Training in progress, epoch 7, checkpoint
Browse files- checkpoint-1750/README.md +9 -0
- checkpoint-1750/adapter_config.json +25 -0
- checkpoint-1750/adapter_model.safetensors +3 -0
- checkpoint-1750/added_tokens.json +5 -0
- checkpoint-1750/merges.txt +0 -0
- checkpoint-1750/optimizer.pt +3 -0
- checkpoint-1750/rng_state_0.pth +3 -0
- checkpoint-1750/rng_state_1.pth +3 -0
- checkpoint-1750/rng_state_2.pth +3 -0
- checkpoint-1750/rng_state_3.pth +3 -0
- checkpoint-1750/scheduler.pt +3 -0
- checkpoint-1750/special_tokens_map.json +14 -0
- checkpoint-1750/tokenizer.json +0 -0
- checkpoint-1750/tokenizer_config.json +43 -0
- checkpoint-1750/trainer_state.json +257 -0
- checkpoint-1750/training_args.bin +3 -0
- checkpoint-1750/vocab.json +0 -0
checkpoint-1750/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-1750/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-1750/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6581280b5dc3d8d8d9a212f8135b2756c6ae37c299698502bb1cb2d9c66d112
|
3 |
+
size 112130416
|
checkpoint-1750/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1750/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1750/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30a83682a742a338d51d363e95a9511b27852609d2aec0652fdca461129ed863
|
3 |
+
size 224537202
|
checkpoint-1750/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:365e25271243a1070dc0263a1af8b71c1a6472776f64683ee814a097895b9516
|
3 |
+
size 15024
|
checkpoint-1750/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a98bf2ac85ce160f22d7366ae18b1ddf52b3db79064aefca8295f98f9d958d1f
|
3 |
+
size 15024
|
checkpoint-1750/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95ddf3466c2e9587aba3126bbc584818cbc473b1df513d7ec3d6a0f553db3953
|
3 |
+
size 15024
|
checkpoint-1750/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4155cd565c654a5c9798323aa2e858a27d05f204fa8ca435e77aae98b85a114
|
3 |
+
size 15024
|
checkpoint-1750/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d532f59f5b0431482a378ff9aa54b5e33d0f4d3899815de6611afb344f15679
|
3 |
+
size 1064
|
checkpoint-1750/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-1750/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1750/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-1750/trainer_state.json
ADDED
@@ -0,0 +1,257 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1750,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4,
|
13 |
+
"grad_norm": 0.48472875356674194,
|
14 |
+
"learning_rate": 0.0003,
|
15 |
+
"loss": 2.3219,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8,
|
20 |
+
"grad_norm": 0.4583953619003296,
|
21 |
+
"learning_rate": 0.0003,
|
22 |
+
"loss": 2.2487,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_accuracy": 0.5168253968253969,
|
28 |
+
"eval_loss": 2.311781167984009,
|
29 |
+
"eval_runtime": 5.4425,
|
30 |
+
"eval_samples_per_second": 91.87,
|
31 |
+
"eval_steps_per_second": 11.576,
|
32 |
+
"step": 250
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"eval_exact_match": 18.6,
|
37 |
+
"eval_f1": 26.999121042356347,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.2,
|
42 |
+
"grad_norm": 0.6610094904899597,
|
43 |
+
"learning_rate": 0.0003,
|
44 |
+
"loss": 2.083,
|
45 |
+
"step": 300
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.6,
|
49 |
+
"grad_norm": 0.7361629605293274,
|
50 |
+
"learning_rate": 0.0003,
|
51 |
+
"loss": 1.9274,
|
52 |
+
"step": 400
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 2.0,
|
56 |
+
"grad_norm": 0.6793610453605652,
|
57 |
+
"learning_rate": 0.0003,
|
58 |
+
"loss": 1.9113,
|
59 |
+
"step": 500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 2.0,
|
63 |
+
"eval_accuracy": 0.5153650793650794,
|
64 |
+
"eval_loss": 2.3749232292175293,
|
65 |
+
"eval_runtime": 5.2167,
|
66 |
+
"eval_samples_per_second": 95.846,
|
67 |
+
"eval_steps_per_second": 12.077,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.0,
|
72 |
+
"eval_exact_match": 18.2,
|
73 |
+
"eval_f1": 26.209704184704197,
|
74 |
+
"step": 500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.4,
|
78 |
+
"grad_norm": 0.8843489289283752,
|
79 |
+
"learning_rate": 0.0003,
|
80 |
+
"loss": 1.4602,
|
81 |
+
"step": 600
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.8,
|
85 |
+
"grad_norm": 0.8380613923072815,
|
86 |
+
"learning_rate": 0.0003,
|
87 |
+
"loss": 1.4924,
|
88 |
+
"step": 700
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 3.0,
|
92 |
+
"eval_accuracy": 0.5098730158730159,
|
93 |
+
"eval_loss": 2.5289740562438965,
|
94 |
+
"eval_runtime": 5.3631,
|
95 |
+
"eval_samples_per_second": 93.23,
|
96 |
+
"eval_steps_per_second": 11.747,
|
97 |
+
"step": 750
