Training in progress, step 75, checkpoint
Browse files- checkpoint-75/README.md +202 -0
- checkpoint-75/adapter_config.json +34 -0
- checkpoint-75/adapter_model.safetensors +3 -0
- checkpoint-75/added_tokens.json +17 -0
- checkpoint-75/optimizer.pt +3 -0
- checkpoint-75/rng_state_0.pth +3 -0
- checkpoint-75/rng_state_1.pth +3 -0
- checkpoint-75/rng_state_2.pth +3 -0
- checkpoint-75/rng_state_3.pth +3 -0
- checkpoint-75/rng_state_4.pth +3 -0
- checkpoint-75/rng_state_5.pth +3 -0
- checkpoint-75/rng_state_6.pth +3 -0
- checkpoint-75/rng_state_7.pth +3 -0
- checkpoint-75/scheduler.pt +3 -0
- checkpoint-75/special_tokens_map.json +30 -0
- checkpoint-75/tokenizer.json +0 -0
- checkpoint-75/tokenizer.model +3 -0
- checkpoint-75/tokenizer_config.json +163 -0
- checkpoint-75/trainer_state.json +574 -0
- checkpoint-75/training_args.bin +3 -0
checkpoint-75/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
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 0.11.1
|
checkpoint-75/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 512,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"o_proj",
|
27 |
+
"qkv_proj",
|
28 |
+
"down_proj",
|
29 |
+
"gate_up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-75/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fd786fb02f9df57284528f424d9c5096fb494614df8a7384707163721ddbdd0
|
3 |
+
size 2004651224
|
checkpoint-75/added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</plan>": 32014,
|
3 |
+
"</thinking>": 32012,
|
4 |
+
"<plan>": 32013,
|
5 |
+
"<thinking>": 32011,
|
6 |
+
"<|assistant|>": 32001,
|
7 |
+
"<|endoftext|>": 32000,
|
8 |
+
"<|end|>": 32007,
|
9 |
+
"<|placeholder1|>": 32002,
|
10 |
+
"<|placeholder2|>": 32003,
|
11 |
+
"<|placeholder3|>": 32004,
|
12 |
+
"<|placeholder4|>": 32005,
|
13 |
+
"<|placeholder5|>": 32008,
|
14 |
+
"<|placeholder6|>": 32009,
|
15 |
+
"<|system|>": 32006,
|
16 |
+
"<|user|>": 32010
|
17 |
+
}
|
checkpoint-75/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd80b24feedaf233ad69a09d92a1b6affd72cff923568f84ed66718cad751657
|
3 |
+
size 4009448634
|
checkpoint-75/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8cc9014cf36259f3c513e5c5fc897df69ac7ea9b388c12cae5f0a11ccb9c9fc
|
3 |
+
size 15984
|
checkpoint-75/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44be4815aeb7bb702bd6453a057e70b52635cd8b3cba140e0368581bd56b098d
|
3 |
+
size 15984
|
checkpoint-75/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb1facf518858e3a03f66aaf2d88d071eb4aee17eb1e9988793518f71574fec3
|
3 |
+
size 15984
|
checkpoint-75/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8413721d4c06bffc4326befe35dc7ee8d08104e1a88257421c3c7cf2e64202e
|
3 |
+
size 15984
|
checkpoint-75/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e430090ac75315ba41c64c78346e313a508a822ac6e55c8efb4468a1f44d91df
|
3 |
+
size 15984
|
checkpoint-75/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83ace4130150aa83942bb9127bebfe6165548ab50143f981f3694a2458c6062d
|
3 |
+
size 15984
|
checkpoint-75/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1418a581fd07561510940237aa823e318a3e88bda121be9b0a854f3d088d0755
|
3 |
+
size 15984
|
checkpoint-75/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0c861a637f0e12be4293f0c63a5f56344bf3c4b8143450502997df1f93abf68
|
3 |
+
size 15984
|
checkpoint-75/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b12bc69afdd94ad849575074e52e02f343ade47c46bc2e039c323acf04a738d
|
3 |
+
size 1064
|
checkpoint-75/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": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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 |
+
}
|
checkpoint-75/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-75/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-75/tokenizer_config.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
