tyzhu commited on
Commit
5072dbb
1 Parent(s): fd494e0

Training in progress, epoch 2, checkpoint

Browse files
checkpoint-1024/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-1024/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-1024/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8acaf03467ccee86ae9e329faa5827113b15c29e694b1f96b5503ead193192
3
+ size 112130416
checkpoint-1024/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-1024/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1024/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f5778342c6f33fc48b5e65aa9a6741ca54a35e8abf8243aaa0049b68abdba7
3
+ size 224537202
checkpoint-1024/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fd4e9ff02f24d24f32e52dd14e217f00fcfe9255de71cb4d39bf05aaee0ee9
3
+ size 15024
checkpoint-1024/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa130e172e7f54a4e6e65d672aee8cf803a353a45f7bad0ed1a71956e1482f2
3
+ size 15024
checkpoint-1024/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0eb7445a1890000f0589318b7da46897fbc4756eedd89321b6c522ee2455ab
3
+ size 15024
checkpoint-1024/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa44aafc22a031c3a8d811410f1ba7c479dd7ea6d80bedb5c13e96f6f756741e
3
+ size 15024
checkpoint-1024/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc7dacd59f3ffbc768de04bdaae029f54f8d45528000bd99f743419fcc8d3ac
3
+ size 1064
checkpoint-1024/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-1024/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1024/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-1024/trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.998535871156662,
5
+ "eval_steps": 500,
6
+ "global_step": 1024,
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": 0.26115021109580994,
14
+ "learning_rate": 3e-05,
15
+ "loss": 2.0719,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.5856515373352855,
20
+ "grad_norm": 0.2679530680179596,
21
+ "learning_rate": 3e-05,
22
+ "loss": 1.969,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.8784773060029283,
27
+ "grad_norm": 0.2916224002838135,
28
+ "learning_rate": 3e-05,
29
+ "loss": 1.9686,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.9985358711566618,
34
+ "eval_accuracy": 0.43743589743589745,
35
+ "eval_loss": 3.6918885707855225,
36
+ "eval_runtime": 5.2974,
37
+ "eval_samples_per_second": 94.385,
38
+ "eval_steps_per_second": 11.893,
39
+ "step": 341
40
+ },
41
+ {
42
+ "epoch": 0.9985358711566618,
43
+ "eval_bleu": 0.1527908371131025,
44
+ "eval_exact_match": 0.012,
45
+ "eval_prefix_exact_match": 0.026,
46
+ "step": 341
47
+ },
48
+ {
49
+ "epoch": 1.171303074670571,
50
+ "grad_norm": 0.3534347712993622,
51
+ "learning_rate": 3e-05,
52
+ "loss": 1.9603,
53
+ "step": 400
54
+ },
55
+ {
56
+ "epoch": 1.4641288433382138,
57
+ "grad_norm": 0.3338424563407898,
58
+ "learning_rate": 3e-05,
59
+ "loss": 1.9235,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 1.7569546120058566,
64
+ "grad_norm": 0.4033390283584595,
65
+ "learning_rate": 3e-05,
66
+ "loss": 1.9337,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_accuracy": 0.44764102564102565,
72
+ "eval_loss": 3.7484843730926514,
73
+ "eval_runtime": 5.0649,
74
+ "eval_samples_per_second": 98.718,
75
+ "eval_steps_per_second": 12.438,
76
+ "step": 683
77
+ },
78
+ {
79
+ "epoch": 2.0,
80
+ "eval_bleu": 0.21311912714932216,
81
+ "eval_exact_match": 0.02,
82
+ "eval_prefix_exact_match": 0.032,
83
+ "step": 683
84
+ },
85
+ {
86
+ "epoch": 2.049780380673499,
87
+ "grad_norm": 0.38882532715797424,
88
+ "learning_rate": 3e-05,
89
+ "loss": 1.9267,
90
+ "step": 700
91
+ },
92
+ {
93
+ "epoch": 2.342606149341142,
94
+ "grad_norm": 0.44310709834098816,
95
+ "learning_rate": 3e-05,
96
+ "loss": 1.8823,
97
+ "step": 800
98
+ },
99
+ {
100
+ "epoch": 2.6354319180087846,
101
+ "grad_norm": 0.5196680426597595,
102
+ "learning_rate": 3e-05,
103
+ "loss": 1.901,
104
+ "step": 900
105
+ },
106
+ {
107
+ "epoch": 2.9282576866764276,
108
+ "grad_norm": 0.5293437242507935,
109
+ "learning_rate": 3e-05,
110
+ "loss": 1.9033,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 2.998535871156662,
115
+ "eval_accuracy": 0.4495897435897436,
116
+ "eval_loss": 3.882551670074463,
117
+ "eval_runtime": 5.1314,
118
+ "eval_samples_per_second": 97.439,
119
+ "eval_steps_per_second": 12.277,
120
+ "step": 1024
121
+ },
122
+ {
123
+ "epoch": 2.998535871156662,
124
+ "eval_bleu": 0.24307488023362148,
125
+ "eval_exact_match": 0.016,
126
+ "eval_prefix_exact_match": 0.032,
127
+ "step": 1024
128
+ }
129
+ ],
130
+ "logging_steps": 100,
131
+ "max_steps": 17050,
132
+ "num_input_tokens_seen": 0,
133
+ "num_train_epochs": 50,
134
+ "save_steps": 500,
135
+ "stateful_callbacks": {
136
+ "TrainerControl": {
137
+ "args": {
138
+ "should_epoch_stop": false,
139
+ "should_evaluate": false,
140
+ "should_log": false,
141
+ "should_save": true,
142
+ "should_training_stop": false
143
+ },
144
+ "attributes": {}
145
+ }
146
+ },
147
+ "total_flos": 8.797537312335462e+16,
148
+ "train_batch_size": 1,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }
checkpoint-1024/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cef08c7f10bf396c269dfc26104fd5a94756f5431d6448312805ef8e298380
3
+ size 5304
checkpoint-1024/vocab.json ADDED
The diff for this file is too large to render. See raw diff