Upload 14 files
Browse files- config.json +5 -4
- generation_config.json +2 -1
- merges.txt +1 -1
- optimizer.pt +3 -0
- pytorch_model.bin +2 -2
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +1516 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"_num_labels": 3,
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
|
@@ -26,7 +27,6 @@
|
|
| 26 |
"force_bos_token_to_be_generated": true,
|
| 27 |
"forced_bos_token_id": 0,
|
| 28 |
"forced_eos_token_id": 2,
|
| 29 |
-
"gradient_checkpointing": false,
|
| 30 |
"id2label": {
|
| 31 |
"0": "LABEL_0",
|
| 32 |
"1": "LABEL_1",
|
|
@@ -62,7 +62,8 @@
|
|
| 62 |
"num_beams": 4
|
| 63 |
}
|
| 64 |
},
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
|
|
|
| 68 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "nikhedward/bart-large-cnn-finetuned-multi-news1",
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
|
|
|
| 27 |
"force_bos_token_to_be_generated": true,
|
| 28 |
"forced_bos_token_id": 0,
|
| 29 |
"forced_eos_token_id": 2,
|
|
|
|
| 30 |
"id2label": {
|
| 31 |
"0": "LABEL_0",
|
| 32 |
"1": "LABEL_1",
|
|
|
|
| 62 |
"num_beams": 4
|
| 63 |
}
|
| 64 |
},
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.27.1",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 50265
|
| 69 |
}
|
generation_config.json
CHANGED
|
@@ -12,5 +12,6 @@
|
|
| 12 |
"no_repeat_ngram_size": 3,
|
| 13 |
"num_beams": 4,
|
| 14 |
"pad_token_id": 1,
|
| 15 |
-
"transformers_version": "4.27.
|
|
|
|
| 16 |
}
|
|
|
|
| 12 |
"no_repeat_ngram_size": 3,
|
| 13 |
"num_beams": 4,
|
| 14 |
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.27.1",
|
| 16 |
+
"use_cache": false
|
| 17 |
}
|
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f08460f0dd4c4ad62a2b46b98822306be801197b10115e6050ac6341322a35e
|
| 3 |
+
size 3250632155
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfa352cc81ad4fc8330bc86104609239650a3096514a391f9ab046dbe08a9a93
|
| 3 |
+
size 1625541389
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:710cec529f099b6826b36b9ea98fa88fa40a0029bf7a28e97ab211ad9426371c
|
| 3 |
+
size 14511
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e26ac3fb38d9bbe287b9c8332c9f2cd1e610d6cc1e1d3cdc379d3eed979055bf
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e95123924eb206df4780d644c10776296d4d21af78be6dc44fda55ec57a829f9
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"sep_token": "</s>",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"tokenizer_class": "BartTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 63.1011,
|
| 3 |
+
"best_model_checkpoint": "output_train_bart_large_local/checkpoint-48000",
|
| 4 |
+
"epoch": 2.0123153700647967,
|
| 5 |
+
"global_step": 50000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 3.9842240824211213e-07,
|
| 13 |
+
"loss": 1.8309,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 8.008692852543465e-07,
|
| 19 |
+
"loss": 1.0322,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"eval_bertscore/f1": 0.7264,
|
| 25 |
+
"eval_bertscore/precision": 0.7345,
|
| 26 |
+
"eval_bertscore/recall": 0.7214,
|
| 27 |
+
"eval_mean_prediction_length_characters": 779.505,
|
| 28 |
+
"eval_mean_prediction_length_tokens": 167.969,
|
| 29 |
+
"eval_num_predicted": 1000,
|
| 30 |
+
"eval_rouge/geometric_mean": 45.7604,
|
| 31 |
+
"eval_rouge/rouge1": 60.4328,
|
| 32 |
+
"eval_rouge/rouge2": 39.8155,
|
| 33 |
+
"eval_rouge/rougeL": 39.824,
|
| 34 |
+
"eval_rouge/rougeLsum": 57.577,
|
| 35 |
+
"eval_runtime": 2363.9821,
|
| 36 |
+
"eval_samples_per_second": 0.423,
|
| 37 |
+
"eval_steps_per_second": 0.423,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"learning_rate": 1.203316162266581e-06,
|
| 43 |
+
"loss": 0.8078,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"learning_rate": 1.6057630392788153e-06,
|
| 49 |
+
"loss": 0.7401,
|
| 50 |
+
"step": 2000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16,
|
| 54 |
+
"eval_bertscore/f1": 0.767,
|
| 55 |
+
"eval_bertscore/precision": 0.7735,
|
| 56 |
+
"eval_bertscore/recall": 0.7627,
|
| 57 |
+
"eval_mean_prediction_length_characters": 746.987,
|
| 58 |
+
"eval_mean_prediction_length_tokens": 167.637,
|
| 59 |
+
"eval_num_predicted": 1000,
|
| 60 |
+
"eval_rouge/geometric_mean": 49.7632,
|
| 61 |
+
"eval_rouge/rouge1": 64.5596,
|
| 62 |
+
"eval_rouge/rouge2": 43.5883,
|
| 63 |
+
"eval_rouge/rougeL": 43.7919,
|
| 64 |
+
"eval_rouge/rougeLsum": 62.268,
|
| 65 |
+
"eval_runtime": 2390.2778,
|
| 66 |
+
"eval_samples_per_second": 0.418,
|
| 67 |
+
"eval_steps_per_second": 0.418,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 2.00820991629105e-06,
|
| 73 |
+
"loss": 0.6952,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 2.4106567933032843e-06,
|
| 79 |
+
"loss": 0.6654,
|
| 80 |
+
"step": 3000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.24,
|
| 84 |
+
"eval_bertscore/f1": 0.775,
|
| 85 |
+
"eval_bertscore/precision": 0.7801,
|
| 86 |
+
"eval_bertscore/recall": 0.7719,
|
| 87 |
+
"eval_mean_prediction_length_characters": 750.739,
|
| 88 |
+
"eval_mean_prediction_length_tokens": 167.441,
|
| 89 |
+
"eval_num_predicted": 1000,
|
| 90 |
+
"eval_rouge/geometric_mean": 51.1255,
|
| 91 |
+
"eval_rouge/rouge1": 65.8167,
|
| 92 |
+
"eval_rouge/rouge2": 45.0215,
|
| 93 |
+
"eval_rouge/rougeL": 45.0979,
|
| 94 |
+
"eval_rouge/rougeLsum": 63.4694,
|
| 95 |
+
"eval_runtime": 2400.8698,
|
| 96 |
+
"eval_samples_per_second": 0.417,
|
| 97 |
+
"eval_steps_per_second": 0.417,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.28,
|
| 102 |
+
"learning_rate": 2.8131036703155183e-06,
|
| 103 |
+
"loss": 0.6532,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.32,
|
| 108 |
+
"learning_rate": 3.215550547327753e-06,
|
| 109 |
+
"loss": 0.6421,
|
| 110 |
+
"step": 4000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.32,
|
| 114 |
+
"eval_bertscore/f1": 0.778,
|
| 115 |
+
"eval_bertscore/precision": 0.7803,
|
| 116 |
+
"eval_bertscore/recall": 0.7778,
|
| 117 |
+
"eval_mean_prediction_length_characters": 787.437,
|
| 118 |
+
"eval_mean_prediction_length_tokens": 175.145,
|
| 119 |
+
"eval_num_predicted": 1000,
|
| 120 |
+
"eval_rouge/geometric_mean": 51.6325,
|
| 121 |
+
"eval_rouge/rouge1": 66.6546,
|
| 122 |
+
"eval_rouge/rouge2": 45.5613,
|
| 123 |
+
"eval_rouge/rougeL": 45.3256,
|
| 124 |
+
"eval_rouge/rougeLsum": 64.2944,
|
| 125 |
+
"eval_runtime": 2500.2502,
|
| 126 |
+
"eval_samples_per_second": 0.4,
|
| 127 |
+
"eval_steps_per_second": 0.4,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.36,
|
| 132 |
+
"learning_rate": 3.6179974243399875e-06,
|
| 133 |
+
"loss": 0.6253,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.4,
|
| 138 |
+
"learning_rate": 4.0196394075981975e-06,
|
| 139 |
+
"loss": 0.62,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4,
|
| 144 |
+
"eval_bertscore/f1": 0.7774,
|
| 145 |
+
"eval_bertscore/precision": 0.7652,
|
| 146 |
+
"eval_bertscore/recall": 0.7921,
|
| 147 |
+
"eval_mean_prediction_length_characters": 948.673,