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": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<thinking>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "</thinking>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<plan>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "</plan>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"bos_token": "<s>",
|
152 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
153 |
+
"clean_up_tokenization_spaces": false,
|
154 |
+
"eos_token": "<|endoftext|>",
|
155 |
+
"legacy": false,
|
156 |
+
"model_max_length": 4096,
|
157 |
+
"pad_token": "<|endoftext|>",
|
158 |
+
"padding_side": "left",
|
159 |
+
"sp_model_kwargs": {},
|
160 |
+
"tokenizer_class": "LlamaTokenizer",
|
161 |
+
"unk_token": "<unk>",
|
162 |
+
"use_default_system_prompt": false
|
163 |
+
}
|
checkpoint-75/trainer_state.json
ADDED
@@ -0,0 +1,574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.25252525252525254,
|
5 |
+
"eval_steps": 38,
|
6 |
+
"global_step": 75,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003367003367003367,
|
13 |
+
"grad_norm": 2.0,
|
14 |
+
"learning_rate": 4.5454545454545457e-07,
|
15 |
+
"loss": 1.0833,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.003367003367003367,
|
20 |
+
"eval_loss": 1.032954454421997,
|
21 |
+
"eval_runtime": 8.7786,
|
22 |
+
"eval_samples_per_second": 56.957,
|
23 |
+
"eval_steps_per_second": 3.645,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006734006734006734,
|
28 |
+
"grad_norm": 2.265625,
|
29 |
+
"learning_rate": 9.090909090909091e-07,
|
30 |
+
"loss": 0.996,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.010101010101010102,
|
35 |
+
"grad_norm": 1.6484375,
|
36 |
+
"learning_rate": 1.3636363636363636e-06,
|
37 |
+
"loss": 1.0487,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013468013468013467,
|
42 |
+
"grad_norm": 2.046875,
|
43 |
+
"learning_rate": 1.8181818181818183e-06,
|
44 |
+
"loss": 1.0554,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.016835016835016835,
|
49 |
+
"grad_norm": 2.4375,
|
50 |
+
"learning_rate": 2.2727272727272728e-06,
|
51 |
+
"loss": 1.0341,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.020202020202020204,
|
56 |
+
"grad_norm": 1.9609375,
|
57 |
+
"learning_rate": 2.7272727272727272e-06,
|
58 |
+
"loss": 1.0132,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.02356902356902357,
|
63 |
+
"grad_norm": 2.625,
|
64 |
+
"learning_rate": 3.181818181818182e-06,
|
65 |
+
"loss": 1.0298,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.026936026936026935,
|
70 |
+
"grad_norm": 2.296875,
|
71 |
+
"learning_rate": 3.6363636363636366e-06,
|
72 |
+
"loss": 1.0216,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.030303030303030304,
|
77 |
+
"grad_norm": 2.234375,
|
78 |
+
"learning_rate": 4.0909090909090915e-06,
|
79 |
+
"loss": 1.0736,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03367003367003367,
|
84 |
+
"grad_norm": 2.1875,
|
85 |
+
"learning_rate": 4.5454545454545455e-06,
|
86 |
+
"loss": 1.0216,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.037037037037037035,
|
91 |
+
"grad_norm": 2.359375,
|
92 |
+
"learning_rate": 5e-06,
|
93 |
+
"loss": 1.0075,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.04040404040404041,
|
98 |
+
"grad_norm": 1.890625,
|
99 |
+
"learning_rate": 5.4545454545454545e-06,
|
100 |
+
"loss": 1.051,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.04377104377104377,
|
105 |
+
"grad_norm": 1.90625,
|
106 |
+
"learning_rate": 5.90909090909091e-06,
|
107 |
+
"loss": 1.0655,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04713804713804714,
|
112 |
+
"grad_norm": 1.6484375,
|
113 |
+
"learning_rate": 6.363636363636364e-06,
|
114 |
+
"loss": 1.0297,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.050505050505050504,
|
119 |
+
"grad_norm": 1.6953125,
|
120 |
+
"learning_rate": 6.818181818181818e-06,
|
121 |
+
"loss": 1.0411,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.05387205387205387,
|
126 |
+
"grad_norm": 1.9921875,
|
127 |
+
