Initial commit
Browse files- config.json +29 -0
- flax_model.msgpack +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- runs/Apr26_16-15-42_pg-gpu18/1650983594.6341333/events.out.tfevents.1650983594.pg-gpu18.19305.1 +3 -0
- runs/Apr26_16-15-42_pg-gpu18/events.out.tfevents.1650983593.pg-gpu18.19305.0 +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1086 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": ".",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 6,
|
19 |
+
"num_heads": 8,
|
20 |
+
"num_layers": 32,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.15.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32100
|
29 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fd817881c9030374b434d176d811a072985b882c12867fe268036dddb581ae9
|
3 |
+
size 569246164
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76c0828f70d07473bd16d19ee612ad1721f04e1169498be7d24ac726d4f2ab55
|
3 |
+
size 1138662581
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86e599334580a042cd3c00573eef9d1bc821f2479a8a3ec889ac6c0d8b5cd906
|
3 |
+
size 569387035
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7742e7dde9ca1ab3cd9b902cf814f241fcce7a39a24281853cdf60775d868f6f
|
3 |
+
size 14503
|
runs/Apr26_16-15-42_pg-gpu18/1650983594.6341333/events.out.tfevents.1650983594.pg-gpu18.19305.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e6e8b9cee58a64f762daa5861e007dcc115225aec30c7024ff69aa142be411e
|
3 |
+
size 5133
|
runs/Apr26_16-15-42_pg-gpu18/events.out.tfevents.1650983593.pg-gpu18.19305.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f635592f6eb5d61af11b7b34881f093fa40d7c54895288fb16a732efce9a8945
|
3 |
+
size 35690
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:374a18984601ceaa197ac91e3793e0f053af79436628e1cb2546ccc04e9050dc
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dffd01fc009b7e92d98eddff8853983e271b41302ed0d363000e8581df12000
|
3 |
+
size 817200
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f6000bdb7632f62639357db3c51375c063309561818ac2da2dac246eabe2c19
|
3 |
+
size 569947488
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "stefan-it/it5-efficient-small-el32", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,1086 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8713160404573231,
|
5 |
+
"global_step": 74000,
|
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": 0.00029941127294563693,
|
13 |
+
"loss": 4.087,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 0.0002988225458912739,
|
19 |
+
"loss": 3.7168,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 0.0002982338188369108,
|
25 |
+
"loss": 3.5567,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 0.00029764509178254774,
|
31 |
+
"loss": 3.4939,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.03,
|
36 |
+
"learning_rate": 0.0002970563647281847,
|
37 |
+
"loss": 3.4094,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.04,
|
42 |
+
"learning_rate": 0.00029646763767382164,
|
43 |
+
"loss": 3.4297,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.04,
|
48 |
+
"learning_rate": 0.0002958789106194586,
|
49 |
+
"loss": 3.3537,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.05,
|
54 |
+
"learning_rate": 0.0002952901835650955,
|
55 |
+
"loss": 3.3117,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.05,
|
60 |
+
"learning_rate": 0.0002947014565107325,
|
61 |
+
"loss": 3.2607,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.06,
|
66 |
+
"learning_rate": 0.0002941127294563694,
|
67 |
+
"loss": 3.2741,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.06,
|
72 |
+
"eval_gen_len": 18.9343,
|
73 |
+
"eval_loss": 2.923264980316162,
|
74 |
+
"eval_rouge1": 21.2236,
|
75 |
+
"eval_rouge2": 9.7543,
|
76 |
+
"eval_rougeL": 19.1786,
|
77 |
+
"eval_rougeLsum": 19.782,
|
78 |
+
"eval_runtime": 554.7643,
|
79 |
+
"eval_samples_per_second": 18.026,
|
80 |
+
"eval_steps_per_second": 2.253,
|
81 |
+
"step": 5000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.06,
