Training in progress, step 341, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +34 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/added_tokens.json +4 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer.model +3 -0
- last-checkpoint/tokenizer_config.json +63 -0
- last-checkpoint/trainer_state.json +2436 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/OpenHermes-2.5-Mistral-7B
|
3 |
+
library_name: peft
|
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 0.13.2
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"o_proj",
|
25 |
+
"down_proj",
|
26 |
+
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"v_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:669a93a7a599d147ac68d4e0cd4acfda8ad8db9f83a76565f9a7cbec3d5822cf
|
3 |
+
size 83945296
|
last-checkpoint/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4e78b8cbbc492e035ec231795143bd705d58ffccf9c6af9264d03f3d598018d
|
3 |
+
size 43123028
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec6897e825191b0a80051b1e34fb6ced22b692c5c07df5bd607896b8ec6078eb
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b0bb58a6976151803bee01b02feadab21639b27a6d2d75a55682622d20ee556
|
3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 32768,
|
54 |
+
"pad_token": "<unk>",
|
55 |
+
"padding_side": "right",
|
56 |
+
"sp_model_kwargs": {},
|
57 |
+
"spaces_between_special_tokens": false,
|
58 |
+
"tokenizer_class": "LlamaTokenizer",
|
59 |
+
"trust_remote_code": false,
|
60 |
+
"unk_token": "<unk>",
|
61 |
+
"use_default_system_prompt": true,
|
62 |
+
"use_fast": true
|
63 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,2436 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0668693009118541,
|
5 |
+
"eval_steps": 341,
|
6 |
+
"global_step": 341,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.00019609765663300324,
|
13 |
+
"grad_norm": 18.01366424560547,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 3.0843,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.00019609765663300324,
|
20 |
+
"eval_loss": 1.1017773151397705,
|
21 |
+
"eval_runtime": 79.0856,
|
22 |
+
"eval_samples_per_second": 27.16,
|
23 |
+
"eval_steps_per_second": 13.58,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0003921953132660065,
|
28 |
+
"grad_norm": 16.80318260192871,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"loss": 3.2221,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0005882929698990097,
|
35 |
+
"grad_norm": 16.65929412841797,
|
36 |
+
"learning_rate": 6e-05,
|
37 |
+
"loss": 3.8956,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.000784390626532013,
|
42 |
+
"grad_norm": 37.782188415527344,
|
43 |
+
"learning_rate": 8e-05,
|
44 |
+
"loss": 5.185,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0009804882831650162,
|
49 |
+
"grad_norm": 19.226940155029297,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 3.1542,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.0011765859397980193,
|
56 |
+
"grad_norm": 26.570402145385742,
|
57 |
+
"learning_rate": 0.00012,
|
58 |
+
"loss": 4.5356,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.0013726835964310226,
|
63 |
+
"grad_norm": 22.43348503112793,
|
64 |
+
"learning_rate": 0.00014,
|
65 |
+
"loss": 3.8177,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.001568781253064026,
|
70 |
+
"grad_norm": 29.817941665649414,
|
71 |
+
"learning_rate": 0.00016,
|
72 |
+
"loss": 4.4013,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.0017648789096970292,
|
77 |
+
"grad_norm": 18.46044158935547,
|
78 |
+
"learning_rate": 0.00018,
|
79 |
+
"loss": 3.374,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.0019609765663300325,
|
84 |
+
"grad_norm": 24.337013244628906,
|
85 |
+
"learning_rate": 0.0002,
|
86 |
+
"loss": 3.2509,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.0021570742229630358,
|
91 |
+
"grad_norm": 18.9931640625,
|
92 |
+
"learning_rate": 0.00019999972962977903,
|
93 |
+
"loss": 2.933,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.0023531718795960386,
|
98 |
+
"grad_norm": 17.7039852142334,
|
99 |
+
"learning_rate": 0.00019999891852057812,
|
100 |
+
"loss": 3.2867,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.002549269536229042,
|
105 |
+
"grad_norm": 15.128417015075684,
|
106 |
+
"learning_rate": 0.0001999975666767833,
|
107 |
+
"loss": 2.2303,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.002745367192862045,
|
112 |
+
"grad_norm": 8.747583389282227,
|
113 |
+
"learning_rate": 0.00019999567410570446,
|
114 |
+
"loss": 1.7348,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.0029414648494950485,
|
119 |
+
"grad_norm": 20.570377349853516,
|
120 |
+
"learning_rate": 0.00019999324081757555,
|
121 |
+
"loss": 3.9284,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.003137562506128052,
|
126 |
+
"grad_norm": 7.86672306060791,
|
127 |
+
"learning_rate": 0.00019999026682555434,
|
128 |
+
"loss": 1.8121,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.003333660162761055,
|
133 |
+
"grad_norm": 10.341567039489746,
|
134 |
+
"learning_rate": 0.0001999867521457224,
|
135 |
+
"loss": 1.5864,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.0035297578193940584,
|
140 |
+
"grad_norm": 7.888909339904785,
|
141 |
+
"learning_rate": 0.00019998269679708504,
|
142 |
+
"loss": 3.1584,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.0037258554760270617,
|
147 |
+
"grad_norm": 15.346771240234375,
|
148 |
+
"learning_rate": 0.00019997810080157113,
|
149 |
+
"loss": 2.0858,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.003921953132660065,
|
154 |
+
"grad_norm": 11.417168617248535,
|
155 |
+
"learning_rate": 0.0001999729641840331,
|
156 |
+
"loss": 3.5646,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.004118050789293068,
|
161 |
+
"grad_norm": 12.86220932006836,
|
162 |
+
"learning_rate": 0.00019996728697224675,
|
163 |
+
"loss": 3.0594,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.0043141484459260715,
|
168 |
+
"grad_norm": 7.418736457824707,
|
169 |
+
"learning_rate": 0.00019996106919691102,
|
170 |
+
"loss": 2.1349,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.004510246102559075,
|
175 |
+
"grad_norm": 4.803528308868408,
|
176 |
+
"learning_rate": 0.00019995431089164795,
|
177 |
+
"loss": 2.3151,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.004706343759192077,
|
182 |
+
"grad_norm": 8.667632102966309,
|
183 |
+
"learning_rate": 0.00019994701209300245,
|
184 |
+
"loss": 1.6791,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.0049024414158250805,
|
189 |
+
"grad_norm": 5.3950724601745605,
|
190 |
+
"learning_rate": 0.00019993917284044202,
|
191 |
+
"loss": 2.7265,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.005098539072458084,
|
196 |
+
"grad_norm": 18.16863441467285,
|
197 |
+
"learning_rate": 0.0001999307931763567,
|
198 |
+
"loss": 1.7289,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.005294636729091087,
|
203 |
+
"grad_norm": 10.66887378692627,
|
204 |
+
"learning_rate": 0.00019992187314605872,
|
205 |
+
"loss": 2.645,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.00549073438572409,
|
210 |
+
"grad_norm": 26.42878532409668,
|
211 |
+
"learning_rate": 0.00019991241279778232,
|
212 |
+
"loss": 3.4603,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.005686832042357094,
|
217 |
+
"grad_norm": 10.017987251281738,
|
218 |
+
"learning_rate": 0.0001999024121826834,
|
219 |
+
"loss": 1.2001,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.005882929698990097,
|
224 |
+
"grad_norm": 11.155564308166504,
|
225 |
+
"learning_rate": 0.00019989187135483933,
|
226 |
+
"loss": 1.5102,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.0060790273556231,
|
231 |
+
"grad_norm": 3.7590131759643555,
|
232 |
+
"learning_rate": 0.00019988079037124864,
|
233 |
+
"loss": 1.0619,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.006275125012256104,
|
238 |
+
"grad_norm": 8.47985553741455,
|
239 |
+
"learning_rate": 0.00019986916929183067,
|
240 |
+
"loss": 2.6256,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.006471222668889107,
|
245 |
+
"grad_norm": 16.655269622802734,
|
246 |
+
"learning_rate": 0.00019985700817942533,
|
247 |
+
"loss": 2.2039,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.00666732032552211,
|
252 |
+
"grad_norm": 9.003829956054688,
|
253 |
+
"learning_rate": 0.00019984430709979264,
|
254 |
+
"loss": 1.7281,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.0068634179821551134,
|
259 |
+
"grad_norm": 36.33080291748047,
|
260 |
+
"learning_rate": 0.0001998310661216125,
|
261 |
+
"loss": 3.0575,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.007059515638788117,
|
266 |
+
"grad_norm": 11.909663200378418,
|
267 |
+
"learning_rate": 0.00019981728531648423,
|
268 |
+
"loss": 1.9623,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.00725561329542112,
|
273 |
+
"grad_norm": 10.967493057250977,
|
274 |
+
"learning_rate": 0.00019980296475892616,
|
275 |
+
"loss": 2.8071,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.007451710952054123,
|
280 |
+
"grad_norm": 11.050918579101562,
|
281 |
+
"learning_rate": 0.00019978810452637543,
|
282 |
+
"loss": 1.8019,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.007647808608687127,
|
287 |
+
"grad_norm": 17.752105712890625,
|
288 |
+
"learning_rate": 0.00019977270469918727,
|
289 |
+
"loss": 3.0332,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.00784390626532013,
