Upload 8 files
Browse files- README.md +202 -3
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2556 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: HuggingFaceM4/idefics-9b
|
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 0.11.2.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "IdeficsForVisionText2Text",
|
5 |
+
"parent_library": "transformers.models.idefics.modeling_idefics"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "HuggingFaceM4/idefics-9b",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"k_proj",
|
28 |
+
"v_proj"
|
29 |
+
],
|
30 |
+
"task_type": null,
|
31 |
+
"use_dora": false,
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4adcdc1b27b26cc3b459237576a7c22af1a443ff6bf899f35702607e6ac96293
|
3 |
+
size 79071880
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77914a0be88e2bc63fb0df31962747962ac11f2fb3851b9ba4107e90e4d008dd
|
3 |
+
size 40107172
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5ada7e807b31cd7e67d730970b5eb49bbbb651c6fb8e146625ae362468f01e0
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e4ab83e042e3deace3597b3caea23cdb552ba15ddeffd03637d82e011425dbf
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,2556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9997069597069597,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1706,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005860805860805861,
|
13 |
+
"grad_norm": 2.521568536758423,
|
14 |
+
"learning_rate": 0.00019941383352872216,
|
15 |
+
"loss": 2.3132,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.011721611721611722,
|
20 |
+
"grad_norm": 2.104935884475708,
|
21 |
+
"learning_rate": 0.00019882766705744433,
|
22 |
+
"loss": 0.9444,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.017582417582417582,
|
27 |
+
"grad_norm": 1.2950881719589233,
|
28 |
+
"learning_rate": 0.00019824150058616647,
|
29 |
+
"loss": 0.357,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.023443223443223443,
|
34 |
+
"grad_norm": 1.1862170696258545,
|
35 |
+
"learning_rate": 0.00019765533411488865,
|
36 |
+
"loss": 0.2105,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.029304029304029304,
|
41 |
+
"grad_norm": 0.5247148871421814,
|
42 |
+
"learning_rate": 0.0001970691676436108,
|
43 |
+
"loss": 0.1087,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.035164835164835165,
|
48 |
+
"grad_norm": 1.2535285949707031,
|
49 |
+
"learning_rate": 0.00019648300117233296,
|
50 |
+
"loss": 0.1185,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.041025641025641026,
|
55 |
+
"grad_norm": 0.5407606959342957,
|
56 |
+
"learning_rate": 0.0001958968347010551,
|
57 |
+
"loss": 0.0775,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.046886446886446886,
|
62 |
+
"grad_norm": 1.137266993522644,
|
63 |
+
"learning_rate": 0.00019531066822977726,
|
64 |
+
"loss": 0.0728,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05274725274725275,
|
69 |
+
"grad_norm": 0.5244052410125732,
|
70 |
+
"learning_rate": 0.00019472450175849943,
|
71 |
+
"loss": 0.056,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.05860805860805861,
|
76 |
+
"grad_norm": 0.4511496126651764,
|
77 |
+
"learning_rate": 0.00019413833528722157,
|
78 |
+
"loss": 0.0648,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.06446886446886448,
|
83 |
+
"grad_norm": 0.33913975954055786,
|
84 |
+
"learning_rate": 0.00019355216881594375,
|
85 |
+
"loss": 0.0479,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.07032967032967033,
|
90 |
+
"grad_norm": 0.354777991771698,
|
91 |
+
"learning_rate": 0.0001929660023446659,
|
92 |
+
"loss": 0.0758,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0761904761904762,
|
97 |
+
"grad_norm": 0.3968910276889801,
|
98 |
+
"learning_rate": 0.00019237983587338807,
|
99 |
+
"loss": 0.0776,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.08205128205128205,
|
104 |
+
"grad_norm": 0.5061652660369873,
|
105 |
+
"learning_rate": 0.0001917936694021102,
|
106 |
+
"loss": 0.0349,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.08791208791208792,
|
111 |
+
"grad_norm": 0.24455250799655914,
|
112 |
+
"learning_rate": 0.00019120750293083236,
|
113 |
+
"loss": 0.0369,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.09377289377289377,
|
118 |
+
"grad_norm": 0.3959537446498871,
|
119 |
+
"learning_rate": 0.00019062133645955453,
|
120 |
+
"loss": 0.0513,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.09963369963369964,
|
125 |
+
"grad_norm": 0.4534469544887543,
|
126 |
+
"learning_rate": 0.00019003516998827668,
|
127 |
+
"loss": 0.0459,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.1054945054945055,
|
132 |
+
"grad_norm": 0.30694451928138733,
|
133 |
+
"learning_rate": 0.00018944900351699885,
|
134 |
+
"loss": 0.0377,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.11135531135531136,
|
139 |
+
"grad_norm": 0.15078052878379822,
|
140 |
+
"learning_rate": 0.000188862837045721,
|
141 |
+
"loss": 0.0297,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.11721611721611722,
|
146 |
+
"grad_norm": 0.3153330981731415,
|
147 |
+
"learning_rate": 0.00018827667057444317,
|
148 |
+
"loss": 0.0301,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.11721611721611722,
|
153 |
+
"eval_loss": 0.028654273599386215,
|
154 |
+
"eval_runtime": 4.8016,
|
155 |
+
"eval_samples_per_second": 5.831,
|
156 |
+
"eval_steps_per_second": 2.916,
|
157 |
+
"step": 100
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.12307692307692308,
|
161 |
+
"grad_norm": 0.5777396559715271,
|
162 |
+
"learning_rate": 0.0001876905041031653,
|
163 |
+
"loss": 0.0515,
|
164 |
+
"step": 105
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.12893772893772895,
|
168 |
+
"grad_norm": 0.3677718937397003,
|
169 |
+
"learning_rate": 0.00018710433763188746,
|
170 |
+
"loss": 0.0315,
|
171 |
+
"step": 110
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.1347985347985348,
|
175 |
+
"grad_norm": 0.30658507347106934,
|
176 |
+
"learning_rate": 0.0001865181711606096,
|
177 |
+
"loss": 0.0248,
|
178 |
+
"step": 115
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.14065934065934066,
|
182 |
+
"grad_norm": 0.21649648249149323,
|
183 |
+
"learning_rate": 0.00018593200468933178,
|
184 |
+
"loss": 0.0352,
|
185 |
+
"step": 120
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.14652014652014653,
|
189 |
+
"grad_norm": 0.2877885103225708,
|
190 |
+
"learning_rate": 0.00018534583821805395,
|
191 |
+
"loss": 0.0456,
|
192 |
+
"step": 125
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.1523809523809524,
|
196 |
+
"grad_norm": 0.1782904863357544,
|
197 |
+
"learning_rate": 0.0001847596717467761,
|
198 |
+
"loss": 0.0257,
|
199 |
+
"step": 130
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.15824175824175823,
|
203 |
+
"grad_norm": 0.1211300641298294,
|
204 |
+
"learning_rate": 0.00018417350527549827,
|
205 |
+
"loss": 0.0437,
|
206 |
+
"step": 135
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.1641025641025641,
|
210 |
+
"grad_norm": 0.298053503036499,
|
211 |
+
"learning_rate": 0.0001835873388042204,
|
212 |
+
"loss": 0.036,
|
213 |
+
"step": 140
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.16996336996336997,
|
217 |
+
"grad_norm": 0.2280658483505249,
|
218 |
+
"learning_rate": 0.00018300117233294256,
|
219 |
+
"loss": 0.0331,
|
220 |
+
"step": 145
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.17582417582417584,
|
224 |
+
"grad_norm": 0.14896267652511597,
|
225 |
+
"learning_rate": 0.0001824150058616647,
|
226 |
+
"loss": 0.0239,
|
227 |
+
"step": 150
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.18168498168498168,
|
231 |
+
"grad_norm": 0.1769961267709732,
|
232 |
+
"learning_rate": 0.00018182883939038688,
|
233 |
+
"loss": 0.0375,
|
234 |
+
"step": 155
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.18754578754578755,
|
238 |
+
"grad_norm": 0.19849297404289246,
|
239 |
+
"learning_rate": 0.00018124267291910902,
|
240 |
+
"loss": 0.0357,
|
241 |
+
"step": 160
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1934065934065934,
|
245 |
+
"grad_norm": 0.2294420450925827,
|
246 |
+
"learning_rate": 0.0001806565064478312,
|
247 |
+
"loss": 0.0504,
|
248 |
+
"step": 165
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.19926739926739928,
|
252 |
+
"grad_norm": 0.10744224488735199,
|
253 |
+
"learning_rate": 0.00018007033997655337,
|
254 |
+
"loss": 0.0209,
|
255 |
+
"step": 170
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.20512820512820512,
|
259 |
+
"grad_norm": 0.06066066771745682,
|
260 |
+
"learning_rate": 0.00017948417350527551,
|
261 |
+
"loss": 0.0175,
|
262 |
+
"step": 175
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.210989010989011,
|
266 |
+
"grad_norm": 0.5421485304832458,
|
267 |
+
"learning_rate": 0.00017889800703399766,
|
268 |
+
"loss": 0.0398,
|
269 |
+
"step": 180
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.21684981684981686,
|
273 |
+
"grad_norm": 0.1306767612695694,
|
274 |
+
"learning_rate": 0.0001783118405627198,
|
275 |
+
"loss": 0.0258,
|
276 |
+
"step": 185
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.22271062271062272,
|
280 |
+
"grad_norm": 0.11510124802589417,
|
281 |
+
"learning_rate": 0.00017772567409144198,
|
282 |
+
"loss": 0.0253,
|
283 |
+
"step": 190
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.22857142857142856,
|
287 |
+
"grad_norm": 0.20577751100063324,
|
288 |
+
"learning_rate": 0.00017713950762016412,
|
289 |
+
"loss": 0.0277,
|
290 |
+
"step": 195
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.23443223443223443,
|
294 |
+
"grad_norm": 0.20588932931423187,
|
295 |
+
"learning_rate": 0.0001765533411488863,
|
296 |
+
"loss": 0.0296,
|
297 |
+
"step": 200
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.23443223443223443,
|
301 |
+
"eval_loss": 0.019306689500808716,
|
302 |
+
"eval_runtime": 4.7344,
|
303 |
+
"eval_samples_per_second": 5.914,
|
304 |
+
"eval_steps_per_second": 2.957,
|
305 |
+
"step": 200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.2402930402930403,
|
309 |
+
"grad_norm": 0.13713975250720978,
