Upload 11 files
Browse files- README.md +202 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +49 -0
- trainer_state.json +291 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
|
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 0.10.0
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "sarvamai/OpenHathi-7B-Hi-v0.1-Base",
|
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": 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": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"down_proj",
|
25 |
+
"up_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a8fda6a761219ec87dab6b7b50321ab293cd2460e99b61b0acae340843025d9
|
3 |
+
size 92824216
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e981d62e30062728686199eda2e60e6261c4e9b3df515efbb69476a877256a5d
|
3 |
+
size 47209298
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8f25ad6a8b01c26ff0b8dfc61b634ac9e28410d2f0f4abade20c5ea2e9a51ee
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:912cbeff6fa4557e074a886ba7c0405503e847fe7cab0926eaa9ffbdd9c517b1
|
3 |
+
size 1064
|
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": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
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 |
+
"32000": {
|
30 |
+
"content": "[PAD]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": false,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<unk>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,291 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5460336720764447,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1800,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"grad_norm": 0.3099820017814636,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 1.8122,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03,
|
20 |
+
"eval_loss": 1.7837988138198853,
|
21 |
+
"eval_runtime": 208.895,
|
22 |
+
"eval_samples_per_second": 6.3,
|
23 |
+
"eval_steps_per_second": 1.575,
|
24 |
+
"step": 100
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.06,
|
28 |
+
"grad_norm": 0.17340590059757233,
|
29 |
+
"learning_rate": 9.655172413793105e-05,
|
30 |
+
"loss": 1.6719,
|
31 |
+
"step": 200
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.06,
|
35 |
+
"eval_loss": 1.7731986045837402,
|
36 |
+
"eval_runtime": 208.8797,
|
37 |
+
"eval_samples_per_second": 6.3,
|
38 |
+
"eval_steps_per_second": 1.575,
|
39 |
+
"step": 200
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.09,
|
43 |
+
"grad_norm": 0.16290397942066193,
|
44 |
+
"learning_rate": 9.310344827586207e-05,
|
45 |
+
"loss": 1.6564,
|
46 |
+
"step": 300
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.09,
|
50 |
+
"eval_loss": 1.76987886428833,
|
51 |
+
"eval_runtime": 208.9321,
|
52 |
+
"eval_samples_per_second": 6.299,
|
53 |
+
"eval_steps_per_second": 1.575,
|
54 |
+
"step": 300
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.12,
|
58 |
+
"grad_norm": 0.1616089642047882,
|
59 |
+
"learning_rate": 8.96551724137931e-05,
|
60 |
+
"loss": 1.6781,
|
61 |
+
"step": 400
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.12,
|
65 |
+
"eval_loss": 1.7673217058181763,
|
66 |
+
"eval_runtime": 208.8655,
|
67 |
+
"eval_samples_per_second": 6.301,
|
68 |
+
"eval_steps_per_second": 1.575,
|
69 |
+
"step": 400
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.15,
|
73 |
+
"grad_norm": 0.21069930493831635,
|
74 |
+
"learning_rate": 8.620689655172413e-05,
|
75 |
+
"loss": 1.6603,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.15,
|
80 |
+
"eval_loss": 1.7704393863677979,
|
81 |
+
"eval_runtime": 208.9211,
|
82 |
+
"eval_samples_per_second": 6.299,
|
83 |
+
"eval_steps_per_second": 1.575,
|
84 |
+
"step": 500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.18,
|
88 |
+
"grad_norm": 0.19658587872982025,
|
89 |
+
"learning_rate": 8.275862068965517e-05,
|
90 |
+
"loss": 1.6579,
|
91 |
+
"step": 600
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.18,
|
95 |
+
"eval_loss": 1.7655415534973145,
|
96 |
+
"eval_runtime": 208.8518,
|
97 |
+
"eval_samples_per_second": 6.301,
|
98 |
+
"eval_steps_per_second": 1.575,
|
99 |
+
"step": 600
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.21,
|
103 |
+
"grad_norm": 0.17741167545318604,
|
104 |
+
"learning_rate": 7.931034482758621e-05,
|
105 |
+
"loss": 1.6573,
|
106 |
+
"step": 700
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.21,
|
110 |
+
"eval_loss": 1.7669495344161987,
|
111 |
+
"eval_runtime": 208.8515,
|
112 |
+
"eval_samples_per_second": 6.301,
|
113 |
+
"eval_steps_per_second": 1.575,
|
114 |
+
"step": 700
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.24,
|
118 |
+
"grad_norm": 0.17904286086559296,
|
119 |
+
"learning_rate": 7.586206896551724e-05,
|
120 |
+
"loss": 1.6398,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24,
|
125 |
+
"eval_loss": 1.7682162523269653,
|
126 |
+
"eval_runtime": 208.8599,
|
127 |
+
"eval_samples_per_second": 6.301,
|
128 |
+