|
294 |
+
"grad_norm": 6.67478609085083,
|
295 |
+
"learning_rate": 0.0001997567653606348,
|
296 |
+
"loss": 1.32,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.008040003921953132,
|
301 |
+
"grad_norm": 7.402947902679443,
|
302 |
+
"learning_rate": 0.00019974028659690843,
|
303 |
+
"loss": 1.4442,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.008236101578586136,
|
308 |
+
"grad_norm": 13.006294250488281,
|
309 |
+
"learning_rate": 0.00019972326849711553,
|
310 |
+
"loss": 2.2418,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.008432199235219139,
|
315 |
+
"grad_norm": 5.940983295440674,
|
316 |
+
"learning_rate": 0.00019970571115327985,
|
317 |
+
"loss": 0.9049,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.008628296891852143,
|
322 |
+
"grad_norm": 9.866477012634277,
|
323 |
+
"learning_rate": 0.00019968761466034103,
|
324 |
+
"loss": 2.7203,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.008824394548485145,
|
329 |
+
"grad_norm": 8.239157676696777,
|
330 |
+
"learning_rate": 0.00019966897911615416,
|
331 |
+
"loss": 1.9653,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.00902049220511815,
|
336 |
+
"grad_norm": 16.142181396484375,
|
337 |
+
"learning_rate": 0.0001996498046214891,
|
338 |
+
"loss": 2.7509,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.009216589861751152,
|
343 |
+
"grad_norm": 9.295431137084961,
|
344 |
+
"learning_rate": 0.00019963009128003018,
|
345 |
+
"loss": 2.0133,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.009412687518384154,
|
350 |
+
"grad_norm": 10.362130165100098,
|
351 |
+
"learning_rate": 0.00019960983919837535,
|
352 |
+
"loss": 1.716,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.009608785175017159,
|
357 |
+
"grad_norm": 28.2889461517334,
|
358 |
+
"learning_rate": 0.00019958904848603584,
|
359 |
+
"loss": 2.8961,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.009804882831650161,
|
364 |
+
"grad_norm": 13.199325561523438,
|
365 |
+
"learning_rate": 0.0001995677192554354,
|
366 |
+
"loss": 2.62,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.010000980488283165,
|
371 |
+
"grad_norm": 11.95132827758789,
|
372 |
+
"learning_rate": 0.00019954585162190985,
|
373 |
+
"loss": 2.792,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.010197078144916168,
|
378 |
+
"grad_norm": 16.581575393676758,
|
379 |
+
"learning_rate": 0.0001995234457037063,
|
380 |
+
"loss": 2.7239,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.010393175801549172,
|
385 |
+
"grad_norm": 12.048559188842773,
|
386 |
+
"learning_rate": 0.00019950050162198258,
|
387 |
+
"loss": 1.9892,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.010589273458182174,
|
392 |
+
"grad_norm": 9.297942161560059,
|
393 |
+
"learning_rate": 0.00019947701950080672,
|
394 |
+
"loss": 1.8015,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.010785371114815178,
|
399 |
+
"grad_norm": 6.09962797164917,
|
400 |
+
"learning_rate": 0.00019945299946715596,
|
401 |
+
"loss": 1.1493,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.01098146877144818,
|
406 |
+
"grad_norm": 6.668224811553955,
|
407 |
+
"learning_rate": 0.00019942844165091633,
|
408 |
+
"loss": 0.9968,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.011177566428081185,
|
413 |
+
"grad_norm": 17.000507354736328,
|
414 |
+
"learning_rate": 0.00019940334618488194,
|
415 |
+
"loss": 1.5857,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.011373664084714187,
|
420 |
+
"grad_norm": 11.42551326751709,
|
421 |
+
"learning_rate": 0.00019937771320475406,
|
422 |
+
"loss": 1.5236,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.011569761741347192,
|
427 |
+
"grad_norm": 13.255271911621094,
|
428 |
+
"learning_rate": 0.00019935154284914065,
|
429 |
+
"loss": 1.6174,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.011765859397980194,
|
434 |
+
"grad_norm": 12.664427757263184,
|
435 |
+
"learning_rate": 0.00019932483525955533,
|
436 |
+
"loss": 1.476,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.011961957054613198,
|
441 |
+
"grad_norm": 19.540660858154297,
|
442 |
+
"learning_rate": 0.00019929759058041687,
|
443 |
+
"loss": 1.5251,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.0121580547112462,
|
448 |
+
"grad_norm": 10.44942855834961,
|
449 |
+
"learning_rate": 0.0001992698089590483,
|
450 |
+
"loss": 1.7865,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.012354152367879203,
|
455 |
+
"grad_norm": 13.294017791748047,
|
456 |
+
"learning_rate": 0.00019924149054567606,
|
457 |
+
"loss": 4.1284,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.012550250024512207,
|
462 |
+
"grad_norm": 13.700861930847168,
|
463 |
+
"learning_rate": 0.00019921263549342922,
|
464 |
+
"loss": 2.8987,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.01274634768114521,
|
469 |
+
"grad_norm": 51.7520866394043,
|
470 |
+
"learning_rate": 0.00019918324395833877,
|
471 |
+
"loss": 1.7335,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.012942445337778214,
|
476 |
+
"grad_norm": 25.415748596191406,
|
477 |
+
"learning_rate": 0.00019915331609933657,
|
478 |
+
"loss": 2.6131,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.013138542994411216,
|
483 |
+
"grad_norm": 10.575088500976562,
|
484 |
+
"learning_rate": 0.00019912285207825475,
|
485 |
+
"loss": 1.202,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.01333464065104422,
|
490 |
+
"grad_norm": 7.0860772132873535,
|
491 |
+
"learning_rate": 0.00019909185205982453,
|
492 |
+
"loss": 1.5077,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.013530738307677223,
|
497 |
+
"grad_norm": 8.169393539428711,
|
498 |
+
"learning_rate": 0.00019906031621167553,
|
499 |
+
"loss": 2.4139,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.013726835964310227,
|
504 |
+
"grad_norm": 15.750587463378906,
|
505 |
+
"learning_rate": 0.00019902824470433489,
|
506 |
+
"loss": 2.8999,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.01392293362094323,
|
511 |
+
"grad_norm": 19.615734100341797,
|
512 |
+
"learning_rate": 0.00019899563771122618,
|
513 |
+
"loss": 3.3154,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.014119031277576233,
|
518 |
+
"grad_norm": 24.015810012817383,
|
519 |
+
"learning_rate": 0.0001989624954086686,
|
520 |
+
"loss": 2.6689,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.014315128934209236,
|
525 |
+
"grad_norm": 7.955759525299072,
|
526 |
+
"learning_rate": 0.00019892881797587601,
|
527 |
+
"loss": 1.8847,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.01451122659084224,
|
532 |
+
"grad_norm": 13.804747581481934,
|
533 |
+
"learning_rate": 0.00019889460559495588,
|
534 |
+
"loss": 2.2221,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.014707324247475242,
|
539 |
+
"grad_norm": 19.74148941040039,
|
540 |
+
"learning_rate": 0.0001988598584509084,
|
541 |
+
"loss": 1.9316,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.014903421904108247,
|
546 |
+
"grad_norm": 7.9701385498046875,
|
547 |
+
"learning_rate": 0.00019882457673162543,
|
548 |
+
"loss": 2.1958,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.015099519560741249,
|
553 |
+
"grad_norm": 4.7594170570373535,
|
554 |
+
"learning_rate": 0.00019878876062788954,
|
555 |
+
"loss": 1.3551,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.015295617217374253,
|
560 |
+
"grad_norm": 7.796854496002197,
|
561 |
+
"learning_rate": 0.0001987524103333728,
|
562 |
+
"loss": 2.616,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.015491714874007256,
|
567 |
+
"grad_norm": 6.997422218322754,
|
568 |
+
"learning_rate": 0.00019871552604463602,
|
569 |
+
"loss": 2.908,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.01568781253064026,
|
574 |
+
"grad_norm": 6.436347484588623,
|
575 |
+
"learning_rate": 0.00019867810796112744,
|
576 |
+
"loss": 3.6826,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.01588391018727326,
|
581 |
+
"grad_norm": 10.243407249450684,
|
582 |
+
"learning_rate": 0.00019864015628518175,
|
583 |
+
"loss": 1.3711,
|
584 |
+
"step": 81
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.016080007843906265,
|
588 |
+
"grad_norm": 11.830530166625977,
|
589 |
+
"learning_rate": 0.00019860167122201904,
|
590 |
+
"loss": 2.2325,
|
591 |
+
"step": 82
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.01627610550053927,
|
595 |
+
"grad_norm": 7.456768989562988,
|
596 |
+
"learning_rate": 0.0001985626529797436,
|
597 |
+
"loss": 1.9991,
|
598 |
+
"step": 83
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.016472203157172273,
|
602 |
+
"grad_norm": 50.91776657104492,
|
603 |
+
"learning_rate": 0.00019852310176934288,
|
604 |
+
"loss": 1.294,
|
605 |
+
"step": 84
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.016668300813805274,
|
609 |
+
"grad_norm": 6.4661054611206055,
|
610 |
+
"learning_rate": 0.00019848301780468622,
|
611 |
+
"loss": 2.4052,
|
612 |
+
"step": 85
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.016864398470438278,
|
616 |
+
"grad_norm": 5.4749674797058105,
|
617 |
+
"learning_rate": 0.00019844240130252385,
|
618 |
+
"loss": 2.1508,
|
619 |
+
"step": 86
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.017060496127071282,
|
623 |
+
"grad_norm": 9.457857131958008,
|
624 |
+
"learning_rate": 0.00019840125248248564,
|
625 |
+
"loss": 2.1732,
|
626 |
+
"step": 87
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.017256593783704286,