|
310 |
+
"learning_rate": 0.00017596717467760847,
|
311 |
+
"loss": 0.0372,
|
312 |
+
"step": 205
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.24615384615384617,
|
316 |
+
"grad_norm": 0.14788508415222168,
|
317 |
+
"learning_rate": 0.00017538100820633061,
|
318 |
+
"loss": 0.033,
|
319 |
+
"step": 210
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.252014652014652,
|
323 |
+
"grad_norm": 0.2372630536556244,
|
324 |
+
"learning_rate": 0.00017479484173505276,
|
325 |
+
"loss": 0.0281,
|
326 |
+
"step": 215
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.2578754578754579,
|
330 |
+
"grad_norm": 0.2357954978942871,
|
331 |
+
"learning_rate": 0.0001742086752637749,
|
332 |
+
"loss": 0.0295,
|
333 |
+
"step": 220
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.26373626373626374,
|
337 |
+
"grad_norm": 0.2537606358528137,
|
338 |
+
"learning_rate": 0.00017362250879249708,
|
339 |
+
"loss": 0.036,
|
340 |
+
"step": 225
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.2695970695970696,
|
344 |
+
"grad_norm": 0.2222289741039276,
|
345 |
+
"learning_rate": 0.00017303634232121922,
|
346 |
+
"loss": 0.0402,
|
347 |
+
"step": 230
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.2754578754578755,
|
351 |
+
"grad_norm": 0.19696177542209625,
|
352 |
+
"learning_rate": 0.0001724501758499414,
|
353 |
+
"loss": 0.025,
|
354 |
+
"step": 235
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.2813186813186813,
|
358 |
+
"grad_norm": 0.08915109932422638,
|
359 |
+
"learning_rate": 0.00017186400937866357,
|
360 |
+
"loss": 0.0292,
|
361 |
+
"step": 240
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.28717948717948716,
|
365 |
+
"grad_norm": 0.39625948667526245,
|
366 |
+
"learning_rate": 0.00017127784290738572,
|
367 |
+
"loss": 0.0324,
|
368 |
+
"step": 245
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.29304029304029305,
|
372 |
+
"grad_norm": 0.05654177442193031,
|
373 |
+
"learning_rate": 0.00017069167643610786,
|
374 |
+
"loss": 0.0384,
|
375 |
+
"step": 250
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.2989010989010989,
|
379 |
+
"grad_norm": 0.23707075417041779,
|
380 |
+
"learning_rate": 0.00017010550996483,
|
381 |
+
"loss": 0.0311,
|
382 |
+
"step": 255
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.3047619047619048,
|
386 |
+
"grad_norm": 0.2619571387767792,
|
387 |
+
"learning_rate": 0.00016951934349355218,
|
388 |
+
"loss": 0.0275,
|
389 |
+
"step": 260
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.31062271062271063,
|
393 |
+
"grad_norm": 0.11028550565242767,
|
394 |
+
"learning_rate": 0.00016893317702227432,
|
395 |
+
"loss": 0.0194,
|
396 |
+
"step": 265
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.31648351648351647,
|
400 |
+
"grad_norm": 0.26710912585258484,
|
401 |
+
"learning_rate": 0.0001683470105509965,
|
402 |
+
"loss": 0.0318,
|
403 |
+
"step": 270
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.32234432234432236,
|
407 |
+
"grad_norm": 0.20064710080623627,
|
408 |
+
"learning_rate": 0.00016776084407971864,
|
409 |
+
"loss": 0.0517,
|
410 |
+
"step": 275
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.3282051282051282,
|
414 |
+
"grad_norm": 0.06760745495557785,
|
415 |
+
"learning_rate": 0.00016717467760844082,
|
416 |
+
"loss": 0.0223,
|
417 |
+
"step": 280
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.33406593406593404,
|
421 |
+
"grad_norm": 0.14518442749977112,
|
422 |
+
"learning_rate": 0.00016658851113716296,
|
423 |
+
"loss": 0.0216,
|
424 |
+
"step": 285
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.33992673992673994,
|
428 |
+
"grad_norm": 0.35427016019821167,
|
429 |
+
"learning_rate": 0.0001660023446658851,
|
430 |
+
"loss": 0.0268,
|
431 |
+
"step": 290
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.3457875457875458,
|
435 |
+
"grad_norm": 0.14693213999271393,
|
436 |
+
"learning_rate": 0.00016541617819460728,
|
437 |
+
"loss": 0.0246,
|
438 |
+
"step": 295
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.3516483516483517,
|
442 |
+
"grad_norm": 0.2351713478565216,
|
443 |
+
"learning_rate": 0.00016483001172332943,
|
444 |
+
"loss": 0.0399,
|
445 |
+
"step": 300
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.3516483516483517,
|
449 |
+
"eval_loss": 0.02264154888689518,
|
450 |
+
"eval_runtime": 4.8013,
|
451 |
+
"eval_samples_per_second": 5.832,
|
452 |
+
"eval_steps_per_second": 2.916,
|
453 |
+
"step": 300
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.3575091575091575,
|
457 |
+
"grad_norm": 0.16985514760017395,
|
458 |
+
"learning_rate": 0.0001642438452520516,
|
459 |
+
"loss": 0.0243,
|
460 |
+
"step": 305
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.36336996336996336,
|
464 |
+
"grad_norm": 0.199642613530159,
|
465 |
+
"learning_rate": 0.00016365767878077374,
|
466 |
+
"loss": 0.0329,
|
467 |
+
"step": 310
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.36923076923076925,
|
471 |
+
"grad_norm": 0.05538804084062576,
|
472 |
+
"learning_rate": 0.00016307151230949592,
|
473 |
+
"loss": 0.0474,
|
474 |
+
"step": 315
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.3750915750915751,
|
478 |
+
"grad_norm": 0.1542443037033081,
|
479 |
+
"learning_rate": 0.00016248534583821806,
|
480 |
+
"loss": 0.0232,
|
481 |
+
"step": 320
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.38095238095238093,
|
485 |
+
"grad_norm": 0.16808335483074188,
|
486 |
+
"learning_rate": 0.0001618991793669402,
|
487 |
+
"loss": 0.0272,
|
488 |
+
"step": 325
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.3868131868131868,
|
492 |
+
"grad_norm": 0.20816853642463684,
|
493 |
+
"learning_rate": 0.00016131301289566238,
|
494 |
+
"loss": 0.0375,
|
495 |
+
"step": 330
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.39267399267399267,
|
499 |
+
"grad_norm": 0.10338038206100464,
|
500 |
+
"learning_rate": 0.00016072684642438453,
|
501 |
+
"loss": 0.0233,
|
502 |
+
"step": 335
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.39853479853479856,
|
506 |
+
"grad_norm": 0.06522126495838165,
|
507 |
+
"learning_rate": 0.0001601406799531067,
|
508 |
+
"loss": 0.0288,
|
509 |
+
"step": 340
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.4043956043956044,
|
513 |
+
"grad_norm": 0.11830403655767441,
|
514 |
+
"learning_rate": 0.00015955451348182884,
|
515 |
+
"loss": 0.0164,
|
516 |
+
"step": 345
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.41025641025641024,
|
520 |
+
"grad_norm": 0.2777006924152374,
|
521 |
+
"learning_rate": 0.00015896834701055102,
|
522 |
+
"loss": 0.0345,
|
523 |
+
"step": 350
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.41611721611721614,
|
527 |
+
"grad_norm": 0.1277918815612793,
|
528 |
+
"learning_rate": 0.00015838218053927316,
|
529 |
+
"loss": 0.0229,
|
530 |
+
"step": 355
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.421978021978022,
|
534 |
+
"grad_norm": 0.09861145913600922,
|
535 |
+
"learning_rate": 0.0001577960140679953,
|
536 |
+
"loss": 0.0181,
|
537 |
+
"step": 360
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.4278388278388278,
|
541 |
+
"grad_norm": 0.08698171377182007,
|
542 |
+
"learning_rate": 0.00015720984759671748,
|
543 |
+
"loss": 0.0365,
|
544 |
+
"step": 365
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.4336996336996337,
|
548 |
+
"grad_norm": 0.23488883674144745,
|
549 |
+
"learning_rate": 0.00015662368112543963,
|
550 |
+
"loss": 0.0352,
|
551 |
+
"step": 370
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.43956043956043955,
|
555 |
+
"grad_norm": 0.05140375718474388,
|
556 |
+
"learning_rate": 0.0001560375146541618,
|
557 |
+
"loss": 0.0235,
|
558 |
+
"step": 375
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.44542124542124545,
|
562 |
+
"grad_norm": 0.15759135782718658,
|
563 |
+
"learning_rate": 0.00015545134818288395,
|
564 |
+
"loss": 0.0236,
|
565 |
+
"step": 380
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.4512820512820513,
|
569 |
+
"grad_norm": 0.07523085922002792,
|
570 |
+
"learning_rate": 0.00015486518171160612,
|
571 |
+
"loss": 0.0218,
|
572 |
+
"step": 385
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.45714285714285713,
|
576 |
+
"grad_norm": 0.1892630159854889,
|
577 |
+
"learning_rate": 0.00015427901524032826,
|
578 |
+
"loss": 0.0264,
|
579 |
+
"step": 390
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.463003663003663,
|
583 |
+
"grad_norm": 0.12749487161636353,
|
584 |
+
"learning_rate": 0.0001536928487690504,
|
585 |
+
"loss": 0.0414,
|
586 |
+
"step": 395
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.46886446886446886,
|
590 |
+
"grad_norm": 0.11519593745470047,
|
591 |
+
"learning_rate": 0.00015310668229777258,
|
592 |
+
"loss": 0.0173,
|
593 |
+
"step": 400
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.46886446886446886,
|
597 |
+
"eval_loss": 0.01765686459839344,
|
598 |
+
"eval_runtime": 4.8182,
|
599 |
+
"eval_samples_per_second": 5.811,
|
600 |
+
"eval_steps_per_second": 2.906,
|
601 |
+
"step": 400
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.4747252747252747,
|
605 |
+
"grad_norm": 0.14240577816963196,
|
606 |
+
"learning_rate": 0.00015252051582649473,
|
607 |
+
"loss": 0.0214,
|
608 |
+
"step": 405
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.4805860805860806,
|
612 |
+
"grad_norm": 0.11283282935619354,
|
613 |
+
"learning_rate": 0.0001519343493552169,
|
614 |
+
"loss": 0.0266,
|
615 |
+
"step": 410
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.48644688644688644,
|
619 |
+
"grad_norm": 0.16279707849025726,
|
620 |
+
"learning_rate": 0.00015134818288393905,
|
621 |
+
"loss": 0.0274,
|
622 |
+
"step": 415
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.49230769230769234,
|
626 |
+
"grad_norm": 0.07319923490285873,
|
627 |
+
"learning_rate": 0.00015076201641266122,
|
628 |
+
"loss": 0.0216,
|
629 |
+
"step": 420
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.4981684981684982,
|
633 |
+
"grad_norm": 0.13532328605651855,
|
634 |
+
"learning_rate": 0.00015017584994138336,
|
635 |
+
