_norm": 0.7433114647865295,
|
937 |
+
"learning_rate": 0.00022376779846659364,
|
938 |
+
"loss": 1.9927,
|
939 |
+
"step": 1260
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.8167202572347267,
|
943 |
+
"grad_norm": 0.7781444787979126,
|
944 |
+
"learning_rate": 0.00022311062431544358,
|
945 |
+
"loss": 2.001,
|
946 |
+
"step": 1270
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.8231511254019293,
|
950 |
+
"grad_norm": 0.7538995742797852,
|
951 |
+
"learning_rate": 0.00022245345016429352,
|
952 |
+
"loss": 1.9947,
|
953 |
+
"step": 1280
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 0.8295819935691319,
|
957 |
+
"grad_norm": 0.7132537961006165,
|
958 |
+
"learning_rate": 0.00022179627601314345,
|
959 |
+
"loss": 1.9781,
|
960 |
+
"step": 1290
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.8360128617363344,
|
964 |
+
"grad_norm": 0.7174340486526489,
|
965 |
+
"learning_rate": 0.0002211391018619934,
|
966 |
+
"loss": 1.9848,
|
967 |
+
"step": 1300
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 0.842443729903537,
|
971 |
+
"grad_norm": 0.7245258092880249,
|
972 |
+
"learning_rate": 0.00022048192771084336,
|
973 |
+
"loss": 2.005,
|
974 |
+
"step": 1310
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.8488745980707395,
|
978 |
+
"grad_norm": 0.667892336845398,
|
979 |
+
"learning_rate": 0.0002198247535596933,
|
980 |
+
"loss": 1.9939,
|
981 |
+
"step": 1320
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.8553054662379421,
|
985 |
+
"grad_norm": 0.7173146605491638,
|
986 |
+
"learning_rate": 0.00021916757940854324,
|
987 |
+
"loss": 2.0636,
|
988 |
+
"step": 1330
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.8617363344051447,
|
992 |
+
"grad_norm": 0.7765901684761047,
|
993 |
+
"learning_rate": 0.0002185104052573932,
|
994 |
+
"loss": 1.9966,
|
995 |
+
"step": 1340
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 0.8681672025723473,
|
999 |
+
"grad_norm": 0.7077351808547974,
|
1000 |
+
"learning_rate": 0.00021785323110624314,
|
1001 |
+
"loss": 2.0078,
|
1002 |
+
"step": 1350
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.8745980707395499,
|
1006 |
+
"grad_norm": 0.736723780632019,
|
1007 |
+
"learning_rate": 0.00021719605695509308,
|
1008 |
+
"loss": 2.0292,
|
1009 |
+
"step": 1360
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 0.8810289389067524,
|
1013 |
+
"grad_norm": 0.732185959815979,
|
1014 |
+
"learning_rate": 0.00021653888280394302,
|
1015 |
+
"loss": 2.0223,
|
1016 |
+
"step": 1370
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.887459807073955,
|
1020 |
+
"grad_norm": 0.7002454400062561,
|
1021 |
+
"learning_rate": 0.00021588170865279298,
|
1022 |
+
"loss": 2.0068,
|
1023 |
+
"step": 1380
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.8938906752411575,
|
1027 |
+
"grad_norm": 0.75859534740448,
|
1028 |
+
"learning_rate": 0.00021522453450164292,
|
1029 |
+
"loss": 1.9556,
|
1030 |
+
"step": 1390
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 0.9003215434083601,
|
1034 |
+
"grad_norm": 0.7475289106369019,
|
1035 |
+
"learning_rate": 0.00021456736035049286,
|
1036 |
+
"loss": 1.9792,
|
1037 |
+
"step": 1400
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 0.9003215434083601,
|
1041 |
+
"eval_loss": 2.0089023113250732,
|
1042 |
+
"eval_runtime": 130.0325,
|
1043 |
+
"eval_samples_per_second": 15.381,
|
1044 |
+
"eval_steps_per_second": 1.923,
|
1045 |
+
"step": 1400
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.9067524115755627,
|
1049 |
+
"grad_norm": 0.7917546629905701,
|
1050 |
+
"learning_rate": 0.00021391018619934283,
|
1051 |
+
"loss": 1.9999,
|
1052 |
+
"step": 1410
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.9131832797427653,
|
1056 |
+
"grad_norm": 0.7062447667121887,
|
1057 |
+
"learning_rate": 0.00021325301204819274,
|
1058 |
+
"loss": 1.9779,
|
1059 |
+
"step": 1420
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.9196141479099679,
|
1063 |
+
"grad_norm": 0.6973288655281067,
|
1064 |
+
"learning_rate": 0.0002125958378970427,
|
1065 |
+
"loss": 2.0511,
|
1066 |
+
"step": 1430
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.9260450160771704,
|
1070 |
+
"grad_norm": 0.7297340035438538,
|
1071 |
+
"learning_rate": 0.00021193866374589267,
|
1072 |
+
"loss": 1.9764,
|
1073 |
+
"step": 1440
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.932475884244373,
|
1077 |
+
"grad_norm": 0.9256350994110107,
|
1078 |
+
"learning_rate": 0.00021128148959474258,
|
1079 |
+
"loss": 1.9559,
|
1080 |
+
"step": 1450
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.9389067524115756,
|
1084 |
+
"grad_norm": 0.6994000673294067,
|
1085 |
+
"learning_rate": 0.00021062431544359255,
|
1086 |
+
"loss": 2.0152,
|
1087 |
+
"step": 1460
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.9453376205787781,
|
1091 |
+
"grad_norm": 0.7412806749343872,
|
1092 |
+
"learning_rate": 0.00020996714129244246,
|
1093 |
+
"loss": 1.9494,
|
1094 |
+
"step": 1470
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.9517684887459807,
|
1098 |
+
"grad_norm": 0.729680061340332,
|
1099 |
+
"learning_rate": 0.00020930996714129242,
|
1100 |
+
"loss": 2.0272,
|
1101 |
+
"step": 1480
