Training in progress, epoch 4, checkpoint
Browse files- checkpoint-1707/README.md +9 -0
- checkpoint-1707/adapter_config.json +25 -0
- checkpoint-1707/adapter_model.safetensors +3 -0
- checkpoint-1707/added_tokens.json +5 -0
- checkpoint-1707/merges.txt +0 -0
- checkpoint-1707/optimizer.pt +3 -0
- checkpoint-1707/rng_state_0.pth +3 -0
- checkpoint-1707/rng_state_1.pth +3 -0
- checkpoint-1707/rng_state_2.pth +3 -0
- checkpoint-1707/rng_state_3.pth +3 -0
- checkpoint-1707/scheduler.pt +3 -0
- checkpoint-1707/special_tokens_map.json +14 -0
- checkpoint-1707/tokenizer.json +0 -0
- checkpoint-1707/tokenizer_config.json +43 -0
- checkpoint-1707/trainer_state.json +232 -0
- checkpoint-1707/training_args.bin +3 -0
- checkpoint-1707/vocab.json +0 -0
checkpoint-1707/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.5.0
|
checkpoint-1707/adapter_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-4B",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"k_proj",
|
19 |
+
"v_proj",
|
20 |
+
"down_proj",
|
21 |
+
"gate_proj",
|
22 |
+
"up_proj"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM"
|
25 |
+
}
|
checkpoint-1707/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:924c3a4d6c9e8439a52a09b5ab849d361ad5f77fbc06e9cbfb3a4f9583962548
|
3 |
+
size 112130416
|
checkpoint-1707/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1707/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1707/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92760969eb3b43e79c8578643b52a61d79188aa713de54d5feba43cd5ae37190
|
3 |
+
size 224537202
|
checkpoint-1707/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace172984bb66d39a99e7dd9a5bfc54e40430b9843356cf9b9b1534d8d75b918
|
3 |
+
size 15024
|
checkpoint-1707/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1158c8814b63073467bf02c279c75cc4cd14f26603ead0c4236a66139c58413
|
3 |
+
size 15024
|
checkpoint-1707/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88530e66b3526c8aa8e3fc2e6f09ed0d775891848469fce44eacfd98fea53a6a
|
3 |
+
size 15024
|
checkpoint-1707/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:860a83a924c36bd26aba67ea76c19aa3c5ef32e1b2096c873e6ae40188b49c10
|
3 |
+
size 15024
|
checkpoint-1707/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0548d738a701507c33991ac1afd40e88000e3b6e2023d7b8b807bd8bb713fb14
|
3 |
+
size 1064
|
checkpoint-1707/special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": "<|endoftext|>"
|
14 |
+
}
|
checkpoint-1707/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1707/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
checkpoint-1707/trainer_state.json
ADDED
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.998535871156662,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1707,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.29282576866764276,
|
13 |
+
"grad_norm": 0.2411503791809082,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 2.0009,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5856515373352855,
|
20 |
+
"grad_norm": 0.22286373376846313,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.9538,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.8784773060029283,
|
27 |
+
"grad_norm": 0.24079065024852753,
|
28 |
+
"learning_rate": 0.0001,
|
29 |
+
"loss": 1.9571,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9985358711566618,
|
34 |
+
"eval_accuracy": 0.45379487179487177,
|
35 |
+
"eval_loss": 3.9512319564819336,
|
36 |
+
"eval_runtime": 5.0647,
|
37 |
+
"eval_samples_per_second": 98.722,
|
38 |
+
"eval_steps_per_second": 12.439,
|
39 |
+
"step": 341
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.9985358711566618,
|
43 |
+
"eval_bleu": 0.28767194245703276,
|
44 |
+
"eval_exact_match": 0.03,
|
45 |
+
"eval_prefix_exact_match": 0.042,
|
46 |
+
"step": 341
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.171303074670571,
|
50 |
+
"grad_norm": 0.33546799421310425,
|
51 |
+
"learning_rate": 0.0001,
|
52 |
+
"loss": 1.9255,
|
53 |
+
"step": 400
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.4641288433382138,
|
57 |
+
"grad_norm": 0.3515666723251343,
|
58 |
+
"learning_rate": 0.0001,
|
59 |
+
"loss": 1.8684,
|
60 |
+
"step": 500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.7569546120058566,
|
64 |
+
"grad_norm": 0.35733896493911743,
|
65 |
+
"learning_rate": 0.0001,
|
66 |
+
"loss": 1.8819,
|
67 |
+
"step": 600
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 2.0,
|
71 |
+
"eval_accuracy": 0.4482564102564103,
|
72 |
+
"eval_loss": 4.112804412841797,
|
73 |
+
"eval_runtime": 5.0848,
|
74 |
+
"eval_samples_per_second": 98.333,
|
75 |
+
"eval_steps_per_second": 12.39,
|
76 |
+
"step": 683
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 2.0,
|
80 |
+
"eval_bleu": 0.24521038067633488,