"loss": 0.0308,
|
636 |
+
"step": 425
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.504029304029304,
|
640 |
+
"grad_norm": 0.12896127998828888,
|
641 |
+
"learning_rate": 0.0001495896834701055,
|
642 |
+
"loss": 0.0129,
|
643 |
+
"step": 430
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.5098901098901099,
|
647 |
+
"grad_norm": 0.03718201071023941,
|
648 |
+
"learning_rate": 0.00014900351699882766,
|
649 |
+
"loss": 0.0181,
|
650 |
+
"step": 435
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.5157509157509158,
|
654 |
+
"grad_norm": 0.05926808714866638,
|
655 |
+
"learning_rate": 0.00014841735052754983,
|
656 |
+
"loss": 0.0146,
|
657 |
+
"step": 440
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.5216117216117216,
|
661 |
+
"grad_norm": 0.09976931661367416,
|
662 |
+
"learning_rate": 0.00014783118405627197,
|
663 |
+
"loss": 0.0231,
|
664 |
+
"step": 445
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.5274725274725275,
|
668 |
+
"grad_norm": 0.18460391461849213,
|
669 |
+
"learning_rate": 0.00014724501758499415,
|
670 |
+
"loss": 0.02,
|
671 |
+
"step": 450
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.5333333333333333,
|
675 |
+
"grad_norm": 0.07457377016544342,
|
676 |
+
"learning_rate": 0.00014665885111371632,
|
677 |
+
"loss": 0.0209,
|
678 |
+
"step": 455
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.5391941391941392,
|
682 |
+
"grad_norm": 0.03992030769586563,
|
683 |
+
"learning_rate": 0.00014607268464243847,
|
684 |
+
"loss": 0.0251,
|
685 |
+
"step": 460
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.545054945054945,
|
689 |
+
"grad_norm": 0.196414053440094,
|
690 |
+
"learning_rate": 0.0001454865181711606,
|
691 |
+
"loss": 0.0344,
|
692 |
+
"step": 465
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.550915750915751,
|
696 |
+
"grad_norm": 0.19978556036949158,
|
697 |
+
"learning_rate": 0.00014490035169988276,
|
698 |
+
"loss": 0.0159,
|
699 |
+
"step": 470
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.5567765567765568,
|
703 |
+
"grad_norm": 0.11389517784118652,
|
704 |
+
"learning_rate": 0.00014431418522860493,
|
705 |
+
"loss": 0.0197,
|
706 |
+
"step": 475
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.5626373626373626,
|
710 |
+
"grad_norm": 0.07047716528177261,
|
711 |
+
"learning_rate": 0.00014372801875732708,
|
712 |
+
"loss": 0.0138,
|
713 |
+
"step": 480
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.5684981684981685,
|
717 |
+
"grad_norm": 0.10614708811044693,
|
718 |
+
"learning_rate": 0.00014314185228604925,
|
719 |
+
"loss": 0.0208,
|
720 |
+
"step": 485
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.5743589743589743,
|
724 |
+
"grad_norm": 0.20569799840450287,
|
725 |
+
"learning_rate": 0.00014255568581477142,
|
726 |
+
"loss": 0.0203,
|
727 |
+
"step": 490
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.5802197802197803,
|
731 |
+
"grad_norm": 0.19309553503990173,
|
732 |
+
"learning_rate": 0.00014196951934349357,
|
733 |
+
"loss": 0.0282,
|
734 |
+
"step": 495
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.5860805860805861,
|
738 |
+
"grad_norm": 0.07542768865823746,
|
739 |
+
"learning_rate": 0.0001413833528722157,
|
740 |
+
"loss": 0.0173,
|
741 |
+
"step": 500
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.5860805860805861,
|
745 |
+
"eval_loss": 0.022126102820038795,
|
746 |
+
"eval_runtime": 4.8755,
|
747 |
+
"eval_samples_per_second": 5.743,
|
748 |
+
"eval_steps_per_second": 2.872,
|
749 |
+
"step": 500
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 0.591941391941392,
|
753 |
+
"grad_norm": 0.1205630674958229,
|
754 |
+
"learning_rate": 0.00014079718640093786,
|
755 |
+
"loss": 0.0322,
|
756 |
+
"step": 505
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.5978021978021978,
|
760 |
+
"grad_norm": 0.13761042058467865,
|
761 |
+
"learning_rate": 0.00014021101992966003,
|
762 |
+
"loss": 0.0203,
|
763 |
+
"step": 510
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.6036630036630036,
|
767 |
+
"grad_norm": 0.08595598489046097,
|
768 |
+
"learning_rate": 0.00013962485345838218,
|
769 |
+
"loss": 0.0145,
|
770 |
+
"step": 515
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.6095238095238096,
|
774 |
+
"grad_norm": 0.11087319999933243,
|
775 |
+
"learning_rate": 0.00013903868698710435,
|
776 |
+
"loss": 0.0218,
|
777 |
+
"step": 520
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.6153846153846154,
|
781 |
+
"grad_norm": 0.14962054789066315,
|
782 |
+
"learning_rate": 0.00013845252051582652,
|
783 |
+
"loss": 0.0322,
|
784 |
+
"step": 525
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 0.6212454212454213,
|
788 |
+
"grad_norm": 0.07573894411325455,
|
789 |
+
"learning_rate": 0.00013786635404454867,
|
790 |
+
"loss": 0.0275,
|
791 |
+
"step": 530
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 0.6271062271062271,
|
795 |
+
"grad_norm": 0.069780133664608,
|
796 |
+
"learning_rate": 0.0001372801875732708,
|
797 |
+
"loss": 0.0235,
|
798 |
+
"step": 535
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.6329670329670329,
|
802 |
+
"grad_norm": 0.07833613455295563,
|
803 |
+
"learning_rate": 0.00013669402110199296,
|
804 |
+
"loss": 0.0344,
|
805 |
+
"step": 540
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.6388278388278388,
|
809 |
+
"grad_norm": 0.07331829518079758,
|
810 |
+
"learning_rate": 0.00013610785463071513,
|
811 |
+
"loss": 0.0135,
|
812 |
+
"step": 545
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.6446886446886447,
|
816 |
+
"grad_norm": 0.22369089722633362,
|
817 |
+
"learning_rate": 0.00013552168815943728,
|
818 |
+
"loss": 0.0222,
|
819 |
+
"step": 550
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.6505494505494506,
|
823 |
+
"grad_norm": 0.1465146392583847,
|
824 |
+
"learning_rate": 0.00013493552168815945,
|
825 |
+
"loss": 0.0307,
|
826 |
+
"step": 555
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.6564102564102564,
|
830 |
+
"grad_norm": 0.06348715722560883,
|
831 |
+
"learning_rate": 0.00013434935521688162,
|
832 |
+
"loss": 0.0358,
|
833 |
+
"step": 560
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 0.6622710622710622,
|
837 |
+
"grad_norm": 0.09298256784677505,
|
838 |
+
"learning_rate": 0.00013376318874560377,
|
839 |
+
"loss": 0.0224,
|
840 |
+
"step": 565
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.6681318681318681,
|
844 |
+
"grad_norm": 0.18280836939811707,
|
845 |
+
"learning_rate": 0.00013317702227432591,
|
846 |
+
"loss": 0.0263,
|
847 |
+
"step": 570
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.673992673992674,
|
851 |
+
"grad_norm": 0.07080171257257462,
|
852 |
+
"learning_rate": 0.00013259085580304806,
|
853 |
+
"loss": 0.0192,
|
854 |
+
"step": 575
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.6798534798534799,
|
858 |
+
"grad_norm": 0.11019092798233032,
|
859 |
+
"learning_rate": 0.00013200468933177023,
|
860 |
+
"loss": 0.0211,
|
861 |
+
"step": 580
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.6857142857142857,
|
865 |
+
"grad_norm": 0.13162659108638763,
|
866 |
+
"learning_rate": 0.00013141852286049238,
|
867 |
+
"loss": 0.0284,
|
868 |
+
"step": 585
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 0.6915750915750916,
|
872 |
+
"grad_norm": 0.19205588102340698,
|
873 |
+
"learning_rate": 0.00013083235638921455,
|
874 |
+
"loss": 0.0245,
|
875 |
+
"step": 590
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 0.6974358974358974,
|
879 |
+
"grad_norm": 0.0971173569560051,
|
880 |
+
"learning_rate": 0.0001302461899179367,
|
881 |
+
"loss": 0.0216,
|
882 |
+
"step": 595
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.7032967032967034,
|
886 |
+
"grad_norm": 0.2179749310016632,
|
887 |
+
"learning_rate": 0.00012966002344665887,
|
888 |
+
"loss": 0.0268,
|
889 |
+
"step": 600
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.7032967032967034,
|
893 |
+
"eval_loss": 0.01850169710814953,
|
894 |
+
"eval_runtime": 4.6688,
|
895 |
+
"eval_samples_per_second": 5.997,
|
896 |
+
"eval_steps_per_second": 2.999,
|
897 |
+
"step": 600
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.7091575091575092,
|
901 |
+
"grad_norm": 0.23079490661621094,
|
902 |
+
"learning_rate": 0.00012907385697538101,
|
903 |
+
"loss": 0.0269,
|
904 |
+
"step": 605
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.715018315018315,
|
908 |
+
"grad_norm": 0.08325810730457306,
|
909 |
+
"learning_rate": 0.00012848769050410316,
|
910 |
+
"loss": 0.0211,
|
911 |
+
"step": 610
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.7208791208791209,
|
915 |
+
"grad_norm": 0.05983910337090492,
|
916 |
+
"learning_rate": 0.00012790152403282533,
|
917 |
+
"loss": 0.0217,
|
918 |
+
"step": 615
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 0.7267399267399267,
|
922 |
+
"grad_norm": 0.13831888139247894,
|
923 |
+
"learning_rate": 0.00012731535756154748,
|
924 |
+
"loss": 0.0142,
|
925 |
+
"step": 620
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.7326007326007326,
|
929 |
+
"grad_norm": 0.12296965718269348,
|
930 |
+
"learning_rate": 0.00012672919109026965,
|
931 |
+
"loss": 0.0253,
|
932 |
+
"step": 625
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.7384615384615385,
|
936 |
+
"grad_norm": 0.13777951896190643,
|
937 |
+
"learning_rate": 0.0001261430246189918,
|
938 |
+
"loss": 0.0214,
|
939 |
+
"step": 630
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.7443223443223443,
|
943 |
+
"grad_norm": 0.12136834859848022,
|
944 |
+
"learning_rate": 0.00012555685814771397,
|
945 |
+
"loss": 0.0244,
|
946 |
+
"step": 635
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.7501831501831502,
|
950 |
+
"grad_norm": 0.050576552748680115,
|
951 |
+
"learning_rate": 0.00012497069167643612,
|
952 |
+
"loss": 0.0137,
|
953 |
+
"step": 640
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 0.756043956043956,
|
957 |
+
"grad_norm": 0.22222141921520233,
|
958 |
+
"learning_rate": 0.00012438452520515826,
|
959 |
+
"loss": 0.0254,
|
960 |
+
"step": 645
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.7619047619047619,