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.9581993569131833,
|
1105 |
+
"grad_norm": 0.7601342797279358,
|
1106 |
+
"learning_rate": 0.0002086527929901424,
|
1107 |
+
"loss": 1.9714,
|
1108 |
+
"step": 1490
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.9646302250803859,
|
1112 |
+
"grad_norm": 0.6875161528587341,
|
1113 |
+
"learning_rate": 0.0002079956188389923,
|
1114 |
+
"loss": 1.993,
|
1115 |
+
"step": 1500
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.9710610932475884,
|
1119 |
+
"grad_norm": 0.7520968317985535,
|
1120 |
+
"learning_rate": 0.00020733844468784227,
|
1121 |
+
"loss": 2.0471,
|
1122 |
+
"step": 1510
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.977491961414791,
|
1126 |
+
"grad_norm": 0.8061411380767822,
|
1127 |
+
"learning_rate": 0.00020668127053669218,
|
1128 |
+
"loss": 2.0145,
|
1129 |
+
"step": 1520
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.9839228295819936,
|
1133 |
+
"grad_norm": 0.7837228775024414,
|
1134 |
+
"learning_rate": 0.00020602409638554214,
|
1135 |
+
"loss": 1.9889,
|
1136 |
+
"step": 1530
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.9903536977491961,
|
1140 |
+
"grad_norm": 0.744296133518219,
|
1141 |
+
"learning_rate": 0.0002053669222343921,
|
1142 |
+
"loss": 1.9834,
|
1143 |
+
"step": 1540
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.9967845659163987,
|
1147 |
+
"grad_norm": 0.7137749791145325,
|
1148 |
+
"learning_rate": 0.00020470974808324202,
|
1149 |
+
"loss": 2.0582,
|
1150 |
+
"step": 1550
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.0032154340836013,
|
1154 |
+
"grad_norm": 0.718320906162262,
|
1155 |
+
"learning_rate": 0.000204052573932092,
|
1156 |
+
"loss": 1.9576,
|
1157 |
+
"step": 1560
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.0096463022508038,
|
1161 |
+
"grad_norm": 0.719998836517334,
|
1162 |
+
"learning_rate": 0.00020339539978094195,
|
1163 |
+
"loss": 1.9138,
|
1164 |
+
"step": 1570
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.0160771704180065,
|
1168 |
+
"grad_norm": 0.7154316306114197,
|
1169 |
+
"learning_rate": 0.00020273822562979186,
|
1170 |
+
"loss": 1.875,
|
1171 |
+
"step": 1580
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.022508038585209,
|
1175 |
+
"grad_norm": 0.6565534472465515,
|
1176 |
+
"learning_rate": 0.00020208105147864183,
|
1177 |
+
"loss": 1.9994,
|
1178 |
+
"step": 1590
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.0289389067524115,
|
1182 |
+
"grad_norm": 0.7222368121147156,
|
1183 |
+
"learning_rate": 0.00020142387732749177,
|
1184 |
+
"loss": 1.9591,
|
1185 |
+
"step": 1600
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.0289389067524115,
|
1189 |
+
"eval_loss": 2.002497673034668,
|
1190 |
+
"eval_runtime": 131.2869,
|
1191 |
+
"eval_samples_per_second": 15.234,
|
1192 |
+
"eval_steps_per_second": 1.904,
|
1193 |
+
"step": 1600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 1.0353697749196142,
|
1197 |
+
"grad_norm": 0.7213057279586792,
|
1198 |
+
"learning_rate": 0.0002007667031763417,
|
1199 |
+
"loss": 1.9464,
|
1200 |
+
"step": 1610
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 1.0418006430868167,
|
1204 |
+
"grad_norm": 0.6436830163002014,
|
1205 |
+
"learning_rate": 0.00020010952902519167,
|
1206 |
+
"loss": 1.8951,
|
1207 |
+
"step": 1620
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.0482315112540193,
|
1211 |
+
"grad_norm": 0.7160071134567261,
|
1212 |
+
"learning_rate": 0.00019945235487404158,
|
1213 |
+
"loss": 1.9062,
|
1214 |
+
"step": 1630
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 1.0546623794212218,
|
1218 |
+
"grad_norm": 0.6585739850997925,
|
1219 |
+
"learning_rate": 0.00019879518072289155,
|
1220 |
+
"loss": 1.9514,
|
1221 |
+
"step": 1640
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.0610932475884245,
|
1225 |
+
"grad_norm": 0.7445241808891296,
|
1226 |
+
"learning_rate": 0.0001981380065717415,
|
1227 |
+
"loss": 1.8301,
|
1228 |
+
"step": 1650
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 1.067524115755627,
|
1232 |
+
"grad_norm": 0.6654142141342163,
|
1233 |
+
"learning_rate": 0.00019748083242059143,
|
1234 |
+
"loss": 1.9048,
|
1235 |
+
"step": 1660
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.0739549839228295,
|
1239 |
+
"grad_norm": 0.7550114393234253,
|
1240 |
+
"learning_rate": 0.0001968236582694414,
|
1241 |
+
"loss": 1.9266,
|
1242 |
+
"step": 1670
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 1.0803858520900322,
|
1246 |
+
"grad_norm": 0.7276896834373474,
|
1247 |
+
"learning_rate": 0.00019616648411829133,
|
1248 |
+
"loss": 1.8942,
|
1249 |
+
"step": 1680
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 1.0868167202572347,
|
1253 |
+
"grad_norm": 0.7431575059890747,
|
1254 |
+
"learning_rate": 0.00019550930996714127,
|
1255 |
+
"loss": 1.9148,
|
1256 |
+
"step": 1690
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.0932475884244373,
|
1260 |
+
"grad_norm": 0.74256831407547,
|
1261 |
+
"learning_rate": 0.0001948521358159912,
|
1262 |
+
"loss": 1.942,
|
1263 |
+
"step": 1700
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.09967845659164,
|
1267 |
+
"grad_norm": 0.7295734286308289,
