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_11-37-53_pg-gpu23/1650965985.2786605/events.out.tfevents.1650965985.pg-gpu23.28067.1 +3 -0
- runs/Apr26_11-37-53_pg-gpu23/events.out.tfevents.1650965985.pg-gpu23.28067.0 +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 +1293 -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:a4b3b1fe9cda9520413a25e321e788e8793be1b0c67b5f1fdbf06819c2fdd13c
|
| 3 |
+
size 569246164
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e424551ffac7923ef282836414c69069126e966946179c1db7a9d9ccc95a7f
|
| 3 |
+
size 1138662581
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa408e3583f5282dd8b5675ea88170d1bebebdf2017416479a2334611b5d4970
|
| 3 |
+
size 569387035
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95493e82e87f2857f96fc36589c415c00043a8767916b8fb7ac138ff0dcc4fea
|
| 3 |
+
size 14503
|
runs/Apr26_11-37-53_pg-gpu23/1650965985.2786605/events.out.tfevents.1650965985.pg-gpu23.28067.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348852b506d31d5c7751d4695f7e8b788c818afe1555695d251943629b28d426
|
| 3 |
+
size 5127
|
runs/Apr26_11-37-53_pg-gpu23/events.out.tfevents.1650965985.pg-gpu23.28067.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5146adaac3d902d1a4579353640210e4a336dbaf00d28e4ba85d15ebada61e7
|
| 3 |
+
size 41394
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ec81f541c694a617df88164fd6b54b33bdad7757694b50dccf1749195a4320f
|
| 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 sha256:399dcadb6dc0846e04f5ffb1313c7600aef29818524ae9bc0ae5b6acf9246852
|
| 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 +1,1293 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.996592844974447,
|
| 5 |
+
"global_step": 88000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0002985397907033341,
|
| 13 |
+
"loss": 4.2075,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 0.00029707958140666826,
|
| 19 |
+
"loss": 3.7047,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 0.0002956193721100024,
|
| 25 |
+
"loss": 3.5253,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.14,
|
| 30 |
+
"learning_rate": 0.00029415916281333654,
|
| 31 |
+
"loss": 3.4404,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 0.0002926989535166707,
|
| 37 |
+
"loss": 3.3437,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"learning_rate": 0.00029123874422000483,
|
| 43 |
+
"loss": 3.3357,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"learning_rate": 0.000289778534923339,
|
| 49 |
+
"loss": 3.275,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"learning_rate": 0.00028831832562667317,
|
| 55 |
+
"loss": 3.2801,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.31,
|
| 60 |
+
"learning_rate": 0.0002868581163300073,
|
| 61 |
+
"loss": 3.2396,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.34,
|
| 66 |
+
"learning_rate": 0.00028539790703334145,
|
| 67 |
+
"loss": 3.2389,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"eval_gen_len": 15.0482,
|
| 73 |
+
"eval_loss": 2.7936947345733643,
|
| 74 |
+
"eval_rouge1": 26.3204,
|
| 75 |
+
"eval_rouge2": 9.4077,
|
| 76 |
+
"eval_rougeL": 23.6598,
|
| 77 |
+
"eval_rougeLsum": 23.8655,
|
| 78 |
+
"eval_runtime": 530.9697,
|
| 79 |
+
"eval_samples_per_second": 18.837,
|
| 80 |
+
"eval_steps_per_second": 2.356,
|
| 81 |
+
"step": 5000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.37,
|
| 85 |
+
"learning_rate": 0.00028393769773667557,
|
| 86 |
+
"loss": 3.2308,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41,
|
| 91 |
+
"learning_rate": 0.00028247748844000974,
|
| 92 |
+
"loss": 3.1836,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.44,
|
| 97 |
+
"learning_rate": 0.00028101727914334385,
|
| 98 |
+
"loss": 3.2004,
|
| 99 |
+
"step": 6500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.48,
|
| 103 |
+
"learning_rate": 0.00027955706984667797,
|
| 104 |
+
"loss": 3.1561,
|
| 105 |
+
"step": 7000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.51,
|
| 109 |
+
"learning_rate": 0.00027809686055001214,
|
| 110 |
+
"loss": 3.1582,
|
| 111 |
+
"step": 7500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.55,
|
| 115 |
+
"learning_rate": 0.00027663665125334625,
|
| 116 |
+
"loss": 3.1249,
|
| 117 |
+
"step": 8000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.58,
|
| 121 |
+
"learning_rate": 0.0002751764419566804,
|
| 122 |
+
"loss": 3.1236,
|
| 123 |
+
"step": 8500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.61,
|
| 127 |
+
"learning_rate": 0.0002737162326600146,
|
| 128 |
+
"loss": 3.0904,
|
| 129 |
+
"step": 9000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.65,
|
| 133 |
+
"learning_rate": 0.0002722560233633487,
|
| 134 |
+
"loss": 3.1179,
|
| 135 |
+