|
964 |
+
"grad_norm": 0.06815624237060547,
|
965 |
+
"learning_rate": 0.00012379835873388043,
|
966 |
+
"loss": 0.0231,
|
967 |
+
"step": 650
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 0.7677655677655678,
|
971 |
+
"grad_norm": 0.19518345594406128,
|
972 |
+
"learning_rate": 0.00012321219226260258,
|
973 |
+
"loss": 0.0218,
|
974 |
+
"step": 655
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.7736263736263737,
|
978 |
+
"grad_norm": 0.06349798291921616,
|
979 |
+
"learning_rate": 0.00012262602579132475,
|
980 |
+
"loss": 0.0265,
|
981 |
+
"step": 660
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.7794871794871795,
|
985 |
+
"grad_norm": 0.09031341969966888,
|
986 |
+
"learning_rate": 0.00012203985932004688,
|
987 |
+
"loss": 0.0299,
|
988 |
+
"step": 665
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.7853479853479853,
|
992 |
+
"grad_norm": 0.060232892632484436,
|
993 |
+
"learning_rate": 0.00012145369284876906,
|
994 |
+
"loss": 0.0227,
|
995 |
+
"step": 670
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 0.7912087912087912,
|
999 |
+
"grad_norm": 0.23972396552562714,
|
1000 |
+
"learning_rate": 0.00012086752637749122,
|
1001 |
+
"loss": 0.0233,
|
1002 |
+
"step": 675
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.7970695970695971,
|
1006 |
+
"grad_norm": 0.06141636520624161,
|
1007 |
+
"learning_rate": 0.00012028135990621336,
|
1008 |
+
"loss": 0.017,
|
1009 |
+
"step": 680
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 0.802930402930403,
|
1013 |
+
"grad_norm": 0.05603253096342087,
|
1014 |
+
"learning_rate": 0.00011969519343493553,
|
1015 |
+
"loss": 0.025,
|
1016 |
+
"step": 685
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.8087912087912088,
|
1020 |
+
"grad_norm": 0.06840907782316208,
|
1021 |
+
"learning_rate": 0.0001191090269636577,
|
1022 |
+
"loss": 0.0164,
|
1023 |
+
"step": 690
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.8146520146520146,
|
1027 |
+
"grad_norm": 0.1270790845155716,
|
1028 |
+
"learning_rate": 0.00011852286049237984,
|
1029 |
+
"loss": 0.0237,
|
1030 |
+
"step": 695
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 0.8205128205128205,
|
1034 |
+
"grad_norm": 0.03222518041729927,
|
1035 |
+
"learning_rate": 0.00011793669402110198,
|
1036 |
+
"loss": 0.0169,
|
1037 |
+
"step": 700
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 0.8205128205128205,
|
1041 |
+
"eval_loss": 0.026108432561159134,
|
1042 |
+
"eval_runtime": 4.6865,
|
1043 |
+
"eval_samples_per_second": 5.975,
|
1044 |
+
"eval_steps_per_second": 2.987,
|
1045 |
+
"step": 700
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.8263736263736263,
|
1049 |
+
"grad_norm": 0.06273896247148514,
|
1050 |
+
"learning_rate": 0.00011735052754982416,
|
1051 |
+
"loss": 0.0245,
|
1052 |
+
"step": 705
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.8322344322344323,
|
1056 |
+
"grad_norm": 0.1422451138496399,
|
1057 |
+
"learning_rate": 0.00011676436107854632,
|
1058 |
+
"loss": 0.0218,
|
1059 |
+
"step": 710
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.8380952380952381,
|
1063 |
+
"grad_norm": 0.07166247069835663,
|
1064 |
+
"learning_rate": 0.00011617819460726846,
|
1065 |
+
"loss": 0.0259,
|
1066 |
+
"step": 715
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.843956043956044,
|
1070 |
+
"grad_norm": 0.13188450038433075,
|
1071 |
+
"learning_rate": 0.00011559202813599064,
|
1072 |
+
"loss": 0.0185,
|
1073 |
+
"step": 720
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.8498168498168498,
|
1077 |
+
"grad_norm": 0.11839079111814499,
|
1078 |
+
"learning_rate": 0.0001150058616647128,
|
1079 |
+
"loss": 0.0196,
|
1080 |
+
"step": 725
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.8556776556776556,
|
1084 |
+
"grad_norm": 0.09421879053115845,
|
1085 |
+
"learning_rate": 0.00011441969519343494,
|
1086 |
+
"loss": 0.0207,
|
1087 |
+
"step": 730
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.8615384615384616,
|
1091 |
+
"grad_norm": 0.11722107976675034,
|
1092 |
+
"learning_rate": 0.00011383352872215709,
|
1093 |
+
"loss": 0.0286,
|
1094 |
+
"step": 735
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.8673992673992674,
|
1098 |
+
"grad_norm": 0.07790110260248184,
|
1099 |
+
"learning_rate": 0.00011324736225087926,
|
1100 |
+
"loss": 0.0157,
|
1101 |
+
"step": 740
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.8732600732600733,
|
1105 |
+
"grad_norm": 0.11153840273618698,
|
1106 |
+
"learning_rate": 0.00011266119577960142,
|
1107 |
+
"loss": 0.0184,
|
1108 |
+
"step": 745
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.8791208791208791,
|
1112 |
+
"grad_norm": 0.07105362415313721,
|
1113 |
+
"learning_rate": 0.00011207502930832356,
|
1114 |
+
"loss": 0.0193,
|
1115 |
+
"step": 750
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.884981684981685,
|
1119 |
+
"grad_norm": 0.11616308242082596,
|
1120 |
+
"learning_rate": 0.00011148886283704571,
|
1121 |
+
"loss": 0.0219,
|
1122 |
+
"step": 755
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.8908424908424909,
|
1126 |
+
"grad_norm": 0.10045047104358673,
|
1127 |
+
"learning_rate": 0.0001109026963657679,
|
1128 |
+
"loss": 0.0177,
|
1129 |
+
"step": 760
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.8967032967032967,
|
1133 |
+
"grad_norm": 0.07033990323543549,
|
1134 |
+
"learning_rate": 0.00011031652989449004,
|
1135 |
+
"loss": 0.0227,
|
1136 |
+
"step": 765
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.9025641025641026,
|
1140 |
+
"grad_norm": 0.07648850232362747,
|
1141 |
+
"learning_rate": 0.00010973036342321219,
|
1142 |
+
"loss": 0.023,
|
1143 |
+
"step": 770
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.9084249084249084,
|
1147 |
+
"grad_norm": 0.05392804369330406,
|
1148 |
+
"learning_rate": 0.00010914419695193436,
|
1149 |
+
"loss": 0.0136,
|
1150 |
+
"step": 775
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.9142857142857143,
|
1154 |
+
"grad_norm": 0.17311276495456696,
|
1155 |
+
"learning_rate": 0.00010855803048065652,
|
1156 |
+
"loss": 0.0257,
|
1157 |
+
"step": 780
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.9201465201465201,
|
1161 |
+
"grad_norm": 0.07022574543952942,
|
1162 |
+
"learning_rate": 0.00010797186400937866,
|
1163 |
+
"loss": 0.0282,
|
1164 |
+
"step": 785
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.926007326007326,
|
1168 |
+
"grad_norm": 0.15858297049999237,
|
1169 |
+
"learning_rate": 0.00010738569753810081,
|
1170 |
+
"loss": 0.0219,
|
1171 |
+
"step": 790
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.9318681318681319,
|
1175 |
+
"grad_norm": 0.06796769052743912,
|
1176 |
+
"learning_rate": 0.00010679953106682298,
|
1177 |
+
"loss": 0.0288,
|
1178 |
+
"step": 795
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.9377289377289377,
|
1182 |
+
"grad_norm": 0.11868051439523697,
|
1183 |
+
"learning_rate": 0.00010621336459554514,
|
1184 |
+
"loss": 0.0248,
|
1185 |
+
"step": 800
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.9377289377289377,
|
1189 |
+
"eval_loss": 0.019950957968831062,
|
1190 |
+
"eval_runtime": 4.8291,
|
1191 |
+
"eval_samples_per_second": 5.798,
|
1192 |
+
"eval_steps_per_second": 2.899,
|
1193 |
+
"step": 800
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.9435897435897436,
|
1197 |
+
"grad_norm": 0.19787561893463135,
|
1198 |
+
"learning_rate": 0.00010562719812426729,
|
1199 |
+
"loss": 0.0249,
|
1200 |
+
"step": 805
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.9494505494505494,
|
1204 |
+
"grad_norm": 0.06437662243843079,
|
1205 |
+
"learning_rate": 0.00010504103165298946,
|
1206 |
+
"loss": 0.0141,
|
1207 |
+
"step": 810
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.9553113553113554,
|
1211 |
+
"grad_norm": 0.09178975969552994,
|
1212 |
+
"learning_rate": 0.00010445486518171162,
|
1213 |
+
"loss": 0.0218,
|
1214 |
+
"step": 815
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.9611721611721612,
|
1218 |
+
"grad_norm": 0.09567834436893463,
|
1219 |
+
"learning_rate": 0.00010386869871043376,
|
1220 |
+
"loss": 0.0229,
|
1221 |
+
"step": 820
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.967032967032967,
|
1225 |
+
"grad_norm": 0.039594829082489014,
|
1226 |
+
"learning_rate": 0.00010328253223915591,
|
1227 |
+
"loss": 0.0186,
|
1228 |
+
"step": 825
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.9728937728937729,
|
1232 |
+
"grad_norm": 0.18495650589466095,
|
1233 |
+
"learning_rate": 0.00010269636576787808,
|
1234 |
+
"loss": 0.0237,
|
1235 |
+
"step": 830
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.9787545787545787,
|
1239 |
+
"grad_norm": 0.1861388385295868,
|
1240 |
+
"learning_rate": 0.00010211019929660024,
|
1241 |
+
"loss": 0.0367,
|
1242 |
+
"step": 835
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.9846153846153847,
|
1246 |
+
"grad_norm": 0.05491223558783531,
|
1247 |
+
"learning_rate": 0.00010152403282532239,
|
1248 |
+
"loss": 0.015,
|
1249 |
+
"step": 840
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.9904761904761905,
|
1253 |
+
"grad_norm": 0.04110349714756012,
|
1254 |
+
"learning_rate": 0.00010093786635404456,
|
1255 |
+
"loss": 0.0258,
|
1256 |
+
"step": 845
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.9963369963369964,
|
1260 |
+
"grad_norm": 0.07649147510528564,
|
1261 |
+
"learning_rate": 0.00010035169988276672,
|
1262 |
+
"loss": 0.0235,
|
1263 |
+
"step": 850
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.0021978021978022,
|
1267 |
+
"grad_norm": 0.11078579723834991,
|
1268 |
+
"learning_rate": 9.976553341148887e-05,
|
1269 |
+
"loss": 0.0204,
|
1270 |
+
"step": 855
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 1.008058608058608,
|
1274 |
+
"grad_norm": 0.08302613347768784,
|
1275 |
+
"learning_rate": 9.917936694021102e-05,
|
1276 |
+
"loss": 0.0188,
|
1277 |
+
"step": 860
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.0139194139194139,
|
1281 |
+
"grad_norm": 0.19045108556747437,
|
1282 |
+
"learning_rate": 9.859320046893318e-05,
