Upload 12 files
Browse files- .gitattributes +1 -0
- config.json +33 -0
- generation_config.json +7 -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 +2461 -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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 1024,
|
| 20 |
+
"model_type": "mt5",
|
| 21 |
+
"num_decoder_layers": 8,
|
| 22 |
+
"num_heads": 6,
|
| 23 |
+
"num_layers": 8,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "T5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.37.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 250112
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"max_length": 1024,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c95ad1a49dd4a6a975f7124006822d255d8197df7cbc7862b7824a2a9e00db8b
|
| 3 |
+
size 1200729512
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f17f9b17033787f46b303f16f8fd40f6777f416f5e5658486ab0de566c4a05
|
| 3 |
+
size 2401574330
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307bbe15658713574c0b996b26e29048ee2e31bf283d936219e28dd7975d7832
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c5df2030891c0dfdaeabdb7935c129f217c8ddcc79ea0dd94e98567de8cdfb
|
| 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 sha256:722bf80470f2ae6a7cfeaaaf876fb7ef9ad33b2e9a514ded463498f4a8bbd6be
|
| 3 |
+
size 16330661
|
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": 1024,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 26.5388,
|
| 3 |
+
"best_model_checkpoint": "output/checkpoint-200000",
|
| 4 |
+
"epoch": 14.498006524102935,
|
| 5 |
+
"eval_steps": 50000,
|
| 6 |
+
"global_step": 200000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 1.9951673311586325e-05,
|
| 14 |
+
"loss": 12.9031,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 1.9903346623172648e-05,
|
| 20 |
+
"loss": 4.995,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 1.985501993475897e-05,
|
| 26 |
+
"loss": 4.013,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.14,
|
| 31 |
+
"learning_rate": 1.9806693246345298e-05,
|
| 32 |
+
"loss": 3.7433,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.18,
|
| 37 |
+
"learning_rate": 1.9758366557931618e-05,
|
| 38 |
+
"loss": 3.5754,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 1.9710039869517944e-05,
|
| 44 |
+
"loss": 3.4371,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.25,
|
| 49 |
+
"learning_rate": 1.9661713181104268e-05,
|
| 50 |
+
"loss": 3.3418,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.29,
|
| 55 |
+
"learning_rate": 1.961338649269059e-05,
|
| 56 |
+
"loss": 3.2642,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.33,
|
| 61 |
+
"learning_rate": 1.9565059804276914e-05,
|
| 62 |
+
"loss": 3.2133,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.36,
|
| 67 |
+
"learning_rate": 1.9516733115863237e-05,
|
| 68 |
+
"loss": 3.1533,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.4,
|
| 73 |
+
"learning_rate": 1.946840642744956e-05,
|
| 74 |
+
"loss": 3.1304,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.43,
|
| 79 |
+
"learning_rate": 1.9420079739035884e-05,
|
| 80 |
+
"loss": 3.0707,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.47,
|
| 85 |
+
"learning_rate": 1.9371753050622207e-05,
|
| 86 |
+
"loss": 3.0091,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.51,
|
| 91 |
+
"learning_rate": 1.932342636220853e-05,
|
| 92 |
+
"loss": 2.9992,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.54,
|
| 97 |
+
"learning_rate": 1.9275099673794853e-05,
|
| 98 |
+
"loss": 2.9653,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.58,
|
| 103 |
+
"learning_rate": 1.922677298538118e-05,
|
| 104 |
+
"loss": 2.9463,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.62,
|
| 109 |
+
"learning_rate": 1.91784462969675e-05,
|
| 110 |
+
"loss": 2.9304,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.65,
|
| 115 |
+
"learning_rate": 1.9130119608553827e-05,
|
| 116 |
+
"loss": 2.8825,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.69,
|
| 121 |
+
"learning_rate": 1.908179292014015e-05,
|
| 122 |
+
"loss": 2.863,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.72,
|
| 127 |
+
"learning_rate": 1.9033466231726473e-05,
|
| 128 |
+
"loss": 2.8367,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.76,
|
| 133 |
+
"learning_rate": 1.8985139543312796e-05,
|
| 134 |
+
"loss": 2.8211,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8,
|
| 139 |
+
"learning_rate": 1.893681285489912e-05,
|
| 140 |
+
"loss": 2.8159,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.83,
|
| 145 |
+
"learning_rate": 1.8888486166485443e-05,
|
| 146 |
+
"loss": 2.7894,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.87,
|
| 151 |