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 3.0,
|
101 |
+
"eval_exact_match": 16.6,
|
102 |
+
"eval_f1": 24.526153291153296,
|
103 |
+
"step": 750
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 3.2,
|
107 |
+
"grad_norm": 1.068247675895691,
|
108 |
+
"learning_rate": 0.0003,
|
109 |
+
"loss": 1.2869,
|
110 |
+
"step": 800
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.6,
|
114 |
+
"grad_norm": 1.041741967201233,
|
115 |
+
"learning_rate": 0.0003,
|
116 |
+
"loss": 1.0749,
|
117 |
+
"step": 900
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 4.0,
|
121 |
+
"grad_norm": 1.267968773841858,
|
122 |
+
"learning_rate": 0.0003,
|
123 |
+
"loss": 1.1157,
|
124 |
+
"step": 1000
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 4.0,
|
128 |
+
"eval_accuracy": 0.5038412698412699,
|
129 |
+
"eval_loss": 2.794942855834961,
|
130 |
+
"eval_runtime": 5.0088,
|
131 |
+
"eval_samples_per_second": 99.825,
|
132 |
+
"eval_steps_per_second": 12.578,
|
133 |
+
"step": 1000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 4.0,
|
137 |
+
"eval_exact_match": 16.4,
|
138 |
+
"eval_f1": 23.978561993561993,
|
139 |
+
"step": 1000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 4.4,
|
143 |
+
"grad_norm": 1.1971005201339722,
|
144 |
+
"learning_rate": 0.0003,
|
145 |
+
"loss": 0.7367,
|
146 |
+
"step": 1100
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 4.8,
|
150 |
+
"grad_norm": 1.2383127212524414,
|
151 |
+
"learning_rate": 0.0003,
|
152 |
+
"loss": 0.7814,
|
153 |
+
"step": 1200
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.0,
|
157 |
+
"eval_accuracy": 0.49853968253968256,
|
158 |
+
"eval_loss": 3.0137181282043457,
|
159 |
+
"eval_runtime": 5.1368,
|
160 |
+
"eval_samples_per_second": 97.337,
|
161 |
+
"eval_steps_per_second": 12.264,
|
162 |
+
"step": 1250
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 5.0,
|
166 |
+
"eval_exact_match": 14.8,
|
167 |
+
"eval_f1": 21.880294705294705,
|
168 |
+
"step": 1250
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 5.2,
|
172 |
+
"grad_norm": 0.9558005928993225,
|
173 |
+
"learning_rate": 0.0003,
|
174 |
+
"loss": 0.6786,
|
175 |
+
"step": 1300
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 5.6,
|
179 |
+
"grad_norm": 1.1341361999511719,
|
180 |
+
"learning_rate": 0.0003,
|
181 |
+
"loss": 0.5741,
|
182 |
+
"step": 1400
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 6.0,
|
186 |
+
"grad_norm": 1.1375033855438232,
|
187 |
+
"learning_rate": 0.0003,
|
188 |
+
"loss": 0.605,
|
189 |
+
"step": 1500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 6.0,
|
193 |
+
"eval_accuracy": 0.49657142857142855,
|
194 |
+
"eval_loss": 3.220507860183716,
|
195 |
+
"eval_runtime": 5.2708,
|
196 |
+
"eval_samples_per_second": 94.863,
|
197 |
+
"eval_steps_per_second": 11.953,
|
198 |
+
"step": 1500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 6.0,
|
202 |
+
"eval_exact_match": 15.4,
|
203 |
+
"eval_f1": 22.281807987334307,
|
204 |
+
"step": 1500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 6.4,
|
208 |
+
"grad_norm": 1.118528962135315,
|
209 |
+
"learning_rate": 0.0003,
|
210 |
+
"loss": 0.4684,
|
211 |
+
"step": 1600
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 6.8,
|
215 |
+
"grad_norm": 0.9311291575431824,
|
216 |
+
"learning_rate": 0.0003,
|
217 |
+
"loss": 0.4968,
|
218 |
+
"step": 1700
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 7.0,
|
222 |
+
"eval_accuracy": 0.4946984126984127,
|
223 |
+
"eval_loss": 3.3760199546813965,
|
224 |
+
"eval_runtime": 5.0734,
|
225 |
+
"eval_samples_per_second": 98.554,
|
226 |
+
"eval_steps_per_second": 12.418,
|
227 |
+
"step": 1750
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 7.0,
|
231 |
+
"eval_exact_match": 14.8,
|
232 |
+
"eval_f1": 21.79480811586075,
|
233 |
+
"step": 1750
|
234 |
+
}
|
235 |
+
],
|
236 |
+
"logging_steps": 100,
|
237 |
+
"max_steps": 12500,
|
238 |
+
"num_input_tokens_seen": 0,
|
239 |
+
"num_train_epochs": 50,
|
240 |
+
"save_steps": 500,
|
241 |
+
"stateful_callbacks": {
|
242 |
+
"TrainerControl": {
|
243 |
+
"args": {
|
244 |
+
"should_epoch_stop": false,
|
245 |
+
"should_evaluate": false,
|
246 |
+
"should_log": false,
|
247 |
+
"should_save": true,
|
248 |
+
"should_training_stop": false
|
249 |
+
},
|
250 |
+
"attributes": {}
|
251 |
+
}
|
252 |
+
},
|
253 |
+
"total_flos": 4.527385022038016e+16,
|
254 |
+
"train_batch_size": 1,
|
255 |
+
"trial_name": null,
|
256 |
+
"trial_params": null
|
257 |
+
}
|
checkpoint-1750/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dae73bb50794744b259c1eaaeb67f6ae0b1d0f39b0a32b5f1162fc82e3a5d6a6
|
3 |
+
size 5304
|
checkpoint-1750/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|