|
1283 |
+
"loss": 0.0226,
|
1284 |
+
"step": 865
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.0197802197802197,
|
1288 |
+
"grad_norm": 0.04657626897096634,
|
1289 |
+
"learning_rate": 9.800703399765534e-05,
|
1290 |
+
"loss": 0.0205,
|
1291 |
+
"step": 870
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.0256410256410255,
|
1295 |
+
"grad_norm": 0.10237232595682144,
|
1296 |
+
"learning_rate": 9.742086752637749e-05,
|
1297 |
+
"loss": 0.0259,
|
1298 |
+
"step": 875
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.0315018315018314,
|
1302 |
+
"grad_norm": 0.1746947020292282,
|
1303 |
+
"learning_rate": 9.683470105509965e-05,
|
1304 |
+
"loss": 0.0229,
|
1305 |
+
"step": 880
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.0373626373626375,
|
1309 |
+
"grad_norm": 0.1032433807849884,
|
1310 |
+
"learning_rate": 9.624853458382182e-05,
|
1311 |
+
"loss": 0.0277,
|
1312 |
+
"step": 885
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.0432234432234433,
|
1316 |
+
"grad_norm": 0.08428288996219635,
|
1317 |
+
"learning_rate": 9.566236811254397e-05,
|
1318 |
+
"loss": 0.0161,
|
1319 |
+
"step": 890
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.0490842490842491,
|
1323 |
+
"grad_norm": 0.16661523282527924,
|
1324 |
+
"learning_rate": 9.507620164126613e-05,
|
1325 |
+
"loss": 0.0212,
|
1326 |
+
"step": 895
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 1.054945054945055,
|
1330 |
+
"grad_norm": 0.08473166078329086,
|
1331 |
+
"learning_rate": 9.449003516998827e-05,
|
1332 |
+
"loss": 0.0285,
|
1333 |
+
"step": 900
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.054945054945055,
|
1337 |
+
"eval_loss": 0.018958253785967827,
|
1338 |
+
"eval_runtime": 4.8179,
|
1339 |
+
"eval_samples_per_second": 5.812,
|
1340 |
+
"eval_steps_per_second": 2.906,
|
1341 |
+
"step": 900
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.0608058608058608,
|
1345 |
+
"grad_norm": 0.04149739816784859,
|
1346 |
+
"learning_rate": 9.390386869871044e-05,
|
1347 |
+
"loss": 0.0138,
|
1348 |
+
"step": 905
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 1.0666666666666667,
|
1352 |
+
"grad_norm": 0.05616866052150726,
|
1353 |
+
"learning_rate": 9.331770222743259e-05,
|
1354 |
+
"loss": 0.0194,
|
1355 |
+
"step": 910
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 1.0725274725274725,
|
1359 |
+
"grad_norm": 0.16730394959449768,
|
1360 |
+
"learning_rate": 9.273153575615475e-05,
|
1361 |
+
"loss": 0.0359,
|
1362 |
+
"step": 915
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 1.0783882783882783,
|
1366 |
+
"grad_norm": 0.06336849927902222,
|
1367 |
+
"learning_rate": 9.214536928487691e-05,
|
1368 |
+
"loss": 0.0147,
|
1369 |
+
"step": 920
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 1.0842490842490842,
|
1373 |
+
"grad_norm": 0.0882687047123909,
|
1374 |
+
"learning_rate": 9.155920281359907e-05,
|
1375 |
+
"loss": 0.015,
|
1376 |
+
"step": 925
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 1.09010989010989,
|
1380 |
+
"grad_norm": 0.05476200208067894,
|
1381 |
+
"learning_rate": 9.097303634232123e-05,
|
1382 |
+
"loss": 0.019,
|
1383 |
+
"step": 930
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.095970695970696,
|
1387 |
+
"grad_norm": 0.05358652025461197,
|
1388 |
+
"learning_rate": 9.038686987104337e-05,
|
1389 |
+
"loss": 0.0174,
|
1390 |
+
"step": 935
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 1.101831501831502,
|
1394 |
+
"grad_norm": 0.24095569550991058,
|
1395 |
+
"learning_rate": 8.980070339976554e-05,
|
1396 |
+
"loss": 0.0293,
|
1397 |
+
"step": 940
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 1.1076923076923078,
|
1401 |
+
"grad_norm": 0.06653840094804764,
|
1402 |
+
"learning_rate": 8.921453692848769e-05,
|
1403 |
+
"loss": 0.0133,
|
1404 |
+
"step": 945
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 1.1135531135531136,
|
1408 |
+
"grad_norm": 0.08839567750692368,
|
1409 |
+
"learning_rate": 8.862837045720985e-05,
|
1410 |
+
"loss": 0.0208,
|
1411 |
+
"step": 950
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 1.1194139194139194,
|
1415 |
+
"grad_norm": 0.032916922122240067,
|
1416 |
+
"learning_rate": 8.804220398593201e-05,
|
1417 |
+
"loss": 0.0267,
|
1418 |
+
"step": 955
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 1.1252747252747253,
|
1422 |
+
"grad_norm": 0.11819420754909515,
|
1423 |
+
"learning_rate": 8.745603751465417e-05,
|
1424 |
+
"loss": 0.0384,
|
1425 |
+
"step": 960
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.1311355311355311,
|
1429 |
+
"grad_norm": 0.06757565587759018,
|
1430 |
+
"learning_rate": 8.686987104337633e-05,
|
1431 |
+
"loss": 0.0135,
|
1432 |
+
"step": 965
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 1.136996336996337,
|
1436 |
+
"grad_norm": 0.0970228835940361,
|
1437 |
+
"learning_rate": 8.628370457209847e-05,
|
1438 |
+
"loss": 0.0166,
|
1439 |
+
"step": 970
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.1428571428571428,
|
1443 |
+
"grad_norm": 0.13436350226402283,
|
1444 |
+
"learning_rate": 8.569753810082065e-05,
|
1445 |
+
"loss": 0.016,
|
1446 |
+
"step": 975
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 1.1487179487179486,
|
1450 |
+
"grad_norm": 0.10584839433431625,
|
1451 |
+
"learning_rate": 8.511137162954279e-05,
|
1452 |
+
"loss": 0.0177,
|
1453 |
+
"step": 980
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 1.1545787545787545,
|
1457 |
+
"grad_norm": 0.21206024289131165,
|
1458 |
+
"learning_rate": 8.452520515826495e-05,
|
1459 |
+
"loss": 0.0325,
|
1460 |
+
"step": 985
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.1604395604395605,
|
1464 |
+
"grad_norm": 0.04815613850951195,
|
1465 |
+
"learning_rate": 8.393903868698711e-05,
|
1466 |
+
"loss": 0.0137,
|
1467 |
+
"step": 990
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.1663003663003664,
|
1471 |
+
"grad_norm": 0.07466138154268265,
|
1472 |
+
"learning_rate": 8.335287221570927e-05,
|
1473 |
+
"loss": 0.0173,
|
1474 |
+
"step": 995
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.1721611721611722,
|
1478 |
+
"grad_norm": 0.09366811066865921,
|
1479 |
+
"learning_rate": 8.276670574443143e-05,
|
1480 |
+
"loss": 0.025,
|
1481 |
+
"step": 1000
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 1.1721611721611722,
|
1485 |
+
"eval_loss": 0.019907595589756966,
|
1486 |
+
"eval_runtime": 4.819,
|
1487 |
+
"eval_samples_per_second": 5.81,
|
1488 |
+
"eval_steps_per_second": 2.905,
|
1489 |
+
"step": 1000
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.178021978021978,
|
1493 |
+
"grad_norm": 0.08527784794569016,
|
1494 |
+
"learning_rate": 8.218053927315357e-05,
|
1495 |
+
"loss": 0.0208,
|
1496 |
+
"step": 1005
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 1.183882783882784,
|
1500 |
+
"grad_norm": 0.08328138291835785,
|
1501 |
+
"learning_rate": 8.159437280187575e-05,
|
1502 |
+
"loss": 0.0216,
|
1503 |
+
"step": 1010
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.1897435897435897,
|
1507 |
+
"grad_norm": 0.05000188946723938,
|
1508 |
+
"learning_rate": 8.100820633059789e-05,
|
1509 |
+
"loss": 0.0211,
|
1510 |
+
"step": 1015
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.1956043956043956,
|
1514 |
+
"grad_norm": 0.028807902708649635,
|
1515 |
+
"learning_rate": 8.042203985932005e-05,
|
1516 |
+
"loss": 0.0096,
|
1517 |
+
"step": 1020
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 1.2014652014652014,
|
1521 |
+
"grad_norm": 0.20507606863975525,
|
1522 |
+
"learning_rate": 7.983587338804221e-05,
|
1523 |
+
"loss": 0.0222,
|
1524 |
+
"step": 1025
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.2073260073260073,
|
1528 |
+
"grad_norm": 0.04885656014084816,
|
1529 |
+
"learning_rate": 7.924970691676437e-05,
|
1530 |
+
"loss": 0.0215,
|
1531 |
+
"step": 1030
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 1.213186813186813,
|
1535 |
+
"grad_norm": 0.047489382326602936,
|
1536 |
+
"learning_rate": 7.866354044548652e-05,
|
1537 |
+
"loss": 0.0178,
|
1538 |
+
"step": 1035
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 1.2190476190476192,
|
1542 |
+
"grad_norm": 0.05971779301762581,
|
1543 |
+
"learning_rate": 7.807737397420867e-05,
|
1544 |
+
"loss": 0.0176,
|
1545 |
+
"step": 1040
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.224908424908425,
|
1549 |
+
"grad_norm": 0.04695736616849899,
|
1550 |
+
"learning_rate": 7.749120750293083e-05,
|
1551 |
+
"loss": 0.0148,
|
1552 |
+
"step": 1045
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 1.2307692307692308,
|
1556 |
+
"grad_norm": 0.08131909370422363,
|
1557 |
+
"learning_rate": 7.690504103165299e-05,
|
1558 |
+
"loss": 0.0201,
|
1559 |
+
"step": 1050
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 1.2366300366300367,
|
1563 |
+
"grad_norm": 0.06954577565193176,
|
1564 |
+
"learning_rate": 7.631887456037515e-05,
|
1565 |
+
"loss": 0.0149,
|
1566 |
+
"step": 1055
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 1.2424908424908425,
|
1570 |
+
"grad_norm": 0.054430391639471054,
|
1571 |
+
"learning_rate": 7.57327080890973e-05,
|
1572 |
+
"loss": 0.0078,
|
1573 |
+
"step": 1060
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 1.2483516483516484,
|
1577 |
+
"grad_norm": 0.12231959402561188,
|
1578 |
+
"learning_rate": 7.514654161781947e-05,
|
1579 |
+
"loss": 0.0258,
|
1580 |
+
"step": 1065
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 1.2542124542124542,
|
1584 |
+
"grad_norm": 0.04983118548989296,
|
1585 |
+
"learning_rate": 7.456037514654162e-05,
|
1586 |
+
"loss": 0.0189,
|
1587 |
+
"step": 1070
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.26007326007326,
|
1591 |
+
"grad_norm": 0.11981873214244843,
|
1592 |
+
"learning_rate": 7.397420867526378e-05,
|
1593 |
+
"loss": 0.0156,
|
1594 |
+
"step": 1075
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 1.2659340659340659,
|
1598 |
+
"grad_norm": 0.03829724341630936,
|
1599 |
+
"learning_rate": 7.338804220398593e-05,
|
1600 |
+
"loss": 0.0162,
|
1601 |
+
"step": 1080
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 1.2717948717948717,
