imvladikon
commited on
Commit
•
9892458
1
Parent(s):
39c7b4a
init
Browse files- config.json +2 -0
- generation_config.json +2 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +2 -2
- trainer_state.json +1280 -92
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"MT5ForConditionalGeneration"
|
4 |
],
|
@@ -24,6 +25,7 @@
|
|
24 |
"tie_word_embeddings": false,
|
25 |
"tokenizer_class": "T5Tokenizer",
|
26 |
"torch_dtype": "float32",
|
|
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 250112
|
29 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/experiments/small_chat/checkpoint-7000",
|
3 |
"architectures": [
|
4 |
"MT5ForConditionalGeneration"
|
5 |
],
|
|
|
25 |
"tie_word_embeddings": false,
|
26 |
"tokenizer_class": "T5Tokenizer",
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 250112
|
31 |
}
|
generation_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
-
"pad_token_id": 0
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
}
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2401527173
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c36f8845e073c322766b2e7834f60244c84825f9b965543c6e9e656c9a24c08c
|
3 |
size 2401527173
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1200772485
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2e728b3baae1db5691071fda9e0b582c0d5f9728c1b33fe26dc0d80ac1f12f
|
3 |
size 1200772485
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32ae2e65042dca64c7579727c05d8d0b8cf81eeb12a87aaf0064500711126419
|
3 |
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9d8cd17f91a1d4c5a81afb5aac665e3193b7ad7dc12dbe4c8ddc2798a2f42ec
|
3 |
size 627
|
tokenizer.json
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:b750506e8d37d847db67c0541ebbedbfd426381d112543c653afbb85f65e51e4
|
3 |
+
size 16315219
|
trainer_state.json
CHANGED
@@ -1,149 +1,1337 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0.
|
12 |
-
"learning_rate": 4.
|
13 |
-
"loss": 2.
|
14 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.14,
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"eval_rouge1": 12.1725,
|
21 |
-
"eval_rouge2": 2.4216,
|
22 |
-
"eval_rougeL": 12.077,
|
23 |
-
"eval_rougeLsum": 12.1411,
|
24 |
-
"eval_runtime": 1560.686,
|
25 |
-
"eval_samples_per_second": 8.565,
|
26 |
-
"eval_steps_per_second": 2.141,
|
27 |
"step": 10000
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 0.
|
31 |
-
"learning_rate": 4.
|
32 |
-
"loss": 2.
|
33 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.28,
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"eval_rouge1": 12.7586,
|
40 |
-
"eval_rouge2": 2.6851,
|
41 |
-
"eval_rougeL": 12.6518,
|
42 |
-
"eval_rougeLsum": 12.733,
|
43 |
-
"eval_runtime": 1548.5251,
|
44 |
-
"eval_samples_per_second": 8.633,
|
45 |
-
"eval_steps_per_second": 2.158,
|
46 |
"step": 20000
|
47 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
{
|
49 |
"epoch": 0.42,
|
50 |
-
"learning_rate": 4.
|
51 |
-
"loss": 2.
|
52 |
"step": 30000
|
53 |
},
|
54 |
{
|
55 |
"epoch": 0.42,
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
|
60 |
-
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.56,
|
69 |
-
"learning_rate": 4.
|
70 |
-
"loss": 2.
|
71 |
"step": 40000
|
72 |
},
|
73 |
{
|
74 |
"epoch": 0.56,
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
|
79 |
-
|
80 |
-
"
|
81 |
-
"
|
82 |
-
"
|
83 |
-
"
|
84 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
},
|
86 |
{
|
87 |
"epoch": 0.7,
|
88 |
-
"learning_rate":
|
89 |
-
"loss": 2.
|
90 |
"step": 50000
|
91 |
},
|
92 |
{
|
93 |
"epoch": 0.7,
|
94 |
-
"
|
95 |
-
"
|
96 |
-
"
|
97 |
-
|
98 |
-
|
99 |
-
"
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"
|
103 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
},
|
105 |
{
|
106 |
"epoch": 0.84,
|
107 |
-
"learning_rate":
|
108 |
-
"loss": 2.
|
109 |
"step": 60000
|
110 |
},
|
111 |
{
|
112 |
"epoch": 0.84,
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
|
117 |
-
|
118 |
-
"
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.98,
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 2.
|
128 |
"step": 70000
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.98,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
"eval_gen_len": 19.0,
|
133 |
-
"eval_loss": 2.
|
134 |
-
"eval_rouge1": 13.
|
135 |
-
"eval_rouge2":
|
136 |
-
"eval_rougeL": 13.
|
137 |
-
"eval_rougeLsum": 13.
|
138 |
-
"eval_runtime":
|
139 |
-
"eval_samples_per_second": 8.
|
140 |
-
"eval_steps_per_second": 2.
