Charlie911
commited on
Commit
•
c8e2b1a
1
Parent(s):
cb043fa
Training in progress, epoch 4, checkpoint
Browse files- checkpoint-860/README.md +202 -0
- checkpoint-860/adapter_config.json +31 -0
- checkpoint-860/adapter_model.safetensors +3 -0
- checkpoint-860/optimizer.pt +3 -0
- checkpoint-860/rng_state.pth +3 -0
- checkpoint-860/scheduler.pt +3 -0
- checkpoint-860/special_tokens_map.json +24 -0
- checkpoint-860/tokenizer.json +0 -0
- checkpoint-860/tokenizer.model +3 -0
- checkpoint-860/tokenizer_config.json +42 -0
- checkpoint-860/trainer_state.json +635 -0
- checkpoint-860/training_args.bin +3 -0
checkpoint-860/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: apple/OpenELM-3B-Instruct
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
checkpoint-860/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "apple/OpenELM-3B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
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": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"proj_1",
|
24 |
+
"proj_2",
|
25 |
+
"out_proj",
|
26 |
+
"qkv_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
checkpoint-860/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3a6999819bd624734025694b60e29f461285db1c9759654b8c013e8e0f259d6
|
3 |
+
size 716217448
|
checkpoint-860/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56d4eedd2e46dc08d129ed8fe9c97dabf338bc218f22f4189116b9b5fdac8c86
|
3 |
+
size 1432597626
|
checkpoint-860/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ca337d76634e43eb87d6626afbfc67a8fe8c027857021e3b6c89dccd7a76f7
|
3 |
+
size 14244
|
checkpoint-860/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d68924d1b593eddd8c41c0dec5d4c9fbe4e3785da926a4fb572f2daa0ef132f
|
3 |
+
size 1064
|
checkpoint-860/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-860/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-860/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-860/tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
checkpoint-860/trainer_state.json
ADDED
@@ -0,0 +1,635 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.9927431059506535,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 860,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05805515239477504,
|
13 |
+
"grad_norm": 0.600770890712738,
|
14 |
+
"learning_rate": 2.9999908009303982e-05,
|
15 |
+
"loss": 2.8908,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.11611030478955008,
|
20 |
+
"grad_norm": 0.3810243308544159,
|
21 |
+
"learning_rate": 2.998887064264453e-05,
|
22 |
+
"loss": 2.6786,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1741654571843251,
|
27 |
+
"grad_norm": 0.2603137493133545,
|
28 |
+
"learning_rate": 2.9959452370912904e-05,
|
29 |
+
"loss": 2.5845,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.23222060957910015,
|
34 |
+
"grad_norm": 0.2289140671491623,
|
35 |
+
"learning_rate": 2.9911693281561532e-05,
|
36 |
+
"loss": 2.4006,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.29027576197387517,
|
41 |
+
"grad_norm": 0.18332642316818237,
|
42 |
+
"learning_rate": 2.9845658454559736e-05,
|
43 |
+
"loss": 2.2503,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3483309143686502,
|
48 |
+
"grad_norm": 0.21847300231456757,
|
49 |
+
"learning_rate": 2.9761437873711118e-05,
|
50 |
+
"loss": 2.0564,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.40638606676342526,
|
55 |
+
"grad_norm": 0.2699638307094574,
|
56 |
+
"learning_rate": 2.9659146304035112e-05,
|
57 |
+
"loss": 1.8541,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4644412191582003,
|
62 |
+
"grad_norm": 0.17481808364391327,
|
63 |
+
"learning_rate": 2.953892313537998e-05,
|
64 |
+
"loss": 1.5994,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5224963715529753,
|
69 |
+
"grad_norm": 0.12553584575653076,
|
70 |
+
"learning_rate": 2.9400932192480125e-05,
|
71 |
+
"loss": 1.4072,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5805515239477503,
|
76 |
+
"grad_norm": 0.12803253531455994,
