Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- checkpoint-1600/README.md +202 -0
- checkpoint-1600/adapter_config.json +31 -0
- checkpoint-1600/adapter_model.safetensors +3 -0
- checkpoint-1600/optimizer.pt +3 -0
- checkpoint-1600/rng_state.pth +3 -0
- checkpoint-1600/scheduler.pt +3 -0
- checkpoint-1600/special_tokens_map.json +24 -0
- checkpoint-1600/tokenizer.json +0 -0
- checkpoint-1600/tokenizer.model +3 -0
- checkpoint-1600/tokenizer_config.json +43 -0
- checkpoint-1600/trainer_state.json +2268 -0
- checkpoint-1600/training_args.bin +3 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83946192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb52ae0ef26354f737e1c2d1f620f177f5fb457e78095521a808722d826cfc1
|
3 |
size 83946192
|
checkpoint-1600/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
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 0.7.1
|
checkpoint-1600/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"up_proj",
|
23 |
+
"o_proj",
|
24 |
+
"down_proj",
|
25 |
+
"k_proj",
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
checkpoint-1600/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb52ae0ef26354f737e1c2d1f620f177f5fb457e78095521a808722d826cfc1
|
3 |
+
size 83946192
|
checkpoint-1600/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10ea142ba6c50c3f1583b32e1419e5fea2b782d3aa7dc4d0b5566d92e3f10bd5
|
3 |
+
size 168150290
|
checkpoint-1600/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a19ce04a9f95ddd2a3a40b8a562310e461447df0aa4cbe8ab42fe56bbf55a56
|
3 |
+
size 14244
|
checkpoint-1600/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9da39c74f88089b89526194ade149399b2c62f9c2c049cb11ec90968f894bea0
|
3 |
+
size 1064
|
checkpoint-1600/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-1600/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1600/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-1600/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
checkpoint-1600/trainer_state.json
ADDED
@@ -0,0 +1,2268 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23758259707476428,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1600,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 1.75,
|
14 |
+
"learning_rate": 2.9673590504451043e-07,
|
15 |
+
"loss": 1.433,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 1.578125,
|
21 |
+
"learning_rate": 1.483679525222552e-06,
|
22 |
+
"loss": 1.5006,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 1.4921875,
|
28 |
+
"learning_rate": 2.967359050445104e-06,
|
29 |
+
"loss": 1.4919,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0,
|
34 |
+
"grad_norm": 1.4921875,
|
35 |
+
"learning_rate": 4.451038575667656e-06,
|
36 |
+
"loss": 1.4531,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0,
|
41 |
+
"grad_norm": 1.0234375,
|
42 |
+
"learning_rate": 5.934718100890208e-06,
|
43 |
+
"loss": 1.4242,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"grad_norm": 0.9453125,
|
49 |
+
"learning_rate": 7.418397626112759e-06,
|
50 |
+
"loss": 1.3932,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"grad_norm": 0.8359375,
|
56 |
+
"learning_rate": 8.902077151335312e-06,
|
57 |
+
"loss": 1.3661,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.01,
|
62 |
+
"grad_norm": 0.828125,
|
63 |
+
"learning_rate": 1.0385756676557864e-05,
|
64 |
+
"loss": 1.3677,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.01,
|
69 |
+
"grad_norm": 0.59375,
|
70 |
+
"learning_rate": 1.1869436201780416e-05,
|
71 |
+
"loss": 1.3497,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.01,
|
76 |
+
"grad_norm": 0.56640625,
|
77 |
+
"learning_rate": 1.3353115727002968e-05,
|
78 |
+
"loss": 1.3049,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.01,
|
83 |
+
"grad_norm": 0.439453125,
|
84 |
+
"learning_rate": 1.4836795252225518e-05,
|
85 |
+
"loss": 1.2836,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"grad_norm": 0.46484375,
|
91 |
+
"learning_rate": 1.6320474777448072e-05,
|
92 |
+
"loss": 1.3133,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.01,
|
97 |
+
"grad_norm": 0.40625,
|
98 |
+
"learning_rate": 1.7804154302670624e-05,
|
99 |
+
"loss": 1.2596,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.01,
|
104 |
+
"grad_norm": 0.408203125,
|
105 |
+
"learning_rate": 1.9287833827893176e-05,
|
106 |
+
"loss": 1.2612,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.01,
|
111 |
+
"grad_norm": 0.376953125,
|
112 |
+
"learning_rate": 2.0771513353115728e-05,
|
113 |
+
"loss": 1.2584,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.01,
|
118 |
+
"grad_norm": 0.40625,
|
119 |
+
"learning_rate": 2.225519287833828e-05,
|
120 |
+
"loss": 1.2386,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.01,
|
125 |
+
"grad_norm": 0.353515625,
|
126 |
+
"learning_rate": 2.3738872403560832e-05,
|
127 |
+
"loss": 1.1833,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01,
|
132 |
+
"grad_norm": 0.349609375,
|
133 |
+
"learning_rate": 2.5222551928783384e-05,
|
134 |
+
"loss": 1.2411,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01,
|
139 |
+
"grad_norm": 0.36328125,
|
140 |
+
"learning_rate": 2.6706231454005936e-05,
|
141 |
+
"loss": 1.1956,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.01,
|
146 |
+
"grad_norm": 0.369140625,
|
147 |
+
"learning_rate": 2.818991097922849e-05,
|
148 |
+
"loss": 1.2327,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.01,
|
153 |
+
"grad_norm": 0.353515625,
|
154 |
+
"learning_rate": 2.9673590504451037e-05,
|
155 |
+
"loss": 1.1896,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.02,
|
160 |
+
"grad_norm": 0.3984375,
|
161 |
+
"learning_rate": 3.115727002967359e-05,
|
162 |
+
"loss": 1.1979,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02,
|
167 |
+
"grad_norm": 0.388671875,
|
168 |
+
"learning_rate": 3.2640949554896144e-05,
|
169 |
+
"loss": 1.2004,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.02,
|
174 |
+
"grad_norm": 0.392578125,
|
175 |
+
"learning_rate": 3.41246290801187e-05,
|
176 |
+
"loss": 1.1624,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.02,
|
181 |
+
"grad_norm": 0.400390625,
|
182 |
+
"learning_rate": 3.560830860534125e-05,
|
183 |
+
"loss": 1.1914,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.02,
|
188 |
+
"grad_norm": 0.41796875,
|
189 |
+
"learning_rate": 3.70919881305638e-05,
|
190 |
+
"loss": 1.1952,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.02,
|
195 |
+
"grad_norm": 0.4140625,
|
196 |
+
"learning_rate": 3.857566765578635e-05,
|
197 |
+
"loss": 1.1538,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.02,
|
202 |
+
"grad_norm": 0.4375,
|
203 |
+
"learning_rate": 4.005934718100891e-05,
|
204 |
+
"loss": 1.1702,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.02,
|
209 |
+
"grad_norm": 0.44140625,
|
210 |
+
"learning_rate": 4.1543026706231456e-05,
|
211 |
+
"loss": 1.1683,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.02,
|
216 |
+
"grad_norm": 0.443359375,
|
217 |
+
"learning_rate": 4.3026706231454005e-05,
|
218 |
+
"loss": 1.1822,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.02,
|
223 |
+
"grad_norm": 0.482421875,
|
224 |
+
"learning_rate": 4.451038575667656e-05,
|
225 |
+
"loss": 1.1649,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.02,
|
230 |
+
"grad_norm": 0.46484375,
|
231 |
+
"learning_rate": 4.5994065281899116e-05,
|
232 |
+
"loss": 1.1868,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.02,
|
237 |
+
"grad_norm": 0.5,
|
238 |
+
"learning_rate": 4.7477744807121664e-05,
|
239 |
+
"loss": 1.161,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.02,
|
244 |
+
"grad_norm": 0.451171875,
|
245 |
+
"learning_rate": 4.896142433234421e-05,
|
246 |
+
"loss": 1.1454,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.03,
|
251 |
+
"grad_norm": 0.45703125,
|
252 |
+