+
"learning_rate": 1.8840159478071766e-05,
|
| 152 |
+
"loss": 2.7596,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.91,
|
| 157 |
+
"learning_rate": 1.8791832789658093e-05,
|
| 158 |
+
"loss": 2.7576,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.94,
|
| 163 |
+
"learning_rate": 1.8743506101244412e-05,
|
| 164 |
+
"loss": 2.7496,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.98,
|
| 169 |
+
"learning_rate": 1.869517941283074e-05,
|
| 170 |
+
"loss": 2.728,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.01,
|
| 175 |
+
"learning_rate": 1.8646852724417062e-05,
|
| 176 |
+
"loss": 2.6927,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.05,
|
| 181 |
+
"learning_rate": 1.8598526036003382e-05,
|
| 182 |
+
"loss": 2.7037,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.09,
|
| 187 |
+
"learning_rate": 1.855019934758971e-05,
|
| 188 |
+
"loss": 2.6919,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.12,
|
| 193 |
+
"learning_rate": 1.8501872659176032e-05,
|
| 194 |
+
"loss": 2.66,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.16,
|
| 199 |
+
"learning_rate": 1.8453545970762355e-05,
|
| 200 |
+
"loss": 2.6546,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.2,
|
| 205 |
+
"learning_rate": 1.840521928234868e-05,
|
| 206 |
+
"loss": 2.6415,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.23,
|
| 211 |
+
"learning_rate": 1.8356892593935e-05,
|
| 212 |
+
"loss": 2.6423,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.27,
|
| 217 |
+
"learning_rate": 1.8308565905521325e-05,
|
| 218 |
+
"loss": 2.625,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.3,
|
| 223 |
+
"learning_rate": 1.8260239217107648e-05,
|
| 224 |
+
"loss": 2.6041,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.34,
|
| 229 |
+
"learning_rate": 1.8211912528693975e-05,
|
| 230 |
+
"loss": 2.5971,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.38,
|
| 235 |
+
"learning_rate": 1.8163585840280295e-05,
|
| 236 |
+
"loss": 2.5993,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.41,
|
| 241 |
+
"learning_rate": 1.811525915186662e-05,
|
| 242 |
+
"loss": 2.5707,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.45,
|
| 247 |
+
"learning_rate": 1.8066932463452944e-05,
|
| 248 |
+
"loss": 2.5933,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.49,
|
| 253 |
+
"learning_rate": 1.8018605775039268e-05,
|
| 254 |
+
"loss": 2.5669,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.52,
|
| 259 |
+
"learning_rate": 1.797027908662559e-05,
|
| 260 |
+
"loss": 2.5681,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.56,
|
| 265 |
+
"learning_rate": 1.7921952398211914e-05,
|
| 266 |
+
"loss": 2.5648,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.59,
|
| 271 |
+
"learning_rate": 1.7873625709798237e-05,
|
| 272 |
+
"loss": 2.5403,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.63,
|
| 277 |
+
"learning_rate": 1.782529902138456e-05,
|
| 278 |
+
"loss": 2.5314,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.67,
|
| 283 |
+
"learning_rate": 1.7776972332970884e-05,
|
| 284 |
+
"loss": 2.5094,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.7,
|
| 289 |
+
"learning_rate": 1.7728645644557207e-05,
|
| 290 |
+
"loss": 2.537,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.74,
|
| 295 |
+
"learning_rate": 1.768031895614353e-05,
|
| 296 |
+
"loss": 2.5389,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.78,
|
| 301 |
+
"learning_rate": 1.7631992267729857e-05,
|
| 302 |
+
"loss": 2.5243,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.81,
|
| 307 |
+
"learning_rate": 1.7583665579316177e-05,
|
| 308 |
+
"loss": 2.5064,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.85,
|
| 313 |
+
"learning_rate": 1.7535338890902503e-05,
|
| 314 |
+
"loss": 2.5106,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.88,
|
| 319 |
+
"learning_rate": 1.7487012202488827e-05,
|
| 320 |
+
"loss": 2.4955,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.92,
|
| 325 |
+
"learning_rate": 1.743868551407515e-05,
|
| 326 |
+
"loss": 2.488,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.96,
|
| 331 |
+
"learning_rate": 1.7390358825661473e-05,
|
| 332 |
+
"loss": 2.4869,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.99,
|
| 337 |
+
"learning_rate": 1.7342032137247796e-05,
|
| 338 |
+
"loss": 2.4838,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.03,
|
| 343 |
+
"learning_rate": 1.729370544883412e-05,
|
| 344 |
+
"loss": 2.4756,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.07,
|
| 349 |
+
"learning_rate": 1.7245378760420443e-05,
|
| 350 |
+
"loss": 2.4512,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.1,
|
| 355 |
+
