Upload 12 files
Browse files- .gitattributes +1 -0
- config.json +36 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +38 -0
- trainer_state.json +3261 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"length_penalty": 0.6,
|
| 20 |
+
"max_length": 128,
|
| 21 |
+
"model_type": "mt5",
|
| 22 |
+
"no_repeat_ngram_size": 2,
|
| 23 |
+
"num_beams": 15,
|
| 24 |
+
"num_decoder_layers": 8,
|
| 25 |
+
"num_heads": 6,
|
| 26 |
+
"num_layers": 8,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"relative_attention_max_distance": 128,
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"tokenizer_class": "T5Tokenizer",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.37.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 250112
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"length_penalty": 0.6,
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"no_repeat_ngram_size": 2,
|
| 7 |
+
"num_beams": 15,
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.37.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2972b3039fb18bcc8094984dfa44b597885d115e5b6a54cd70f4eeafcc0af1fa
|
| 3 |
+
size 1200729512
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f832cb364dde559d5e297ac0c214178ac32643f96f21552d5914571ad7ded8c3
|
| 3 |
+
size 2879866
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed38ae69ed750830b0b9b3d3bd8c12c9dec26eff006a895844abf0707f7af3a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ca13fa48f302fc8caf4e693db070792a08d5233b24935994930e3191e65a84
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a036c0dfd2d80e1202a7e2961aeee653ff63d67cd369b155c78a6e2003a390
|
| 3 |
+
size 16330562
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 5.555555555555555e-05,
|
| 14 |
+
"loss": 41.2711,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 0.0001111111111111111,
|
| 20 |
+
"loss": 36.9402,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 0.00016666666666666666,
|
| 26 |
+
"loss": 30.5965,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 0.0002222222222222222,
|
| 32 |
+
"loss": 25.168,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 0.0002777777777777778,
|
| 38 |
+
"loss": 20.2342,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"learning_rate": 0.0003333333333333333,
|
| 44 |
+
"loss": 15.0822,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.14,
|
| 49 |
+
"learning_rate": 0.0003888888888888889,
|
| 50 |
+
"loss": 10.8182,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16,
|
| 55 |
+
"learning_rate": 0.0004444444444444444,
|
| 56 |
+
"loss": 7.5259,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.18,
|
| 61 |
+
"learning_rate": 0.0005,
|
| 62 |
+
"loss": 5.6658,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.2,
|
| 67 |
+
"learning_rate": 0.0004989816700610998,
|
| 68 |
+
"loss": 4.1956,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.2,
|
| 73 |
+
"eval_loss": 3.1490368843078613,
|
| 74 |
+
"eval_rouge1": 0.15401031761230216,
|
| 75 |
+
"eval_rouge2": 0.06183084855722348,
|
| 76 |
+
"eval_rougeL": 0.1487638574423534,
|
| 77 |
+
"eval_rougeLsum": 0.1488931379114581,
|
| 78 |
+
"eval_runtime": 12.0897,
|
| 79 |
+
"eval_samples_per_second": 1.654,
|
| 80 |
+
"eval_steps_per_second": 0.827,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.22,
|
| 85 |
+
"learning_rate": 0.0004979633401221996,
|
| 86 |
+
"loss": 3.6249,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"learning_rate": 0.0004969450101832995,
|
| 92 |
+
"loss": 3.271,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26,
|
| 97 |
+
"learning_rate": 0.0004959266802443992,
|
| 98 |
+
"loss": 3.1977,
|
| 99 |
+
"step": 130
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.28,
|
| 103 |
+
"learning_rate": 0.000494908350305499,
|
| 104 |
+
"loss": 2.8583,
|
| 105 |
+
"step": 140
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.3,
|
| 109 |
+
"learning_rate": 0.0004938900203665988,
|
| 110 |
+
"loss": 2.5156,
|
| 111 |
+
"step": 150
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.32,
|
| 115 |
+
"learning_rate": 0.0004928716904276986,
|
| 116 |
+
"loss": 2.1851,
|
| 117 |
+
"step": 160
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.34,
|
| 121 |
+
"learning_rate": 0.0004918533604887983,
|
| 122 |
+
"loss": 1.9845,
|
| 123 |
+
"step": 170
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.36,
|
| 127 |
+
"learning_rate": 0.0004908350305498982,
|
| 128 |
+
"loss": 1.8303,
|
| 129 |
+
"step": 180
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.38,
|
| 133 |
+
"learning_rate": 0.0004898167006109979,
|
| 134 |
+
"loss": 1.7903,
|
| 135 |
+
"step": 190
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4,
|
| 139 |
+
"learning_rate": 0.0004887983706720978,
|
| 140 |
+
"loss": 1.7158,
|
| 141 |
+
"step": 200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.4,
|
| 145 |
+
"eval_loss": 1.259326696395874,
|
| 146 |
+
"eval_rouge1": 0.3038539506809194,
|
| 147 |
+
"eval_rouge2": 0.1446061100175765,
|
| 148 |
+
"eval_rougeL": 0.2647138754144953,
|
| 149 |
+
"eval_rougeLsum": 0.26637210414553936,
|
| 150 |
+
"eval_runtime": 18.5868,
|
| 151 |
+
"eval_samples_per_second": 1.076,
|
| 152 |
+
"eval_steps_per_second": 0.538,
|
| 153 |
+
"step": 200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.42,
|
| 157 |
+
"learning_rate": 0.0004877800407331975,
|
| 158 |
+
"loss": 1.7002,
|
| 159 |
+
"step": 210
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.44,
|
| 163 |
+
"learning_rate": 0.0004867617107942974,
|
| 164 |
+
"loss": 1.6374,
|
| 165 |
+
"step": 220
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.46,
|
| 169 |
+
"learning_rate": 0.00048574338085539715,
|
| 170 |
+
"loss": 1.7013,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.48,
|
| 175 |
+
"learning_rate": 0.0004847250509164969,
|
| 176 |
+
"loss": 1.624,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5,
|
| 181 |
+
"learning_rate": 0.0004837067209775968,
|
| 182 |
+
"loss": 1.6216,
|
| 183 |
+
"step": 250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.52,
|
| 187 |
+
"learning_rate": 0.00048268839103869654,
|
| 188 |
+
"loss": 1.5784,
|
| 189 |
+
"step": 260
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.54,
|
| 193 |
+
"learning_rate": 0.00048167006109979635,
|
| 194 |
+
"loss": 1.5394,
|
| 195 |
+
"step": 270
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.56,
|
| 199 |
+
"learning_rate": 0.00048065173116089617,
|
| 200 |
+
"loss": 1.5302,
|
| 201 |
+
"step": 280
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.58,
|
| 205 |
+
"learning_rate": 0.00047963340122199593,
|
| 206 |
+
"loss": 1.5071,
|
| 207 |
+
"step": 290
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.6,
|
| 211 |
+
"learning_rate": 0.00047861507128309574,
|
| 212 |
+
"loss": 1.526,
|
| 213 |
+
"step": 300
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6,
|
| 217 |
+
"eval_loss": 1.1715915203094482,
|
| 218 |
+
"eval_rouge1": 0.29557394630545675,
|
| 219 |
+
"eval_rouge2": 0.1360179746171492,
|
| 220 |
+
"eval_rougeL": 0.25515731019715504,
|
| 221 |
+
"eval_rougeLsum": 0.25695835000784906,
|
| 222 |
+
"eval_runtime": 27.3621,
|
| 223 |
+
"eval_samples_per_second": 0.731,
|
| 224 |
+
"eval_steps_per_second": 0.365,
|
| 225 |
+
"step": 300
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.62,
|
| 229 |
+
"learning_rate": 0.0004775967413441955,
|
| 230 |
+
"loss": 1.4737,
|
| 231 |
+
"step": 310
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.64,
|
| 235 |
+
"learning_rate": 0.0004765784114052953,
|
| 236 |
+
"loss": 1.4955,
|
| 237 |
+
"step": 320
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.66,
|
| 241 |
+
"learning_rate": 0.00047556008146639513,
|
| 242 |
+
"loss": 1.4392,
|
| 243 |
+
"step": 330
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.68,
|
| 247 |
+
"learning_rate": 0.0004745417515274949,
|
| 248 |
+
"loss": 1.4535,
|
| 249 |
+
"step": 340
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.7,
|
| 253 |
+
"learning_rate": 0.00047352342158859476,
|
| 254 |
+
"loss": 1.4625,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.72,
|
| 259 |
+
"learning_rate": 0.0004725050916496945,
|
| 260 |
+
"loss": 1.4353,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.74,
|
| 265 |
+
"learning_rate": 0.0004714867617107943,
|
| 266 |
+
"loss": 1.4088,
|
| 267 |
+
"step": 370
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.76,
|
| 271 |
+
"learning_rate": 0.0004704684317718941,
|
| 272 |
+
"loss": 1.4472,
|
| 273 |
+
"step": 380
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.78,
|
| 277 |
+
"learning_rate": 0.0004694501018329939,
|
| 278 |
+
"loss": 1.4318,
|
| 279 |
+
"step": 390
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.8,
|
| 283 |
+
"learning_rate": 0.0004684317718940937,
|
| 284 |
+
"loss": 1.4318,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.8,
|
| 289 |
+
"eval_loss": 1.1233234405517578,
|
| 290 |
+
"eval_rouge1": 0.33840282066392835,
|
| 291 |
+
"eval_rouge2": 0.16041046986254748,
|
| 292 |
+
"eval_rougeL": 0.2758850020825072,
|
| 293 |
+
"eval_rougeLsum": 0.27526491091998107,
|
| 294 |
+
"eval_runtime": 25.6589,
|
| 295 |
+
"eval_samples_per_second": 0.779,
|
| 296 |
+
"eval_steps_per_second": 0.39,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.82,
|
| 301 |
+
"learning_rate": 0.0004674134419551935,
|
| 302 |
+
"loss": 1.3872,
|
| 303 |
+
"step": 410
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.84,
|
| 307 |
+
"learning_rate": 0.0004663951120162933,
|
| 308 |
+
"loss": 1.4539,
|
| 309 |
+
"step": 420
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.86,
|
| 313 |
+
"learning_rate": 0.00046537678207739307,
|
| 314 |
+
"loss": 1.4651,
|
| 315 |
+
"step": 430
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.88,
|
| 319 |
+
"learning_rate": 0.0004643584521384929,
|
| 320 |
+
"loss": 1.3875,
|
| 321 |
+
"step": 440
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.9,
|
| 325 |
+
"learning_rate": 0.00046334012219959264,
|
| 326 |
+
"loss": 1.4463,
|
| 327 |
+
"step": 450
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.92,
|
| 331 |
+
"learning_rate": 0.0004623217922606925,
|
| 332 |
+
"loss": 1.4106,
|
| 333 |
+
"step": 460
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.94,
|
| 337 |
+
"learning_rate": 0.00046130346232179227,
|
| 338 |
+
"loss": 1.3987,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.96,
|
| 343 |
+
"learning_rate": 0.00046028513238289203,
|
| 344 |
+
"loss": 1.4239,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.98,
|
| 349 |
+
"learning_rate": 0.0004592668024439919,
|
| 350 |
+
"loss": 1.4184,
|
| 351 |
+
"step": 490
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.0,
|
| 355 |
+
"learning_rate": 0.00045824847250509166,
|
| 356 |
+
"loss": 1.438,
|
| 357 |
+
"step": 500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.0,
|
| 361 |
+
"eval_loss": 1.0997542142868042,
|
| 362 |
+
"eval_rouge1": 0.31808868620058295,
|
| 363 |
+
"eval_rouge2": 0.15095978898822576,
|
| 364 |
+
"eval_rougeL": 0.2758976305910347,
|
| 365 |
+
"eval_rougeLsum": 0.2783141924283456,
|
| 366 |
+
"eval_runtime": 24.4917,
|
| 367 |
+
"eval_samples_per_second": 0.817,
|
| 368 |
+
"eval_steps_per_second": 0.408,
|
| 369 |
+
"step": 500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.02,
|
| 373 |
+
"learning_rate": 0.0004572301425661914,
|
| 374 |
+
"loss": 1.3892,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.04,
|
| 379 |
+
"learning_rate": 0.0004562118126272913,
|
| 380 |
+
"loss": 1.3238,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.06,
|
| 385 |
+
"learning_rate": 0.00045519348268839105,
|
| 386 |
+
"loss": 1.3365,
|
| 387 |
+
"step": 530
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.08,
|
| 391 |
+
"learning_rate": 0.0004541751527494908,
|
| 392 |
+
"loss": 1.3769,
|
| 393 |
+
"step": 540
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.1,
|
| 397 |
+
"learning_rate": 0.0004531568228105906,
|
| 398 |
+
"loss": 1.337,
|
| 399 |
+
"step": 550