|
141 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
}
|
143 |
],
|
144 |
-
"max_steps":
|
145 |
-
"num_train_epochs":
|
146 |
-
"total_flos":
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.518549993730757,
|
5 |
+
"global_step": 109000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 4.993034174340685e-05,
|
13 |
+
"loss": 2.3834,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.986068348681369e-05,
|
19 |
+
"loss": 2.3564,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 4.979102523022054e-05,
|
25 |
+
"loss": 2.3619,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.03,
|
30 |
+
"learning_rate": 4.972136697362739e-05,
|
31 |
+
"loss": 2.3887,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.03,
|
36 |
+
"learning_rate": 4.965170871703423e-05,
|
37 |
+
"loss": 2.3675,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.04,
|
42 |
+
"learning_rate": 4.958205046044108e-05,
|
43 |
+
"loss": 2.3616,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.05,
|
48 |
+
"learning_rate": 4.951239220384793e-05,
|
49 |
+
"loss": 2.3612,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.06,
|
54 |
+
"learning_rate": 4.944273394725477e-05,
|
55 |
+
"loss": 2.3387,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.06,
|
60 |
+
"learning_rate": 4.937307569066162e-05,
|
61 |
+
"loss": 2.3691,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.07,
|
66 |
+
"learning_rate": 4.9303417434068464e-05,
|
67 |
+
"loss": 2.3528,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.08,
|
72 |
+
"learning_rate": 4.923375917747531e-05,
|
73 |
+
"loss": 2.3344,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.08,
|
78 |
+
"learning_rate": 4.916410092088216e-05,
|
79 |
+
"loss": 2.3454,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.09,
|
84 |
+
"learning_rate": 4.9094442664289e-05,
|
85 |
+
"loss": 2.3597,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1,
|
90 |
+
"learning_rate": 4.9024784407695844e-05,
|
91 |
+
"loss": 2.3215,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.1,
|
96 |
+
"learning_rate": 4.8955126151102695e-05,
|
97 |
+
"loss": 2.3358,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.11,
|
102 |
+
"learning_rate": 4.888546789450954e-05,
|
103 |
+
"loss": 2.3134,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.12,
|
108 |
+
"learning_rate": 4.881580963791638e-05,
|
109 |
+
"loss": 2.3409,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.13,
|
114 |
+
"learning_rate": 4.874615138132323e-05,
|
115 |
+
"loss": 2.3431,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.13,
|
120 |
+
"learning_rate": 4.8676493124730075e-05,
|
121 |
+
"loss": 2.3337,
|
122 |
+
"step": 9500
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.14,
|
126 |
+
"learning_rate": 4.8606834868136925e-05,
|
127 |
+
"loss": 2.3242,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
"step": 10000
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.15,
|
132 |
+
"learning_rate": 4.853717661154377e-05,
|
133 |
+
"loss": 2.3335,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.15,
|
138 |
+
"learning_rate": 4.846751835495061e-05,
|
139 |
+
"loss": 2.3331,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.16,
|
144 |
+
"learning_rate": 4.839786009835746e-05,
|
145 |
+
"loss": 2.3122,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.17,
|
150 |
+
"learning_rate": 4.8328201841764306e-05,
|
151 |
+
"loss": 2.3356,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.17,
|
156 |
+
"learning_rate": 4.825854358517115e-05,
|
157 |
+
"loss": 2.3029,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.18,
|
162 |
+
"learning_rate": 4.8188885328578e-05,
|
163 |
+
"loss": 2.2891,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.19,
|
168 |
+
"learning_rate": 4.811922707198484e-05,
|
169 |
+
"loss": 2.3112,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2,
|
174 |
+
"learning_rate": 4.804956881539169e-05,
|
175 |
+
"loss": 2.3219,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.2,
|
180 |
+
"learning_rate": 4.797991055879854e-05,
|
181 |
+
"loss": 2.3077,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.21,
|
186 |
+
"learning_rate": 4.791025230220538e-05,
|
187 |
+
"loss": 2.3153,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.22,
|
192 |
+
"learning_rate": 4.784059404561223e-05,
|
193 |
+
"loss": 2.2975,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.22,
|
198 |
+
"learning_rate": 4.7770935789019074e-05,
|
199 |
+
"loss": 2.3129,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.23,
|
204 |
+
"learning_rate": 4.770127753242592e-05,
|
205 |
+
"loss": 2.3149,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.24,
|
210 |
+
"learning_rate": 4.763161927583277e-05,
|
211 |
+
"loss": 2.3233,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.24,