"learning_rate": 1.719705207200677e-05,
|
| 356 |
+
"loss": 2.4456,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.14,
|
| 361 |
+
"learning_rate": 1.714872538359309e-05,
|
| 362 |
+
"loss": 2.4485,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.17,
|
| 367 |
+
"learning_rate": 1.7100398695179416e-05,
|
| 368 |
+
"loss": 2.4304,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.21,
|
| 373 |
+
"learning_rate": 1.705207200676574e-05,
|
| 374 |
+
"loss": 2.4417,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.25,
|
| 379 |
+
"learning_rate": 1.7003745318352062e-05,
|
| 380 |
+
"loss": 2.43,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.28,
|
| 385 |
+
"learning_rate": 1.6955418629938385e-05,
|
| 386 |
+
"loss": 2.443,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.32,
|
| 391 |
+
"learning_rate": 1.690709194152471e-05,
|
| 392 |
+
"loss": 2.4195,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.36,
|
| 397 |
+
"learning_rate": 1.6858765253111032e-05,
|
| 398 |
+
"loss": 2.4103,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.39,
|
| 403 |
+
"learning_rate": 1.6810438564697355e-05,
|
| 404 |
+
"loss": 2.4133,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.43,
|
| 409 |
+
"learning_rate": 1.676211187628368e-05,
|
| 410 |
+
"loss": 2.4059,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.46,
|
| 415 |
+
"learning_rate": 1.671378518787e-05,
|
| 416 |
+
"loss": 2.4059,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.5,
|
| 421 |
+
"learning_rate": 1.6665458499456325e-05,
|
| 422 |
+
"loss": 2.4109,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.54,
|
| 427 |
+
"learning_rate": 1.661713181104265e-05,
|
| 428 |
+
"loss": 2.4025,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.57,
|
| 433 |
+
"learning_rate": 1.656880512262897e-05,
|
| 434 |
+
"loss": 2.397,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.61,
|
| 439 |
+
"learning_rate": 1.6520478434215298e-05,
|
| 440 |
+
"loss": 2.3958,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.65,
|
| 445 |
+
"learning_rate": 1.647215174580162e-05,
|
| 446 |
+
"loss": 2.3681,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.68,
|
| 451 |
+
"learning_rate": 1.6423825057387944e-05,
|
| 452 |
+
"loss": 2.4033,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.72,
|
| 457 |
+
"learning_rate": 1.6375498368974268e-05,
|
| 458 |
+
"loss": 2.3801,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.75,
|
| 463 |
+
"learning_rate": 1.632717168056059e-05,
|
| 464 |
+
"loss": 2.3898,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.79,
|
| 469 |
+
"learning_rate": 1.6278844992146914e-05,
|
| 470 |
+
"loss": 2.3613,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.83,
|
| 475 |
+
"learning_rate": 1.6230518303733237e-05,
|
| 476 |
+
"loss": 2.3879,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.86,
|
| 481 |
+
"learning_rate": 1.6182191615319564e-05,
|
| 482 |
+
"loss": 2.362,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.9,
|
| 487 |
+
"learning_rate": 1.6133864926905884e-05,
|
| 488 |
+
"loss": 2.3625,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.94,
|
| 493 |
+
"learning_rate": 1.608553823849221e-05,
|
| 494 |
+
"loss": 2.3635,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.97,
|
| 499 |
+
"learning_rate": 1.6037211550078534e-05,
|
| 500 |
+
"loss": 2.3615,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.01,
|
| 505 |
+
"learning_rate": 1.5988884861664853e-05,
|
| 506 |
+
"loss": 2.3327,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.04,
|
| 511 |
+
"learning_rate": 1.594055817325118e-05,
|
| 512 |
+
"loss": 2.3424,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.08,
|
| 517 |
+
"learning_rate": 1.5892231484837503e-05,
|
| 518 |
+
"loss": 2.3462,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.12,
|
| 523 |
+
"learning_rate": 1.5843904796423827e-05,
|
| 524 |
+
"loss": 2.3395,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.15,
|
| 529 |
+
"learning_rate": 1.579557810801015e-05,
|
| 530 |
+
"loss": 2.3287,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.19,
|
| 535 |
+
"learning_rate": 1.5747251419596473e-05,
|
| 536 |
+
"loss": 2.3408,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.23,
|
| 541 |
+
"learning_rate": 1.5698924731182796e-05,
|
| 542 |
+
"loss": 2.3126,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.26,
|
| 547 |
+
"learning_rate": 1.565059804276912e-05,
|
| 548 |
+
"loss": 2.3234,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.3,
|
| 553 |
+
"learning_rate": 1.5602271354355446e-05,
|
| 554 |
+
"loss": 2.324,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.33,
|
| 559 |
+