"learning_rate": 7.272727272727273e-06,
|
128 |
+
"loss": 1.0618,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05723905723905724,
|
133 |
+
"grad_norm": 1.4453125,
|
134 |
+
"learning_rate": 7.727272727272727e-06,
|
135 |
+
"loss": 1.0052,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.06060606060606061,
|
140 |
+
"grad_norm": 1.390625,
|
141 |
+
"learning_rate": 8.181818181818183e-06,
|
142 |
+
"loss": 1.0053,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.06397306397306397,
|
147 |
+
"grad_norm": 1.2734375,
|
148 |
+
"learning_rate": 8.636363636363637e-06,
|
149 |
+
"loss": 0.9786,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.06734006734006734,
|
154 |
+
"grad_norm": 1.234375,
|
155 |
+
"learning_rate": 9.090909090909091e-06,
|
156 |
+
"loss": 1.0419,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.0707070707070707,
|
161 |
+
"grad_norm": 1.1484375,
|
162 |
+
"learning_rate": 9.545454545454547e-06,
|
163 |
+
"loss": 1.0356,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07407407407407407,
|
168 |
+
"grad_norm": 1.28125,
|
169 |
+
"learning_rate": 1e-05,
|
170 |
+
"loss": 0.9778,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07744107744107744,
|
175 |
+
"grad_norm": 1.1875,
|
176 |
+
"learning_rate": 1.0454545454545455e-05,
|
177 |
+
"loss": 0.9691,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.08080808080808081,
|
182 |
+
"grad_norm": 1.1953125,
|
183 |
+
"learning_rate": 1.0909090909090909e-05,
|
184 |
+
"loss": 1.0408,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.08417508417508418,
|
189 |
+
"grad_norm": 1.078125,
|
190 |
+
"learning_rate": 1.1363636363636366e-05,
|
191 |
+
"loss": 0.9799,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.08754208754208755,
|
196 |
+
"grad_norm": 1.0390625,
|
197 |
+
"learning_rate": 1.181818181818182e-05,
|
198 |
+
"loss": 0.9756,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.09090909090909091,
|
203 |
+
"grad_norm": 1.1875,
|
204 |
+
"learning_rate": 1.2272727272727274e-05,
|
205 |
+
"loss": 1.0451,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09427609427609428,
|
210 |
+
"grad_norm": 1.0546875,
|
211 |
+
"learning_rate": 1.2727272727272728e-05,
|
212 |
+
"loss": 1.0093,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09764309764309764,
|
217 |
+
"grad_norm": 0.96484375,
|
218 |
+
"learning_rate": 1.3181818181818183e-05,
|
219 |
+
"loss": 0.99,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.10101010101010101,
|
224 |
+
"grad_norm": 1.0703125,
|
225 |
+
"learning_rate": 1.3636363636363637e-05,
|
226 |
+
"loss": 1.0079,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.10437710437710437,
|
231 |
+
"grad_norm": 0.89453125,
|
232 |
+
"learning_rate": 1.4090909090909092e-05,
|
233 |
+
"loss": 0.9653,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.10774410774410774,
|
238 |
+
"grad_norm": 1.0546875,
|
239 |
+
"learning_rate": 1.4545454545454546e-05,
|
240 |
+
"loss": 0.9926,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1111111111111111,
|
245 |
+
"grad_norm": 0.96875,
|
246 |
+
"learning_rate": 1.5000000000000002e-05,
|
247 |
+
"loss": 0.9857,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11447811447811448,
|
252 |
+
"grad_norm": 1.1484375,
|
253 |
+
"learning_rate": 1.5454545454545454e-05,
|
254 |
+
"loss": 0.9676,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11784511784511785,
|
259 |
+
"grad_norm": 1.078125,
|
260 |
+
"learning_rate": 1.590909090909091e-05,
|
261 |
+
"loss": 0.9686,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12121212121212122,
|
266 |
+
"grad_norm": 0.8203125,
|
267 |
+
"learning_rate": 1.6363636363636366e-05,
|
268 |
+
"loss": 0.9182,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12457912457912458,
|
273 |
+
"grad_norm": 0.8515625,
|
274 |
+
"learning_rate": 1.681818181818182e-05,
|
275 |
+
"loss": 0.9506,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12794612794612795,
|
280 |
+