|
1605 |
+
"grad_norm": 0.1572490632534027,
|
1606 |
+
"learning_rate": 7.28018757327081e-05,
|
1607 |
+
"loss": 0.0188,
|
1608 |
+
"step": 1085
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.2776556776556776,
|
1612 |
+
"grad_norm": 0.122514508664608,
|
1613 |
+
"learning_rate": 7.221570926143025e-05,
|
1614 |
+
"loss": 0.0229,
|
1615 |
+
"step": 1090
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 1.2835164835164834,
|
1619 |
+
"grad_norm": 0.06537042558193207,
|
1620 |
+
"learning_rate": 7.16295427901524e-05,
|
1621 |
+
"loss": 0.0222,
|
1622 |
+
"step": 1095
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 1.2893772893772895,
|
1626 |
+
"grad_norm": 0.1269371509552002,
|
1627 |
+
"learning_rate": 7.104337631887457e-05,
|
1628 |
+
"loss": 0.0272,
|
1629 |
+
"step": 1100
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.2893772893772895,
|
1633 |
+
"eval_loss": 0.015397748909890652,
|
1634 |
+
"eval_runtime": 4.7526,
|
1635 |
+
"eval_samples_per_second": 5.892,
|
1636 |
+
"eval_steps_per_second": 2.946,
|
1637 |
+
"step": 1100
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 1.2952380952380953,
|
1641 |
+
"grad_norm": 0.07507819682359695,
|
1642 |
+
"learning_rate": 7.045720984759672e-05,
|
1643 |
+
"loss": 0.0256,
|
1644 |
+
"step": 1105
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.3010989010989011,
|
1648 |
+
"grad_norm": 0.04198193550109863,
|
1649 |
+
"learning_rate": 6.987104337631888e-05,
|
1650 |
+
"loss": 0.0102,
|
1651 |
+
"step": 1110
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 1.306959706959707,
|
1655 |
+
"grad_norm": 0.053751297295093536,
|
1656 |
+
"learning_rate": 6.928487690504104e-05,
|
1657 |
+
"loss": 0.0141,
|
1658 |
+
"step": 1115
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.3128205128205128,
|
1662 |
+
"grad_norm": 0.12076237797737122,
|
1663 |
+
"learning_rate": 6.86987104337632e-05,
|
1664 |
+
"loss": 0.0165,
|
1665 |
+
"step": 1120
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.3186813186813187,
|
1669 |
+
"grad_norm": 0.0769004300236702,
|
1670 |
+
"learning_rate": 6.811254396248535e-05,
|
1671 |
+
"loss": 0.0191,
|
1672 |
+
"step": 1125
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 1.3245421245421245,
|
1676 |
+
"grad_norm": 0.08021704852581024,
|
1677 |
+
"learning_rate": 6.75263774912075e-05,
|
1678 |
+
"loss": 0.0253,
|
1679 |
+
"step": 1130
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 1.3304029304029303,
|
1683 |
+
"grad_norm": 0.09786754846572876,
|
1684 |
+
"learning_rate": 6.694021101992967e-05,
|
1685 |
+
"loss": 0.0191,
|
1686 |
+
"step": 1135
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 1.3362637362637364,
|
1690 |
+
"grad_norm": 0.06878714263439178,
|
1691 |
+
"learning_rate": 6.635404454865182e-05,
|
1692 |
+
"loss": 0.0326,
|
1693 |
+
"step": 1140
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 1.3421245421245422,
|
1697 |
+
"grad_norm": 0.11297193914651871,
|
1698 |
+
"learning_rate": 6.576787807737398e-05,
|
1699 |
+
"loss": 0.0185,
|
1700 |
+
"step": 1145
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.347985347985348,
|
1704 |
+
"grad_norm": 0.10731342434883118,
|
1705 |
+
"learning_rate": 6.518171160609614e-05,
|
1706 |
+
"loss": 0.0168,
|
1707 |
+
"step": 1150
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.353846153846154,
|
1711 |
+
"grad_norm": 0.08888328820466995,
|
1712 |
+
"learning_rate": 6.45955451348183e-05,
|
1713 |
+
"loss": 0.0182,
|
1714 |
+
"step": 1155
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.3597069597069598,
|
1718 |
+
"grad_norm": 0.1666301190853119,
|
1719 |
+
"learning_rate": 6.400937866354045e-05,
|
1720 |
+
"loss": 0.0254,
|
1721 |
+
"step": 1160
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 1.3655677655677656,
|
1725 |
+
"grad_norm": 0.1334419697523117,
|
1726 |
+
"learning_rate": 6.34232121922626e-05,
|
1727 |
+
"loss": 0.0215,
|
1728 |
+
"step": 1165
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 1.3714285714285714,
|
1732 |
+
"grad_norm": 0.05616243556141853,
|
1733 |
+
"learning_rate": 6.283704572098477e-05,
|
1734 |
+
"loss": 0.0156,
|
1735 |
+
"step": 1170
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 1.3772893772893773,
|
1739 |
+
"grad_norm": 0.1660885214805603,
|
1740 |
+
"learning_rate": 6.225087924970692e-05,
|
1741 |
+
"loss": 0.0241,
|
1742 |
+
"step": 1175
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 1.3831501831501831,
|
1746 |
+
"grad_norm": 0.09245380759239197,
|
1747 |
+
"learning_rate": 6.166471277842908e-05,
|
1748 |
+
"loss": 0.0222,
|
1749 |
+
"step": 1180
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.389010989010989,
|
1753 |
+
"grad_norm": 0.08635041117668152,
|
1754 |
+
"learning_rate": 6.107854630715122e-05,
|
1755 |
+
"loss": 0.0203,
|
1756 |
+
"step": 1185
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.3948717948717948,
|
1760 |
+
"grad_norm": 0.07752135396003723,
|
1761 |
+
"learning_rate": 6.049237983587339e-05,
|
1762 |
+
"loss": 0.0216,
|
1763 |
+
"step": 1190
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 1.4007326007326006,
|
1767 |
+
"grad_norm": 0.10603225976228714,
|
1768 |
+
"learning_rate": 5.990621336459554e-05,
|
1769 |
+
"loss": 0.0205,
|
1770 |
+
"step": 1195
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 1.4065934065934065,
|
1774 |
+
"grad_norm": 0.04343140870332718,
|
1775 |
+
"learning_rate": 5.932004689331771e-05,
|
1776 |
+
"loss": 0.0105,
|
1777 |
+
"step": 1200
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 1.4065934065934065,
|
1781 |
+
"eval_loss": 0.015952473506331444,
|
1782 |
+
"eval_runtime": 4.7686,
|
1783 |
+
"eval_samples_per_second": 5.872,
|
1784 |
+
"eval_steps_per_second": 2.936,
|
1785 |
+
"step": 1200
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 1.4124542124542123,
|
1789 |
+
"grad_norm": 0.12541887164115906,
|
1790 |
+
"learning_rate": 5.873388042203987e-05,
|
1791 |
+
"loss": 0.0217,
|
1792 |
+
"step": 1205
|
1793 |
+
},
|
1794 |
+
{
|
1795 |
+
"epoch": 1.4183150183150184,
|
1796 |
+
"grad_norm": 0.05417335778474808,
|
1797 |
+
"learning_rate": 5.814771395076202e-05,
|
1798 |
+
"loss": 0.0205,
|
1799 |
+
"step": 1210
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"epoch": 1.4241758241758242,
|
1803 |
+
"grad_norm": 0.04461506009101868,
|
1804 |
+
"learning_rate": 5.756154747948418e-05,
|
1805 |
+
"loss": 0.0211,
|
1806 |
+
"step": 1215
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.43003663003663,
|
1810 |
+
"grad_norm": 0.09423286467790604,
|
1811 |
+
"learning_rate": 5.697538100820633e-05,
|
1812 |
+
"loss": 0.0238,
|
1813 |
+
"step": 1220
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 1.435897435897436,
|
1817 |
+
"grad_norm": 0.050094570964574814,
|
1818 |
+
"learning_rate": 5.638921453692849e-05,
|
1819 |
+
"loss": 0.0163,
|
1820 |
+
"step": 1225
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 1.4417582417582417,
|
1824 |
+
"grad_norm": 0.13104532659053802,
|
1825 |
+
"learning_rate": 5.580304806565064e-05,
|
1826 |
+
"loss": 0.0219,
|
1827 |
+
"step": 1230
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.4476190476190476,
|
1831 |
+
"grad_norm": 0.08238503336906433,
|
1832 |
+
"learning_rate": 5.52168815943728e-05,
|
1833 |
+
"loss": 0.0126,
|
1834 |
+
"step": 1235
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.4534798534798534,
|
1838 |
+
"grad_norm": 0.1029452383518219,
|
1839 |
+
"learning_rate": 5.463071512309497e-05,
|
1840 |
+
"loss": 0.0247,
|
1841 |
+
"step": 1240
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"epoch": 1.4593406593406593,
|
1845 |
+
"grad_norm": 0.05564792454242706,
|
1846 |
+
"learning_rate": 5.404454865181712e-05,
|
1847 |
+
"loss": 0.0212,
|
1848 |
+
"step": 1245
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 1.4652014652014653,
|
1852 |
+
"grad_norm": 0.08589282631874084,
|
1853 |
+
"learning_rate": 5.345838218053928e-05,
|
1854 |
+
"loss": 0.0184,
|
1855 |
+
"step": 1250
|
1856 |
+
},
|
1857 |
+
{
|
1858 |
+
"epoch": 1.4710622710622712,
|
1859 |
+
"grad_norm": 0.15644195675849915,
|
1860 |
+
"learning_rate": 5.287221570926143e-05,
|
1861 |
+
"loss": 0.0165,
|
1862 |
+
"step": 1255
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 1.476923076923077,
|
1866 |
+
"grad_norm": 0.11301274597644806,
|
1867 |
+
"learning_rate": 5.228604923798359e-05,
|
1868 |
+
"loss": 0.0322,
|
1869 |
+
"step": 1260
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.4827838827838828,
|
1873 |
+
"grad_norm": 0.044553741812705994,
|
1874 |
+
"learning_rate": 5.1699882766705743e-05,
|
1875 |
+
"loss": 0.0183,
|
1876 |
+
"step": 1265
|
1877 |
+
},
|
1878 |
+
{
|
1879 |
+
"epoch": 1.4886446886446887,
|
1880 |
+
"grad_norm": 0.06141185760498047,
|
1881 |
+
"learning_rate": 5.11137162954279e-05,
|
1882 |
+
"loss": 0.0102,
|
1883 |
+
"step": 1270
|
1884 |
+
},
|
1885 |
+
{
|
1886 |
+
"epoch": 1.4945054945054945,
|
1887 |
+
"grad_norm": 0.08107537031173706,
|
1888 |
+
"learning_rate": 5.0527549824150055e-05,
|
1889 |
+
"loss": 0.0215,
|
1890 |
+
"step": 1275
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 1.5003663003663004,
|
1894 |
+
"grad_norm": 0.06017793342471123,
|
1895 |
+
"learning_rate": 4.9941383352872214e-05,
|
1896 |
+
"loss": 0.0176,
|
1897 |
+
"step": 1280
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 1.5062271062271062,
|
1901 |
+
"grad_norm": 0.051033902913331985,
|
1902 |
+
"learning_rate": 4.9355216881594373e-05,
|
1903 |
+
"loss": 0.0149,
|
1904 |
+
"step": 1285
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 1.512087912087912,
|
1908 |
+
"grad_norm": 0.124452143907547,
|
1909 |
+
"learning_rate": 4.876905041031653e-05,
|
1910 |
+
"loss": 0.0209,
|
1911 |
+
"step": 1290
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 1.5179487179487179,
|
1915 |
+
"grad_norm": 0.1616523712873459,
|
1916 |
+
"learning_rate": 4.8182883939038685e-05,
|
1917 |
+
"loss": 0.0192,
|
1918 |
+
"step": 1295
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 1.5238095238095237,
|
1922 |
+
"grad_norm": 0.07067764550447464,
