Chauhan
commited on
Commit
•
c831e1d
1
Parent(s):
153bb10
Training in progress, step 1000
Browse files- README.md +52 -0
- all_results.json +8 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Feb21_15-03-48_52e53dc2f2d6/events.out.tfevents.1708527838.52e53dc2f2d6.2349.0 +3 -0
- runs/Feb21_16-05-32_52e53dc2f2d6/events.out.tfevents.1708531548.52e53dc2f2d6.2773.0 +3 -0
- runs/Feb21_16-07-41_52e53dc2f2d6/events.out.tfevents.1708531664.52e53dc2f2d6.2833.0 +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- train_results.json +8 -0
- trainer_state.json +170 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: belie-gen-l1-7b-v2
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# belie-gen-l1-7b-v2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 1
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- training_steps: 10000
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.39.0.dev0
|
50 |
+
- Pytorch 2.1.2
|
51 |
+
- Datasets 2.17.1
|
52 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 11.15,
|
3 |
+
"train_loss": 0.6717062408447265,
|
4 |
+
"train_runtime": 2130.1373,
|
5 |
+
"train_samples": 897,
|
6 |
+
"train_samples_per_second": 4.695,
|
7 |
+
"train_steps_per_second": 4.695
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.39.0.dev0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.39.0.dev0"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd2b967722cc70cecbacdf1a9d714ee33f80d2f6a3b3003a3086661250f2673c
|
3 |
+
size 497774208
|
runs/Feb21_15-03-48_52e53dc2f2d6/events.out.tfevents.1708527838.52e53dc2f2d6.2349.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8310930c4adee7340491e20034596b68372629cecba914ae85527752924b3546
|
3 |
+
size 9392
|
runs/Feb21_16-05-32_52e53dc2f2d6/events.out.tfevents.1708531548.52e53dc2f2d6.2773.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5d088d3cf7e88c3a07c97b799b8bf223cec6e4d7953e541ceabfa3fc74b3c6f
|
3 |
+
size 4184
|
runs/Feb21_16-07-41_52e53dc2f2d6/events.out.tfevents.1708531664.52e53dc2f2d6.2833.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57a9034bacf1c54cbb1513ee6f3619457c42262e2be36170db449b2ac6e21153
|
3 |
+
size 5237
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
18 |
+
"unk_token": "<|endoftext|>"
|
19 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 11.15,
|
3 |
+
"train_loss": 0.6717062408447265,
|
4 |
+
"train_runtime": 2130.1373,
|
5 |
+
"train_samples": 897,
|
6 |
+
"train_samples_per_second": 4.695,
|
7 |
+
"train_steps_per_second": 4.695
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.148272017837236,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.56,
|
13 |
+
"grad_norm": 4.136017322540283,
|
14 |
+
"learning_rate": 4.75e-05,
|
15 |
+
"loss": 1.4862,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.11,
|
20 |
+
"grad_norm": 3.5059304237365723,
|
21 |
+
"learning_rate": 4.5e-05,
|
22 |
+
"loss": 1.2182,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.67,
|
27 |
+
"grad_norm": 3.1735312938690186,
|
28 |
+
"learning_rate": 4.25e-05,
|
29 |
+
"loss": 1.0549,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.23,
|
34 |
+
"grad_norm": 3.1064469814300537,
|
35 |
+
"learning_rate": 4e-05,
|
36 |
+
"loss": 0.9527,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.79,
|
41 |
+
"grad_norm": 2.8415098190307617,
|
42 |
+
"learning_rate": 3.7500000000000003e-05,
|
43 |
+
"loss": 0.8717,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.34,
|
48 |
+
"grad_norm": 2.4496607780456543,
|
49 |
+
"learning_rate": 3.5e-05,
|
50 |
+
"loss": 0.783,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.9,
|
55 |
+
"grad_norm": 2.9042794704437256,
|
56 |
+
"learning_rate": 3.2500000000000004e-05,
|
57 |
+
"loss": 0.7372,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 4.46,
|
62 |
+
"grad_norm": 2.628190517425537,
|
63 |
+
"learning_rate": 3e-05,
|
64 |
+
"loss": 0.6509,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.02,
|
69 |
+
"grad_norm": 2.9309325218200684,
|
70 |
+
"learning_rate": 2.7500000000000004e-05,
|
71 |
+
"loss": 0.6398,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 5.57,
|
76 |
+
"grad_norm": 2.357445240020752,
|
77 |
+
"learning_rate": 2.5e-05,
|
78 |
+
"loss": 0.56,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 6.13,
|
83 |
+
"grad_norm": 2.1420226097106934,
|
84 |
+
"learning_rate": 2.25e-05,
|
85 |
+
"loss": 0.5543,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.69,
|
90 |
+
"grad_norm": 2.6394078731536865,
|
91 |
+
"learning_rate": 2e-05,
|
92 |
+
"loss": 0.5104,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 7.25,
|
97 |
+
"grad_norm": 2.395305633544922,
|
98 |
+
"learning_rate": 1.75e-05,
|
99 |
+
"loss": 0.4832,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 7.8,
|
104 |
+
"grad_norm": 2.048461675643921,
|
105 |
+
"learning_rate": 1.5e-05,
|
106 |
+
"loss": 0.4705,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.36,
|
111 |
+
"grad_norm": 2.379493236541748,
|
112 |
+
"learning_rate": 1.25e-05,
|
113 |
+
"loss": 0.442,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 8.92,
|
118 |
+
"grad_norm": 2.170802116394043,
|
119 |
+
"learning_rate": 1e-05,
|
120 |
+
"loss": 0.4264,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 9.48,
|
125 |
+
"grad_norm": 2.277756690979004,
|
126 |
+
"learning_rate": 7.5e-06,
|
127 |
+
"loss": 0.405,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 10.03,
|
132 |
+
"grad_norm": 2.3412973880767822,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.4069,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 10.59,
|
139 |
+
"grad_norm": 2.220499038696289,
|
140 |
+
"learning_rate": 2.5e-06,
|
141 |
+
"loss": 0.3937,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 11.15,
|
146 |
+
"grad_norm": 2.1124320030212402,
|
147 |
+
"learning_rate": 0.0,
|
148 |
+
"loss": 0.3872,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 11.15,
|
153 |
+
"step": 10000,
|
154 |
+
"total_flos": 5225840640000000.0,
|
155 |
+
"train_loss": 0.6717062408447265,
|
156 |
+
"train_runtime": 2130.1373,
|
157 |
+
"train_samples_per_second": 4.695,
|
158 |
+
"train_steps_per_second": 4.695
|
159 |
+
}
|
160 |
+
],
|
161 |
+
"logging_steps": 500,
|
162 |
+
"max_steps": 10000,
|
163 |
+
"num_input_tokens_seen": 0,
|
164 |
+
"num_train_epochs": 12,
|
165 |
+
"save_steps": 1000,
|
166 |
+
"total_flos": 5225840640000000.0,
|
167 |
+
"train_batch_size": 1,
|
168 |
+
"trial_name": null,
|
169 |
+
"trial_params": null
|
170 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cb61092570b7d8e04b17ecc72c4885d59d221bb701f17e1d74e03054ed3006a
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|