"learning_rate": 1.5553944665941766e-05,
|
| 560 |
+
"loss": 2.3156,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.37,
|
| 565 |
+
"learning_rate": 1.5505617977528093e-05,
|
| 566 |
+
"loss": 2.3264,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.41,
|
| 571 |
+
"learning_rate": 1.5457291289114416e-05,
|
| 572 |
+
"loss": 2.3086,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.44,
|
| 577 |
+
"learning_rate": 1.540896460070074e-05,
|
| 578 |
+
"loss": 2.3095,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.48,
|
| 583 |
+
"learning_rate": 1.5360637912287062e-05,
|
| 584 |
+
"loss": 2.3015,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.52,
|
| 589 |
+
"learning_rate": 1.5312311223873385e-05,
|
| 590 |
+
"loss": 2.302,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.55,
|
| 595 |
+
"learning_rate": 1.526398453545971e-05,
|
| 596 |
+
"loss": 2.3164,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.59,
|
| 601 |
+
"learning_rate": 1.5215657847046032e-05,
|
| 602 |
+
"loss": 2.3067,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.62,
|
| 607 |
+
"learning_rate": 1.5167331158632357e-05,
|
| 608 |
+
"loss": 2.2705,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.62,
|
| 613 |
+
"eval_bleu": 23.2646,
|
| 614 |
+
"eval_gen_len": 26.1331,
|
| 615 |
+
"eval_loss": 1.9072902202606201,
|
| 616 |
+
"eval_runtime": 5550.0392,
|
| 617 |
+
"eval_samples_per_second": 9.942,
|
| 618 |
+
"eval_steps_per_second": 1.243,
|
| 619 |
+
"step": 50000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.66,
|
| 623 |
+
"learning_rate": 1.5119004470218678e-05,
|
| 624 |
+
"loss": 2.2769,
|
| 625 |
+
"step": 50500
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.7,
|
| 629 |
+
"learning_rate": 1.5070677781805003e-05,
|
| 630 |
+
"loss": 2.3089,
|
| 631 |
+
"step": 51000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.73,
|
| 635 |
+
"learning_rate": 1.5022351093391328e-05,
|
| 636 |
+
"loss": 2.2817,
|
| 637 |
+
"step": 51500
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 3.77,
|
| 641 |
+
"learning_rate": 1.497402440497765e-05,
|
| 642 |
+
"loss": 2.2757,
|
| 643 |
+
"step": 52000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 3.81,
|
| 647 |
+
"learning_rate": 1.4925697716563973e-05,
|
| 648 |
+
"loss": 2.287,
|
| 649 |
+
"step": 52500
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.84,
|
| 653 |
+
"learning_rate": 1.4877371028150298e-05,
|
| 654 |
+
"loss": 2.289,
|
| 655 |
+
"step": 53000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.88,
|
| 659 |
+
"learning_rate": 1.482904433973662e-05,
|
| 660 |
+
"loss": 2.268,
|
| 661 |
+
"step": 53500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.91,
|
| 665 |
+
"learning_rate": 1.4780717651322944e-05,
|
| 666 |
+
"loss": 2.2766,
|
| 667 |
+
"step": 54000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.95,
|
| 671 |
+
"learning_rate": 1.473239096290927e-05,
|
| 672 |
+
"loss": 2.2775,
|
| 673 |
+
"step": 54500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.99,
|
| 677 |
+
"learning_rate": 1.4684064274495591e-05,
|
| 678 |
+
"loss": 2.2795,
|
| 679 |
+
"step": 55000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 4.02,
|
| 683 |
+
"learning_rate": 1.4635737586081916e-05,
|
| 684 |
+
"loss": 2.2683,
|
| 685 |
+
"step": 55500
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 4.06,
|
| 689 |
+
"learning_rate": 1.4587410897668239e-05,
|
| 690 |
+
"loss": 2.2551,
|
| 691 |
+
"step": 56000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.1,
|
| 695 |
+
"learning_rate": 1.4539084209254562e-05,
|
| 696 |
+
"loss": 2.2511,
|
| 697 |
+
"step": 56500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.13,
|
| 701 |
+
"learning_rate": 1.4490757520840885e-05,
|
| 702 |
+
"loss": 2.258,
|
| 703 |
+
"step": 57000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.17,
|
| 707 |
+
"learning_rate": 1.444243083242721e-05,
|
| 708 |
+
"loss": 2.2593,
|
| 709 |
+
"step": 57500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.2,
|
| 713 |
+
"learning_rate": 1.4394104144013532e-05,
|
| 714 |
+
"loss": 2.2481,
|
| 715 |
+
"step": 58000
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 4.24,
|
| 719 |
+
"learning_rate": 1.4345777455599857e-05,
|
| 720 |
+
"loss": 2.2485,
|
| 721 |
+
"step": 58500
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 4.28,
|
| 725 |
+
"learning_rate": 1.429745076718618e-05,
|
| 726 |
+
"loss": 2.2594,
|
| 727 |
+
"step": 59000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 4.31,
|
| 731 |
+
"learning_rate": 1.4249124078772503e-05,
|
| 732 |
+
"loss": 2.2593,
|
| 733 |
+
"step": 59500
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.35,
|
| 737 |