"step": 9500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.68,
|
| 139 |
+
"learning_rate": 0.0002707958140666829,
|
| 140 |
+
"loss": 3.0741,
|
| 141 |
+
"step": 10000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.68,
|
| 145 |
+
"eval_gen_len": 14.4006,
|
| 146 |
+
"eval_loss": 2.6971848011016846,
|
| 147 |
+
"eval_rouge1": 26.9258,
|
| 148 |
+
"eval_rouge2": 9.7445,
|
| 149 |
+
"eval_rougeL": 24.2045,
|
| 150 |
+
"eval_rougeLsum": 24.4155,
|
| 151 |
+
"eval_runtime": 528.5359,
|
| 152 |
+
"eval_samples_per_second": 18.924,
|
| 153 |
+
"eval_steps_per_second": 2.367,
|
| 154 |
+
"step": 10000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.72,
|
| 158 |
+
"learning_rate": 0.00026933560477001705,
|
| 159 |
+
"loss": 3.0814,
|
| 160 |
+
"step": 10500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.75,
|
| 164 |
+
"learning_rate": 0.00026787539547335116,
|
| 165 |
+
"loss": 3.1,
|
| 166 |
+
"step": 11000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.78,
|
| 170 |
+
"learning_rate": 0.00026641518617668533,
|
| 171 |
+
"loss": 3.0672,
|
| 172 |
+
"step": 11500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.82,
|
| 176 |
+
"learning_rate": 0.00026495497688001945,
|
| 177 |
+
"loss": 3.0728,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.85,
|
| 182 |
+
"learning_rate": 0.0002634947675833536,
|
| 183 |
+
"loss": 3.0516,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.89,
|
| 188 |
+
"learning_rate": 0.00026203455828668773,
|
| 189 |
+
"loss": 3.0587,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.92,
|
| 194 |
+
"learning_rate": 0.00026057434899002185,
|
| 195 |
+
"loss": 3.061,
|
| 196 |
+
"step": 13500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.95,
|
| 200 |
+
"learning_rate": 0.000259114139693356,
|
| 201 |
+
"loss": 3.0404,
|
| 202 |
+
"step": 14000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.99,
|
| 206 |
+
"learning_rate": 0.00025765393039669013,
|
| 207 |
+
"loss": 3.0352,
|
| 208 |
+
"step": 14500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.02,
|
| 212 |
+
"learning_rate": 0.0002561937211000243,
|
| 213 |
+
"loss": 2.9119,
|
| 214 |
+
"step": 15000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.02,
|
| 218 |
+
"eval_gen_len": 15.1769,
|
| 219 |
+
"eval_loss": 2.641094923019409,
|
| 220 |
+
"eval_rouge1": 27.6132,
|
| 221 |
+
"eval_rouge2": 10.2843,
|
| 222 |
+
"eval_rougeL": 24.6804,
|
| 223 |
+
"eval_rougeLsum": 24.9483,
|
| 224 |
+
"eval_runtime": 519.8172,
|
| 225 |
+
"eval_samples_per_second": 19.241,
|
| 226 |
+
"eval_steps_per_second": 2.407,
|
| 227 |
+
"step": 15000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.06,
|
| 231 |
+
"learning_rate": 0.00025473351180335847,
|
| 232 |
+
"loss": 2.8945,
|
| 233 |
+
"step": 15500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.09,
|
| 237 |
+
"learning_rate": 0.0002532733025066926,
|
| 238 |
+
"loss": 2.8809,
|
| 239 |
+
"step": 16000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.12,
|
| 243 |
+
"learning_rate": 0.00025181309321002676,
|
| 244 |
+
"loss": 2.8548,
|
| 245 |
+
"step": 16500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.16,
|
| 249 |
+
"learning_rate": 0.0002503528839133609,
|
| 250 |
+
"loss": 2.8613,
|
| 251 |
+
"step": 17000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.19,
|
| 255 |
+
"learning_rate": 0.00024889267461669504,
|
| 256 |
+
"loss": 2.8463,
|
| 257 |
+
"step": 17500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.23,
|
| 261 |
+
"learning_rate": 0.0002474324653200292,
|
| 262 |
+
"loss": 2.8409,
|
| 263 |
+
"step": 18000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.26,
|
| 267 |
+
"learning_rate": 0.0002459722560233633,
|
| 268 |
+
"loss": 2.8519,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.29,
|
| 273 |
+
"learning_rate": 0.0002445120467266975,
|
| 274 |
+
"loss": 2.8457,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.33,
|
| 279 |
+
"learning_rate": 0.0002430518374300316,
|
| 280 |
+
"loss": 2.8603,
|
| 281 |
+
"step": 19500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.36,
|
| 285 |
+
"learning_rate": 0.00024159162813336578,
|
| 286 |
+
"loss": 2.8272,
|
| 287 |
+
"step": 20000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.36,
|
| 291 |
+
"eval_gen_len": 15.1337,
|
| 292 |
+
"eval_loss": 2.596390962600708,
|
| 293 |
+
"eval_rouge1": 27.5723,
|
| 294 |
+
"eval_rouge2": 10.131,
|
| 295 |
+
"eval_rougeL": 24.6773,
|
| 296 |
+
"eval_rougeLsum": 24.9496,
|
| 297 |
+
"eval_runtime": 529.2072,
|
| 298 |
+
"eval_samples_per_second": 18.9,
|
| 299 |
+
"eval_steps_per_second": 2.364,
|
| 300 |
+
"step": 20000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.4,
|
| 304 |
+
"learning_rate": 0.0002401314188366999,
|
| 305 |
+