|
630 |
+
"grad_norm": 6.932736396789551,
|
631 |
+
"learning_rate": 0.00019835957156707988,
|
632 |
+
"loss": 1.0618,
|
633 |
+
"step": 88
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.017452691440337287,
|
637 |
+
"grad_norm": 10.447488784790039,
|
638 |
+
"learning_rate": 0.00019831735878169212,
|
639 |
+
"loss": 1.1214,
|
640 |
+
"step": 89
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.01764878909697029,
|
644 |
+
"grad_norm": 7.159199237823486,
|
645 |
+
"learning_rate": 0.000198274614354584,
|
646 |
+
"loss": 2.495,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.017844886753603295,
|
651 |
+
"grad_norm": 8.753946304321289,
|
652 |
+
"learning_rate": 0.00019823133851689187,
|
653 |
+
"loss": 2.343,
|
654 |
+
"step": 91
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.0180409844102363,
|
658 |
+
"grad_norm": 9.124870300292969,
|
659 |
+
"learning_rate": 0.00019818753150262574,
|
660 |
+
"loss": 1.6556,
|
661 |
+
"step": 92
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.0182370820668693,
|
665 |
+
"grad_norm": 5.470896244049072,
|
666 |
+
"learning_rate": 0.00019814319354866786,
|
667 |
+
"loss": 1.2787,
|
668 |
+
"step": 93
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.018433179723502304,
|
672 |
+
"grad_norm": 8.39749526977539,
|
673 |
+
"learning_rate": 0.00019809832489477142,
|
674 |
+
"loss": 1.6804,
|
675 |
+
"step": 94
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.01862927738013531,
|
679 |
+
"grad_norm": 6.869524955749512,
|
680 |
+
"learning_rate": 0.0001980529257835594,
|
681 |
+
"loss": 1.6563,
|
682 |
+
"step": 95
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.01882537503676831,
|
686 |
+
"grad_norm": 11.144633293151855,
|
687 |
+
"learning_rate": 0.0001980069964605232,
|
688 |
+
"loss": 1.9428,
|
689 |
+
"step": 96
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.019021472693401313,
|
693 |
+
"grad_norm": 11.564960479736328,
|
694 |
+
"learning_rate": 0.00019796053717402118,
|
695 |
+
"loss": 2.2905,
|
696 |
+
"step": 97
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.019217570350034317,
|
700 |
+
"grad_norm": 4.628671169281006,
|
701 |
+
"learning_rate": 0.00019791354817527755,
|
702 |
+
"loss": 1.0654,
|
703 |
+
"step": 98
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.01941366800666732,
|
707 |
+
"grad_norm": 15.970938682556152,
|
708 |
+
"learning_rate": 0.00019786602971838074,
|
709 |
+
"loss": 2.9314,
|
710 |
+
"step": 99
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.019609765663300322,
|
714 |
+
"grad_norm": 5.425403594970703,
|
715 |
+
"learning_rate": 0.00019781798206028239,
|
716 |
+
"loss": 1.7236,
|
717 |
+
"step": 100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.019805863319933326,
|
721 |
+
"grad_norm": 5.114929676055908,
|
722 |
+
"learning_rate": 0.0001977694054607955,
|
723 |
+
"loss": 2.1674,
|
724 |
+
"step": 101
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.02000196097656633,
|
728 |
+
"grad_norm": 9.564162254333496,
|
729 |
+
"learning_rate": 0.0001977203001825935,
|
730 |
+
"loss": 2.3091,
|
731 |
+
"step": 102
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.020198058633199335,
|
735 |
+
"grad_norm": 7.184217929840088,
|
736 |
+
"learning_rate": 0.00019767066649120838,
|
737 |
+
"loss": 2.5231,
|
738 |
+
"step": 103
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.020394156289832335,
|
742 |
+
"grad_norm": 8.926065444946289,
|
743 |
+
"learning_rate": 0.00019762050465502965,
|
744 |
+
"loss": 1.3343,
|
745 |
+
"step": 104
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.02059025394646534,
|
749 |
+
"grad_norm": 5.511591911315918,
|
750 |
+
"learning_rate": 0.0001975698149453026,
|
751 |
+
"loss": 1.7055,
|
752 |
+
"step": 105
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.020786351603098344,
|
756 |
+
"grad_norm": 8.730749130249023,
|
757 |
+
"learning_rate": 0.00019751859763612704,
|
758 |
+
"loss": 1.7862,
|
759 |
+
"step": 106
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.020982449259731348,
|
763 |
+
"grad_norm": 10.519305229187012,
|
764 |
+
"learning_rate": 0.00019746685300445565,
|
765 |
+
"loss": 1.9938,
|
766 |
+
"step": 107
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.02117854691636435,
|
770 |
+
"grad_norm": 6.307378768920898,
|
771 |
+
"learning_rate": 0.00019741458133009258,
|
772 |
+
"loss": 1.5184,
|
773 |
+
"step": 108
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.021374644572997353,
|
777 |
+
"grad_norm": 10.66562557220459,
|
778 |
+
"learning_rate": 0.00019736178289569186,
|
779 |
+
"loss": 2.0555,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.021570742229630357,
|
784 |
+
"grad_norm": 6.235299587249756,
|
785 |
+
"learning_rate": 0.0001973084579867561,
|
786 |
+
"loss": 1.4547,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.021766839886263357,
|
791 |
+
"grad_norm": 12.061420440673828,
|
792 |
+
"learning_rate": 0.00019725460689163455,
|
793 |
+
"loss": 1.9823,
|
794 |
+
"step": 111
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.02196293754289636,
|
798 |
+
"grad_norm": 8.891043663024902,
|
799 |
+
"learning_rate": 0.0001972002299015219,
|
800 |
+
"loss": 2.4757,
|
801 |
+
"step": 112
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.022159035199529366,
|
805 |
+
"grad_norm": 8.200632095336914,
|
806 |
+
"learning_rate": 0.00019714532731045649,
|
807 |
+
"loss": 1.4906,
|
808 |
+
"step": 113
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.02235513285616237,
|
812 |
+
"grad_norm": 8.106672286987305,
|
813 |
+
"learning_rate": 0.00019708989941531887,
|
814 |
+
"loss": 0.8863,
|
815 |
+
"step": 114
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.02255123051279537,
|
819 |
+
"grad_norm": 6.451066493988037,
|
820 |
+
"learning_rate": 0.0001970339465158301,
|
821 |
+
"loss": 2.1244,
|
822 |
+
"step": 115
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.022747328169428375,
|
826 |
+
"grad_norm": 6.3670220375061035,
|
827 |
+
"learning_rate": 0.0001969774689145501,
|
828 |
+
"loss": 1.3732,
|
829 |
+
"step": 116
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.02294342582606138,
|
833 |
+
"grad_norm": 6.401678562164307,
|
834 |
+
"learning_rate": 0.0001969204669168761,
|
835 |
+
"loss": 1.3963,
|
836 |
+
"step": 117
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.023139523482694383,
|
840 |
+
"grad_norm": 6.917253494262695,
|
841 |
+
"learning_rate": 0.00019686294083104094,
|
842 |
+
"loss": 1.3802,
|
843 |
+
"step": 118
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.023335621139327384,
|
847 |
+
"grad_norm": 4.852232456207275,
|
848 |
+
"learning_rate": 0.00019680489096811149,
|
849 |
+
"loss": 0.7538,
|
850 |
+
"step": 119
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.023531718795960388,
|
854 |
+
"grad_norm": 5.08411169052124,
|
855 |
+
"learning_rate": 0.00019674631764198677,
|
856 |
+
"loss": 1.5128,
|
857 |
+
"step": 120
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.023727816452593392,
|
861 |
+
"grad_norm": 13.64840316772461,
|
862 |
+
"learning_rate": 0.00019668722116939649,
|
863 |
+
"loss": 1.2718,
|
864 |
+
"step": 121
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.023923914109226396,
|
868 |
+
"grad_norm": 7.075209617614746,
|
869 |
+
"learning_rate": 0.00019662760186989913,
|
870 |
+
"loss": 2.4186,
|
871 |
+
"step": 122
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.024120011765859397,
|
875 |
+
"grad_norm": 12.186111450195312,
|
876 |
+
"learning_rate": 0.00019656746006588044,
|
877 |
+
"loss": 2.8495,
|
878 |
+
"step": 123
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.0243161094224924,
|
882 |
+
"grad_norm": 13.221094131469727,
|
883 |
+
"learning_rate": 0.00019650679608255138,
|
884 |
+
"loss": 1.1832,
|
885 |
+
"step": 124
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.024512207079125405,
|
889 |
+
"grad_norm": 4.765728950500488,
|
890 |
+
"learning_rate": 0.0001964456102479467,
|
891 |
+
"loss": 1.1407,
|
892 |
+
"step": 125
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.024708304735758406,
|
896 |
+
"grad_norm": 4.750761032104492,
|
897 |
+
"learning_rate": 0.00019638390289292295,
|
898 |
+
"loss": 1.1096,
|
899 |
+
"step": 126
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.02490440239239141,
|
903 |
+
"grad_norm": 5.133049011230469,
|
904 |
+
"learning_rate": 0.0001963216743511567,
|
905 |
+
"loss": 2.6525,
|
906 |
+
"step": 127
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.025100500049024414,
|
910 |
+
"grad_norm": 14.541696548461914,
|
911 |
+
"learning_rate": 0.0001962589249591429,
|
912 |
+
"loss": 3.3739,
|
913 |
+
"step": 128
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.02529659770565742,
|
917 |
+
"grad_norm": 7.252123832702637,
|
918 |
+
"learning_rate": 0.00019619565505619288,
|
919 |
+
"loss": 2.0899,
|
920 |
+
"step": 129
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.02549269536229042,
|
924 |
+
"grad_norm": 7.14664888381958,
|
925 |
+
"learning_rate": 0.00019613186498443257,
|
926 |
+
"loss": 1.4538,
|
927 |
+
"step": 130
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.025688793018923423,
|
931 |
+
"grad_norm": 7.936334609985352,
|
932 |
+
"learning_rate": 0.0001960675550888007,
|
933 |
+
"loss": 1.351,
|
934 |
+
"step": 131
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.025884890675556427,
|
938 |
+
