Training in progress, epoch 2, checkpoint
Browse files- checkpoint-1058/adapter_config.json +1 -1
- checkpoint-1058/adapter_model.bin +3 -0
- checkpoint-1058/added_tokens.json +3 -3
- checkpoint-1058/optimizer.pt +2 -2
- checkpoint-1058/rng_state_0.pth +1 -1
- checkpoint-1058/rng_state_1.pth +1 -1
- checkpoint-1058/rng_state_2.pth +1 -1
- checkpoint-1058/rng_state_3.pth +1 -1
- checkpoint-1058/special_tokens_map.json +4 -12
- checkpoint-1058/tokenizer.json +0 -0
- checkpoint-1058/tokenizer.model +3 -0
- checkpoint-1058/tokenizer_config.json +17 -20
- checkpoint-1058/trainer_state.json +43 -67
- checkpoint-1058/training_args.bin +2 -2
checkpoint-1058/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-1058/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9040eaee490ead8d0e4f9d3f4ece86ed129701fac838801a0af3827a0c527fb2
|
3 |
+
size 143269386
|
checkpoint-1058/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-1058/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 sha256:3b7b477e5c7f757d0e6b1984b9fc86ed3f4ead1c929dcc3ead0d233a8fe10556
|
3 |
+
size 286585234
|
checkpoint-1058/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 sha256:458578bae1caaf681c519d44436dce37641b4ace554a352f58d44b0f6f91061a
|
3 |
size 15024
|
checkpoint-1058/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 sha256:9ea41cbbe4faba103f6f538edf76399f71895b7a53fab3b6a6e3905c43c9cf86
|
3 |
size 15024
|
checkpoint-1058/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:ea2413e20b441903a2f637b49d56be3328c5f96413b24ee65725cc56ecc076d1
|
3 |
size 15024
|
checkpoint-1058/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:a401ee1ef5def2068c6885aebcc57621d12f2e4781418c7dba7af0da5f90189b
|
3 |
size 15024
|
checkpoint-1058/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-1058/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1058/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-1058/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-1058/trainer_state.json
CHANGED
@@ -9,133 +9,109 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 7.269421577453613,
|
14 |
"learning_rate": 0.0005,
|
15 |
-
"loss": 1.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm": 1.071650505065918,
|
21 |
"learning_rate": 0.0005,
|
22 |
-
"loss": 1.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.5662499070167542,
|
28 |
"learning_rate": 0.0005,
|
29 |
-
"loss":
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 0.47088223695755005,
|
35 |
"learning_rate": 0.0005,
|
36 |
-
"loss": 1.
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm": 0.3653932511806488,
|
42 |
"learning_rate": 0.0005,
|
43 |
-
"loss": 1.
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second":
|
53 |
"step": 529
|
54 |
},
|
55 |
{
|
56 |
"epoch": 1.0,
|
57 |
-
"eval_exact_match":
|
58 |
-
"eval_f1":
|
59 |
-
"eval_qa_bleu":
|
60 |
-
"eval_qa_exact_match": 0.
|
61 |
-
"eval_recite_bleu":
|
62 |
-
"eval_recite_exact_match": 0.
|
63 |
"step": 529
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 1.
|
67 |
-
"grad_norm": 0.5318541526794434,
|
68 |
"learning_rate": 0.0005,
|
69 |
-
"loss": 1.
|
70 |
"step": 600
|
71 |
},
|
72 |
{
|
73 |
-
"epoch": 1.
|
74 |
-
"grad_norm": 235.6529998779297,
|
75 |
"learning_rate": 0.0005,
|
76 |
-
"loss":
|
77 |
"step": 700
|
78 |
},
|
79 |
{
|
80 |
-
"epoch": 1.
|
81 |
-
"grad_norm": 0.5057249069213867,
|
82 |
"learning_rate": 0.0005,
|
83 |
-
"loss":
|
84 |
"step": 800
|
85 |
},
|
86 |
{
|
87 |
-
"epoch": 1.
|
88 |
-
"grad_norm": 0.5339187383651733,
|
89 |
"learning_rate": 0.0005,
|
90 |
-
"loss":
|
91 |
"step": 900
|
92 |
},
|
93 |
{
|
94 |
-
"epoch": 1.
|
95 |
-
"grad_norm": 0.5649825930595398,
|
96 |
"learning_rate": 0.0005,
|
97 |
-
"loss":
|
98 |
"step": 1000
|
99 |
},
|
100 |
{
|
101 |
"epoch": 2.0,
|
102 |
-
"eval_accuracy": 0.