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.12,
|
| 403 |
+
"learning_rate": 0.00045213849287169044,
|
| 404 |
+
"loss": 1.3606,
|
| 405 |
+
"step": 560
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.14,
|
| 409 |
+
"learning_rate": 0.00045112016293279026,
|
| 410 |
+
"loss": 1.3643,
|
| 411 |
+
"step": 570
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.16,
|
| 415 |
+
"learning_rate": 0.00045010183299389,
|
| 416 |
+
"loss": 1.297,
|
| 417 |
+
"step": 580
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.18,
|
| 421 |
+
"learning_rate": 0.00044908350305498983,
|
| 422 |
+
"loss": 1.3871,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.2,
|
| 427 |
+
"learning_rate": 0.00044806517311608965,
|
| 428 |
+
"loss": 1.3163,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.2,
|
| 433 |
+
"eval_loss": 1.0784223079681396,
|
| 434 |
+
"eval_rouge1": 0.3334137177907346,
|
| 435 |
+
"eval_rouge2": 0.15261190778459077,
|
| 436 |
+
"eval_rougeL": 0.2719649985784092,
|
| 437 |
+
"eval_rougeLsum": 0.27272497195004963,
|
| 438 |
+
"eval_runtime": 21.6088,
|
| 439 |
+
"eval_samples_per_second": 0.926,
|
| 440 |
+
"eval_steps_per_second": 0.463,
|
| 441 |
+
"step": 600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.22,
|
| 445 |
+
"learning_rate": 0.0004470468431771894,
|
| 446 |
+
"loss": 1.3417,
|
| 447 |
+
"step": 610
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.24,
|
| 451 |
+
"learning_rate": 0.00044602851323828917,
|
| 452 |
+
"loss": 1.3073,
|
| 453 |
+
"step": 620
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.26,
|
| 457 |
+
"learning_rate": 0.00044501018329938904,
|
| 458 |
+
"loss": 1.3036,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.28,
|
| 463 |
+
"learning_rate": 0.0004439918533604888,
|
| 464 |
+
"loss": 1.3535,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3,
|
| 469 |
+
"learning_rate": 0.0004429735234215886,
|
| 470 |
+
"loss": 1.334,
|
| 471 |
+
"step": 650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.32,
|
| 475 |
+
"learning_rate": 0.00044195519348268843,
|
| 476 |
+
"loss": 1.372,
|
| 477 |
+
"step": 660
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.34,
|
| 481 |
+
"learning_rate": 0.0004409368635437882,
|
| 482 |
+
"loss": 1.3312,
|
| 483 |
+
"step": 670
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.36,
|
| 487 |
+
"learning_rate": 0.000439918533604888,
|
| 488 |
+
"loss": 1.3126,
|
| 489 |
+
"step": 680
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.38,
|
| 493 |
+
"learning_rate": 0.00043890020366598776,
|
| 494 |
+
"loss": 1.3103,
|
| 495 |
+
"step": 690
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.4,
|
| 499 |
+
"learning_rate": 0.0004378818737270876,
|
| 500 |
+
"loss": 1.3625,
|
| 501 |
+
"step": 700
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.4,
|
| 505 |
+
"eval_loss": 1.0480375289916992,
|
| 506 |
+
"eval_rouge1": 0.3252587017685009,
|
| 507 |
+
"eval_rouge2": 0.14695387868011492,
|
| 508 |
+
"eval_rougeL": 0.2819448898014987,
|
| 509 |
+
"eval_rougeLsum": 0.2825983453315859,
|
| 510 |
+
"eval_runtime": 21.3066,
|
| 511 |
+
"eval_samples_per_second": 0.939,
|
| 512 |
+
"eval_steps_per_second": 0.469,
|
| 513 |
+
"step": 700
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.42,
|
| 517 |
+
"learning_rate": 0.0004368635437881874,
|
| 518 |
+
"loss": 1.3607,
|
| 519 |
+
"step": 710
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.44,
|
| 523 |
+
"learning_rate": 0.00043584521384928715,
|
| 524 |
+
"loss": 1.3053,
|
| 525 |
+
"step": 720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.46,
|
| 529 |
+
"learning_rate": 0.00043482688391038697,
|
| 530 |
+
"loss": 1.306,
|
| 531 |
+
"step": 730
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.48,
|
| 535 |
+
"learning_rate": 0.0004338085539714868,
|
| 536 |
+
"loss": 1.3133,
|
| 537 |
+
"step": 740
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.5,
|
| 541 |
+
"learning_rate": 0.00043279022403258654,
|
| 542 |
+
"loss": 1.3261,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.52,
|
| 547 |
+
"learning_rate": 0.0004317718940936864,
|
| 548 |
+
"loss": 1.2707,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.54,
|
| 553 |
+
"learning_rate": 0.0004307535641547862,
|
| 554 |
+
"loss": 1.305,
|
| 555 |
+
"step": 770
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.56,
|
| 559 |
+
"learning_rate": 0.00042973523421588593,
|
| 560 |
+
"loss": 1.3298,
|
| 561 |
+
"step": 780
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.58,
|
| 565 |
+
"learning_rate": 0.00042871690427698575,
|
| 566 |
+
"loss": 1.295,
|
| 567 |
+
"step": 790
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.6,
|
| 571 |
+
"learning_rate": 0.00042769857433808556,
|
| 572 |
+
"loss": 1.3147,
|
| 573 |
+
"step": 800
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.6,
|
| 577 |
+
"eval_loss": 1.0463201999664307,
|
| 578 |
+
"eval_rouge1": 0.3472651013247176,
|
| 579 |
+
"eval_rouge2": 0.16642476533004819,
|
| 580 |
+
"eval_rougeL": 0.2866317550606935,
|
| 581 |
+
"eval_rougeLsum": 0.2880956525742435,
|
| 582 |
+
"eval_runtime": 23.4232,
|
| 583 |
+
"eval_samples_per_second": 0.854,
|
| 584 |
+
"eval_steps_per_second": 0.427,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.62,
|
| 589 |
+
"learning_rate": 0.0004266802443991853,
|
| 590 |
+
"loss": 1.258,
|
| 591 |
+
"step": 810
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.64,
|
| 595 |
+
"learning_rate": 0.00042566191446028514,
|
| 596 |
+
"loss": 1.3465,
|
| 597 |
+
"step": 820
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.66,
|
| 601 |
+
"learning_rate": 0.00042464358452138495,
|
| 602 |
+
"loss": 1.3383,
|
| 603 |
+
"step": 830
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.68,
|
| 607 |
+
"learning_rate": 0.0004236252545824847,
|
| 608 |
+
"loss": 1.2732,
|
| 609 |
+
"step": 840
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.7,
|
| 613 |
+
"learning_rate": 0.00042260692464358453,
|
| 614 |
+
"loss": 1.2712,
|
| 615 |
+
"step": 850
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.72,
|
| 619 |
+
"learning_rate": 0.0004215885947046843,
|
| 620 |
+
"loss": 1.2621,
|
| 621 |
+
"step": 860
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.74,
|
| 625 |
+
"learning_rate": 0.00042057026476578416,
|
| 626 |
+
"loss": 1.2981,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.76,
|
| 631 |
+
"learning_rate": 0.0004195519348268839,
|
| 632 |
+
"loss": 1.3079,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.78,
|
| 637 |
+
"learning_rate": 0.0004185336048879837,
|
| 638 |
+
"loss": 1.3029,
|
| 639 |
+
"step": 890
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.8,
|
| 643 |
+
"learning_rate": 0.00041751527494908355,
|
| 644 |
+
"loss": 1.2826,
|
| 645 |
+
"step": 900
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.8,
|
| 649 |
+
"eval_loss": 1.0260637998580933,
|
| 650 |
+
"eval_rouge1": 0.3271562809197811,
|
| 651 |
+
"eval_rouge2": 0.14988747443733796,
|
| 652 |
+
"eval_rougeL": 0.27055113042556145,
|
| 653 |
+
"eval_rougeLsum": 0.27258271275088874,
|
| 654 |
+
"eval_runtime": 21.6038,
|
| 655 |
+
"eval_samples_per_second": 0.926,
|
| 656 |
+
"eval_steps_per_second": 0.463,
|
| 657 |
+
"step": 900
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.82,
|
| 661 |
+
"learning_rate": 0.0004164969450101833,
|
| 662 |
+
"loss": 1.296,
|
| 663 |
+
"step": 910
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.84,
|
| 667 |
+
"learning_rate": 0.00041547861507128307,
|
| 668 |
+
"loss": 1.2451,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.86,
|
| 673 |
+
"learning_rate": 0.0004144602851323829,
|
| 674 |
+
"loss": 1.2716,
|
| 675 |
+
"step": 930
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.88,
|
| 679 |
+
"learning_rate": 0.0004134419551934827,
|
| 680 |
+
"loss": 1.2908,
|
| 681 |
+
"step": 940
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.9,
|
| 685 |
+
"learning_rate": 0.0004124236252545825,
|
| 686 |
+
"loss": 1.2433,
|
| 687 |
+
"step": 950
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.92,
|
| 691 |
+
"learning_rate": 0.0004114052953156823,
|
| 692 |
+
"loss": 1.2606,
|
| 693 |
+
"step": 960
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.94,
|
| 697 |
+
"learning_rate": 0.0004103869653767821,
|
| 698 |
+
"loss": 1.2975,
|
| 699 |
+
"step": 970
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.96,
|
| 703 |
+
"learning_rate": 0.0004093686354378819,
|
| 704 |
+
"loss": 1.245,
|
| 705 |
+
"step": 980
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.98,
|
| 709 |
+
"learning_rate": 0.00040835030549898167,
|
| 710 |
+
"loss": 1.2774,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0,
|
| 715 |
+
"learning_rate": 0.0004073319755600815,
|
| 716 |
+
"loss": 1.297,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.0,
|
| 721 |
+
"eval_loss": 1.02230966091156,
|
| 722 |
+
"eval_rouge1": 0.33765263015500535,
|
| 723 |
+
"eval_rouge2": 0.16173841205100162,
|
| 724 |
+
"eval_rougeL": 0.2891261055238028,
|
| 725 |
+
"eval_rougeLsum": 0.2913636739603367,
|
| 726 |
+
"eval_runtime": 21.7283,
|
| 727 |
+
"eval_samples_per_second": 0.92,
|
| 728 |
+
"eval_steps_per_second": 0.46,
|
| 729 |
+
"step": 1000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.02,
|
| 733 |
+
"learning_rate": 0.0004063136456211813,
|
| 734 |
+
"loss": 1.2437,
|
| 735 |
+
"step": 1010
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.04,
|
| 739 |
+
"learning_rate": 0.00040529531568228106,
|
| 740 |
+
"loss": 1.228,
|
| 741 |
+
"step": 1020
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.06,
|
| 745 |
+
"learning_rate": 0.0004042769857433808,
|
| 746 |
+
"loss": 1.1951,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.08,
|
| 751 |
+
"learning_rate": 0.0004032586558044807,
|
| 752 |
+
"loss": 1.205,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.1,
|
| 757 |
+
"learning_rate": 0.00040224032586558045,
|
| 758 |
+
"loss": 1.2154,
|
| 759 |
+
"step": 1050
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.12,
|
| 763 |
+
"learning_rate": 0.00040122199592668026,
|
| 764 |
+
"loss": 1.2449,
|
| 765 |
+
"step": 1060
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.14,
|
| 769 |
+
"learning_rate": 0.0004002036659877801,
|
| 770 |
+
"loss": 1.2331,
|
| 771 |
+
"step": 1070
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.16,
|
| 775 |
+
"learning_rate": 0.00039918533604887984,
|
| 776 |
+
"loss": 1.1912,
|
| 777 |
+
"step": 1080
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.18,
|
| 781 |
+
"learning_rate": 0.00039816700610997965,
|
| 782 |
+
"loss": 1.2084,
|
| 783 |
+
"step": 1090
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.2,
|
| 787 |
+
"learning_rate": 0.0003971486761710794,
|
| 788 |
+
"loss": 1.2038,
|
| 789 |
+
"step": 1100
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.2,
|
| 793 |
+
"eval_loss": 1.014428973197937,
|
| 794 |
+
"eval_rouge1": 0.32994381772002457,
|
| 795 |
+
"eval_rouge2": 0.1560313842830252,
|
| 796 |
+
"eval_rougeL": 0.2757795040195402,
|
| 797 |
+
"eval_rougeLsum": 0.27717385084380153,
|
| 798 |
+
"eval_runtime": 21.4325,
|
| 799 |
+
"eval_samples_per_second": 0.933,
|
| 800 |
+
"eval_steps_per_second": 0.467,
|
| 801 |
+
"step": 1100
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.22,
|
| 805 |
+
"learning_rate": 0.00039613034623217923,
|
| 806 |
+
"loss": 1.281,
|
| 807 |
+
"step": 1110
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.24,
|
| 811 |
+
"learning_rate": 0.00039511201629327904,
|
| 812 |
+
"loss": 1.1934,
|
| 813 |
+
"step": 1120
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.26,
|
| 817 |
+
"learning_rate": 0.0003940936863543788,
|
| 818 |
+
"loss": 1.2564,
|
| 819 |
+
"step": 1130
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.28,
|
| 823 |
+
"learning_rate": 0.0003930753564154787,
|
| 824 |
+
"loss": 1.2175,
|
| 825 |
+
"step": 1140
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.3,
|
| 829 |
+
"learning_rate": 0.00039205702647657843,