"learning_rate": 5.044510385756677e-05,
|
253 |
+
"loss": 1.1388,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.03,
|
258 |
+
"grad_norm": 0.490234375,
|
259 |
+
"learning_rate": 5.1928783382789324e-05,
|
260 |
+
"loss": 1.1253,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.03,
|
265 |
+
"grad_norm": 0.51171875,
|
266 |
+
"learning_rate": 5.341246290801187e-05,
|
267 |
+
"loss": 1.1527,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.03,
|
272 |
+
"grad_norm": 0.486328125,
|
273 |
+
"learning_rate": 5.489614243323442e-05,
|
274 |
+
"loss": 1.1234,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.03,
|
279 |
+
"grad_norm": 0.46875,
|
280 |
+
"learning_rate": 5.637982195845698e-05,
|
281 |
+
"loss": 1.113,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.03,
|
286 |
+
"grad_norm": 0.458984375,
|
287 |
+
"learning_rate": 5.7863501483679525e-05,
|
288 |
+
"loss": 1.1368,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.03,
|
293 |
+
"grad_norm": 0.484375,
|
294 |
+
"learning_rate": 5.9347181008902074e-05,
|
295 |
+
"loss": 1.137,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.03,
|
300 |
+
"grad_norm": 0.4765625,
|
301 |
+
"learning_rate": 6.0830860534124636e-05,
|
302 |
+
"loss": 1.1286,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.03,
|
307 |
+
"grad_norm": 0.484375,
|
308 |
+
"learning_rate": 6.231454005934718e-05,
|
309 |
+
"loss": 1.1277,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.03,
|
314 |
+
"grad_norm": 0.474609375,
|
315 |
+
"learning_rate": 6.379821958456974e-05,
|
316 |
+
"loss": 1.1268,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.03,
|
321 |
+
"grad_norm": 0.47265625,
|
322 |
+
"learning_rate": 6.528189910979229e-05,
|
323 |
+
"loss": 1.0993,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.03,
|
328 |
+
"grad_norm": 0.50390625,
|
329 |
+
"learning_rate": 6.676557863501484e-05,
|
330 |
+
"loss": 1.1017,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.03,
|
335 |
+
"grad_norm": 0.4609375,
|
336 |
+
"learning_rate": 6.82492581602374e-05,
|
337 |
+
"loss": 1.1345,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.03,
|
342 |
+
"grad_norm": 0.48828125,
|
343 |
+
"learning_rate": 6.973293768545995e-05,
|
344 |
+
"loss": 1.1086,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.04,
|
349 |
+
"grad_norm": 0.45703125,
|
350 |
+
"learning_rate": 7.12166172106825e-05,
|
351 |
+
"loss": 1.0791,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.04,
|
356 |
+
"grad_norm": 0.470703125,
|
357 |
+
"learning_rate": 7.270029673590505e-05,
|
358 |
+
"loss": 1.1158,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.04,
|
363 |
+
"grad_norm": 0.46875,
|
364 |
+
"learning_rate": 7.41839762611276e-05,
|
365 |
+
"loss": 1.132,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.04,
|
370 |
+
"grad_norm": 0.4609375,
|
371 |
+
"learning_rate": 7.566765578635016e-05,
|
372 |
+
"loss": 1.1438,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.04,
|
377 |
+
"grad_norm": 0.470703125,
|
378 |
+
"learning_rate": 7.71513353115727e-05,
|
379 |
+
"loss": 1.1405,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.04,
|
384 |
+
"grad_norm": 0.447265625,
|
385 |
+
"learning_rate": 7.863501483679525e-05,
|
386 |
+
"loss": 1.1124,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.04,
|
391 |
+
"grad_norm": 0.486328125,
|
392 |
+
"learning_rate": 8.011869436201782e-05,
|
393 |
+
"loss": 1.0813,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.04,
|
398 |
+
"grad_norm": 0.48046875,
|
399 |
+
"learning_rate": 8.160237388724036e-05,
|
400 |
+
"loss": 1.1194,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.04,
|
405 |
+
"grad_norm": 0.462890625,
|
406 |
+
"learning_rate": 8.308605341246291e-05,
|
407 |
+
"loss": 1.0927,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.04,
|
412 |
+
"grad_norm": 0.48046875,
|
413 |
+
"learning_rate": 8.456973293768546e-05,
|
414 |
+
"loss": 1.1277,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.04,
|
419 |
+
"grad_norm": 0.4453125,
|
420 |
+
"learning_rate": 8.605341246290801e-05,
|
421 |
+
"loss": 1.1271,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.04,
|
426 |
+
"grad_norm": 0.435546875,
|
427 |
+
"learning_rate": 8.753709198813057e-05,
|
428 |
+
"loss": 1.1162,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.04,
|
433 |
+
"grad_norm": 0.44921875,
|
434 |
+
"learning_rate": 8.902077151335312e-05,
|
435 |
+
"loss": 1.0857,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.05,
|
440 |
+
"grad_norm": 0.4375,
|
441 |
+
"learning_rate": 9.050445103857568e-05,
|
442 |
+
"loss": 1.0869,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.05,
|
447 |
+
"grad_norm": 0.4453125,
|
448 |
+
"learning_rate": 9.198813056379823e-05,
|
449 |
+
"loss": 1.0655,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.05,
|
454 |
+
"grad_norm": 0.4296875,
|
455 |
+
"learning_rate": 9.347181008902077e-05,
|
456 |
+
"loss": 1.0585,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.05,
|
461 |
+
"grad_norm": 0.41796875,
|
462 |
+
"learning_rate": 9.495548961424333e-05,
|
463 |
+
"loss": 1.1144,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.05,
|
468 |
+
"grad_norm": 0.43359375,
|
469 |
+
"learning_rate": 9.643916913946588e-05,
|
470 |
+
"loss": 1.0719,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.05,
|
475 |
+
"grad_norm": 0.416015625,
|
476 |
+
"learning_rate": 9.792284866468843e-05,
|
477 |
+
"loss": 1.0919,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.05,
|
482 |
+
"grad_norm": 0.423828125,
|
483 |
+
"learning_rate": 9.940652818991099e-05,
|
484 |
+
"loss": 1.1223,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.05,
|
489 |
+
"grad_norm": 0.431640625,
|
490 |
+
"learning_rate": 0.00010089020771513354,
|
491 |
+
"loss": 1.0565,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.05,
|
496 |
+
"grad_norm": 0.431640625,
|
497 |
+
"learning_rate": 0.00010237388724035609,
|
498 |
+
"loss": 1.0962,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.05,
|
503 |
+
"grad_norm": 0.44921875,
|
504 |
+
"learning_rate": 0.00010385756676557865,
|
505 |
+
"loss": 1.0959,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.05,
|
510 |
+
"grad_norm": 0.43359375,
|
511 |
+
"learning_rate": 0.0001053412462908012,
|
512 |
+
"loss": 1.0628,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.05,
|
517 |
+
"grad_norm": 0.431640625,
|
518 |
+
"learning_rate": 0.00010682492581602374,
|
519 |
+
"loss": 1.0975,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.05,
|
524 |
+
"grad_norm": 0.42578125,
|
525 |
+
"learning_rate": 0.0001083086053412463,
|
526 |
+
"loss": 1.0727,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.05,
|
531 |
+
"grad_norm": 0.416015625,
|
532 |
+
"learning_rate": 0.00010979228486646884,
|
533 |
+
"loss": 1.0649,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.06,
|
538 |
+
"grad_norm": 0.4296875,
|
539 |
+
"learning_rate": 0.00011127596439169139,
|
540 |
+
"loss": 1.0904,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.06,
|
545 |
+
"grad_norm": 0.3984375,
|
546 |
+
"learning_rate": 0.00011275964391691397,
|
547 |
+
"loss": 1.079,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.06,
|
552 |
+
"grad_norm": 0.40234375,
|
553 |
+
"learning_rate": 0.0001142433234421365,
|
554 |
+
"loss": 1.0522,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.06,
|
559 |
+
"grad_norm": 0.431640625,
|
560 |
+
"learning_rate": 0.00011572700296735905,
|
561 |
+
"loss": 1.0579,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.06,
|
566 |
+
"grad_norm": 0.396484375,
|
567 |
+
"learning_rate": 0.0001172106824925816,
|
568 |
+
"loss": 1.0871,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.06,
|
573 |
+
"grad_norm": 0.41015625,
|
574 |
+
"learning_rate": 0.00011869436201780415,
|
575 |
+