|
| 148 |
+
"eval_mean_prediction_length_tokens": 206.93,
|
| 149 |
+
"eval_num_predicted": 1000,
|
| 150 |
+
"eval_rouge/geometric_mean": 51.4967,
|
| 151 |
+
"eval_rouge/rouge1": 67.0983,
|
| 152 |
+
"eval_rouge/rouge2": 45.6949,
|
| 153 |
+
"eval_rouge/rougeL": 44.541,
|
| 154 |
+
"eval_rouge/rougeLsum": 64.5765,
|
| 155 |
+
"eval_runtime": 2980.0062,
|
| 156 |
+
"eval_samples_per_second": 0.336,
|
| 157 |
+
"eval_steps_per_second": 0.336,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.44,
|
| 162 |
+
"learning_rate": 4.4220862846104314e-06,
|
| 163 |
+
"loss": 0.6041,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.48,
|
| 168 |
+
"learning_rate": 4.824533161622666e-06,
|
| 169 |
+
"loss": 0.5949,
|
| 170 |
+
"step": 6000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.48,
|
| 174 |
+
"eval_bertscore/f1": 0.7803,
|
| 175 |
+
"eval_bertscore/precision": 0.7732,
|
| 176 |
+
"eval_bertscore/recall": 0.7895,
|
| 177 |
+
"eval_mean_prediction_length_characters": 879.72,
|
| 178 |
+
"eval_mean_prediction_length_tokens": 192.817,
|
| 179 |
+
"eval_num_predicted": 1000,
|
| 180 |
+
"eval_rouge/geometric_mean": 52.1495,
|
| 181 |
+
"eval_rouge/rouge1": 67.3707,
|
| 182 |
+
"eval_rouge/rouge2": 46.4072,
|
| 183 |
+
"eval_rouge/rougeL": 45.3622,
|
| 184 |
+
"eval_rouge/rougeLsum": 65.0424,
|
| 185 |
+
"eval_runtime": 2666.0858,
|
| 186 |
+
"eval_samples_per_second": 0.375,
|
| 187 |
+
"eval_steps_per_second": 0.375,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.52,
|
| 192 |
+
"learning_rate": 5.2269800386349e-06,
|
| 193 |
+
"loss": 0.5762,
|
| 194 |
+
"step": 6500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.56,
|
| 198 |
+
"learning_rate": 5.629426915647135e-06,
|
| 199 |
+
"loss": 0.5719,
|
| 200 |
+
"step": 7000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.56,
|
| 204 |
+
"eval_bertscore/f1": 0.7838,
|
| 205 |
+
"eval_bertscore/precision": 0.7832,
|
| 206 |
+
"eval_bertscore/recall": 0.7866,
|
| 207 |
+
"eval_mean_prediction_length_characters": 832.624,
|
| 208 |
+
"eval_mean_prediction_length_tokens": 183.52,
|
| 209 |
+
"eval_num_predicted": 1000,
|
| 210 |
+
"eval_rouge/geometric_mean": 52.9627,
|
| 211 |
+
"eval_rouge/rouge1": 67.8554,
|
| 212 |
+
"eval_rouge/rouge2": 47.0328,
|
| 213 |
+
"eval_rouge/rougeL": 46.5505,
|
| 214 |
+
"eval_rouge/rougeLsum": 65.5148,
|
| 215 |
+
"eval_runtime": 2493.7707,
|
| 216 |
+
"eval_samples_per_second": 0.401,
|
| 217 |
+
"eval_steps_per_second": 0.401,
|
| 218 |
+
"step": 7000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.6,
|
| 222 |
+
"learning_rate": 6.031068898905345e-06,
|
| 223 |
+
"loss": 0.5718,
|
| 224 |
+
"step": 7500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.64,
|
| 228 |
+
"learning_rate": 6.433515775917579e-06,
|
| 229 |
+
"loss": 0.5541,
|
| 230 |
+
"step": 8000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.64,
|
| 234 |
+
"eval_bertscore/f1": 0.7856,
|
| 235 |
+
"eval_bertscore/precision": 0.7835,
|
| 236 |
+
"eval_bertscore/recall": 0.7897,
|
| 237 |
+
"eval_mean_prediction_length_characters": 831.437,
|
| 238 |
+
"eval_mean_prediction_length_tokens": 184.28,
|
| 239 |
+
"eval_num_predicted": 1000,
|
| 240 |
+
"eval_rouge/geometric_mean": 53.234,
|
| 241 |
+
"eval_rouge/rouge1": 68.2648,
|
| 242 |
+
"eval_rouge/rouge2": 47.5788,
|
| 243 |
+
"eval_rouge/rougeL": 46.447,
|
| 244 |
+
"eval_rouge/rougeLsum": 65.9056,
|
| 245 |
+
"eval_runtime": 2476.0861,
|
| 246 |
+
"eval_samples_per_second": 0.404,
|
| 247 |
+
"eval_steps_per_second": 0.404,
|
| 248 |
+
"step": 8000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.68,
|
| 252 |
+
"learning_rate": 6.835962652929814e-06,
|
| 253 |
+
"loss": 0.5621,
|
| 254 |
+
"step": 8500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.72,
|
| 258 |
+
"learning_rate": 7.238409529942049e-06,
|
| 259 |
+
"loss": 0.5509,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.72,
|
| 264 |
+
"eval_bertscore/f1": 0.7876,
|
| 265 |
+
"eval_bertscore/precision": 0.787,
|
| 266 |
+
"eval_bertscore/recall": 0.79,
|
| 267 |
+
"eval_mean_prediction_length_characters": 825.034,
|
| 268 |
+
"eval_mean_prediction_length_tokens": 181.78,
|
| 269 |
+
"eval_num_predicted": 1000,
|
| 270 |
+
"eval_rouge/geometric_mean": 53.6596,
|
| 271 |
+
"eval_rouge/rouge1": 68.4619,
|
| 272 |
+
"eval_rouge/rouge2": 47.9553,
|
| 273 |
+
"eval_rouge/rougeL": 47.0605,
|
| 274 |
+
"eval_rouge/rougeLsum": 66.229,
|
| 275 |
+
"eval_runtime": 2413.4877,
|
| 276 |
+
"eval_samples_per_second": 0.414,
|
| 277 |
+
"eval_steps_per_second": 0.414,
|
| 278 |
+
"step": 9000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.76,
|
| 282 |
+
"learning_rate": 7.640856406954282e-06,
|
| 283 |
+
"loss": 0.5319,
|
| 284 |
+
"step": 9500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.8,
|
| 288 |
+
"learning_rate": 8.042498390212493e-06,
|
| 289 |
+
"loss": 0.5317,
|
| 290 |
+
"step": 10000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.8,
|
| 294 |
+
"eval_bertscore/f1": 0.7801,
|
| 295 |
+
"eval_bertscore/precision": 0.7653,
|
| 296 |
+
"eval_bertscore/recall": 0.7976,
|
| 297 |
+
"eval_mean_prediction_length_characters": 983.333,
|
| 298 |
+
"eval_mean_prediction_length_tokens": 212.132,
|
| 299 |
+
"eval_num_predicted": 1000,
|
| 300 |
+
"eval_rouge/geometric_mean": 52.2204,
|
| 301 |
+
"eval_rouge/rouge1": 67.4114,
|
| 302 |
+
"eval_rouge/rouge2": 46.8366,
|
| 303 |
+
"eval_rouge/rougeL": 45.1025,
|
| 304 |
+
"eval_rouge/rougeLsum": 64.9737,
|
| 305 |
+
"eval_runtime": 2850.8965,
|
| 306 |
+
"eval_samples_per_second": 0.351,
|
| 307 |
+
"eval_steps_per_second": 0.351,
|
| 308 |
+
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.85,
|
| 312 |
+
"learning_rate": 8.444945267224727e-06,
|
| 313 |
+
"loss": 0.5246,
|
| 314 |
+
"step": 10500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.89,
|
| 318 |
+
"learning_rate": 8.847392144236962e-06,
|
| 319 |
+
"loss": 0.5306,
|
| 320 |
+
"step": 11000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.89,
|
| 324 |
+
"eval_bertscore/f1": 0.7812,
|
| 325 |
+
"eval_bertscore/precision": 0.7727,
|
| 326 |
+
"eval_bertscore/recall": 0.7923,
|
| 327 |
+
"eval_mean_prediction_length_characters": 929.756,
|
| 328 |
+
"eval_mean_prediction_length_tokens": 198.992,
|
| 329 |
+
"eval_num_predicted": 1000,
|
| 330 |
+
"eval_rouge/geometric_mean": 52.9021,
|
| 331 |
+
"eval_rouge/rouge1": 67.7205,
|
| 332 |
+
"eval_rouge/rouge2": 47.5736,
|
| 333 |
+
"eval_rouge/rougeL": 45.955,
|
| 334 |
+
"eval_rouge/rougeLsum": 65.2918,
|
| 335 |
+
"eval_runtime": 2641.4953,
|
| 336 |
+
"eval_samples_per_second": 0.379,
|
| 337 |
+
"eval_steps_per_second": 0.379,
|
| 338 |
+
"step": 11000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.93,
|
| 342 |
+
"learning_rate": 9.249839021249196e-06,
|
| 343 |
+
"loss": 0.5118,
|
| 344 |
+
"step": 11500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.97,
|
| 348 |
+