"eval_steps_per_second": 1.575,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.27,
|
133 |
+
"grad_norm": 0.17510022222995758,
|
134 |
+
"learning_rate": 7.241379310344828e-05,
|
135 |
+
"loss": 1.6464,
|
136 |
+
"step": 900
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.27,
|
140 |
+
"eval_loss": 1.7680007219314575,
|
141 |
+
"eval_runtime": 208.9236,
|
142 |
+
"eval_samples_per_second": 6.299,
|
143 |
+
"eval_steps_per_second": 1.575,
|
144 |
+
"step": 900
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.3,
|
148 |
+
"grad_norm": 0.16618536412715912,
|
149 |
+
"learning_rate": 6.896551724137931e-05,
|
150 |
+
"loss": 1.6402,
|
151 |
+
"step": 1000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.3,
|
155 |
+
"eval_loss": 1.7689732313156128,
|
156 |
+
"eval_runtime": 208.9404,
|
157 |
+
"eval_samples_per_second": 6.298,
|
158 |
+
"eval_steps_per_second": 1.575,
|
159 |
+
"step": 1000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.33,
|
163 |
+
"grad_norm": 0.1838076114654541,
|
164 |
+
"learning_rate": 6.551724137931034e-05,
|
165 |
+
"loss": 1.6602,
|
166 |
+
"step": 1100
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.33,
|
170 |
+
"eval_loss": 1.7677079439163208,
|
171 |
+
"eval_runtime": 208.8621,
|
172 |
+
"eval_samples_per_second": 6.301,
|
173 |
+
"eval_steps_per_second": 1.575,
|
174 |
+
"step": 1100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.36,
|
178 |
+
"grad_norm": 0.1798967868089676,
|
179 |
+
"learning_rate": 6.206896551724138e-05,
|
180 |
+
"loss": 1.6399,
|
181 |
+
"step": 1200
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.36,
|
185 |
+
"eval_loss": 1.7679466009140015,
|
186 |
+
"eval_runtime": 208.7864,
|
187 |
+
"eval_samples_per_second": 6.303,
|
188 |
+
"eval_steps_per_second": 1.576,
|
189 |
+
"step": 1200
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.39,
|
193 |
+
"grad_norm": 0.19117586314678192,
|
194 |
+
"learning_rate": 5.862068965517241e-05,
|
195 |
+
"loss": 1.6428,
|
196 |
+
"step": 1300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.39,
|
200 |
+
"eval_loss": 1.7693601846694946,
|
201 |
+
"eval_runtime": 208.7845,
|
202 |
+
"eval_samples_per_second": 6.303,
|
203 |
+
"eval_steps_per_second": 1.576,
|
204 |
+
"step": 1300
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.42,
|
208 |
+
"grad_norm": 0.18876388669013977,
|
209 |
+
"learning_rate": 5.517241379310345e-05,
|
210 |
+
"loss": 1.6403,
|
211 |
+
"step": 1400
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.42,
|
215 |
+
"eval_loss": 1.7661293745040894,
|
216 |
+
"eval_runtime": 208.7761,
|
217 |
+
"eval_samples_per_second": 6.303,
|
218 |
+
"eval_steps_per_second": 1.576,
|
219 |
+
"step": 1400
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.46,
|
223 |
+
"grad_norm": 0.17072780430316925,
|
224 |
+
"learning_rate": 5.172413793103449e-05,
|
225 |
+
"loss": 1.6403,
|
226 |
+
"step": 1500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.46,
|
230 |
+
"eval_loss": 1.7662379741668701,
|
231 |
+
"eval_runtime": 208.8393,
|
232 |
+
"eval_samples_per_second": 6.301,
|
233 |
+
"eval_steps_per_second": 1.575,
|
234 |
+
"step": 1500
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.49,
|
238 |
+
"grad_norm": 0.20399431884288788,
|
239 |
+
"learning_rate": 4.827586206896552e-05,
|
240 |
+
"loss": 1.637,
|
241 |
+
"step": 1600
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.49,
|
245 |
+
"eval_loss": 1.7682374715805054,
|
246 |
+
"eval_runtime": 208.7744,
|
247 |
+
"eval_samples_per_second": 6.303,
|
248 |
+
"eval_steps_per_second": 1.576,
|
249 |
+
"step": 1600
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.52,
|
253 |
+
"grad_norm": 0.2173861563205719,
|
254 |
+
"learning_rate": 4.482758620689655e-05,
|
255 |
+
"loss": 1.6366,
|
256 |
+
"step": 1700
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.52,
|
260 |
+
"eval_loss": 1.7696117162704468,
|
261 |
+
"eval_runtime": 208.7744,
|
262 |
+
"eval_samples_per_second": 6.303,
|
263 |
+
"eval_steps_per_second": 1.576,
|
264 |
+
"step": 1700
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.55,
|
268 |
+
"grad_norm": 0.19538724422454834,
|
269 |
+
"learning_rate": 4.1379310344827587e-05,
|
270 |
+
"loss": 1.6377,
|
271 |
+
"step": 1800
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.55,
|
275 |
+
"eval_loss": 1.7682461738586426,
|
276 |
+
"eval_runtime": 208.7775,
|
277 |
+
"eval_samples_per_second": 6.303,
|
278 |
+
"eval_steps_per_second": 1.576,
|
279 |
+
"step": 1800
|
280 |
+
}
|
281 |
+
],
|
282 |
+
"logging_steps": 100,
|
283 |
+
"max_steps": 3000,
|
284 |
+
"num_input_tokens_seen": 0,
|
285 |
+
"num_train_epochs": 1,
|
286 |
+
"save_steps": 50,
|
287 |
+
"total_flos": 4.823467998404936e+17,
|
288 |
+
"train_batch_size": 4,
|
289 |
+
"trial_name": null,
|
290 |
+
"trial_params": null
|
291 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e595dff08d37c59b50699ff1db296b1cde2e4ecb4f8fd815285f35611ee75d7
|
3 |
+
size 4856
|