+
"learning_rate": 1.4200797390358827e-05,
|
| 738 |
+
"loss": 2.242,
|
| 739 |
+
"step": 60000
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.39,
|
| 743 |
+
"learning_rate": 1.4152470701945151e-05,
|
| 744 |
+
"loss": 2.2294,
|
| 745 |
+
"step": 60500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 4.42,
|
| 749 |
+
"learning_rate": 1.4104144013531473e-05,
|
| 750 |
+
"loss": 2.2517,
|
| 751 |
+
"step": 61000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.46,
|
| 755 |
+
"learning_rate": 1.4055817325117798e-05,
|
| 756 |
+
"loss": 2.2243,
|
| 757 |
+
"step": 61500
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 4.49,
|
| 761 |
+
"learning_rate": 1.4007490636704121e-05,
|
| 762 |
+
"loss": 2.2484,
|
| 763 |
+
"step": 62000
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 4.53,
|
| 767 |
+
"learning_rate": 1.3959163948290444e-05,
|
| 768 |
+
"loss": 2.228,
|
| 769 |
+
"step": 62500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.57,
|
| 773 |
+
"learning_rate": 1.3910837259876768e-05,
|
| 774 |
+
"loss": 2.2314,
|
| 775 |
+
"step": 63000
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.6,
|
| 779 |
+
"learning_rate": 1.3862510571463093e-05,
|
| 780 |
+
"loss": 2.2317,
|
| 781 |
+
"step": 63500
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 4.64,
|
| 785 |
+
"learning_rate": 1.3814183883049414e-05,
|
| 786 |
+
"loss": 2.2187,
|
| 787 |
+
"step": 64000
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 4.68,
|
| 791 |
+
"learning_rate": 1.3765857194635739e-05,
|
| 792 |
+
"loss": 2.2325,
|
| 793 |
+
"step": 64500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.71,
|
| 797 |
+
"learning_rate": 1.3717530506222064e-05,
|
| 798 |
+
"loss": 2.2221,
|
| 799 |
+
"step": 65000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 4.75,
|
| 803 |
+
"learning_rate": 1.3669203817808385e-05,
|
| 804 |
+
"loss": 2.2218,
|
| 805 |
+
"step": 65500
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 4.78,
|
| 809 |
+
"learning_rate": 1.3620877129394709e-05,
|
| 810 |
+
"loss": 2.2156,
|
| 811 |
+
"step": 66000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.82,
|
| 815 |
+
"learning_rate": 1.3572550440981034e-05,
|
| 816 |
+
"loss": 2.2232,
|
| 817 |
+
"step": 66500
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 4.86,
|
| 821 |
+
"learning_rate": 1.3524223752567355e-05,
|
| 822 |
+
"loss": 2.2084,
|
| 823 |
+
"step": 67000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 4.89,
|
| 827 |
+
"learning_rate": 1.347589706415368e-05,
|
| 828 |
+
"loss": 2.2374,
|
| 829 |
+
"step": 67500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.93,
|
| 833 |
+
"learning_rate": 1.3427570375740005e-05,
|
| 834 |
+
"loss": 2.2046,
|
| 835 |
+
"step": 68000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.97,
|
| 839 |
+
"learning_rate": 1.3379243687326327e-05,
|
| 840 |
+
"loss": 2.2109,
|
| 841 |
+
"step": 68500
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 5.0,
|
| 845 |
+
"learning_rate": 1.3330916998912651e-05,
|
| 846 |
+
"loss": 2.2115,
|
| 847 |
+
"step": 69000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 5.04,
|
| 851 |
+
"learning_rate": 1.3282590310498975e-05,
|
| 852 |
+
"loss": 2.2053,
|
| 853 |
+
"step": 69500
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 5.07,
|
| 857 |
+
"learning_rate": 1.3234263622085298e-05,
|
| 858 |
+
"loss": 2.1956,
|
| 859 |
+
"step": 70000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 5.11,
|
| 863 |
+
"learning_rate": 1.3185936933671621e-05,
|
| 864 |
+
"loss": 2.2031,
|
| 865 |
+
"step": 70500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 5.15,
|
| 869 |
+
"learning_rate": 1.3137610245257946e-05,
|
| 870 |
+
"loss": 2.1959,
|
| 871 |
+
"step": 71000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 5.18,
|
| 875 |
+
"learning_rate": 1.3089283556844268e-05,
|
| 876 |
+
"loss": 2.2023,
|
| 877 |
+
"step": 71500
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 5.22,
|
| 881 |
+
"learning_rate": 1.3040956868430593e-05,
|
| 882 |
+
"loss": 2.197,
|
| 883 |
+
"step": 72000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 5.26,
|
| 887 |
+
"learning_rate": 1.2992630180016916e-05,
|
| 888 |
+
"loss": 2.212,
|
| 889 |
+
"step": 72500
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 5.29,
|
| 893 |
+
"learning_rate": 1.2944303491603239e-05,
|
| 894 |
+
"loss": 2.204,
|
| 895 |
+
"step": 73000
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 5.33,
|
| 899 |
+
"learning_rate": 1.2895976803189562e-05,
|
| 900 |
+
"loss": 2.1871,
|
| 901 |
+
"step": 73500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 5.36,
|
| 905 |
+
"learning_rate": 1.2847650114775887e-05,