|
216 |
+
"learning_rate": 4.756196101923962e-05,
|
217 |
+
"loss": 2.2995,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.25,
|
222 |
+
"learning_rate": 4.7492302762646454e-05,
|
223 |
+
"loss": 2.3327,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.26,
|
228 |
+
"learning_rate": 4.7422644506053305e-05,
|
229 |
+
"loss": 2.2787,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.26,
|
234 |
+
"learning_rate": 4.7352986249460155e-05,
|
235 |
+
"loss": 2.2952,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.27,
|
240 |
+
"learning_rate": 4.7283327992867e-05,
|
241 |
+
"loss": 2.2961,
|
242 |
+
"step": 19500
|
243 |
},
|
244 |
{
|
245 |
"epoch": 0.28,
|
246 |
+
"learning_rate": 4.721366973627384e-05,
|
247 |
+
"loss": 2.2844,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
"step": 20000
|
249 |
},
|
250 |
+
{
|
251 |
+
"epoch": 0.29,
|
252 |
+
"learning_rate": 4.714401147968069e-05,
|
253 |
+
"loss": 2.3003,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.29,
|
258 |
+
"learning_rate": 4.7074353223087535e-05,
|
259 |
+
"loss": 2.2918,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.3,
|
264 |
+
"learning_rate": 4.700469496649438e-05,
|
265 |
+
"loss": 2.2911,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.31,
|
270 |
+
"learning_rate": 4.693503670990122e-05,
|
271 |
+
"loss": 2.3298,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.31,
|
276 |
+
"learning_rate": 4.686537845330807e-05,
|
277 |
+
"loss": 2.288,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.32,
|
282 |
+
"learning_rate": 4.679572019671492e-05,
|
283 |
+
"loss": 2.3024,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.33,
|
288 |
+
"learning_rate": 4.672606194012176e-05,
|
289 |
+
"loss": 2.3144,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.33,
|
294 |
+
"learning_rate": 4.665640368352861e-05,
|
295 |
+
"loss": 2.2914,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.34,
|
300 |
+
"learning_rate": 4.658674542693546e-05,
|
301 |
+
"loss": 2.3032,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.35,
|
306 |
+
"learning_rate": 4.65170871703423e-05,
|
307 |
+
"loss": 2.285,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.36,
|
312 |
+
"learning_rate": 4.644742891374915e-05,
|
313 |
+
"loss": 2.3003,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.36,
|
318 |
+
"learning_rate": 4.6377770657156e-05,
|
319 |
+
"loss": 2.3186,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.37,
|
324 |
+
"learning_rate": 4.630811240056284e-05,
|
325 |
+
"loss": 2.3173,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.38,
|
330 |
+
"learning_rate": 4.623845414396969e-05,
|
331 |
+
"loss": 2.2682,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.38,
|
336 |
+
"learning_rate": 4.6168795887376534e-05,
|
337 |
+
"loss": 2.2887,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.39,
|
342 |
+
"learning_rate": 4.609913763078338e-05,
|
343 |
+
"loss": 2.3012,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.4,
|
348 |
+
"learning_rate": 4.602947937419023e-05,
|
349 |
+
"loss": 2.2775,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.4,
|
354 |
+
"learning_rate": 4.595982111759707e-05,
|
355 |
+
"loss": 2.2973,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.41,
|
360 |
+
"learning_rate": 4.5890162861003915e-05,
|
361 |
+
"loss": 2.2992,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
{
|
365 |
"epoch": 0.42,
|
366 |
+
"learning_rate": 4.5820504604410765e-05,
|
367 |
+
"loss": 2.2588,
|
368 |
"step": 30000
|
369 |
},
|
370 |
{
|
371 |
"epoch": 0.42,
|
372 |
+
"learning_rate": 4.575084634781761e-05,
|
373 |
+
"loss": 2.2797,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.43,
|
378 |
+
"learning_rate": 4.568118809122445e-05,
|
379 |
+
"loss": 2.2706,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.44,
|
384 |
+
"learning_rate": 4.56115298346313e-05,
|
385 |
+
"loss": 2.3081,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.45,
|
390 |
+
"learning_rate": 4.5541871578038145e-05,
|
391 |
+
"loss": 2.2698,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.45,
|
396 |
+
"learning_rate": 4.5472213321444996e-05,
|
397 |
+
"loss": 2.2789,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.46,
|
402 |
+
"learning_rate": 4.540255506485184e-05,
|
403 |
+
"loss": 2.3017,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.47,
|
408 |
+
"learning_rate": 4.533289680825868e-05,
|
409 |
+
"loss": 2.2938,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.47,
|
414 |
+
"learning_rate": 4.526323855166553e-05,
|
415 |
+
"loss": 2.3085,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.48,
|
420 |
+
"learning_rate": 4.519358029507238e-05,
|
421 |
+
"loss": 2.3055,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.49,
|
426 |
