Training in progress, epoch 1, checkpoint
Browse files- checkpoint-250/adapter_config.json +1 -1
- checkpoint-250/adapter_model.bin +3 -0
- checkpoint-250/added_tokens.json +3 -3
- checkpoint-250/optimizer.pt +2 -2
- checkpoint-250/rng_state_0.pth +1 -1
- checkpoint-250/rng_state_1.pth +1 -1
- checkpoint-250/rng_state_2.pth +1 -1
- checkpoint-250/rng_state_3.pth +1 -1
- checkpoint-250/special_tokens_map.json +4 -12
- checkpoint-250/tokenizer.json +0 -0
- checkpoint-250/tokenizer.model +3 -0
- checkpoint-250/tokenizer_config.json +17 -20
- checkpoint-250/trainer_state.json +10 -26
- checkpoint-250/training_args.bin +2 -2
checkpoint-250/adapter_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
checkpoint-250/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ef217ccbd903fb321e924cb94add0242a28db728e542e9611ce5fd3231f2374
|
3 |
+
size 143269386
|
checkpoint-250/added_tokens.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
}
|
checkpoint-250/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf54e44689b027d0fa77b3b7659d74cc20b54fcba7920f3607458731aa8d8e33
|
3 |
+
size 286585234
|
checkpoint-250/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dc34686ffce674ceea4132dde9e2364deb3134693da9e54ffaabe419a6a9b09
|
3 |
size 15024
|
checkpoint-250/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb03dc224530159a2021b8c7503173f06392798cc662ac104090b48769ac2d7e
|
3 |
size 15024
|
checkpoint-250/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c3935ff01fd7944272c9e5647090f0b94a975358eaabcc0e6f2b36f9e5722dc
|
3 |
size 15024
|
checkpoint-250/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e16290622104234d57dfb4dfcc45eb682fe7f81ebbd5c13a542e166f7cbd17a8
|
3 |
size 15024
|
checkpoint-250/special_tokens_map.json
CHANGED
@@ -1,14 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
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 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
checkpoint-250/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-250/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-250/tokenizer_config.json
CHANGED
@@ -1,24 +1,23 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
-
"content": "
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
-
"content": "
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
@@ -26,18 +25,16 @@
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"additional_special_tokens": [
|
30 |
-
|
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": "
|
37 |
-
"
|
38 |
-
"model_max_length":
|
39 |
-
"pad_token": "
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
43 |
}
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "left",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
}
|
checkpoint-250/trainer_state.json
CHANGED
@@ -10,53 +10,37 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.4,
|
13 |
-
"grad_norm": 0.6251392960548401,
|
14 |
"learning_rate": 5e-05,
|
15 |
-
"loss": 2.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.8,
|
20 |
-
"grad_norm": 0.6590011715888977,
|
21 |
"learning_rate": 5e-05,
|
22 |
-
"loss":
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.0,
|
27 |
-
"eval_accuracy": 0.
|
28 |
-
"eval_loss":
|
29 |
-
"eval_runtime":
|
30 |
-
"eval_samples_per_second":
|
31 |
-
"eval_steps_per_second":
|
32 |
"step": 250
|
33 |
},
|
34 |
{
|
35 |
"epoch": 1.0,
|
36 |
-
"eval_exact_match":
|
37 |
-
"eval_f1":
|
38 |
"step": 250
|
39 |
}
|
40 |
],
|
41 |
"logging_steps": 100,
|
42 |
"max_steps": 12500,
|
43 |
-
"num_input_tokens_seen": 0,
|
44 |
"num_train_epochs": 50,
|
45 |
"save_steps": 500,
|
46 |
-
"
|
47 |
-
"TrainerControl": {
|
48 |
-
"args": {
|
49 |
-
"should_epoch_stop": false,
|
50 |
-
"should_evaluate": false,
|
51 |
-
"should_log": false,
|
52 |
-
"should_save": true,
|
53 |
-
"should_training_stop": false
|
54 |
-
},
|
55 |
-
"attributes": {}
|
56 |
-
}
|
57 |
-
},
|
58 |
-
"total_flos": 6467693003669504.0,
|
59 |
-
"train_batch_size": 1,
|
60 |
"trial_name": null,
|
61 |
"trial_params": null
|
62 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.4,
|
|
|
13 |
"learning_rate": 5e-05,
|
14 |
+
"loss": 2.1914,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.8,
|
|
|
19 |
"learning_rate": 5e-05,
|
20 |
+
"loss": 1.798,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.0,
|
25 |
+
"eval_accuracy": 0.6067341772151899,
|
26 |
+
"eval_loss": 1.8213441371917725,
|
27 |
+
"eval_runtime": 4.8116,
|
28 |
+
"eval_samples_per_second": 103.916,
|
29 |
+
"eval_steps_per_second": 13.093,
|
30 |
"step": 250
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.0,
|
34 |
+
"eval_exact_match": 25.4,
|
35 |
+
"eval_f1": 35.50992875545509,
|
36 |
"step": 250
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 100,
|
40 |
"max_steps": 12500,
|
|
|
41 |
"num_train_epochs": 50,
|
42 |
"save_steps": 500,
|
43 |
+
"total_flos": 1.5945416663105536e+16,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|
checkpoint-250/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddd08619aa8955df0f518864a252643438869f6968a9f390d3026fbeb48e7ddf
|
3 |
+
size 4728
|