"grad_norm": 7.465827465057373,
|
939 |
+
"learning_rate": 0.00019600272571704687,
|
940 |
+
"loss": 1.0752,
|
941 |
+
"step": 132
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.02608098833218943,
|
945 |
+
"grad_norm": 12.85190486907959,
|
946 |
+
"learning_rate": 0.00019593737721972977,
|
947 |
+
"loss": 2.5674,
|
948 |
+
"step": 133
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.026277085988822432,
|
952 |
+
"grad_norm": 8.640382766723633,
|
953 |
+
"learning_rate": 0.00019587150995021505,
|
954 |
+
"loss": 2.5631,
|
955 |
+
"step": 134
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.026473183645455436,
|
959 |
+
"grad_norm": 5.070466995239258,
|
960 |
+
"learning_rate": 0.00019580512426467376,
|
961 |
+
"loss": 0.8935,
|
962 |
+
"step": 135
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.02666928130208844,
|
966 |
+
"grad_norm": 5.741654872894287,
|
967 |
+
"learning_rate": 0.00019573822052208013,
|
968 |
+
"loss": 2.1005,
|
969 |
+
"step": 136
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.026865378958721445,
|
973 |
+
"grad_norm": 8.615095138549805,
|
974 |
+
"learning_rate": 0.00019567079908420972,
|
975 |
+
"loss": 2.7478,
|
976 |
+
"step": 137
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.027061476615354445,
|
980 |
+
"grad_norm": 15.559739112854004,
|
981 |
+
"learning_rate": 0.00019560286031563754,
|
982 |
+
"loss": 1.8455,
|
983 |
+
"step": 138
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.02725757427198745,
|
987 |
+
"grad_norm": 5.683060169219971,
|
988 |
+
"learning_rate": 0.000195534404583736,
|
989 |
+
"loss": 1.6896,
|
990 |
+
"step": 139
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.027453671928620454,
|
994 |
+
"grad_norm": 5.791153430938721,
|
995 |
+
"learning_rate": 0.00019546543225867292,
|
996 |
+
"loss": 1.9291,
|
997 |
+
"step": 140
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.027649769585253458,
|
1001 |
+
"grad_norm": 6.800760269165039,
|
1002 |
+
"learning_rate": 0.0001953959437134095,
|
1003 |
+
"loss": 1.789,
|
1004 |
+
"step": 141
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.02784586724188646,
|
1008 |
+
"grad_norm": 6.912458896636963,
|
1009 |
+
"learning_rate": 0.00019532593932369849,
|
1010 |
+
"loss": 2.2544,
|
1011 |
+
"step": 142
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.028041964898519463,
|
1015 |
+
"grad_norm": 6.928767681121826,
|
1016 |
+
"learning_rate": 0.00019525541946808188,
|
1017 |
+
"loss": 1.2531,
|
1018 |
+
"step": 143
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.028238062555152467,
|
1022 |
+
"grad_norm": 8.96179485321045,
|
1023 |
+
"learning_rate": 0.00019518438452788907,
|
1024 |
+
"loss": 2.3403,
|
1025 |
+
"step": 144
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.028434160211785468,
|
1029 |
+
"grad_norm": 7.004507064819336,
|
1030 |
+
"learning_rate": 0.00019511283488723473,
|
1031 |
+
"loss": 1.1211,
|
1032 |
+
"step": 145
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.028630257868418472,
|
1036 |
+
"grad_norm": 8.655360221862793,
|
1037 |
+
"learning_rate": 0.00019504077093301665,
|
1038 |
+
"loss": 1.6074,
|
1039 |
+
"step": 146
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.028826355525051476,
|
1043 |
+
"grad_norm": 7.188142776489258,
|
1044 |
+
"learning_rate": 0.00019496819305491383,
|
1045 |
+
"loss": 1.3564,
|
1046 |
+
"step": 147
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.02902245318168448,
|
1050 |
+
"grad_norm": 5.618204116821289,
|
1051 |
+
"learning_rate": 0.00019489510164538416,
|
1052 |
+
"loss": 2.5936,
|
1053 |
+
"step": 148
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.02921855083831748,
|
1057 |
+
"grad_norm": 6.578945159912109,
|
1058 |
+
"learning_rate": 0.00019482149709966246,
|
1059 |
+
"loss": 0.9577,
|
1060 |
+
"step": 149
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.029414648494950485,
|
1064 |
+
"grad_norm": 11.468759536743164,
|
1065 |
+
"learning_rate": 0.00019474737981575832,
|
1066 |
+
"loss": 2.1746,
|
1067 |
+
"step": 150
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.02961074615158349,
|
1071 |
+
"grad_norm": 5.663360595703125,
|
1072 |
+
"learning_rate": 0.00019467275019445385,
|
1073 |
+
"loss": 1.2751,
|
1074 |
+
"step": 151
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.029806843808216493,
|
1078 |
+
"grad_norm": 6.297888278961182,
|
1079 |
+
"learning_rate": 0.00019459760863930155,
|
1080 |
+
"loss": 1.574,
|
1081 |
+
"step": 152
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.030002941464849494,
|
1085 |
+
"grad_norm": 8.760517120361328,
|
1086 |
+
"learning_rate": 0.00019452195555662224,
|
1087 |
+
"loss": 1.1148,
|
1088 |
+
"step": 153
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.030199039121482498,
|
1092 |
+
"grad_norm": 8.745152473449707,
|
1093 |
+
"learning_rate": 0.00019444579135550273,
|
1094 |
+
"loss": 1.4212,
|
1095 |
+
"step": 154
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.030395136778115502,
|
1099 |
+
"grad_norm": 7.594636917114258,
|
1100 |
+
"learning_rate": 0.00019436911644779366,
|
1101 |
+
"loss": 0.9161,
|
1102 |
+
"step": 155
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.030591234434748506,
|
1106 |
+
"grad_norm": 8.563089370727539,
|
1107 |
+
"learning_rate": 0.00019429193124810725,
|
1108 |
+
"loss": 1.5844,
|
1109 |
+
"step": 156
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.030787332091381507,
|
1113 |
+
"grad_norm": 16.4445743560791,
|
1114 |
+
"learning_rate": 0.00019421423617381508,
|
1115 |
+
"loss": 1.4798,
|
1116 |
+
"step": 157
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.03098342974801451,
|
1120 |
+
"grad_norm": 6.86074161529541,
|
1121 |
+
"learning_rate": 0.00019413603164504588,
|
1122 |
+
"loss": 2.3323,
|
1123 |
+
"step": 158
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.031179527404647515,
|
1127 |
+
"grad_norm": 11.293970108032227,
|
1128 |
+
"learning_rate": 0.0001940573180846831,
|
1129 |
+
"loss": 2.0304,
|
1130 |
+
"step": 159
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.03137562506128052,
|
1134 |
+
"grad_norm": 9.772544860839844,
|
1135 |
+
"learning_rate": 0.00019397809591836286,
|
1136 |
+
"loss": 3.1622,
|
1137 |
+
"step": 160
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.031571722717913524,
|
1141 |
+
"grad_norm": 8.489032745361328,
|
1142 |
+
"learning_rate": 0.00019389836557447143,
|
1143 |
+
"loss": 1.0113,
|
1144 |
+
"step": 161
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.03176782037454652,
|
1148 |
+
"grad_norm": 12.992219924926758,
|
1149 |
+
"learning_rate": 0.000193818127484143,
|
1150 |
+
"loss": 2.5478,
|
1151 |
+
"step": 162
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.031963918031179525,
|
1155 |
+
"grad_norm": 6.758875846862793,
|
1156 |
+
"learning_rate": 0.0001937373820812574,
|
1157 |
+
"loss": 1.8935,
|
1158 |
+
"step": 163
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.03216001568781253,
|
1162 |
+
"grad_norm": 11.88957405090332,
|
1163 |
+
"learning_rate": 0.0001936561298024377,
|
1164 |
+
"loss": 3.1899,
|
1165 |
+
"step": 164
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.03235611334444553,
|
1169 |
+
"grad_norm": 8.777862548828125,
|
1170 |
+
"learning_rate": 0.00019357437108704777,
|
1171 |
+
"loss": 2.7038,
|
1172 |
+
"step": 165
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.03255221100107854,
|
1176 |
+
"grad_norm": 5.135364532470703,
|
1177 |
+
"learning_rate": 0.0001934921063771901,
|
1178 |
+
"loss": 0.7644,
|
1179 |
+
"step": 166
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.03274830865771154,
|
1183 |
+
"grad_norm": 9.942065238952637,
|
1184 |
+
"learning_rate": 0.00019340933611770321,
|
1185 |
+
"loss": 1.4148,
|
1186 |
+
"step": 167
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.032944406314344546,
|
1190 |
+
"grad_norm": 7.881731033325195,
|
1191 |
+
"learning_rate": 0.0001933260607561594,
|
1192 |
+
"loss": 1.7402,
|
1193 |
+
"step": 168
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.03314050397097755,
|
1197 |
+
"grad_norm": 6.189711570739746,
|
1198 |
+
"learning_rate": 0.00019324228074286222,
|
1199 |
+
"loss": 1.642,
|
1200 |
+
"step": 169
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.03333660162761055,
|
1204 |
+
"grad_norm": 4.979406356811523,
|
1205 |
+
"learning_rate": 0.00019315799653084404,
|
1206 |
+
"loss": 2.425,
|
1207 |
+
"step": 170
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.03353269928424355,
|
1211 |
+
"grad_norm": 8.461871147155762,
|
1212 |
+
"learning_rate": 0.00019307320857586376,
|
1213 |
+
"loss": 2.6563,
|
1214 |
+
"step": 171
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.033728796940876556,
|
1218 |
+
"grad_norm": 8.992694854736328,
|
1219 |
+
"learning_rate": 0.00019298791733640406,
|
1220 |
+
"loss": 1.7962,
|
1221 |
+
"step": 172
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.03392489459750956,
|
1225 |
+
"grad_norm": 8.074629783630371,
|
1226 |
+
"learning_rate": 0.00019290212327366924,
|
1227 |
+
"loss": 1.5342,
|
1228 |
+
"step": 173
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.034120992254142564,
|
1232 |
+
"grad_norm": 6.5658111572265625,
|
1233 |
+
"learning_rate": 0.00019281582685158247,
|
1234 |
+
"loss": 0.7919,
|
1235 |
+
"step": 174
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.03431708991077557,
|
1239 |
+
"grad_norm": 9.946451187133789,