+
"learning_rate": 4.512392203847922e-05,
|
427 |
+
"loss": 2.2903,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.49,
|
432 |
+
"learning_rate": 4.505426378188607e-05,
|
433 |
+
"loss": 2.2923,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.5,
|
438 |
+
"learning_rate": 4.498460552529291e-05,
|
439 |
+
"loss": 2.2878,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.51,
|
444 |
+
"learning_rate": 4.491494726869976e-05,
|
445 |
+
"loss": 2.2875,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.52,
|
450 |
+
"learning_rate": 4.484528901210661e-05,
|
451 |
+
"loss": 2.2575,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.52,
|
456 |
+
"learning_rate": 4.477563075551345e-05,
|
457 |
+
"loss": 2.3053,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.53,
|
462 |
+
"learning_rate": 4.47059724989203e-05,
|
463 |
+
"loss": 2.2795,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.54,
|
468 |
+
"learning_rate": 4.4636314242327144e-05,
|
469 |
+
"loss": 2.2766,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.54,
|
474 |
+
"learning_rate": 4.456665598573399e-05,
|
475 |
+
"loss": 2.2476,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.55,
|
480 |
+
"learning_rate": 4.449699772914084e-05,
|
481 |
+
"loss": 2.3061,
|
482 |
+
"step": 39500
|
483 |
},
|
484 |
{
|
485 |
"epoch": 0.56,
|
486 |
+
"learning_rate": 4.442733947254769e-05,
|
487 |
+
"loss": 2.2821,
|
488 |
"step": 40000
|
489 |
},
|
490 |
{
|
491 |
"epoch": 0.56,
|
492 |
+
"learning_rate": 4.4357681215954525e-05,
|
493 |
+
"loss": 2.282,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.57,
|
498 |
+
"learning_rate": 4.4288022959361375e-05,
|
499 |
+
"loss": 2.276,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.58,
|
504 |
+
"learning_rate": 4.4218364702768225e-05,
|
505 |
+
"loss": 2.2973,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.59,
|
510 |
+
"learning_rate": 4.414870644617507e-05,
|
511 |
+
"loss": 2.2998,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.59,
|
516 |
+
"learning_rate": 4.407904818958191e-05,
|
517 |
+
"loss": 2.271,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.6,
|
522 |
+
"learning_rate": 4.400938993298876e-05,
|
523 |
+
"loss": 2.268,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.61,
|
528 |
+
"learning_rate": 4.3939731676395606e-05,
|
529 |
+
"loss": 2.2975,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.61,
|
534 |
+
"learning_rate": 4.387007341980245e-05,
|
535 |
+
"loss": 2.2643,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.62,
|
540 |
+
"learning_rate": 4.38004151632093e-05,
|
541 |
+
"loss": 2.3335,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.63,
|
546 |
+
"learning_rate": 4.373075690661614e-05,
|
547 |
+
"loss": 2.3195,
|
548 |
+
"step": 45000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.63,
|
552 |
+
"learning_rate": 4.366109865002299e-05,
|
553 |
+
"loss": 2.3385,
|
554 |
+
"step": 45500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.64,
|
558 |
+
"learning_rate": 4.3591440393429836e-05,
|
559 |
+
"loss": 2.3292,
|
560 |
+
"step": 46000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.65,
|
564 |
+
"learning_rate": 4.352178213683668e-05,
|
565 |
+
"loss": 2.329,
|
566 |
+
"step": 46500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.65,
|
570 |
+
"learning_rate": 4.345212388024353e-05,
|
571 |
+
"loss": 2.331,
|
572 |
+
"step": 47000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.66,
|
576 |
+
"learning_rate": 4.3382465623650374e-05,
|
577 |
+
"loss": 2.3483,
|
578 |
+
"step": 47500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.67,
|
582 |
+
"learning_rate": 4.331280736705722e-05,
|
583 |
+
"loss": 2.3124,
|
584 |
+
"step": 48000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.68,
|
588 |
+
"learning_rate": 4.324314911046407e-05,
|
589 |
+
"loss": 2.3102,
|
590 |
+
"step": 48500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.68,
|
594 |
+
"learning_rate": 4.317349085387091e-05,
|
595 |
+
"loss": 2.3151,
|
596 |
+
"step": 49000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.69,
|
600 |
+
"learning_rate": 4.310383259727776e-05,
|
601 |
+
"loss": 2.323,
|
602 |
+
"step": 49500
|
603 |
},
|
604 |
{
|
605 |
"epoch": 0.7,
|
606 |
+
"learning_rate": 4.3034174340684604e-05,
|
607 |
+
"loss": 2.3174,
|
608 |
"step": 50000
|
609 |
},
|
610 |
{
|
611 |
"epoch": 0.7,
|
612 |
+
"learning_rate": 4.296451608409145e-05,
|
613 |
+
"loss": 2.3188,
|
614 |
+
"step": 50500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.71,
|
618 |
+
"learning_rate": 4.28948578274983e-05,
|
619 |
+
"loss": 2.3054,
|
620 |
+
"step": 51000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.72,
|
624 |
+
"learning_rate": 4.282519957090514e-05,
|
625 |
+
"loss": 2.3133,
|
626 |
+