"loss": 2.8576,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.43,
|
| 310 |
+
"learning_rate": 0.00023867120954003404,
|
| 311 |
+
"loss": 2.8396,
|
| 312 |
+
"step": 21000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.47,
|
| 316 |
+
"learning_rate": 0.0002372110002433682,
|
| 317 |
+
"loss": 2.838,
|
| 318 |
+
"step": 21500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5,
|
| 322 |
+
"learning_rate": 0.00023575079094670232,
|
| 323 |
+
"loss": 2.842,
|
| 324 |
+
"step": 22000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.53,
|
| 328 |
+
"learning_rate": 0.0002342905816500365,
|
| 329 |
+
"loss": 2.8255,
|
| 330 |
+
"step": 22500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.57,
|
| 334 |
+
"learning_rate": 0.0002328303723533706,
|
| 335 |
+
"loss": 2.8173,
|
| 336 |
+
"step": 23000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.6,
|
| 340 |
+
"learning_rate": 0.00023137016305670478,
|
| 341 |
+
"loss": 2.8115,
|
| 342 |
+
"step": 23500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.64,
|
| 346 |
+
"learning_rate": 0.00022990995376003892,
|
| 347 |
+
"loss": 2.8148,
|
| 348 |
+
"step": 24000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.67,
|
| 352 |
+
"learning_rate": 0.00022844974446337306,
|
| 353 |
+
"loss": 2.8155,
|
| 354 |
+
"step": 24500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.7,
|
| 358 |
+
"learning_rate": 0.0002269895351667072,
|
| 359 |
+
"loss": 2.8135,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7,
|
| 364 |
+
"eval_gen_len": 15.4393,
|
| 365 |
+
"eval_loss": 2.5782437324523926,
|
| 366 |
+
"eval_rouge1": 28.7444,
|
| 367 |
+
"eval_rouge2": 10.8958,
|
| 368 |
+
"eval_rougeL": 25.6842,
|
| 369 |
+
"eval_rougeLsum": 25.9691,
|
| 370 |
+
"eval_runtime": 520.1126,
|
| 371 |
+
"eval_samples_per_second": 19.23,
|
| 372 |
+
"eval_steps_per_second": 2.405,
|
| 373 |
+
"step": 25000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.74,
|
| 377 |
+
"learning_rate": 0.00022552932587004137,
|
| 378 |
+
"loss": 2.8161,
|
| 379 |
+
"step": 25500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.77,
|
| 383 |
+
"learning_rate": 0.0002240691165733755,
|
| 384 |
+
"loss": 2.8132,
|
| 385 |
+
"step": 26000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.81,
|
| 389 |
+
"learning_rate": 0.00022260890727670966,
|
| 390 |
+
"loss": 2.8192,
|
| 391 |
+
"step": 26500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.84,
|
| 395 |
+
"learning_rate": 0.00022114869798004378,
|
| 396 |
+
"loss": 2.8098,
|
| 397 |
+
"step": 27000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.87,
|
| 401 |
+
"learning_rate": 0.00021968848868337792,
|
| 402 |
+
"loss": 2.776,
|
| 403 |
+
"step": 27500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.91,
|
| 407 |
+
"learning_rate": 0.0002182282793867121,
|
| 408 |
+
"loss": 2.7931,
|
| 409 |
+
"step": 28000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.94,
|
| 413 |
+
"learning_rate": 0.0002167680700900462,
|
| 414 |
+
"loss": 2.7675,
|
| 415 |
+
"step": 28500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.98,
|
| 419 |
+
"learning_rate": 0.00021530786079338037,
|
| 420 |
+
"loss": 2.788,
|
| 421 |
+
"step": 29000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.01,
|
| 425 |
+
"learning_rate": 0.0002138476514967145,
|
| 426 |
+
"loss": 2.7194,
|
| 427 |
+
"step": 29500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.04,
|
| 431 |
+
"learning_rate": 0.00021238744220004866,
|
| 432 |
+
"loss": 2.6235,
|
| 433 |
+
"step": 30000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.04,
|
| 437 |
+
"eval_gen_len": 14.9003,
|
| 438 |
+
"eval_loss": 2.551361322402954,
|
| 439 |
+
"eval_rouge1": 29.1138,
|
| 440 |
+
"eval_rouge2": 11.1582,
|
| 441 |
+
"eval_rougeL": 25.9524,
|
| 442 |
+
"eval_rougeLsum": 26.2659,
|
| 443 |
+
"eval_runtime": 524.2558,
|
| 444 |
+
"eval_samples_per_second": 19.078,
|
| 445 |
+
"eval_steps_per_second": 2.386,
|
| 446 |
+
"step": 30000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.08,
|
| 450 |
+
"learning_rate": 0.0002109272329033828,
|
| 451 |
+
"loss": 2.6189,
|
| 452 |
+
"step": 30500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.11,
|
| 456 |
+
"learning_rate": 0.00020946702360671694,
|
| 457 |
+
"loss": 2.6318,
|
| 458 |
+
"step": 31000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.15,
|
| 462 |
+
"learning_rate": 0.00020800681431005108,
|
| 463 |
+
"loss": 2.6356,
|
| 464 |
+
"step": 31500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.18,
|
| 468 |
+
"learning_rate": 0.00020654660501338525,
|
| 469 |
+
"loss": 2.6379,
|
| 470 |
+
"step": 32000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.21,
|
| 474 |
+
"learning_rate": 0.00020508639571671937,
|
| 475 |
+