|
77 |
+
"learning_rate": 2.9245361511716764e-05,
|
78 |
+
"loss": 1.3509,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6386066763425254,
|
83 |
+
"grad_norm": 0.0883030965924263,
|
84 |
+
"learning_rate": 2.907242308488601e-05,
|
85 |
+
"loss": 1.3609,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6966618287373004,
|
90 |
+
"grad_norm": 0.08672440052032471,
|
91 |
+
"learning_rate": 2.8882352570323616e-05,
|
92 |
+
"loss": 1.3838,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.7547169811320755,
|
97 |
+
"grad_norm": 0.08096282929182053,
|
98 |
+
"learning_rate": 2.8675408971779997e-05,
|
99 |
+
"loss": 1.3488,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8127721335268505,
|
104 |
+
"grad_norm": 0.08677352964878082,
|
105 |
+
"learning_rate": 2.8451874285483073e-05,
|
106 |
+
"loss": 1.3902,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.8708272859216255,
|
111 |
+
"grad_norm": 0.06741151958703995,
|
112 |
+
"learning_rate": 2.8212053115869935e-05,
|
113 |
+
"loss": 1.319,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.9288824383164006,
|
118 |
+
"grad_norm": 0.0820663794875145,
|
119 |
+
"learning_rate": 2.7956272260510948e-05,
|
120 |
+
"loss": 1.3725,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.9869375907111756,
|
125 |
+
"grad_norm": 0.06830213963985443,
|
126 |
+
"learning_rate": 2.768488026479187e-05,
|
127 |
+
"loss": 1.3809,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.0449927431059507,
|
132 |
+
"grad_norm": 0.08063437789678574,
|
133 |
+
"learning_rate": 2.7398246946960864e-05,
|
134 |
+
"loss": 1.286,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.1030478955007257,
|
139 |
+
"grad_norm": 0.07576021552085876,
|
140 |
+
"learning_rate": 2.7096762894187533e-05,
|
141 |
+
"loss": 1.3281,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.1611030478955007,
|
146 |
+
"grad_norm": 0.06808394193649292,
|
147 |
+
"learning_rate": 2.678083893032079e-05,
|
148 |
+
"loss": 1.3432,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.2191582002902757,
|
153 |
+
"grad_norm": 0.06429944187402725,
|
154 |
+
"learning_rate": 2.6450905556070718e-05,
|
155 |
+
"loss": 1.3108,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.2772133526850509,
|
160 |
+
"grad_norm": 0.07570013403892517,
|
161 |
+
"learning_rate": 2.610741236237734e-05,
|
162 |
+
"loss": 1.2846,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.3352685050798259,
|
167 |
+
"grad_norm": 0.0730566531419754,
|
168 |
+
"learning_rate": 2.5750827417765714e-05,
|
169 |
+
"loss": 1.2743,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.3933236574746009,
|
174 |
+
"grad_norm": 0.07746976613998413,
|
175 |
+
"learning_rate": 2.5381636630522056e-05,
|
176 |
+
"loss": 1.2424,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.4513788098693758,
|
181 |
+
"grad_norm": 0.063927061855793,
|
182 |
+
"learning_rate": 2.50003430865602e-05,
|
183 |
+
"loss": 1.3057,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.509433962264151,
|
188 |
+
"grad_norm": 0.06818998605012894,
|
189 |
+
"learning_rate": 2.4607466363880555e-05,
|
190 |
+
"loss": 1.2931,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.567489114658926,
|
195 |
+
"grad_norm": 0.07596269994974136,
|
196 |
+
"learning_rate": 2.4203541824555744e-05,
|
197 |
+
"loss": 1.3029,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.625544267053701,
|
202 |
+
"grad_norm": 0.07179366797208786,
|
203 |
+
"learning_rate": 2.378911988520776e-05,
|
204 |
+
"loss": 1.2844,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.683599419448476,
|
209 |
+
"grad_norm": 0.06046036258339882,
|
210 |
+
"learning_rate": 2.33647652669707e-05,
|
211 |
+
"loss": 1.3078,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.741654571843251,
|
216 |
+
"grad_norm": 0.07098483294248581,
|
217 |
+
"learning_rate": 2.2931056225961137e-05,
|
218 |
+
"loss": 1.3307,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.799709724238026,
|
223 |
+