|
103 |
-
"eval_loss":
|
104 |
-
"eval_runtime":
|
105 |
-
"eval_samples_per_second":
|
106 |
-
"eval_steps_per_second":
|
107 |
"step": 1058
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.0,
|
111 |
-
"eval_exact_match":
|
112 |
-
"eval_f1":
|
113 |
-
"eval_qa_bleu":
|
114 |
-
"eval_qa_exact_match": 0.
|
115 |
-
"eval_recite_bleu":
|
116 |
-
"eval_recite_exact_match": 0.
|
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 |
-
"
|
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 |
}
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.19,
|
|
|
13 |
"learning_rate": 0.0005,
|
14 |
+
"loss": 1.3631,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.38,
|
|
|
19 |
"learning_rate": 0.0005,
|
20 |
+
"loss": 1.294,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.57,
|
|
|
25 |
"learning_rate": 0.0005,
|
26 |
+
"loss": 1.302,
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 0.76,
|
|
|
31 |
"learning_rate": 0.0005,
|
32 |
+
"loss": 1.2626,
|
33 |
"step": 400
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 0.95,
|
|
|
37 |
"learning_rate": 0.0005,
|
38 |
+
"loss": 1.2156,
|
39 |
"step": 500
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.0,
|
43 |
+
"eval_accuracy": 0.6911294117647059,
|
44 |
+
"eval_loss": 1.012805700302124,
|
45 |
+
"eval_runtime": 7.0918,
|
46 |
+
"eval_samples_per_second": 70.504,
|
47 |
+
"eval_steps_per_second": 8.883,
|
48 |
"step": 529
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.0,
|
52 |
+
"eval_exact_match": 27.6,
|
53 |
+
"eval_f1": 35.68145743145743,
|
54 |
+
"eval_qa_bleu": 19.064111689202868,
|
55 |
+
"eval_qa_exact_match": 0.216,
|
56 |
+
"eval_recite_bleu": 17.898525975872754,
|
57 |
+
"eval_recite_exact_match": 0.006,
|
58 |
"step": 529
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 1.13,
|
|
|
62 |
"learning_rate": 0.0005,
|
63 |
+
"loss": 1.0305,
|
64 |
"step": 600
|
65 |
},
|
66 |
{
|
67 |
+
"epoch": 1.32,
|
|
|
68 |
"learning_rate": 0.0005,
|
69 |
+
"loss": 0.9199,
|
70 |
"step": 700
|
71 |
},
|
72 |
{
|
73 |
+
"epoch": 1.51,
|
|
|
74 |
"learning_rate": 0.0005,
|
75 |
+
"loss": 0.9086,
|
76 |
"step": 800
|
77 |
},
|
78 |
{
|
79 |
+
"epoch": 1.7,
|
|
|
80 |
"learning_rate": 0.0005,
|
81 |
+
"loss": 2.9245,
|
82 |
"step": 900
|
83 |
},
|
84 |
{
|
85 |
+
"epoch": 1.89,
|
|
|
86 |
"learning_rate": 0.0005,
|
87 |
+
"loss": 4.9199,
|
88 |
"step": 1000
|
89 |
},
|
90 |
{
|
91 |
"epoch": 2.0,
|
92 |
+
"eval_accuracy": 0.22922352941176471,
|
93 |
+
"eval_loss": 7.1224870681762695,
|
94 |
+
"eval_runtime": 7.7159,
|
95 |
+
"eval_samples_per_second": 64.801,
|
96 |
+
"eval_steps_per_second": 8.165,
|
97 |
"step": 1058
|
98 |
},
|
99 |
{
|
100 |
"epoch": 2.0,
|
101 |
+
"eval_exact_match": 0.0,
|
102 |
+
"eval_f1": 0.0,
|
103 |
+
"eval_qa_bleu": 0.0,
|
104 |
+
"eval_qa_exact_match": 0.0,
|
105 |
+
"eval_recite_bleu": 0.0,
|
106 |
+
"eval_recite_exact_match": 0.0,
|
107 |
"step": 1058
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 100,
|
111 |
"max_steps": 26450,
|
|
|
112 |
"num_train_epochs": 50,
|
113 |
"save_steps": 500,
|
114 |
+
"total_flos": 2.2443222219358208e+17,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
"trial_name": null,
|
116 |
"trial_params": null
|
117 |
}
|
checkpoint-1058/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:b01f751e6b30f6919dad64453b51b9e04d3c36ac30d2f54e574df56cf37b82bc
|
3 |
+
size 4728
|