"step": 51500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.72,
|
630 |
+
"learning_rate": 4.2755541314311985e-05,
|
631 |
+
"loss": 2.3224,
|
632 |
+
"step": 52000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.73,
|
636 |
+
"learning_rate": 4.2685883057718835e-05,
|
637 |
+
"loss": 2.3354,
|
638 |
+
"step": 52500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.74,
|
642 |
+
"learning_rate": 4.261622480112568e-05,
|
643 |
+
"loss": 2.3386,
|
644 |
+
"step": 53000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.75,
|
648 |
+
"learning_rate": 4.254656654453252e-05,
|
649 |
+
"loss": 2.3276,
|
650 |
+
"step": 53500
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.75,
|
654 |
+
"learning_rate": 4.247690828793937e-05,
|
655 |
+
"loss": 2.3057,
|
656 |
+
"step": 54000
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.76,
|
660 |
+
"learning_rate": 4.2407250031346216e-05,
|
661 |
+
"loss": 2.2921,
|
662 |
+
"step": 54500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.77,
|
666 |
+
"learning_rate": 4.2337591774753066e-05,
|
667 |
+
"loss": 2.3185,
|
668 |
+
"step": 55000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.77,
|
672 |
+
"learning_rate": 4.226793351815991e-05,
|
673 |
+
"loss": 2.3046,
|
674 |
+
"step": 55500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.78,
|
678 |
+
"learning_rate": 4.219827526156675e-05,
|
679 |
+
"loss": 2.3018,
|
680 |
+
"step": 56000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.79,
|
684 |
+
"learning_rate": 4.21286170049736e-05,
|
685 |
+
"loss": 2.2825,
|
686 |
+
"step": 56500
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.79,
|
690 |
+
"learning_rate": 4.2058958748380446e-05,
|
691 |
+
"loss": 2.3068,
|
692 |
+
"step": 57000
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.8,
|
696 |
+
"learning_rate": 4.198930049178729e-05,
|
697 |
+
"loss": 2.3115,
|
698 |
+
"step": 57500
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.81,
|
702 |
+
"learning_rate": 4.191964223519414e-05,
|
703 |
+
"loss": 2.3247,
|
704 |
+
"step": 58000
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.82,
|
708 |
+
"learning_rate": 4.184998397860099e-05,
|
709 |
+
"loss": 2.2919,
|
710 |
+
"step": 58500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.82,
|
714 |
+
"learning_rate": 4.178032572200783e-05,
|
715 |
+
"loss": 2.345,
|
716 |
+
"step": 59000
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.83,
|
720 |
+
"learning_rate": 4.171066746541468e-05,
|
721 |
+
"loss": 2.298,
|
722 |
+
"step": 59500
|
723 |
},
|
724 |
{
|
725 |
"epoch": 0.84,
|
726 |
+
"learning_rate": 4.164100920882153e-05,
|
727 |
+
"loss": 2.3093,
|
728 |
"step": 60000
|
729 |
},
|
730 |
{
|
731 |
"epoch": 0.84,
|
732 |
+
"learning_rate": 4.157135095222837e-05,
|
733 |
+
"loss": 2.3259,
|
734 |
+
"step": 60500
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.85,
|
738 |
+
"learning_rate": 4.1501692695635214e-05,
|
739 |
+
"loss": 2.3174,
|
740 |
+
"step": 61000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.86,
|
744 |
+
"learning_rate": 4.1432034439042064e-05,
|
745 |
+
"loss": 2.3268,
|
746 |
+
"step": 61500
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.86,
|
750 |
+
"learning_rate": 4.136237618244891e-05,
|
751 |
+
"loss": 2.2997,
|
752 |
+
"step": 62000
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.87,
|
756 |
+
"learning_rate": 4.129271792585576e-05,
|
757 |
+
"loss": 2.3239,
|
758 |
+
"step": 62500
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.88,
|
762 |
+
"learning_rate": 4.1223059669262595e-05,
|
763 |
+
"loss": 2.3302,
|
764 |
+
"step": 63000
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.88,
|
768 |
+
"learning_rate": 4.1153401412669445e-05,
|
769 |
+
"loss": 2.322,
|
770 |
+
"step": 63500
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.89,
|
774 |
+
"learning_rate": 4.1083743156076295e-05,
|
775 |
+
"loss": 2.3216,
|
776 |
+
"step": 64000
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.9,
|
780 |
+
"learning_rate": 4.101408489948313e-05,
|
781 |
+
"loss": 2.319,
|
782 |
+
"step": 64500
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.91,
|
786 |
+
"learning_rate": 4.094442664288998e-05,
|
787 |
+
"loss": 2.304,
|
788 |
+
"step": 65000
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.91,
|
792 |
+
"learning_rate": 4.087476838629683e-05,
|
793 |
+
"loss": 2.2772,
|
794 |
+
"step": 65500
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.92,
|
798 |
+
"learning_rate": 4.0805110129703676e-05,
|
799 |
+
"loss": 2.3205,
|
800 |
+
"step": 66000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.93,
|
804 |
+
"learning_rate": 4.073545187311052e-05,
|
805 |
+
"loss": 2.3053,
|
806 |
+
"step": 66500
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.93,
|
810 |
+