"learning_rate": 9.65228589826143e-06,
|
| 349 |
+
"loss": 0.5125,
|
| 350 |
+
"step": 12000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.97,
|
| 354 |
+
"eval_bertscore/f1": 0.7924,
|
| 355 |
+
"eval_bertscore/precision": 0.8025,
|
| 356 |
+
"eval_bertscore/recall": 0.7847,
|
| 357 |
+
"eval_mean_prediction_length_characters": 739.515,
|
| 358 |
+
"eval_mean_prediction_length_tokens": 166.617,
|
| 359 |
+
"eval_num_predicted": 1000,
|
| 360 |
+
"eval_rouge/geometric_mean": 54.3827,
|
| 361 |
+
"eval_rouge/rouge1": 68.5657,
|
| 362 |
+
"eval_rouge/rouge2": 48.8496,
|
| 363 |
+
"eval_rouge/rougeL": 48.0192,
|
| 364 |
+
"eval_rouge/rougeLsum": 66.6464,
|
| 365 |
+
"eval_runtime": 2173.7087,
|
| 366 |
+
"eval_samples_per_second": 0.46,
|
| 367 |
+
"eval_steps_per_second": 0.46,
|
| 368 |
+
"step": 12000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.01,
|
| 372 |
+
"learning_rate": 9.993918580525149e-06,
|
| 373 |
+
"loss": 0.4953,
|
| 374 |
+
"step": 12500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.05,
|
| 378 |
+
"learning_rate": 9.949202260857123e-06,
|
| 379 |
+
"loss": 0.4559,
|
| 380 |
+
"step": 13000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.05,
|
| 384 |
+
"eval_bertscore/f1": 0.7876,
|
| 385 |
+
"eval_bertscore/precision": 0.782,
|
| 386 |
+
"eval_bertscore/recall": 0.7953,
|
| 387 |
+
"eval_mean_prediction_length_characters": 872.104,
|
| 388 |
+
"eval_mean_prediction_length_tokens": 188.836,
|
| 389 |
+
"eval_num_predicted": 1000,
|
| 390 |
+
"eval_rouge/geometric_mean": 54.0286,
|
| 391 |
+
"eval_rouge/rouge1": 68.9929,
|
| 392 |
+
"eval_rouge/rouge2": 48.683,
|
| 393 |
+
"eval_rouge/rougeL": 46.9557,
|
| 394 |
+
"eval_rouge/rougeLsum": 66.5892,
|
| 395 |
+
"eval_runtime": 2531.5352,
|
| 396 |
+
"eval_samples_per_second": 0.395,
|
| 397 |
+
"eval_steps_per_second": 0.395,
|
| 398 |
+
"step": 13000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.09,
|
| 402 |
+
"learning_rate": 9.904575373828433e-06,
|
| 403 |
+
"loss": 0.4572,
|
| 404 |
+
"step": 13500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.13,
|
| 408 |
+
"learning_rate": 9.859859054160406e-06,
|
| 409 |
+
"loss": 0.4455,
|
| 410 |
+
"step": 14000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.13,
|
| 414 |
+
"eval_bertscore/f1": 0.792,
|
| 415 |
+
"eval_bertscore/precision": 0.7832,
|
| 416 |
+
"eval_bertscore/recall": 0.8031,
|
| 417 |
+
"eval_mean_prediction_length_characters": 921.871,
|
| 418 |
+
"eval_mean_prediction_length_tokens": 200.026,
|
| 419 |
+
"eval_num_predicted": 1000,
|
| 420 |
+
"eval_rouge/geometric_mean": 54.5933,
|
| 421 |
+
"eval_rouge/rouge1": 69.3876,
|
| 422 |
+
"eval_rouge/rouge2": 49.1971,
|
| 423 |
+
"eval_rouge/rougeL": 47.6645,
|
| 424 |
+
"eval_rouge/rougeLsum": 67.1636,
|
| 425 |
+
"eval_runtime": 2729.0713,
|
| 426 |
+
"eval_samples_per_second": 0.366,
|
| 427 |
+
"eval_steps_per_second": 0.366,
|
| 428 |
+
"step": 14000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.17,
|
| 432 |
+
"learning_rate": 9.81514273449238e-06,
|
| 433 |
+
"loss": 0.446,
|
| 434 |
+
"step": 14500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.21,
|
| 438 |
+
"learning_rate": 9.770426414824355e-06,
|
| 439 |
+
"loss": 0.4376,
|
| 440 |
+
"step": 15000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.21,
|
| 444 |
+
"eval_bertscore/f1": 0.7943,
|
| 445 |
+
"eval_bertscore/precision": 0.7909,
|
| 446 |
+
"eval_bertscore/recall": 0.7996,
|
| 447 |
+
"eval_mean_prediction_length_characters": 856.751,
|
| 448 |
+
"eval_mean_prediction_length_tokens": 186.271,
|
| 449 |
+
"eval_num_predicted": 1000,
|
| 450 |
+
"eval_rouge/geometric_mean": 55.0336,
|
| 451 |
+
"eval_rouge/rouge1": 69.6177,
|
| 452 |
+
"eval_rouge/rouge2": 49.6842,
|
| 453 |
+
"eval_rouge/rougeL": 48.1889,
|
| 454 |
+
"eval_rouge/rougeLsum": 67.4597,
|
| 455 |
+
"eval_runtime": 2554.3498,
|
| 456 |
+
"eval_samples_per_second": 0.391,
|
| 457 |
+
"eval_steps_per_second": 0.391,
|
| 458 |
+
"step": 15000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.25,
|
| 462 |
+
"learning_rate": 9.725710095156328e-06,
|
| 463 |
+
"loss": 0.4338,
|
| 464 |
+
"step": 15500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.29,
|
| 468 |
+
"learning_rate": 9.680993775488303e-06,
|
| 469 |
+
"loss": 0.4333,
|
| 470 |
+
"step": 16000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.29,
|
| 474 |
+
"eval_bertscore/f1": 0.7941,
|
| 475 |
+
"eval_bertscore/precision": 0.7901,
|
| 476 |
+
"eval_bertscore/recall": 0.8003,
|
| 477 |
+
"eval_mean_prediction_length_characters": 857.762,
|
| 478 |
+
"eval_mean_prediction_length_tokens": 185.042,
|
| 479 |
+
"eval_num_predicted": 1000,
|
| 480 |
+
"eval_rouge/geometric_mean": 55.3969,
|
| 481 |
+
"eval_rouge/rouge1": 69.5818,
|
| 482 |
+
"eval_rouge/rouge2": 50.0439,
|
| 483 |
+
"eval_rouge/rougeL": 48.8213,
|
| 484 |
+
"eval_rouge/rougeLsum": 67.3532,
|
| 485 |
+
"eval_runtime": 2568.5908,
|
| 486 |
+
"eval_samples_per_second": 0.389,
|
| 487 |
+
"eval_steps_per_second": 0.389,
|
| 488 |
+
"step": 16000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.33,
|
| 492 |
+
"learning_rate": 9.636366888459613e-06,
|
| 493 |
+
"loss": 0.4224,
|
| 494 |
+
"step": 16500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.37,
|
| 498 |
+
"learning_rate": 9.591650568791587e-06,
|
| 499 |
+
"loss": 0.4229,
|
| 500 |
+
"step": 17000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.37,
|
| 504 |
+
"eval_bertscore/f1": 0.7968,
|
| 505 |
+
"eval_bertscore/precision": 0.7936,
|
| 506 |
+
"eval_bertscore/recall": 0.802,
|
| 507 |
+
"eval_mean_prediction_length_characters": 850.064,
|
| 508 |
+
"eval_mean_prediction_length_tokens": 186.438,
|
| 509 |
+
"eval_num_predicted": 1000,
|
| 510 |
+
"eval_rouge/geometric_mean": 56.2479,
|
| 511 |
+
"eval_rouge/rouge1": 70.2657,
|
| 512 |
+
"eval_rouge/rouge2": 50.9461,
|
| 513 |
+
"eval_rouge/rougeL": 49.7123,
|
| 514 |
+
"eval_rouge/rougeLsum": 68.1758,
|
| 515 |
+
"eval_runtime": 2596.5556,
|
| 516 |
+
"eval_samples_per_second": 0.385,
|
| 517 |
+
"eval_steps_per_second": 0.385,
|
| 518 |
+
"step": 17000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.41,
|
| 522 |
+
"learning_rate": 9.54693424912356e-06,
|
| 523 |
+
"loss": 0.4215,
|
| 524 |
+
"step": 17500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.45,
|
| 528 |
+
"learning_rate": 9.502217929455535e-06,
|
| 529 |
+
"loss": 0.4145,
|
| 530 |
+
"step": 18000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.45,
|
| 534 |
+
"eval_bertscore/f1": 0.7982,
|
| 535 |
+
"eval_bertscore/precision": 0.7974,
|
| 536 |
+
"eval_bertscore/recall": 0.801,
|
| 537 |
+
"eval_mean_prediction_length_characters": 821.211,
|
| 538 |
+
"eval_mean_prediction_length_tokens": 179.198,
|
| 539 |
+
"eval_num_predicted": 1000,
|
| 540 |
+
"eval_rouge/geometric_mean": 56.2997,
|
| 541 |
+
"eval_rouge/rouge1": 70.2035,
|
| 542 |
+
"eval_rouge/rouge2": 51.1438,
|
| 543 |
+
"eval_rouge/rougeL": 49.7011,