|
85 |
+
"learning_rate": 0.00029352400240200636,
|
86 |
+
"loss": 3.2403,
|
87 |
+
"step": 5500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.07,
|
91 |
+
"learning_rate": 0.0002929352753476433,
|
92 |
+
"loss": 3.2089,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.08,
|
97 |
+
"learning_rate": 0.0002923465482932802,
|
98 |
+
"loss": 3.1972,
|
99 |
+
"step": 6500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.08,
|
103 |
+
"learning_rate": 0.0002917578212389172,
|
104 |
+
"loss": 3.1384,
|
105 |
+
"step": 7000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.09,
|
109 |
+
"learning_rate": 0.0002911690941845541,
|
110 |
+
"loss": 3.1834,
|
111 |
+
"step": 7500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.09,
|
115 |
+
"learning_rate": 0.0002905803671301911,
|
116 |
+
"loss": 3.1484,
|
117 |
+
"step": 8000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.1,
|
121 |
+
"learning_rate": 0.00028999164007582803,
|
122 |
+
"loss": 3.1509,
|
123 |
+
"step": 8500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.11,
|
127 |
+
"learning_rate": 0.00028940291302146493,
|
128 |
+
"loss": 3.125,
|
129 |
+
"step": 9000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.11,
|
133 |
+
"learning_rate": 0.00028881418596710194,
|
134 |
+
"loss": 3.1113,
|
135 |
+
"step": 9500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.12,
|
139 |
+
"learning_rate": 0.00028822545891273884,
|
140 |
+
"loss": 3.1359,
|
141 |
+
"step": 10000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.12,
|
145 |
+
"eval_gen_len": 18.9427,
|
146 |
+
"eval_loss": 2.825679302215576,
|
147 |
+
"eval_rouge1": 23.1537,
|
148 |
+
"eval_rouge2": 11.6804,
|
149 |
+
"eval_rougeL": 21.2251,
|
150 |
+
"eval_rougeLsum": 21.8301,
|
151 |
+
"eval_runtime": 547.7371,
|
152 |
+
"eval_samples_per_second": 18.257,
|
153 |
+
"eval_steps_per_second": 2.282,
|
154 |
+
"step": 10000
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.12,
|
158 |
+
"learning_rate": 0.0002876367318583758,
|
159 |
+
"loss": 3.085,
|
160 |
+
"step": 10500
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.13,
|
164 |
+
"learning_rate": 0.00028704800480401274,
|
165 |
+
"loss": 3.0939,
|
166 |
+
"step": 11000
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.14,
|
170 |
+
"learning_rate": 0.0002864592777496497,
|
171 |
+
"loss": 3.0683,
|
172 |
+
"step": 11500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.14,
|
176 |
+
"learning_rate": 0.00028587055069528665,
|
177 |
+
"loss": 3.0748,
|
178 |
+
"step": 12000
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.15,
|
182 |
+
"learning_rate": 0.00028528182364092355,
|
183 |
+
"loss": 3.0484,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.15,
|
188 |
+
"learning_rate": 0.0002846930965865605,
|
189 |
+
"loss": 3.0441,
|
190 |
+
"step": 13000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.16,
|
194 |
+
"learning_rate": 0.00028410436953219746,
|
195 |
+
"loss": 3.0315,
|
196 |
+
"step": 13500
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.16,
|
200 |
+
"learning_rate": 0.0002835156424778344,
|
201 |
+
"loss": 3.0418,
|
202 |
+
"step": 14000
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.17,
|
206 |
+
"learning_rate": 0.00028292691542347137,
|
207 |
+
"loss": 3.036,
|
208 |
+
"step": 14500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.18,
|
212 |
+
"learning_rate": 0.00028233818836910827,
|
213 |
+
"loss": 3.0571,
|
214 |
+
"step": 15000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.18,
|
218 |
+
"eval_gen_len": 18.8978,
|
219 |
+
"eval_loss": 2.760854721069336,
|
220 |
+
"eval_rouge1": 23.6484,
|
221 |
+
"eval_rouge2": 12.3437,
|
222 |
+
"eval_rougeL": 21.8478,
|
223 |
+
"eval_rougeLsum": 22.4063,
|
224 |
+
"eval_runtime": 548.4414,
|
225 |
+
"eval_samples_per_second": 18.233,
|
226 |
+
"eval_steps_per_second": 2.279,
|
227 |
+
"step": 15000
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.18,