"loss": 1.0936,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.06,
|
580 |
+
"grad_norm": 0.412109375,
|
581 |
+
"learning_rate": 0.00012017804154302672,
|
582 |
+
"loss": 1.0734,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.06,
|
587 |
+
"grad_norm": 0.392578125,
|
588 |
+
"learning_rate": 0.00012166172106824927,
|
589 |
+
"loss": 1.0657,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.06,
|
594 |
+
"grad_norm": 0.4140625,
|
595 |
+
"learning_rate": 0.00012314540059347182,
|
596 |
+
"loss": 1.0884,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.06,
|
601 |
+
"grad_norm": 0.408203125,
|
602 |
+
"learning_rate": 0.00012462908011869436,
|
603 |
+
"loss": 1.0683,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.06,
|
608 |
+
"grad_norm": 0.3984375,
|
609 |
+
"learning_rate": 0.00012611275964391692,
|
610 |
+
"loss": 1.1073,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.06,
|
615 |
+
"grad_norm": 0.412109375,
|
616 |
+
"learning_rate": 0.00012759643916913948,
|
617 |
+
"loss": 1.0849,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.06,
|
622 |
+
"grad_norm": 0.40625,
|
623 |
+
"learning_rate": 0.00012908011869436204,
|
624 |
+
"loss": 1.0798,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.07,
|
629 |
+
"grad_norm": 0.404296875,
|
630 |
+
"learning_rate": 0.00013056379821958458,
|
631 |
+
"loss": 1.1029,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.07,
|
636 |
+
"grad_norm": 0.3828125,
|
637 |
+
"learning_rate": 0.0001320474777448071,
|
638 |
+
"loss": 1.0664,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.07,
|
643 |
+
"grad_norm": 0.38671875,
|
644 |
+
"learning_rate": 0.00013353115727002967,
|
645 |
+
"loss": 1.0998,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.07,
|
650 |
+
"grad_norm": 0.40234375,
|
651 |
+
"learning_rate": 0.00013501483679525224,
|
652 |
+
"loss": 1.0834,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.07,
|
657 |
+
"grad_norm": 0.400390625,
|
658 |
+
"learning_rate": 0.0001364985163204748,
|
659 |
+
"loss": 1.062,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.07,
|
664 |
+
"grad_norm": 0.3984375,
|
665 |
+
"learning_rate": 0.00013798219584569733,
|
666 |
+
"loss": 1.0825,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.07,
|
671 |
+
"grad_norm": 0.388671875,
|
672 |
+
"learning_rate": 0.0001394658753709199,
|
673 |
+
"loss": 1.0689,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.07,
|
678 |
+
"grad_norm": 0.392578125,
|
679 |
+
"learning_rate": 0.00014094955489614243,
|
680 |
+
"loss": 1.0557,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.07,
|
685 |
+
"grad_norm": 0.380859375,
|
686 |
+
"learning_rate": 0.000142433234421365,
|
687 |
+
"loss": 1.0582,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.07,
|
692 |
+
"grad_norm": 0.380859375,
|
693 |
+
"learning_rate": 0.00014391691394658756,
|
694 |
+
"loss": 1.0921,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.07,
|
699 |
+
"grad_norm": 0.384765625,
|
700 |
+
"learning_rate": 0.0001454005934718101,
|
701 |
+
"loss": 1.0544,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.07,
|
706 |
+
"grad_norm": 0.39453125,
|
707 |
+
"learning_rate": 0.00014688427299703265,
|
708 |
+
"loss": 1.0333,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.07,
|
713 |
+
"grad_norm": 0.384765625,
|
714 |
+
"learning_rate": 0.0001483679525222552,
|
715 |
+
"loss": 1.0454,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.07,
|
720 |
+
"grad_norm": 0.37890625,
|
721 |
+
"learning_rate": 0.00014985163204747775,
|
722 |
+
"loss": 1.0434,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.08,
|
727 |
+
"grad_norm": 0.390625,
|
728 |
+
"learning_rate": 0.0001513353115727003,
|
729 |
+
"loss": 1.0768,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.08,
|
734 |
+
"grad_norm": 0.376953125,
|
735 |
+
"learning_rate": 0.00015281899109792285,
|
736 |
+
"loss": 1.0774,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.08,
|
741 |
+
"grad_norm": 0.365234375,
|
742 |
+
"learning_rate": 0.0001543026706231454,
|
743 |
+
"loss": 1.0438,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.08,
|
748 |
+
"grad_norm": 0.373046875,
|
749 |
+
"learning_rate": 0.00015578635014836794,
|
750 |
+
"loss": 1.0573,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.08,
|
755 |
+
"grad_norm": 0.380859375,
|
756 |
+
"learning_rate": 0.0001572700296735905,
|
757 |
+
"loss": 1.0501,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.08,
|
762 |
+
"grad_norm": 0.392578125,
|
763 |
+
"learning_rate": 0.00015875370919881307,
|
764 |
+
"loss": 1.0413,
|
765 |
+
"step": 535
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.08,
|
769 |
+
"grad_norm": 0.37109375,
|
770 |
+
"learning_rate": 0.00016023738872403563,
|
771 |
+
"loss": 1.0234,
|
772 |
+
"step": 540
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.08,
|
776 |
+
"grad_norm": 0.3671875,
|
777 |
+
"learning_rate": 0.00016172106824925817,
|
778 |
+
"loss": 1.0538,
|
779 |
+
"step": 545
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.08,
|
783 |
+
"grad_norm": 0.41015625,
|
784 |
+
"learning_rate": 0.00016320474777448073,
|
785 |
+
"loss": 1.0493,
|
786 |
+
"step": 550
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.08,
|
790 |
+
"grad_norm": 0.35546875,
|
791 |
+
"learning_rate": 0.00016468842729970326,
|
792 |
+
"loss": 1.0686,
|
793 |
+
"step": 555
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.08,
|
797 |
+
"grad_norm": 0.36328125,
|
798 |
+
"learning_rate": 0.00016617210682492583,
|
799 |
+
"loss": 1.0794,
|
800 |
+
"step": 560
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.08,
|
804 |
+
"grad_norm": 0.380859375,
|
805 |
+
"learning_rate": 0.0001676557863501484,
|
806 |
+
"loss": 1.0575,
|
807 |
+
"step": 565
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.08,
|
811 |
+
"grad_norm": 0.37109375,
|
812 |
+
"learning_rate": 0.00016913946587537092,
|
813 |
+
"loss": 1.0682,
|
814 |
+
"step": 570
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.09,
|
818 |
+
"grad_norm": 0.361328125,
|
819 |
+
"learning_rate": 0.00017062314540059348,
|
820 |
+
"loss": 1.0237,
|
821 |
+
"step": 575
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.09,
|
825 |
+
"grad_norm": 0.37109375,
|
826 |
+
"learning_rate": 0.00017210682492581602,
|
827 |
+
"loss": 1.0493,
|
828 |
+
"step": 580
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.09,
|
832 |
+
"grad_norm": 0.361328125,
|
833 |
+
"learning_rate": 0.00017359050445103858,
|
834 |
+
"loss": 1.0613,
|
835 |
+
"step": 585
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.09,
|
839 |
+
"grad_norm": 0.380859375,
|
840 |
+
"learning_rate": 0.00017507418397626114,
|
841 |
+
"loss": 1.0346,
|
842 |
+
"step": 590
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.09,
|
846 |
+
"grad_norm": 0.375,
|
847 |
+
"learning_rate": 0.00017655786350148368,
|
848 |
+
"loss": 1.0749,
|
849 |
+
"step": 595
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.09,
|
853 |
+
"grad_norm": 0.34765625,
|
854 |
+
"learning_rate": 0.00017804154302670624,
|
855 |
+
"loss": 1.0289,
|
856 |
+
"step": 600
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.09,
|
860 |
+
"grad_norm": 0.353515625,
|
861 |
+
"learning_rate": 0.00017952522255192878,
|
862 |
+
"loss": 1.0606,
|
863 |
+
"step": 605
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.09,
|
867 |
+
"grad_norm": 0.36328125,
|
868 |
+
"learning_rate": 0.00018100890207715137,
|
869 |
+
"loss": 1.0166,
|
870 |
+
"step": 610
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.09,
|
874 |
+
"grad_norm": 0.375,
|
875 |
+
"learning_rate": 0.0001824925816023739,
|
876 |
+
"loss": 1.0347,
|
877 |
+
"step": 615
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.09,
|
881 |
+
"grad_norm": 0.3671875,
|
882 |
+
"learning_rate": 0.00018397626112759646,