"grad_norm": 0.86328125,
|
281 |
+
"learning_rate": 1.7272727272727274e-05,
|
282 |
+
"loss": 0.9533,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.12794612794612795,
|
287 |
+
"eval_loss": 0.9329763054847717,
|
288 |
+
"eval_runtime": 8.7095,
|
289 |
+
"eval_samples_per_second": 57.409,
|
290 |
+
"eval_steps_per_second": 3.674,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.13131313131313133,
|
295 |
+
"grad_norm": 0.7890625,
|
296 |
+
"learning_rate": 1.772727272727273e-05,
|
297 |
+
"loss": 0.9225,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.13468013468013468,
|
302 |
+
"grad_norm": 0.890625,
|
303 |
+
"learning_rate": 1.8181818181818182e-05,
|
304 |
+
"loss": 0.9378,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.13804713804713806,
|
309 |
+
"grad_norm": 1.046875,
|
310 |
+
"learning_rate": 1.8636363636363638e-05,
|
311 |
+
"loss": 0.8982,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.1414141414141414,
|
316 |
+
"grad_norm": 0.94921875,
|
317 |
+
"learning_rate": 1.9090909090909094e-05,
|
318 |
+
"loss": 0.8958,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.1447811447811448,
|
323 |
+
"grad_norm": 0.9765625,
|
324 |
+
"learning_rate": 1.9545454545454546e-05,
|
325 |
+
"loss": 0.8796,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.14814814814814814,
|
330 |
+
"grad_norm": 0.92578125,
|
331 |
+
"learning_rate": 2e-05,
|
332 |
+
"loss": 0.8808,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.15151515151515152,
|
337 |
+
"grad_norm": 0.94921875,
|
338 |
+
"learning_rate": 1.9999931213623708e-05,
|
339 |
+
"loss": 0.8638,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15488215488215487,
|
344 |
+
"grad_norm": 1.0390625,
|
345 |
+
"learning_rate": 1.999972485544114e-05,
|
346 |
+
"loss": 0.9124,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15824915824915825,
|
351 |
+
"grad_norm": 1.046875,
|
352 |
+
"learning_rate": 1.999938092829122e-05,
|
353 |
+
"loss": 0.8757,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16161616161616163,
|
358 |
+
"grad_norm": 0.73046875,
|
359 |
+
"learning_rate": 1.999889943690545e-05,
|
360 |
+
"loss": 0.885,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16498316498316498,
|
365 |
+
"grad_norm": 0.86328125,
|
366 |
+
"learning_rate": 1.9998280387907845e-05,
|
367 |
+
"loss": 0.8664,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.16835016835016836,
|
372 |
+
"grad_norm": 0.87109375,
|
373 |
+
"learning_rate": 1.9997523789814827e-05,
|
374 |
+
"loss": 0.8512,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.1717171717171717,
|
379 |
+
"grad_norm": 0.80859375,
|
380 |
+
"learning_rate": 1.9996629653035128e-05,
|
381 |
+
"loss": 0.8428,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.1750841750841751,
|
386 |
+
"grad_norm": 0.71875,
|
387 |
+
"learning_rate": 1.9995597989869625e-05,
|
388 |
+
"loss": 0.8536,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17845117845117844,
|
393 |
+
"grad_norm": 0.6171875,
|
394 |
+
"learning_rate": 1.9994428814511205e-05,
|
395 |
+
"loss": 0.82,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18181818181818182,
|
400 |
+
"grad_norm": 0.71875,
|
401 |
+
"learning_rate": 1.999312214304453e-05,
|
402 |
+
"loss": 0.8043,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18518518518518517,
|
407 |
+
"grad_norm": 0.8046875,
|
408 |
+
"learning_rate": 1.9991677993445832e-05,
|
409 |
+
"loss": 0.8525,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.18855218855218855,
|
414 |
+
"grad_norm": 0.6015625,
|
415 |
+
"learning_rate": 1.9990096385582682e-05,
|
416 |
+
"loss": 0.7958,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.1919191919191919,
|
421 |
+
"grad_norm": 0.79296875,
|
422 |
+
"learning_rate": 1.998837734121369e-05,
|
423 |
+
"loss": 0.8001,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19528619528619529,
|
428 |
+
"grad_norm": 0.7109375,
|
429 |
+
"learning_rate": 1.9986520883988233e-05,
|
430 |