|
231 |
+
"learning_rate": 0.0002817494613147452,
|
232 |
+
"loss": 3.0305,
|
233 |
+
"step": 15500
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.19,
|
237 |
+
"learning_rate": 0.0002811607342603822,
|
238 |
+
"loss": 3.0116,
|
239 |
+
"step": 16000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.19,
|
243 |
+
"learning_rate": 0.00028057200720601913,
|
244 |
+
"loss": 3.0284,
|
245 |
+
"step": 16500
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.2,
|
249 |
+
"learning_rate": 0.0002799832801516561,
|
250 |
+
"loss": 3.0063,
|
251 |
+
"step": 17000
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.21,
|
255 |
+
"learning_rate": 0.000279394553097293,
|
256 |
+
"loss": 2.9533,
|
257 |
+
"step": 17500
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.21,
|
261 |
+
"learning_rate": 0.00027880582604292994,
|
262 |
+
"loss": 2.9608,
|
263 |
+
"step": 18000
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.22,
|
267 |
+
"learning_rate": 0.0002782170989885669,
|
268 |
+
"loss": 2.9796,
|
269 |
+
"step": 18500
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.22,
|
273 |
+
"learning_rate": 0.00027762837193420385,
|
274 |
+
"loss": 2.9651,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.23,
|
279 |
+
"learning_rate": 0.0002770396448798408,
|
280 |
+
"loss": 2.963,
|
281 |
+
"step": 19500
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.24,
|
285 |
+
"learning_rate": 0.0002764509178254777,
|
286 |
+
"loss": 2.9887,
|
287 |
+
"step": 20000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.24,
|
291 |
+
"eval_gen_len": 18.9275,
|
292 |
+
"eval_loss": 2.7225496768951416,
|
293 |
+
"eval_rouge1": 24.3863,
|
294 |
+
"eval_rouge2": 13.0699,
|
295 |
+
"eval_rougeL": 22.5709,
|
296 |
+
"eval_rougeLsum": 23.1191,
|
297 |
+
"eval_runtime": 548.8094,
|
298 |
+
"eval_samples_per_second": 18.221,
|
299 |
+
"eval_steps_per_second": 2.278,
|
300 |
+
"step": 20000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.24,
|
304 |
+
"learning_rate": 0.00027586219077111465,
|
305 |
+
"loss": 2.9618,
|
306 |
+
"step": 20500
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.25,
|
310 |
+
"learning_rate": 0.0002752734637167516,
|
311 |
+
"loss": 2.9229,
|
312 |
+
"step": 21000
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.25,
|
316 |
+
"learning_rate": 0.00027468473666238856,
|
317 |
+
"loss": 2.9284,
|
318 |
+
"step": 21500
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.26,
|
322 |
+
"learning_rate": 0.0002740960096080255,
|
323 |
+
"loss": 2.9324,
|
324 |
+
"step": 22000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.26,
|
328 |
+
"learning_rate": 0.00027350728255366247,
|
329 |
+
"loss": 2.941,
|
330 |
+
"step": 22500
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.27,
|
334 |
+
"learning_rate": 0.0002729185554992994,
|
335 |
+
"loss": 2.9216,
|
336 |
+
"step": 23000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 0.28,
|
340 |
+
"learning_rate": 0.0002723298284449363,
|
341 |
+
"loss": 2.9258,
|
342 |
+
"step": 23500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.28,
|
346 |
+
"learning_rate": 0.0002717411013905733,
|
347 |
+
"loss": 2.9075,
|
348 |
+
"step": 24000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.29,
|
352 |
+
"learning_rate": 0.00027115237433621023,
|
353 |
+
"loss": 2.9001,
|
354 |
+
"step": 24500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.29,
|
358 |
+
"learning_rate": 0.0002705636472818472,
|
359 |
+
"loss": 2.8939,
|
360 |
+
"step": 25000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.29,
|
364 |
+
"eval_gen_len": 18.8512,
|
365 |
+
"eval_loss": 2.6895627975463867,
|
366 |
+
"eval_rouge1": 23.8549,
|
367 |
+
"eval_rouge2": 12.6254,
|
368 |
+
"eval_rougeL": 22.1601,
|
369 |
+
"eval_rougeLsum": 22.688,
|
370 |
+
"eval_runtime": 544.7255,
|
371 |
+
"eval_samples_per_second": 18.358,
|
372 |
+
"eval_steps_per_second": 2.295,
|
373 |
+