|
1268 |
+
"learning_rate": 0.00019419496166484117,
|
1269 |
+
"loss": 1.9331,
|
1270 |
+
"step": 1710
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 1.1061093247588425,
|
1274 |
+
"grad_norm": 0.7749672532081604,
|
1275 |
+
"learning_rate": 0.0001935377875136911,
|
1276 |
+
"loss": 1.9373,
|
1277 |
+
"step": 1720
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.112540192926045,
|
1281 |
+
"grad_norm": 0.6896611452102661,
|
1282 |
+
"learning_rate": 0.00019288061336254105,
|
1283 |
+
"loss": 1.8813,
|
1284 |
+
"step": 1730
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.1189710610932475,
|
1288 |
+
"grad_norm": 0.7282217741012573,
|
1289 |
+
"learning_rate": 0.00019222343921139102,
|
1290 |
+
"loss": 1.9634,
|
1291 |
+
"step": 1740
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.1254019292604502,
|
1295 |
+
"grad_norm": 0.7761743068695068,
|
1296 |
+
"learning_rate": 0.00019156626506024093,
|
1297 |
+
"loss": 1.8708,
|
1298 |
+
"step": 1750
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.1318327974276527,
|
1302 |
+
"grad_norm": 0.7596757411956787,
|
1303 |
+
"learning_rate": 0.0001909090909090909,
|
1304 |
+
"loss": 1.9446,
|
1305 |
+
"step": 1760
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.1382636655948553,
|
1309 |
+
"grad_norm": 0.7023797631263733,
|
1310 |
+
"learning_rate": 0.00019025191675794086,
|
1311 |
+
"loss": 1.8837,
|
1312 |
+
"step": 1770
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.144694533762058,
|
1316 |
+
"grad_norm": 0.7191573977470398,
|
1317 |
+
"learning_rate": 0.00018959474260679077,
|
1318 |
+
"loss": 1.9141,
|
1319 |
+
"step": 1780
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.1511254019292605,
|
1323 |
+
"grad_norm": 0.784885048866272,
|
1324 |
+
"learning_rate": 0.00018893756845564074,
|
1325 |
+
"loss": 1.9506,
|
1326 |
+
"step": 1790
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 1.157556270096463,
|
1330 |
+
"grad_norm": 0.710903525352478,
|
1331 |
+
"learning_rate": 0.00018828039430449068,
|
1332 |
+
"loss": 1.9157,
|
1333 |
+
"step": 1800
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.157556270096463,
|
1337 |
+
"eval_loss": 1.998835563659668,
|
1338 |
+
"eval_runtime": 121.0458,
|
1339 |
+
"eval_samples_per_second": 16.523,
|
1340 |
+
"eval_steps_per_second": 2.065,
|
1341 |
+
"step": 1800
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.1639871382636655,
|
1345 |
+
"grad_norm": 0.7552351355552673,
|
1346 |
+
"learning_rate": 0.00018762322015334062,
|
1347 |
+
"loss": 1.9139,
|
1348 |
+
"step": 1810
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 1.1704180064308682,
|
1352 |
+
"grad_norm": 0.7722271084785461,
|
1353 |
+
"learning_rate": 0.00018696604600219058,
|
1354 |
+
"loss": 1.863,
|
1355 |
+
"step": 1820
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 1.1768488745980707,
|
1359 |
+
"grad_norm": 0.7195548415184021,
|
1360 |
+
"learning_rate": 0.0001863088718510405,
|
1361 |
+
"loss": 1.8697,
|
1362 |
+
"step": 1830
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 1.1832797427652733,
|
1366 |
+
"grad_norm": 0.7423893809318542,
|
1367 |
+
"learning_rate": 0.00018565169769989046,
|
1368 |
+
"loss": 1.9772,
|
1369 |
+
"step": 1840
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 1.189710610932476,
|
1373 |
+
"grad_norm": 0.7222315073013306,
|
1374 |
+
"learning_rate": 0.00018499452354874042,
|
1375 |
+
"loss": 1.9308,
|
1376 |
+
"step": 1850
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 1.1961414790996785,
|
1380 |
+
"grad_norm": 0.6815035939216614,
|
1381 |
+
"learning_rate": 0.00018433734939759034,
|
1382 |
+
"loss": 1.9675,
|
1383 |
+
"step": 1860
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.202572347266881,
|
1387 |
+
"grad_norm": 0.7621594071388245,
|
1388 |
+
"learning_rate": 0.0001836801752464403,
|
1389 |
+
"loss": 1.9295,
|
1390 |
+
"step": 1870
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 1.2090032154340835,
|
1394 |
+
"grad_norm": 0.7405025959014893,
|
1395 |
+
"learning_rate": 0.0001830230010952902,
|
1396 |
+
"loss": 1.9088,
|
1397 |
+
"step": 1880
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 1.2154340836012862,
|
1401 |
+
"grad_norm": 0.6729809641838074,
|
1402 |
+
"learning_rate": 0.00018236582694414018,
|
1403 |
+
"loss": 1.9446,
|
1404 |
+
"step": 1890
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 1.2218649517684887,
|
1408 |
+
"grad_norm": 0.7389471530914307,
|
1409 |
+
"learning_rate": 0.00018170865279299014,
|
1410 |
+
"loss": 1.8841,
|
1411 |
+
"step": 1900
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 1.2282958199356913,
|
1415 |
+
"grad_norm": 0.6453628540039062,
|
1416 |
+
"learning_rate": 0.00018105147864184006,
|
1417 |
+
"loss": 1.8661,
|
1418 |
+
"step": 1910
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 1.234726688102894,
|
1422 |
+
"grad_norm": 0.6971079111099243,
|
1423 |
+
"learning_rate": 0.00018039430449069002,
|
1424 |
+
"loss": 1.9807,
|
1425 |
+
"step": 1920
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.2411575562700965,
|
1429 |
+
"grad_norm": 0.7807840704917908,
|
1430 |
+
"learning_rate": 0.00017973713033953996,
|
1431 |
+
"loss": 1.9475,