+
"loss": 0.805,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.19865319865319866,
|
435 |
+
"grad_norm": 0.84375,
|
436 |
+
"learning_rate": 1.9984527039446093e-05,
|
437 |
+
"loss": 0.7821,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20202020202020202,
|
442 |
+
"grad_norm": 1.1015625,
|
443 |
+
"learning_rate": 1.998239583501714e-05,
|
444 |
+
"loss": 0.7932,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2053872053872054,
|
449 |
+
"grad_norm": 0.6953125,
|
450 |
+
"learning_rate": 1.9980127300020946e-05,
|
451 |
+
"loss": 0.7925,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20875420875420875,
|
456 |
+
"grad_norm": 0.60546875,
|
457 |
+
"learning_rate": 1.9977721465666365e-05,
|
458 |
+
"loss": 0.7846,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21212121212121213,
|
463 |
+
"grad_norm": 0.7265625,
|
464 |
+
"learning_rate": 1.9975178365051123e-05,
|
465 |
+
"loss": 0.7671,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21548821548821548,
|
470 |
+
"grad_norm": 0.70703125,
|
471 |
+
"learning_rate": 1.997249803316136e-05,
|
472 |
+
"loss": 0.8194,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21885521885521886,
|
477 |
+
"grad_norm": 0.81640625,
|
478 |
+
"learning_rate": 1.9969680506871138e-05,
|
479 |
+
"loss": 0.7607,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2222222222222222,
|
484 |
+
"grad_norm": 0.61328125,
|
485 |
+
"learning_rate": 1.9966725824941933e-05,
|
486 |
+
"loss": 0.7858,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2255892255892256,
|
491 |
+
"grad_norm": 0.66015625,
|
492 |
+
"learning_rate": 1.9963634028022133e-05,
|
493 |
+
"loss": 0.7546,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.22895622895622897,
|
498 |
+
"grad_norm": 0.6875,
|
499 |
+
"learning_rate": 1.9960405158646425e-05,
|
500 |
+
"loss": 0.7915,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.23232323232323232,
|
505 |
+
"grad_norm": 0.59765625,
|
506 |
+
"learning_rate": 1.9957039261235263e-05,
|
507 |
+
"loss": 0.7324,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.2356902356902357,
|
512 |
+
"grad_norm": 0.65625,
|
513 |
+
"learning_rate": 1.9953536382094218e-05,
|
514 |
+
"loss": 0.7735,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.23905723905723905,
|
519 |
+
"grad_norm": 0.984375,
|
520 |
+
"learning_rate": 1.9949896569413368e-05,
|
521 |
+
"loss": 0.7356,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24242424242424243,
|
526 |
+
"grad_norm": 0.8125,
|
527 |
+
"learning_rate": 1.9946119873266615e-05,
|
528 |
+
"loss": 0.7407,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24579124579124578,
|
533 |
+
"grad_norm": 0.76953125,
|
534 |
+
"learning_rate": 1.9942206345611008e-05,
|
535 |
+
"loss": 0.7124,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24915824915824916,
|
540 |
+
"grad_norm": 0.6640625,
|
541 |
+
"learning_rate": 1.9938156040286027e-05,
|
542 |
+
"loss": 0.7295,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25252525252525254,
|
547 |
+
"grad_norm": 0.5546875,
|
548 |
+
"learning_rate": 1.993396901301283e-05,
|
549 |
+
"loss": 0.733,
|
550 |
+
"step": 75
|
551 |
+
}
|
552 |
+
],
|
553 |
+
"logging_steps": 1,
|
554 |
+
"max_steps": 891,
|
555 |
+
"num_input_tokens_seen": 0,
|
556 |
+
"num_train_epochs": 3,
|
557 |
+
"save_steps": 75,
|
558 |
+
"stateful_callbacks": {
|
559 |
+
"TrainerControl": {
|
560 |
+
"args": {
|
561 |
+
"should_epoch_stop": false,
|
562 |
+
"should_evaluate": false,
|
563 |
+
"should_log": false,
|
564 |
+
"should_save": true,
|
565 |
+
"should_training_stop": false
|
566 |
+
},
|
567 |
+
"attributes": {}
|
568 |
+
}
|
569 |
+
},
|
570 |
+
"total_flos": 1.36437672443904e+17,
|
571 |
+
"train_batch_size": 2,
|
572 |
+
"trial_name": null,
|
573 |
+
"trial_params": null
|
574 |
+
}
|
checkpoint-75/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe3399e1833e4baeabfb150d83c5b0e5f796c95cfa06424bda5f2c881c0a1e7
|
3 |
+
size 6392
|