|
| 830 |
+
"loss": 1.2252,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.32,
|
| 835 |
+
"learning_rate": 0.0003910386965376782,
|
| 836 |
+
"loss": 1.2343,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.34,
|
| 841 |
+
"learning_rate": 0.000390020366598778,
|
| 842 |
+
"loss": 1.2715,
|
| 843 |
+
"step": 1170
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.36,
|
| 847 |
+
"learning_rate": 0.0003890020366598778,
|
| 848 |
+
"loss": 1.2275,
|
| 849 |
+
"step": 1180
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.38,
|
| 853 |
+
"learning_rate": 0.0003879837067209776,
|
| 854 |
+
"loss": 1.2482,
|
| 855 |
+
"step": 1190
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.4,
|
| 859 |
+
"learning_rate": 0.0003869653767820774,
|
| 860 |
+
"loss": 1.2617,
|
| 861 |
+
"step": 1200
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.4,
|
| 865 |
+
"eval_loss": 0.9945599436759949,
|
| 866 |
+
"eval_rouge1": 0.34311982189768164,
|
| 867 |
+
"eval_rouge2": 0.16176698655947228,
|
| 868 |
+
"eval_rougeL": 0.2933063191954748,
|
| 869 |
+
"eval_rougeLsum": 0.29522199653692416,
|
| 870 |
+
"eval_runtime": 20.2751,
|
| 871 |
+
"eval_samples_per_second": 0.986,
|
| 872 |
+
"eval_steps_per_second": 0.493,
|
| 873 |
+
"step": 1200
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.42,
|
| 877 |
+
"learning_rate": 0.0003859470468431772,
|
| 878 |
+
"loss": 1.19,
|
| 879 |
+
"step": 1210
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.44,
|
| 883 |
+
"learning_rate": 0.000384928716904277,
|
| 884 |
+
"loss": 1.2462,
|
| 885 |
+
"step": 1220
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.46,
|
| 889 |
+
"learning_rate": 0.0003839103869653768,
|
| 890 |
+
"loss": 1.2387,
|
| 891 |
+
"step": 1230
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.48,
|
| 895 |
+
"learning_rate": 0.00038289205702647655,
|
| 896 |
+
"loss": 1.2516,
|
| 897 |
+
"step": 1240
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.5,
|
| 901 |
+
"learning_rate": 0.0003818737270875764,
|
| 902 |
+
"loss": 1.2543,
|
| 903 |
+
"step": 1250
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.52,
|
| 907 |
+
"learning_rate": 0.0003808553971486762,
|
| 908 |
+
"loss": 1.246,
|
| 909 |
+
"step": 1260
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.54,
|
| 913 |
+
"learning_rate": 0.00037983706720977594,
|
| 914 |
+
"loss": 1.2356,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.56,
|
| 919 |
+
"learning_rate": 0.0003788187372708758,
|
| 920 |
+
"loss": 1.2301,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.58,
|
| 925 |
+
"learning_rate": 0.00037780040733197557,
|
| 926 |
+
"loss": 1.2465,
|
| 927 |
+
"step": 1290
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.6,
|
| 931 |
+
"learning_rate": 0.00037678207739307533,
|
| 932 |
+
"loss": 1.2219,
|
| 933 |
+
"step": 1300
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.6,
|
| 937 |
+
"eval_loss": 0.9984191656112671,
|
| 938 |
+
"eval_rouge1": 0.35530591683468205,
|
| 939 |
+
"eval_rouge2": 0.1738300131149214,
|
| 940 |
+
"eval_rougeL": 0.3007508066988732,
|
| 941 |
+
"eval_rougeLsum": 0.30111433503149587,
|
| 942 |
+
"eval_runtime": 21.0854,
|
| 943 |
+
"eval_samples_per_second": 0.949,
|
| 944 |
+
"eval_steps_per_second": 0.474,
|
| 945 |
+
"step": 1300
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.62,
|
| 949 |
+
"learning_rate": 0.0003757637474541752,
|
| 950 |
+
"loss": 1.2142,
|
| 951 |
+
"step": 1310
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.64,
|
| 955 |
+
"learning_rate": 0.00037474541751527496,
|
| 956 |
+
"loss": 1.1964,
|
| 957 |
+
"step": 1320
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.66,
|
| 961 |
+
"learning_rate": 0.0003737270875763747,
|
| 962 |
+
"loss": 1.2053,
|
| 963 |
+
"step": 1330
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.68,
|
| 967 |
+
"learning_rate": 0.00037270875763747454,
|
| 968 |
+
"loss": 1.2118,
|
| 969 |
+
"step": 1340
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.7,
|
| 973 |
+
"learning_rate": 0.00037169042769857435,
|
| 974 |
+
"loss": 1.1915,
|
| 975 |
+
"step": 1350
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.72,
|
| 979 |
+
"learning_rate": 0.00037067209775967417,
|
| 980 |
+
"loss": 1.2272,
|
| 981 |
+
"step": 1360
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.74,
|
| 985 |
+
"learning_rate": 0.00036965376782077393,
|
| 986 |
+
"loss": 1.1926,
|
| 987 |
+
"step": 1370
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.76,
|
| 991 |
+
"learning_rate": 0.00036863543788187374,
|
| 992 |
+
"loss": 1.2056,
|
| 993 |
+
"step": 1380
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.78,
|
| 997 |
+
"learning_rate": 0.00036761710794297356,
|
| 998 |
+
"loss": 1.1868,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.8,
|
| 1003 |
+
"learning_rate": 0.0003665987780040733,
|
| 1004 |
+
"loss": 1.1906,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.8,
|
| 1009 |
+
"eval_loss": 0.9987648129463196,
|
| 1010 |
+
"eval_rouge1": 0.3497044345695397,
|
| 1011 |
+
"eval_rouge2": 0.17488344746541123,
|
| 1012 |
+
"eval_rougeL": 0.2920352923144545,
|
| 1013 |
+
"eval_rougeLsum": 0.2936840461100848,
|
| 1014 |
+
"eval_runtime": 20.5611,
|
| 1015 |
+
"eval_samples_per_second": 0.973,
|
| 1016 |
+
"eval_steps_per_second": 0.486,
|
| 1017 |
+
"step": 1400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.82,
|
| 1021 |
+
"learning_rate": 0.0003655804480651731,
|
| 1022 |
+
"loss": 1.1981,
|
| 1023 |
+
"step": 1410
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.84,
|
| 1027 |
+
"learning_rate": 0.00036456211812627295,
|
| 1028 |
+
"loss": 1.2079,
|
| 1029 |
+
"step": 1420
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.86,
|
| 1033 |
+
"learning_rate": 0.0003635437881873727,
|
| 1034 |
+
"loss": 1.2036,
|
| 1035 |
+
"step": 1430
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.88,
|
| 1039 |
+
"learning_rate": 0.00036252545824847247,
|
| 1040 |
+
"loss": 1.1892,
|
| 1041 |
+
"step": 1440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.9,
|
| 1045 |
+
"learning_rate": 0.00036150712830957234,
|
| 1046 |
+
"loss": 1.2223,
|
| 1047 |
+
"step": 1450
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.92,
|
| 1051 |
+
"learning_rate": 0.0003604887983706721,
|
| 1052 |
+
"loss": 1.2214,
|
| 1053 |
+
"step": 1460
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.94,
|
| 1057 |
+
"learning_rate": 0.0003594704684317719,
|
| 1058 |
+
"loss": 1.2206,
|
| 1059 |
+
"step": 1470
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.96,
|
| 1063 |
+
"learning_rate": 0.0003584521384928717,
|
| 1064 |
+
"loss": 1.2218,
|
| 1065 |
+
"step": 1480
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.98,
|
| 1069 |
+
"learning_rate": 0.0003574338085539715,
|
| 1070 |
+
"loss": 1.1856,
|
| 1071 |
+
"step": 1490
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.0,
|
| 1075 |
+
"learning_rate": 0.0003564154786150713,
|
| 1076 |
+
"loss": 1.2303,
|
| 1077 |
+
"step": 1500
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.0,
|
| 1081 |
+
"eval_loss": 0.9856168031692505,
|
| 1082 |
+
"eval_rouge1": 0.3750110269055352,
|
| 1083 |
+
"eval_rouge2": 0.17459799489090816,
|
| 1084 |
+
"eval_rougeL": 0.3003592834064919,
|
| 1085 |
+
"eval_rougeLsum": 0.30119936143252757,
|
| 1086 |
+
"eval_runtime": 23.4082,
|
| 1087 |
+
"eval_samples_per_second": 0.854,
|
| 1088 |
+
"eval_steps_per_second": 0.427,
|
| 1089 |
+
"step": 1500
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.02,
|
| 1093 |
+
"learning_rate": 0.00035539714867617106,
|
| 1094 |
+
"loss": 1.1498,
|
| 1095 |
+
"step": 1510
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.04,
|
| 1099 |
+
"learning_rate": 0.0003543788187372709,
|
| 1100 |
+
"loss": 1.2083,
|
| 1101 |
+
"step": 1520
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.06,
|
| 1105 |
+
"learning_rate": 0.0003533604887983707,
|
| 1106 |
+
"loss": 1.2291,
|
| 1107 |
+
"step": 1530
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 3.08,
|
| 1111 |
+
"learning_rate": 0.00035234215885947045,
|
| 1112 |
+
"loss": 1.1733,
|
| 1113 |
+
"step": 1540
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.1,
|
| 1117 |
+
"learning_rate": 0.0003513238289205703,
|
| 1118 |
+
"loss": 1.1716,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.12,
|
| 1123 |
+
"learning_rate": 0.0003503054989816701,
|
| 1124 |
+
"loss": 1.1657,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.14,
|
| 1129 |
+
"learning_rate": 0.00034928716904276985,
|
| 1130 |
+
"loss": 1.1538,
|
| 1131 |
+
"step": 1570
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 3.16,
|
| 1135 |
+
"learning_rate": 0.00034826883910386966,
|
| 1136 |
+
"loss": 1.1579,
|
| 1137 |
+
"step": 1580
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.18,
|
| 1141 |
+
"learning_rate": 0.0003472505091649695,
|
| 1142 |
+
"loss": 1.1945,
|
| 1143 |
+
"step": 1590
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.2,
|
| 1147 |
+
"learning_rate": 0.00034623217922606924,
|
| 1148 |
+
"loss": 1.18,
|
| 1149 |
+
"step": 1600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.2,
|
| 1153 |
+
"eval_loss": 0.9823005795478821,
|
| 1154 |
+
"eval_rouge1": 0.35334084985835634,
|
| 1155 |
+
"eval_rouge2": 0.1773564424695835,
|
| 1156 |
+
"eval_rougeL": 0.30516391982892244,
|
| 1157 |
+
"eval_rougeLsum": 0.30596841516938367,
|
| 1158 |
+
"eval_runtime": 22.0682,
|
| 1159 |
+
"eval_samples_per_second": 0.906,
|
| 1160 |
+
"eval_steps_per_second": 0.453,
|
| 1161 |
+
"step": 1600
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.22,
|
| 1165 |
+
"learning_rate": 0.00034521384928716905,
|
| 1166 |
+
"loss": 1.1782,
|
| 1167 |
+
"step": 1610
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.24,
|
| 1171 |
+
"learning_rate": 0.00034419551934826887,
|
| 1172 |
+
"loss": 1.2039,
|
| 1173 |
+
"step": 1620
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.26,
|
| 1177 |
+
"learning_rate": 0.0003431771894093686,
|
| 1178 |
+
"loss": 1.1961,
|
| 1179 |
+
"step": 1630
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.28,
|
| 1183 |
+
"learning_rate": 0.00034215885947046844,
|
| 1184 |
+
"loss": 1.1846,
|
| 1185 |
+
"step": 1640
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.3,
|
| 1189 |
+
"learning_rate": 0.0003411405295315682,
|
| 1190 |
+
"loss": 1.1776,
|
| 1191 |
+
"step": 1650
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 3.32,
|
| 1195 |
+
"learning_rate": 0.00034012219959266807,
|
| 1196 |
+
"loss": 1.1549,
|
| 1197 |
+
"step": 1660
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.34,
|
| 1201 |
+
"learning_rate": 0.00033910386965376783,
|
| 1202 |
+
"loss": 1.1442,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 3.36,
|
| 1207 |
+
"learning_rate": 0.0003380855397148676,
|
| 1208 |
+
"loss": 1.1672,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.38,
|
| 1213 |
+
"learning_rate": 0.00033706720977596746,
|
| 1214 |
+
"loss": 1.1854,
|
| 1215 |
+
"step": 1690
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.4,
|
| 1219 |
+
"learning_rate": 0.0003360488798370672,
|
| 1220 |
+
"loss": 1.1435,
|
| 1221 |
+
"step": 1700
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 3.4,
|
| 1225 |
+
"eval_loss": 0.9792933464050293,
|
| 1226 |
+
"eval_rouge1": 0.3566145348467804,
|
| 1227 |
+
"eval_rouge2": 0.16981457897259283,
|
| 1228 |
+
"eval_rougeL": 0.29555110085672354,
|
| 1229 |
+
"eval_rougeLsum": 0.29638538572800865,
|
| 1230 |
+
"eval_runtime": 20.8074,
|
| 1231 |
+
"eval_samples_per_second": 0.961,
|
| 1232 |
+
"eval_steps_per_second": 0.481,
|
| 1233 |
+
"step": 1700
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 3.42,
|
| 1237 |
+
"learning_rate": 0.000335030549898167,
|
| 1238 |
+
"loss": 1.1721,
|
| 1239 |
+
"step": 1710
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.44,
|
| 1243 |
+
"learning_rate": 0.0003340122199592668,
|
| 1244 |
+
"loss": 1.1546,
|
| 1245 |
+
"step": 1720
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 3.46,