|
883 |
+
"loss": 1.0388,
|
884 |
+
"step": 620
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.09,
|
888 |
+
"grad_norm": 0.365234375,
|
889 |
+
"learning_rate": 0.000185459940652819,
|
890 |
+
"loss": 1.0545,
|
891 |
+
"step": 625
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.09,
|
895 |
+
"grad_norm": 0.361328125,
|
896 |
+
"learning_rate": 0.00018694362017804153,
|
897 |
+
"loss": 1.0281,
|
898 |
+
"step": 630
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.09,
|
902 |
+
"grad_norm": 0.34765625,
|
903 |
+
"learning_rate": 0.0001884272997032641,
|
904 |
+
"loss": 1.0347,
|
905 |
+
"step": 635
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.1,
|
909 |
+
"grad_norm": 0.353515625,
|
910 |
+
"learning_rate": 0.00018991097922848666,
|
911 |
+
"loss": 1.0347,
|
912 |
+
"step": 640
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.1,
|
916 |
+
"grad_norm": 0.357421875,
|
917 |
+
"learning_rate": 0.00019139465875370922,
|
918 |
+
"loss": 1.0594,
|
919 |
+
"step": 645
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.1,
|
923 |
+
"grad_norm": 0.353515625,
|
924 |
+
"learning_rate": 0.00019287833827893175,
|
925 |
+
"loss": 1.0201,
|
926 |
+
"step": 650
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.1,
|
930 |
+
"grad_norm": 0.384765625,
|
931 |
+
"learning_rate": 0.00019436201780415432,
|
932 |
+
"loss": 1.0287,
|
933 |
+
"step": 655
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.1,
|
937 |
+
"grad_norm": 0.359375,
|
938 |
+
"learning_rate": 0.00019584569732937685,
|
939 |
+
"loss": 1.0777,
|
940 |
+
"step": 660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.1,
|
944 |
+
"grad_norm": 0.349609375,
|
945 |
+
"learning_rate": 0.00019732937685459941,
|
946 |
+
"loss": 1.0157,
|
947 |
+
"step": 665
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.1,
|
951 |
+
"grad_norm": 0.349609375,
|
952 |
+
"learning_rate": 0.00019881305637982198,
|
953 |
+
"loss": 1.0474,
|
954 |
+
"step": 670
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.1,
|
958 |
+
"grad_norm": 0.353515625,
|
959 |
+
"learning_rate": 0.0001999999865623139,
|
960 |
+
"loss": 1.0452,
|
961 |
+
"step": 675
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.1,
|
965 |
+
"grad_norm": 0.3828125,
|
966 |
+
"learning_rate": 0.00019999951624367985,
|
967 |
+
"loss": 1.02,
|
968 |
+
"step": 680
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.1,
|
972 |
+
"grad_norm": 0.345703125,
|
973 |
+
"learning_rate": 0.0001999983740443526,
|
974 |
+
"loss": 1.041,
|
975 |
+
"step": 685
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.1,
|
979 |
+
"grad_norm": 0.353515625,
|
980 |
+
"learning_rate": 0.00019999655997200635,
|
981 |
+
"loss": 1.0305,
|
982 |
+
"step": 690
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.1,
|
986 |
+
"grad_norm": 0.359375,
|
987 |
+
"learning_rate": 0.0001999940740388296,
|
988 |
+
"loss": 1.032,
|
989 |
+
"step": 695
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.1,
|
993 |
+
"grad_norm": 0.35546875,
|
994 |
+
"learning_rate": 0.00019999091626152492,
|
995 |
+
"loss": 1.0027,
|
996 |
+
"step": 700
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.1,
|
1000 |
+
"grad_norm": 0.349609375,
|
1001 |
+
"learning_rate": 0.00019998708666130893,
|
1002 |
+
"loss": 1.0311,
|
1003 |
+
"step": 705
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.11,
|
1007 |
+
"grad_norm": 0.37109375,
|
1008 |
+
"learning_rate": 0.00019998258526391207,
|
1009 |
+
"loss": 1.0165,
|
1010 |
+
"step": 710
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.11,
|
1014 |
+
"grad_norm": 0.361328125,
|
1015 |
+
"learning_rate": 0.00019997741209957853,
|
1016 |
+
"loss": 1.013,
|
1017 |
+
"step": 715
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.11,
|
1021 |
+
"grad_norm": 0.357421875,
|
1022 |
+
"learning_rate": 0.00019997156720306597,
|
1023 |
+
"loss": 0.9992,
|
1024 |
+
"step": 720
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.11,
|
1028 |
+
"grad_norm": 0.34765625,
|
1029 |
+
"learning_rate": 0.00019996505061364527,
|
1030 |
+
"loss": 1.044,
|
1031 |
+
"step": 725
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.11,
|
1035 |
+
"grad_norm": 0.55859375,
|
1036 |
+
"learning_rate": 0.0001999578623751004,
|
1037 |
+
"loss": 0.998,
|
1038 |
+
"step": 730
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.11,
|
1042 |
+
"grad_norm": 0.349609375,
|
1043 |
+
"learning_rate": 0.00019995000253572798,
|
1044 |
+
"loss": 1.0354,
|
1045 |
+
"step": 735
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.11,
|
1049 |
+
"grad_norm": 0.353515625,
|
1050 |
+
"learning_rate": 0.00019994147114833698,
|
1051 |
+
"loss": 1.0083,
|
1052 |
+
"step": 740
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.11,
|
1056 |
+
"grad_norm": 0.359375,
|
1057 |
+
"learning_rate": 0.00019993226827024843,
|
1058 |
+
"loss": 1.012,
|
1059 |
+
"step": 745
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.11,
|
1063 |
+
"grad_norm": 0.359375,
|
1064 |
+
"learning_rate": 0.00019992239396329498,
|
1065 |
+
"loss": 0.9953,
|
1066 |
+
"step": 750
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.11,
|
1070 |
+
"grad_norm": 0.3515625,
|
1071 |
+
"learning_rate": 0.00019991184829382057,
|
1072 |
+
"loss": 1.0095,
|
1073 |
+
"step": 755
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.11,
|
1077 |
+
"grad_norm": 0.349609375,
|
1078 |
+
"learning_rate": 0.00019990063133267975,
|
1079 |
+
"loss": 1.0518,
|
1080 |
+
"step": 760
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.11,
|
1084 |
+
"grad_norm": 0.369140625,
|
1085 |
+
"learning_rate": 0.0001998887431552376,
|
1086 |
+
"loss": 1.0357,
|
1087 |
+
"step": 765
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.11,
|
1091 |
+
"grad_norm": 0.359375,
|
1092 |
+
"learning_rate": 0.00019987618384136879,
|
1093 |
+
"loss": 1.0542,
|
1094 |
+
"step": 770
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.12,
|
1098 |
+
"grad_norm": 0.361328125,
|
1099 |
+
"learning_rate": 0.0001998629534754574,
|
1100 |
+
"loss": 1.0071,
|
1101 |
+
"step": 775
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.12,
|
1105 |
+
"grad_norm": 0.34375,
|
1106 |
+
"learning_rate": 0.00019984905214639608,
|
1107 |
+
"loss": 1.0414,
|
1108 |
+
"step": 780
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.12,
|
1112 |
+
"grad_norm": 0.376953125,
|
1113 |
+
"learning_rate": 0.00019983447994758563,
|
1114 |
+
"loss": 1.003,
|
1115 |
+
"step": 785
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.12,
|
1119 |
+
"grad_norm": 0.3515625,
|
1120 |
+
"learning_rate": 0.00019981923697693437,
|
1121 |
+
"loss": 1.0482,
|
1122 |
+
"step": 790
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.12,
|
1126 |
+
"grad_norm": 0.361328125,
|
1127 |
+
"learning_rate": 0.00019980332333685729,
|
1128 |
+
"loss": 1.0394,
|
1129 |
+
"step": 795
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.12,
|
1133 |
+
"grad_norm": 0.353515625,
|
1134 |
+
"learning_rate": 0.00019978673913427568,
|
1135 |
+
"loss": 0.985,
|
1136 |
+
"step": 800
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.12,
|
1140 |
+
"grad_norm": 0.33984375,
|
1141 |
+
"learning_rate": 0.00019976948448061603,
|
1142 |
+
"loss": 1.0149,
|
1143 |
+
"step": 805
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.12,
|
1147 |
+
"grad_norm": 0.345703125,
|
1148 |
+
"learning_rate": 0.00019975155949180967,
|
1149 |
+
"loss": 1.0253,
|
1150 |
+
"step": 810
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.12,
|
1154 |
+
"grad_norm": 0.34765625,
|
1155 |
+
"learning_rate": 0.00019973296428829168,
|
1156 |
+
"loss": 1.0067,
|
1157 |
+
"step": 815
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.12,
|
1161 |
+
"grad_norm": 0.3515625,
|
1162 |
+
"learning_rate": 0.00019971369899500024,
|
1163 |
+
"loss": 1.013,
|
1164 |
+