|
| 906 |
+
"loss": 2.1852,
|
| 907 |
+
"step": 74000
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 5.4,
|
| 911 |
+
"learning_rate": 1.2799323426362209e-05,
|
| 912 |
+
"loss": 2.1804,
|
| 913 |
+
"step": 74500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 5.44,
|
| 917 |
+
"learning_rate": 1.2750996737948534e-05,
|
| 918 |
+
"loss": 2.1949,
|
| 919 |
+
"step": 75000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 5.47,
|
| 923 |
+
"learning_rate": 1.2702670049534857e-05,
|
| 924 |
+
"loss": 2.1662,
|
| 925 |
+
"step": 75500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 5.51,
|
| 929 |
+
"learning_rate": 1.265434336112118e-05,
|
| 930 |
+
"loss": 2.1871,
|
| 931 |
+
"step": 76000
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 5.55,
|
| 935 |
+
"learning_rate": 1.2606016672707503e-05,
|
| 936 |
+
"loss": 2.1841,
|
| 937 |
+
"step": 76500
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 5.58,
|
| 941 |
+
"learning_rate": 1.2557689984293828e-05,
|
| 942 |
+
"loss": 2.1719,
|
| 943 |
+
"step": 77000
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 5.62,
|
| 947 |
+
"learning_rate": 1.250936329588015e-05,
|
| 948 |
+
"loss": 2.1755,
|
| 949 |
+
"step": 77500
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 5.65,
|
| 953 |
+
"learning_rate": 1.2461036607466475e-05,
|
| 954 |
+
"loss": 2.1589,
|
| 955 |
+
"step": 78000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 5.69,
|
| 959 |
+
"learning_rate": 1.24127099190528e-05,
|
| 960 |
+
"loss": 2.1785,
|
| 961 |
+
"step": 78500
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 5.73,
|
| 965 |
+
"learning_rate": 1.2364383230639121e-05,
|
| 966 |
+
"loss": 2.1931,
|
| 967 |
+
"step": 79000
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 5.76,
|
| 971 |
+
"learning_rate": 1.2316056542225444e-05,
|
| 972 |
+
"loss": 2.1827,
|
| 973 |
+
"step": 79500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 5.8,
|
| 977 |
+
"learning_rate": 1.226772985381177e-05,
|
| 978 |
+
"loss": 2.1628,
|
| 979 |
+
"step": 80000
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 5.84,
|
| 983 |
+
"learning_rate": 1.2219403165398091e-05,
|
| 984 |
+
"loss": 2.1702,
|
| 985 |
+
"step": 80500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.87,
|
| 989 |
+
"learning_rate": 1.2171076476984416e-05,
|
| 990 |
+
"loss": 2.161,
|
| 991 |
+
"step": 81000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 5.91,
|
| 995 |
+
"learning_rate": 1.212274978857074e-05,
|
| 996 |
+
"loss": 2.172,
|
| 997 |
+
"step": 81500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 5.94,
|
| 1001 |
+
"learning_rate": 1.2074423100157062e-05,
|
| 1002 |
+
"loss": 2.1731,
|
| 1003 |
+
"step": 82000
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 5.98,
|
| 1007 |
+
"learning_rate": 1.2026096411743387e-05,
|
| 1008 |
+
"loss": 2.1582,
|
| 1009 |
+
"step": 82500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 6.02,
|
| 1013 |
+
"learning_rate": 1.197776972332971e-05,
|
| 1014 |
+
"loss": 2.1739,
|
| 1015 |
+
"step": 83000
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 6.05,
|
| 1019 |
+
"learning_rate": 1.1929443034916034e-05,
|
| 1020 |
+
"loss": 2.1447,
|
| 1021 |
+
"step": 83500
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 6.09,
|
| 1025 |
+
"learning_rate": 1.1881116346502357e-05,
|
| 1026 |
+
"loss": 2.159,
|
| 1027 |
+
"step": 84000
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 6.13,
|
| 1031 |
+
"learning_rate": 1.1832789658088682e-05,
|
| 1032 |
+
"loss": 2.17,
|
| 1033 |
+
"step": 84500
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 6.16,
|
| 1037 |
+
"learning_rate": 1.1784462969675003e-05,
|
| 1038 |
+
"loss": 2.1441,
|
| 1039 |
+
"step": 85000
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 6.2,
|
| 1043 |
+
"learning_rate": 1.1736136281261328e-05,
|
| 1044 |
+
"loss": 2.1447,
|
| 1045 |
+
"step": 85500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 6.23,
|
| 1049 |
+
"learning_rate": 1.1687809592847651e-05,
|
| 1050 |
+
"loss": 2.1529,
|
| 1051 |
+
"step": 86000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 6.27,
|
| 1055 |
+
"learning_rate": 1.1639482904433975e-05,
|
| 1056 |
+
"loss": 2.1558,
|
| 1057 |
+
"step": 86500
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 6.31,
|
| 1061 |
+
"learning_rate": 1.1591156216020298e-05,
|
| 1062 |
+
"loss": 2.1356,
|
| 1063 |
+
"step": 87000
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 6.34,
|
| 1067 |
+
"learning_rate": 1.1542829527606623e-05,
|
| 1068 |
+
"loss": 2.1593,
|
| 1069 |
+
"step": 87500
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 6.38,
|
| 1073 |
+
"learning_rate": 1.1494502839192944e-05,