|
| 1249 |
+
"learning_rate": 0.0003329938900203666,
|
| 1250 |
+
"loss": 1.1843,
|
| 1251 |
+
"step": 1730
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.48,
|
| 1255 |
+
"learning_rate": 0.00033197556008146637,
|
| 1256 |
+
"loss": 1.1968,
|
| 1257 |
+
"step": 1740
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.5,
|
| 1261 |
+
"learning_rate": 0.0003309572301425662,
|
| 1262 |
+
"loss": 1.1481,
|
| 1263 |
+
"step": 1750
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.52,
|
| 1267 |
+
"learning_rate": 0.000329938900203666,
|
| 1268 |
+
"loss": 1.1473,
|
| 1269 |
+
"step": 1760
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.54,
|
| 1273 |
+
"learning_rate": 0.0003289205702647658,
|
| 1274 |
+
"loss": 1.1729,
|
| 1275 |
+
"step": 1770
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.56,
|
| 1279 |
+
"learning_rate": 0.0003279022403258656,
|
| 1280 |
+
"loss": 1.1401,
|
| 1281 |
+
"step": 1780
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.58,
|
| 1285 |
+
"learning_rate": 0.0003268839103869654,
|
| 1286 |
+
"loss": 1.1602,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.6,
|
| 1291 |
+
"learning_rate": 0.0003258655804480652,
|
| 1292 |
+
"loss": 1.1473,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.6,
|
| 1297 |
+
"eval_loss": 0.9619871973991394,
|
| 1298 |
+
"eval_rouge1": 0.36668217495119926,
|
| 1299 |
+
"eval_rouge2": 0.18802901856822518,
|
| 1300 |
+
"eval_rougeL": 0.3009048329724593,
|
| 1301 |
+
"eval_rougeLsum": 0.3020958756940847,
|
| 1302 |
+
"eval_runtime": 20.3135,
|
| 1303 |
+
"eval_samples_per_second": 0.985,
|
| 1304 |
+
"eval_steps_per_second": 0.492,
|
| 1305 |
+
"step": 1800
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.62,
|
| 1309 |
+
"learning_rate": 0.00032484725050916497,
|
| 1310 |
+
"loss": 1.1533,
|
| 1311 |
+
"step": 1810
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.64,
|
| 1315 |
+
"learning_rate": 0.00032382892057026473,
|
| 1316 |
+
"loss": 1.1557,
|
| 1317 |
+
"step": 1820
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 3.66,
|
| 1321 |
+
"learning_rate": 0.0003228105906313646,
|
| 1322 |
+
"loss": 1.2091,
|
| 1323 |
+
"step": 1830
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 3.68,
|
| 1327 |
+
"learning_rate": 0.00032179226069246436,
|
| 1328 |
+
"loss": 1.1791,
|
| 1329 |
+
"step": 1840
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.7,
|
| 1333 |
+
"learning_rate": 0.0003207739307535642,
|
| 1334 |
+
"loss": 1.1407,
|
| 1335 |
+
"step": 1850
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.72,
|
| 1339 |
+
"learning_rate": 0.000319755600814664,
|
| 1340 |
+
"loss": 1.1498,
|
| 1341 |
+
"step": 1860
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.74,
|
| 1345 |
+
"learning_rate": 0.00031873727087576375,
|
| 1346 |
+
"loss": 1.1368,
|
| 1347 |
+
"step": 1870
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.76,
|
| 1351 |
+
"learning_rate": 0.00031771894093686356,
|
| 1352 |
+
"loss": 1.1634,
|
| 1353 |
+
"step": 1880
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.78,
|
| 1357 |
+
"learning_rate": 0.0003167006109979633,
|
| 1358 |
+
"loss": 1.168,
|
| 1359 |
+
"step": 1890
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.8,
|
| 1363 |
+
"learning_rate": 0.00031568228105906314,
|
| 1364 |
+
"loss": 1.1588,
|
| 1365 |
+
"step": 1900
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 3.8,
|
| 1369 |
+
"eval_loss": 0.9718366861343384,
|
| 1370 |
+
"eval_rouge1": 0.36821337929430387,
|
| 1371 |
+
"eval_rouge2": 0.17821834663511393,
|
| 1372 |
+
"eval_rougeL": 0.30543977513475806,
|
| 1373 |
+
"eval_rougeLsum": 0.3075353240284504,
|
| 1374 |
+
"eval_runtime": 20.7174,
|
| 1375 |
+
"eval_samples_per_second": 0.965,
|
| 1376 |
+
"eval_steps_per_second": 0.483,
|
| 1377 |
+
"step": 1900
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.82,
|
| 1381 |
+
"learning_rate": 0.00031466395112016295,
|
| 1382 |
+
"loss": 1.1989,
|
| 1383 |
+
"step": 1910
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 3.84,
|
| 1387 |
+
"learning_rate": 0.0003136456211812627,
|
| 1388 |
+
"loss": 1.1542,
|
| 1389 |
+
"step": 1920
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.86,
|
| 1393 |
+
"learning_rate": 0.00031262729124236253,
|
| 1394 |
+
"loss": 1.203,
|
| 1395 |
+
"step": 1930
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.88,
|
| 1399 |
+
"learning_rate": 0.00031160896130346234,
|
| 1400 |
+
"loss": 1.1644,
|
| 1401 |
+
"step": 1940
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.9,
|
| 1405 |
+
"learning_rate": 0.0003105906313645621,
|
| 1406 |
+
"loss": 1.1266,
|
| 1407 |
+
"step": 1950
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.92,
|
| 1411 |
+
"learning_rate": 0.0003095723014256619,
|
| 1412 |
+
"loss": 1.1994,
|
| 1413 |
+
"step": 1960
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.94,
|
| 1417 |
+
"learning_rate": 0.00030855397148676173,
|
| 1418 |
+
"loss": 1.1402,
|
| 1419 |
+
"step": 1970
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.96,
|
| 1423 |
+
"learning_rate": 0.0003075356415478615,
|
| 1424 |
+
"loss": 1.1348,
|
| 1425 |
+
"step": 1980
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 3.98,
|
| 1429 |
+
"learning_rate": 0.0003065173116089613,
|
| 1430 |
+
"loss": 1.1582,
|
| 1431 |
+
"step": 1990
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 4.0,
|
| 1435 |
+
"learning_rate": 0.0003054989816700611,
|
| 1436 |
+
"loss": 1.127,
|
| 1437 |
+
"step": 2000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.0,
|
| 1441 |
+
"eval_loss": 0.9626486897468567,
|
| 1442 |
+
"eval_rouge1": 0.33933999922378055,
|
| 1443 |
+
"eval_rouge2": 0.15960640801652384,
|
| 1444 |
+
"eval_rougeL": 0.27841295690954404,
|
| 1445 |
+
"eval_rougeLsum": 0.2805778340104648,
|
| 1446 |
+
"eval_runtime": 20.5994,
|
| 1447 |
+
"eval_samples_per_second": 0.971,
|
| 1448 |
+
"eval_steps_per_second": 0.485,
|
| 1449 |
+
"step": 2000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 4.02,
|
| 1453 |
+
"learning_rate": 0.0003044806517311609,
|
| 1454 |
+
"loss": 1.1229,
|
| 1455 |
+
"step": 2010
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.04,
|
| 1459 |
+
"learning_rate": 0.0003034623217922607,
|
| 1460 |
+
"loss": 1.1027,
|
| 1461 |
+
"step": 2020
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 4.06,
|
| 1465 |
+
"learning_rate": 0.0003024439918533605,
|
| 1466 |
+
"loss": 1.0923,
|
| 1467 |
+
"step": 2030
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.08,
|
| 1471 |
+
"learning_rate": 0.0003014256619144603,
|
| 1472 |
+
"loss": 1.1416,
|
| 1473 |
+
"step": 2040
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 4.1,
|
| 1477 |
+
"learning_rate": 0.0003004073319755601,
|
| 1478 |
+
"loss": 1.1066,
|
| 1479 |
+
"step": 2050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.12,
|
| 1483 |
+
"learning_rate": 0.00029938900203665985,
|
| 1484 |
+
"loss": 1.1045,
|
| 1485 |
+
"step": 2060
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 4.14,
|
| 1489 |
+
"learning_rate": 0.0002983706720977597,
|
| 1490 |
+
"loss": 1.1172,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 4.16,
|
| 1495 |
+
"learning_rate": 0.0002973523421588595,
|
| 1496 |
+
"loss": 1.1535,
|
| 1497 |
+
"step": 2080
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.18,
|
| 1501 |
+
"learning_rate": 0.00029633401221995924,
|
| 1502 |
+
"loss": 1.1866,
|
| 1503 |
+
"step": 2090
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 4.2,
|
| 1507 |
+
"learning_rate": 0.0002953156822810591,
|
| 1508 |
+
"loss": 1.1251,
|
| 1509 |
+
"step": 2100
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.2,
|
| 1513 |
+
"eval_loss": 0.9701215028762817,
|
| 1514 |
+
"eval_rouge1": 0.36918849108015117,
|
| 1515 |
+
"eval_rouge2": 0.1756845524684395,
|
| 1516 |
+
"eval_rougeL": 0.29888162339098345,
|
| 1517 |
+
"eval_rougeLsum": 0.30162046588140573,
|
| 1518 |
+
"eval_runtime": 24.6363,
|
| 1519 |
+
"eval_samples_per_second": 0.812,
|
| 1520 |
+
"eval_steps_per_second": 0.406,
|
| 1521 |
+
"step": 2100
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.22,
|
| 1525 |
+
"learning_rate": 0.00029429735234215887,
|
| 1526 |
+
"loss": 1.1246,
|
| 1527 |
+
"step": 2110
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 4.24,
|
| 1531 |
+
"learning_rate": 0.00029327902240325863,
|
| 1532 |
+
"loss": 1.1562,
|
| 1533 |
+
"step": 2120
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 4.26,
|
| 1537 |
+
"learning_rate": 0.00029226069246435845,
|
| 1538 |
+
"loss": 1.1627,
|
| 1539 |
+
"step": 2130
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.28,
|
| 1543 |
+
"learning_rate": 0.00029124236252545826,
|
| 1544 |
+
"loss": 1.1157,
|
| 1545 |
+
"step": 2140
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 4.3,
|
| 1549 |
+
"learning_rate": 0.0002902240325865581,
|
| 1550 |
+
"loss": 1.1398,
|
| 1551 |
+
"step": 2150
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 4.32,
|
| 1555 |
+
"learning_rate": 0.00028920570264765784,
|
| 1556 |
+
"loss": 1.1432,
|
| 1557 |
+
"step": 2160
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 4.34,
|
| 1561 |
+
"learning_rate": 0.00028818737270875765,
|
| 1562 |
+
"loss": 1.1318,
|
| 1563 |
+
"step": 2170
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 4.36,
|
| 1567 |
+
"learning_rate": 0.00028716904276985747,
|
| 1568 |
+
"loss": 1.1461,
|
| 1569 |
+
"step": 2180
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 4.38,
|
| 1573 |
+
"learning_rate": 0.00028615071283095723,
|
| 1574 |
+
"loss": 1.13,
|
| 1575 |
+
"step": 2190
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 4.4,
|
| 1579 |
+
"learning_rate": 0.000285132382892057,
|
| 1580 |
+
"loss": 1.085,
|
| 1581 |
+
"step": 2200
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 4.4,
|
| 1585 |
+
"eval_loss": 0.9604999423027039,
|
| 1586 |
+
"eval_rouge1": 0.3531685802104979,
|
| 1587 |
+
"eval_rouge2": 0.16500844586291133,
|
| 1588 |
+
"eval_rougeL": 0.28475165873194214,
|
| 1589 |
+
"eval_rougeLsum": 0.2861591101839957,
|
| 1590 |
+
"eval_runtime": 20.5667,
|
| 1591 |
+
"eval_samples_per_second": 0.972,
|
| 1592 |
+
"eval_steps_per_second": 0.486,
|
| 1593 |
+
"step": 2200
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 4.42,
|
| 1597 |
+
"learning_rate": 0.00028411405295315686,
|
| 1598 |
+
"loss": 1.1408,
|
| 1599 |
+
"step": 2210
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.44,
|
| 1603 |
+
"learning_rate": 0.0002830957230142566,
|
| 1604 |
+
"loss": 1.1458,
|
| 1605 |
+
"step": 2220
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 4.46,
|
| 1609 |
+
"learning_rate": 0.0002820773930753564,
|
| 1610 |
+
"loss": 1.1056,
|
| 1611 |
+
"step": 2230
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 4.48,
|
| 1615 |
+
"learning_rate": 0.00028105906313645625,
|
| 1616 |
+
"loss": 1.1933,
|
| 1617 |
+
"step": 2240
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 4.5,
|
| 1621 |
+
"learning_rate": 0.000280040733197556,
|
| 1622 |
+
"loss": 1.1478,
|
| 1623 |
+
"step": 2250
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 4.52,
|
| 1627 |
+
"learning_rate": 0.0002790224032586558,
|
| 1628 |
+
"loss": 1.0862,
|
| 1629 |
+
"step": 2260
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 4.54,
|
| 1633 |
+
"learning_rate": 0.0002780040733197556,
|
| 1634 |
+
"loss": 1.1433,
|
| 1635 |
+
"step": 2270
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 4.56,
|
| 1639 |
+
"learning_rate": 0.0002769857433808554,
|
| 1640 |
+
"loss": 1.124,
|
| 1641 |
+
"step": 2280
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 4.58,
|
| 1645 |
+
"learning_rate": 0.0002759674134419552,
|
| 1646 |
+
"loss": 1.095,
|
| 1647 |
+
"step": 2290
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 4.6,
|
| 1651 |
+
"learning_rate": 0.000274949083503055,
|
| 1652 |
+
"loss": 1.0922,
|
| 1653 |
+
"step": 2300
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 4.6,
|
| 1657 |
+
"eval_loss": 0.9633736610412598,
|
| 1658 |
+
"eval_rouge1": 0.35626224117845484,
