Training in progress, epoch 3, checkpoint
Browse files- checkpoint-1587/README.md +9 -0
- checkpoint-1587/adapter_config.json +25 -0
- checkpoint-1587/adapter_model.safetensors +3 -0
- checkpoint-1587/added_tokens.json +5 -0
- checkpoint-1587/merges.txt +0 -0
- checkpoint-1587/optimizer.pt +3 -0
- checkpoint-1587/rng_state_0.pth +3 -0
- checkpoint-1587/rng_state_1.pth +3 -0
- checkpoint-1587/rng_state_2.pth +3 -0
- checkpoint-1587/rng_state_3.pth +3 -0
- checkpoint-1587/scheduler.pt +3 -0
- checkpoint-1587/special_tokens_map.json +14 -0
- checkpoint-1587/tokenizer.json +0 -0
- checkpoint-1587/tokenizer_config.json +43 -0
- checkpoint-1587/trainer_state.json +183 -0
- checkpoint-1587/training_args.bin +3 -0
- checkpoint-1587/vocab.json +0 -0
checkpoint-1587/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-1587/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-1587/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae5407f92f7f07c39d7fe87b45811a9ec70128be1e9cf12b24f0fa380ad11ee8
|
3 |
+
size 112130416
|
checkpoint-1587/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1587/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1587/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a2d0591c68986d014c797782275559afb49032b7ee5e0805efb130285deb4a
|
3 |
+
size 224537202
|
checkpoint-1587/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1008dc54079343aaefc46fa5c95479a0db7304024186db34c7a166ead7a30a2
|
3 |
+
size 15024
|
checkpoint-1587/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17ad761d69d26ff0f3355b4c69c3cf4e9f8343b98fd941ee447bd478192fac1d
|
3 |
+
size 15024
|
checkpoint-1587/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbdbaac4efcffee4dc354bd4b30bf8a4e978cc408de58040955679fccedee377
|
3 |
+
size 15024
|
checkpoint-1587/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db9c577e6fdb59676a3e4ffb5e8ac20bab14a1433889f80e8d3cbb93d2c172b4
|
3 |
+
size 15024
|
checkpoint-1587/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c712d51d8bd7d2da430ecc3f0cab82d9e334b17a2588d393c31b65eac6e6424b
|
3 |
+
size 1064
|
checkpoint-1587/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-1587/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1587/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-1587/trainer_state.json
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1587,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1890359168241966,
|
13 |
+
"grad_norm": 0.5107442140579224,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.0482,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3780718336483932,
|
20 |
+
"grad_norm": 0.5563424229621887,
|
21 |
+
"learning_rate": 5e-05,
|
22 |
+
"loss": 1.8835,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5671077504725898,
|
27 |
+
"grad_norm": 0.4735371172428131,
|
28 |
+
"learning_rate": 5e-05,
|
29 |
+
"loss": 1.8512,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7561436672967864,
|
34 |
+
"grad_norm": 0.4543495178222656,
|
35 |
+
"learning_rate": 5e-05,
|
36 |
+
"loss": 1.8489,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.945179584120983,
|
41 |
+
"grad_norm": 0.5007112622261047,
|
42 |
+
"learning_rate": 5e-05,
|
43 |
+
"loss": 1.8439,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 0.5733333333333334,
|
49 |
+
"eval_loss": 1.6194567680358887,
|
50 |
+
"eval_runtime": 5.4154,
|
51 |
+
"eval_samples_per_second": 92.33,
|
52 |
+
"eval_steps_per_second": 11.634,
|
53 |
+
"step": 529
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.0,
|
57 |
+
"eval_exact_match": 17.0,
|
58 |
+
"eval_f1": 26.880952380952387,
|
59 |
+
"step": 529
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.1342155009451795,