|
1240 |
+
"learning_rate": 0.00019272902853678336,
|
1241 |
+
"loss": 1.5664,
|
1242 |
+
"step": 175
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.03451318756740857,
|
1246 |
+
"grad_norm": 6.764862060546875,
|
1247 |
+
"learning_rate": 0.00019264172879862552,
|
1248 |
+
"loss": 2.1083,
|
1249 |
+
"step": 176
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.03470928522404157,
|
1253 |
+
"grad_norm": 11.195146560668945,
|
1254 |
+
"learning_rate": 0.000192553928109174,
|
1255 |
+
"loss": 1.3371,
|
1256 |
+
"step": 177
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.034905382880674574,
|
1260 |
+
"grad_norm": 6.352316856384277,
|
1261 |
+
"learning_rate": 0.00019246562694320255,
|
1262 |
+
"loss": 2.543,
|
1263 |
+
"step": 178
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.03510148053730758,
|
1267 |
+
"grad_norm": 4.030996799468994,
|
1268 |
+
"learning_rate": 0.00019237682577819137,
|
1269 |
+
"loss": 0.9273,
|
1270 |
+
"step": 179
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.03529757819394058,
|
1274 |
+
"grad_norm": 6.009339809417725,
|
1275 |
+
"learning_rate": 0.00019228752509432417,
|
1276 |
+
"loss": 2.1444,
|
1277 |
+
"step": 180
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.035493675850573586,
|
1281 |
+
"grad_norm": 14.911331176757812,
|
1282 |
+
"learning_rate": 0.00019219772537448597,
|
1283 |
+
"loss": 1.5989,
|
1284 |
+
"step": 181
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.03568977350720659,
|
1288 |
+
"grad_norm": 6.454592227935791,
|
1289 |
+
"learning_rate": 0.00019210742710426012,
|
1290 |
+
"loss": 1.0608,
|
1291 |
+
"step": 182
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.035885871163839594,
|
1295 |
+
"grad_norm": 11.354242324829102,
|
1296 |
+
"learning_rate": 0.00019201663077192586,
|
1297 |
+
"loss": 1.7558,
|
1298 |
+
"step": 183
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.0360819688204726,
|
1302 |
+
"grad_norm": 5.804329872131348,
|
1303 |
+
"learning_rate": 0.0001919253368684557,
|
1304 |
+
"loss": 1.411,
|
1305 |
+
"step": 184
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.036278066477105596,
|
1309 |
+
"grad_norm": 6.735583305358887,
|
1310 |
+
"learning_rate": 0.00019183354588751271,
|
1311 |
+
"loss": 2.4473,
|
1312 |
+
"step": 185
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.0364741641337386,
|
1316 |
+
"grad_norm": 9.169321060180664,
|
1317 |
+
"learning_rate": 0.00019174125832544786,
|
1318 |
+
"loss": 1.8947,
|
1319 |
+
"step": 186
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.036670261790371604,
|
1323 |
+
"grad_norm": 3.465175151824951,
|
1324 |
+
"learning_rate": 0.0001916484746812973,
|
1325 |
+
"loss": 1.1306,
|
1326 |
+
"step": 187
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.03686635944700461,
|
1330 |
+
"grad_norm": 10.71740436553955,
|
1331 |
+
"learning_rate": 0.0001915551954567797,
|
1332 |
+
"loss": 1.0832,
|
1333 |
+
"step": 188
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.03706245710363761,
|
1337 |
+
"grad_norm": 10.946560859680176,
|
1338 |
+
"learning_rate": 0.0001914614211562936,
|
1339 |
+
"loss": 1.9391,
|
1340 |
+
"step": 189
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.03725855476027062,
|
1344 |
+
"grad_norm": 6.847762584686279,
|
1345 |
+
"learning_rate": 0.0001913671522869145,
|
1346 |
+
"loss": 2.197,
|
1347 |
+
"step": 190
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.03745465241690362,
|
1351 |
+
"grad_norm": 13.330089569091797,
|
1352 |
+
"learning_rate": 0.00019127238935839235,
|
1353 |
+
"loss": 2.3539,
|
1354 |
+
"step": 191
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.03765075007353662,
|
1358 |
+
"grad_norm": 22.94158172607422,
|
1359 |
+
"learning_rate": 0.00019117713288314863,
|
1360 |
+
"loss": 2.868,
|
1361 |
+
"step": 192
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.03784684773016962,
|
1365 |
+
"grad_norm": 7.080881595611572,
|
1366 |
+
"learning_rate": 0.00019108138337627358,
|
1367 |
+
"loss": 1.7925,
|
1368 |
+
"step": 193
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.038042945386802626,
|
1372 |
+
"grad_norm": 4.726489067077637,
|
1373 |
+
"learning_rate": 0.00019098514135552357,
|
1374 |
+
"loss": 1.008,
|
1375 |
+
"step": 194
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.03823904304343563,
|
1379 |
+
"grad_norm": 5.7414870262146,
|
1380 |
+
"learning_rate": 0.00019088840734131807,
|
1381 |
+
"loss": 0.8934,
|
1382 |
+
"step": 195
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.038435140700068635,
|
1386 |
+
"grad_norm": 6.781312465667725,
|
1387 |
+
"learning_rate": 0.00019079118185673705,
|
1388 |
+
"loss": 1.6637,
|
1389 |
+
"step": 196
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.03863123835670164,
|
1393 |
+
"grad_norm": 12.264861106872559,
|
1394 |
+
"learning_rate": 0.00019069346542751803,
|
1395 |
+
"loss": 1.6055,
|
1396 |
+
"step": 197
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.03882733601333464,
|
1400 |
+
"grad_norm": 8.975689888000488,
|
1401 |
+
"learning_rate": 0.00019059525858205323,
|
1402 |
+
"loss": 2.6467,
|
1403 |
+
"step": 198
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.03902343366996765,
|
1407 |
+
"grad_norm": 9.027484893798828,
|
1408 |
+
"learning_rate": 0.0001904965618513868,
|
1409 |
+
"loss": 1.9813,
|
1410 |
+
"step": 199
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.039219531326600644,
|
1414 |
+
"grad_norm": 9.491011619567871,
|
1415 |
+
"learning_rate": 0.0001903973757692119,
|
1416 |
+
"loss": 1.4225,
|
1417 |
+
"step": 200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.03941562898323365,
|
1421 |
+
"grad_norm": 5.202075481414795,
|
1422 |
+
"learning_rate": 0.00019029770087186773,
|
1423 |
+
"loss": 1.3524,
|
1424 |
+
"step": 201
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.03961172663986665,
|
1428 |
+
"grad_norm": 11.139556884765625,
|
1429 |
+
"learning_rate": 0.00019019753769833678,
|
1430 |
+
"loss": 2.0723,
|
1431 |
+
"step": 202
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.03980782429649966,
|
1435 |
+
"grad_norm": 11.383284568786621,
|
1436 |
+
"learning_rate": 0.0001900968867902419,
|
1437 |
+
"loss": 1.5843,
|
1438 |
+
"step": 203
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.04000392195313266,
|
1442 |
+
"grad_norm": 7.112687110900879,
|
1443 |
+
"learning_rate": 0.00018999574869184324,
|
1444 |
+
"loss": 1.3899,
|
1445 |
+
"step": 204
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.040200019609765665,
|
1449 |
+
"grad_norm": 13.50672721862793,
|
1450 |
+
"learning_rate": 0.00018989412395003537,
|
1451 |
+
"loss": 1.7484,
|
1452 |
+
"step": 205
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.04039611726639867,
|
1456 |
+
"grad_norm": 13.107057571411133,
|
1457 |
+
"learning_rate": 0.00018979201311434434,
|
1458 |
+
"loss": 1.6412,
|
1459 |
+
"step": 206
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.040592214923031666,
|
1463 |
+
"grad_norm": 11.221402168273926,
|
1464 |
+
"learning_rate": 0.0001896894167369248,
|
1465 |
+
"loss": 2.608,
|
1466 |
+
"step": 207
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.04078831257966467,
|
1470 |
+
"grad_norm": 4.945010662078857,
|
1471 |
+
"learning_rate": 0.0001895863353725568,
|
1472 |
+
"loss": 1.3582,
|
1473 |
+
"step": 208
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.040984410236297675,
|
1477 |
+
"grad_norm": 15.066801071166992,
|
1478 |
+
"learning_rate": 0.00018948276957864299,
|
1479 |
+
"loss": 1.7296,
|
1480 |
+
"step": 209
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.04118050789293068,
|
1484 |
+
"grad_norm": 7.497617244720459,
|
1485 |
+
"learning_rate": 0.0001893787199152055,
|
1486 |
+
"loss": 1.4961,
|
1487 |
+
"step": 210
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.04137660554956368,
|
1491 |
+
"grad_norm": 4.299473762512207,
|
1492 |
+
"learning_rate": 0.00018927418694488296,
|
1493 |
+
"loss": 1.7403,
|
1494 |
+
"step": 211
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.04157270320619669,
|
1498 |
+
"grad_norm": 6.988886833190918,
|
1499 |
+
"learning_rate": 0.00018916917123292738,
|
1500 |
+
"loss": 2.6546,
|
1501 |
+
"step": 212
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.04176880086282969,
|
1505 |
+
"grad_norm": 9.461721420288086,
|
1506 |
+
"learning_rate": 0.00018906367334720124,
|
1507 |
+
"loss": 2.067,
|
1508 |
+
"step": 213
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.041964898519462696,
|
1512 |
+
"grad_norm": 4.021213054656982,
|
1513 |
+
"learning_rate": 0.0001889576938581742,
|
1514 |
+
"loss": 1.0274,
|
1515 |
+
"step": 214
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.04216099617609569,
|
1519 |
+
"grad_norm": 7.254751205444336,
|
1520 |
+
"learning_rate": 0.00018885123333892026,
|
1521 |
+
"loss": 1.7091,
|
1522 |
+
"step": 215
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.0423570938327287,
|
1526 |
+
"grad_norm": 10.783350944519043,
|
1527 |
+
"learning_rate": 0.00018874429236511448,
|
1528 |
+
"loss": 1.3779,
|
1529 |
+
"step": 216
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.0425531914893617,
|
1533 |
+
"grad_norm": 16.38484764099121,
|
1534 |
+
"learning_rate": 0.00018863687151503,
|
1535 |
+
"loss": 2.8516,
|
1536 |
+
"step": 217
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.042749289145994705,
|
1540 |
+
"grad_norm": 5.848017692565918,