|
| 1659 |
+
"eval_rouge2": 0.16997535406808995,
|
| 1660 |
+
"eval_rougeL": 0.2941903529387039,
|
| 1661 |
+
"eval_rougeLsum": 0.2963873855076279,
|
| 1662 |
+
"eval_runtime": 22.0443,
|
| 1663 |
+
"eval_samples_per_second": 0.907,
|
| 1664 |
+
"eval_steps_per_second": 0.454,
|
| 1665 |
+
"step": 2300
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 4.62,
|
| 1669 |
+
"learning_rate": 0.0002739307535641548,
|
| 1670 |
+
"loss": 1.1468,
|
| 1671 |
+
"step": 2310
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 4.64,
|
| 1675 |
+
"learning_rate": 0.0002729124236252546,
|
| 1676 |
+
"loss": 1.1456,
|
| 1677 |
+
"step": 2320
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 4.66,
|
| 1681 |
+
"learning_rate": 0.00027189409368635437,
|
| 1682 |
+
"loss": 1.1317,
|
| 1683 |
+
"step": 2330
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 4.68,
|
| 1687 |
+
"learning_rate": 0.0002708757637474542,
|
| 1688 |
+
"loss": 1.1078,
|
| 1689 |
+
"step": 2340
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.7,
|
| 1693 |
+
"learning_rate": 0.000269857433808554,
|
| 1694 |
+
"loss": 1.143,
|
| 1695 |
+
"step": 2350
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 4.72,
|
| 1699 |
+
"learning_rate": 0.00026883910386965376,
|
| 1700 |
+
"loss": 1.1194,
|
| 1701 |
+
"step": 2360
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 4.74,
|
| 1705 |
+
"learning_rate": 0.00026782077393075357,
|
| 1706 |
+
"loss": 1.1122,
|
| 1707 |
+
"step": 2370
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 4.76,
|
| 1711 |
+
"learning_rate": 0.0002668024439918534,
|
| 1712 |
+
"loss": 1.1275,
|
| 1713 |
+
"step": 2380
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 4.78,
|
| 1717 |
+
"learning_rate": 0.00026578411405295315,
|
| 1718 |
+
"loss": 1.1305,
|
| 1719 |
+
"step": 2390
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 4.8,
|
| 1723 |
+
"learning_rate": 0.00026476578411405296,
|
| 1724 |
+
"loss": 1.1649,
|
| 1725 |
+
"step": 2400
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 4.8,
|
| 1729 |
+
"eval_loss": 0.9545726776123047,
|
| 1730 |
+
"eval_rouge1": 0.38101044159436365,
|
| 1731 |
+
"eval_rouge2": 0.1957583700370854,
|
| 1732 |
+
"eval_rougeL": 0.3214174366996265,
|
| 1733 |
+
"eval_rougeLsum": 0.3228583149166323,
|
| 1734 |
+
"eval_runtime": 21.4511,
|
| 1735 |
+
"eval_samples_per_second": 0.932,
|
| 1736 |
+
"eval_steps_per_second": 0.466,
|
| 1737 |
+
"step": 2400
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 4.82,
|
| 1741 |
+
"learning_rate": 0.0002637474541751528,
|
| 1742 |
+
"loss": 1.104,
|
| 1743 |
+
"step": 2410
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 4.84,
|
| 1747 |
+
"learning_rate": 0.00026272912423625254,
|
| 1748 |
+
"loss": 1.1482,
|
| 1749 |
+
"step": 2420
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 4.86,
|
| 1753 |
+
"learning_rate": 0.00026171079429735235,
|
| 1754 |
+
"loss": 1.1361,
|
| 1755 |
+
"step": 2430
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 4.88,
|
| 1759 |
+
"learning_rate": 0.0002606924643584521,
|
| 1760 |
+
"loss": 1.0924,
|
| 1761 |
+
"step": 2440
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 4.9,
|
| 1765 |
+
"learning_rate": 0.000259674134419552,
|
| 1766 |
+
"loss": 1.1313,
|
| 1767 |
+
"step": 2450
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 4.92,
|
| 1771 |
+
"learning_rate": 0.00025865580448065174,
|
| 1772 |
+
"loss": 1.0971,
|
| 1773 |
+
"step": 2460
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 4.94,
|
| 1777 |
+
"learning_rate": 0.0002576374745417515,
|
| 1778 |
+
"loss": 1.1653,
|
| 1779 |
+
"step": 2470
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 4.96,
|
| 1783 |
+
"learning_rate": 0.00025661914460285137,
|
| 1784 |
+
"loss": 1.1438,
|
| 1785 |
+
"step": 2480
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 4.98,
|
| 1789 |
+
"learning_rate": 0.00025560081466395113,
|
| 1790 |
+
"loss": 1.139,
|
| 1791 |
+
"step": 2490
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 5.0,
|
| 1795 |
+
"learning_rate": 0.0002545824847250509,
|
| 1796 |
+
"loss": 1.1279,
|
| 1797 |
+
"step": 2500
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 5.0,
|
| 1801 |
+
"eval_loss": 0.9487113952636719,
|
| 1802 |
+
"eval_rouge1": 0.3782997160632432,
|
| 1803 |
+
"eval_rouge2": 0.20289958909161465,
|
| 1804 |
+
"eval_rougeL": 0.3222664292441296,
|
| 1805 |
+
"eval_rougeLsum": 0.3240112049119128,
|
| 1806 |
+
"eval_runtime": 21.5846,
|
| 1807 |
+
"eval_samples_per_second": 0.927,
|
| 1808 |
+
"eval_steps_per_second": 0.463,
|
| 1809 |
+
"step": 2500
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 5.02,
|
| 1813 |
+
"learning_rate": 0.0002535641547861507,
|
| 1814 |
+
"loss": 1.1028,
|
| 1815 |
+
"step": 2510
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 5.04,
|
| 1819 |
+
"learning_rate": 0.0002525458248472505,
|
| 1820 |
+
"loss": 1.0659,
|
| 1821 |
+
"step": 2520
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 5.06,
|
| 1825 |
+
"learning_rate": 0.0002515274949083503,
|
| 1826 |
+
"loss": 1.115,
|
| 1827 |
+
"step": 2530
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 5.08,
|
| 1831 |
+
"learning_rate": 0.0002505091649694501,
|
| 1832 |
+
"loss": 1.0952,
|
| 1833 |
+
"step": 2540
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 5.1,
|
| 1837 |
+
"learning_rate": 0.0002494908350305499,
|
| 1838 |
+
"loss": 1.1092,
|
| 1839 |
+
"step": 2550
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 5.12,
|
| 1843 |
+
"learning_rate": 0.00024847250509164973,
|
| 1844 |
+
"loss": 1.1194,
|
| 1845 |
+
"step": 2560
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 5.14,
|
| 1849 |
+
"learning_rate": 0.0002474541751527495,
|
| 1850 |
+
"loss": 1.11,
|
| 1851 |
+
"step": 2570
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 5.16,
|
| 1855 |
+
"learning_rate": 0.0002464358452138493,
|
| 1856 |
+
"loss": 1.1524,
|
| 1857 |
+
"step": 2580
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 5.18,
|
| 1861 |
+
"learning_rate": 0.0002454175152749491,
|
| 1862 |
+
"loss": 1.1122,
|
| 1863 |
+
"step": 2590
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 5.2,
|
| 1867 |
+
"learning_rate": 0.0002443991853360489,
|
| 1868 |
+
"loss": 1.0798,
|
| 1869 |
+
"step": 2600
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 5.2,
|
| 1873 |
+
"eval_loss": 0.9421226382255554,
|
| 1874 |
+
"eval_rouge1": 0.3597269877576089,
|
| 1875 |
+
"eval_rouge2": 0.1775049607682675,
|
| 1876 |
+
"eval_rougeL": 0.2919995300536511,
|
| 1877 |
+
"eval_rougeLsum": 0.29538083346340016,
|
| 1878 |
+
"eval_runtime": 22.4063,
|
| 1879 |
+
"eval_samples_per_second": 0.893,
|
| 1880 |
+
"eval_steps_per_second": 0.446,
|
| 1881 |
+
"step": 2600
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 5.22,
|
| 1885 |
+
"learning_rate": 0.0002433808553971487,
|
| 1886 |
+
"loss": 1.1141,
|
| 1887 |
+
"step": 2610
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 5.24,
|
| 1891 |
+
"learning_rate": 0.00024236252545824845,
|
| 1892 |
+
"loss": 1.11,
|
| 1893 |
+
"step": 2620
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 5.26,
|
| 1897 |
+
"learning_rate": 0.00024134419551934827,
|
| 1898 |
+
"loss": 1.1206,
|
| 1899 |
+
"step": 2630
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 5.28,
|
| 1903 |
+
"learning_rate": 0.00024032586558044808,
|
| 1904 |
+
"loss": 1.1035,
|
| 1905 |
+
"step": 2640
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 5.3,
|
| 1909 |
+
"learning_rate": 0.00023930753564154787,
|
| 1910 |
+
"loss": 1.1362,
|
| 1911 |
+
"step": 2650
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 5.32,
|
| 1915 |
+
"learning_rate": 0.00023828920570264766,
|
| 1916 |
+
"loss": 1.1023,
|
| 1917 |
+
"step": 2660
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 5.34,
|
| 1921 |
+
"learning_rate": 0.00023727087576374745,
|
| 1922 |
+
"loss": 1.1237,
|
| 1923 |
+
"step": 2670
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 5.36,
|
| 1927 |
+
"learning_rate": 0.00023625254582484726,
|
| 1928 |
+
"loss": 1.0934,
|
| 1929 |
+
"step": 2680
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 5.38,
|
| 1933 |
+
"learning_rate": 0.00023523421588594705,
|
| 1934 |
+
"loss": 1.0976,
|
| 1935 |
+
"step": 2690
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 5.4,
|
| 1939 |
+
"learning_rate": 0.00023421588594704684,
|
| 1940 |
+
"loss": 1.1468,
|
| 1941 |
+
"step": 2700
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 5.4,
|
| 1945 |
+
"eval_loss": 0.9474976658821106,
|
| 1946 |
+
"eval_rouge1": 0.37719594840753984,
|
| 1947 |
+
"eval_rouge2": 0.19434086595475156,
|
| 1948 |
+
"eval_rougeL": 0.312798697930013,
|
| 1949 |
+
"eval_rougeLsum": 0.3158141266137696,
|
| 1950 |
+
"eval_runtime": 21.5064,
|
| 1951 |
+
"eval_samples_per_second": 0.93,
|
| 1952 |
+
"eval_steps_per_second": 0.465,
|
| 1953 |
+
"step": 2700
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 5.42,
|
| 1957 |
+
"learning_rate": 0.00023319755600814665,
|
| 1958 |
+
"loss": 1.1283,
|
| 1959 |
+
"step": 2710
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 5.44,
|
| 1963 |
+
"learning_rate": 0.00023217922606924644,
|
| 1964 |
+
"loss": 1.105,
|
| 1965 |
+
"step": 2720
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 5.46,
|
| 1969 |
+
"learning_rate": 0.00023116089613034625,
|
| 1970 |
+
"loss": 1.0968,
|
| 1971 |
+
"step": 2730
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 5.48,
|
| 1975 |
+
"learning_rate": 0.00023014256619144602,
|
| 1976 |
+
"loss": 1.0931,
|
| 1977 |
+
"step": 2740
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 5.5,
|
| 1981 |
+
"learning_rate": 0.00022912423625254583,
|
| 1982 |
+
"loss": 1.1181,
|
| 1983 |
+
"step": 2750
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 5.52,
|
| 1987 |
+
"learning_rate": 0.00022810590631364565,
|
| 1988 |
+
"loss": 1.0492,
|
| 1989 |
+
"step": 2760
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 5.54,
|
| 1993 |
+
"learning_rate": 0.0002270875763747454,
|
| 1994 |
+
"loss": 1.0888,
|
| 1995 |
+
"step": 2770
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 5.56,
|
| 1999 |
+
"learning_rate": 0.00022606924643584522,
|
| 2000 |
+
"loss": 1.0944,
|
| 2001 |
+
"step": 2780
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 5.58,
|
| 2005 |
+
"learning_rate": 0.000225050916496945,
|
| 2006 |
+
"loss": 1.0851,
|
| 2007 |
+
"step": 2790
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 5.6,
|
| 2011 |
+
"learning_rate": 0.00022403258655804482,
|
| 2012 |
+
"loss": 1.073,
|
| 2013 |
+
"step": 2800
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 5.6,
|
| 2017 |
+
"eval_loss": 0.9429187774658203,
|
| 2018 |
+
"eval_rouge1": 0.3534213889657237,
|
| 2019 |
+
"eval_rouge2": 0.1666029802662448,
|
| 2020 |
+
"eval_rougeL": 0.298122774116486,
|
| 2021 |
+
"eval_rougeLsum": 0.3017447168430196,
|
| 2022 |
+
"eval_runtime": 21.9067,
|
| 2023 |
+
"eval_samples_per_second": 0.913,
|
| 2024 |
+
"eval_steps_per_second": 0.456,
|
| 2025 |
+
"step": 2800
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 5.62,
|
| 2029 |
+
"learning_rate": 0.00022301425661914458,
|
| 2030 |
+
"loss": 1.1145,
|
| 2031 |
+
"step": 2810
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 5.64,
|
| 2035 |
+
"learning_rate": 0.0002219959266802444,
|
| 2036 |
+
"loss": 1.081,
|
| 2037 |
+
"step": 2820
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 5.66,
|
| 2041 |
+
"learning_rate": 0.00022097759674134421,
|
| 2042 |
+
"loss": 1.1057,
|
| 2043 |
+
"step": 2830
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 5.68,
|
| 2047 |
+
"learning_rate": 0.000219959266802444,
|
| 2048 |
+
"loss": 1.1037,
|
| 2049 |
+
"step": 2840
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 5.7,
|
| 2053 |
+
"learning_rate": 0.0002189409368635438,
|
| 2054 |
+
"loss": 1.0963,
|
| 2055 |
+
"step": 2850
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 5.72,
|
| 2059 |
+
"learning_rate": 0.00021792260692464358,
|
| 2060 |
+