"loss": 2.6018,
|
| 476 |
+
"step": 32500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.25,
|
| 480 |
+
"learning_rate": 0.00020362618642005354,
|
| 481 |
+
"loss": 2.6223,
|
| 482 |
+
"step": 33000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.28,
|
| 486 |
+
"learning_rate": 0.00020216597712338765,
|
| 487 |
+
"loss": 2.6421,
|
| 488 |
+
"step": 33500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.32,
|
| 492 |
+
"learning_rate": 0.0002007057678267218,
|
| 493 |
+
"loss": 2.6397,
|
| 494 |
+
"step": 34000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.35,
|
| 498 |
+
"learning_rate": 0.00019924555853005597,
|
| 499 |
+
"loss": 2.6401,
|
| 500 |
+
"step": 34500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.39,
|
| 504 |
+
"learning_rate": 0.00019778534923339008,
|
| 505 |
+
"loss": 2.641,
|
| 506 |
+
"step": 35000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.39,
|
| 510 |
+
"eval_gen_len": 14.8827,
|
| 511 |
+
"eval_loss": 2.526247978210449,
|
| 512 |
+
"eval_rouge1": 29.1569,
|
| 513 |
+
"eval_rouge2": 11.2473,
|
| 514 |
+
"eval_rougeL": 26.0977,
|
| 515 |
+
"eval_rougeLsum": 26.4149,
|
| 516 |
+
"eval_runtime": 516.1021,
|
| 517 |
+
"eval_samples_per_second": 19.38,
|
| 518 |
+
"eval_steps_per_second": 2.424,
|
| 519 |
+
"step": 35000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.42,
|
| 523 |
+
"learning_rate": 0.00019632513993672425,
|
| 524 |
+
"loss": 2.6228,
|
| 525 |
+
"step": 35500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.45,
|
| 529 |
+
"learning_rate": 0.0001948649306400584,
|
| 530 |
+
"loss": 2.6487,
|
| 531 |
+
"step": 36000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.49,
|
| 535 |
+
"learning_rate": 0.00019340472134339254,
|
| 536 |
+
"loss": 2.6373,
|
| 537 |
+
"step": 36500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.52,
|
| 541 |
+
"learning_rate": 0.00019194451204672668,
|
| 542 |
+
"loss": 2.6493,
|
| 543 |
+
"step": 37000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.56,
|
| 547 |
+
"learning_rate": 0.00019048430275006085,
|
| 548 |
+
"loss": 2.6378,
|
| 549 |
+
"step": 37500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.59,
|
| 553 |
+
"learning_rate": 0.00018902409345339496,
|
| 554 |
+
"loss": 2.6264,
|
| 555 |
+
"step": 38000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.62,
|
| 559 |
+
"learning_rate": 0.00018756388415672913,
|
| 560 |
+
"loss": 2.6223,
|
| 561 |
+
"step": 38500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.66,
|
| 565 |
+
"learning_rate": 0.00018610367486006325,
|
| 566 |
+
"loss": 2.6156,
|
| 567 |
+
"step": 39000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.69,
|
| 571 |
+
"learning_rate": 0.00018464346556339742,
|
| 572 |
+
"loss": 2.6221,
|
| 573 |
+
"step": 39500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.73,
|
| 577 |
+
"learning_rate": 0.00018318325626673156,
|
| 578 |
+
"loss": 2.6342,
|
| 579 |
+
"step": 40000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.73,
|
| 583 |
+
"eval_gen_len": 14.8778,
|
| 584 |
+
"eval_loss": 2.5141656398773193,
|
| 585 |
+
"eval_rouge1": 29.2214,
|
| 586 |
+
"eval_rouge2": 11.1812,
|
| 587 |
+
"eval_rougeL": 26.1029,
|
| 588 |
+
"eval_rougeLsum": 26.3802,
|
| 589 |
+
"eval_runtime": 526.5352,
|
| 590 |
+
"eval_samples_per_second": 18.996,
|
| 591 |
+
"eval_steps_per_second": 2.376,
|
| 592 |
+
"step": 40000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.76,
|
| 596 |
+
"learning_rate": 0.00018172304697006568,
|
| 597 |
+
"loss": 2.6198,
|
| 598 |
+
"step": 40500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.79,
|
| 602 |
+
"learning_rate": 0.00018026283767339985,
|
| 603 |
+
"loss": 2.6206,
|
| 604 |
+
"step": 41000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.83,
|
| 608 |
+
"learning_rate": 0.00017880262837673396,
|
| 609 |
+
"loss": 2.6106,
|
| 610 |
+
"step": 41500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.86,
|
| 614 |
+
"learning_rate": 0.00017734241908006813,
|
| 615 |
+
"loss": 2.6162,
|
| 616 |
+
"step": 42000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.9,
|
| 620 |
+
"learning_rate": 0.00017588220978340227,
|
| 621 |
+
"loss": 2.6218,
|
| 622 |
+
"step": 42500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.93,
|
| 626 |
+
"learning_rate": 0.00017442200048673642,
|
| 627 |
+
"loss": 2.6045,
|
| 628 |
+
"step": 43000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.96,
|
| 632 |
+
"learning_rate": 0.00017296179119007056,
|
| 633 |
+
"loss": 2.579,
|
| 634 |
+
"step": 43500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.0,
|
| 638 |
+
"learning_rate": 0.00017150158189340473,
|
| 639 |
+
"loss": 2.6103,
|
| 640 |
+
"step": 44000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.03,