|
1923 |
+
"learning_rate": 4.759671746776085e-05,
|
1924 |
+
"loss": 0.0279,
|
1925 |
+
"step": 1300
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 1.5238095238095237,
|
1929 |
+
"eval_loss": 0.017229218035936356,
|
1930 |
+
"eval_runtime": 4.6702,
|
1931 |
+
"eval_samples_per_second": 5.996,
|
1932 |
+
"eval_steps_per_second": 2.998,
|
1933 |
+
"step": 1300
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"epoch": 1.5296703296703296,
|
1937 |
+
"grad_norm": 0.06332267820835114,
|
1938 |
+
"learning_rate": 4.7010550996483003e-05,
|
1939 |
+
"loss": 0.0253,
|
1940 |
+
"step": 1305
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 1.5355311355311354,
|
1944 |
+
"grad_norm": 0.08032066375017166,
|
1945 |
+
"learning_rate": 4.642438452520516e-05,
|
1946 |
+
"loss": 0.0128,
|
1947 |
+
"step": 1310
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 1.5413919413919412,
|
1951 |
+
"grad_norm": 0.11456907540559769,
|
1952 |
+
"learning_rate": 4.5838218053927315e-05,
|
1953 |
+
"loss": 0.0127,
|
1954 |
+
"step": 1315
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.5472527472527473,
|
1958 |
+
"grad_norm": 0.19653138518333435,
|
1959 |
+
"learning_rate": 4.5252051582649474e-05,
|
1960 |
+
"loss": 0.0236,
|
1961 |
+
"step": 1320
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 1.5531135531135531,
|
1965 |
+
"grad_norm": 0.08195839822292328,
|
1966 |
+
"learning_rate": 4.4665885111371633e-05,
|
1967 |
+
"loss": 0.0173,
|
1968 |
+
"step": 1325
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 1.558974358974359,
|
1972 |
+
"grad_norm": 0.11376089602708817,
|
1973 |
+
"learning_rate": 4.4079718640093786e-05,
|
1974 |
+
"loss": 0.0115,
|
1975 |
+
"step": 1330
|
1976 |
+
},
|
1977 |
+
{
|
1978 |
+
"epoch": 1.5648351648351648,
|
1979 |
+
"grad_norm": 0.055264201015233994,
|
1980 |
+
"learning_rate": 4.3493552168815945e-05,
|
1981 |
+
"loss": 0.0198,
|
1982 |
+
"step": 1335
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 1.5706959706959707,
|
1986 |
+
"grad_norm": 0.13038881123065948,
|
1987 |
+
"learning_rate": 4.2907385697538104e-05,
|
1988 |
+
"loss": 0.0231,
|
1989 |
+
"step": 1340
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.5765567765567765,
|
1993 |
+
"grad_norm": 0.0317939892411232,
|
1994 |
+
"learning_rate": 4.2321219226260263e-05,
|
1995 |
+
"loss": 0.0083,
|
1996 |
+
"step": 1345
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 1.5824175824175826,
|
2000 |
+
"grad_norm": 0.151336207985878,
|
2001 |
+
"learning_rate": 4.1735052754982416e-05,
|
2002 |
+
"loss": 0.0225,
|
2003 |
+
"step": 1350
|
2004 |
+
},
|
2005 |
+
{
|
2006 |
+
"epoch": 1.5882783882783884,
|
2007 |
+
"grad_norm": 0.07817093282938004,
|
2008 |
+
"learning_rate": 4.1148886283704575e-05,
|
2009 |
+
"loss": 0.0226,
|
2010 |
+
"step": 1355
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.5941391941391942,
|
2014 |
+
"grad_norm": 0.1341279149055481,
|
2015 |
+
"learning_rate": 4.056271981242673e-05,
|
2016 |
+
"loss": 0.0263,
|
2017 |
+
"step": 1360
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 1.6,
|
2021 |
+
"grad_norm": 0.06353727728128433,
|
2022 |
+
"learning_rate": 3.997655334114889e-05,
|
2023 |
+
"loss": 0.0198,
|
2024 |
+
"step": 1365
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 1.605860805860806,
|
2028 |
+
"grad_norm": 0.11177901178598404,
|
2029 |
+
"learning_rate": 3.9390386869871046e-05,
|
2030 |
+
"loss": 0.0172,
|
2031 |
+
"step": 1370
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 1.6117216117216118,
|
2035 |
+
"grad_norm": 0.047024596482515335,
|
2036 |
+
"learning_rate": 3.88042203985932e-05,
|
2037 |
+
"loss": 0.0207,
|
2038 |
+
"step": 1375
|
2039 |
+
},
|
2040 |
+
{
|
2041 |
+
"epoch": 1.6175824175824176,
|
2042 |
+
"grad_norm": 0.04343528300523758,
|
2043 |
+
"learning_rate": 3.8218053927315364e-05,
|
2044 |
+
"loss": 0.0214,
|
2045 |
+
"step": 1380
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 1.6234432234432234,
|
2049 |
+
"grad_norm": 0.08330193161964417,
|
2050 |
+
"learning_rate": 3.763188745603752e-05,
|
2051 |
+
"loss": 0.0286,
|
2052 |
+
"step": 1385
|
2053 |
+
},
|
2054 |
+
{
|
2055 |
+
"epoch": 1.6293040293040293,
|
2056 |
+
"grad_norm": 0.0811009556055069,
|
2057 |
+
"learning_rate": 3.7045720984759676e-05,
|
2058 |
+
"loss": 0.0148,
|
2059 |
+
"step": 1390
|
2060 |
+
},
|
2061 |
+
{
|
2062 |
+
"epoch": 1.6351648351648351,
|
2063 |
+
"grad_norm": 0.1049441322684288,
|
2064 |
+
"learning_rate": 3.645955451348183e-05,
|
2065 |
+
"loss": 0.0184,
|
2066 |
+
"step": 1395
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.641025641025641,
|
2070 |
+
"grad_norm": 0.11944428086280823,
|
2071 |
+
"learning_rate": 3.587338804220399e-05,
|
2072 |
+
"loss": 0.0122,
|
2073 |
+
"step": 1400
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 1.641025641025641,
|
2077 |
+
"eval_loss": 0.017561230808496475,
|
2078 |
+
"eval_runtime": 4.685,
|
2079 |
+
"eval_samples_per_second": 5.977,
|
2080 |
+
"eval_steps_per_second": 2.988,
|
2081 |
+
"step": 1400
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 1.6468864468864468,
|
2085 |
+
"grad_norm": 0.14023366570472717,
|
2086 |
+
"learning_rate": 3.528722157092615e-05,
|
2087 |
+
"loss": 0.0178,
|
2088 |
+
"step": 1405
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 1.6527472527472526,
|
2092 |
+
"grad_norm": 0.14057691395282745,
|
2093 |
+
"learning_rate": 3.47010550996483e-05,
|
2094 |
+
"loss": 0.0268,
|
2095 |
+
"step": 1410
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 1.6586080586080585,
|
2099 |
+
"grad_norm": 0.1253061443567276,
|
2100 |
+
"learning_rate": 3.411488862837046e-05,
|
2101 |
+
"loss": 0.0266,
|
2102 |
+
"step": 1415
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.6644688644688643,
|
2106 |
+
"grad_norm": 0.03431854769587517,
|
2107 |
+
"learning_rate": 3.352872215709262e-05,
|
2108 |
+
"loss": 0.02,
|
2109 |
+
"step": 1420
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.6703296703296702,
|
2113 |
+
"grad_norm": 0.13929079473018646,
|
2114 |
+
"learning_rate": 3.294255568581478e-05,
|
2115 |
+
"loss": 0.0226,
|
2116 |
+
"step": 1425
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.6761904761904762,
|
2120 |
+
"grad_norm": 0.06429693102836609,
|
2121 |
+
"learning_rate": 3.235638921453693e-05,
|
2122 |
+
"loss": 0.0225,
|
2123 |
+
"step": 1430
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 1.682051282051282,
|
2127 |
+
"grad_norm": 0.029311953112483025,
|
2128 |
+
"learning_rate": 3.177022274325909e-05,
|
2129 |
+
"loss": 0.0161,
|
2130 |
+
"step": 1435
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 1.687912087912088,
|
2134 |
+
"grad_norm": 0.04346455633640289,
|
2135 |
+
"learning_rate": 3.118405627198124e-05,
|
2136 |
+
"loss": 0.0155,
|
2137 |
+
"step": 1440
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 1.6937728937728938,
|
2141 |
+
"grad_norm": 0.09009824693202972,
|
2142 |
+
"learning_rate": 3.05978898007034e-05,
|
2143 |
+
"loss": 0.0153,
|
2144 |
+
"step": 1445
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 1.6996336996336996,
|
2148 |
+
"grad_norm": 0.071926549077034,
|
2149 |
+
"learning_rate": 3.0011723329425556e-05,
|
2150 |
+
"loss": 0.0136,
|
2151 |
+
"step": 1450
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.7054945054945057,
|
2155 |
+
"grad_norm": 0.06461833417415619,
|
2156 |
+
"learning_rate": 2.9425556858147718e-05,
|
2157 |
+
"loss": 0.0237,
|
2158 |
+
"step": 1455
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.7113553113553115,
|
2162 |
+
"grad_norm": 0.039929524064064026,
|
2163 |
+
"learning_rate": 2.8839390386869874e-05,
|
2164 |
+
"loss": 0.0187,
|
2165 |
+
"step": 1460
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 1.7172161172161173,
|
2169 |
+
"grad_norm": 0.0534372515976429,
|
2170 |
+
"learning_rate": 2.825322391559203e-05,
|
2171 |
+
"loss": 0.0192,
|
2172 |
+
"step": 1465
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 1.7230769230769232,
|
2176 |
+
"grad_norm": 0.1467376947402954,
|
2177 |
+
"learning_rate": 2.7667057444314186e-05,
|
2178 |
+
"loss": 0.0203,
|
2179 |
+
"step": 1470
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 1.728937728937729,
|
2183 |
+
"grad_norm": 0.0830003172159195,
|
2184 |
+
"learning_rate": 2.7080890973036345e-05,
|
2185 |
+
"loss": 0.0188,
|
2186 |
+
"step": 1475
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 1.7347985347985349,
|
2190 |
+
"grad_norm": 0.07220768928527832,
|
2191 |
+
"learning_rate": 2.64947245017585e-05,
|
2192 |
+
"loss": 0.0118,
|
2193 |
+
"step": 1480
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 1.7406593406593407,
|
2197 |
+
"grad_norm": 0.0751115009188652,
|
2198 |
+
"learning_rate": 2.5908558030480656e-05,
|
2199 |
+
"loss": 0.0156,
|
2200 |
+
"step": 1485
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 1.7465201465201465,
|
2204 |
+
"grad_norm": 0.07690921425819397,
|
2205 |
+
"learning_rate": 2.5322391559202812e-05,
|
2206 |
+
"loss": 0.0347,
|
2207 |
+
"step": 1490
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 1.7523809523809524,
|
2211 |
+
"grad_norm": 0.05416159704327583,
|
2212 |
+
"learning_rate": 2.473622508792497e-05,
|
2213 |
+
"loss": 0.0167,
|
2214 |
+
"step": 1495
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.7582417582417582,
|
2218 |
+
"grad_norm": 0.0676250010728836,
|
2219 |
+
"learning_rate": 2.4150058616647127e-05,
|
2220 |
+
"loss": 0.0205,
|
2221 |
+
"step": 1500
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 1.7582417582417582,
|
2225 |
+
"eval_loss": 0.019522378221154213,
|
2226 |
+
"eval_runtime": 4.6942,
|
2227 |
+
"eval_samples_per_second": 5.965,
|
2228 |
+
"eval_steps_per_second": 2.982,
|
2229 |
+
"step": 1500
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 1.764102564102564,
|
2233 |
+
"grad_norm": 0.08909754455089569,
|
2234 |
+
"learning_rate": 2.3563892145369286e-05,
|
2235 |
+
"loss": 0.0249,
|
2236 |
+
"step": 1505
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 1.76996336996337,
|
2240 |
+
"grad_norm": 0.042161233723163605,
|
2241 |
+