"loss": 1.0834,
|
| 2061 |
+
"step": 2860
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 5.74,
|
| 2065 |
+
"learning_rate": 0.0002169042769857434,
|
| 2066 |
+
"loss": 1.1108,
|
| 2067 |
+
"step": 2870
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 5.76,
|
| 2071 |
+
"learning_rate": 0.0002158859470468432,
|
| 2072 |
+
"loss": 1.1077,
|
| 2073 |
+
"step": 2880
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 5.78,
|
| 2077 |
+
"learning_rate": 0.00021486761710794297,
|
| 2078 |
+
"loss": 1.0936,
|
| 2079 |
+
"step": 2890
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 5.8,
|
| 2083 |
+
"learning_rate": 0.00021384928716904278,
|
| 2084 |
+
"loss": 1.0598,
|
| 2085 |
+
"step": 2900
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 5.8,
|
| 2089 |
+
"eval_loss": 0.9476393461227417,
|
| 2090 |
+
"eval_rouge1": 0.3460493427394816,
|
| 2091 |
+
"eval_rouge2": 0.16425447886287378,
|
| 2092 |
+
"eval_rougeL": 0.29176256122671795,
|
| 2093 |
+
"eval_rougeLsum": 0.2932874710130029,
|
| 2094 |
+
"eval_runtime": 22.7632,
|
| 2095 |
+
"eval_samples_per_second": 0.879,
|
| 2096 |
+
"eval_steps_per_second": 0.439,
|
| 2097 |
+
"step": 2900
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 5.82,
|
| 2101 |
+
"learning_rate": 0.00021283095723014257,
|
| 2102 |
+
"loss": 1.1012,
|
| 2103 |
+
"step": 2910
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 5.84,
|
| 2107 |
+
"learning_rate": 0.00021181262729124236,
|
| 2108 |
+
"loss": 1.1155,
|
| 2109 |
+
"step": 2920
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 5.86,
|
| 2113 |
+
"learning_rate": 0.00021079429735234215,
|
| 2114 |
+
"loss": 1.0611,
|
| 2115 |
+
"step": 2930
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 5.88,
|
| 2119 |
+
"learning_rate": 0.00020977596741344196,
|
| 2120 |
+
"loss": 1.1044,
|
| 2121 |
+
"step": 2940
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 5.9,
|
| 2125 |
+
"learning_rate": 0.00020875763747454178,
|
| 2126 |
+
"loss": 1.0781,
|
| 2127 |
+
"step": 2950
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 5.92,
|
| 2131 |
+
"learning_rate": 0.00020773930753564154,
|
| 2132 |
+
"loss": 1.118,
|
| 2133 |
+
"step": 2960
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 5.94,
|
| 2137 |
+
"learning_rate": 0.00020672097759674135,
|
| 2138 |
+
"loss": 1.0767,
|
| 2139 |
+
"step": 2970
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 5.96,
|
| 2143 |
+
"learning_rate": 0.00020570264765784114,
|
| 2144 |
+
"loss": 1.1183,
|
| 2145 |
+
"step": 2980
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 5.98,
|
| 2149 |
+
"learning_rate": 0.00020468431771894095,
|
| 2150 |
+
"loss": 1.0675,
|
| 2151 |
+
"step": 2990
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 6.0,
|
| 2155 |
+
"learning_rate": 0.00020366598778004074,
|
| 2156 |
+
"loss": 1.0567,
|
| 2157 |
+
"step": 3000
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 6.0,
|
| 2161 |
+
"eval_loss": 0.9474280476570129,
|
| 2162 |
+
"eval_rouge1": 0.3549405529957428,
|
| 2163 |
+
"eval_rouge2": 0.17220677580168336,
|
| 2164 |
+
"eval_rougeL": 0.29622719821503607,
|
| 2165 |
+
"eval_rougeLsum": 0.29765510347367236,
|
| 2166 |
+
"eval_runtime": 21.6142,
|
| 2167 |
+
"eval_samples_per_second": 0.925,
|
| 2168 |
+
"eval_steps_per_second": 0.463,
|
| 2169 |
+
"step": 3000
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 6.02,
|
| 2173 |
+
"learning_rate": 0.00020264765784114053,
|
| 2174 |
+
"loss": 1.082,
|
| 2175 |
+
"step": 3010
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 6.04,
|
| 2179 |
+
"learning_rate": 0.00020162932790224034,
|
| 2180 |
+
"loss": 1.0653,
|
| 2181 |
+
"step": 3020
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 6.06,
|
| 2185 |
+
"learning_rate": 0.00020061099796334013,
|
| 2186 |
+
"loss": 1.0819,
|
| 2187 |
+
"step": 3030
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 6.08,
|
| 2191 |
+
"learning_rate": 0.00019959266802443992,
|
| 2192 |
+
"loss": 1.0833,
|
| 2193 |
+
"step": 3040
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 6.1,
|
| 2197 |
+
"learning_rate": 0.0001985743380855397,
|
| 2198 |
+
"loss": 1.0683,
|
| 2199 |
+
"step": 3050
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 6.12,
|
| 2203 |
+
"learning_rate": 0.00019755600814663952,
|
| 2204 |
+
"loss": 1.0805,
|
| 2205 |
+
"step": 3060
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 6.14,
|
| 2209 |
+
"learning_rate": 0.00019653767820773934,
|
| 2210 |
+
"loss": 1.0535,
|
| 2211 |
+
"step": 3070
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 6.16,
|
| 2215 |
+
"learning_rate": 0.0001955193482688391,
|
| 2216 |
+
"loss": 1.0952,
|
| 2217 |
+
"step": 3080
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 6.18,
|
| 2221 |
+
"learning_rate": 0.0001945010183299389,
|
| 2222 |
+
"loss": 1.0997,
|
| 2223 |
+
"step": 3090
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 6.2,
|
| 2227 |
+
"learning_rate": 0.0001934826883910387,
|
| 2228 |
+
"loss": 1.0773,
|
| 2229 |
+
"step": 3100
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 6.2,
|
| 2233 |
+
"eval_loss": 0.9442319869995117,
|
| 2234 |
+
"eval_rouge1": 0.3697494602820765,
|
| 2235 |
+
"eval_rouge2": 0.17309826892569075,
|
| 2236 |
+
"eval_rougeL": 0.30189218077829605,
|
| 2237 |
+
"eval_rougeLsum": 0.3058880236996683,
|
| 2238 |
+
"eval_runtime": 22.8637,
|
| 2239 |
+
"eval_samples_per_second": 0.875,
|
| 2240 |
+
"eval_steps_per_second": 0.437,
|
| 2241 |
+
"step": 3100
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 6.22,
|
| 2245 |
+
"learning_rate": 0.0001924643584521385,
|
| 2246 |
+
"loss": 1.0739,
|
| 2247 |
+
"step": 3110
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 6.24,
|
| 2251 |
+
"learning_rate": 0.00019144602851323828,
|
| 2252 |
+
"loss": 1.0964,
|
| 2253 |
+
"step": 3120
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 6.26,
|
| 2257 |
+
"learning_rate": 0.0001904276985743381,
|
| 2258 |
+
"loss": 1.0914,
|
| 2259 |
+
"step": 3130
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 6.28,
|
| 2263 |
+
"learning_rate": 0.0001894093686354379,
|
| 2264 |
+
"loss": 1.0836,
|
| 2265 |
+
"step": 3140
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 6.3,
|
| 2269 |
+
"learning_rate": 0.00018839103869653767,
|
| 2270 |
+
"loss": 1.0812,
|
| 2271 |
+
"step": 3150
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 6.32,
|
| 2275 |
+
"learning_rate": 0.00018737270875763748,
|
| 2276 |
+
"loss": 1.1139,
|
| 2277 |
+
"step": 3160
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 6.34,
|
| 2281 |
+
"learning_rate": 0.00018635437881873727,
|
| 2282 |
+
"loss": 1.0565,
|
| 2283 |
+
"step": 3170
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 6.36,
|
| 2287 |
+
"learning_rate": 0.00018533604887983708,
|
| 2288 |
+
"loss": 1.1065,
|
| 2289 |
+
"step": 3180
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 6.38,
|
| 2293 |
+
"learning_rate": 0.00018431771894093687,
|
| 2294 |
+
"loss": 1.0972,
|
| 2295 |
+
"step": 3190
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 6.4,
|
| 2299 |
+
"learning_rate": 0.00018329938900203666,
|
| 2300 |
+
"loss": 1.0704,
|
| 2301 |
+
"step": 3200
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 6.4,
|
| 2305 |
+
"eval_loss": 0.9415400624275208,
|
| 2306 |
+
"eval_rouge1": 0.3552015796577298,
|
| 2307 |
+
"eval_rouge2": 0.17624288378508868,
|
| 2308 |
+
"eval_rougeL": 0.29158581025602837,
|
| 2309 |
+
"eval_rougeLsum": 0.2947848268366889,
|
| 2310 |
+
"eval_runtime": 21.6045,
|
| 2311 |
+
"eval_samples_per_second": 0.926,
|
| 2312 |
+
"eval_steps_per_second": 0.463,
|
| 2313 |
+
"step": 3200
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 6.42,
|
| 2317 |
+
"learning_rate": 0.00018228105906313647,
|
| 2318 |
+
"loss": 1.0911,
|
| 2319 |
+
"step": 3210
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 6.44,
|
| 2323 |
+
"learning_rate": 0.00018126272912423623,
|
| 2324 |
+
"loss": 1.1143,
|
| 2325 |
+
"step": 3220
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 6.46,
|
| 2329 |
+
"learning_rate": 0.00018024439918533605,
|
| 2330 |
+
"loss": 1.0511,
|
| 2331 |
+
"step": 3230
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 6.48,
|
| 2335 |
+
"learning_rate": 0.00017922606924643584,
|
| 2336 |
+
"loss": 1.0629,
|
| 2337 |
+
"step": 3240
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 6.5,
|
| 2341 |
+
"learning_rate": 0.00017820773930753565,
|
| 2342 |
+
"loss": 1.0291,
|
| 2343 |
+
"step": 3250
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 6.52,
|
| 2347 |
+
"learning_rate": 0.00017718940936863544,
|
| 2348 |
+
"loss": 1.0673,
|
| 2349 |
+
"step": 3260
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 6.54,
|
| 2353 |
+
"learning_rate": 0.00017617107942973523,
|
| 2354 |
+
"loss": 1.0804,
|
| 2355 |
+
"step": 3270
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 6.56,
|
| 2359 |
+
"learning_rate": 0.00017515274949083504,
|
| 2360 |
+
"loss": 1.0569,
|
| 2361 |
+
"step": 3280
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 6.58,
|
| 2365 |
+
"learning_rate": 0.00017413441955193483,
|
| 2366 |
+
"loss": 1.086,
|
| 2367 |
+
"step": 3290
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 6.6,
|
| 2371 |
+
"learning_rate": 0.00017311608961303462,
|
| 2372 |
+
"loss": 1.0676,
|
| 2373 |
+
"step": 3300
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 6.6,
|
| 2377 |
+
"eval_loss": 0.9348514676094055,
|
| 2378 |
+
"eval_rouge1": 0.37110363769688715,
|
| 2379 |
+
"eval_rouge2": 0.18311514856569724,
|
| 2380 |
+
"eval_rougeL": 0.3001004216892586,
|
| 2381 |
+
"eval_rougeLsum": 0.30109761355013054,
|
| 2382 |
+
"eval_runtime": 22.0391,
|
| 2383 |
+
"eval_samples_per_second": 0.907,
|
| 2384 |
+
"eval_steps_per_second": 0.454,
|
| 2385 |
+
"step": 3300
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 6.62,
|
| 2389 |
+
"learning_rate": 0.00017209775967413443,
|
| 2390 |
+
"loss": 1.0646,
|
| 2391 |
+
"step": 3310
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 6.64,
|
| 2395 |
+
"learning_rate": 0.00017107942973523422,
|
| 2396 |
+
"loss": 1.1062,
|
| 2397 |
+
"step": 3320
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 6.66,
|
| 2401 |
+
"learning_rate": 0.00017006109979633404,
|
| 2402 |
+
"loss": 1.0522,
|
| 2403 |
+
"step": 3330
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 6.68,
|
| 2407 |
+
"learning_rate": 0.0001690427698574338,
|
| 2408 |
+
"loss": 1.0598,
|
| 2409 |
+
"step": 3340
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 6.7,
|
| 2413 |
+
"learning_rate": 0.0001680244399185336,
|
| 2414 |
+
"loss": 1.0777,
|
| 2415 |
+
"step": 3350
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 6.72,
|
| 2419 |
+
"learning_rate": 0.0001670061099796334,
|
| 2420 |
+
"loss": 1.0967,
|
| 2421 |
+
"step": 3360
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 6.74,
|
| 2425 |
+
"learning_rate": 0.00016598778004073319,
|
| 2426 |
+
"loss": 1.0654,
|
| 2427 |
+
"step": 3370
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 6.76,
|
| 2431 |
+
"learning_rate": 0.000164969450101833,
|
| 2432 |
+
"loss": 1.0776,
|
| 2433 |
+
"step": 3380
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 6.78,
|
| 2437 |
+
"learning_rate": 0.0001639511201629328,
|
| 2438 |
+
"loss": 1.126,
|
| 2439 |
+
"step": 3390
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 6.8,
|
| 2443 |
+
"learning_rate": 0.0001629327902240326,
|
| 2444 |
+
"loss": 1.1015,
|
| 2445 |
+
"step": 3400
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 6.8,
|
| 2449 |
+
"eval_loss": 0.9340616464614868,
|
| 2450 |
+
"eval_rouge1": 0.3645773285826771,
|
| 2451 |
+
"eval_rouge2": 0.1797763488186414,
|
| 2452 |
+
"eval_rougeL": 0.3043672589098563,
|
| 2453 |
+
"eval_rougeLsum": 0.30620848729732686,
|
| 2454 |
+
"eval_runtime": 22.359,
|
| 2455 |
+
"eval_samples_per_second": 0.894,
|
| 2456 |
+
"eval_steps_per_second": 0.447,
|
| 2457 |
+
"step": 3400
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 6.82,
|
| 2461 |
+
"learning_rate": 0.00016191446028513236,