|
| 644 |
+
"learning_rate": 0.00017004137259673884,
|
| 645 |
+
"loss": 2.454,
|
| 646 |
+
"step": 44500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.07,
|
| 650 |
+
"learning_rate": 0.000168581163300073,
|
| 651 |
+
"loss": 2.4637,
|
| 652 |
+
"step": 45000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.07,
|
| 656 |
+
"eval_gen_len": 15.2305,
|
| 657 |
+
"eval_loss": 2.511312246322632,
|
| 658 |
+
"eval_rouge1": 29.6711,
|
| 659 |
+
"eval_rouge2": 11.5,
|
| 660 |
+
"eval_rougeL": 26.4325,
|
| 661 |
+
"eval_rougeLsum": 26.7634,
|
| 662 |
+
"eval_runtime": 524.3633,
|
| 663 |
+
"eval_samples_per_second": 19.075,
|
| 664 |
+
"eval_steps_per_second": 2.386,
|
| 665 |
+
"step": 45000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.1,
|
| 669 |
+
"learning_rate": 0.00016712095400340713,
|
| 670 |
+
"loss": 2.4633,
|
| 671 |
+
"step": 45500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.13,
|
| 675 |
+
"learning_rate": 0.0001656607447067413,
|
| 676 |
+
"loss": 2.4437,
|
| 677 |
+
"step": 46000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.17,
|
| 681 |
+
"learning_rate": 0.00016420053541007544,
|
| 682 |
+
"loss": 2.4744,
|
| 683 |
+
"step": 46500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.2,
|
| 687 |
+
"learning_rate": 0.00016274032611340956,
|
| 688 |
+
"loss": 2.4618,
|
| 689 |
+
"step": 47000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.24,
|
| 693 |
+
"learning_rate": 0.00016128011681674372,
|
| 694 |
+
"loss": 2.4945,
|
| 695 |
+
"step": 47500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.27,
|
| 699 |
+
"learning_rate": 0.00015981990752007784,
|
| 700 |
+
"loss": 2.4747,
|
| 701 |
+
"step": 48000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.3,
|
| 705 |
+
"learning_rate": 0.000158359698223412,
|
| 706 |
+
"loss": 2.4632,
|
| 707 |
+
"step": 48500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 3.34,
|
| 711 |
+
"learning_rate": 0.00015689948892674615,
|
| 712 |
+
"loss": 2.4892,
|
| 713 |
+
"step": 49000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.37,
|
| 717 |
+
"learning_rate": 0.0001554392796300803,
|
| 718 |
+
"loss": 2.4389,
|
| 719 |
+
"step": 49500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.41,
|
| 723 |
+
"learning_rate": 0.00015397907033341444,
|
| 724 |
+
"loss": 2.5028,
|
| 725 |
+
"step": 50000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 3.41,
|
| 729 |
+
"eval_gen_len": 15.2348,
|
| 730 |
+
"eval_loss": 2.494405746459961,
|
| 731 |
+
"eval_rouge1": 29.8317,
|
| 732 |
+
"eval_rouge2": 11.5675,
|
| 733 |
+
"eval_rougeL": 26.4741,
|
| 734 |
+
"eval_rougeLsum": 26.7943,
|
| 735 |
+
"eval_runtime": 526.1631,
|
| 736 |
+
"eval_samples_per_second": 19.009,
|
| 737 |
+
"eval_steps_per_second": 2.378,
|
| 738 |
+
"step": 50000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.44,
|
| 742 |
+
"learning_rate": 0.0001525188610367486,
|
| 743 |
+
"loss": 2.457,
|
| 744 |
+
"step": 50500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.48,
|
| 748 |
+
"learning_rate": 0.00015105865174008272,
|
| 749 |
+
"loss": 2.4586,
|
| 750 |
+
"step": 51000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.51,
|
| 754 |
+
"learning_rate": 0.00014959844244341686,
|
| 755 |
+
"loss": 2.4731,
|
| 756 |
+
"step": 51500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 3.54,
|
| 760 |
+
"learning_rate": 0.000148138233146751,
|
| 761 |
+
"loss": 2.492,
|
| 762 |
+
"step": 52000
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 3.58,
|
| 766 |
+
"learning_rate": 0.00014667802385008518,
|
| 767 |
+
"loss": 2.485,
|
| 768 |
+
"step": 52500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.61,
|
| 772 |
+
"learning_rate": 0.00014521781455341932,
|
| 773 |
+
"loss": 2.4679,
|
| 774 |
+
"step": 53000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.65,
|
| 778 |
+
"learning_rate": 0.00014375760525675346,
|
| 779 |
+
"loss": 2.4675,
|
| 780 |
+
"step": 53500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.68,
|
| 784 |
+
"learning_rate": 0.0001422973959600876,
|
| 785 |
+
"loss": 2.4659,
|
| 786 |
+
"step": 54000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.71,
|
| 790 |
+
"learning_rate": 0.00014083718666342175,
|
| 791 |
+
"loss": 2.472,
|
| 792 |
+
"step": 54500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.75,
|
| 796 |
+
"learning_rate": 0.0001393769773667559,
|
| 797 |
+
"loss": 2.4507,
|
| 798 |
+
"step": 55000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 3.75,
|
| 802 |
+
"eval_gen_len": 14.9608,
|
| 803 |
+
"eval_loss": 2.479571580886841,
|
| 804 |
+
"eval_rouge1": 29.8158,
|
| 805 |
+
"eval_rouge2": 11.6394,
|
| 806 |
+
"eval_rougeL": 26.5371,
|
| 807 |
+
"eval_rougeLsum": 26.8625,
|
| 808 |
+