"step": 820
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.12,
|
1168 |
+
"grad_norm": 0.3515625,
|
1169 |
+
"learning_rate": 0.00019969376374137578,
|
1170 |
+
"loss": 1.0253,
|
1171 |
+
"step": 825
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.12,
|
1175 |
+
"grad_norm": 0.345703125,
|
1176 |
+
"learning_rate": 0.0001996731586613601,
|
1177 |
+
"loss": 1.0505,
|
1178 |
+
"step": 830
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.12,
|
1182 |
+
"grad_norm": 0.3671875,
|
1183 |
+
"learning_rate": 0.00019965188389339537,
|
1184 |
+
"loss": 1.0199,
|
1185 |
+
"step": 835
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.12,
|
1189 |
+
"grad_norm": 0.345703125,
|
1190 |
+
"learning_rate": 0.00019962993958042336,
|
1191 |
+
"loss": 1.0066,
|
1192 |
+
"step": 840
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.13,
|
1196 |
+
"grad_norm": 0.33203125,
|
1197 |
+
"learning_rate": 0.00019960732586988438,
|
1198 |
+
"loss": 1.0226,
|
1199 |
+
"step": 845
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.13,
|
1203 |
+
"grad_norm": 0.345703125,
|
1204 |
+
"learning_rate": 0.00019958404291371635,
|
1205 |
+
"loss": 0.9902,
|
1206 |
+
"step": 850
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.13,
|
1210 |
+
"grad_norm": 0.365234375,
|
1211 |
+
"learning_rate": 0.0001995600908683537,
|
1212 |
+
"loss": 1.0338,
|
1213 |
+
"step": 855
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.13,
|
1217 |
+
"grad_norm": 0.349609375,
|
1218 |
+
"learning_rate": 0.00019953546989472633,
|
1219 |
+
"loss": 1.0103,
|
1220 |
+
"step": 860
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.13,
|
1224 |
+
"grad_norm": 0.3515625,
|
1225 |
+
"learning_rate": 0.00019951018015825866,
|
1226 |
+
"loss": 1.0237,
|
1227 |
+
"step": 865
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.13,
|
1231 |
+
"grad_norm": 0.349609375,
|
1232 |
+
"learning_rate": 0.00019948422182886833,
|
1233 |
+
"loss": 0.972,
|
1234 |
+
"step": 870
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.13,
|
1238 |
+
"grad_norm": 0.357421875,
|
1239 |
+
"learning_rate": 0.00019945759508096527,
|
1240 |
+
"loss": 1.0472,
|
1241 |
+
"step": 875
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.13,
|
1245 |
+
"grad_norm": 0.34765625,
|
1246 |
+
"learning_rate": 0.00019943030009345023,
|
1247 |
+
"loss": 1.0156,
|
1248 |
+
"step": 880
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.13,
|
1252 |
+
"grad_norm": 0.3515625,
|
1253 |
+
"learning_rate": 0.00019940233704971388,
|
1254 |
+
"loss": 1.0365,
|
1255 |
+
"step": 885
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.13,
|
1259 |
+
"grad_norm": 0.33984375,
|
1260 |
+
"learning_rate": 0.00019937370613763543,
|
1261 |
+
"loss": 1.0098,
|
1262 |
+
"step": 890
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.13,
|
1266 |
+
"grad_norm": 0.33203125,
|
1267 |
+
"learning_rate": 0.00019934440754958136,
|
1268 |
+
"loss": 1.0042,
|
1269 |
+
"step": 895
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.13,
|
1273 |
+
"grad_norm": 0.33984375,
|
1274 |
+
"learning_rate": 0.00019931444148240423,
|
1275 |
+
"loss": 1.0053,
|
1276 |
+
"step": 900
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.13,
|
1280 |
+
"grad_norm": 0.353515625,
|
1281 |
+
"learning_rate": 0.00019928380813744119,
|
1282 |
+
"loss": 1.0311,
|
1283 |
+
"step": 905
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.14,
|
1287 |
+
"grad_norm": 0.345703125,
|
1288 |
+
"learning_rate": 0.00019925250772051276,
|
1289 |
+
"loss": 0.9973,
|
1290 |
+
"step": 910
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.14,
|
1294 |
+
"grad_norm": 0.353515625,
|
1295 |
+
"learning_rate": 0.00019922054044192145,
|
1296 |
+
"loss": 1.0023,
|
1297 |
+
"step": 915
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.14,
|
1301 |
+
"grad_norm": 0.341796875,
|
1302 |
+
"learning_rate": 0.00019918790651645023,
|
1303 |
+
"loss": 1.0097,
|
1304 |
+
"step": 920
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.14,
|
1308 |
+
"grad_norm": 0.34375,
|
1309 |
+
"learning_rate": 0.00019915460616336126,
|
1310 |
+
"loss": 1.013,
|
1311 |
+
"step": 925
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.14,
|
1315 |
+
"grad_norm": 0.34765625,
|
1316 |
+
"learning_rate": 0.0001991206396063942,
|
1317 |
+
"loss": 0.9989,
|
1318 |
+
"step": 930
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.14,
|
1322 |
+
"grad_norm": 0.34375,
|
1323 |
+
"learning_rate": 0.00019908600707376495,
|
1324 |
+
"loss": 0.9815,
|
1325 |
+
"step": 935
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.14,
|
1329 |
+
"grad_norm": 0.3515625,
|
1330 |
+
"learning_rate": 0.0001990507087981639,
|
1331 |
+
"loss": 0.9753,
|
1332 |
+
"step": 940
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.14,
|
1336 |
+
"grad_norm": 0.33984375,
|
1337 |
+
"learning_rate": 0.0001990147450167545,
|
1338 |
+
"loss": 1.0145,
|
1339 |
+
"step": 945
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.14,
|
1343 |
+
"grad_norm": 0.35546875,
|
1344 |
+
"learning_rate": 0.00019897811597117168,
|
1345 |
+
"loss": 1.0359,
|
1346 |
+
"step": 950
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.14,
|
1350 |
+
"grad_norm": 0.333984375,
|
1351 |
+
"learning_rate": 0.00019894082190751998,
|
1352 |
+
"loss": 0.9902,
|
1353 |
+
"step": 955
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.14,
|
1357 |
+
"grad_norm": 0.349609375,
|
1358 |
+
"learning_rate": 0.00019890286307637237,
|
1359 |
+
"loss": 0.9997,
|
1360 |
+
"step": 960
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.14,
|
1364 |
+
"grad_norm": 0.33984375,
|
1365 |
+
"learning_rate": 0.0001988642397327681,
|
1366 |
+
"loss": 1.0412,
|
1367 |
+
"step": 965
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.14,
|
1371 |
+
"grad_norm": 0.33984375,
|
1372 |
+
"learning_rate": 0.00019882495213621116,
|
1373 |
+
"loss": 0.9552,
|
1374 |
+
"step": 970
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.14,
|
1378 |
+
"grad_norm": 0.3515625,
|
1379 |
+
"learning_rate": 0.00019878500055066866,
|
1380 |
+
"loss": 0.9901,
|
1381 |
+
"step": 975
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.15,
|
1385 |
+
"grad_norm": 0.337890625,
|
1386 |
+
"learning_rate": 0.00019874438524456888,
|
1387 |
+
"loss": 1.035,
|
1388 |
+
"step": 980
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.15,
|
1392 |
+
"grad_norm": 0.34765625,
|
1393 |
+
"learning_rate": 0.0001987031064907995,
|
1394 |
+
"loss": 0.996,
|
1395 |
+
"step": 985
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.15,
|
1399 |
+
"grad_norm": 0.333984375,
|
1400 |
+
"learning_rate": 0.0001986611645667059,
|
1401 |
+
"loss": 1.0248,
|
1402 |
+
"step": 990
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.15,
|
1406 |
+
"grad_norm": 0.3515625,
|
1407 |
+
"learning_rate": 0.0001986185597540891,
|
1408 |
+
"loss": 0.9889,
|
1409 |
+
"step": 995
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.15,
|
1413 |
+
"grad_norm": 0.341796875,
|
1414 |
+
"learning_rate": 0.00019857529233920397,
|
1415 |
+
"loss": 1.0151,
|
1416 |
+
"step": 1000
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.15,
|
1420 |
+
"grad_norm": 0.3671875,
|
1421 |
+
"learning_rate": 0.00019853136261275737,
|
1422 |
+
"loss": 0.9882,
|
1423 |
+
"step": 1005
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.15,
|
1427 |
+
"grad_norm": 0.33984375,
|
1428 |
+
"learning_rate": 0.00019848677086990605,
|
1429 |
+
"loss": 1.0051,
|
1430 |
+
"step": 1010
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.15,
|
1434 |
+
"grad_norm": 0.34375,
|
1435 |
+
"learning_rate": 0.0001984415174102548,
|
1436 |
+
"loss": 0.9904,
|
1437 |
+
"step": 1015
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.15,
|
1441 |
+
"grad_norm": 0.34765625,
|
1442 |
+
"learning_rate": 0.0001983956025378543,