|
| 2462 |
+
"loss": 1.0782,
|
| 2463 |
+
"step": 3410
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 6.84,
|
| 2467 |
+
"learning_rate": 0.00016089613034623218,
|
| 2468 |
+
"loss": 1.0664,
|
| 2469 |
+
"step": 3420
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 6.86,
|
| 2473 |
+
"learning_rate": 0.000159877800407332,
|
| 2474 |
+
"loss": 1.0867,
|
| 2475 |
+
"step": 3430
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 6.88,
|
| 2479 |
+
"learning_rate": 0.00015885947046843178,
|
| 2480 |
+
"loss": 1.0813,
|
| 2481 |
+
"step": 3440
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 6.9,
|
| 2485 |
+
"learning_rate": 0.00015784114052953157,
|
| 2486 |
+
"loss": 1.0541,
|
| 2487 |
+
"step": 3450
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 6.92,
|
| 2491 |
+
"learning_rate": 0.00015682281059063136,
|
| 2492 |
+
"loss": 1.0479,
|
| 2493 |
+
"step": 3460
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 6.94,
|
| 2497 |
+
"learning_rate": 0.00015580448065173117,
|
| 2498 |
+
"loss": 1.0574,
|
| 2499 |
+
"step": 3470
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 6.96,
|
| 2503 |
+
"learning_rate": 0.00015478615071283096,
|
| 2504 |
+
"loss": 1.0775,
|
| 2505 |
+
"step": 3480
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 6.98,
|
| 2509 |
+
"learning_rate": 0.00015376782077393075,
|
| 2510 |
+
"loss": 1.0567,
|
| 2511 |
+
"step": 3490
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 7.0,
|
| 2515 |
+
"learning_rate": 0.00015274949083503056,
|
| 2516 |
+
"loss": 1.0895,
|
| 2517 |
+
"step": 3500
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 7.0,
|
| 2521 |
+
"eval_loss": 0.9335128664970398,
|
| 2522 |
+
"eval_rouge1": 0.3564737046975759,
|
| 2523 |
+
"eval_rouge2": 0.17665902660761595,
|
| 2524 |
+
"eval_rougeL": 0.2936209010289881,
|
| 2525 |
+
"eval_rougeLsum": 0.29567036214117715,
|
| 2526 |
+
"eval_runtime": 21.7504,
|
| 2527 |
+
"eval_samples_per_second": 0.92,
|
| 2528 |
+
"eval_steps_per_second": 0.46,
|
| 2529 |
+
"step": 3500
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 7.02,
|
| 2533 |
+
"learning_rate": 0.00015173116089613035,
|
| 2534 |
+
"loss": 1.019,
|
| 2535 |
+
"step": 3510
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 7.04,
|
| 2539 |
+
"learning_rate": 0.00015071283095723014,
|
| 2540 |
+
"loss": 1.0701,
|
| 2541 |
+
"step": 3520
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 7.06,
|
| 2545 |
+
"learning_rate": 0.00014969450101832993,
|
| 2546 |
+
"loss": 1.064,
|
| 2547 |
+
"step": 3530
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 7.08,
|
| 2551 |
+
"learning_rate": 0.00014867617107942974,
|
| 2552 |
+
"loss": 1.0464,
|
| 2553 |
+
"step": 3540
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 7.1,
|
| 2557 |
+
"learning_rate": 0.00014765784114052956,
|
| 2558 |
+
"loss": 1.0958,
|
| 2559 |
+
"step": 3550
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 7.12,
|
| 2563 |
+
"learning_rate": 0.00014663951120162932,
|
| 2564 |
+
"loss": 1.0458,
|
| 2565 |
+
"step": 3560
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 7.14,
|
| 2569 |
+
"learning_rate": 0.00014562118126272913,
|
| 2570 |
+
"loss": 1.0012,
|
| 2571 |
+
"step": 3570
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 7.16,
|
| 2575 |
+
"learning_rate": 0.00014460285132382892,
|
| 2576 |
+
"loss": 1.0629,
|
| 2577 |
+
"step": 3580
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 7.18,
|
| 2581 |
+
"learning_rate": 0.00014358452138492873,
|
| 2582 |
+
"loss": 1.049,
|
| 2583 |
+
"step": 3590
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 7.2,
|
| 2587 |
+
"learning_rate": 0.0001425661914460285,
|
| 2588 |
+
"loss": 1.0839,
|
| 2589 |
+
"step": 3600
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 7.2,
|
| 2593 |
+
"eval_loss": 0.9262797236442566,
|
| 2594 |
+
"eval_rouge1": 0.3608261849266158,
|
| 2595 |
+
"eval_rouge2": 0.16796265957036072,
|
| 2596 |
+
"eval_rougeL": 0.300587364099427,
|
| 2597 |
+
"eval_rougeLsum": 0.3018268665573097,
|
| 2598 |
+
"eval_runtime": 22.8495,
|
| 2599 |
+
"eval_samples_per_second": 0.875,
|
| 2600 |
+
"eval_steps_per_second": 0.438,
|
| 2601 |
+
"step": 3600
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 7.22,
|
| 2605 |
+
"learning_rate": 0.0001415478615071283,
|
| 2606 |
+
"loss": 1.0231,
|
| 2607 |
+
"step": 3610
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 7.24,
|
| 2611 |
+
"learning_rate": 0.00014052953156822812,
|
| 2612 |
+
"loss": 1.043,
|
| 2613 |
+
"step": 3620
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 7.26,
|
| 2617 |
+
"learning_rate": 0.0001395112016293279,
|
| 2618 |
+
"loss": 1.0423,
|
| 2619 |
+
"step": 3630
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 7.28,
|
| 2623 |
+
"learning_rate": 0.0001384928716904277,
|
| 2624 |
+
"loss": 1.1131,
|
| 2625 |
+
"step": 3640
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"epoch": 7.3,
|
| 2629 |
+
"learning_rate": 0.0001374745417515275,
|
| 2630 |
+
"loss": 1.0106,
|
| 2631 |
+
"step": 3650
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 7.32,
|
| 2635 |
+
"learning_rate": 0.0001364562118126273,
|
| 2636 |
+
"loss": 1.0663,
|
| 2637 |
+
"step": 3660
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 7.34,
|
| 2641 |
+
"learning_rate": 0.0001354378818737271,
|
| 2642 |
+
"loss": 1.0842,
|
| 2643 |
+
"step": 3670
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 7.36,
|
| 2647 |
+
"learning_rate": 0.00013441955193482688,
|
| 2648 |
+
"loss": 1.0482,
|
| 2649 |
+
"step": 3680
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 7.38,
|
| 2653 |
+
"learning_rate": 0.0001334012219959267,
|
| 2654 |
+
"loss": 1.1137,
|
| 2655 |
+
"step": 3690
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 7.4,
|
| 2659 |
+
"learning_rate": 0.00013238289205702648,
|
| 2660 |
+
"loss": 1.0737,
|
| 2661 |
+
"step": 3700
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 7.4,
|
| 2665 |
+
"eval_loss": 0.9295714497566223,
|
| 2666 |
+
"eval_rouge1": 0.35713241736503193,
|
| 2667 |
+
"eval_rouge2": 0.18064337174705725,
|
| 2668 |
+
"eval_rougeL": 0.2977802249700461,
|
| 2669 |
+
"eval_rougeLsum": 0.2990767538657372,
|
| 2670 |
+
"eval_runtime": 21.6594,
|
| 2671 |
+
"eval_samples_per_second": 0.923,
|
| 2672 |
+
"eval_steps_per_second": 0.462,
|
| 2673 |
+
"step": 3700
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 7.42,
|
| 2677 |
+
"learning_rate": 0.00013136456211812627,
|
| 2678 |
+
"loss": 1.0793,
|
| 2679 |
+
"step": 3710
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 7.44,
|
| 2683 |
+
"learning_rate": 0.00013034623217922606,
|
| 2684 |
+
"loss": 1.0964,
|
| 2685 |
+
"step": 3720
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 7.46,
|
| 2689 |
+
"learning_rate": 0.00012932790224032587,
|
| 2690 |
+
"loss": 1.0471,
|
| 2691 |
+
"step": 3730
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 7.48,
|
| 2695 |
+
"learning_rate": 0.00012830957230142569,
|
| 2696 |
+
"loss": 1.0647,
|
| 2697 |
+
"step": 3740
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 7.5,
|
| 2701 |
+
"learning_rate": 0.00012729124236252545,
|
| 2702 |
+
"loss": 1.095,
|
| 2703 |
+
"step": 3750
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 7.52,
|
| 2707 |
+
"learning_rate": 0.00012627291242362526,
|
| 2708 |
+
"loss": 1.0891,
|
| 2709 |
+
"step": 3760
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 7.54,
|
| 2713 |
+
"learning_rate": 0.00012525458248472505,
|
| 2714 |
+
"loss": 1.0876,
|
| 2715 |
+
"step": 3770
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 7.56,
|
| 2719 |
+
"learning_rate": 0.00012423625254582486,
|
| 2720 |
+
"loss": 1.0112,
|
| 2721 |
+
"step": 3780
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 7.58,
|
| 2725 |
+
"learning_rate": 0.00012321792260692465,
|
| 2726 |
+
"loss": 1.0352,
|
| 2727 |
+
"step": 3790
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 7.6,
|
| 2731 |
+
"learning_rate": 0.00012219959266802444,
|
| 2732 |
+
"loss": 1.0549,
|
| 2733 |
+
"step": 3800
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 7.6,
|
| 2737 |
+
"eval_loss": 0.9341118931770325,
|
| 2738 |
+
"eval_rouge1": 0.35969569162284754,
|
| 2739 |
+
"eval_rouge2": 0.17023162775203884,
|
| 2740 |
+
"eval_rougeL": 0.28257423918684926,
|
| 2741 |
+
"eval_rougeLsum": 0.28412150462963986,
|
| 2742 |
+
"eval_runtime": 22.2811,
|
| 2743 |
+
"eval_samples_per_second": 0.898,
|
| 2744 |
+
"eval_steps_per_second": 0.449,
|
| 2745 |
+
"step": 3800
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 7.62,
|
| 2749 |
+
"learning_rate": 0.00012118126272912423,
|
| 2750 |
+
"loss": 1.0636,
|
| 2751 |
+
"step": 3810
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 7.64,
|
| 2755 |
+
"learning_rate": 0.00012016293279022404,
|
| 2756 |
+
"loss": 1.0719,
|
| 2757 |
+
"step": 3820
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 7.66,
|
| 2761 |
+
"learning_rate": 0.00011914460285132383,
|
| 2762 |
+
"loss": 1.0451,
|
| 2763 |
+
"step": 3830
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 7.68,
|
| 2767 |
+
"learning_rate": 0.00011812627291242363,
|
| 2768 |
+
"loss": 1.0509,
|
| 2769 |
+
"step": 3840
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 7.7,
|
| 2773 |
+
"learning_rate": 0.00011710794297352342,
|
| 2774 |
+
"loss": 1.0515,
|
| 2775 |
+
"step": 3850
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 7.72,
|
| 2779 |
+
"learning_rate": 0.00011608961303462322,
|
| 2780 |
+
"loss": 1.0525,
|
| 2781 |
+
"step": 3860
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 7.74,
|
| 2785 |
+
"learning_rate": 0.00011507128309572301,
|
| 2786 |
+
"loss": 1.0751,
|
| 2787 |
+
"step": 3870
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 7.76,
|
| 2791 |
+
"learning_rate": 0.00011405295315682282,
|
| 2792 |
+
"loss": 1.059,
|
| 2793 |
+
"step": 3880
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 7.78,
|
| 2797 |
+
"learning_rate": 0.00011303462321792261,
|
| 2798 |
+
"loss": 1.0352,
|
| 2799 |
+
"step": 3890
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 7.8,
|
| 2803 |
+
"learning_rate": 0.00011201629327902241,
|
| 2804 |
+
"loss": 1.065,
|
| 2805 |
+
"step": 3900
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 7.8,
|
| 2809 |
+
"eval_loss": 0.9318963885307312,
|
| 2810 |
+
"eval_rouge1": 0.36719535582225143,
|
| 2811 |
+
"eval_rouge2": 0.18487793490577756,
|
| 2812 |
+
"eval_rougeL": 0.3063474590760422,
|
| 2813 |
+
"eval_rougeLsum": 0.3072518409290927,
|
| 2814 |
+
"eval_runtime": 22.5338,
|
| 2815 |
+
"eval_samples_per_second": 0.888,
|
| 2816 |
+
"eval_steps_per_second": 0.444,
|
| 2817 |
+
"step": 3900
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 7.82,
|
| 2821 |
+
"learning_rate": 0.0001109979633401222,
|
| 2822 |
+
"loss": 1.0591,
|
| 2823 |
+
"step": 3910
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 7.84,
|
| 2827 |
+
"learning_rate": 0.000109979633401222,
|
| 2828 |
+
"loss": 1.0553,
|
| 2829 |
+
"step": 3920
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 7.86,
|
| 2833 |
+
"learning_rate": 0.00010896130346232179,
|
| 2834 |
+
"loss": 1.0766,
|
| 2835 |
+
"step": 3930
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"epoch": 7.88,
|
| 2839 |
+
"learning_rate": 0.0001079429735234216,
|
| 2840 |
+
"loss": 1.0434,
|
| 2841 |
+
"step": 3940
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 7.9,
|
| 2845 |
+
"learning_rate": 0.00010692464358452139,
|
| 2846 |
+
"loss": 1.0453,
|
| 2847 |
+
"step": 3950
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 7.92,
|
| 2851 |
+
"learning_rate": 0.00010590631364562118,
|
| 2852 |
+
"loss": 1.0754,
|
| 2853 |
+
"step": 3960
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 7.94,
|
| 2857 |
+
"learning_rate": 0.00010488798370672098,
|
| 2858 |
+
"loss": 1.0754,
|
| 2859 |
+
"step": 3970
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 7.96,
|
| 2863 |
+
"learning_rate": 0.00010386965376782077,
|
| 2864 |
+
"loss": 1.0743,
|
| 2865 |
+
"step": 3980
