Training in progress, epoch 0, checkpoint
Browse files- checkpoint-341/README.md +9 -0
- checkpoint-341/adapter_config.json +25 -0
- checkpoint-341/adapter_model.safetensors +3 -0
- checkpoint-341/added_tokens.json +5 -0
- checkpoint-341/merges.txt +0 -0
- checkpoint-341/optimizer.pt +3 -0
- checkpoint-341/rng_state_0.pth +3 -0
- checkpoint-341/rng_state_1.pth +3 -0
- checkpoint-341/rng_state_2.pth +3 -0
- checkpoint-341/rng_state_3.pth +3 -0
- checkpoint-341/scheduler.pt +3 -0
- checkpoint-341/special_tokens_map.json +14 -0
- checkpoint-341/tokenizer.json +0 -0
- checkpoint-341/tokenizer_config.json +43 -0
- checkpoint-341/trainer_state.json +70 -0
- checkpoint-341/training_args.bin +3 -0
- checkpoint-341/vocab.json +0 -0
checkpoint-341/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-341/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-341/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8eee0e83a081bf6cedafc1d872a177e2bcef7ce1d113acf9c347a1375077716
|
3 |
+
size 112130416
|
checkpoint-341/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-341/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-341/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebfd611761993801f1662bb977e6a91947863b3edd22b5cfaf3e10fc470b6f28
|
3 |
+
size 224537202
|
checkpoint-341/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3b429a86a575cbf896b9f3211624258c926e760fb7a6b78b1bddea20bce0db7
|
3 |
+
size 15024
|
checkpoint-341/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ada55898a19e60848ceb78efd9c836ec71622b429ed9dd1b1611476ba036bbb
|
3 |
+
size 15024
|
checkpoint-341/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4907abb8113a62b89056dbcc63aadbc5818d3f756b6f295e1b0d62830b30b5
|
3 |
+
size 15024
|
checkpoint-341/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e0e16976296ec9ce8b31359165ff24c395720b493dc928f0c1724494237df0b
|
3 |
+
size 15024
|
checkpoint-341/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9d708fbed88e09c3b287077852d0746bde2ab5c6154098b9c1edf14184f513
|
3 |
+
size 1064
|
checkpoint-341/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-341/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-341/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-341/trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9985358711566618,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 341,
|
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 |
+
"logging_steps": 100,
|
50 |
+
"max_steps": 17050,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 50,
|
53 |
+
"save_steps": 500,
|
54 |
+
"stateful_callbacks": {
|
55 |
+
"TrainerControl": {
|
56 |
+
"args": {
|
57 |
+
"should_epoch_stop": false,
|
58 |
+
"should_evaluate": false,
|
59 |
+
"should_log": false,
|
60 |
+
"should_save": true,
|
61 |
+
"should_training_stop": false
|
62 |
+
},
|
63 |
+
"attributes": {}
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"total_flos": 2.932523890691277e+16,
|
67 |
+
"train_batch_size": 1,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
checkpoint-341/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-341/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|