|
1541 |
+
"learning_rate": 0.00018852897136953473,
|
1542 |
+
"loss": 1.6814,
|
1543 |
+
"step": 218
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.04294538680262771,
|
1547 |
+
"grad_norm": 5.781267166137695,
|
1548 |
+
"learning_rate": 0.00018842059251208845,
|
1549 |
+
"loss": 2.1672,
|
1550 |
+
"step": 219
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.043141484459260714,
|
1554 |
+
"grad_norm": 6.244543552398682,
|
1555 |
+
"learning_rate": 0.00018831173552873946,
|
1556 |
+
"loss": 0.6934,
|
1557 |
+
"step": 220
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.04333758211589372,
|
1561 |
+
"grad_norm": 6.526815414428711,
|
1562 |
+
"learning_rate": 0.0001882024010081215,
|
1563 |
+
"loss": 1.6071,
|
1564 |
+
"step": 221
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.043533679772526715,
|
1568 |
+
"grad_norm": 6.064664363861084,
|
1569 |
+
"learning_rate": 0.00018809258954145052,
|
1570 |
+
"loss": 1.8964,
|
1571 |
+
"step": 222
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.04372977742915972,
|
1575 |
+
"grad_norm": 6.710343837738037,
|
1576 |
+
"learning_rate": 0.0001879823017225215,
|
1577 |
+
"loss": 2.063,
|
1578 |
+
"step": 223
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.04392587508579272,
|
1582 |
+
"grad_norm": 9.060622215270996,
|
1583 |
+
"learning_rate": 0.00018787153814770537,
|
1584 |
+
"loss": 1.568,
|
1585 |
+
"step": 224
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.04412197274242573,
|
1589 |
+
"grad_norm": 4.686062335968018,
|
1590 |
+
"learning_rate": 0.00018776029941594552,
|
1591 |
+
"loss": 1.1178,
|
1592 |
+
"step": 225
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.04431807039905873,
|
1596 |
+
"grad_norm": 6.257881164550781,
|
1597 |
+
"learning_rate": 0.00018764858612875472,
|
1598 |
+
"loss": 2.1195,
|
1599 |
+
"step": 226
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.044514168055691736,
|
1603 |
+
"grad_norm": 9.814234733581543,
|
1604 |
+
"learning_rate": 0.00018753639889021196,
|
1605 |
+
"loss": 1.1679,
|
1606 |
+
"step": 227
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.04471026571232474,
|
1610 |
+
"grad_norm": 13.946937561035156,
|
1611 |
+
"learning_rate": 0.00018742373830695898,
|
1612 |
+
"loss": 1.6899,
|
1613 |
+
"step": 228
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.044906363368957744,
|
1617 |
+
"grad_norm": 6.277964115142822,
|
1618 |
+
"learning_rate": 0.0001873106049881971,
|
1619 |
+
"loss": 1.5076,
|
1620 |
+
"step": 229
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.04510246102559074,
|
1624 |
+
"grad_norm": 14.092109680175781,
|
1625 |
+
"learning_rate": 0.00018719699954568398,
|
1626 |
+
"loss": 1.9726,
|
1627 |
+
"step": 230
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.045298558682223745,
|
1631 |
+
"grad_norm": 6.5708231925964355,
|
1632 |
+
"learning_rate": 0.00018708292259373015,
|
1633 |
+
"loss": 0.6623,
|
1634 |
+
"step": 231
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.04549465633885675,
|
1638 |
+
"grad_norm": 6.839974880218506,
|
1639 |
+
"learning_rate": 0.00018696837474919582,
|
1640 |
+
"loss": 1.8836,
|
1641 |
+
"step": 232
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.045690753995489754,
|
1645 |
+
"grad_norm": 17.919775009155273,
|
1646 |
+
"learning_rate": 0.00018685335663148753,
|
1647 |
+
"loss": 2.2343,
|
1648 |
+
"step": 233
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.04588685165212276,
|
1652 |
+
"grad_norm": 7.140262603759766,
|
1653 |
+
"learning_rate": 0.00018673786886255476,
|
1654 |
+
"loss": 1.9653,
|
1655 |
+
"step": 234
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.04608294930875576,
|
1659 |
+
"grad_norm": 11.049707412719727,
|
1660 |
+
"learning_rate": 0.00018662191206688658,
|
1661 |
+
"loss": 1.8658,
|
1662 |
+
"step": 235
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.046279046965388766,
|
1666 |
+
"grad_norm": 5.617869853973389,
|
1667 |
+
"learning_rate": 0.00018650548687150823,
|
1668 |
+
"loss": 1.862,
|
1669 |
+
"step": 236
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.04647514462202176,
|
1673 |
+
"grad_norm": 6.494004726409912,
|
1674 |
+
"learning_rate": 0.00018638859390597792,
|
1675 |
+
"loss": 3.787,
|
1676 |
+
"step": 237
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.04667124227865477,
|
1680 |
+
"grad_norm": 17.628082275390625,
|
1681 |
+
"learning_rate": 0.00018627123380238314,
|
1682 |
+
"loss": 1.9129,
|
1683 |
+
"step": 238
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.04686733993528777,
|
1687 |
+
"grad_norm": 5.634758949279785,
|
1688 |
+
"learning_rate": 0.0001861534071953374,
|
1689 |
+
"loss": 1.4702,
|
1690 |
+
"step": 239
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.047063437591920776,
|
1694 |
+
"grad_norm": 20.99329948425293,
|
1695 |
+
"learning_rate": 0.00018603511472197685,
|
1696 |
+
"loss": 2.2196,
|
1697 |
+
"step": 240
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.04725953524855378,
|
1701 |
+
"grad_norm": 6.650235652923584,
|
1702 |
+
"learning_rate": 0.00018591635702195673,
|
1703 |
+
"loss": 0.986,
|
1704 |
+
"step": 241
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.047455632905186784,
|
1708 |
+
"grad_norm": 4.837536334991455,
|
1709 |
+
"learning_rate": 0.00018579713473744795,
|
1710 |
+
"loss": 1.2033,
|
1711 |
+
"step": 242
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.04765173056181979,
|
1715 |
+
"grad_norm": 9.390655517578125,
|
1716 |
+
"learning_rate": 0.00018567744851313362,
|
1717 |
+
"loss": 1.7356,
|
1718 |
+
"step": 243
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.04784782821845279,
|
1722 |
+
"grad_norm": 8.881529808044434,
|
1723 |
+
"learning_rate": 0.0001855572989962056,
|
1724 |
+
"loss": 1.0063,
|
1725 |
+
"step": 244
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.04804392587508579,
|
1729 |
+
"grad_norm": 6.325936317443848,
|
1730 |
+
"learning_rate": 0.00018543668683636085,
|
1731 |
+
"loss": 1.5957,
|
1732 |
+
"step": 245
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.048240023531718794,
|
1736 |
+
"grad_norm": 10.866408348083496,
|
1737 |
+
"learning_rate": 0.0001853156126857981,
|
1738 |
+
"loss": 2.0472,
|
1739 |
+
"step": 246
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.0484361211883518,
|
1743 |
+
"grad_norm": 6.741912364959717,
|
1744 |
+
"learning_rate": 0.00018519407719921427,
|
1745 |
+
"loss": 1.6029,
|
1746 |
+
"step": 247
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.0486322188449848,
|
1750 |
+
"grad_norm": 5.979978561401367,
|
1751 |
+
"learning_rate": 0.00018507208103380092,
|
1752 |
+
"loss": 0.9353,
|
1753 |
+
"step": 248
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.048828316501617806,
|
1757 |
+
"grad_norm": 6.375998020172119,
|
1758 |
+
"learning_rate": 0.00018494962484924058,
|
1759 |
+
"loss": 2.5973,
|
1760 |
+
"step": 249
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.04902441415825081,
|
1764 |
+
"grad_norm": 8.528829574584961,
|
1765 |
+
"learning_rate": 0.00018482670930770342,
|
1766 |
+
"loss": 1.1618,
|
1767 |
+
"step": 250
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.049220511814883815,
|
1771 |
+
"grad_norm": 7.874660491943359,
|
1772 |
+
"learning_rate": 0.0001847033350738435,
|
1773 |
+
"loss": 1.3043,
|
1774 |
+
"step": 251
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 0.04941660947151681,
|
1778 |
+
"grad_norm": 4.421433925628662,
|
1779 |
+
"learning_rate": 0.00018457950281479513,
|
1780 |
+
"loss": 2.0768,
|
1781 |
+
"step": 252
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.049612707128149816,
|
1785 |
+
"grad_norm": 8.347919464111328,
|
1786 |
+
"learning_rate": 0.00018445521320016944,
|
1787 |
+
"loss": 1.0983,
|
1788 |
+
"step": 253
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 0.04980880478478282,
|
1792 |
+
"grad_norm": 6.713651657104492,
|
1793 |
+
"learning_rate": 0.00018433046690205068,
|
1794 |
+
"loss": 0.9891,
|
1795 |
+
"step": 254
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.050004902441415824,
|
1799 |
+
"grad_norm": 12.359843254089355,
|
1800 |
+
"learning_rate": 0.0001842052645949925,
|
1801 |
+
"loss": 2.5271,
|
1802 |
+
"step": 255
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 0.05020100009804883,
|
1806 |
+
"grad_norm": 4.7271199226379395,
|
1807 |
+
"learning_rate": 0.00018407960695601442,
|
1808 |
+
"loss": 1.394,
|
1809 |
+
"step": 256
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.05039709775468183,
|
1813 |
+
"grad_norm": 5.810708522796631,
|
1814 |
+
"learning_rate": 0.0001839534946645981,
|
1815 |
+
"loss": 1.7354,
|
1816 |
+
"step": 257
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 0.05059319541131484,
|
1820 |
+
"grad_norm": 28.575908660888672,
|
1821 |
+
"learning_rate": 0.00018382692840268367,
|
1822 |
+
"loss": 3.4793,
|
1823 |
+
"step": 258
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 0.05078929306794784,
|
1827 |
+
"grad_norm": 5.775376319885254,
|
1828 |
+
"learning_rate": 0.00018369990885466617,
|
1829 |
+
"loss": 1.4695,
|
1830 |
+
"step": 259
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 0.05098539072458084,
|
1834 |
+
"grad_norm": 7.531515121459961,
|
1835 |
+
"learning_rate": 0.0001835724367073916,
|
1836 |
+
"loss": 2.0772,
|
1837 |
+
"step": 260
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 0.05118148838121384,
|
1841 |
+