|
| 544 |
+
"eval_rouge/rougeLsum": 68.1054,
|
| 545 |
+
"eval_runtime": 2500.5637,
|
| 546 |
+
"eval_samples_per_second": 0.4,
|
| 547 |
+
"eval_steps_per_second": 0.4,
|
| 548 |
+
"step": 18000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.49,
|
| 552 |
+
"learning_rate": 9.457501609787508e-06,
|
| 553 |
+
"loss": 0.4108,
|
| 554 |
+
"step": 18500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.53,
|
| 558 |
+
"learning_rate": 9.41287472275882e-06,
|
| 559 |
+
"loss": 0.413,
|
| 560 |
+
"step": 19000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.53,
|
| 564 |
+
"eval_bertscore/f1": 0.7981,
|
| 565 |
+
"eval_bertscore/precision": 0.7992,
|
| 566 |
+
"eval_bertscore/recall": 0.799,
|
| 567 |
+
"eval_mean_prediction_length_characters": 806.834,
|
| 568 |
+
"eval_mean_prediction_length_tokens": 176.24,
|
| 569 |
+
"eval_num_predicted": 1000,
|
| 570 |
+
"eval_rouge/geometric_mean": 56.5708,
|
| 571 |
+
"eval_rouge/rouge1": 70.2439,
|
| 572 |
+
"eval_rouge/rouge2": 51.4876,
|
| 573 |
+
"eval_rouge/rougeL": 50.0572,
|
| 574 |
+
"eval_rouge/rougeLsum": 68.1941,
|
| 575 |
+
"eval_runtime": 2443.1073,
|
| 576 |
+
"eval_samples_per_second": 0.409,
|
| 577 |
+
"eval_steps_per_second": 0.409,
|
| 578 |
+
"step": 19000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.57,
|
| 582 |
+
"learning_rate": 9.368158403090792e-06,
|
| 583 |
+
"loss": 0.4064,
|
| 584 |
+
"step": 19500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.61,
|
| 588 |
+
"learning_rate": 9.323442083422767e-06,
|
| 589 |
+
"loss": 0.4004,
|
| 590 |
+
"step": 20000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.61,
|
| 594 |
+
"eval_bertscore/f1": 0.8022,
|
| 595 |
+
"eval_bertscore/precision": 0.7971,
|
| 596 |
+
"eval_bertscore/recall": 0.8093,
|
| 597 |
+
"eval_mean_prediction_length_characters": 860.077,
|
| 598 |
+
"eval_mean_prediction_length_tokens": 188.397,
|
| 599 |
+
"eval_num_predicted": 1000,
|
| 600 |
+
"eval_rouge/geometric_mean": 57.2862,
|
| 601 |
+
"eval_rouge/rouge1": 71.0513,
|
| 602 |
+
"eval_rouge/rouge2": 52.0715,
|
| 603 |
+
"eval_rouge/rougeL": 50.8134,
|
| 604 |
+
"eval_rouge/rougeLsum": 69.0639,
|
| 605 |
+
"eval_runtime": 2596.2685,
|
| 606 |
+
"eval_samples_per_second": 0.385,
|
| 607 |
+
"eval_steps_per_second": 0.385,
|
| 608 |
+
"step": 20000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.65,
|
| 612 |
+
"learning_rate": 9.278725763754741e-06,
|
| 613 |
+
"loss": 0.3953,
|
| 614 |
+
"step": 20500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.69,
|
| 618 |
+
"learning_rate": 9.234009444086714e-06,
|
| 619 |
+
"loss": 0.3905,
|
| 620 |
+
"step": 21000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.69,
|
| 624 |
+
"eval_bertscore/f1": 0.8009,
|
| 625 |
+
"eval_bertscore/precision": 0.792,
|
| 626 |
+
"eval_bertscore/recall": 0.812,
|
| 627 |
+
"eval_mean_prediction_length_characters": 922.278,
|
| 628 |
+
"eval_mean_prediction_length_tokens": 199.619,
|
| 629 |
+
"eval_num_predicted": 1000,
|
| 630 |
+
"eval_rouge/geometric_mean": 56.8514,
|
| 631 |
+
"eval_rouge/rouge1": 70.8436,
|
| 632 |
+
"eval_rouge/rouge2": 51.8156,
|
| 633 |
+
"eval_rouge/rougeL": 50.0567,
|
| 634 |
+
"eval_rouge/rougeLsum": 68.8517,
|
| 635 |
+
"eval_runtime": 2741.6372,
|
| 636 |
+
"eval_samples_per_second": 0.365,
|
| 637 |
+
"eval_steps_per_second": 0.365,
|
| 638 |
+
"step": 21000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.73,
|
| 642 |
+
"learning_rate": 9.189382557058024e-06,
|
| 643 |
+
"loss": 0.3834,
|
| 644 |
+
"step": 21500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.77,
|
| 648 |
+
"learning_rate": 9.144666237389999e-06,
|
| 649 |
+
"loss": 0.3772,
|
| 650 |
+
"step": 22000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.77,
|
| 654 |
+
"eval_bertscore/f1": 0.802,
|
| 655 |
+
"eval_bertscore/precision": 0.8014,
|
| 656 |
+
"eval_bertscore/recall": 0.8048,
|
| 657 |
+
"eval_mean_prediction_length_characters": 821.195,
|
| 658 |
+
"eval_mean_prediction_length_tokens": 179.279,
|
| 659 |
+
"eval_num_predicted": 1000,
|
| 660 |
+
"eval_rouge/geometric_mean": 57.3719,
|
| 661 |
+
"eval_rouge/rouge1": 70.4754,
|
| 662 |
+
"eval_rouge/rouge2": 52.2981,
|
| 663 |
+
"eval_rouge/rougeL": 51.2358,
|
| 664 |
+
"eval_rouge/rougeLsum": 68.5129,
|
| 665 |
+
"eval_runtime": 2484.708,
|
| 666 |
+
"eval_samples_per_second": 0.402,
|
| 667 |
+
"eval_steps_per_second": 0.402,
|
| 668 |
+
"step": 22000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.81,
|
| 672 |
+
"learning_rate": 9.099949917721973e-06,
|
| 673 |
+
"loss": 0.3796,
|
| 674 |
+
"step": 22500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.85,
|
| 678 |
+
"learning_rate": 9.055233598053946e-06,
|
| 679 |
+
"loss": 0.3745,
|
| 680 |
+
"step": 23000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.85,
|
| 684 |
+
"eval_bertscore/f1": 0.8077,
|
| 685 |
+
"eval_bertscore/precision": 0.8096,
|
| 686 |
+
"eval_bertscore/recall": 0.8076,
|
| 687 |
+
"eval_mean_prediction_length_characters": 797.37,
|
| 688 |
+
"eval_mean_prediction_length_tokens": 176.263,
|
| 689 |
+
"eval_num_predicted": 1000,
|
| 690 |
+
"eval_rouge/geometric_mean": 58.2667,
|
| 691 |
+
"eval_rouge/rouge1": 71.7377,
|
| 692 |
+
"eval_rouge/rouge2": 53.2732,
|
| 693 |
+
"eval_rouge/rougeL": 51.7614,
|
| 694 |
+
"eval_rouge/rougeLsum": 69.9972,
|
| 695 |
+
"eval_runtime": 2452.4348,
|
| 696 |
+
"eval_samples_per_second": 0.408,
|
| 697 |
+
"eval_steps_per_second": 0.408,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.89,
|
| 702 |
+
"learning_rate": 9.01051727838592e-06,
|
| 703 |
+
"loss": 0.3705,
|
| 704 |
+
"step": 23500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.93,
|
| 708 |
+
"learning_rate": 8.96589039135723e-06,
|
| 709 |
+
"loss": 0.3709,
|
| 710 |
+
"step": 24000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.93,
|
| 714 |
+
"eval_bertscore/f1": 0.8108,
|
| 715 |
+
"eval_bertscore/precision": 0.8141,
|
| 716 |
+
"eval_bertscore/recall": 0.8094,
|
| 717 |
+
"eval_mean_prediction_length_characters": 798.81,
|
| 718 |
+
"eval_mean_prediction_length_tokens": 176.217,
|
| 719 |
+
"eval_num_predicted": 1000,
|
| 720 |
+
"eval_rouge/geometric_mean": 58.6206,
|
| 721 |
+
"eval_rouge/rouge1": 72.0193,
|
| 722 |
+
"eval_rouge/rouge2": 53.6884,
|
| 723 |
+
"eval_rouge/rougeL": 52.098,
|
| 724 |
+
"eval_rouge/rougeLsum": 70.3419,
|
| 725 |
+
"eval_runtime": 2449.0615,
|
| 726 |
+
"eval_samples_per_second": 0.408,
|
| 727 |
+
"eval_steps_per_second": 0.408,
|
| 728 |
+
"step": 24000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.97,
|
| 732 |
+
"learning_rate": 8.92126350432854e-06,
|
| 733 |
+
"loss": 0.3638,
|
| 734 |
+
"step": 24500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.01,
|
| 738 |
+
"learning_rate": 8.876547184660515e-06,
|
| 739 |
+
"loss": 0.3461,
|
| 740 |
+
"step": 25000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.01,
|
| 744 |
+
"eval_bertscore/f1": 0.8092,
|
| 745 |
+