"grad_norm": 0.07308895885944366,
|
224 |
+
"learning_rate": 2.2488583765304748e-05,
|
225 |
+
"loss": 1.2819,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.8577648766328012,
|
230 |
+
"grad_norm": 0.06851565092802048,
|
231 |
+
"learning_rate": 2.203795082979298e-05,
|
232 |
+
"loss": 1.267,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.9158200290275762,
|
237 |
+
"grad_norm": 0.07384185492992401,
|
238 |
+
"learning_rate": 2.1579771484267097e-05,
|
239 |
+
"loss": 1.2629,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.9738751814223512,
|
244 |
+
"grad_norm": 0.0664062350988388,
|
245 |
+
"learning_rate": 2.111467007684928e-05,
|
246 |
+
"loss": 1.2841,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.0319303338171264,
|
251 |
+
"grad_norm": 0.07113119959831238,
|
252 |
+
"learning_rate": 2.0643280388160994e-05,
|
253 |
+
"loss": 1.2779,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.0899854862119014,
|
258 |
+
"grad_norm": 0.07706930488348007,
|
259 |
+
"learning_rate": 2.0166244767687922e-05,
|
260 |
+
"loss": 1.2854,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.1480406386066764,
|
265 |
+
"grad_norm": 0.06886892020702362,
|
266 |
+
"learning_rate": 1.968421325846838e-05,
|
267 |
+
"loss": 1.2983,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.2060957910014514,
|
272 |
+
"grad_norm": 0.07846487313508987,
|
273 |
+
"learning_rate": 1.919784271129792e-05,
|
274 |
+
"loss": 1.286,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.2641509433962264,
|
279 |
+
"grad_norm": 0.09121862053871155,
|
280 |
+
"learning_rate": 1.8707795889657207e-05,
|
281 |
+
"loss": 1.2774,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 2.3222060957910013,
|
286 |
+
"grad_norm": 0.07675393670797348,
|
287 |
+
"learning_rate": 1.8214740566582862e-05,
|
288 |
+
"loss": 1.2635,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.3802612481857763,
|
293 |
+
"grad_norm": 0.06239638477563858,
|
294 |
+
"learning_rate": 1.7719348614711877e-05,
|
295 |
+
"loss": 1.2833,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.4383164005805513,
|
300 |
+
"grad_norm": 0.0633472129702568,
|
301 |
+
"learning_rate": 1.7222295090739667e-05,
|
302 |
+
"loss": 1.2657,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.4963715529753268,
|
307 |
+
"grad_norm": 0.0839238315820694,
|
308 |
+
"learning_rate": 1.672425731553926e-05,
|
309 |
+
"loss": 1.2424,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.5544267053701017,
|
314 |
+
"grad_norm": 0.061606671661138535,
|
315 |
+
"learning_rate": 1.6225913951195186e-05,
|
316 |
+
"loss": 1.2802,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.6124818577648767,
|
321 |
+
"grad_norm": 0.07224655896425247,
|
322 |
+
"learning_rate": 1.5727944076209725e-05,
|
323 |
+
"loss": 1.2556,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.6705370101596517,
|
328 |
+
"grad_norm": 0.07351450622081757,
|
329 |
+
"learning_rate": 1.5231026260141692e-05,
|
330 |
+
"loss": 1.292,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.7285921625544267,
|
335 |
+
"grad_norm": 0.06462671607732773,
|
336 |
+
"learning_rate": 1.4735837638938767e-05,
|
337 |
+
"loss": 1.2588,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.7866473149492017,
|
342 |
+
"grad_norm": 0.0673007071018219,
|
343 |
+
"learning_rate": 1.4243052992223376e-05,
|
344 |
+
"loss": 1.2889,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.8447024673439767,
|
349 |
+
"grad_norm": 0.06969607621431351,
|
350 |
+
"learning_rate": 1.3753343823789447e-05,
|
351 |
+
"loss": 1.2591,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.9027576197387517,
|
356 |
+
"grad_norm": 0.07535108923912048,
|
357 |
+
"learning_rate": 1.3267377446563042e-05,
|
358 |
+
"loss": 1.3026,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.9608127721335267,
|
363 |
+
"grad_norm": 0.06275378167629242,
|
364 |
+
"learning_rate": 1.2785816073273818e-05,
|
365 |
+
"loss": 1.2005,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 3.018867924528302,