"eval_runtime": 518.7283,
|
| 809 |
+
"eval_samples_per_second": 19.282,
|
| 810 |
+
"eval_steps_per_second": 2.412,
|
| 811 |
+
"step": 55000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 3.78,
|
| 815 |
+
"learning_rate": 0.00013791676807009003,
|
| 816 |
+
"loss": 2.489,
|
| 817 |
+
"step": 55500
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 3.82,
|
| 821 |
+
"learning_rate": 0.00013645655877342417,
|
| 822 |
+
"loss": 2.4626,
|
| 823 |
+
"step": 56000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 3.85,
|
| 827 |
+
"learning_rate": 0.00013499634947675834,
|
| 828 |
+
"loss": 2.4534,
|
| 829 |
+
"step": 56500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.88,
|
| 833 |
+
"learning_rate": 0.00013353614018009246,
|
| 834 |
+
"loss": 2.4664,
|
| 835 |
+
"step": 57000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 3.92,
|
| 839 |
+
"learning_rate": 0.0001320759308834266,
|
| 840 |
+
"loss": 2.4927,
|
| 841 |
+
"step": 57500
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.95,
|
| 845 |
+
"learning_rate": 0.00013061572158676074,
|
| 846 |
+
"loss": 2.4654,
|
| 847 |
+
"step": 58000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 3.99,
|
| 851 |
+
"learning_rate": 0.00012915551229009489,
|
| 852 |
+
"loss": 2.48,
|
| 853 |
+
"step": 58500
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 4.02,
|
| 857 |
+
"learning_rate": 0.00012769530299342906,
|
| 858 |
+
"loss": 2.3542,
|
| 859 |
+
"step": 59000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 4.05,
|
| 863 |
+
"learning_rate": 0.0001262350936967632,
|
| 864 |
+
"loss": 2.3249,
|
| 865 |
+
"step": 59500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 4.09,
|
| 869 |
+
"learning_rate": 0.00012477488440009734,
|
| 870 |
+
"loss": 2.3282,
|
| 871 |
+
"step": 60000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.09,
|
| 875 |
+
"eval_gen_len": 14.9966,
|
| 876 |
+
"eval_loss": 2.4929299354553223,
|
| 877 |
+
"eval_rouge1": 29.8621,
|
| 878 |
+
"eval_rouge2": 11.5076,
|
| 879 |
+
"eval_rougeL": 26.5598,
|
| 880 |
+
"eval_rougeLsum": 26.9032,
|
| 881 |
+
"eval_runtime": 525.8633,
|
| 882 |
+
"eval_samples_per_second": 19.02,
|
| 883 |
+
"eval_steps_per_second": 2.379,
|
| 884 |
+
"step": 60000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.12,
|
| 888 |
+
"learning_rate": 0.00012331467510343148,
|
| 889 |
+
"loss": 2.3419,
|
| 890 |
+
"step": 60500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.16,
|
| 894 |
+
"learning_rate": 0.00012185446580676563,
|
| 895 |
+
"loss": 2.3247,
|
| 896 |
+
"step": 61000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.19,
|
| 900 |
+
"learning_rate": 0.00012039425651009977,
|
| 901 |
+
"loss": 2.3349,
|
| 902 |
+
"step": 61500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.22,
|
| 906 |
+
"learning_rate": 0.00011893404721343392,
|
| 907 |
+
"loss": 2.3203,
|
| 908 |
+
"step": 62000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.26,
|
| 912 |
+
"learning_rate": 0.00011747383791676807,
|
| 913 |
+
"loss": 2.3494,
|
| 914 |
+
"step": 62500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.29,
|
| 918 |
+
"learning_rate": 0.00011601362862010221,
|
| 919 |
+
"loss": 2.3575,
|
| 920 |
+
"step": 63000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.33,
|
| 924 |
+
"learning_rate": 0.00011455341932343635,
|
| 925 |
+
"loss": 2.343,
|
| 926 |
+
"step": 63500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.36,
|
| 930 |
+
"learning_rate": 0.00011309321002677048,
|
| 931 |
+
"loss": 2.3609,
|
| 932 |
+
"step": 64000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 4.4,
|
| 936 |
+
"learning_rate": 0.00011163300073010464,
|
| 937 |
+
"loss": 2.3294,
|
| 938 |
+
"step": 64500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.43,
|
| 942 |
+
"learning_rate": 0.00011017279143343878,
|
| 943 |
+
"loss": 2.3218,
|
| 944 |
+
"step": 65000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.43,
|
| 948 |
+
"eval_gen_len": 15.2109,
|
| 949 |
+
"eval_loss": 2.473184585571289,
|
| 950 |
+
"eval_rouge1": 30.1018,
|
| 951 |
+
"eval_rouge2": 11.8166,
|
| 952 |
+
"eval_rougeL": 26.72,
|
| 953 |
+
"eval_rougeLsum": 27.0393,
|
| 954 |
+
"eval_runtime": 525.9361,
|
| 955 |
+
"eval_samples_per_second": 19.018,
|
| 956 |
+
"eval_steps_per_second": 2.379,
|
| 957 |
+
"step": 65000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 4.46,
|
| 961 |
+
"learning_rate": 0.00010871258213677292,
|
| 962 |
+
"loss": 2.3574,
|
| 963 |
+
"step": 65500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 4.5,
|
| 967 |
+
"learning_rate": 0.00010725237284010706,
|
| 968 |
+
"loss": 2.3396,
|
| 969 |
+
"step": 66000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.53,
|
| 973 |
+