"step": 25000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.3,
|
377 |
+
"learning_rate": 0.00026997492022748414,
|
378 |
+
"loss": 2.8947,
|
379 |
+
"step": 25500
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.31,
|
383 |
+
"learning_rate": 0.00026938619317312104,
|
384 |
+
"loss": 2.9073,
|
385 |
+
"step": 26000
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.31,
|
389 |
+
"learning_rate": 0.000268797466118758,
|
390 |
+
"loss": 2.9035,
|
391 |
+
"step": 26500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.32,
|
395 |
+
"learning_rate": 0.00026820873906439495,
|
396 |
+
"loss": 2.9128,
|
397 |
+
"step": 27000
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.32,
|
401 |
+
"learning_rate": 0.0002676200120100319,
|
402 |
+
"loss": 2.8639,
|
403 |
+
"step": 27500
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.33,
|
407 |
+
"learning_rate": 0.00026703128495566886,
|
408 |
+
"loss": 2.8944,
|
409 |
+
"step": 28000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.34,
|
413 |
+
"learning_rate": 0.00026644255790130575,
|
414 |
+
"loss": 2.8952,
|
415 |
+
"step": 28500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.34,
|
419 |
+
"learning_rate": 0.0002658538308469427,
|
420 |
+
"loss": 2.8956,
|
421 |
+
"step": 29000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.35,
|
425 |
+
"learning_rate": 0.00026526510379257966,
|
426 |
+
"loss": 2.8959,
|
427 |
+
"step": 29500
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.35,
|
431 |
+
"learning_rate": 0.0002646763767382166,
|
432 |
+
"loss": 2.8614,
|
433 |
+
"step": 30000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.35,
|
437 |
+
"eval_gen_len": 18.9345,
|
438 |
+
"eval_loss": 2.6755456924438477,
|
439 |
+
"eval_rouge1": 24.3321,
|
440 |
+
"eval_rouge2": 13.0763,
|
441 |
+
"eval_rougeL": 22.6103,
|
442 |
+
"eval_rougeLsum": 23.1247,
|
443 |
+
"eval_runtime": 546.9326,
|
444 |
+
"eval_samples_per_second": 18.284,
|
445 |
+
"eval_steps_per_second": 2.285,
|
446 |
+
"step": 30000
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.36,
|
450 |
+
"learning_rate": 0.00026408764968385357,
|
451 |
+
"loss": 2.8459,
|
452 |
+
"step": 30500
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.37,
|
456 |
+
"learning_rate": 0.00026349892262949047,
|
457 |
+
"loss": 2.8591,
|
458 |
+
"step": 31000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.37,
|
462 |
+
"learning_rate": 0.0002629101955751274,
|
463 |
+
"loss": 2.8291,
|
464 |
+
"step": 31500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.38,
|
468 |
+
"learning_rate": 0.0002623214685207644,
|
469 |
+
"loss": 2.8645,
|
470 |
+
"step": 32000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.38,
|
474 |
+
"learning_rate": 0.00026173274146640133,
|
475 |
+
"loss": 2.8185,
|
476 |
+
"step": 32500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.39,
|
480 |
+
"learning_rate": 0.0002611440144120383,
|
481 |
+
"loss": 2.8498,
|
482 |
+
"step": 33000
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.39,
|
486 |
+
"learning_rate": 0.0002605552873576752,
|
487 |
+
"loss": 2.8384,
|
488 |
+
"step": 33500
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.4,
|
492 |
+
"learning_rate": 0.00025996656030331214,
|
493 |
+
"loss": 2.8515,
|
494 |
+
"step": 34000
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.41,
|
498 |
+
"learning_rate": 0.0002593778332489491,
|
499 |
+
"loss": 2.8378,
|
500 |
+
"step": 34500
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.41,
|
504 |
+
"learning_rate": 0.00025878910619458605,
|
505 |
+
"loss": 2.849,
|
506 |
+
"step": 35000
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.41,
|
510 |
+
"eval_gen_len": 18.8908,
|
511 |
+
"eval_loss": 2.6249804496765137,
|
512 |
+
"eval_rouge1": 24.2486,
|
513 |
+
"eval_rouge2": 12.8938,
|
514 |
+
"eval_rougeL": 22.5311,
|
515 |
+
"eval_rougeLsum": 23.0375,
|
516 |
+
"eval_runtime": 549.356,
|
517 |
+
"eval_samples_per_second": 18.203,