|
370 |
+
"grad_norm": 0.05750374495983124,
|
371 |
+
"learning_rate": 1.2309315914076298e-05,
|
372 |
+
"loss": 1.1945,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 3.076923076923077,
|
377 |
+
"grad_norm": 0.06437436491250992,
|
378 |
+
"learning_rate": 1.1838526282350759e-05,
|
379 |
+
"loss": 1.2601,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 3.134978229317852,
|
384 |
+
"grad_norm": 0.05980416387319565,
|
385 |
+
"learning_rate": 1.1374088709902117e-05,
|
386 |
+
"loss": 1.2469,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.193033381712627,
|
391 |
+
"grad_norm": 0.0727262794971466,
|
392 |
+
"learning_rate": 1.0916636072762575e-05,
|
393 |
+
"loss": 1.2763,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 3.251088534107402,
|
398 |
+
"grad_norm": 0.0568414144217968,
|
399 |
+
"learning_rate": 1.0466791728789216e-05,
|
400 |
+
"loss": 1.2867,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.309143686502177,
|
405 |
+
"grad_norm": 0.062224190682172775,
|
406 |
+
"learning_rate": 1.0025168668231769e-05,
|
407 |
+
"loss": 1.2627,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 3.367198838896952,
|
412 |
+
"grad_norm": 0.05727972835302353,
|
413 |
+
"learning_rate": 9.592368678428012e-06,
|
414 |
+
"loss": 1.265,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 3.425253991291727,
|
419 |
+
"grad_norm": 0.06459406763315201,
|
420 |
+
"learning_rate": 9.168981523765108e-06,
|
421 |
+
"loss": 1.2674,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 3.483309143686502,
|
426 |
+
"grad_norm": 0.06641963869333267,
|
427 |
+
"learning_rate": 8.755584142024184e-06,
|
428 |
+
"loss": 1.271,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 3.5413642960812775,
|
433 |
+
"grad_norm": 0.06708668172359467,
|
434 |
+
"learning_rate": 8.352739858203466e-06,
|
435 |
+
"loss": 1.2262,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 3.599419448476052,
|
440 |
+
"grad_norm": 0.0688287690281868,
|
441 |
+
"learning_rate": 7.960997616891126e-06,
|
442 |
+
"loss": 1.2368,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.6574746008708274,
|
447 |
+
"grad_norm": 0.07018615305423737,
|
448 |
+
"learning_rate": 7.580891234233905e-06,
|
449 |
+
"loss": 1.2569,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 3.7155297532656024,
|
454 |
+
"grad_norm": 0.07098717987537384,
|
455 |
+
"learning_rate": 7.212938670520841e-06,
|
456 |
+
"loss": 1.2335,
|
457 |
+
"step": 640
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 3.7735849056603774,
|
461 |
+
"grad_norm": 0.062128230929374695,
|
462 |
+
"learning_rate": 6.857641324373356e-06,
|
463 |
+
"loss": 1.2773,
|
464 |
+
"step": 650
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 3.8316400580551524,
|
468 |
+
"grad_norm": 0.07041653245687485,
|
469 |
+
"learning_rate": 6.515483349503413e-06,
|
470 |
+
"loss": 1.2542,
|
471 |
+
"step": 660
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 3.8896952104499274,
|
475 |
+
"grad_norm": 0.06907247006893158,
|
476 |
+
"learning_rate": 6.186930994970886e-06,
|
477 |
+
"loss": 1.2725,
|
478 |
+
"step": 670
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 3.9477503628447024,
|
482 |
+
"grad_norm": 0.07188240438699722,
|
483 |
+
"learning_rate": 5.872431969839034e-06,
|
484 |
+
"loss": 1.2734,
|
485 |
+
"step": 680
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 4.005805515239477,
|
489 |
+
"grad_norm": 0.06503301858901978,
|
490 |
+
"learning_rate": 5.572414833093956e-06,
|
491 |
+
"loss": 1.2622,
|
492 |
+
"step": 690
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 4.063860667634253,
|
496 |
+
"grad_norm": 0.06649517267942429,
|
497 |
+
"learning_rate": 5.287288409659299e-06,
|
498 |
+
"loss": 1.2478,
|
499 |
+
"step": 700
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 4.121915820029027,
|
503 |
+
"grad_norm": 0.063417449593544,
|
504 |
+
"learning_rate": 5.017441233302014e-06,
|
505 |
+