"learning_rate": 4.066579361651737e-05,
|
811 |
+
"loss": 2.3196,
|
812 |
+
"step": 67000
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.94,
|
816 |
+
"learning_rate": 4.059613535992421e-05,
|
817 |
+
"loss": 2.3245,
|
818 |
+
"step": 67500
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.95,
|
822 |
+
"learning_rate": 4.052647710333106e-05,
|
823 |
+
"loss": 2.2804,
|
824 |
+
"step": 68000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.95,
|
828 |
+
"learning_rate": 4.0456818846737907e-05,
|
829 |
+
"loss": 2.2981,
|
830 |
+
"step": 68500
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.96,
|
834 |
+
"learning_rate": 4.038716059014475e-05,
|
835 |
+
"loss": 2.307,
|
836 |
+
"step": 69000
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.97,
|
840 |
+
"learning_rate": 4.03175023335516e-05,
|
841 |
+
"loss": 2.3003,
|
842 |
+
"step": 69500
|
843 |
},
|
844 |
{
|
845 |
"epoch": 0.98,
|
846 |
+
"learning_rate": 4.0247844076958444e-05,
|
847 |
+
"loss": 2.2922,
|
848 |
"step": 70000
|
849 |
},
|
850 |
{
|
851 |
"epoch": 0.98,
|
852 |
+
"learning_rate": 4.017818582036529e-05,
|
853 |
+
"loss": 2.351,
|
854 |
+
"step": 70500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.99,
|
858 |
+
"learning_rate": 4.010852756377214e-05,
|
859 |
+
"loss": 2.3629,
|
860 |
+
"step": 71000
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 1.0,
|
864 |
+
"learning_rate": 4.003886930717898e-05,
|
865 |
+
"loss": 2.3658,
|
866 |
+
"step": 71500
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.0,
|
870 |
"eval_gen_len": 19.0,
|
871 |
+
"eval_loss": 2.0120694637298584,
|
872 |
+
"eval_rouge1": 13.694,
|
873 |
+
"eval_rouge2": 3.0324,
|
874 |
+
"eval_rougeL": 13.5592,
|
875 |
+
"eval_rougeLsum": 13.6473,
|
876 |
+
"eval_runtime": 1519.7773,
|
877 |
+
"eval_samples_per_second": 8.796,
|
878 |
+
"eval_steps_per_second": 2.199,
|
879 |
+
"step": 71779
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 1.0,
|
883 |
+
"learning_rate": 3.9969211050585824e-05,
|
884 |
+
"loss": 2.3626,
|
885 |
+
"step": 72000
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.01,
|
889 |
+
"learning_rate": 3.9899552793992674e-05,
|
890 |
+
"loss": 2.3326,
|
891 |
+
"step": 72500
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 1.02,
|
895 |
+
"learning_rate": 3.982989453739952e-05,
|
896 |
+
"loss": 2.33,
|
897 |
+
"step": 73000
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 1.02,
|
901 |
+
"learning_rate": 3.976023628080637e-05,
|
902 |
+
"loss": 2.3426,
|
903 |
+
"step": 73500
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 1.03,
|
907 |
+
"learning_rate": 3.969057802421321e-05,
|
908 |
+
"loss": 2.3469,
|
909 |
+
"step": 74000
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 1.04,
|
913 |
+
"learning_rate": 3.9620919767620055e-05,
|
914 |
+
"loss": 2.3075,
|
915 |
+
"step": 74500
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 1.04,
|
919 |
+
"learning_rate": 3.9551261511026905e-05,
|
920 |
+
"loss": 2.3124,
|
921 |
+
"step": 75000
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 1.05,
|
925 |
+
"learning_rate": 3.9481603254433755e-05,
|
926 |
+
"loss": 2.344,
|
927 |
+
"step": 75500
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.06,
|
931 |
+
"learning_rate": 3.941194499784059e-05,
|
932 |
+
"loss": 2.3329,
|
933 |
+
"step": 76000
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.07,
|
937 |
+
"learning_rate": 3.934228674124744e-05,
|
938 |
+
"loss": 2.3163,
|
939 |
+
"step": 76500
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.07,
|
943 |
+
"learning_rate": 3.9272628484654286e-05,
|
944 |
+
"loss": 2.3322,
|
945 |
+
"step": 77000
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 1.08,
|
949 |
+
"learning_rate": 3.9202970228061136e-05,
|
950 |
+
"loss": 2.3133,
|
951 |
+
"step": 77500
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 1.09,
|
955 |
+
"learning_rate": 3.913331197146798e-05,
|
956 |
+
"loss": 2.3388,
|
957 |
+
"step": 78000
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.09,
|
961 |
+
"learning_rate": 3.906365371487482e-05,
|
962 |
+
"loss": 2.289,
|
963 |
+
"step": 78500
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 1.1,
|
967 |
+
"learning_rate": 3.899399545828167e-05,
|
968 |
+
"loss": 2.2948,
|
969 |
+
"step": 79000
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.11,
|
973 |
+
"learning_rate": 3.8924337201688517e-05,
|
974 |
+
"loss": 2.3597,
|
975 |
+
"step": 79500
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 1.11,
|
979 |
+
"learning_rate": 3.885467894509536e-05,
|
980 |
+
"loss": 2.3136,
|
981 |
+
"step": 80000
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 1.12,
|
985 |
+
"learning_rate": 3.878502068850221e-05,
|
986 |
+
"loss": 2.3143,
|
987 |
+
"step": 80500