"grad_norm": 5.099686145782471,
|
1842 |
+
"learning_rate": 0.00018344451265015348,
|
1843 |
+
"loss": 3.2733,
|
1844 |
+
"step": 261
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.05137758603784685,
|
1848 |
+
"grad_norm": 5.558218479156494,
|
1849 |
+
"learning_rate": 0.00018331613737468887,
|
1850 |
+
"loss": 1.7578,
|
1851 |
+
"step": 262
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.05157368369447985,
|
1855 |
+
"grad_norm": 7.837512016296387,
|
1856 |
+
"learning_rate": 0.00018318731157517478,
|
1857 |
+
"loss": 2.7413,
|
1858 |
+
"step": 263
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 0.051769781351112855,
|
1862 |
+
"grad_norm": 9.013374328613281,
|
1863 |
+
"learning_rate": 0.00018305803594822448,
|
1864 |
+
"loss": 1.7722,
|
1865 |
+
"step": 264
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 0.05196587900774586,
|
1869 |
+
"grad_norm": 7.108828067779541,
|
1870 |
+
"learning_rate": 0.00018292831119288348,
|
1871 |
+
"loss": 1.31,
|
1872 |
+
"step": 265
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 0.05216197666437886,
|
1876 |
+
"grad_norm": 6.387202739715576,
|
1877 |
+
"learning_rate": 0.0001827981380106261,
|
1878 |
+
"loss": 1.0588,
|
1879 |
+
"step": 266
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 0.05235807432101187,
|
1883 |
+
"grad_norm": 13.306784629821777,
|
1884 |
+
"learning_rate": 0.00018266751710535131,
|
1885 |
+
"loss": 2.6092,
|
1886 |
+
"step": 267
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 0.052554171977644865,
|
1890 |
+
"grad_norm": 7.774232864379883,
|
1891 |
+
"learning_rate": 0.00018253644918337915,
|
1892 |
+
"loss": 1.2318,
|
1893 |
+
"step": 268
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.05275026963427787,
|
1897 |
+
"grad_norm": 5.396208763122559,
|
1898 |
+
"learning_rate": 0.00018240493495344694,
|
1899 |
+
"loss": 1.2144,
|
1900 |
+
"step": 269
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 0.05294636729091087,
|
1904 |
+
"grad_norm": 13.393839836120605,
|
1905 |
+
"learning_rate": 0.0001822729751267053,
|
1906 |
+
"loss": 2.4278,
|
1907 |
+
"step": 270
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 0.05314246494754388,
|
1911 |
+
"grad_norm": 14.873156547546387,
|
1912 |
+
"learning_rate": 0.00018214057041671434,
|
1913 |
+
"loss": 2.4015,
|
1914 |
+
"step": 271
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.05333856260417688,
|
1918 |
+
"grad_norm": 7.224187850952148,
|
1919 |
+
"learning_rate": 0.00018200772153943988,
|
1920 |
+
"loss": 1.578,
|
1921 |
+
"step": 272
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.053534660260809885,
|
1925 |
+
"grad_norm": 16.03417205810547,
|
1926 |
+
"learning_rate": 0.00018187442921324958,
|
1927 |
+
"loss": 2.4634,
|
1928 |
+
"step": 273
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.05373075791744289,
|
1932 |
+
"grad_norm": 6.284254550933838,
|
1933 |
+
"learning_rate": 0.00018174069415890888,
|
1934 |
+
"loss": 1.1995,
|
1935 |
+
"step": 274
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.05392685557407589,
|
1939 |
+
"grad_norm": 5.986271858215332,
|
1940 |
+
"learning_rate": 0.00018160651709957736,
|
1941 |
+
"loss": 1.8718,
|
1942 |
+
"step": 275
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.05412295323070889,
|
1946 |
+
"grad_norm": 13.663339614868164,
|
1947 |
+
"learning_rate": 0.00018147189876080463,
|
1948 |
+
"loss": 1.8664,
|
1949 |
+
"step": 276
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 0.054319050887341895,
|
1953 |
+
"grad_norm": 8.843401908874512,
|
1954 |
+
"learning_rate": 0.0001813368398705265,
|
1955 |
+
"loss": 4.1059,
|
1956 |
+
"step": 277
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 0.0545151485439749,
|
1960 |
+
"grad_norm": 6.658843994140625,
|
1961 |
+
"learning_rate": 0.00018120134115906096,
|
1962 |
+
"loss": 0.8269,
|
1963 |
+
"step": 278
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 0.0547112462006079,
|
1967 |
+
"grad_norm": 14.153685569763184,
|
1968 |
+
"learning_rate": 0.0001810654033591044,
|
1969 |
+
"loss": 1.9537,
|
1970 |
+
"step": 279
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.05490734385724091,
|
1974 |
+
"grad_norm": 5.585552215576172,
|
1975 |
+
"learning_rate": 0.00018092902720572745,
|
1976 |
+
"loss": 1.2531,
|
1977 |
+
"step": 280
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.05510344151387391,
|
1981 |
+
"grad_norm": 6.414156436920166,
|
1982 |
+
"learning_rate": 0.00018079221343637113,
|
1983 |
+
"loss": 0.9456,
|
1984 |
+
"step": 281
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 0.055299539170506916,
|
1988 |
+
"grad_norm": 6.674518585205078,
|
1989 |
+
"learning_rate": 0.00018065496279084283,
|
1990 |
+
"loss": 1.1899,
|
1991 |
+
"step": 282
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 0.05549563682713991,
|
1995 |
+
"grad_norm": 16.878883361816406,
|
1996 |
+
"learning_rate": 0.00018051727601131227,
|
1997 |
+
"loss": 0.8761,
|
1998 |
+
"step": 283
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 0.05569173448377292,
|
2002 |
+
"grad_norm": 31.99020004272461,
|
2003 |
+
"learning_rate": 0.0001803791538423076,
|
2004 |
+
"loss": 1.7235,
|
2005 |
+
"step": 284
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.05588783214040592,
|
2009 |
+
"grad_norm": 4.821253776550293,
|
2010 |
+
"learning_rate": 0.0001802405970307112,
|
2011 |
+
"loss": 1.2902,
|
2012 |
+
"step": 285
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.056083929797038926,
|
2016 |
+
"grad_norm": 7.2293267250061035,
|
2017 |
+
"learning_rate": 0.00018010160632575577,
|
2018 |
+
"loss": 1.0864,
|
2019 |
+
"step": 286
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.05628002745367193,
|
2023 |
+
"grad_norm": 8.262434959411621,
|
2024 |
+
"learning_rate": 0.00017996218247902035,
|
2025 |
+
"loss": 1.6246,
|
2026 |
+
"step": 287
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 0.056476125110304934,
|
2030 |
+
"grad_norm": 7.845222473144531,
|
2031 |
+
"learning_rate": 0.00017982232624442595,
|
2032 |
+
"loss": 1.7249,
|
2033 |
+
"step": 288
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 0.05667222276693794,
|
2037 |
+
"grad_norm": 9.781503677368164,
|
2038 |
+
"learning_rate": 0.0001796820383782319,
|
2039 |
+
"loss": 1.9911,
|
2040 |
+
"step": 289
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 0.056868320423570935,
|
2044 |
+
"grad_norm": 10.7435884475708,
|
2045 |
+
"learning_rate": 0.00017954131963903133,
|
2046 |
+
"loss": 1.4689,
|
2047 |
+
"step": 290
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 0.05706441808020394,
|
2051 |
+
"grad_norm": 8.709835052490234,
|
2052 |
+
"learning_rate": 0.00017940017078774747,
|
2053 |
+
"loss": 2.3939,
|
2054 |
+
"step": 291
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.057260515736836944,
|
2058 |
+
"grad_norm": 6.140249252319336,
|
2059 |
+
"learning_rate": 0.00017925859258762915,
|
2060 |
+
"loss": 2.0753,
|
2061 |
+
"step": 292
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.05745661339346995,
|
2065 |
+
"grad_norm": 9.725993156433105,
|
2066 |
+
"learning_rate": 0.00017911658580424704,
|
2067 |
+
"loss": 1.5315,
|
2068 |
+
"step": 293
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.05765271105010295,
|
2072 |
+
"grad_norm": 20.413393020629883,
|
2073 |
+
"learning_rate": 0.00017897415120548917,
|
2074 |
+
"loss": 2.4083,
|
2075 |
+
"step": 294
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 0.057848808706735956,
|
2079 |
+
"grad_norm": 7.881735324859619,
|
2080 |
+
"learning_rate": 0.00017883128956155706,
|
2081 |
+
"loss": 3.1099,
|
2082 |
+
"step": 295
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 0.05804490636336896,
|
2086 |
+
"grad_norm": 8.856921195983887,
|
2087 |
+
"learning_rate": 0.0001786880016449614,
|
2088 |
+
"loss": 0.9566,
|
2089 |
+
"step": 296
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 0.058241004020001964,
|
2093 |
+
"grad_norm": 25.80061912536621,
|
2094 |
+
"learning_rate": 0.0001785442882305179,
|
2095 |
+
"loss": 2.6205,
|
2096 |
+
"step": 297
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.05843710167663496,
|
2100 |
+
"grad_norm": 13.293787956237793,
|
2101 |
+
"learning_rate": 0.00017840015009534308,
|
2102 |
+
"loss": 1.7317,
|
2103 |
+
"step": 298
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.058633199333267966,
|
2107 |
+
"grad_norm": 11.313176155090332,
|
2108 |
+
"learning_rate": 0.00017825558801885016,
|
2109 |
+
"loss": 1.5122,
|
2110 |
+
"step": 299
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 0.05882929698990097,
|
2114 |
+
"grad_norm": 9.636054039001465,
|
2115 |
+
"learning_rate": 0.00017811060278274474,
|
2116 |
+
"loss": 2.1976,
|
2117 |
+
"step": 300
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 0.059025394646533974,
|
2121 |
+
"grad_norm": 11.10985279083252,
|
2122 |
+
"learning_rate": 0.00017796519517102066,
|
2123 |
+
"loss": 2.5926,
|
2124 |
+
"step": 301
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.05922149230316698,
|
2128 |
+
"grad_norm": 6.27458381652832,
|
2129 |
+
"learning_rate": 0.00017781936596995563,
|
2130 |
+
"loss": 2.5326,
|
2131 |
+
"step": 302
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 0.05941758995979998,
|
2135 |
+
"grad_norm": 10.134029388427734,
|
2136 |
+
"learning_rate": 0.00017767311596810715,
|
2137 |
+
"loss": 1.4142,
|
2138 |
+
"step": 303