"eval_bertscore/precision": 0.8022,
|
| 746 |
+
"eval_bertscore/recall": 0.8182,
|
| 747 |
+
"eval_mean_prediction_length_characters": 891.59,
|
| 748 |
+
"eval_mean_prediction_length_tokens": 193.579,
|
| 749 |
+
"eval_num_predicted": 1000,
|
| 750 |
+
"eval_rouge/geometric_mean": 58.5159,
|
| 751 |
+
"eval_rouge/rouge1": 72.4344,
|
| 752 |
+
"eval_rouge/rouge2": 54.0016,
|
| 753 |
+
"eval_rouge/rougeL": 51.2235,
|
| 754 |
+
"eval_rouge/rougeLsum": 70.5176,
|
| 755 |
+
"eval_runtime": 2696.2641,
|
| 756 |
+
"eval_samples_per_second": 0.371,
|
| 757 |
+
"eval_steps_per_second": 0.371,
|
| 758 |
+
"step": 25000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.05,
|
| 762 |
+
"learning_rate": 8.83183086499249e-06,
|
| 763 |
+
"loss": 0.2926,
|
| 764 |
+
"step": 25500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.09,
|
| 768 |
+
"learning_rate": 8.787114545324463e-06,
|
| 769 |
+
"loss": 0.2935,
|
| 770 |
+
"step": 26000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.09,
|
| 774 |
+
"eval_bertscore/f1": 0.8099,
|
| 775 |
+
"eval_bertscore/precision": 0.806,
|
| 776 |
+
"eval_bertscore/recall": 0.8158,
|
| 777 |
+
"eval_mean_prediction_length_characters": 858.323,
|
| 778 |
+
"eval_mean_prediction_length_tokens": 186.494,
|
| 779 |
+
"eval_num_predicted": 1000,
|
| 780 |
+
"eval_rouge/geometric_mean": 59.0206,
|
| 781 |
+
"eval_rouge/rouge1": 72.3233,
|
| 782 |
+
"eval_rouge/rouge2": 54.4823,
|
| 783 |
+
"eval_rouge/rougeL": 52.1769,
|
| 784 |
+
"eval_rouge/rougeLsum": 70.5191,
|
| 785 |
+
"eval_runtime": 2616.4872,
|
| 786 |
+
"eval_samples_per_second": 0.382,
|
| 787 |
+
"eval_steps_per_second": 0.382,
|
| 788 |
+
"step": 26000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.13,
|
| 792 |
+
"learning_rate": 8.742398225656437e-06,
|
| 793 |
+
"loss": 0.2945,
|
| 794 |
+
"step": 26500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.17,
|
| 798 |
+
"learning_rate": 8.69768190598841e-06,
|
| 799 |
+
"loss": 0.2859,
|
| 800 |
+
"step": 27000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.17,
|
| 804 |
+
"eval_bertscore/f1": 0.8021,
|
| 805 |
+
"eval_bertscore/precision": 0.7967,
|
| 806 |
+
"eval_bertscore/recall": 0.8098,
|
| 807 |
+
"eval_mean_prediction_length_characters": 862.623,
|
| 808 |
+
"eval_mean_prediction_length_tokens": 187.108,
|
| 809 |
+
"eval_num_predicted": 1000,
|
| 810 |
+
"eval_rouge/geometric_mean": 58.0972,
|
| 811 |
+
"eval_rouge/rouge1": 71.3169,
|
| 812 |
+
"eval_rouge/rouge2": 53.5502,
|
| 813 |
+
"eval_rouge/rougeL": 51.3466,
|
| 814 |
+
"eval_rouge/rougeLsum": 69.328,
|
| 815 |
+
"eval_runtime": 2591.3634,
|
| 816 |
+
"eval_samples_per_second": 0.386,
|
| 817 |
+
"eval_steps_per_second": 0.386,
|
| 818 |
+
"step": 27000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.21,
|
| 822 |
+
"learning_rate": 8.65305501895972e-06,
|
| 823 |
+
"loss": 0.2913,
|
| 824 |
+
"step": 27500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.25,
|
| 828 |
+
"learning_rate": 8.608338699291695e-06,
|
| 829 |
+
"loss": 0.2871,
|
| 830 |
+
"step": 28000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.25,
|
| 834 |
+
"eval_bertscore/f1": 0.8125,
|
| 835 |
+
"eval_bertscore/precision": 0.81,
|
| 836 |
+
"eval_bertscore/recall": 0.8167,
|
| 837 |
+
"eval_mean_prediction_length_characters": 839.348,
|
| 838 |
+
"eval_mean_prediction_length_tokens": 182.08,
|
| 839 |
+
"eval_num_predicted": 1000,
|
| 840 |
+
"eval_rouge/geometric_mean": 59.5943,
|
| 841 |
+
"eval_rouge/rouge1": 72.7757,
|
| 842 |
+
"eval_rouge/rouge2": 55.0591,
|
| 843 |
+
"eval_rouge/rougeL": 52.82,
|
| 844 |
+
"eval_rouge/rougeLsum": 70.9482,
|
| 845 |
+
"eval_runtime": 2411.5587,
|
| 846 |
+
"eval_samples_per_second": 0.415,
|
| 847 |
+
"eval_steps_per_second": 0.415,
|
| 848 |
+
"step": 28000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.29,
|
| 852 |
+
"learning_rate": 8.563622379623669e-06,
|
| 853 |
+
"loss": 0.2858,
|
| 854 |
+
"step": 28500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.33,
|
| 858 |
+
"learning_rate": 8.518906059955642e-06,
|
| 859 |
+
"loss": 0.2849,
|
| 860 |
+
"step": 29000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.33,
|
| 864 |
+
"eval_bertscore/f1": 0.8151,
|
| 865 |
+
"eval_bertscore/precision": 0.8177,
|
| 866 |
+
"eval_bertscore/recall": 0.8143,
|
| 867 |
+
"eval_mean_prediction_length_characters": 801.734,
|
| 868 |
+
"eval_mean_prediction_length_tokens": 175.958,
|
| 869 |
+
"eval_num_predicted": 1000,
|
| 870 |
+
"eval_rouge/geometric_mean": 60.3823,
|
| 871 |
+
"eval_rouge/rouge1": 73.1311,
|
| 872 |
+
"eval_rouge/rouge2": 56.0185,
|
| 873 |
+
"eval_rouge/rougeL": 53.7397,
|
| 874 |
+
"eval_rouge/rougeLsum": 71.4246,
|
| 875 |
+
"eval_runtime": 2330.5152,
|
| 876 |
+
"eval_samples_per_second": 0.429,
|
| 877 |
+
"eval_steps_per_second": 0.429,
|
| 878 |
+
"step": 29000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.37,
|
| 882 |
+
"learning_rate": 8.474189740287617e-06,
|
| 883 |
+
"loss": 0.2787,
|
| 884 |
+
"step": 29500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.41,
|
| 888 |
+
"learning_rate": 8.429473420619591e-06,
|
| 889 |
+
"loss": 0.2819,
|
| 890 |
+
"step": 30000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.41,
|
| 894 |
+
"eval_bertscore/f1": 0.8142,
|
| 895 |
+
"eval_bertscore/precision": 0.8077,
|
| 896 |
+
"eval_bertscore/recall": 0.8228,
|
| 897 |
+
"eval_mean_prediction_length_characters": 894.063,
|
| 898 |
+
"eval_mean_prediction_length_tokens": 192.74,
|
| 899 |
+
"eval_num_predicted": 1000,
|
| 900 |
+
"eval_rouge/geometric_mean": 60.1592,
|
| 901 |
+
"eval_rouge/rouge1": 73.1791,
|
| 902 |
+
"eval_rouge/rouge2": 55.8507,
|
| 903 |
+
"eval_rouge/rougeL": 53.2711,
|
| 904 |
+
"eval_rouge/rougeLsum": 71.4419,
|
| 905 |
+
"eval_runtime": 2537.8153,
|
| 906 |
+
"eval_samples_per_second": 0.394,
|
| 907 |
+
"eval_steps_per_second": 0.394,
|
| 908 |
+
"step": 30000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.45,
|
| 912 |
+
"learning_rate": 8.384757100951564e-06,
|
| 913 |
+
"loss": 0.2799,
|
| 914 |
+
"step": 30500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.5,
|
| 918 |
+
"learning_rate": 8.340040781283539e-06,
|
| 919 |
+
"loss": 0.2776,
|
| 920 |
+
"step": 31000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.5,
|
| 924 |
+
"eval_bertscore/f1": 0.8054,
|
| 925 |
+
"eval_bertscore/precision": 0.7925,
|
| 926 |
+
"eval_bertscore/recall": 0.821,
|
| 927 |
+
"eval_mean_prediction_length_characters": 967.121,
|
| 928 |
+
"eval_mean_prediction_length_tokens": 206.944,
|
| 929 |
+
"eval_num_predicted": 1000,
|
| 930 |
+
"eval_rouge/geometric_mean": 58.7521,
|
| 931 |
+
"eval_rouge/rouge1": 71.9074,
|
| 932 |
+
"eval_rouge/rouge2": 54.5099,
|
| 933 |
+
"eval_rouge/rougeL": 51.7393,
|
| 934 |
+
"eval_rouge/rougeLsum": 69.9728,
|
| 935 |
+
"eval_runtime": 2713.6577,
|
| 936 |
+
"eval_samples_per_second": 0.369,
|
| 937 |
+
"eval_steps_per_second": 0.369,
|
| 938 |
+