|
518 |
+
"eval_steps_per_second": 2.275,
|
519 |
+
"step": 35000
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.42,
|
523 |
+
"learning_rate": 0.000258200379140223,
|
524 |
+
"loss": 2.813,
|
525 |
+
"step": 35500
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.42,
|
529 |
+
"learning_rate": 0.00025761165208585996,
|
530 |
+
"loss": 2.8157,
|
531 |
+
"step": 36000
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.43,
|
535 |
+
"learning_rate": 0.00025702292503149686,
|
536 |
+
"loss": 2.83,
|
537 |
+
"step": 36500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.44,
|
541 |
+
"learning_rate": 0.0002564341979771338,
|
542 |
+
"loss": 2.8324,
|
543 |
+
"step": 37000
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.44,
|
547 |
+
"learning_rate": 0.00025584547092277076,
|
548 |
+
"loss": 2.849,
|
549 |
+
"step": 37500
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.45,
|
553 |
+
"learning_rate": 0.0002552567438684077,
|
554 |
+
"loss": 2.8163,
|
555 |
+
"step": 38000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.45,
|
559 |
+
"learning_rate": 0.00025466801681404467,
|
560 |
+
"loss": 2.8215,
|
561 |
+
"step": 38500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.46,
|
565 |
+
"learning_rate": 0.00025407928975968157,
|
566 |
+
"loss": 2.777,
|
567 |
+
"step": 39000
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.47,
|
571 |
+
"learning_rate": 0.0002534905627053185,
|
572 |
+
"loss": 2.8147,
|
573 |
+
"step": 39500
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.47,
|
577 |
+
"learning_rate": 0.0002529018356509555,
|
578 |
+
"loss": 2.7994,
|
579 |
+
"step": 40000
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.47,
|
583 |
+
"eval_gen_len": 18.891,
|
584 |
+
"eval_loss": 2.618790626525879,
|
585 |
+
"eval_rouge1": 24.5722,
|
586 |
+
"eval_rouge2": 13.3685,
|
587 |
+
"eval_rougeL": 22.865,
|
588 |
+
"eval_rougeLsum": 23.3852,
|
589 |
+
"eval_runtime": 548.1205,
|
590 |
+
"eval_samples_per_second": 18.244,
|
591 |
+
"eval_steps_per_second": 2.281,
|
592 |
+
"step": 40000
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.48,
|
596 |
+
"learning_rate": 0.00025231310859659243,
|
597 |
+
"loss": 2.7992,
|
598 |
+
"step": 40500
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.48,
|
602 |
+
"learning_rate": 0.0002517243815422294,
|
603 |
+
"loss": 2.8235,
|
604 |
+
"step": 41000
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.49,
|
608 |
+
"learning_rate": 0.0002511356544878663,
|
609 |
+
"loss": 2.8081,
|
610 |
+
"step": 41500
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.49,
|
614 |
+
"learning_rate": 0.00025054692743350324,
|
615 |
+
"loss": 2.812,
|
616 |
+
"step": 42000
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.5,
|
620 |
+
"learning_rate": 0.0002499582003791402,
|
621 |
+
"loss": 2.7941,
|
622 |
+
"step": 42500
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.51,
|
626 |
+
"learning_rate": 0.00024936947332477715,
|
627 |
+
"loss": 2.8014,
|
628 |
+
"step": 43000
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.51,
|
632 |
+
"learning_rate": 0.0002487807462704141,
|
633 |
+
"loss": 2.7778,
|
634 |
+
"step": 43500
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.52,
|
638 |
+
"learning_rate": 0.000248192019216051,
|
639 |
+
"loss": 2.7734,
|
640 |
+
"step": 44000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.52,
|
644 |
+
"learning_rate": 0.00024760329216168796,
|
645 |
+
"loss": 2.8093,
|
646 |
+
"step": 44500
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.53,
|
650 |
+
"learning_rate": 0.0002470145651073249,
|
651 |
+
"loss": 2.7899,
|
652 |
+
"step": 45000
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 0.53,
|
656 |
+
"eval_gen_len": 18.9064,
|
657 |
+
"eval_loss": 2.6196963787078857,
|
658 |
+
"eval_rouge1": 24.3304,
|
659 |
+
"eval_rouge2": 13.157,
|
660 |
+
"eval_rougeL": 22.6459,
|
661 |
+
"eval_rougeLsum": 23.1647,
|
662 |
+