|
1443 |
+
"loss": 0.9899,
|
1444 |
+
"step": 1020
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.15,
|
1448 |
+
"grad_norm": 0.341796875,
|
1449 |
+
"learning_rate": 0.00019834902656119924,
|
1450 |
+
"loss": 0.999,
|
1451 |
+
"step": 1025
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.15,
|
1455 |
+
"grad_norm": 0.3515625,
|
1456 |
+
"learning_rate": 0.00019830178979322614,
|
1457 |
+
"loss": 0.9798,
|
1458 |
+
"step": 1030
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.15,
|
1462 |
+
"grad_norm": 0.349609375,
|
1463 |
+
"learning_rate": 0.00019825389255131125,
|
1464 |
+
"loss": 0.984,
|
1465 |
+
"step": 1035
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.15,
|
1469 |
+
"grad_norm": 0.34765625,
|
1470 |
+
"learning_rate": 0.0001982053351572684,
|
1471 |
+
"loss": 1.0014,
|
1472 |
+
"step": 1040
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.16,
|
1476 |
+
"grad_norm": 0.345703125,
|
1477 |
+
"learning_rate": 0.000198156117937347,
|
1478 |
+
"loss": 1.0148,
|
1479 |
+
"step": 1045
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.16,
|
1483 |
+
"grad_norm": 0.330078125,
|
1484 |
+
"learning_rate": 0.0001981062412222296,
|
1485 |
+
"loss": 1.0271,
|
1486 |
+
"step": 1050
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.16,
|
1490 |
+
"grad_norm": 0.341796875,
|
1491 |
+
"learning_rate": 0.00019805570534702987,
|
1492 |
+
"loss": 0.9902,
|
1493 |
+
"step": 1055
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.16,
|
1497 |
+
"grad_norm": 0.330078125,
|
1498 |
+
"learning_rate": 0.00019800451065129018,
|
1499 |
+
"loss": 0.9699,
|
1500 |
+
"step": 1060
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.16,
|
1504 |
+
"grad_norm": 0.337890625,
|
1505 |
+
"learning_rate": 0.00019795265747897956,
|
1506 |
+
"loss": 0.9911,
|
1507 |
+
"step": 1065
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.16,
|
1511 |
+
"grad_norm": 0.345703125,
|
1512 |
+
"learning_rate": 0.00019790014617849106,
|
1513 |
+
"loss": 0.9923,
|
1514 |
+
"step": 1070
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.16,
|
1518 |
+
"grad_norm": 0.341796875,
|
1519 |
+
"learning_rate": 0.00019784697710263974,
|
1520 |
+
"loss": 0.9976,
|
1521 |
+
"step": 1075
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.16,
|
1525 |
+
"grad_norm": 0.3515625,
|
1526 |
+
"learning_rate": 0.00019779315060866007,
|
1527 |
+
"loss": 0.9647,
|
1528 |
+
"step": 1080
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.16,
|
1532 |
+
"grad_norm": 0.353515625,
|
1533 |
+
"learning_rate": 0.00019773866705820363,
|
1534 |
+
"loss": 0.9589,
|
1535 |
+
"step": 1085
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.16,
|
1539 |
+
"grad_norm": 0.330078125,
|
1540 |
+
"learning_rate": 0.00019768352681733662,
|
1541 |
+
"loss": 1.005,
|
1542 |
+
"step": 1090
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.16,
|
1546 |
+
"grad_norm": 0.341796875,
|
1547 |
+
"learning_rate": 0.00019762773025653747,
|
1548 |
+
"loss": 1.0066,
|
1549 |
+
"step": 1095
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.16,
|
1553 |
+
"grad_norm": 0.345703125,
|
1554 |
+
"learning_rate": 0.0001975712777506943,
|
1555 |
+
"loss": 1.0118,
|
1556 |
+
"step": 1100
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.16,
|
1560 |
+
"grad_norm": 0.34375,
|
1561 |
+
"learning_rate": 0.00019751416967910248,
|
1562 |
+
"loss": 1.0445,
|
1563 |
+
"step": 1105
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.16,
|
1567 |
+
"grad_norm": 0.34765625,
|
1568 |
+
"learning_rate": 0.00019745640642546196,
|
1569 |
+
"loss": 0.9766,
|
1570 |
+
"step": 1110
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.17,
|
1574 |
+
"grad_norm": 0.353515625,
|
1575 |
+
"learning_rate": 0.0001973979883778747,
|
1576 |
+
"loss": 0.9897,
|
1577 |
+
"step": 1115
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.17,
|
1581 |
+
"grad_norm": 0.3515625,
|
1582 |
+
"learning_rate": 0.00019733891592884227,
|
1583 |
+
"loss": 0.9826,
|
1584 |
+
"step": 1120
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.17,
|
1588 |
+
"grad_norm": 0.34765625,
|
1589 |
+
"learning_rate": 0.00019727918947526292,
|
1590 |
+
"loss": 0.988,
|
1591 |
+
"step": 1125
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.17,
|
1595 |
+
"grad_norm": 0.349609375,
|
1596 |
+
"learning_rate": 0.00019721880941842913,
|
1597 |
+
"loss": 1.0101,
|
1598 |
+
"step": 1130
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.17,
|
1602 |
+
"grad_norm": 0.34375,
|
1603 |
+
"learning_rate": 0.00019715777616402479,
|
1604 |
+
"loss": 0.9744,
|
1605 |
+
"step": 1135
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.17,
|
1609 |
+
"grad_norm": 0.33984375,
|
1610 |
+
"learning_rate": 0.0001970960901221225,
|
1611 |
+
"loss": 0.9896,
|
1612 |
+
"step": 1140
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.17,
|
1616 |
+
"grad_norm": 0.357421875,
|
1617 |
+
"learning_rate": 0.00019703375170718093,
|
1618 |
+
"loss": 0.9786,
|
1619 |
+
"step": 1145
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.17,
|
1623 |
+
"grad_norm": 0.34765625,
|
1624 |
+
"learning_rate": 0.00019697076133804185,
|
1625 |
+
"loss": 0.9958,
|
1626 |
+
"step": 1150
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.17,
|
1630 |
+
"grad_norm": 0.341796875,
|
1631 |
+
"learning_rate": 0.0001969071194379275,
|
1632 |
+
"loss": 0.9803,
|
1633 |
+
"step": 1155
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.17,
|
1637 |
+
"grad_norm": 0.3515625,
|
1638 |
+
"learning_rate": 0.00019684282643443748,
|
1639 |
+
"loss": 0.9894,
|
1640 |
+
"step": 1160
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.17,
|
1644 |
+
"grad_norm": 0.357421875,
|
1645 |
+
"learning_rate": 0.00019677788275954624,
|
1646 |
+
"loss": 1.0073,
|
1647 |
+
"step": 1165
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.17,
|
1651 |
+
"grad_norm": 0.33984375,
|
1652 |
+
"learning_rate": 0.00019671228884959987,
|
1653 |
+
"loss": 1.0145,
|
1654 |
+
"step": 1170
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.17,
|
1658 |
+
"grad_norm": 0.357421875,
|
1659 |
+
"learning_rate": 0.00019664604514531332,
|
1660 |
+
"loss": 1.0035,
|
1661 |
+
"step": 1175
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.18,
|
1665 |
+
"grad_norm": 0.353515625,
|
1666 |
+
"learning_rate": 0.0001965791520917674,
|
1667 |
+
"loss": 0.9856,
|
1668 |
+
"step": 1180
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.18,
|
1672 |
+
"grad_norm": 0.33984375,
|
1673 |
+
"learning_rate": 0.00019651161013840583,
|
1674 |
+
"loss": 0.9573,
|
1675 |
+
"step": 1185
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.18,
|
1679 |
+
"grad_norm": 0.328125,
|
1680 |
+
"learning_rate": 0.00019644341973903208,
|
1681 |
+
"loss": 0.9824,
|
1682 |
+
"step": 1190
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.18,
|
1686 |
+
"grad_norm": 0.333984375,
|
1687 |
+
"learning_rate": 0.00019637458135180657,
|
1688 |
+
"loss": 0.9873,
|
1689 |
+
"step": 1195
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.18,
|
1693 |
+
"grad_norm": 0.3515625,
|
1694 |
+
"learning_rate": 0.0001963050954392433,
|
1695 |
+
"loss": 0.9743,
|
1696 |
+
"step": 1200
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.18,
|
1700 |
+
"grad_norm": 0.345703125,
|
1701 |
+
"learning_rate": 0.00019623496246820704,
|
1702 |
+
"loss": 0.9987,
|
1703 |
+
"step": 1205
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.18,
|
1707 |
+
"grad_norm": 0.349609375,
|
1708 |
+
"learning_rate": 0.00019616418290990993,
|
1709 |
+
"loss": 1.0153,
|
1710 |
+
"step": 1210
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.18,
|
1714 |
+
"grad_norm": 0.39453125,
|
1715 |
+
"learning_rate": 0.0001960927572399084,
|
1716 |
+
"loss": 0.9907,
|
1717 |
+
"step": 1215
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.18,