|
1432 |
+
"step": 1930
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 1.247588424437299,
|
1436 |
+
"grad_norm": 0.78909832239151,
|
1437 |
+
"learning_rate": 0.0001790799561883899,
|
1438 |
+
"loss": 1.8439,
|
1439 |
+
"step": 1940
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.2540192926045015,
|
1443 |
+
"grad_norm": 0.7715321183204651,
|
1444 |
+
"learning_rate": 0.00017842278203723986,
|
1445 |
+
"loss": 1.9478,
|
1446 |
+
"step": 1950
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 1.2604501607717042,
|
1450 |
+
"grad_norm": 0.7786479592323303,
|
1451 |
+
"learning_rate": 0.0001777656078860898,
|
1452 |
+
"loss": 1.8773,
|
1453 |
+
"step": 1960
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 1.2668810289389068,
|
1457 |
+
"grad_norm": 0.6935726404190063,
|
1458 |
+
"learning_rate": 0.00017710843373493974,
|
1459 |
+
"loss": 1.94,
|
1460 |
+
"step": 1970
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.2733118971061093,
|
1464 |
+
"grad_norm": 0.7824066877365112,
|
1465 |
+
"learning_rate": 0.00017645125958378968,
|
1466 |
+
"loss": 1.8996,
|
1467 |
+
"step": 1980
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.279742765273312,
|
1471 |
+
"grad_norm": 0.7019379138946533,
|
1472 |
+
"learning_rate": 0.00017579408543263962,
|
1473 |
+
"loss": 1.9114,
|
1474 |
+
"step": 1990
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.2861736334405145,
|
1478 |
+
"grad_norm": 0.8215466737747192,
|
1479 |
+
"learning_rate": 0.00017513691128148958,
|
1480 |
+
"loss": 1.8294,
|
1481 |
+
"step": 2000
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 1.2861736334405145,
|
1485 |
+
"eval_loss": 1.9947528839111328,
|
1486 |
+
"eval_runtime": 132.3397,
|
1487 |
+
"eval_samples_per_second": 15.113,
|
1488 |
+
"eval_steps_per_second": 1.889,
|
1489 |
+
"step": 2000
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.292604501607717,
|
1493 |
+
"grad_norm": 0.7088531851768494,
|
1494 |
+
"learning_rate": 0.00017447973713033952,
|
1495 |
+
"loss": 1.9497,
|
1496 |
+
"step": 2010
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 1.2990353697749195,
|
1500 |
+
"grad_norm": 0.7754150032997131,
|
1501 |
+
"learning_rate": 0.00017382256297918946,
|
1502 |
+
"loss": 1.9047,
|
1503 |
+
"step": 2020
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.3054662379421222,
|
1507 |
+
"grad_norm": 0.7185202836990356,
|
1508 |
+
"learning_rate": 0.00017316538882803943,
|
1509 |
+
"loss": 1.8529,
|
1510 |
+
"step": 2030
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.3118971061093248,
|
1514 |
+
"grad_norm": 0.7496573328971863,
|
1515 |
+
"learning_rate": 0.00017250821467688937,
|
1516 |
+
"loss": 1.8618,
|
1517 |
+
"step": 2040
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 1.3183279742765273,
|
1521 |
+
"grad_norm": 0.6794284582138062,
|
1522 |
+
"learning_rate": 0.0001718510405257393,
|
1523 |
+
"loss": 1.898,
|
1524 |
+
"step": 2050
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.32475884244373,
|
1528 |
+
"grad_norm": 0.7059448957443237,
|
1529 |
+
"learning_rate": 0.00017119386637458924,
|
1530 |
+
"loss": 1.9594,
|
1531 |
+
"step": 2060
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 1.3311897106109325,
|
1535 |
+
"grad_norm": 0.7007871866226196,
|
1536 |
+
"learning_rate": 0.0001705366922234392,
|
1537 |
+
"loss": 1.9476,
|
1538 |
+
"step": 2070
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 1.337620578778135,
|
1542 |
+
"grad_norm": 0.6973986029624939,
|
1543 |
+
"learning_rate": 0.00016987951807228915,
|
1544 |
+
"loss": 1.9567,
|
1545 |
+
"step": 2080
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.3440514469453375,
|
1549 |
+
"grad_norm": 0.7169969081878662,
|
1550 |
+
"learning_rate": 0.00016922234392113909,
|
1551 |
+
"loss": 1.9685,
|
1552 |
+
"step": 2090
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 1.3504823151125402,
|
1556 |
+
"grad_norm": 0.7009272575378418,
|
1557 |
+
"learning_rate": 0.00016856516976998905,
|
1558 |
+
"loss": 1.9714,
|
1559 |
+
"step": 2100
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 1.3569131832797428,
|
1563 |
+
"grad_norm": 0.7070193290710449,
|
1564 |
+
"learning_rate": 0.00016790799561883896,
|
1565 |
+
"loss": 1.9695,
|
1566 |
+
"step": 2110
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 1.3633440514469453,
|
1570 |
+
"grad_norm": 0.7268947958946228,
|
1571 |
+
"learning_rate": 0.00016725082146768893,
|
1572 |
+
"loss": 1.9107,
|
1573 |
+
"step": 2120
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 1.369774919614148,
|
1577 |
+
"grad_norm": 0.7544928789138794,
|
1578 |
+
"learning_rate": 0.00016659364731653887,
|
1579 |
+
"loss": 1.8658,
|
1580 |
+
"step": 2130
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 1.3762057877813505,
|
1584 |
+
"grad_norm": 0.6320627927780151,
|
1585 |
+
"learning_rate": 0.0001659364731653888,
|
1586 |
+
"loss": 1.8917,
|
1587 |
+
"step": 2140
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.382636655948553,
|
1591 |
+
"grad_norm": 0.6863923668861389,
|
1592 |
+
"learning_rate": 0.00016527929901423877,
|
1593 |
+
"loss": 1.9237,
|
1594 |
+
"step": 2150
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 1.3890675241157555,