"loss": 1.2547,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 4.179970972423803,
|
510 |
+
"grad_norm": 0.07145430147647858,
|
511 |
+
"learning_rate": 4.763241017188311e-06,
|
512 |
+
"loss": 1.2288,
|
513 |
+
"step": 720
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.238026124818577,
|
517 |
+
"grad_norm": 0.06684500724077225,
|
518 |
+
"learning_rate": 4.525034152811261e-06,
|
519 |
+
"loss": 1.2546,
|
520 |
+
"step": 730
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 4.296081277213353,
|
524 |
+
"grad_norm": 0.0568925105035305,
|
525 |
+
"learning_rate": 4.3031452379728275e-06,
|
526 |
+
"loss": 1.2464,
|
527 |
+
"step": 740
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 4.354136429608127,
|
531 |
+
"grad_norm": 0.0680786520242691,
|
532 |
+
"learning_rate": 4.097876634463584e-06,
|
533 |
+
"loss": 1.2538,
|
534 |
+
"step": 750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 4.412191582002903,
|
538 |
+
"grad_norm": 0.07063416391611099,
|
539 |
+
"learning_rate": 3.909508056042768e-06,
|
540 |
+
"loss": 1.2556,
|
541 |
+
"step": 760
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 4.470246734397678,
|
545 |
+
"grad_norm": 0.06249029189348221,
|
546 |
+
"learning_rate": 3.738296187280223e-06,
|
547 |
+
"loss": 1.2563,
|
548 |
+
"step": 770
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.528301886792453,
|
552 |
+
"grad_norm": 0.06654863804578781,
|
553 |
+
"learning_rate": 3.584474333779529e-06,
|
554 |
+
"loss": 1.2856,
|
555 |
+
"step": 780
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.586357039187228,
|
559 |
+
"grad_norm": 0.06898177415132523,
|
560 |
+
"learning_rate": 3.448252104259028e-06,
|
561 |
+
"loss": 1.2733,
|
562 |
+
"step": 790
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 4.644412191582003,
|
566 |
+
"grad_norm": 0.0666985884308815,
|
567 |
+
"learning_rate": 3.329815124923895e-06,
|
568 |
+
"loss": 1.2532,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 4.702467343976778,
|
573 |
+
"grad_norm": 0.06734010577201843,
|
574 |
+
"learning_rate": 3.2293247865185367e-06,
|
575 |
+
"loss": 1.2648,
|
576 |
+
"step": 810
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 4.760522496371553,
|
580 |
+
"grad_norm": 0.08086594194173813,
|
581 |
+
"learning_rate": 3.146918024403947e-06,
|
582 |
+
"loss": 1.2215,
|
583 |
+
"step": 820
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 4.818577648766328,
|
587 |
+
"grad_norm": 0.06437994539737701,
|
588 |
+
"learning_rate": 3.0827071319597517e-06,
|
589 |
+
"loss": 1.2537,
|
590 |
+
"step": 830
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.876632801161103,
|
594 |
+
"grad_norm": 0.06487814337015152,
|
595 |
+
"learning_rate": 3.036779607565159e-06,
|
596 |
+
"loss": 1.2932,
|
597 |
+
"step": 840
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 4.934687953555878,
|
601 |
+
"grad_norm": 0.06499958038330078,
|
602 |
+
"learning_rate": 3.0091980353673875e-06,
|
603 |
+
"loss": 1.2452,
|
604 |
+
"step": 850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 4.9927431059506535,
|
608 |
+
"grad_norm": 0.06908879429101944,
|
609 |
+
"learning_rate": 3e-06,
|
610 |
+
"loss": 1.2488,
|
611 |
+
"step": 860
|
612 |
+
}
|
613 |
+
],
|
614 |
+
"logging_steps": 10,
|
615 |
+
"max_steps": 860,
|
616 |
+
"num_input_tokens_seen": 0,
|
617 |
+
"num_train_epochs": 5,
|
618 |
+
"save_steps": 500,
|
619 |
+
"stateful_callbacks": {
|
620 |
+
"TrainerControl": {
|
621 |
+
"args": {
|
622 |
+
"should_epoch_stop": false,
|
623 |
+
"should_evaluate": false,
|
624 |
+
"should_log": false,
|
625 |
+
"should_save": true,
|
626 |
+
"should_training_stop": true
|
627 |
+
},
|
628 |
+
"attributes": {}
|
629 |
+
}
|
630 |
+
},
|
631 |
+
"total_flos": 1.2296125210723123e+17,
|
632 |
+
"train_batch_size": 4,
|
633 |
+
"trial_name": null,
|
634 |
+
"trial_params": null
|
635 |
+
}
|
checkpoint-860/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15deb499b16c29b5823a28d18e908e729eb8b1344d163133bf2547c81359a0c0
|
3 |
+
size 5432
|