"eval_runtime": 540.7531,
|
663 |
+
"eval_samples_per_second": 18.493,
|
664 |
+
"eval_steps_per_second": 2.312,
|
665 |
+
"step": 45000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.54,
|
669 |
+
"learning_rate": 0.00024642583805296187,
|
670 |
+
"loss": 2.8157,
|
671 |
+
"step": 45500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.54,
|
675 |
+
"learning_rate": 0.0002458371109985988,
|
676 |
+
"loss": 2.7576,
|
677 |
+
"step": 46000
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.55,
|
681 |
+
"learning_rate": 0.0002452483839442357,
|
682 |
+
"loss": 2.7482,
|
683 |
+
"step": 46500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.55,
|
687 |
+
"learning_rate": 0.00024465965688987273,
|
688 |
+
"loss": 2.7704,
|
689 |
+
"step": 47000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.56,
|
693 |
+
"learning_rate": 0.00024407092983550963,
|
694 |
+
"loss": 2.7597,
|
695 |
+
"step": 47500
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.57,
|
699 |
+
"learning_rate": 0.0002434822027811466,
|
700 |
+
"loss": 2.765,
|
701 |
+
"step": 48000
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 0.57,
|
705 |
+
"learning_rate": 0.00024289347572678354,
|
706 |
+
"loss": 2.7709,
|
707 |
+
"step": 48500
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.58,
|
711 |
+
"learning_rate": 0.00024230474867242046,
|
712 |
+
"loss": 2.7519,
|
713 |
+
"step": 49000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.58,
|
717 |
+
"learning_rate": 0.00024171602161805742,
|
718 |
+
"loss": 2.74,
|
719 |
+
"step": 49500
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.59,
|
723 |
+
"learning_rate": 0.00024112729456369434,
|
724 |
+
"loss": 2.786,
|
725 |
+
"step": 50000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.59,
|
729 |
+
"eval_gen_len": 18.8697,
|
730 |
+
"eval_loss": 2.584320545196533,
|
731 |
+
"eval_rouge1": 24.7437,
|
732 |
+
"eval_rouge2": 13.5493,
|
733 |
+
"eval_rougeL": 23.0267,
|
734 |
+
"eval_rougeLsum": 23.5281,
|
735 |
+
"eval_runtime": 542.416,
|
736 |
+
"eval_samples_per_second": 18.436,
|
737 |
+
"eval_steps_per_second": 2.305,
|
738 |
+
"step": 50000
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.59,
|
742 |
+
"learning_rate": 0.00024053856750933132,
|
743 |
+
"loss": 2.7556,
|
744 |
+
"step": 50500
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.6,
|
748 |
+
"learning_rate": 0.00023994984045496825,
|
749 |
+
"loss": 2.746,
|
750 |
+
"step": 51000
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.61,
|
754 |
+
"learning_rate": 0.00023936111340060518,
|
755 |
+
"loss": 2.767,
|
756 |
+
"step": 51500
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.61,
|
760 |
+
"learning_rate": 0.00023877238634624213,
|
761 |
+
"loss": 2.7261,
|
762 |
+
"step": 52000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.62,
|
766 |
+
"learning_rate": 0.00023818365929187906,
|
767 |
+
"loss": 2.773,
|
768 |
+
"step": 52500
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.62,
|
772 |
+
"learning_rate": 0.00023759493223751604,
|
773 |
+
"loss": 2.7811,
|
774 |
+
"step": 53000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.63,
|
778 |
+
"learning_rate": 0.00023700620518315297,
|
779 |
+
"loss": 2.7727,
|
780 |
+
"step": 53500
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.64,
|
784 |
+
"learning_rate": 0.0002364174781287899,
|
785 |
+
"loss": 2.75,
|
786 |
+
"step": 54000
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.64,
|
790 |
+
"learning_rate": 0.00023582875107442685,
|
791 |
+
"loss": 2.7689,
|
792 |
+
"step": 54500
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.65,
|
796 |
+
"learning_rate": 0.0002352400240200638,
|
797 |
+
"loss": 2.7765,
|
798 |
+
"step": 55000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.65,
|
802 |
+
"eval_gen_len": 18.8908,
|
803 |
+
"eval_loss": 2.5723013877868652,
|
804 |
+
"eval_rouge1": 24.55,
|
805 |
+
"eval_rouge2": 13.501,
|
806 |
+
"eval_rougeL": 22.8132,