|
1721 |
+
"grad_norm": 0.337890625,
|
1722 |
+
"learning_rate": 0.00019602068593810014,
|
1723 |
+
"loss": 1.0148,
|
1724 |
+
"step": 1220
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.18,
|
1728 |
+
"grad_norm": 0.34375,
|
1729 |
+
"learning_rate": 0.0001959479694887206,
|
1730 |
+
"loss": 1.0024,
|
1731 |
+
"step": 1225
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.18,
|
1735 |
+
"grad_norm": 0.34765625,
|
1736 |
+
"learning_rate": 0.00019587460838033996,
|
1737 |
+
"loss": 1.0298,
|
1738 |
+
"step": 1230
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.18,
|
1742 |
+
"grad_norm": 0.357421875,
|
1743 |
+
"learning_rate": 0.00019580060310585973,
|
1744 |
+
"loss": 0.9946,
|
1745 |
+
"step": 1235
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.18,
|
1749 |
+
"grad_norm": 0.349609375,
|
1750 |
+
"learning_rate": 0.00019572595416250942,
|
1751 |
+
"loss": 0.9961,
|
1752 |
+
"step": 1240
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.18,
|
1756 |
+
"grad_norm": 0.333984375,
|
1757 |
+
"learning_rate": 0.00019565066205184332,
|
1758 |
+
"loss": 1.0016,
|
1759 |
+
"step": 1245
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.19,
|
1763 |
+
"grad_norm": 0.353515625,
|
1764 |
+
"learning_rate": 0.00019557472727973707,
|
1765 |
+
"loss": 0.9829,
|
1766 |
+
"step": 1250
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.19,
|
1770 |
+
"grad_norm": 0.34765625,
|
1771 |
+
"learning_rate": 0.00019549815035638414,
|
1772 |
+
"loss": 0.9781,
|
1773 |
+
"step": 1255
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.19,
|
1777 |
+
"grad_norm": 0.353515625,
|
1778 |
+
"learning_rate": 0.00019542093179629268,
|
1779 |
+
"loss": 1.0089,
|
1780 |
+
"step": 1260
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.19,
|
1784 |
+
"grad_norm": 0.34375,
|
1785 |
+
"learning_rate": 0.0001953430721182817,
|
1786 |
+
"loss": 0.9942,
|
1787 |
+
"step": 1265
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.19,
|
1791 |
+
"grad_norm": 0.357421875,
|
1792 |
+
"learning_rate": 0.00019526457184547793,
|
1793 |
+
"loss": 0.9818,
|
1794 |
+
"step": 1270
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.19,
|
1798 |
+
"grad_norm": 0.359375,
|
1799 |
+
"learning_rate": 0.00019518543150531207,
|
1800 |
+
"loss": 1.018,
|
1801 |
+
"step": 1275
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.19,
|
1805 |
+
"grad_norm": 0.345703125,
|
1806 |
+
"learning_rate": 0.00019510565162951537,
|
1807 |
+
"loss": 0.9697,
|
1808 |
+
"step": 1280
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.19,
|
1812 |
+
"grad_norm": 0.359375,
|
1813 |
+
"learning_rate": 0.00019502523275411599,
|
1814 |
+
"loss": 1.0331,
|
1815 |
+
"step": 1285
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.19,
|
1819 |
+
"grad_norm": 0.34375,
|
1820 |
+
"learning_rate": 0.00019494417541943547,
|
1821 |
+
"loss": 1.0071,
|
1822 |
+
"step": 1290
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.19,
|
1826 |
+
"grad_norm": 0.345703125,
|
1827 |
+
"learning_rate": 0.00019486248017008503,
|
1828 |
+
"loss": 0.9699,
|
1829 |
+
"step": 1295
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.19,
|
1833 |
+
"grad_norm": 0.34765625,
|
1834 |
+
"learning_rate": 0.00019478014755496196,
|
1835 |
+
"loss": 1.0168,
|
1836 |
+
"step": 1300
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.19,
|
1840 |
+
"grad_norm": 0.345703125,
|
1841 |
+
"learning_rate": 0.00019469717812724575,
|
1842 |
+
"loss": 0.9719,
|
1843 |
+
"step": 1305
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.19,
|
1847 |
+
"grad_norm": 0.345703125,
|
1848 |
+
"learning_rate": 0.00019461357244439479,
|
1849 |
+
"loss": 0.9974,
|
1850 |
+
"step": 1310
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.2,
|
1854 |
+
"grad_norm": 0.34375,
|
1855 |
+
"learning_rate": 0.00019452933106814223,
|
1856 |
+
"loss": 0.9897,
|
1857 |
+
"step": 1315
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.2,
|
1861 |
+
"grad_norm": 0.345703125,
|
1862 |
+
"learning_rate": 0.0001944444545644923,
|
1863 |
+
"loss": 0.9809,
|
1864 |
+
"step": 1320
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.2,
|
1868 |
+
"grad_norm": 0.341796875,
|
1869 |
+
"learning_rate": 0.0001943589435037166,
|
1870 |
+
"loss": 0.9601,
|
1871 |
+
"step": 1325
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.2,
|
1875 |
+
"grad_norm": 0.345703125,
|
1876 |
+
"learning_rate": 0.00019427279846035025,
|
1877 |
+
"loss": 0.9615,
|
1878 |
+
"step": 1330
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.2,
|
1882 |
+
"grad_norm": 0.337890625,
|
1883 |
+
"learning_rate": 0.00019418602001318797,
|
1884 |
+
"loss": 0.9888,
|
1885 |
+
"step": 1335
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.2,
|
1889 |
+
"grad_norm": 0.341796875,
|
1890 |
+
"learning_rate": 0.00019409860874528017,
|
1891 |
+
"loss": 1.0099,
|
1892 |
+
"step": 1340
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.2,
|
1896 |
+
"grad_norm": 0.333984375,
|
1897 |
+
"learning_rate": 0.00019401056524392916,
|
1898 |
+
"loss": 0.9911,
|
1899 |
+
"step": 1345
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.2,
|
1903 |
+
"grad_norm": 0.3515625,
|
1904 |
+
"learning_rate": 0.00019392189010068508,
|
1905 |
+
"loss": 0.992,
|
1906 |
+
"step": 1350
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.2,
|
1910 |
+
"grad_norm": 0.337890625,
|
1911 |
+
"learning_rate": 0.000193832583911342,
|
1912 |
+
"loss": 0.9827,
|
1913 |
+
"step": 1355
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.2,
|
1917 |
+
"grad_norm": 0.3515625,
|
1918 |
+
"learning_rate": 0.0001937426472759338,
|
1919 |
+
"loss": 0.9473,
|
1920 |
+
"step": 1360
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.2,
|
1924 |
+
"grad_norm": 0.3671875,
|
1925 |
+
"learning_rate": 0.00019365208079873036,
|
1926 |
+
"loss": 0.9863,
|
1927 |
+
"step": 1365
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.2,
|
1931 |
+
"grad_norm": 0.349609375,
|
1932 |
+
"learning_rate": 0.0001935608850882333,
|
1933 |
+
"loss": 0.9662,
|
1934 |
+
"step": 1370
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.2,
|
1938 |
+
"grad_norm": 0.3515625,
|
1939 |
+
"learning_rate": 0.0001934690607571719,
|
1940 |
+
"loss": 0.9864,
|
1941 |
+
"step": 1375
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.2,
|
1945 |
+
"grad_norm": 0.345703125,
|
1946 |
+
"learning_rate": 0.00019337660842249914,
|
1947 |
+
"loss": 1.0151,
|
1948 |
+
"step": 1380
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.21,
|
1952 |
+
"grad_norm": 0.337890625,
|
1953 |
+
"learning_rate": 0.0001932835287053874,
|
1954 |
+
"loss": 0.9638,
|
1955 |
+
"step": 1385
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.21,
|
1959 |
+
"grad_norm": 0.341796875,
|
1960 |
+
"learning_rate": 0.00019318982223122437,
|
1961 |
+
"loss": 1.0149,
|
1962 |
+
"step": 1390
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.21,
|
1966 |
+
"grad_norm": 0.341796875,
|
1967 |
+
"learning_rate": 0.00019309548962960876,
|
1968 |
+
"loss": 0.9827,
|
1969 |
+
"step": 1395
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.21,
|
1973 |
+
"grad_norm": 0.349609375,
|
1974 |
+
"learning_rate": 0.00019300053153434622,
|
1975 |
+
"loss": 0.9726,
|
1976 |
+
"step": 1400
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.21,
|
1980 |
+
"grad_norm": 0.33984375,
|
1981 |
+
"learning_rate": 0.00019290494858344493,
|
1982 |
+
"loss": 0.9742,
|
1983 |
+
"step": 1405
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.21,
|
1987 |
+
"grad_norm": 0.345703125,
|
1988 |
+
"learning_rate": 0.00019280874141911137,
|
1989 |
+
"loss": 0.9987,
|
1990 |
+
"step": 1410
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.21,
|
1994 |
+
"grad_norm": 0.349609375,
|
1995 |
+
"learning_rate": 0.00019271191068774606,
|
1996 |
+
"loss": 1.0067,
|
1997 |