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.059613687616432987,
|
2142 |
+
"grad_norm": 10.580477714538574,
|
2143 |
+
"learning_rate": 0.0001775264459563081,
|
2144 |
+
"loss": 2.3389,
|
2145 |
+
"step": 304
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.059809785273065984,
|
2149 |
+
"grad_norm": 7.545969009399414,
|
2150 |
+
"learning_rate": 0.00017737935672766257,
|
2151 |
+
"loss": 2.3728,
|
2152 |
+
"step": 305
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 0.06000588292969899,
|
2156 |
+
"grad_norm": 6.5107622146606445,
|
2157 |
+
"learning_rate": 0.00017723184907754154,
|
2158 |
+
"loss": 1.0087,
|
2159 |
+
"step": 306
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 0.06020198058633199,
|
2163 |
+
"grad_norm": 10.663747787475586,
|
2164 |
+
"learning_rate": 0.00017708392380357845,
|
2165 |
+
"loss": 2.2001,
|
2166 |
+
"step": 307
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 0.060398078242964996,
|
2170 |
+
"grad_norm": 10.211285591125488,
|
2171 |
+
"learning_rate": 0.0001769355817056651,
|
2172 |
+
"loss": 2.2537,
|
2173 |
+
"step": 308
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 0.060594175899598,
|
2177 |
+
"grad_norm": 8.512606620788574,
|
2178 |
+
"learning_rate": 0.00017678682358594728,
|
2179 |
+
"loss": 1.0687,
|
2180 |
+
"step": 309
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 0.060790273556231005,
|
2184 |
+
"grad_norm": 10.64330768585205,
|
2185 |
+
"learning_rate": 0.0001766376502488202,
|
2186 |
+
"loss": 2.4672,
|
2187 |
+
"step": 310
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.06098637121286401,
|
2191 |
+
"grad_norm": 9.972363471984863,
|
2192 |
+
"learning_rate": 0.0001764880625009245,
|
2193 |
+
"loss": 2.2277,
|
2194 |
+
"step": 311
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 0.06118246886949701,
|
2198 |
+
"grad_norm": 10.01198959350586,
|
2199 |
+
"learning_rate": 0.0001763380611511416,
|
2200 |
+
"loss": 1.906,
|
2201 |
+
"step": 312
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 0.06137856652613001,
|
2205 |
+
"grad_norm": 11.719582557678223,
|
2206 |
+
"learning_rate": 0.00017618764701058949,
|
2207 |
+
"loss": 2.4849,
|
2208 |
+
"step": 313
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 0.061574664182763014,
|
2212 |
+
"grad_norm": 9.08901309967041,
|
2213 |
+
"learning_rate": 0.0001760368208926182,
|
2214 |
+
"loss": 1.4476,
|
2215 |
+
"step": 314
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 0.06177076183939602,
|
2219 |
+
"grad_norm": 11.74946403503418,
|
2220 |
+
"learning_rate": 0.00017588558361280557,
|
2221 |
+
"loss": 1.3607,
|
2222 |
+
"step": 315
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 0.06196685949602902,
|
2226 |
+
"grad_norm": 6.549604892730713,
|
2227 |
+
"learning_rate": 0.00017573393598895276,
|
2228 |
+
"loss": 2.066,
|
2229 |
+
"step": 316
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.06216295715266203,
|
2233 |
+
"grad_norm": 5.160909652709961,
|
2234 |
+
"learning_rate": 0.00017558187884107978,
|
2235 |
+
"loss": 0.9799,
|
2236 |
+
"step": 317
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 0.06235905480929503,
|
2240 |
+
"grad_norm": 11.00747299194336,
|
2241 |
+
"learning_rate": 0.00017542941299142112,
|
2242 |
+
"loss": 2.3193,
|
2243 |
+
"step": 318
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 0.06255515246592804,
|
2247 |
+
"grad_norm": 4.467062473297119,
|
2248 |
+
"learning_rate": 0.00017527653926442135,
|
2249 |
+
"loss": 1.9208,
|
2250 |
+
"step": 319
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 0.06275125012256104,
|
2254 |
+
"grad_norm": 11.554845809936523,
|
2255 |
+
"learning_rate": 0.00017512325848673043,
|
2256 |
+
"loss": 1.5197,
|
2257 |
+
"step": 320
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 0.06294734777919404,
|
2261 |
+
"grad_norm": 6.626307964324951,
|
2262 |
+
"learning_rate": 0.0001749695714871996,
|
2263 |
+
"loss": 2.0222,
|
2264 |
+
"step": 321
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.06314344543582705,
|
2268 |
+
"grad_norm": 5.357675075531006,
|
2269 |
+
"learning_rate": 0.00017481547909687658,
|
2270 |
+
"loss": 2.3264,
|
2271 |
+
"step": 322
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.06333954309246005,
|
2275 |
+
"grad_norm": 9.451851844787598,
|
2276 |
+
"learning_rate": 0.00017466098214900124,
|
2277 |
+
"loss": 1.5699,
|
2278 |
+
"step": 323
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 0.06353564074909304,
|
2282 |
+
"grad_norm": 5.937804698944092,
|
2283 |
+
"learning_rate": 0.00017450608147900106,
|
2284 |
+
"loss": 1.832,
|
2285 |
+
"step": 324
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 0.06373173840572605,
|
2289 |
+
"grad_norm": 10.744606971740723,
|
2290 |
+
"learning_rate": 0.00017435077792448664,
|
2291 |
+
"loss": 1.4665,
|
2292 |
+
"step": 325
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 0.06392783606235905,
|
2296 |
+
"grad_norm": 9.900199890136719,
|
2297 |
+
"learning_rate": 0.0001741950723252471,
|
2298 |
+
"loss": 1.4785,
|
2299 |
+
"step": 326
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 0.06412393371899205,
|
2303 |
+
"grad_norm": 13.663531303405762,
|
2304 |
+
"learning_rate": 0.00017403896552324553,
|
2305 |
+
"loss": 0.9564,
|
2306 |
+
"step": 327
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.06432003137562506,
|
2310 |
+
"grad_norm": 4.708930015563965,
|
2311 |
+
"learning_rate": 0.00017388245836261464,
|
2312 |
+
"loss": 0.8293,
|
2313 |
+
"step": 328
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.06451612903225806,
|
2317 |
+
"grad_norm": 6.656357288360596,
|
2318 |
+
"learning_rate": 0.00017372555168965184,
|
2319 |
+
"loss": 2.2177,
|
2320 |
+
"step": 329
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.06471222668889107,
|
2324 |
+
"grad_norm": 6.349363803863525,
|
2325 |
+
"learning_rate": 0.00017356824635281502,
|
2326 |
+
"loss": 3.3319,
|
2327 |
+
"step": 330
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.06490832434552407,
|
2331 |
+
"grad_norm": 10.561055183410645,
|
2332 |
+
"learning_rate": 0.00017341054320271776,
|
2333 |
+
"loss": 1.919,
|
2334 |
+
"step": 331
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.06510442200215708,
|
2338 |
+
"grad_norm": 10.805617332458496,
|
2339 |
+
"learning_rate": 0.00017325244309212475,
|
2340 |
+
"loss": 2.9898,
|
2341 |
+
"step": 332
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.06530051965879008,
|
2345 |
+
"grad_norm": 9.67844009399414,
|
2346 |
+
"learning_rate": 0.0001730939468759472,
|
2347 |
+
"loss": 3.0727,
|
2348 |
+
"step": 333
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.06549661731542308,
|
2352 |
+
"grad_norm": 9.487295150756836,
|
2353 |
+
"learning_rate": 0.00017293505541123833,
|
2354 |
+
"loss": 1.2741,
|
2355 |
+
"step": 334
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.06569271497205609,
|
2359 |
+
"grad_norm": 5.027645111083984,
|
2360 |
+
"learning_rate": 0.00017277576955718847,
|
2361 |
+
"loss": 1.6962,
|
2362 |
+
"step": 335
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 0.06588881262868909,
|
2366 |
+
"grad_norm": 6.2696685791015625,
|
2367 |
+
"learning_rate": 0.0001726160901751207,
|
2368 |
+
"loss": 1.4388,
|
2369 |
+
"step": 336
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 0.0660849102853221,
|
2373 |
+
"grad_norm": 9.509906768798828,
|
2374 |
+
"learning_rate": 0.000172456018128486,
|
2375 |
+
"loss": 2.3173,
|
2376 |
+
"step": 337
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 0.0662810079419551,
|
2380 |
+
"grad_norm": 5.882188320159912,
|
2381 |
+
"learning_rate": 0.00017229555428285864,
|
2382 |
+
"loss": 1.1832,
|
2383 |
+
"step": 338
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 0.06647710559858809,
|
2387 |
+
"grad_norm": 8.857211112976074,
|
2388 |
+
"learning_rate": 0.00017213469950593156,
|
2389 |
+
"loss": 2.484,
|
2390 |
+
"step": 339
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.0666732032552211,
|
2394 |
+
"grad_norm": 10.660289764404297,
|
2395 |
+
"learning_rate": 0.00017197345466751158,
|
2396 |
+
"loss": 2.5169,
|
2397 |
+
"step": 340
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.0668693009118541,
|
2401 |
+
"grad_norm": 6.141770839691162,
|
2402 |
+
"learning_rate": 0.00017181182063951474,
|
2403 |
+
"loss": 1.601,
|
2404 |
+
"step": 341
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 0.0668693009118541,
|
2408 |
+
"eval_loss": 0.4308730363845825,
|
2409 |
+
"eval_runtime": 77.758,
|
2410 |
+
"eval_samples_per_second": 27.624,
|
2411 |
+
"eval_steps_per_second": 13.812,
|
2412 |
+
"step": 341
|
2413 |
+
}
|
2414 |
+
],
|
2415 |
+
"logging_steps": 1,
|
2416 |
+
"max_steps": 1361,
|
2417 |
+
"num_input_tokens_seen": 0,
|
2418 |
+
"num_train_epochs": 1,
|
2419 |
+
"save_steps": 341,
|
2420 |
+
"stateful_callbacks": {
|
2421 |
+
"TrainerControl": {
|
2422 |
+
"args": {
|
2423 |
+
"should_epoch_stop": false,
|
2424 |
+
"should_evaluate": false,
|
2425 |
+
"should_log": false,
|
2426 |
+
"should_save": true,
|
2427 |
+
"should_training_stop": false
|
2428 |
+
},
|
2429 |
+
"attributes": {}
|
2430 |
+
}
|
2431 |
+
},
|
2432 |
+
"total_flos": 7.34807651820503e+16,
|
2433 |
+
"train_batch_size": 2,
|
2434 |
+
"trial_name": null,
|
2435 |
+
"trial_params": null
|
2436 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b824b34abb9b483ba144d252745a6c7219fffc9242a3b936ca3b8b5c3590fbfe
|
3 |
+
size 6776
|