|
81 |
+
"eval_exact_match": 0.02,
|
82 |
+
"eval_prefix_exact_match": 0.044,
|
83 |
+
"step": 683
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 2.049780380673499,
|
87 |
+
"grad_norm": 0.3784458339214325,
|
88 |
+
"learning_rate": 0.0001,
|
89 |
+
"loss": 1.8613,
|
90 |
+
"step": 700
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.342606149341142,
|
94 |
+
"grad_norm": 0.46702849864959717,
|
95 |
+
"learning_rate": 0.0001,
|
96 |
+
"loss": 1.743,
|
97 |
+
"step": 800
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.6354319180087846,
|
101 |
+
"grad_norm": 0.5156407356262207,
|
102 |
+
"learning_rate": 0.0001,
|
103 |
+
"loss": 1.7653,
|
104 |
+
"step": 900
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.9282576866764276,
|
108 |
+
"grad_norm": 0.4755038619041443,
|
109 |
+
"learning_rate": 0.0001,
|
110 |
+
"loss": 1.7702,
|
111 |
+
"step": 1000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.998535871156662,
|
115 |
+
"eval_accuracy": 0.446051282051282,
|
116 |
+
"eval_loss": 4.327652454376221,
|
117 |
+
"eval_runtime": 5.1641,
|
118 |
+
"eval_samples_per_second": 96.822,
|
119 |
+
"eval_steps_per_second": 12.2,
|
120 |
+
"step": 1024
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.998535871156662,
|
124 |
+
"eval_bleu": 0.2598440457703149,
|
125 |
+
"eval_exact_match": 0.018,
|
126 |
+
"eval_prefix_exact_match": 0.034,
|
127 |
+
"step": 1024
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 3.22108345534407,
|
131 |
+
"grad_norm": 0.5288150906562805,
|
132 |
+
"learning_rate": 0.0001,
|
133 |
+
"loss": 1.6325,
|
134 |
+
"step": 1100
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.513909224011713,
|
138 |
+
"grad_norm": 0.5784010887145996,
|
139 |
+
"learning_rate": 0.0001,
|
140 |
+
"loss": 1.5896,
|
141 |
+
"step": 1200
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.8067349926793557,
|
145 |
+
"grad_norm": 0.6458429098129272,
|
146 |
+
"learning_rate": 0.0001,
|
147 |
+
"loss": 1.6163,
|
148 |
+
"step": 1300
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 4.0,
|
152 |
+
"eval_accuracy": 0.44235897435897437,
|
153 |
+
"eval_loss": 4.584905624389648,
|
154 |
+
"eval_runtime": 4.9243,
|
155 |
+
"eval_samples_per_second": 101.538,
|
156 |
+
"eval_steps_per_second": 12.794,
|
157 |
+
"step": 1366
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 4.0,
|
161 |
+
"eval_bleu": 0.27967222841565076,
|
162 |
+
"eval_exact_match": 0.01,
|
163 |
+
"eval_prefix_exact_match": 0.038,
|
164 |
+
"step": 1366
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.099560761346998,
|
168 |
+
"grad_norm": 0.732841432094574,
|
169 |
+
"learning_rate": 0.0001,
|
170 |
+
"loss": 1.5441,
|
171 |
+
"step": 1400
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 4.392386530014641,
|
175 |
+
"grad_norm": 0.7372816205024719,
|
176 |
+
"learning_rate": 0.0001,
|
177 |
+
"loss": 1.4142,
|
178 |
+
"step": 1500
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 4.685212298682284,
|
182 |
+
"grad_norm": 0.8235049247741699,
|
183 |
+
"learning_rate": 0.0001,
|
184 |
+
"loss": 1.4198,
|
185 |
+
"step": 1600
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 4.978038067349927,
|
189 |
+
"grad_norm": 0.7765743732452393,
|
190 |
+
"learning_rate": 0.0001,
|
191 |
+
"loss": 1.4427,
|
192 |
+
"step": 1700
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 4.998535871156662,
|
196 |
+
"eval_accuracy": 0.43861538461538463,
|
197 |
+
"eval_loss": 4.850330829620361,
|
198 |
+
"eval_runtime": 4.9395,
|
199 |
+
"eval_samples_per_second": 101.224,
|
200 |
+
"eval_steps_per_second": 12.754,
|
201 |
+
"step": 1707
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.998535871156662,
|
205 |
+
"eval_bleu": 0.2170008640509292,
|
206 |
+
"eval_exact_match": 0.006,
|
207 |
+
"eval_prefix_exact_match": 0.032,
|
208 |
+
"step": 1707
|
209 |
+
}
|
210 |
+
],
|
211 |
+
"logging_steps": 100,
|
212 |
+
"max_steps": 17050,
|
213 |
+
"num_input_tokens_seen": 0,
|
214 |
+
"num_train_epochs": 50,
|
215 |
+
"save_steps": 500,
|
216 |
+
"stateful_callbacks": {
|
217 |
+
"TrainerControl": {
|
218 |
+
"args": {
|
219 |
+
"should_epoch_stop": false,
|
220 |
+
"should_evaluate": false,
|
221 |
+
"should_log": false,
|
222 |
+
"should_save": true,
|
223 |
+
"should_training_stop": false
|
224 |
+
},
|
225 |
+
"attributes": {}
|
226 |
+
}
|
227 |
+
},
|
228 |
+
"total_flos": 1.466248183330898e+17,
|
229 |
+
"train_batch_size": 1,
|
230 |
+
"trial_name": null,
|
231 |
+
"trial_params": null
|
232 |
+
}
|
checkpoint-1707/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e63e74298c414f7364874e60281a380506bddfac466373e2426a740b4eb5594
|
3 |
+
size 5304
|
checkpoint-1707/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|