"step": 31000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.54,
|
| 942 |
+
"learning_rate": 8.295413894254849e-06,
|
| 943 |
+
"loss": 0.2761,
|
| 944 |
+
"step": 31500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 2.58,
|
| 948 |
+
"learning_rate": 8.250697574586823e-06,
|
| 949 |
+
"loss": 0.2742,
|
| 950 |
+
"step": 32000
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.58,
|
| 954 |
+
"eval_bertscore/f1": 0.8187,
|
| 955 |
+
"eval_bertscore/precision": 0.8125,
|
| 956 |
+
"eval_bertscore/recall": 0.827,
|
| 957 |
+
"eval_mean_prediction_length_characters": 880.74,
|
| 958 |
+
"eval_mean_prediction_length_tokens": 191.221,
|
| 959 |
+
"eval_num_predicted": 1000,
|
| 960 |
+
"eval_rouge/geometric_mean": 60.9358,
|
| 961 |
+
"eval_rouge/rouge1": 73.8216,
|
| 962 |
+
"eval_rouge/rouge2": 56.8015,
|
| 963 |
+
"eval_rouge/rougeL": 53.9603,
|
| 964 |
+
"eval_rouge/rougeLsum": 72.1193,
|
| 965 |
+
"eval_runtime": 2491.9164,
|
| 966 |
+
"eval_samples_per_second": 0.401,
|
| 967 |
+
"eval_steps_per_second": 0.401,
|
| 968 |
+
"step": 32000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.62,
|
| 972 |
+
"learning_rate": 8.205981254918796e-06,
|
| 973 |
+
"loss": 0.2737,
|
| 974 |
+
"step": 32500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.66,
|
| 978 |
+
"learning_rate": 8.16126493525077e-06,
|
| 979 |
+
"loss": 0.2663,
|
| 980 |
+
"step": 33000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.66,
|
| 984 |
+
"eval_bertscore/f1": 0.8215,
|
| 985 |
+
"eval_bertscore/precision": 0.8174,
|
| 986 |
+
"eval_bertscore/recall": 0.8272,
|
| 987 |
+
"eval_mean_prediction_length_characters": 862.393,
|
| 988 |
+
"eval_mean_prediction_length_tokens": 187.552,
|
| 989 |
+
"eval_num_predicted": 1000,
|
| 990 |
+
"eval_rouge/geometric_mean": 61.7551,
|
| 991 |
+
"eval_rouge/rouge1": 74.5811,
|
| 992 |
+
"eval_rouge/rouge2": 57.6565,
|
| 993 |
+
"eval_rouge/rougeL": 54.7699,
|
| 994 |
+
"eval_rouge/rougeLsum": 72.9841,
|
| 995 |
+
"eval_runtime": 2430.2491,
|
| 996 |
+
"eval_samples_per_second": 0.411,
|
| 997 |
+
"eval_steps_per_second": 0.411,
|
| 998 |
+
"step": 33000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.7,
|
| 1002 |
+
"learning_rate": 8.116548615582743e-06,
|
| 1003 |
+
"loss": 0.2636,
|
| 1004 |
+
"step": 33500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.74,
|
| 1008 |
+
"learning_rate": 8.071921728554053e-06,
|
| 1009 |
+
"loss": 0.2672,
|
| 1010 |
+
"step": 34000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.74,
|
| 1014 |
+
"eval_bertscore/f1": 0.8194,
|
| 1015 |
+
"eval_bertscore/precision": 0.8133,
|
| 1016 |
+
"eval_bertscore/recall": 0.8274,
|
| 1017 |
+
"eval_mean_prediction_length_characters": 893.688,
|
| 1018 |
+
"eval_mean_prediction_length_tokens": 193.593,
|
| 1019 |
+
"eval_num_predicted": 1000,
|
| 1020 |
+
"eval_rouge/geometric_mean": 61.3651,
|
| 1021 |
+
"eval_rouge/rouge1": 74.2269,
|
| 1022 |
+
"eval_rouge/rouge2": 57.4497,
|
| 1023 |
+
"eval_rouge/rougeL": 54.1897,
|
| 1024 |
+
"eval_rouge/rougeLsum": 72.5834,
|
| 1025 |
+
"eval_runtime": 2499.9317,
|
| 1026 |
+
"eval_samples_per_second": 0.4,
|
| 1027 |
+
"eval_steps_per_second": 0.4,
|
| 1028 |
+
"step": 34000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.39,
|
| 1032 |
+
"learning_rate": 9.569096202090125e-06,
|
| 1033 |
+
"loss": 0.2366,
|
| 1034 |
+
"step": 34500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.41,
|
| 1038 |
+
"learning_rate": 9.54673714242274e-06,
|
| 1039 |
+
"loss": 0.2405,
|
| 1040 |
+
"step": 35000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.41,
|
| 1044 |
+
"eval_bertscore/f1": 0.8145,
|
| 1045 |
+
"eval_bertscore/precision": 0.8054,
|
| 1046 |
+
"eval_bertscore/recall": 0.8256,
|
| 1047 |
+
"eval_mean_prediction_length_characters": 927.422,
|
| 1048 |
+
"eval_mean_prediction_length_tokens": 200.478,
|
| 1049 |
+
"eval_num_predicted": 1000,
|
| 1050 |
+
"eval_rouge/geometric_mean": 60.0655,
|
| 1051 |
+
"eval_rouge/rouge1": 73.2741,
|
| 1052 |
+
"eval_rouge/rouge2": 55.8854,
|
| 1053 |
+
"eval_rouge/rougeL": 52.9208,
|
| 1054 |
+
"eval_rouge/rougeLsum": 71.6192,
|
| 1055 |
+
"eval_runtime": 2620.9045,
|
| 1056 |
+
"eval_samples_per_second": 0.382,
|
| 1057 |
+
"eval_steps_per_second": 0.382,
|
| 1058 |
+
"step": 35000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.43,
|
| 1062 |
+
"learning_rate": 9.524378082755352e-06,
|
| 1063 |
+
"loss": 0.2489,
|
| 1064 |
+
"step": 35500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.45,
|
| 1068 |
+
"learning_rate": 9.502019023087967e-06,
|
| 1069 |
+
"loss": 0.2428,
|
| 1070 |
+
"step": 36000
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.45,
|
| 1074 |
+
"eval_bertscore/f1": 0.8171,
|
| 1075 |
+
"eval_bertscore/precision": 0.8136,
|
| 1076 |
+
"eval_bertscore/recall": 0.8226,
|
| 1077 |
+
"eval_mean_prediction_length_characters": 847.398,
|
| 1078 |
+
"eval_mean_prediction_length_tokens": 183.753,
|
| 1079 |
+
"eval_num_predicted": 1000,
|
| 1080 |
+
"eval_rouge/geometric_mean": 60.8081,
|
| 1081 |
+
"eval_rouge/rouge1": 73.4983,
|
| 1082 |
+
"eval_rouge/rouge2": 56.5892,
|
| 1083 |
+
"eval_rouge/rougeL": 54.0596,
|
| 1084 |
+
"eval_rouge/rougeLsum": 71.9013,
|
| 1085 |
+
"eval_runtime": 2373.5033,
|
| 1086 |
+
"eval_samples_per_second": 0.421,
|
| 1087 |
+
"eval_steps_per_second": 0.421,
|
| 1088 |
+
"step": 36000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.47,
|
| 1092 |
+
"learning_rate": 9.47965996342058e-06,
|
| 1093 |
+
"loss": 0.2511,
|
| 1094 |
+
"step": 36500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.49,
|
| 1098 |
+
"learning_rate": 9.457300903753192e-06,
|
| 1099 |
+
"loss": 0.2416,
|
| 1100 |
+
"step": 37000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.49,
|
| 1104 |
+
"eval_bertscore/f1": 0.8155,
|
| 1105 |
+
"eval_bertscore/precision": 0.8154,
|
| 1106 |
+
"eval_bertscore/recall": 0.8179,
|
| 1107 |
+
"eval_mean_prediction_length_characters": 850.697,
|
| 1108 |
+
"eval_mean_prediction_length_tokens": 185.038,
|
| 1109 |
+
"eval_num_predicted": 1000,
|
| 1110 |
+
"eval_rouge/geometric_mean": 60.5988,
|
| 1111 |
+
"eval_rouge/rouge1": 72.9601,
|
| 1112 |
+
"eval_rouge/rouge2": 56.3526,
|
| 1113 |
+
"eval_rouge/rougeL": 54.1244,
|
| 1114 |
+
"eval_rouge/rougeLsum": 71.3786,
|
| 1115 |
+
"eval_runtime": 2440.9193,
|
| 1116 |
+
"eval_samples_per_second": 0.41,
|
| 1117 |
+
"eval_steps_per_second": 0.41,
|
| 1118 |
+
"step": 37000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.51,
|
| 1122 |
+
"learning_rate": 9.43498656220514e-06,
|
| 1123 |
+
"loss": 0.2404,
|
| 1124 |
+
"step": 37500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.53,
|
| 1128 |
+
"learning_rate": 9.412627502537755e-06,
|
| 1129 |
+
"loss": 0.2597,
|
| 1130 |
+
"step": 38000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.53,
|
| 1134 |
+
"eval_bertscore/f1": 0.8146,
|
| 1135 |
+
"eval_bertscore/precision": 0.8118,
|
| 1136 |
+
"eval_bertscore/recall": 0.8194,