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 7.98,
|
| 2869 |
+
"learning_rate": 0.00010285132382892057,
|
| 2870 |
+
"loss": 1.0792,
|
| 2871 |
+
"step": 3990
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 8.0,
|
| 2875 |
+
"learning_rate": 0.00010183299389002037,
|
| 2876 |
+
"loss": 1.0676,
|
| 2877 |
+
"step": 4000
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 8.0,
|
| 2881 |
+
"eval_loss": 0.9239376783370972,
|
| 2882 |
+
"eval_rouge1": 0.3708780006445588,
|
| 2883 |
+
"eval_rouge2": 0.18486714155230236,
|
| 2884 |
+
"eval_rougeL": 0.30909528682097154,
|
| 2885 |
+
"eval_rougeLsum": 0.31117436309534663,
|
| 2886 |
+
"eval_runtime": 22.2042,
|
| 2887 |
+
"eval_samples_per_second": 0.901,
|
| 2888 |
+
"eval_steps_per_second": 0.45,
|
| 2889 |
+
"step": 4000
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 8.02,
|
| 2893 |
+
"learning_rate": 0.00010081466395112017,
|
| 2894 |
+
"loss": 1.0105,
|
| 2895 |
+
"step": 4010
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 8.04,
|
| 2899 |
+
"learning_rate": 9.979633401221996e-05,
|
| 2900 |
+
"loss": 1.0505,
|
| 2901 |
+
"step": 4020
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 8.06,
|
| 2905 |
+
"learning_rate": 9.877800407331976e-05,
|
| 2906 |
+
"loss": 1.0375,
|
| 2907 |
+
"step": 4030
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 8.08,
|
| 2911 |
+
"learning_rate": 9.775967413441955e-05,
|
| 2912 |
+
"loss": 1.0465,
|
| 2913 |
+
"step": 4040
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 8.1,
|
| 2917 |
+
"learning_rate": 9.674134419551935e-05,
|
| 2918 |
+
"loss": 1.0249,
|
| 2919 |
+
"step": 4050
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 8.12,
|
| 2923 |
+
"learning_rate": 9.572301425661914e-05,
|
| 2924 |
+
"loss": 1.0806,
|
| 2925 |
+
"step": 4060
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 8.14,
|
| 2929 |
+
"learning_rate": 9.470468431771895e-05,
|
| 2930 |
+
"loss": 1.0233,
|
| 2931 |
+
"step": 4070
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 8.16,
|
| 2935 |
+
"learning_rate": 9.368635437881874e-05,
|
| 2936 |
+
"loss": 1.0605,
|
| 2937 |
+
"step": 4080
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 8.18,
|
| 2941 |
+
"learning_rate": 9.266802443991854e-05,
|
| 2942 |
+
"loss": 1.0336,
|
| 2943 |
+
"step": 4090
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 8.2,
|
| 2947 |
+
"learning_rate": 9.164969450101833e-05,
|
| 2948 |
+
"loss": 1.0327,
|
| 2949 |
+
"step": 4100
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 8.2,
|
| 2953 |
+
"eval_loss": 0.9313555955886841,
|
| 2954 |
+
"eval_rouge1": 0.3612621102138621,
|
| 2955 |
+
"eval_rouge2": 0.17914853351838206,
|
| 2956 |
+
"eval_rougeL": 0.3058448839143484,
|
| 2957 |
+
"eval_rougeLsum": 0.30736619803392246,
|
| 2958 |
+
"eval_runtime": 21.8087,
|
| 2959 |
+
"eval_samples_per_second": 0.917,
|
| 2960 |
+
"eval_steps_per_second": 0.459,
|
| 2961 |
+
"step": 4100
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 8.22,
|
| 2965 |
+
"learning_rate": 9.063136456211812e-05,
|
| 2966 |
+
"loss": 1.0526,
|
| 2967 |
+
"step": 4110
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 8.24,
|
| 2971 |
+
"learning_rate": 8.961303462321792e-05,
|
| 2972 |
+
"loss": 1.0063,
|
| 2973 |
+
"step": 4120
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 8.26,
|
| 2977 |
+
"learning_rate": 8.859470468431772e-05,
|
| 2978 |
+
"loss": 1.071,
|
| 2979 |
+
"step": 4130
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 8.28,
|
| 2983 |
+
"learning_rate": 8.757637474541752e-05,
|
| 2984 |
+
"loss": 1.06,
|
| 2985 |
+
"step": 4140
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 8.3,
|
| 2989 |
+
"learning_rate": 8.655804480651731e-05,
|
| 2990 |
+
"loss": 1.016,
|
| 2991 |
+
"step": 4150
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 8.32,
|
| 2995 |
+
"learning_rate": 8.553971486761711e-05,
|
| 2996 |
+
"loss": 1.0764,
|
| 2997 |
+
"step": 4160
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 8.34,
|
| 3001 |
+
"learning_rate": 8.45213849287169e-05,
|
| 3002 |
+
"loss": 1.0446,
|
| 3003 |
+
"step": 4170
|
| 3004 |
+
},
|
| 3005 |
+
{
|
| 3006 |
+
"epoch": 8.36,
|
| 3007 |
+
"learning_rate": 8.35030549898167e-05,
|
| 3008 |
+
"loss": 1.0479,
|
| 3009 |
+
"step": 4180
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 8.38,
|
| 3013 |
+
"learning_rate": 8.24847250509165e-05,
|
| 3014 |
+
"loss": 1.0283,
|
| 3015 |
+
"step": 4190
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 8.4,
|
| 3019 |
+
"learning_rate": 8.14663951120163e-05,
|
| 3020 |
+
"loss": 1.0532,
|
| 3021 |
+
"step": 4200
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 8.4,
|
| 3025 |
+
"eval_loss": 0.9309422373771667,
|
| 3026 |
+
"eval_rouge1": 0.3629265409740602,
|
| 3027 |
+
"eval_rouge2": 0.18256578670757062,
|
| 3028 |
+
"eval_rougeL": 0.30644935758402025,
|
| 3029 |
+
"eval_rougeLsum": 0.3074292385019225,
|
| 3030 |
+
"eval_runtime": 21.7991,
|
| 3031 |
+
"eval_samples_per_second": 0.917,
|
| 3032 |
+
"eval_steps_per_second": 0.459,
|
| 3033 |
+
"step": 4200
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 8.42,
|
| 3037 |
+
"learning_rate": 8.044806517311609e-05,
|
| 3038 |
+
"loss": 1.0408,
|
| 3039 |
+
"step": 4210
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 8.44,
|
| 3043 |
+
"learning_rate": 7.942973523421589e-05,
|
| 3044 |
+
"loss": 1.0554,
|
| 3045 |
+
"step": 4220
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"epoch": 8.46,
|
| 3049 |
+
"learning_rate": 7.841140529531568e-05,
|
| 3050 |
+
"loss": 1.086,
|
| 3051 |
+
"step": 4230
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 8.48,
|
| 3055 |
+
"learning_rate": 7.739307535641548e-05,
|
| 3056 |
+
"loss": 1.0316,
|
| 3057 |
+
"step": 4240
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 8.5,
|
| 3061 |
+
"learning_rate": 7.637474541751528e-05,
|
| 3062 |
+
"loss": 1.052,
|
| 3063 |
+
"step": 4250
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 8.52,
|
| 3067 |
+
"learning_rate": 7.535641547861507e-05,
|
| 3068 |
+
"loss": 1.0419,
|
| 3069 |
+
"step": 4260
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 8.54,
|
| 3073 |
+
"learning_rate": 7.433808553971487e-05,
|
| 3074 |
+
"loss": 1.0657,
|
| 3075 |
+
"step": 4270
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 8.56,
|
| 3079 |
+
"learning_rate": 7.331975560081466e-05,
|
| 3080 |
+
"loss": 1.03,
|
| 3081 |
+
"step": 4280
|
| 3082 |
+
},
|
| 3083 |
+
{
|
| 3084 |
+
"epoch": 8.58,
|
| 3085 |
+
"learning_rate": 7.230142566191446e-05,
|
| 3086 |
+
"loss": 1.042,
|
| 3087 |
+
"step": 4290
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 8.6,
|
| 3091 |
+
"learning_rate": 7.128309572301425e-05,
|
| 3092 |
+
"loss": 1.0649,
|
| 3093 |
+
"step": 4300
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 8.6,
|
| 3097 |
+
"eval_loss": 0.9269277453422546,
|
| 3098 |
+
"eval_rouge1": 0.3670666365189951,
|
| 3099 |
+
"eval_rouge2": 0.18356209763485815,
|
| 3100 |
+
"eval_rougeL": 0.3012090907355077,
|
| 3101 |
+
"eval_rougeLsum": 0.3039222282541081,
|
| 3102 |
+
"eval_runtime": 22.1694,
|
| 3103 |
+
"eval_samples_per_second": 0.902,
|
| 3104 |
+
"eval_steps_per_second": 0.451,
|
| 3105 |
+
"step": 4300
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 8.62,
|
| 3109 |
+
"learning_rate": 7.026476578411406e-05,
|
| 3110 |
+
"loss": 1.0671,
|
| 3111 |
+
"step": 4310
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 8.64,
|
| 3115 |
+
"learning_rate": 6.924643584521385e-05,
|
| 3116 |
+
"loss": 1.0237,
|
| 3117 |
+
"step": 4320
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 8.66,
|
| 3121 |
+
"learning_rate": 6.822810590631365e-05,
|
| 3122 |
+
"loss": 1.0582,
|
| 3123 |
+
"step": 4330
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 8.68,
|
| 3127 |
+
"learning_rate": 6.720977596741344e-05,
|
| 3128 |
+
"loss": 1.0325,
|
| 3129 |
+
"step": 4340
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 8.7,
|
| 3133 |
+
"learning_rate": 6.619144602851324e-05,
|
| 3134 |
+
"loss": 1.0474,
|
| 3135 |
+
"step": 4350
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 8.72,
|
| 3139 |
+
"learning_rate": 6.517311608961303e-05,
|
| 3140 |
+
"loss": 1.0346,
|
| 3141 |
+
"step": 4360
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 8.74,
|
| 3145 |
+
"learning_rate": 6.415478615071284e-05,
|
| 3146 |
+
"loss": 1.063,
|
| 3147 |
+
"step": 4370
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 8.76,
|
| 3151 |
+
"learning_rate": 6.313645621181263e-05,
|
| 3152 |
+
"loss": 1.0337,
|
| 3153 |
+
"step": 4380
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 8.78,
|
| 3157 |
+
"learning_rate": 6.211812627291243e-05,
|
| 3158 |
+
"loss": 1.0531,
|
| 3159 |
+
"step": 4390
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 8.8,
|
| 3163 |
+
"learning_rate": 6.109979633401222e-05,
|
| 3164 |
+
"loss": 1.073,
|
| 3165 |
+
"step": 4400
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 8.8,
|
| 3169 |
+
"eval_loss": 0.9253420829772949,
|
| 3170 |
+
"eval_rouge1": 0.3653533114499009,
|
| 3171 |
+
"eval_rouge2": 0.17889561755188924,
|
| 3172 |
+
"eval_rougeL": 0.30070525024462247,
|
| 3173 |
+
"eval_rougeLsum": 0.3024312386336895,
|
| 3174 |
+
"eval_runtime": 21.8579,
|
| 3175 |
+
"eval_samples_per_second": 0.915,
|
| 3176 |
+
"eval_steps_per_second": 0.458,
|
| 3177 |
+
"step": 4400
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 8.82,
|
| 3181 |
+
"learning_rate": 6.008146639511202e-05,
|
| 3182 |
+
"loss": 1.0716,
|
| 3183 |
+
"step": 4410
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 8.84,
|
| 3187 |
+
"learning_rate": 5.9063136456211815e-05,
|
| 3188 |
+
"loss": 1.0522,
|
| 3189 |
+
"step": 4420
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 8.86,
|
| 3193 |
+
"learning_rate": 5.804480651731161e-05,
|
| 3194 |
+
"loss": 1.0401,
|
| 3195 |
+
"step": 4430
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 8.88,
|
| 3199 |
+
"learning_rate": 5.702647657841141e-05,
|
| 3200 |
+
"loss": 1.0178,
|
| 3201 |
+
"step": 4440
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 8.9,
|
| 3205 |
+
"learning_rate": 5.6008146639511206e-05,
|
| 3206 |
+
"loss": 1.1043,
|
| 3207 |
+
"step": 4450
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 8.92,
|
| 3211 |
+
"learning_rate": 5.4989816700611e-05,
|
| 3212 |
+
"loss": 1.0424,
|
| 3213 |
+
"step": 4460
|
| 3214 |
+
},
|
| 3215 |
+
{
|
| 3216 |
+
"epoch": 8.94,
|
| 3217 |
+
"learning_rate": 5.39714867617108e-05,
|
| 3218 |
+
"loss": 1.0599,
|
| 3219 |
+
"step": 4470
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 8.96,
|
| 3223 |
+
"learning_rate": 5.295315682281059e-05,
|
| 3224 |
+
"loss": 1.0331,
|
| 3225 |
+
"step": 4480
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 8.98,
|
| 3229 |
+
"learning_rate": 5.1934826883910384e-05,
|
| 3230 |
+
"loss": 1.0467,
|
| 3231 |
+
"step": 4490
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 9.0,
|
| 3235 |
+
"learning_rate": 5.0916496945010185e-05,
|
| 3236 |
+
"loss": 1.0491,
|
| 3237 |
+
"step": 4500
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 9.0,
|
| 3241 |
+
"eval_loss": 0.9241307973861694,
|
| 3242 |
+
"eval_rouge1": 0.3664328537702999,
|
| 3243 |
+
"eval_rouge2": 0.18102691382663055,
|
| 3244 |
+
"eval_rougeL": 0.2998899427822319,
|
| 3245 |
+
"eval_rougeLsum": 0.301943630367904,
|
| 3246 |
+
"eval_runtime": 22.1092,
|
| 3247 |
+
"eval_samples_per_second": 0.905,
|
| 3248 |
+
"eval_steps_per_second": 0.452,
|
| 3249 |
+
"step": 4500
|
| 3250 |
+
}
|
| 3251 |
+
],
|
| 3252 |
+
"logging_steps": 10,
|
| 3253 |
+
"max_steps": 5000,
|
| 3254 |
+
"num_input_tokens_seen": 0,
|
| 3255 |
+
"num_train_epochs": 10,
|
| 3256 |
+
"save_steps": 500,
|
| 3257 |
+
"total_flos": 3.0455982194688e+17,
|
| 3258 |
+
"train_batch_size": 4,
|
| 3259 |
+
"trial_name": null,
|
| 3260 |
+
"trial_params": null
|
| 3261 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f88382c56410581ffd5ccbae54944d036343700176e572c15a967f7dbdaf2952
|
| 3 |
+
size 4792
|