"learning_rate": 0.00010579216354344122,
|
| 974 |
+
"loss": 2.3742,
|
| 975 |
+
"step": 66500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 4.57,
|
| 979 |
+
"learning_rate": 0.00010433195424677536,
|
| 980 |
+
"loss": 2.3382,
|
| 981 |
+
"step": 67000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 4.6,
|
| 985 |
+
"learning_rate": 0.0001028717449501095,
|
| 986 |
+
"loss": 2.3518,
|
| 987 |
+
"step": 67500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 4.63,
|
| 991 |
+
"learning_rate": 0.00010141153565344366,
|
| 992 |
+
"loss": 2.3659,
|
| 993 |
+
"step": 68000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 4.67,
|
| 997 |
+
"learning_rate": 9.99513263567778e-05,
|
| 998 |
+
"loss": 2.3487,
|
| 999 |
+
"step": 68500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.7,
|
| 1003 |
+
"learning_rate": 9.849111706011195e-05,
|
| 1004 |
+
"loss": 2.3337,
|
| 1005 |
+
"step": 69000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.74,
|
| 1009 |
+
"learning_rate": 9.703090776344609e-05,
|
| 1010 |
+
"loss": 2.3426,
|
| 1011 |
+
"step": 69500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 4.77,
|
| 1015 |
+
"learning_rate": 9.557069846678024e-05,
|
| 1016 |
+
"loss": 2.3321,
|
| 1017 |
+
"step": 70000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.77,
|
| 1021 |
+
"eval_gen_len": 14.7861,
|
| 1022 |
+
"eval_loss": 2.462064266204834,
|
| 1023 |
+
"eval_rouge1": 30.3513,
|
| 1024 |
+
"eval_rouge2": 11.9542,
|
| 1025 |
+
"eval_rougeL": 27.074,
|
| 1026 |
+
"eval_rougeLsum": 27.39,
|
| 1027 |
+
"eval_runtime": 529.0668,
|
| 1028 |
+
"eval_samples_per_second": 18.905,
|
| 1029 |
+
"eval_steps_per_second": 2.365,
|
| 1030 |
+
"step": 70000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 4.8,
|
| 1034 |
+
"learning_rate": 9.411048917011437e-05,
|
| 1035 |
+
"loss": 2.3369,
|
| 1036 |
+
"step": 70500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 4.84,
|
| 1040 |
+
"learning_rate": 9.265027987344852e-05,
|
| 1041 |
+
"loss": 2.3536,
|
| 1042 |
+
"step": 71000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 4.87,
|
| 1046 |
+
"learning_rate": 9.119007057678266e-05,
|
| 1047 |
+
"loss": 2.3364,
|
| 1048 |
+
"step": 71500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 4.91,
|
| 1052 |
+
"learning_rate": 8.97298612801168e-05,
|
| 1053 |
+
"loss": 2.3412,
|
| 1054 |
+
"step": 72000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 4.94,
|
| 1058 |
+
"learning_rate": 8.826965198345096e-05,
|
| 1059 |
+
"loss": 2.3364,
|
| 1060 |
+
"step": 72500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 4.97,
|
| 1064 |
+
"learning_rate": 8.68094426867851e-05,
|
| 1065 |
+
"loss": 2.3605,
|
| 1066 |
+
"step": 73000
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 5.01,
|
| 1070 |
+
"learning_rate": 8.534923339011924e-05,
|
| 1071 |
+
"loss": 2.3124,
|
| 1072 |
+
"step": 73500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 5.04,
|
| 1076 |
+
"learning_rate": 8.388902409345338e-05,
|
| 1077 |
+
"loss": 2.2233,
|
| 1078 |
+
"step": 74000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 5.08,
|
| 1082 |
+
"learning_rate": 8.242881479678754e-05,
|
| 1083 |
+
"loss": 2.2063,
|
| 1084 |
+
"step": 74500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 5.11,
|
| 1088 |
+
"learning_rate": 8.096860550012168e-05,
|
| 1089 |
+
"loss": 2.2197,
|
| 1090 |
+
"step": 75000
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 5.11,
|
| 1094 |
+
"eval_gen_len": 14.9783,
|
| 1095 |
+
"eval_loss": 2.4723336696624756,
|
| 1096 |
+
"eval_rouge1": 30.3337,
|
| 1097 |
+
"eval_rouge2": 11.9362,
|
| 1098 |
+
"eval_rougeL": 27.0161,
|
| 1099 |
+
"eval_rougeLsum": 27.365,
|
| 1100 |
+
"eval_runtime": 522.7349,
|
| 1101 |
+
"eval_samples_per_second": 19.134,
|
| 1102 |
+
"eval_steps_per_second": 2.393,
|
| 1103 |
+
"step": 75000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 5.14,
|
| 1107 |
+
"learning_rate": 7.950839620345582e-05,
|
| 1108 |
+
"loss": 2.2218,
|
| 1109 |
+
"step": 75500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.18,
|
| 1113 |
+
"learning_rate": 7.804818690678997e-05,
|
| 1114 |
+
"loss": 2.2415,
|
| 1115 |
+
"step": 76000
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 5.21,
|
| 1119 |
+
"learning_rate": 7.658797761012412e-05,
|
| 1120 |
+
"loss": 2.2132,
|
| 1121 |
+
"step": 76500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 5.25,
|
| 1125 |
+
"learning_rate": 7.512776831345825e-05,
|
| 1126 |
+
"loss": 2.2604,
|
| 1127 |
+
"step": 77000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 5.28,
|
| 1131 |
+
"learning_rate": 7.366755901679241e-05,
|
| 1132 |
+
"loss": 2.2573,
|
| 1133 |
+
"step": 77500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 5.32,
|
| 1137 |
+