|
1598 |
+
"grad_norm": 0.7775669097900391,
|
1599 |
+
"learning_rate": 0.00016462212486308868,
|
1600 |
+
"loss": 1.8548,
|
1601 |
+
"step": 2160
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 1.3954983922829582,
|
1605 |
+
"grad_norm": 0.7198719382286072,
|
1606 |
+
"learning_rate": 0.00016396495071193865,
|
1607 |
+
"loss": 1.9145,
|
1608 |
+
"step": 2170
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.4019292604501608,
|
1612 |
+
"grad_norm": 0.7938317656517029,
|
1613 |
+
"learning_rate": 0.00016330777656078861,
|
1614 |
+
"loss": 1.8939,
|
1615 |
+
"step": 2180
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 1.4083601286173635,
|
1619 |
+
"grad_norm": 0.7361711263656616,
|
1620 |
+
"learning_rate": 0.00016265060240963853,
|
1621 |
+
"loss": 1.9642,
|
1622 |
+
"step": 2190
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 1.414790996784566,
|
1626 |
+
"grad_norm": 0.7385576963424683,
|
1627 |
+
"learning_rate": 0.0001619934282584885,
|
1628 |
+
"loss": 1.9134,
|
1629 |
+
"step": 2200
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.414790996784566,
|
1633 |
+
"eval_loss": 1.9883830547332764,
|
1634 |
+
"eval_runtime": 130.0767,
|
1635 |
+
"eval_samples_per_second": 15.376,
|
1636 |
+
"eval_steps_per_second": 1.922,
|
1637 |
+
"step": 2200
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 1.4212218649517685,
|
1641 |
+
"grad_norm": 0.7863461971282959,
|
1642 |
+
"learning_rate": 0.0001613362541073384,
|
1643 |
+
"loss": 2.0157,
|
1644 |
+
"step": 2210
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.427652733118971,
|
1648 |
+
"grad_norm": 0.7755898237228394,
|
1649 |
+
"learning_rate": 0.00016067907995618837,
|
1650 |
+
"loss": 1.8973,
|
1651 |
+
"step": 2220
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.4340836012861735,
|
1655 |
+
"grad_norm": 0.7090388536453247,
|
1656 |
+
"learning_rate": 0.00016002190580503833,
|
1657 |
+
"loss": 1.9034,
|
1658 |
+
"step": 2230
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.4405144694533762,
|
1662 |
+
"grad_norm": 0.6487644910812378,
|
1663 |
+
"learning_rate": 0.00015936473165388825,
|
1664 |
+
"loss": 1.906,
|
1665 |
+
"step": 2240
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.4469453376205788,
|
1669 |
+
"grad_norm": 0.6597898006439209,
|
1670 |
+
"learning_rate": 0.0001587075575027382,
|
1671 |
+
"loss": 1.843,
|
1672 |
+
"step": 2250
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 1.4533762057877815,
|
1676 |
+
"grad_norm": 0.7069796323776245,
|
1677 |
+
"learning_rate": 0.00015805038335158818,
|
1678 |
+
"loss": 1.9554,
|
1679 |
+
"step": 2260
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 1.459807073954984,
|
1683 |
+
"grad_norm": 0.7358680367469788,
|
1684 |
+
"learning_rate": 0.0001573932092004381,
|
1685 |
+
"loss": 1.9268,
|
1686 |
+
"step": 2270
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 1.4662379421221865,
|
1690 |
+
"grad_norm": 0.675457775592804,
|
1691 |
+
"learning_rate": 0.00015673603504928806,
|
1692 |
+
"loss": 1.8981,
|
1693 |
+
"step": 2280
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 1.472668810289389,
|
1697 |
+
"grad_norm": 0.7369397878646851,
|
1698 |
+
"learning_rate": 0.000156078860898138,
|
1699 |
+
"loss": 1.9535,
|
1700 |
+
"step": 2290
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.4790996784565915,
|
1704 |
+
"grad_norm": 0.666994035243988,
|
1705 |
+
"learning_rate": 0.00015542168674698793,
|
1706 |
+
"loss": 1.8657,
|
1707 |
+
"step": 2300
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.4855305466237942,
|
1711 |
+
"grad_norm": 0.7241340279579163,
|
1712 |
+
"learning_rate": 0.0001547645125958379,
|
1713 |
+
"loss": 1.8097,
|
1714 |
+
"step": 2310
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.4919614147909968,
|
1718 |
+
"grad_norm": 0.7224936485290527,
|
1719 |
+
"learning_rate": 0.0001541073384446878,
|
1720 |
+
"loss": 1.8397,
|
1721 |
+
"step": 2320
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 1.4983922829581995,
|
1725 |
+
"grad_norm": 0.7167637348175049,
|
1726 |
+
"learning_rate": 0.00015345016429353778,
|
1727 |
+
"loss": 1.9225,
|
1728 |
+
"step": 2330
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 1.504823151125402,
|
1732 |
+
"grad_norm": 0.7176666259765625,
|
1733 |
+
"learning_rate": 0.00015279299014238771,
|
1734 |
+
"loss": 1.8764,
|
1735 |
+
"step": 2340
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 1.5112540192926045,
|
1739 |
+
"grad_norm": 0.735252857208252,
|
1740 |
+
"learning_rate": 0.00015213581599123765,
|
1741 |
+
"loss": 1.8935,
|
1742 |
+
"step": 2350
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 1.517684887459807,
|
1746 |
+
"grad_norm": 0.6805827021598816,
|
1747 |
+
"learning_rate": 0.00015147864184008762,
|
1748 |
+
"loss": 1.9212,
|
1749 |
+
"step": 2360
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.5241157556270095,
|
1753 |
+
"grad_norm": 0.7019375562667847,
|
1754 |
+
"learning_rate": 0.00015082146768893756,
|
1755 |
+
"loss": 1.9318,
|
1756 |
+
"step": 2370
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.5305466237942122,
|
1760 |
+
"grad_norm": 0.6795372366905212,
|
1761 |
+