"learning_rate": 2.2977725674091442e-05,
|
2242 |
+
"loss": 0.0117,
|
2243 |
+
"step": 1510
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 1.7758241758241757,
|
2247 |
+
"grad_norm": 0.07136218249797821,
|
2248 |
+
"learning_rate": 2.23915592028136e-05,
|
2249 |
+
"loss": 0.0212,
|
2250 |
+
"step": 1515
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 1.7816849816849816,
|
2254 |
+
"grad_norm": 0.14128735661506653,
|
2255 |
+
"learning_rate": 2.1805392731535757e-05,
|
2256 |
+
"loss": 0.0189,
|
2257 |
+
"step": 1520
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 1.7875457875457874,
|
2261 |
+
"grad_norm": 0.05959760770201683,
|
2262 |
+
"learning_rate": 2.1219226260257916e-05,
|
2263 |
+
"loss": 0.0119,
|
2264 |
+
"step": 1525
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.7934065934065933,
|
2268 |
+
"grad_norm": 0.038479190319776535,
|
2269 |
+
"learning_rate": 2.0633059788980072e-05,
|
2270 |
+
"loss": 0.013,
|
2271 |
+
"step": 1530
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 1.7992673992673993,
|
2275 |
+
"grad_norm": 0.09512809664011002,
|
2276 |
+
"learning_rate": 2.0046893317702228e-05,
|
2277 |
+
"loss": 0.0148,
|
2278 |
+
"step": 1535
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 1.8051282051282052,
|
2282 |
+
"grad_norm": 0.14848454296588898,
|
2283 |
+
"learning_rate": 1.9460726846424384e-05,
|
2284 |
+
"loss": 0.019,
|
2285 |
+
"step": 1540
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 1.810989010989011,
|
2289 |
+
"grad_norm": 0.10240516811609268,
|
2290 |
+
"learning_rate": 1.8874560375146543e-05,
|
2291 |
+
"loss": 0.017,
|
2292 |
+
"step": 1545
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 1.8168498168498168,
|
2296 |
+
"grad_norm": 0.09345954656600952,
|
2297 |
+
"learning_rate": 1.82883939038687e-05,
|
2298 |
+
"loss": 0.0237,
|
2299 |
+
"step": 1550
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 1.8227106227106227,
|
2303 |
+
"grad_norm": 0.03815275430679321,
|
2304 |
+
"learning_rate": 1.7702227432590858e-05,
|
2305 |
+
"loss": 0.0188,
|
2306 |
+
"step": 1555
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.8285714285714287,
|
2310 |
+
"grad_norm": 0.027827398851513863,
|
2311 |
+
"learning_rate": 1.7116060961313014e-05,
|
2312 |
+
"loss": 0.0183,
|
2313 |
+
"step": 1560
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 1.8344322344322346,
|
2317 |
+
"grad_norm": 0.08811303228139877,
|
2318 |
+
"learning_rate": 1.6529894490035173e-05,
|
2319 |
+
"loss": 0.0191,
|
2320 |
+
"step": 1565
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.8402930402930404,
|
2324 |
+
"grad_norm": 0.03119056299328804,
|
2325 |
+
"learning_rate": 1.594372801875733e-05,
|
2326 |
+
"loss": 0.0183,
|
2327 |
+
"step": 1570
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 1.8461538461538463,
|
2331 |
+
"grad_norm": 0.09752997010946274,
|
2332 |
+
"learning_rate": 1.5357561547479485e-05,
|
2333 |
+
"loss": 0.0161,
|
2334 |
+
"step": 1575
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.852014652014652,
|
2338 |
+
"grad_norm": 0.0855243131518364,
|
2339 |
+
"learning_rate": 1.477139507620164e-05,
|
2340 |
+
"loss": 0.015,
|
2341 |
+
"step": 1580
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 1.857875457875458,
|
2345 |
+
"grad_norm": 0.08388842642307281,
|
2346 |
+
"learning_rate": 1.41852286049238e-05,
|
2347 |
+
"loss": 0.0148,
|
2348 |
+
"step": 1585
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 1.8637362637362638,
|
2352 |
+
"grad_norm": 0.10147551447153091,
|
2353 |
+
"learning_rate": 1.3599062133645957e-05,
|
2354 |
+
"loss": 0.0154,
|
2355 |
+
"step": 1590
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 1.8695970695970696,
|
2359 |
+
"grad_norm": 0.0457012839615345,
|
2360 |
+
"learning_rate": 1.3012895662368113e-05,
|
2361 |
+
"loss": 0.0186,
|
2362 |
+
"step": 1595
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.8754578754578755,
|
2366 |
+
"grad_norm": 0.03654688224196434,
|
2367 |
+
"learning_rate": 1.242672919109027e-05,
|
2368 |
+
"loss": 0.0321,
|
2369 |
+
"step": 1600
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 1.8754578754578755,
|
2373 |
+
"eval_loss": 0.017443044111132622,
|
2374 |
+
"eval_runtime": 4.7108,
|
2375 |
+
"eval_samples_per_second": 5.944,
|
2376 |
+
"eval_steps_per_second": 2.972,
|
2377 |
+
"step": 1600
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 1.8813186813186813,
|
2381 |
+
"grad_norm": 0.07887323200702667,
|
2382 |
+
"learning_rate": 1.1840562719812428e-05,
|
2383 |
+
"loss": 0.0142,
|
2384 |
+
"step": 1605
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 1.8871794871794871,
|
2388 |
+
"grad_norm": 0.11328335106372833,
|
2389 |
+
"learning_rate": 1.1254396248534585e-05,
|
2390 |
+
"loss": 0.025,
|
2391 |
+
"step": 1610
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.893040293040293,
|
2395 |
+
"grad_norm": 0.09318089485168457,
|
2396 |
+
"learning_rate": 1.0668229777256741e-05,
|
2397 |
+
"loss": 0.0204,
|
2398 |
+
"step": 1615
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 1.8989010989010988,
|
2402 |
+
"grad_norm": 0.06992164254188538,
|
2403 |
+
"learning_rate": 1.0082063305978899e-05,
|
2404 |
+
"loss": 0.0135,
|
2405 |
+
"step": 1620
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 1.9047619047619047,
|
2409 |
+
"grad_norm": 0.14927181601524353,
|
2410 |
+
"learning_rate": 9.495896834701056e-06,
|
2411 |
+
"loss": 0.0245,
|
2412 |
+
"step": 1625
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 1.9106227106227105,
|
2416 |
+
"grad_norm": 0.11408836394548416,
|
2417 |
+
"learning_rate": 8.909730363423214e-06,
|
2418 |
+
"loss": 0.0161,
|
2419 |
+
"step": 1630
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 1.9164835164835163,
|
2423 |
+
"grad_norm": 0.06911155581474304,
|
2424 |
+
"learning_rate": 8.32356389214537e-06,
|
2425 |
+
"loss": 0.0154,
|
2426 |
+
"step": 1635
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 1.9223443223443224,
|
2430 |
+
"grad_norm": 0.11621779948472977,
|
2431 |
+
"learning_rate": 7.737397420867527e-06,
|
2432 |
+
"loss": 0.0144,
|
2433 |
+
"step": 1640
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 1.9282051282051282,
|
2437 |
+
"grad_norm": 0.046058397740125656,
|
2438 |
+
"learning_rate": 7.151230949589684e-06,
|
2439 |
+
"loss": 0.0093,
|
2440 |
+
"step": 1645
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 1.934065934065934,
|
2444 |
+
"grad_norm": 0.11228576302528381,
|
2445 |
+
"learning_rate": 6.565064478311841e-06,
|
2446 |
+
"loss": 0.022,
|
2447 |
+
"step": 1650
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 1.93992673992674,
|
2451 |
+
"grad_norm": 0.1315338909626007,
|
2452 |
+
"learning_rate": 5.978898007033998e-06,
|
2453 |
+
"loss": 0.0193,
|
2454 |
+
"step": 1655
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 1.9457875457875458,
|
2458 |
+
"grad_norm": 0.040056392550468445,
|
2459 |
+
"learning_rate": 5.3927315357561546e-06,
|
2460 |
+
"loss": 0.0132,
|
2461 |
+
"step": 1660
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 1.9516483516483516,
|
2465 |
+
"grad_norm": 0.10741738229990005,
|
2466 |
+
"learning_rate": 4.806565064478312e-06,
|
2467 |
+
"loss": 0.0352,
|
2468 |
+
"step": 1665
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 1.9575091575091577,
|
2472 |
+
"grad_norm": 0.059029560536146164,
|
2473 |
+
"learning_rate": 4.220398593200469e-06,
|
2474 |
+
"loss": 0.019,
|
2475 |
+
"step": 1670
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 1.9633699633699635,
|
2479 |
+
"grad_norm": 0.06789711117744446,
|
2480 |
+
"learning_rate": 3.6342321219226262e-06,
|
2481 |
+
"loss": 0.0189,
|
2482 |
+
"step": 1675
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 1.9692307692307693,
|
2486 |
+
"grad_norm": 0.02918117679655552,
|
2487 |
+
"learning_rate": 3.0480656506447833e-06,
|
2488 |
+
"loss": 0.0259,
|
2489 |
+
"step": 1680
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 1.9750915750915752,
|
2493 |
+
"grad_norm": 0.08073403686285019,
|
2494 |
+
"learning_rate": 2.4618991793669404e-06,
|
2495 |
+
"loss": 0.0286,
|
2496 |
+
"step": 1685
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 1.980952380952381,
|
2500 |
+
"grad_norm": 0.1617717295885086,
|
2501 |
+
"learning_rate": 1.8757327080890972e-06,
|
2502 |
+
"loss": 0.0191,
|
2503 |
+
"step": 1690
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 1.9868131868131869,
|
2507 |
+
"grad_norm": 0.06613462418317795,
|
2508 |
+
"learning_rate": 1.2895662368112545e-06,
|
2509 |
+
"loss": 0.0128,
|
2510 |
+
"step": 1695
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 1.9926739926739927,
|
2514 |
+
"grad_norm": 0.08398256450891495,
|
2515 |
+
"learning_rate": 7.033997655334116e-07,
|
2516 |
+
"loss": 0.0118,
|
2517 |
+
"step": 1700
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 1.9926739926739927,
|
2521 |
+
"eval_loss": 0.018166696652770042,
|
2522 |
+
"eval_runtime": 4.6959,
|
2523 |
+
"eval_samples_per_second": 5.963,
|
2524 |
+
"eval_steps_per_second": 2.981,
|
2525 |
+
"step": 1700
|
2526 |
+
},
|
2527 |
+
{
|
2528 |
+
"epoch": 1.9985347985347985,
|
2529 |
+
"grad_norm": 0.0773661658167839,
|
2530 |
+
"learning_rate": 1.1723329425556858e-07,
|
2531 |
+
"loss": 0.0146,
|
2532 |
+
"step": 1705
|
2533 |
+
}
|
2534 |
+
],
|
2535 |
+
"logging_steps": 5,
|
2536 |
+
"max_steps": 1706,
|
2537 |
+
"num_input_tokens_seen": 0,
|
2538 |
+
"num_train_epochs": 2,
|
2539 |
+
"save_steps": 1000,
|
2540 |
+
"stateful_callbacks": {
|
2541 |
+
"TrainerControl": {
|
2542 |
+
"args": {
|
2543 |
+
"should_epoch_stop": false,
|
2544 |
+
"should_evaluate": false,
|
2545 |
+
"should_log": false,
|
2546 |
+
"should_save": true,
|
2547 |
+
"should_training_stop": true
|
2548 |
+
},
|
2549 |
+
"attributes": {}
|
2550 |
+
}
|
2551 |
+
},
|
2552 |
+
"total_flos": 5.764499308335456e+16,
|
2553 |
+
"train_batch_size": 2,
|
2554 |
+
"trial_name": null,
|
2555 |
+
"trial_params": null
|
2556 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a1417d5a273a397df996a9b4c569c3bc6e83978393843d305b311edfe15d0c4
|
3 |
+
size 5112
|