"learning_rate": 7.220734972012655e-05,
|
| 1138 |
+
"loss": 2.2291,
|
| 1139 |
+
"step": 78000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 5.35,
|
| 1143 |
+
"learning_rate": 7.074714042346069e-05,
|
| 1144 |
+
"loss": 2.2489,
|
| 1145 |
+
"step": 78500
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 5.38,
|
| 1149 |
+
"learning_rate": 6.928693112679484e-05,
|
| 1150 |
+
"loss": 2.225,
|
| 1151 |
+
"step": 79000
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 5.42,
|
| 1155 |
+
"learning_rate": 6.782672183012898e-05,
|
| 1156 |
+
"loss": 2.2077,
|
| 1157 |
+
"step": 79500
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 5.45,
|
| 1161 |
+
"learning_rate": 6.636651253346312e-05,
|
| 1162 |
+
"loss": 2.2273,
|
| 1163 |
+
"step": 80000
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 5.45,
|
| 1167 |
+
"eval_gen_len": 14.8784,
|
| 1168 |
+
"eval_loss": 2.4681761264801025,
|
| 1169 |
+
"eval_rouge1": 30.4217,
|
| 1170 |
+
"eval_rouge2": 12.0307,
|
| 1171 |
+
"eval_rougeL": 27.11,
|
| 1172 |
+
"eval_rougeLsum": 27.4155,
|
| 1173 |
+
"eval_runtime": 524.8636,
|
| 1174 |
+
"eval_samples_per_second": 19.056,
|
| 1175 |
+
"eval_steps_per_second": 2.383,
|
| 1176 |
+
"step": 80000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 5.49,
|
| 1180 |
+
"learning_rate": 6.490630323679726e-05,
|
| 1181 |
+
"loss": 2.2231,
|
| 1182 |
+
"step": 80500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 5.52,
|
| 1186 |
+
"learning_rate": 6.344609394013142e-05,
|
| 1187 |
+
"loss": 2.2679,
|
| 1188 |
+
"step": 81000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 5.55,
|
| 1192 |
+
"learning_rate": 6.198588464346556e-05,
|
| 1193 |
+
"loss": 2.2423,
|
| 1194 |
+
"step": 81500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 5.59,
|
| 1198 |
+
"learning_rate": 6.05256753467997e-05,
|
| 1199 |
+
"loss": 2.2195,
|
| 1200 |
+
"step": 82000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 5.62,
|
| 1204 |
+
"learning_rate": 5.9065466050133846e-05,
|
| 1205 |
+
"loss": 2.2439,
|
| 1206 |
+
"step": 82500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 5.66,
|
| 1210 |
+
"learning_rate": 5.760525675346799e-05,
|
| 1211 |
+
"loss": 2.2261,
|
| 1212 |
+
"step": 83000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 5.69,
|
| 1216 |
+
"learning_rate": 5.614504745680214e-05,
|
| 1217 |
+
"loss": 2.2562,
|
| 1218 |
+
"step": 83500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 5.72,
|
| 1222 |
+
"learning_rate": 5.468483816013628e-05,
|
| 1223 |
+
"loss": 2.2477,
|
| 1224 |
+
"step": 84000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 5.76,
|
| 1228 |
+
"learning_rate": 5.322462886347043e-05,
|
| 1229 |
+
"loss": 2.2257,
|
| 1230 |
+
"step": 84500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 5.79,
|
| 1234 |
+
"learning_rate": 5.176441956680457e-05,
|
| 1235 |
+
"loss": 2.2407,
|
| 1236 |
+
"step": 85000
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 5.79,
|
| 1240 |
+
"eval_gen_len": 14.8097,
|
| 1241 |
+
"eval_loss": 2.4504895210266113,
|
| 1242 |
+
"eval_rouge1": 30.4682,
|
| 1243 |
+
"eval_rouge2": 11.9828,
|
| 1244 |
+
"eval_rougeL": 27.0725,
|
| 1245 |
+
"eval_rougeLsum": 27.3849,
|
| 1246 |
+
"eval_runtime": 526.291,
|
| 1247 |
+
"eval_samples_per_second": 19.005,
|
| 1248 |
+
"eval_steps_per_second": 2.377,
|
| 1249 |
+
"step": 85000
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 5.83,
|
| 1253 |
+
"learning_rate": 5.0304210270138715e-05,
|
| 1254 |
+
"loss": 2.2334,
|
| 1255 |
+
"step": 85500
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 5.86,
|
| 1259 |
+
"learning_rate": 4.884400097347286e-05,
|
| 1260 |
+
"loss": 2.2468,
|
| 1261 |
+
"step": 86000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 5.89,
|
| 1265 |
+
"learning_rate": 4.7383791676807007e-05,
|
| 1266 |
+
"loss": 2.2107,
|
| 1267 |
+
"step": 86500
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 5.93,
|
| 1271 |
+
"learning_rate": 4.592358238014115e-05,
|
| 1272 |
+
"loss": 2.2534,
|
| 1273 |
+
"step": 87000
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 5.96,
|
| 1277 |
+
"learning_rate": 4.44633730834753e-05,
|
| 1278 |
+
"loss": 2.2311,
|
| 1279 |
+
"step": 87500
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 6.0,
|
| 1283 |
+
"learning_rate": 4.300316378680944e-05,
|
| 1284 |
+
"loss": 2.2225,
|
| 1285 |
+
"step": 88000
|
| 1286 |
+
}
|
| 1287 |
+
],
|
| 1288 |
+
"max_steps": 102725,
|
| 1289 |
+
"num_train_epochs": 7,
|
| 1290 |
+
"total_flos": 2.7215384355038822e+17,
|
| 1291 |
+
"trial_name": null,
|
| 1292 |
+
"trial_params": null
|
| 1293 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56f790e94cc86b9db5c3f1689781a8582790cc77570e0499444210aca59c8725
|
| 3 |
+
size 3183
|