Training in progress, epoch 2, checkpoint
Browse files- checkpoint-1058/README.md +9 -0
- checkpoint-1058/adapter_config.json +25 -0
- checkpoint-1058/adapter_model.safetensors +3 -0
- checkpoint-1058/added_tokens.json +5 -0
- checkpoint-1058/merges.txt +0 -0
- checkpoint-1058/optimizer.pt +3 -0
- checkpoint-1058/rng_state_0.pth +3 -0
- checkpoint-1058/rng_state_1.pth +3 -0
- checkpoint-1058/rng_state_2.pth +3 -0
- checkpoint-1058/rng_state_3.pth +3 -0
- checkpoint-1058/scheduler.pt +3 -0
- checkpoint-1058/special_tokens_map.json +14 -0
- checkpoint-1058/tokenizer.json +0 -0
- checkpoint-1058/tokenizer_config.json +43 -0
- checkpoint-1058/trainer_state.json +141 -0
- checkpoint-1058/training_args.bin +3 -0
- checkpoint-1058/vocab.json +0 -0
checkpoint-1058/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-1058/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-1058/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d0ad28e57881d4bb08739409cd450be71937d58c61b989d435d98630a58e0c7
|
3 |
+
size 112130416
|
checkpoint-1058/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1058/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1058/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:957afa72e49377d85bec04280e02f5b33a527e18dbe5a98a669695567fa9b9ca
|
3 |
+
size 224537202
|
checkpoint-1058/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb3c37fe70d28e07b56883476bf630741d46d260b67684564fa15146812ae116
|
3 |
+
size 15024
|
checkpoint-1058/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:191f1173f063793abd3ddd6ad2ce273604af6b408ea5301298951bac55ff257f
|
3 |
+
size 15024
|
checkpoint-1058/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d56b276d38bf0d2660b6712b96592588121643e0cde94450a30b7ce706bb2d6c
|
3 |
+
size 15024
|
checkpoint-1058/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6250a2f7fdd6add9072d5babc78527cff62efb7792dd6b7b7aa88301d210e3fc
|
3 |
+
size 15024
|
checkpoint-1058/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b871de9035826d4b30c30167a4fe8759528b610203dcdc247cfc5c19619b090
|
3 |
+
size 1064
|
checkpoint-1058/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-1058/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1058/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-1058/trainer_state.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1058,
|
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": 7.269421577453613,
|
14 |
+
"learning_rate": 0.0005,
|
15 |
+
"loss": 1.9195,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3780718336483932,
|
20 |
+
"grad_norm": 1.071650505065918,
|
21 |
+
"learning_rate": 0.0005,
|
22 |
+
"loss": 1.9396,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5671077504725898,
|
27 |
+
"grad_norm": 0.5662499070167542,
|
28 |
+
"learning_rate": 0.0005,
|
29 |
+
"loss": 2.3641,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7561436672967864,
|
34 |
+
"grad_norm": 0.47088223695755005,
|
35 |
+
"learning_rate": 0.0005,
|
36 |
+
"loss": 1.8969,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.945179584120983,
|
41 |
+
"grad_norm": 0.3653932511806488,
|
42 |
+
"learning_rate": 0.0005,
|
43 |
+
"loss": 1.8531,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_accuracy": 0.6214529147982063,
|
49 |
+
"eval_loss": 1.5580899715423584,
|
50 |
+
"eval_runtime": 5.56,
|
51 |
+
"eval_samples_per_second": 89.928,
|
52 |
+
"eval_steps_per_second": 11.331,
|
53 |
+
"step": 529
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.0,
|
57 |
+
"eval_exact_match": 14.4,
|
58 |
+
"eval_f1": 20.983333333333345,
|
59 |
+
"eval_qa_bleu": 12.514681390986086,
|
60 |
+
"eval_qa_exact_match": 0.102,
|
61 |
+
"eval_recite_bleu": 12.61307158352263,
|
62 |
+
"eval_recite_exact_match": 0.0,
|
63 |
+
"step": 529
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.1342155009451795,
|
67 |
+
"grad_norm": 0.5318541526794434,
|
68 |
+
"learning_rate": 0.0005,
|
69 |
+
"loss": 1.6622,
|
70 |
+
"step": 600
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.3232514177693762,
|
74 |
+
"grad_norm": 235.6529998779297,
|
75 |
+
"learning_rate": 0.0005,
|
76 |
+
"loss": 1.5596,
|
77 |
+
"step": 700
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.5122873345935728,
|
81 |
+
"grad_norm": 0.5057249069213867,
|
82 |
+
"learning_rate": 0.0005,
|
83 |
+
"loss": 1.5296,
|
84 |
+
"step": 800
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.7013232514177694,
|
88 |
+
"grad_norm": 0.5339187383651733,
|
89 |
+
"learning_rate": 0.0005,
|
90 |
+
"loss": 1.5036,
|
91 |
+
"step": 900
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.8903591682419658,
|
95 |
+
"grad_norm": 0.5649825930595398,
|
96 |
+
"learning_rate": 0.0005,
|
97 |
+
"loss": 1.4884,
|
98 |
+
"step": 1000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.0,
|
102 |
+
"eval_accuracy": 0.6643587443946188,
|
103 |
+
"eval_loss": 1.2189537286758423,
|
104 |
+
"eval_runtime": 6.192,
|
105 |
+
"eval_samples_per_second": 80.749,
|
106 |
+
"eval_steps_per_second": 10.174,
|
107 |
+
"step": 1058
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.0,
|
111 |
+
"eval_exact_match": 11.2,
|
112 |
+
"eval_f1": 18.31238095238096,
|
113 |
+
"eval_qa_bleu": 10.766593815425745,
|
114 |
+
"eval_qa_exact_match": 0.096,
|
115 |
+
"eval_recite_bleu": 13.257993783037875,
|
116 |
+
"eval_recite_exact_match": 0.002,
|
117 |
+
"step": 1058
|
118 |
+
}
|
119 |
+
],
|
120 |
+
"logging_steps": 100,
|
121 |
+
"max_steps": 26450,
|
122 |
+
"num_input_tokens_seen": 0,
|
123 |
+
"num_train_epochs": 50,
|
124 |
+
"save_steps": 500,
|
125 |
+
"stateful_callbacks": {
|
126 |
+
"TrainerControl": {
|
127 |
+
"args": {
|
128 |
+
"should_epoch_stop": false,
|
129 |
+
"should_evaluate": false,
|
130 |
+
"should_log": false,
|
131 |
+
"should_save": true,
|
132 |
+
"should_training_stop": false
|
133 |
+
},
|
134 |
+
"attributes": {}
|
135 |
+
}
|
136 |
+
},
|
137 |
+
"total_flos": 9.642374156674662e+16,
|
138 |
+
"train_batch_size": 1,
|
139 |
+
"trial_name": null,
|
140 |
+
"trial_params": null
|
141 |
+
}
|
checkpoint-1058/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1820a0b512c2fa8b3950f986e6f44420dacfa98792c1f255a5842682ec51f235
|
3 |
+
size 5304
|
checkpoint-1058/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|