"learning_rate": 0.0001501642935377875,
|
1762 |
+
"loss": 1.9023,
|
1763 |
+
"step": 2380
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 1.5369774919614148,
|
1767 |
+
"grad_norm": 0.6497982144355774,
|
1768 |
+
"learning_rate": 0.00014950711938663743,
|
1769 |
+
"loss": 1.9721,
|
1770 |
+
"step": 2390
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 1.5434083601286175,
|
1774 |
+
"grad_norm": 0.7713346481323242,
|
1775 |
+
"learning_rate": 0.0001488499452354874,
|
1776 |
+
"loss": 1.9906,
|
1777 |
+
"step": 2400
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 1.5434083601286175,
|
1781 |
+
"eval_loss": 1.9822700023651123,
|
1782 |
+
"eval_runtime": 130.376,
|
1783 |
+
"eval_samples_per_second": 15.34,
|
1784 |
+
"eval_steps_per_second": 1.918,
|
1785 |
+
"step": 2400
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 1.54983922829582,
|
1789 |
+
"grad_norm": 0.7202898263931274,
|
1790 |
+
"learning_rate": 0.00014819277108433734,
|
1791 |
+
"loss": 1.8816,
|
1792 |
+
"step": 2410
|
1793 |
+
},
|
1794 |
+
{
|
1795 |
+
"epoch": 1.5562700964630225,
|
1796 |
+
"grad_norm": 0.7167313694953918,
|
1797 |
+
"learning_rate": 0.00014753559693318728,
|
1798 |
+
"loss": 1.9316,
|
1799 |
+
"step": 2420
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"epoch": 1.562700964630225,
|
1803 |
+
"grad_norm": 0.7133712768554688,
|
1804 |
+
"learning_rate": 0.00014687842278203724,
|
1805 |
+
"loss": 2.0053,
|
1806 |
+
"step": 2430
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.5691318327974275,
|
1810 |
+
"grad_norm": 0.76304692029953,
|
1811 |
+
"learning_rate": 0.00014622124863088718,
|
1812 |
+
"loss": 1.8718,
|
1813 |
+
"step": 2440
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 1.5755627009646302,
|
1817 |
+
"grad_norm": 0.667654812335968,
|
1818 |
+
"learning_rate": 0.00014556407447973712,
|
1819 |
+
"loss": 1.8727,
|
1820 |
+
"step": 2450
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 1.5819935691318328,
|
1824 |
+
"grad_norm": 0.7308873534202576,
|
1825 |
+
"learning_rate": 0.00014490690032858706,
|
1826 |
+
"loss": 1.8918,
|
1827 |
+
"step": 2460
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.5884244372990355,
|
1831 |
+
"grad_norm": 0.9376251697540283,
|
1832 |
+
"learning_rate": 0.00014424972617743702,
|
1833 |
+
"loss": 1.96,
|
1834 |
+
"step": 2470
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.594855305466238,
|
1838 |
+
"grad_norm": 0.6924982666969299,
|
1839 |
+
"learning_rate": 0.00014359255202628696,
|
1840 |
+
"loss": 1.8744,
|
1841 |
+
"step": 2480
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"epoch": 1.6012861736334405,
|
1845 |
+
"grad_norm": 0.7420899868011475,
|
1846 |
+
"learning_rate": 0.0001429353778751369,
|
1847 |
+
"loss": 1.9112,
|
1848 |
+
"step": 2490
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 1.607717041800643,
|
1852 |
+
"grad_norm": 0.7384818196296692,
|
1853 |
+
"learning_rate": 0.00014227820372398684,
|
1854 |
+
"loss": 1.9562,
|
1855 |
+
"step": 2500
|
1856 |
+
},
|
1857 |
+
{
|
1858 |
+
"epoch": 1.6141479099678455,
|
1859 |
+
"grad_norm": 0.7550799250602722,
|
1860 |
+
"learning_rate": 0.0001416210295728368,
|
1861 |
+
"loss": 1.891,
|
1862 |
+
"step": 2510
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 1.6205787781350482,
|
1866 |
+
"grad_norm": 0.7184371948242188,
|
1867 |
+
"learning_rate": 0.00014096385542168674,
|
1868 |
+
"loss": 1.9361,
|
1869 |
+
"step": 2520
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.6270096463022508,
|
1873 |
+
"grad_norm": 0.770914614200592,
|
1874 |
+
"learning_rate": 0.00014030668127053668,
|
1875 |
+
"loss": 1.9132,
|
1876 |
+
"step": 2530
|
1877 |
+
},
|
1878 |
+
{
|
1879 |
+
"epoch": 1.6334405144694535,
|
1880 |
+
"grad_norm": 0.7566716074943542,
|
1881 |
+
"learning_rate": 0.00013964950711938662,
|
1882 |
+
"loss": 1.8982,
|
1883 |
+
"step": 2540
|
1884 |
+
},
|
1885 |
+
{
|
1886 |
+
"epoch": 1.639871382636656,
|
1887 |
+
"grad_norm": 0.6670147776603699,
|
1888 |
+
"learning_rate": 0.00013899233296823656,
|
1889 |
+
"loss": 1.9211,
|
1890 |
+
"step": 2550
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 1.6463022508038585,
|
1894 |
+
"grad_norm": 0.7093060612678528,
|
1895 |
+
"learning_rate": 0.00013833515881708653,
|
1896 |
+
"loss": 1.8881,
|
1897 |
+
"step": 2560
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 1.652733118971061,
|
1901 |
+
"grad_norm": 0.6549977660179138,
|
1902 |
+
"learning_rate": 0.00013767798466593646,
|
1903 |
+
"loss": 1.9187,
|
1904 |
+
"step": 2570
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 1.6591639871382635,
|
1908 |
+
"grad_norm": 0.7039531469345093,
|
1909 |
+
"learning_rate": 0.0001370208105147864,
|
1910 |
+
"loss": 1.9165,
|
1911 |
+
"step": 2580
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 1.6655948553054662,
|
1915 |
+
"grad_norm": 0.7216307520866394,
|
1916 |
+
"learning_rate": 0.00013636363636363634,
|
1917 |
+
"loss": 1.9228,
|
1918 |
+
"step": 2590
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 1.6720257234726688,
|
1922 |
+
"grad_norm": 0.6866537928581238,
|
1923 |
+
"learning_rate": 0.00013570646221248628,
|
1924 |
+
"loss": 1.9003,
|
1925 |
+
"step": 2600