|
| 1074 |
+
"loss": 2.1467,
|
| 1075 |
+
"step": 88000
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 6.42,
|
| 1079 |
+
"learning_rate": 1.144617615077927e-05,
|
| 1080 |
+
"loss": 2.1533,
|
| 1081 |
+
"step": 88500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 6.45,
|
| 1085 |
+
"learning_rate": 1.1397849462365593e-05,
|
| 1086 |
+
"loss": 2.1261,
|
| 1087 |
+
"step": 89000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 6.49,
|
| 1091 |
+
"learning_rate": 1.1349522773951916e-05,
|
| 1092 |
+
"loss": 2.1519,
|
| 1093 |
+
"step": 89500
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 6.52,
|
| 1097 |
+
"learning_rate": 1.1301196085538239e-05,
|
| 1098 |
+
"loss": 2.1513,
|
| 1099 |
+
"step": 90000
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 6.56,
|
| 1103 |
+
"learning_rate": 1.1252869397124564e-05,
|
| 1104 |
+
"loss": 2.1404,
|
| 1105 |
+
"step": 90500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 6.6,
|
| 1109 |
+
"learning_rate": 1.1204542708710885e-05,
|
| 1110 |
+
"loss": 2.1427,
|
| 1111 |
+
"step": 91000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 6.63,
|
| 1115 |
+
"learning_rate": 1.115621602029721e-05,
|
| 1116 |
+
"loss": 2.138,
|
| 1117 |
+
"step": 91500
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 6.67,
|
| 1121 |
+
"learning_rate": 1.1107889331883535e-05,
|
| 1122 |
+
"loss": 2.1382,
|
| 1123 |
+
"step": 92000
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 6.71,
|
| 1127 |
+
"learning_rate": 1.1059562643469857e-05,
|
| 1128 |
+
"loss": 2.1344,
|
| 1129 |
+
"step": 92500
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 6.74,
|
| 1133 |
+
"learning_rate": 1.101123595505618e-05,
|
| 1134 |
+
"loss": 2.1474,
|
| 1135 |
+
"step": 93000
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 6.78,
|
| 1139 |
+
"learning_rate": 1.0962909266642505e-05,
|
| 1140 |
+
"loss": 2.1197,
|
| 1141 |
+
"step": 93500
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 6.81,
|
| 1145 |
+
"learning_rate": 1.0914582578228827e-05,
|
| 1146 |
+
"loss": 2.146,
|
| 1147 |
+
"step": 94000
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 6.85,
|
| 1151 |
+
"learning_rate": 1.0866255889815151e-05,
|
| 1152 |
+
"loss": 2.1313,
|
| 1153 |
+
"step": 94500
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 6.89,
|
| 1157 |
+
"learning_rate": 1.0817929201401476e-05,
|
| 1158 |
+
"loss": 2.1374,
|
| 1159 |
+
"step": 95000
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 6.92,
|
| 1163 |
+
"learning_rate": 1.0769602512987798e-05,
|
| 1164 |
+
"loss": 2.1329,
|
| 1165 |
+
"step": 95500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 6.96,
|
| 1169 |
+
"learning_rate": 1.0721275824574123e-05,
|
| 1170 |
+
"loss": 2.132,
|
| 1171 |
+
"step": 96000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 7.0,
|
| 1175 |
+
"learning_rate": 1.0672949136160446e-05,
|
| 1176 |
+
"loss": 2.1142,
|
| 1177 |
+
"step": 96500
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 7.03,
|
| 1181 |
+
"learning_rate": 1.062462244774677e-05,
|
| 1182 |
+
"loss": 2.1338,
|
| 1183 |
+
"step": 97000
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 7.07,
|
| 1187 |
+
"learning_rate": 1.0576295759333093e-05,
|
| 1188 |
+
"loss": 2.1137,
|
| 1189 |
+
"step": 97500
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 7.1,
|
| 1193 |
+
"learning_rate": 1.0527969070919417e-05,
|
| 1194 |
+
"loss": 2.1221,
|
| 1195 |
+
"step": 98000
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 7.14,
|
| 1199 |
+
"learning_rate": 1.0479642382505739e-05,
|
| 1200 |
+
"loss": 2.1382,
|
| 1201 |
+
"step": 98500
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 7.18,
|
| 1205 |
+
"learning_rate": 1.0431315694092064e-05,
|
| 1206 |
+
"loss": 2.1207,
|
| 1207 |
+
"step": 99000
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 7.21,
|
| 1211 |
+
"learning_rate": 1.0382989005678387e-05,
|
| 1212 |
+
"loss": 2.1163,
|
| 1213 |
+
"step": 99500
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 7.25,
|
| 1217 |
+
"learning_rate": 1.033466231726471e-05,
|
| 1218 |
+
"loss": 2.1263,
|
| 1219 |
+
"step": 100000
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 7.25,
|
| 1223 |
+
"eval_bleu": 25.2752,
|
| 1224 |
+
"eval_gen_len": 24.8098,
|
| 1225 |
+
"eval_loss": 1.8044791221618652,
|
| 1226 |
+
"eval_runtime": 4767.4438,
|
| 1227 |
+
"eval_samples_per_second": 11.574,
|
| 1228 |
+
"eval_steps_per_second": 1.447,
|
| 1229 |
+
"step": 100000
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 7.29,
|
| 1233 |
+
"learning_rate": 1.0286335628851034e-05,
|
| 1234 |
+
"loss": 2.0977,
|
| 1235 |
+
"step": 100500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 7.32,