|
| 1137 |
+
"eval_mean_prediction_length_characters": 856.43,
|
| 1138 |
+
"eval_mean_prediction_length_tokens": 186.628,
|
| 1139 |
+
"eval_num_predicted": 1000,
|
| 1140 |
+
"eval_rouge/geometric_mean": 60.5122,
|
| 1141 |
+
"eval_rouge/rouge1": 73.1873,
|
| 1142 |
+
"eval_rouge/rouge2": 56.3588,
|
| 1143 |
+
"eval_rouge/rougeL": 53.7195,
|
| 1144 |
+
"eval_rouge/rougeLsum": 71.5458,
|
| 1145 |
+
"eval_runtime": 2434.8964,
|
| 1146 |
+
"eval_samples_per_second": 0.411,
|
| 1147 |
+
"eval_steps_per_second": 0.411,
|
| 1148 |
+
"step": 38000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.55,
|
| 1152 |
+
"learning_rate": 9.390268442870366e-06,
|
| 1153 |
+
"loss": 0.2436,
|
| 1154 |
+
"step": 38500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.57,
|
| 1158 |
+
"learning_rate": 9.367954101322315e-06,
|
| 1159 |
+
"loss": 0.2526,
|
| 1160 |
+
"step": 39000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.57,
|
| 1164 |
+
"eval_bertscore/f1": 0.8206,
|
| 1165 |
+
"eval_bertscore/precision": 0.8186,
|
| 1166 |
+
"eval_bertscore/recall": 0.8245,
|
| 1167 |
+
"eval_mean_prediction_length_characters": 843.759,
|
| 1168 |
+
"eval_mean_prediction_length_tokens": 183.492,
|
| 1169 |
+
"eval_num_predicted": 1000,
|
| 1170 |
+
"eval_rouge/geometric_mean": 61.4692,
|
| 1171 |
+
"eval_rouge/rouge1": 74.1108,
|
| 1172 |
+
"eval_rouge/rouge2": 57.3353,
|
| 1173 |
+
"eval_rouge/rougeL": 54.6598,
|
| 1174 |
+
"eval_rouge/rougeLsum": 72.5858,
|
| 1175 |
+
"eval_runtime": 2441.5715,
|
| 1176 |
+
"eval_samples_per_second": 0.41,
|
| 1177 |
+
"eval_steps_per_second": 0.41,
|
| 1178 |
+
"step": 39000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.59,
|
| 1182 |
+
"learning_rate": 9.34559504165493e-06,
|
| 1183 |
+
"loss": 0.248,
|
| 1184 |
+
"step": 39500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.61,
|
| 1188 |
+
"learning_rate": 9.323235981987542e-06,
|
| 1189 |
+
"loss": 0.2431,
|
| 1190 |
+
"step": 40000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.61,
|
| 1194 |
+
"eval_bertscore/f1": 0.8214,
|
| 1195 |
+
"eval_bertscore/precision": 0.8186,
|
| 1196 |
+
"eval_bertscore/recall": 0.826,
|
| 1197 |
+
"eval_mean_prediction_length_characters": 854.807,
|
| 1198 |
+
"eval_mean_prediction_length_tokens": 186.06,
|
| 1199 |
+
"eval_num_predicted": 1000,
|
| 1200 |
+
"eval_rouge/geometric_mean": 61.6121,
|
| 1201 |
+
"eval_rouge/rouge1": 74.3063,
|
| 1202 |
+
"eval_rouge/rouge2": 57.6124,
|
| 1203 |
+
"eval_rouge/rougeL": 54.6331,
|
| 1204 |
+
"eval_rouge/rougeLsum": 72.7609,
|
| 1205 |
+
"eval_runtime": 2483.1491,
|
| 1206 |
+
"eval_samples_per_second": 0.403,
|
| 1207 |
+
"eval_steps_per_second": 0.403,
|
| 1208 |
+
"step": 40000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.63,
|
| 1212 |
+
"learning_rate": 9.300876922320155e-06,
|
| 1213 |
+
"loss": 0.2413,
|
| 1214 |
+
"step": 40500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.65,
|
| 1218 |
+
"learning_rate": 9.27851786265277e-06,
|
| 1219 |
+
"loss": 0.2556,
|
| 1220 |
+
"step": 41000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.65,
|
| 1224 |
+
"eval_bertscore/f1": 0.8212,
|
| 1225 |
+
"eval_bertscore/precision": 0.8166,
|
| 1226 |
+
"eval_bertscore/recall": 0.8277,
|
| 1227 |
+
"eval_mean_prediction_length_characters": 871.94,
|
| 1228 |
+
"eval_mean_prediction_length_tokens": 189.412,
|
| 1229 |
+
"eval_num_predicted": 1000,
|
| 1230 |
+
"eval_rouge/geometric_mean": 61.6287,
|
| 1231 |
+
"eval_rouge/rouge1": 74.4291,
|
| 1232 |
+
"eval_rouge/rouge2": 57.5628,
|
| 1233 |
+
"eval_rouge/rougeL": 54.6343,
|
| 1234 |
+
"eval_rouge/rougeLsum": 72.7972,
|
| 1235 |
+
"eval_runtime": 2504.8302,
|
| 1236 |
+
"eval_samples_per_second": 0.399,
|
| 1237 |
+
"eval_steps_per_second": 0.399,
|
| 1238 |
+
"step": 41000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.67,
|
| 1242 |
+
"learning_rate": 9.256158802985382e-06,
|
| 1243 |
+
"loss": 0.2414,
|
| 1244 |
+
"step": 41500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.69,
|
| 1248 |
+
"learning_rate": 9.233799743317997e-06,
|
| 1249 |
+
"loss": 0.2493,
|
| 1250 |
+
"step": 42000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.69,
|
| 1254 |
+
"eval_bertscore/f1": 0.8202,
|
| 1255 |
+
"eval_bertscore/precision": 0.8115,
|
| 1256 |
+
"eval_bertscore/recall": 0.831,
|
| 1257 |
+
"eval_mean_prediction_length_characters": 919.152,
|
| 1258 |
+
"eval_mean_prediction_length_tokens": 199.285,
|
| 1259 |
+
"eval_num_predicted": 1000,
|
| 1260 |
+
"eval_rouge/geometric_mean": 61.6474,
|
| 1261 |
+
"eval_rouge/rouge1": 74.2897,
|
| 1262 |
+
"eval_rouge/rouge2": 57.7571,
|
| 1263 |
+
"eval_rouge/rougeL": 54.6022,
|
| 1264 |
+
"eval_rouge/rougeLsum": 72.7195,
|
| 1265 |
+
"eval_runtime": 2638.78,
|
| 1266 |
+
"eval_samples_per_second": 0.379,
|
| 1267 |
+
"eval_steps_per_second": 0.379,
|
| 1268 |
+
"step": 42000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.71,
|
| 1272 |
+
"learning_rate": 9.21144068365061e-06,
|
| 1273 |
+
"loss": 0.2467,
|
| 1274 |
+
"step": 42500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.73,
|
| 1278 |
+
"learning_rate": 9.189081623983222e-06,
|
| 1279 |
+
"loss": 0.2421,
|
| 1280 |
+
"step": 43000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.73,
|
| 1284 |
+
"eval_bertscore/f1": 0.823,
|
| 1285 |
+
"eval_bertscore/precision": 0.8258,
|
| 1286 |
+
"eval_bertscore/recall": 0.8222,
|
| 1287 |
+
"eval_mean_prediction_length_characters": 803.212,
|
| 1288 |
+
"eval_mean_prediction_length_tokens": 176.172,
|
| 1289 |
+
"eval_num_predicted": 1000,
|
| 1290 |
+
"eval_rouge/geometric_mean": 61.9161,
|
| 1291 |
+
"eval_rouge/rouge1": 74.3746,
|
| 1292 |
+
"eval_rouge/rouge2": 57.9399,
|
| 1293 |
+
"eval_rouge/rougeL": 55.0818,
|
| 1294 |
+
"eval_rouge/rougeLsum": 72.8967,
|
| 1295 |
+
"eval_runtime": 2327.757,
|
| 1296 |
+
"eval_samples_per_second": 0.43,
|
| 1297 |
+
"eval_steps_per_second": 0.43,
|
| 1298 |
+
"step": 43000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.75,
|
| 1302 |
+
"learning_rate": 9.166722564315837e-06,
|
| 1303 |
+
"loss": 0.2478,
|
| 1304 |
+
"step": 43500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.77,
|
| 1308 |
+
"learning_rate": 9.14436350464845e-06,
|
| 1309 |
+
"loss": 0.229,
|
| 1310 |
+
"step": 44000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.77,
|
| 1314 |
+
"eval_bertscore/f1": 0.8212,
|
| 1315 |
+
"eval_bertscore/precision": 0.822,
|
| 1316 |
+
"eval_bertscore/recall": 0.8227,
|
| 1317 |
+
"eval_mean_prediction_length_characters": 819.677,
|
| 1318 |
+
"eval_mean_prediction_length_tokens": 178.389,
|
| 1319 |
+
"eval_num_predicted": 1000,
|
| 1320 |
+
"eval_rouge/geometric_mean": 61.8804,
|
| 1321 |
+
"eval_rouge/rouge1": 74.0116,
|
| 1322 |
+
"eval_rouge/rouge2": 57.9086,
|
| 1323 |
+
"eval_rouge/rougeL": 55.2862,
|
| 1324 |
+
"eval_rouge/rougeLsum": 72.466,
|
| 1325 |
+
"eval_runtime": 2366.2663,
|
| 1326 |
+
"eval_samples_per_second": 0.423,
|
| 1327 |
+