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 1.6720257234726688,
|
1929 |
+
"eval_loss": 1.977206826210022,
|
1930 |
+
"eval_runtime": 131.9243,
|
1931 |
+
"eval_samples_per_second": 15.16,
|
1932 |
+
"eval_steps_per_second": 1.895,
|
1933 |
+
"step": 2600
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"epoch": 1.6784565916398715,
|
1937 |
+
"grad_norm": 0.7328875660896301,
|
1938 |
+
"learning_rate": 0.00013504928806133625,
|
1939 |
+
"loss": 1.9,
|
1940 |
+
"step": 2610
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 1.684887459807074,
|
1944 |
+
"grad_norm": 0.7623500227928162,
|
1945 |
+
"learning_rate": 0.00013439211391018618,
|
1946 |
+
"loss": 1.9117,
|
1947 |
+
"step": 2620
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 1.6913183279742765,
|
1951 |
+
"grad_norm": 0.6996557712554932,
|
1952 |
+
"learning_rate": 0.00013373493975903612,
|
1953 |
+
"loss": 1.8342,
|
1954 |
+
"step": 2630
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.697749196141479,
|
1958 |
+
"grad_norm": 0.6597011685371399,
|
1959 |
+
"learning_rate": 0.00013307776560788606,
|
1960 |
+
"loss": 1.911,
|
1961 |
+
"step": 2640
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 1.7041800643086815,
|
1965 |
+
"grad_norm": 0.7154627442359924,
|
1966 |
+
"learning_rate": 0.00013242059145673603,
|
1967 |
+
"loss": 1.8955,
|
1968 |
+
"step": 2650
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 1.7106109324758842,
|
1972 |
+
"grad_norm": 0.6822642087936401,
|
1973 |
+
"learning_rate": 0.00013176341730558597,
|
1974 |
+
"loss": 1.928,
|
1975 |
+
"step": 2660
|
1976 |
+
},
|
1977 |
+
{
|
1978 |
+
"epoch": 1.717041800643087,
|
1979 |
+
"grad_norm": 0.6770340204238892,
|
1980 |
+
"learning_rate": 0.0001311062431544359,
|
1981 |
+
"loss": 1.934,
|
1982 |
+
"step": 2670
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 1.7234726688102895,
|
1986 |
+
"grad_norm": 0.7235671877861023,
|
1987 |
+
"learning_rate": 0.00013044906900328584,
|
1988 |
+
"loss": 1.9248,
|
1989 |
+
"step": 2680
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.729903536977492,
|
1993 |
+
"grad_norm": 0.6428620219230652,
|
1994 |
+
"learning_rate": 0.0001297918948521358,
|
1995 |
+
"loss": 1.8998,
|
1996 |
+
"step": 2690
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 1.7363344051446945,
|
2000 |
+
"grad_norm": 0.7132564783096313,
|
2001 |
+
"learning_rate": 0.00012913472070098575,
|
2002 |
+
"loss": 1.9353,
|
2003 |
+
"step": 2700
|
2004 |
+
},
|
2005 |
+
{
|
2006 |
+
"epoch": 1.742765273311897,
|
2007 |
+
"grad_norm": 0.7110019326210022,
|
2008 |
+
"learning_rate": 0.0001284775465498357,
|
2009 |
+
"loss": 1.8877,
|
2010 |
+
"step": 2710
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.7491961414790995,
|
2014 |
+
"grad_norm": 0.7546197772026062,
|
2015 |
+
"learning_rate": 0.00012782037239868565,
|
2016 |
+
"loss": 1.9219,
|
2017 |
+
"step": 2720
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 1.7556270096463023,
|
2021 |
+
"grad_norm": 0.8485615253448486,
|
2022 |
+
"learning_rate": 0.0001271631982475356,
|
2023 |
+
"loss": 1.9238,
|
2024 |
+
"step": 2730
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 1.762057877813505,
|
2028 |
+
"grad_norm": 0.7058401703834534,
|
2029 |
+
"learning_rate": 0.00012650602409638553,
|
2030 |
+
"loss": 1.9012,
|
2031 |
+
"step": 2740
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 1.7684887459807075,
|
2035 |
+
"grad_norm": 0.7222112417221069,
|
2036 |
+
"learning_rate": 0.00012584884994523547,
|
2037 |
+
"loss": 1.8442,
|
2038 |
+
"step": 2750
|
2039 |
+
},
|
2040 |
+
{
|
2041 |
+
"epoch": 1.77491961414791,
|
2042 |
+
"grad_norm": 0.7010639905929565,
|
2043 |
+
"learning_rate": 0.00012519167579408543,
|
2044 |
+
"loss": 1.9322,
|
2045 |
+
"step": 2760
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 1.7813504823151125,
|
2049 |
+
"grad_norm": 0.6908234357833862,
|
2050 |
+
"learning_rate": 0.00012453450164293537,
|
2051 |
+
"loss": 1.9456,
|
2052 |
+
"step": 2770
|
2053 |
+
},
|
2054 |
+
{
|
2055 |
+
"epoch": 1.787781350482315,
|
2056 |
+
"grad_norm": 0.6615903973579407,
|
2057 |
+
"learning_rate": 0.0001238773274917853,
|
2058 |
+
"loss": 1.9052,
|
2059 |
+
"step": 2780
|
2060 |
+
},
|
2061 |
+
{
|
2062 |
+
"epoch": 1.7942122186495175,
|
2063 |
+
"grad_norm": 0.6688089370727539,
|
2064 |
+
"learning_rate": 0.00012322015334063528,
|
2065 |
+
"loss": 1.87,
|
2066 |
+
"step": 2790
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.8006430868167203,
|
2070 |
+
"grad_norm": 0.7396994233131409,
|
2071 |
+
"learning_rate": 0.00012256297918948522,
|
2072 |
+
"loss": 1.9243,
|
2073 |
+
"step": 2800
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 1.8006430868167203,
|
2077 |
+
"eval_loss": 1.974278450012207,
|
2078 |
+
"eval_runtime": 144.2243,
|
2079 |
+
"eval_samples_per_second": 13.867,
|
2080 |
+
"eval_steps_per_second": 1.733,
|
2081 |
+
"step": 2800
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 1.807073954983923,
|
2085 |
+
"grad_norm": 0.6520466208457947,
|
2086 |
+
"learning_rate": 0.00012190580503833514,
|
2087 |
+
"loss": 1.902,
|
2088 |
+
"step": 2810
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 1.8135048231511255,
|