|
807 |
+
"eval_rougeLsum": 23.3216,
|
808 |
+
"eval_runtime": 548.4906,
|
809 |
+
"eval_samples_per_second": 18.232,
|
810 |
+
"eval_steps_per_second": 2.279,
|
811 |
+
"step": 55000
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.65,
|
815 |
+
"learning_rate": 0.00023465129696570076,
|
816 |
+
"loss": 2.7603,
|
817 |
+
"step": 55500
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.66,
|
821 |
+
"learning_rate": 0.00023406256991133768,
|
822 |
+
"loss": 2.7369,
|
823 |
+
"step": 56000
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.67,
|
827 |
+
"learning_rate": 0.0002334738428569746,
|
828 |
+
"loss": 2.6958,
|
829 |
+
"step": 56500
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.67,
|
833 |
+
"learning_rate": 0.0002328851158026116,
|
834 |
+
"loss": 2.7746,
|
835 |
+
"step": 57000
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.68,
|
839 |
+
"learning_rate": 0.00023229638874824852,
|
840 |
+
"loss": 2.7596,
|
841 |
+
"step": 57500
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.68,
|
845 |
+
"learning_rate": 0.00023170766169388547,
|
846 |
+
"loss": 2.7118,
|
847 |
+
"step": 58000
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.69,
|
851 |
+
"learning_rate": 0.0002311189346395224,
|
852 |
+
"loss": 2.7248,
|
853 |
+
"step": 58500
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.69,
|
857 |
+
"learning_rate": 0.00023053020758515932,
|
858 |
+
"loss": 2.7307,
|
859 |
+
"step": 59000
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.7,
|
863 |
+
"learning_rate": 0.0002299414805307963,
|
864 |
+
"loss": 2.7487,
|
865 |
+
"step": 59500
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.71,
|
869 |
+
"learning_rate": 0.00022935275347643323,
|
870 |
+
"loss": 2.7591,
|
871 |
+
"step": 60000
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.71,
|
875 |
+
"eval_gen_len": 18.8755,
|
876 |
+
"eval_loss": 2.5769457817077637,
|
877 |
+
"eval_rouge1": 24.78,
|
878 |
+
"eval_rouge2": 13.6656,
|
879 |
+
"eval_rougeL": 23.0842,
|
880 |
+
"eval_rougeLsum": 23.6064,
|
881 |
+
"eval_runtime": 548.2586,
|
882 |
+
"eval_samples_per_second": 18.24,
|
883 |
+
"eval_steps_per_second": 2.28,
|
884 |
+
"step": 60000
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.71,
|
888 |
+
"learning_rate": 0.0002287640264220702,
|
889 |
+
"loss": 2.7621,
|
890 |
+
"step": 60500
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.72,
|
894 |
+
"learning_rate": 0.00022817529936770711,
|
895 |
+
"loss": 2.7554,
|
896 |
+
"step": 61000
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.72,
|
900 |
+
"learning_rate": 0.00022758657231334404,
|
901 |
+
"loss": 2.7484,
|
902 |
+
"step": 61500
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.73,
|
906 |
+
"learning_rate": 0.00022699784525898102,
|
907 |
+
"loss": 2.7762,
|
908 |
+
"step": 62000
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.74,
|
912 |
+
"learning_rate": 0.00022640911820461795,
|
913 |
+
"loss": 2.7248,
|
914 |
+
"step": 62500
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.74,
|
918 |
+
"learning_rate": 0.0002258203911502549,
|
919 |
+
"loss": 2.6949,
|
920 |
+
"step": 63000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.75,
|
924 |
+
"learning_rate": 0.00022523166409589183,
|
925 |
+
"loss": 2.7287,
|
926 |
+
"step": 63500
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.75,
|
930 |
+
"learning_rate": 0.0002246429370415288,
|
931 |
+
"loss": 2.7017,
|
932 |
+
"step": 64000
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.76,
|
936 |
+
"learning_rate": 0.00022405420998716574,
|
937 |
+
"loss": 2.6926,
|
938 |
+
"step": 64500
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.77,
|
942 |
+
"learning_rate": 0.00022346548293280266,
|
943 |
+
"loss": 2.7254,
|
944 |
+
"step": 65000
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.77,
|
948 |
+
"eval_gen_len": 18.8954,
|
949 |
+
"eval_loss": 2.566603183746338,
|
950 |
+