|
63 |
+
"grad_norm": 0.5181360244750977,
|
64 |
+
"learning_rate": 5e-05,
|
65 |
+
"loss": 1.8217,
|
66 |
+
"step": 600
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.3232514177693762,
|
70 |
+
"grad_norm": 1.1348918676376343,
|
71 |
+
"learning_rate": 5e-05,
|
72 |
+
"loss": 1.7866,
|
73 |
+
"step": 700
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.5122873345935728,
|
77 |
+
"grad_norm": 0.661758303642273,
|
78 |
+
"learning_rate": 5e-05,
|
79 |
+
"loss": 1.7934,
|
80 |
+
"step": 800
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.7013232514177694,
|
84 |
+
"grad_norm": 0.5634772777557373,
|
85 |
+
"learning_rate": 5e-05,
|
86 |
+
"loss": 1.7731,
|
87 |
+
"step": 900
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.8903591682419658,
|
91 |
+
"grad_norm": 0.6698930263519287,
|
92 |
+
"learning_rate": 5e-05,
|
93 |
+
"loss": 1.7969,
|
94 |
+
"step": 1000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 2.0,
|
98 |
+
"eval_accuracy": 0.5751794871794872,
|
99 |
+
"eval_loss": 1.603736162185669,
|
100 |
+
"eval_runtime": 5.0986,
|
101 |
+
"eval_samples_per_second": 98.066,
|
102 |
+
"eval_steps_per_second": 12.356,
|
103 |
+
"step": 1058
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 2.0,
|
107 |
+
"eval_exact_match": 17.6,
|
108 |
+
"eval_f1": 27.218095238095238,
|
109 |
+
"step": 1058
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 2.0793950850661624,
|
113 |
+
"grad_norm": 0.6265193223953247,
|
114 |
+
"learning_rate": 5e-05,
|
115 |
+
"loss": 1.7416,
|
116 |
+
"step": 1100
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.268431001890359,
|
120 |
+
"grad_norm": 0.812364935874939,
|
121 |
+
"learning_rate": 5e-05,
|
122 |
+
"loss": 1.6957,
|
123 |
+
"step": 1200
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.4574669187145557,
|
127 |
+
"grad_norm": 1.0972926616668701,
|
128 |
+
"learning_rate": 5e-05,
|
129 |
+
"loss": 1.7033,
|
130 |
+
"step": 1300
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.6465028355387523,
|
134 |
+
"grad_norm": 1.0831658840179443,
|
135 |
+
"learning_rate": 5e-05,
|
136 |
+
"loss": 1.6935,
|
137 |
+
"step": 1400
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.835538752362949,
|
141 |
+
"grad_norm": 1.0022494792938232,
|
142 |
+
"learning_rate": 5e-05,
|
143 |
+
"loss": 1.6799,
|
144 |
+
"step": 1500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.0,
|
148 |
+
"eval_accuracy": 0.573025641025641,
|
149 |
+
"eval_loss": 1.6428505182266235,
|
150 |
+
"eval_runtime": 5.1488,
|
151 |
+
"eval_samples_per_second": 97.111,
|
152 |
+
"eval_steps_per_second": 12.236,
|
153 |
+
"step": 1587
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 3.0,
|
157 |
+
"eval_exact_match": 20.2,
|
158 |
+
"eval_f1": 27.93809523809523,
|
159 |
+
"step": 1587
|
160 |
+
}
|
161 |
+
],
|
162 |
+
"logging_steps": 100,
|
163 |
+
"max_steps": 26450,
|
164 |
+
"num_input_tokens_seen": 0,
|
165 |
+
"num_train_epochs": 50,
|
166 |
+
"save_steps": 500,
|
167 |
+
"stateful_callbacks": {
|
168 |
+
"TrainerControl": {
|
169 |
+
"args": {
|
170 |
+
"should_epoch_stop": false,
|
171 |
+
"should_evaluate": false,
|
172 |
+
"should_log": false,
|
173 |
+
"should_save": true,
|
174 |
+
"should_training_stop": false
|
175 |
+
},
|
176 |
+
"attributes": {}
|
177 |
+
}
|
178 |
+
},
|
179 |
+
"total_flos": 9.776262836492698e+16,
|
180 |
+
"train_batch_size": 1,
|
181 |
+
"trial_name": null,
|
182 |
+
"trial_params": null
|
183 |
+
}
|
checkpoint-1587/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f01d18f717251d8791982fc93ed5352f2d247add98e1102e2a52cc0a32128bb7
|
3 |
+
size 5304
|
checkpoint-1587/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|