2092 |
+
"grad_norm": 0.7591603398323059,
|
2093 |
+
"learning_rate": 0.00012124863088718509,
|
2094 |
+
"loss": 1.9079,
|
2095 |
+
"step": 2820
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 1.819935691318328,
|
2099 |
+
"grad_norm": 0.6622514128684998,
|
2100 |
+
"learning_rate": 0.00012059145673603504,
|
2101 |
+
"loss": 1.9288,
|
2102 |
+
"step": 2830
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.8263665594855305,
|
2106 |
+
"grad_norm": 0.7578607797622681,
|
2107 |
+
"learning_rate": 0.00011993428258488498,
|
2108 |
+
"loss": 1.8936,
|
2109 |
+
"step": 2840
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.832797427652733,
|
2113 |
+
"grad_norm": 0.730093240737915,
|
2114 |
+
"learning_rate": 0.00011927710843373494,
|
2115 |
+
"loss": 1.8809,
|
2116 |
+
"step": 2850
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.8392282958199357,
|
2120 |
+
"grad_norm": 0.6403250098228455,
|
2121 |
+
"learning_rate": 0.00011861993428258487,
|
2122 |
+
"loss": 1.8866,
|
2123 |
+
"step": 2860
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 1.8456591639871383,
|
2127 |
+
"grad_norm": 0.7032350897789001,
|
2128 |
+
"learning_rate": 0.00011796276013143481,
|
2129 |
+
"loss": 1.938,
|
2130 |
+
"step": 2870
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 1.852090032154341,
|
2134 |
+
"grad_norm": 0.7376342415809631,
|
2135 |
+
"learning_rate": 0.00011730558598028478,
|
2136 |
+
"loss": 1.8925,
|
2137 |
+
"step": 2880
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 1.8585209003215435,
|
2141 |
+
"grad_norm": 0.7093110680580139,
|
2142 |
+
"learning_rate": 0.00011664841182913472,
|
2143 |
+
"loss": 1.9029,
|
2144 |
+
"step": 2890
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 1.864951768488746,
|
2148 |
+
"grad_norm": 0.6826250553131104,
|
2149 |
+
"learning_rate": 0.00011599123767798466,
|
2150 |
+
"loss": 1.8956,
|
2151 |
+
"step": 2900
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.8713826366559485,
|
2155 |
+
"grad_norm": 0.7709969282150269,
|
2156 |
+
"learning_rate": 0.0001153340635268346,
|
2157 |
+
"loss": 1.92,
|
2158 |
+
"step": 2910
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.877813504823151,
|
2162 |
+
"grad_norm": 0.6641222238540649,
|
2163 |
+
"learning_rate": 0.00011467688937568453,
|
2164 |
+
"loss": 1.8998,
|
2165 |
+
"step": 2920
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 1.8842443729903537,
|
2169 |
+
"grad_norm": 0.7321887612342834,
|
2170 |
+
"learning_rate": 0.0001140197152245345,
|
2171 |
+
"loss": 1.9257,
|
2172 |
+
"step": 2930
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 1.8906752411575563,
|
2176 |
+
"grad_norm": 0.7000001668930054,
|
2177 |
+
"learning_rate": 0.00011336254107338444,
|
2178 |
+
"loss": 1.8944,
|
2179 |
+
"step": 2940
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 1.897106109324759,
|
2183 |
+
"grad_norm": 0.7347818613052368,
|
2184 |
+
"learning_rate": 0.00011270536692223438,
|
2185 |
+
"loss": 1.9256,
|
2186 |
+
"step": 2950
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 1.9035369774919615,
|
2190 |
+
"grad_norm": 0.708888590335846,
|
2191 |
+
"learning_rate": 0.00011204819277108433,
|
2192 |
+
"loss": 1.9307,
|
2193 |
+
"step": 2960
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 1.909967845659164,
|
2197 |
+
"grad_norm": 0.6980915665626526,
|
2198 |
+
"learning_rate": 0.00011139101861993428,
|
2199 |
+
"loss": 1.883,
|
2200 |
+
"step": 2970
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 1.9163987138263665,
|
2204 |
+
"grad_norm": 0.8052535653114319,
|
2205 |
+
"learning_rate": 0.00011073384446878422,
|
2206 |
+
"loss": 1.899,
|
2207 |
+
"step": 2980
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 1.922829581993569,
|
2211 |
+
"grad_norm": 0.707011878490448,
|
2212 |
+
"learning_rate": 0.00011007667031763416,
|
2213 |
+
"loss": 1.9263,
|
2214 |
+
"step": 2990
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.9292604501607717,
|
2218 |
+
"grad_norm": 0.7086938619613647,
|
2219 |
+
"learning_rate": 0.00010941949616648411,
|
2220 |
+
"loss": 1.883,
|
2221 |
+
"step": 3000
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 1.9292604501607717,
|
2225 |
+
"eval_loss": 1.9664931297302246,
|
2226 |
+
"eval_runtime": 133.023,
|
2227 |
+
"eval_samples_per_second": 15.035,
|
2228 |
+
"eval_steps_per_second": 1.879,
|
2229 |
+
"step": 3000
|
2230 |
+
}
|
2231 |
+
],
|
2232 |
+
"logging_steps": 10,
|
2233 |
+
"max_steps": 4665,
|
2234 |
+
"num_input_tokens_seen": 0,
|
2235 |
+
"num_train_epochs": 3,
|
2236 |
+
"save_steps": 200,
|
2237 |
+
"stateful_callbacks": {
|
2238 |
+
"TrainerControl": {
|
2239 |
+
"args": {
|
2240 |
+
"should_epoch_stop": false,
|
2241 |
+
"should_evaluate": false,
|
2242 |
+
"should_log": false,
|
2243 |
+
"should_save": true,
|
2244 |
+
"should_training_stop": false
|
2245 |
+
},
|
2246 |
+
"attributes": {}
|
2247 |
+
}
|
2248 |
+
},
|
2249 |
+
"total_flos": 3.0137669676957696e+17,
|
2250 |
+
"train_batch_size": 16,
|
2251 |
+
"trial_name": null,
|
2252 |
+
"trial_params": null
|
2253 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cab22ba79cda15f54ce907097c40aecb6ebd4c038c6657764e0d5bf9d78a133c
|
3 |
+
size 5048
|