"eval_rouge1": 24.8284,
|
951 |
+
"eval_rouge2": 13.73,
|
952 |
+
"eval_rougeL": 23.0997,
|
953 |
+
"eval_rougeLsum": 23.6334,
|
954 |
+
"eval_runtime": 557.6451,
|
955 |
+
"eval_samples_per_second": 17.933,
|
956 |
+
"eval_steps_per_second": 2.242,
|
957 |
+
"step": 65000
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.77,
|
961 |
+
"learning_rate": 0.00022287675587843962,
|
962 |
+
"loss": 2.7054,
|
963 |
+
"step": 65500
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.78,
|
967 |
+
"learning_rate": 0.00022228802882407655,
|
968 |
+
"loss": 2.6841,
|
969 |
+
"step": 66000
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.78,
|
973 |
+
"learning_rate": 0.00022169930176971353,
|
974 |
+
"loss": 2.7164,
|
975 |
+
"step": 66500
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.79,
|
979 |
+
"learning_rate": 0.00022111057471535045,
|
980 |
+
"loss": 2.7272,
|
981 |
+
"step": 67000
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.79,
|
985 |
+
"learning_rate": 0.00022052184766098738,
|
986 |
+
"loss": 2.715,
|
987 |
+
"step": 67500
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.8,
|
991 |
+
"learning_rate": 0.00021993312060662433,
|
992 |
+
"loss": 2.6992,
|
993 |
+
"step": 68000
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.81,
|
997 |
+
"learning_rate": 0.0002193443935522613,
|
998 |
+
"loss": 2.7124,
|
999 |
+
"step": 68500
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.81,
|
1003 |
+
"learning_rate": 0.00021875566649789824,
|
1004 |
+
"loss": 2.685,
|
1005 |
+
"step": 69000
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.82,
|
1009 |
+
"learning_rate": 0.00021816693944353517,
|
1010 |
+
"loss": 2.6867,
|
1011 |
+
"step": 69500
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.82,
|
1015 |
+
"learning_rate": 0.0002175782123891721,
|
1016 |
+
"loss": 2.6814,
|
1017 |
+
"step": 70000
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.82,
|
1021 |
+
"eval_gen_len": 18.8313,
|
1022 |
+
"eval_loss": 2.5359628200531006,
|
1023 |
+
"eval_rouge1": 24.849,
|
1024 |
+
"eval_rouge2": 13.8366,
|
1025 |
+
"eval_rougeL": 23.1903,
|
1026 |
+
"eval_rougeLsum": 23.6941,
|
1027 |
+
"eval_runtime": 544.4942,
|
1028 |
+
"eval_samples_per_second": 18.366,
|
1029 |
+
"eval_steps_per_second": 2.296,
|
1030 |
+
"step": 70000
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 0.83,
|
1034 |
+
"learning_rate": 0.00021698948533480908,
|
1035 |
+
"loss": 2.6868,
|
1036 |
+
"step": 70500
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 0.84,
|
1040 |
+
"learning_rate": 0.000216400758280446,
|
1041 |
+
"loss": 2.6849,
|
1042 |
+
"step": 71000
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.84,
|
1046 |
+
"learning_rate": 0.00021581203122608296,
|
1047 |
+
"loss": 2.705,
|
1048 |
+
"step": 71500
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.85,
|
1052 |
+
"learning_rate": 0.00021522330417171988,
|
1053 |
+
"loss": 2.7154,
|
1054 |
+
"step": 72000
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.85,
|
1058 |
+
"learning_rate": 0.0002146345771173568,
|
1059 |
+
"loss": 2.6585,
|
1060 |
+
"step": 72500
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.86,
|
1064 |
+
"learning_rate": 0.0002140458500629938,
|
1065 |
+
"loss": 2.6848,
|
1066 |
+
"step": 73000
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.87,
|
1070 |
+
"learning_rate": 0.00021345712300863072,
|
1071 |
+
"loss": 2.6787,
|
1072 |
+
"step": 73500
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 0.87,
|
1076 |
+
"learning_rate": 0.00021286839595426767,
|
1077 |
+
"loss": 2.646,
|
1078 |
+
"step": 74000
|
1079 |
+
}
|
1080 |
+
],
|
1081 |
+
"max_steps": 254787,
|
1082 |
+
"num_train_epochs": 3,
|
1083 |
+
"total_flos": 2.2883060458635264e+17,
|
1084 |
+
"trial_name": null,
|
1085 |
+
"trial_params": null
|
1086 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca4ae6292dc487dcc49cb4227353e87a1082dadb12ea7c15aa3290aa077653d8
|
3 |
+
size 3183
|