+
"step": 1415
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.21,
|
2001 |
+
"grad_norm": 0.33984375,
|
2002 |
+
"learning_rate": 0.00019261445703993912,
|
2003 |
+
"loss": 0.9833,
|
2004 |
+
"step": 1420
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.21,
|
2008 |
+
"grad_norm": 0.35546875,
|
2009 |
+
"learning_rate": 0.00019251638113046597,
|
2010 |
+
"loss": 0.9599,
|
2011 |
+
"step": 1425
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.21,
|
2015 |
+
"grad_norm": 0.3671875,
|
2016 |
+
"learning_rate": 0.0001924176836182829,
|
2017 |
+
"loss": 0.9793,
|
2018 |
+
"step": 1430
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.21,
|
2022 |
+
"grad_norm": 0.337890625,
|
2023 |
+
"learning_rate": 0.00019231836516652261,
|
2024 |
+
"loss": 0.965,
|
2025 |
+
"step": 1435
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.21,
|
2029 |
+
"grad_norm": 0.353515625,
|
2030 |
+
"learning_rate": 0.0001922184264424899,
|
2031 |
+
"loss": 0.9598,
|
2032 |
+
"step": 1440
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.21,
|
2036 |
+
"grad_norm": 0.3359375,
|
2037 |
+
"learning_rate": 0.00019211786811765692,
|
2038 |
+
"loss": 0.9931,
|
2039 |
+
"step": 1445
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.22,
|
2043 |
+
"grad_norm": 0.345703125,
|
2044 |
+
"learning_rate": 0.00019201669086765902,
|
2045 |
+
"loss": 0.9571,
|
2046 |
+
"step": 1450
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.22,
|
2050 |
+
"grad_norm": 0.328125,
|
2051 |
+
"learning_rate": 0.0001919148953722898,
|
2052 |
+
"loss": 0.9448,
|
2053 |
+
"step": 1455
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.22,
|
2057 |
+
"grad_norm": 0.328125,
|
2058 |
+
"learning_rate": 0.0001918124823154969,
|
2059 |
+
"loss": 0.9523,
|
2060 |
+
"step": 1460
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.22,
|
2064 |
+
"grad_norm": 0.34765625,
|
2065 |
+
"learning_rate": 0.00019170945238537718,
|
2066 |
+
"loss": 0.9888,
|
2067 |
+
"step": 1465
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.22,
|
2071 |
+
"grad_norm": 0.34765625,
|
2072 |
+
"learning_rate": 0.00019160580627417223,
|
2073 |
+
"loss": 0.9735,
|
2074 |
+
"step": 1470
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.22,
|
2078 |
+
"grad_norm": 0.337890625,
|
2079 |
+
"learning_rate": 0.00019150154467826357,
|
2080 |
+
"loss": 0.9726,
|
2081 |
+
"step": 1475
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.22,
|
2085 |
+
"grad_norm": 0.34765625,
|
2086 |
+
"learning_rate": 0.00019139666829816817,
|
2087 |
+
"loss": 0.9679,
|
2088 |
+
"step": 1480
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.22,
|
2092 |
+
"grad_norm": 0.33203125,
|
2093 |
+
"learning_rate": 0.0001912911778385336,
|
2094 |
+
"loss": 0.9913,
|
2095 |
+
"step": 1485
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.22,
|
2099 |
+
"grad_norm": 0.33203125,
|
2100 |
+
"learning_rate": 0.00019118507400813325,
|
2101 |
+
"loss": 0.9736,
|
2102 |
+
"step": 1490
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.22,
|
2106 |
+
"grad_norm": 0.337890625,
|
2107 |
+
"learning_rate": 0.0001910783575198618,
|
2108 |
+
"loss": 0.9535,
|
2109 |
+
"step": 1495
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.22,
|
2113 |
+
"grad_norm": 0.341796875,
|
2114 |
+
"learning_rate": 0.0001909710290907302,
|
2115 |
+
"loss": 0.993,
|
2116 |
+
"step": 1500
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.22,
|
2120 |
+
"grad_norm": 0.3515625,
|
2121 |
+
"learning_rate": 0.00019086308944186084,
|
2122 |
+
"loss": 0.9645,
|
2123 |
+
"step": 1505
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.22,
|
2127 |
+
"grad_norm": 0.33984375,
|
2128 |
+
"learning_rate": 0.000190754539298483,
|
2129 |
+
"loss": 0.9694,
|
2130 |
+
"step": 1510
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.22,
|
2134 |
+
"grad_norm": 0.337890625,
|
2135 |
+
"learning_rate": 0.00019064537938992757,
|
2136 |
+
"loss": 0.9775,
|
2137 |
+
"step": 1515
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.23,
|
2141 |
+
"grad_norm": 0.34375,
|
2142 |
+
"learning_rate": 0.0001905356104496225,
|
2143 |
+
"loss": 0.9388,
|
2144 |
+
"step": 1520
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.23,
|
2148 |
+
"grad_norm": 0.357421875,
|
2149 |
+
"learning_rate": 0.00019042523321508768,
|
2150 |
+
"loss": 0.9755,
|
2151 |
+
"step": 1525
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.23,
|
2155 |
+
"grad_norm": 0.359375,
|
2156 |
+
"learning_rate": 0.00019031424842793,
|
2157 |
+
"loss": 1.0159,
|
2158 |
+
"step": 1530
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.23,
|
2162 |
+
"grad_norm": 0.3515625,
|
2163 |
+
"learning_rate": 0.00019020265683383842,
|
2164 |
+
"loss": 0.9835,
|
2165 |
+
"step": 1535
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.23,
|
2169 |
+
"grad_norm": 0.349609375,
|
2170 |
+
"learning_rate": 0.000190090459182579,
|
2171 |
+
"loss": 0.9711,
|
2172 |
+
"step": 1540
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.23,
|
2176 |
+
"grad_norm": 0.341796875,
|
2177 |
+
"learning_rate": 0.00018997765622798967,
|
2178 |
+
"loss": 0.9742,
|
2179 |
+
"step": 1545
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.23,
|
2183 |
+
"grad_norm": 0.33984375,
|
2184 |
+
"learning_rate": 0.0001898642487279754,
|
2185 |
+
"loss": 0.9669,
|
2186 |
+
"step": 1550
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.23,
|
2190 |
+
"grad_norm": 0.3359375,
|
2191 |
+
"learning_rate": 0.000189750237444503,
|
2192 |
+
"loss": 0.9516,
|
2193 |
+
"step": 1555
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.23,
|
2197 |
+
"grad_norm": 0.349609375,
|
2198 |
+
"learning_rate": 0.00018963562314359595,
|
2199 |
+
"loss": 1.0002,
|
2200 |
+
"step": 1560
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.23,
|
2204 |
+
"grad_norm": 0.341796875,
|
2205 |
+
"learning_rate": 0.00018952040659532936,
|
2206 |
+
"loss": 0.937,
|
2207 |
+
"step": 1565
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.23,
|
2211 |
+
"grad_norm": 0.33984375,
|
2212 |
+
"learning_rate": 0.00018940458857382467,
|
2213 |
+
"loss": 0.9757,
|
2214 |
+
"step": 1570
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.23,
|
2218 |
+
"grad_norm": 0.333984375,
|
2219 |
+
"learning_rate": 0.00018928816985724458,
|
2220 |
+
"loss": 0.9968,
|
2221 |
+
"step": 1575
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.23,
|
2225 |
+
"grad_norm": 0.3359375,
|
2226 |
+
"learning_rate": 0.0001891711512277878,
|
2227 |
+
"loss": 0.974,
|
2228 |
+
"step": 1580
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.24,
|
2232 |
+
"grad_norm": 0.34765625,
|
2233 |
+
"learning_rate": 0.00018905353347168366,
|
2234 |
+
"loss": 0.9641,
|
2235 |
+
"step": 1585
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.24,
|
2239 |
+
"grad_norm": 0.33984375,
|
2240 |
+
"learning_rate": 0.00018893531737918702,
|
2241 |
+
"loss": 0.9799,
|
2242 |
+
"step": 1590
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.24,
|
2246 |
+
"grad_norm": 0.3359375,
|
2247 |
+
"learning_rate": 0.0001888165037445728,
|
2248 |
+
"loss": 0.9385,
|
2249 |
+
"step": 1595
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.24,
|
2253 |
+
"grad_norm": 0.357421875,
|
2254 |
+
"learning_rate": 0.00018869709336613073,
|
2255 |
+
"loss": 1.0199,
|
2256 |
+
"step": 1600
|
2257 |
+
}
|
2258 |
+
],
|
2259 |
+
"logging_steps": 5,
|
2260 |
+
"max_steps": 6734,
|
2261 |
+
"num_input_tokens_seen": 0,
|
2262 |
+
"num_train_epochs": 1,
|
2263 |
+
"save_steps": 100,
|
2264 |
+
"total_flos": 2.2500144814112113e+18,
|
2265 |
+
"train_batch_size": 2,
|
2266 |
+
"trial_name": null,
|
2267 |
+
"trial_params": null
|
2268 |
+
}
|
checkpoint-1600/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efa607b4c9da9ebfc565f13d64324b7945d1ef5e182ff6164c71a2bc73b18b7c
|
3 |
+
size 4984
|