"eval_steps_per_second": 0.423,
|
| 1328 |
+
"step": 44000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.79,
|
| 1332 |
+
"learning_rate": 9.122049163100398e-06,
|
| 1333 |
+
"loss": 0.2398,
|
| 1334 |
+
"step": 44500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.81,
|
| 1338 |
+
"learning_rate": 9.09969010343301e-06,
|
| 1339 |
+
"loss": 0.2429,
|
| 1340 |
+
"step": 45000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.81,
|
| 1344 |
+
"eval_bertscore/f1": 0.8243,
|
| 1345 |
+
"eval_bertscore/precision": 0.8174,
|
| 1346 |
+
"eval_bertscore/recall": 0.8333,
|
| 1347 |
+
"eval_mean_prediction_length_characters": 896.966,
|
| 1348 |
+
"eval_mean_prediction_length_tokens": 195.349,
|
| 1349 |
+
"eval_num_predicted": 1000,
|
| 1350 |
+
"eval_rouge/geometric_mean": 62.2879,
|
| 1351 |
+
"eval_rouge/rouge1": 74.8367,
|
| 1352 |
+
"eval_rouge/rouge2": 58.4326,
|
| 1353 |
+
"eval_rouge/rougeL": 55.2638,
|
| 1354 |
+
"eval_rouge/rougeLsum": 73.3944,
|
| 1355 |
+
"eval_runtime": 2574.2161,
|
| 1356 |
+
"eval_samples_per_second": 0.388,
|
| 1357 |
+
"eval_steps_per_second": 0.388,
|
| 1358 |
+
"step": 45000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.83,
|
| 1362 |
+
"learning_rate": 9.077331043765623e-06,
|
| 1363 |
+
"loss": 0.2355,
|
| 1364 |
+
"step": 45500
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.85,
|
| 1368 |
+
"learning_rate": 9.054971984098238e-06,
|
| 1369 |
+
"loss": 0.2375,
|
| 1370 |
+
"step": 46000
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.85,
|
| 1374 |
+
"eval_bertscore/f1": 0.824,
|
| 1375 |
+
"eval_bertscore/precision": 0.82,
|
| 1376 |
+
"eval_bertscore/recall": 0.8303,
|
| 1377 |
+
"eval_mean_prediction_length_characters": 873.321,
|
| 1378 |
+
"eval_mean_prediction_length_tokens": 190.408,
|
| 1379 |
+
"eval_num_predicted": 1000,
|
| 1380 |
+
"eval_rouge/geometric_mean": 62.1689,
|
| 1381 |
+
"eval_rouge/rouge1": 74.7062,
|
| 1382 |
+
"eval_rouge/rouge2": 58.2978,
|
| 1383 |
+
"eval_rouge/rougeL": 55.1711,
|
| 1384 |
+
"eval_rouge/rougeLsum": 73.2347,
|
| 1385 |
+
"eval_runtime": 2618.1437,
|
| 1386 |
+
"eval_samples_per_second": 0.382,
|
| 1387 |
+
"eval_steps_per_second": 0.382,
|
| 1388 |
+
"step": 46000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.87,
|
| 1392 |
+
"learning_rate": 9.032657642550186e-06,
|
| 1393 |
+
"loss": 0.2425,
|
| 1394 |
+
"step": 46500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.89,
|
| 1398 |
+
"learning_rate": 9.010298582882799e-06,
|
| 1399 |
+
"loss": 0.228,
|
| 1400 |
+
"step": 47000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.89,
|
| 1404 |
+
"eval_bertscore/f1": 0.8258,
|
| 1405 |
+
"eval_bertscore/precision": 0.8189,
|
| 1406 |
+
"eval_bertscore/recall": 0.8348,
|
| 1407 |
+
"eval_mean_prediction_length_characters": 904.242,
|
| 1408 |
+
"eval_mean_prediction_length_tokens": 196.813,
|
| 1409 |
+
"eval_num_predicted": 1000,
|
| 1410 |
+
"eval_rouge/geometric_mean": 62.6657,
|
| 1411 |
+
"eval_rouge/rouge1": 75.0484,
|
| 1412 |
+
"eval_rouge/rouge2": 59.0138,
|
| 1413 |
+
"eval_rouge/rougeL": 55.5642,
|
| 1414 |
+
"eval_rouge/rougeLsum": 73.6606,
|
| 1415 |
+
"eval_runtime": 2709.9214,
|
| 1416 |
+
"eval_samples_per_second": 0.369,
|
| 1417 |
+
"eval_steps_per_second": 0.369,
|
| 1418 |
+
"step": 47000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.91,
|
| 1422 |
+
"learning_rate": 8.987939523215412e-06,
|
| 1423 |
+
"loss": 0.2388,
|
| 1424 |
+
"step": 47500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.93,
|
| 1428 |
+
"learning_rate": 8.965580463548026e-06,
|
| 1429 |
+
"loss": 0.2398,
|
| 1430 |
+
"step": 48000
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.93,
|
| 1434 |
+
"eval_bertscore/f1": 0.8287,
|
| 1435 |
+
"eval_bertscore/precision": 0.8255,
|
| 1436 |
+
"eval_bertscore/recall": 0.8338,
|
| 1437 |
+
"eval_mean_prediction_length_characters": 861.415,
|
| 1438 |
+
"eval_mean_prediction_length_tokens": 187.846,
|
| 1439 |
+
"eval_num_predicted": 1000,
|
| 1440 |
+
"eval_rouge/geometric_mean": 63.1011,
|
| 1441 |
+
"eval_rouge/rouge1": 75.5807,
|
| 1442 |
+
"eval_rouge/rouge2": 59.457,
|
| 1443 |
+
"eval_rouge/rougeL": 55.9108,
|
| 1444 |
+
"eval_rouge/rougeLsum": 74.1699,
|
| 1445 |
+
"eval_runtime": 2601.0783,
|
| 1446 |
+
"eval_samples_per_second": 0.384,
|
| 1447 |
+
"eval_steps_per_second": 0.384,
|
| 1448 |
+
"step": 48000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.95,
|
| 1452 |
+
"learning_rate": 8.943221403880639e-06,
|
| 1453 |
+
"loss": 0.2399,
|
| 1454 |
+
"step": 48500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.97,
|
| 1458 |
+
"learning_rate": 8.920862344213252e-06,
|
| 1459 |
+
"loss": 0.2373,
|
| 1460 |
+
"step": 49000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.97,
|
| 1464 |
+
"eval_bertscore/f1": 0.8253,
|
| 1465 |
+
"eval_bertscore/precision": 0.8244,
|
| 1466 |
+
"eval_bertscore/recall": 0.828,
|
| 1467 |
+
"eval_mean_prediction_length_characters": 840.263,
|
| 1468 |
+
"eval_mean_prediction_length_tokens": 182.473,
|
| 1469 |
+
"eval_num_predicted": 1000,
|
| 1470 |
+
"eval_rouge/geometric_mean": 62.7461,
|
| 1471 |
+
"eval_rouge/rouge1": 74.8987,
|
| 1472 |
+
"eval_rouge/rouge2": 59.0142,
|
| 1473 |
+
"eval_rouge/rougeL": 55.8894,
|
| 1474 |
+
"eval_rouge/rougeLsum": 73.4189,
|
| 1475 |
+
"eval_runtime": 2549.6944,
|
| 1476 |
+
"eval_samples_per_second": 0.392,
|
| 1477 |
+
"eval_steps_per_second": 0.392,
|
| 1478 |
+
"step": 49000
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.99,
|
| 1482 |
+
"learning_rate": 8.8985480026652e-06,
|
| 1483 |
+
"loss": 0.2397,
|
| 1484 |
+
"step": 49500
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 2.01,
|
| 1488 |
+
"learning_rate": 8.876233661117149e-06,
|
| 1489 |
+
"loss": 0.2057,
|
| 1490 |
+
"step": 50000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 2.01,
|
| 1494 |
+
"eval_bertscore/f1": 0.8258,
|
| 1495 |
+
"eval_bertscore/precision": 0.8222,
|
| 1496 |
+
"eval_bertscore/recall": 0.8313,
|
| 1497 |
+
"eval_mean_prediction_length_characters": 857.49,
|
| 1498 |
+
"eval_mean_prediction_length_tokens": 186.547,
|
| 1499 |
+
"eval_num_predicted": 1000,
|
| 1500 |
+
"eval_rouge/geometric_mean": 62.8166,
|
| 1501 |
+
"eval_rouge/rouge1": 75.1042,
|
| 1502 |
+
"eval_rouge/rouge2": 59.0815,
|
| 1503 |
+
"eval_rouge/rougeL": 55.8608,
|
| 1504 |
+
"eval_rouge/rougeLsum": 73.5713,
|
| 1505 |
+
"eval_runtime": 2602.9106,
|
| 1506 |
+
"eval_samples_per_second": 0.384,
|
| 1507 |
+
"eval_steps_per_second": 0.384,
|
| 1508 |
+
"step": 50000
|
| 1509 |
+
}
|
| 1510 |
+
],
|
| 1511 |
+
"max_steps": 248470,
|
| 1512 |
+
"num_train_epochs": 10,
|
| 1513 |
+
"total_flos": 6.239894115827712e+16,
|
| 1514 |
+
"trial_name": null,
|
| 1515 |
+
"trial_params": null
|
| 1516 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ebacc2bfe37ef4f2408c439429e67a92e14b1488d5b38c7429a21c86590a2bd
|
| 3 |
+
size 3899
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|