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 1.13,
|
991 |
+
"learning_rate": 3.871536243190906e-05,
|
992 |
+
"loss": 2.3085,
|
993 |
+
"step": 81000
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 1.14,
|
997 |
+
"learning_rate": 3.86457041753159e-05,
|
998 |
+
"loss": 2.3485,
|
999 |
+
"step": 81500
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 1.14,
|
1003 |
+
"learning_rate": 3.857604591872275e-05,
|
1004 |
+
"loss": 2.2972,
|
1005 |
+
"step": 82000
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 1.15,
|
1009 |
+
"learning_rate": 3.85063876621296e-05,
|
1010 |
+
"loss": 2.3323,
|
1011 |
+
"step": 82500
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 1.16,
|
1015 |
+
"learning_rate": 3.843672940553644e-05,
|
1016 |
+
"loss": 2.3263,
|
1017 |
+
"step": 83000
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.16,
|
1021 |
+
"learning_rate": 3.8367071148943284e-05,
|
1022 |
+
"loss": 2.2894,
|
1023 |
+
"step": 83500
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 1.17,
|
1027 |
+
"learning_rate": 3.8297412892350135e-05,
|
1028 |
+
"loss": 2.3156,
|
1029 |
+
"step": 84000
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.18,
|
1033 |
+
"learning_rate": 3.822775463575698e-05,
|
1034 |
+
"loss": 2.3401,
|
1035 |
+
"step": 84500
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 1.18,
|
1039 |
+
"learning_rate": 3.815809637916383e-05,
|
1040 |
+
"loss": 2.3034,
|
1041 |
+
"step": 85000
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 1.19,
|
1045 |
+
"learning_rate": 3.808843812257067e-05,
|
1046 |
+
"loss": 2.3141,
|
1047 |
+
"step": 85500
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 1.2,
|
1051 |
+
"learning_rate": 3.8018779865977515e-05,
|
1052 |
+
"loss": 2.3265,
|
1053 |
+
"step": 86000
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 1.21,
|
1057 |
+
"learning_rate": 3.7949121609384365e-05,
|
1058 |
+
"loss": 2.3211,
|
1059 |
+
"step": 86500
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.21,
|
1063 |
+
"learning_rate": 3.787946335279121e-05,
|
1064 |
+
"loss": 2.3137,
|
1065 |
+
"step": 87000
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 1.22,
|
1069 |
+
"learning_rate": 3.780980509619805e-05,
|
1070 |
+
"loss": 2.3216,
|
1071 |
+
"step": 87500
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 1.23,
|
1075 |
+
"learning_rate": 3.77401468396049e-05,
|
1076 |
+
"loss": 2.3043,
|
1077 |
+
"step": 88000
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 1.23,
|
1081 |
+
"learning_rate": 3.7670488583011746e-05,
|
1082 |
+
"loss": 2.3245,
|
1083 |
+
"step": 88500
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 1.24,
|
1087 |
+
"learning_rate": 3.760083032641859e-05,
|
1088 |
+
"loss": 2.3319,
|
1089 |
+
"step": 89000
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 1.25,
|
1093 |
+
"learning_rate": 3.753117206982544e-05,
|
1094 |
+
"loss": 2.3025,
|
1095 |
+
"step": 89500
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.25,
|
1099 |
+
"learning_rate": 3.746151381323228e-05,
|
1100 |
+
"loss": 2.2983,
|
1101 |
+
"step": 90000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.26,
|
1105 |
+
"learning_rate": 3.739185555663913e-05,
|
1106 |
+
"loss": 2.3107,
|
1107 |
+
"step": 90500
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 1.27,
|
1111 |
+
"learning_rate": 3.732219730004598e-05,
|
1112 |
+
"loss": 2.3137,
|
1113 |
+
"step": 91000
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 1.27,
|
1117 |
+
"learning_rate": 3.725253904345282e-05,
|
1118 |
+
"loss": 2.3006,
|
1119 |
+
"step": 91500
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.28,
|
1123 |
+
"learning_rate": 3.718288078685967e-05,
|
1124 |
+
"loss": 2.3058,
|
1125 |
+
"step": 92000
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 1.29,
|
1129 |
+
"learning_rate": 3.7113222530266514e-05,
|
1130 |
+
"loss": 2.3175,
|
1131 |
+
"step": 92500
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 1.3,
|
1135 |
+
"learning_rate": 3.704356427367336e-05,
|
1136 |
+
"loss": 2.2991,
|
1137 |
+
"step": 93000
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 1.3,
|
1141 |
+
"learning_rate": 3.697390601708021e-05,
|
1142 |
+
"loss": 2.302,
|
1143 |
+
"step": 93500
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.31,
|
1147 |
+
"learning_rate": 3.690424776048705e-05,
|
1148 |
+
"loss": 2.3089,
|
1149 |
+
"step": 94000
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 1.32,
|
1153 |
+
"learning_rate": 3.6834589503893894e-05,
|
1154 |
+
"loss": 2.2957,
|
1155 |
+
"step": 94500
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 1.32,
|
1159 |
+
"learning_rate": 3.6764931247300745e-05,
|
1160 |
+
"loss": 2.331,
|
1161 |
+
"step": 95000
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.33,
|
1165 |
+
"learning_rate": 3.669527299070759e-05,
|
1166 |
+
"loss": 2.3044,
|
1167 |
+
"step": 95500
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 1.34,
|
1171 |
+
"learning_rate": 3.662561473411444e-05,
|
1172 |
+
"loss": 2.2887,
|
1173 |
+
"step": 96000
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 1.34,
|
1177 |
+
"learning_rate": 3.655595647752128e-05,
|
1178 |
+
"loss": 2.2816,
|
1179 |
+
"step": 96500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.35,
|
1183 |
+
"learning_rate": 3.6486298220928125e-05,
|
1184 |
+
"loss": 2.3284,
|
1185 |
+
"step": 97000
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.36,
|
1189 |
+
"learning_rate": 3.6416639964334975e-05,
|
1190 |
+
"loss": 2.2985,
|
1191 |
+
"step": 97500
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.37,
|
1195 |
+
"learning_rate": 3.6346981707741826e-05,
|
1196 |
+
"loss": 2.3366,
|
1197 |
+
"step": 98000
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.37,
|
1201 |
+
"learning_rate": 3.627732345114866e-05,
|
1202 |
+
"loss": 2.3232,
|
1203 |
+
"step": 98500
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.38,
|
1207 |
+
"learning_rate": 3.620766519455551e-05,
|
1208 |
+
"loss": 2.2867,
|
1209 |
+
"step": 99000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.39,
|
1213 |
+
"learning_rate": 3.613800693796236e-05,
|
1214 |
+
"loss": 2.2818,
|
1215 |
+
"step": 99500
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.39,
|
1219 |
+
"learning_rate": 3.60683486813692e-05,
|
1220 |
+
"loss": 2.3103,
|
1221 |
+
"step": 100000
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.4,
|
1225 |
+
"learning_rate": 3.599869042477605e-05,
|
1226 |
+
"loss": 2.2815,
|
1227 |
+
"step": 100500
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.41,
|
1231 |
+
"learning_rate": 3.59290321681829e-05,
|
1232 |
+
"loss": 2.2924,
|
1233 |
+
"step": 101000
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.41,
|
1237 |
+
"learning_rate": 3.585937391158974e-05,
|
1238 |
+
"loss": 2.3227,
|
1239 |
+
"step": 101500
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.42,
|
1243 |
+
"learning_rate": 3.578971565499659e-05,
|
1244 |
+
"loss": 2.3177,
|
1245 |
+
"step": 102000
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.43,
|
1249 |
+
"learning_rate": 3.572005739840344e-05,
|
1250 |
+
"loss": 2.3085,
|
1251 |
+
"step": 102500
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.43,
|
1255 |
+
"learning_rate": 3.565039914181028e-05,
|
1256 |
+
"loss": 2.2983,
|
1257 |
+
"step": 103000
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 1.44,
|
1261 |
+
"learning_rate": 3.558074088521713e-05,
|
1262 |
+
"loss": 2.2718,
|
1263 |
+
"step": 103500
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.45,
|
1267 |
+
"learning_rate": 3.551108262862397e-05,
|
1268 |
+
"loss": 2.2958,
|
1269 |
+
"step": 104000
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.46,
|
1273 |
+
"learning_rate": 3.544142437203082e-05,
|
1274 |
+
"loss": 2.3368,
|
1275 |
+
"step": 104500
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 1.46,
|
1279 |
+
"learning_rate": 3.537176611543767e-05,
|
1280 |
+
"loss": 2.2821,
|
1281 |
+
"step": 105000
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.47,
|
1285 |
+
"learning_rate": 3.530210785884451e-05,
|
1286 |
+
"loss": 2.2903,
|
1287 |
+
"step": 105500
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.48,
|
1291 |
+
"learning_rate": 3.5232449602251355e-05,
|
1292 |
+
"loss": 2.2941,
|
1293 |
+
"step": 106000
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 1.48,
|
1297 |
+
"learning_rate": 3.5162791345658205e-05,
|
1298 |
+
"loss": 2.2957,
|
1299 |
+
"step": 106500
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.49,
|
1303 |
+
"learning_rate": 3.509313308906505e-05,
|
1304 |
+
"loss": 2.2894,
|
1305 |
+
"step": 107000
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.5,
|
1309 |
+
"learning_rate": 3.502347483247189e-05,
|
1310 |
+
"loss": 2.3138,
|
1311 |
+
"step": 107500
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.5,
|
1315 |
+
"learning_rate": 3.495381657587874e-05,
|
1316 |
+
"loss": 2.3015,
|
1317 |
+
"step": 108000
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 1.51,
|
1321 |
+
"learning_rate": 3.4884158319285585e-05,
|
1322 |
+
"loss": 2.315,
|
1323 |
+
"step": 108500
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.52,
|
1327 |
+
"learning_rate": 3.4814500062692436e-05,
|
1328 |
+
"loss": 2.2956,
|
1329 |
+
"step": 109000
|
1330 |
}
|
1331 |
],
|
1332 |
+
"max_steps": 358895,
|
1333 |
+
"num_train_epochs": 5,
|
1334 |
+
"total_flos": 2.305332748437504e+17,
|
1335 |
"trial_name": null,
|
1336 |
"trial_params": null
|
1337 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7ee933c8d4adc27cb0c3e1e0d0fce5e38fe0c4eea9cb47f843e43410605f744
|
3 |
size 4091
|