|
| 1239 |
+
"learning_rate": 1.0238008940437359e-05,
|
| 1240 |
+
"loss": 2.1114,
|
| 1241 |
+
"step": 101000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 7.36,
|
| 1245 |
+
"learning_rate": 1.018968225202368e-05,
|
| 1246 |
+
"loss": 2.1208,
|
| 1247 |
+
"step": 101500
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 7.39,
|
| 1251 |
+
"learning_rate": 1.0141355563610005e-05,
|
| 1252 |
+
"loss": 2.1006,
|
| 1253 |
+
"step": 102000
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 7.43,
|
| 1257 |
+
"learning_rate": 1.0093028875196328e-05,
|
| 1258 |
+
"loss": 2.1091,
|
| 1259 |
+
"step": 102500
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 7.47,
|
| 1263 |
+
"learning_rate": 1.0044702186782651e-05,
|
| 1264 |
+
"loss": 2.1347,
|
| 1265 |
+
"step": 103000
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 7.5,
|
| 1269 |
+
"learning_rate": 9.996375498368975e-06,
|
| 1270 |
+
"loss": 2.1106,
|
| 1271 |
+
"step": 103500
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 7.54,
|
| 1275 |
+
"learning_rate": 9.948048809955298e-06,
|
| 1276 |
+
"loss": 2.1071,
|
| 1277 |
+
"step": 104000
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 7.58,
|
| 1281 |
+
"learning_rate": 9.899722121541621e-06,
|
| 1282 |
+
"loss": 2.0954,
|
| 1283 |
+
"step": 104500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 7.61,
|
| 1287 |
+
"learning_rate": 9.851395433127946e-06,
|
| 1288 |
+
"loss": 2.1072,
|
| 1289 |
+
"step": 105000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 7.65,
|
| 1293 |
+
"learning_rate": 9.80306874471427e-06,
|
| 1294 |
+
"loss": 2.1051,
|
| 1295 |
+
"step": 105500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 7.68,
|
| 1299 |
+
"learning_rate": 9.754742056300593e-06,
|
| 1300 |
+
"loss": 2.1066,
|
| 1301 |
+
"step": 106000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 7.72,
|
| 1305 |
+
"learning_rate": 9.706415367886916e-06,
|
| 1306 |
+
"loss": 2.1122,
|
| 1307 |
+
"step": 106500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 7.76,
|
| 1311 |
+
"learning_rate": 9.658088679473239e-06,
|
| 1312 |
+
"loss": 2.0952,
|
| 1313 |
+
"step": 107000
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 7.79,
|
| 1317 |
+
"learning_rate": 9.609761991059562e-06,
|
| 1318 |
+
"loss": 2.085,
|
| 1319 |
+
"step": 107500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 7.83,
|
| 1323 |
+
"learning_rate": 9.561435302645887e-06,
|
| 1324 |
+
"loss": 2.1076,
|
| 1325 |
+
"step": 108000
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 7.87,
|
| 1329 |
+
"learning_rate": 9.51310861423221e-06,
|
| 1330 |
+
"loss": 2.1236,
|
| 1331 |
+
"step": 108500
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 7.9,
|
| 1335 |
+
"learning_rate": 9.464781925818534e-06,
|
| 1336 |
+
"loss": 2.0932,
|
| 1337 |
+
"step": 109000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 7.94,
|
| 1341 |
+
"learning_rate": 9.416455237404859e-06,
|
| 1342 |
+
"loss": 2.0892,
|
| 1343 |
+
"step": 109500
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 7.97,
|
| 1347 |
+
"learning_rate": 9.368128548991182e-06,
|
| 1348 |
+
"loss": 2.0778,
|
| 1349 |
+
"step": 110000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 8.01,
|
| 1353 |
+
"learning_rate": 9.319801860577505e-06,
|
| 1354 |
+
"loss": 2.1035,
|
| 1355 |
+
"step": 110500
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 8.05,
|
| 1359 |
+
"learning_rate": 9.271475172163828e-06,
|
| 1360 |
+
"loss": 2.0876,
|
| 1361 |
+
"step": 111000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 8.08,
|
| 1365 |
+
"learning_rate": 9.223148483750151e-06,
|
| 1366 |
+
"loss": 2.0869,
|
| 1367 |
+
"step": 111500
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 8.12,
|
| 1371 |
+
"learning_rate": 9.174821795336475e-06,
|
| 1372 |
+
"loss": 2.0972,
|
| 1373 |
+
"step": 112000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 8.16,
|
| 1377 |
+
"learning_rate": 9.1264951069228e-06,
|
| 1378 |
+
"loss": 2.0948,
|
| 1379 |
+
"step": 112500
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 8.19,
|
| 1383 |
+
"learning_rate": 9.078168418509123e-06,
|
| 1384 |
+
"loss": 2.0742,
|
| 1385 |
+
"step": 113000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 8.23,
|
| 1389 |
+
"learning_rate": 9.029841730095446e-06,
|
| 1390 |
+
"loss": 2.085,
|
| 1391 |
+
"step": 113500
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 8.26,
|
| 1395 |
+
"learning_rate": 8.98151504168177e-06,
|
| 1396 |
+
"loss": 2.0885,
|
| 1397 |
+
"step": 114000
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 8.3,
|
| 1401 |
+
"learning_rate": 8.933188353268093e-06,
|
| 1402 |
+
"loss": 2.0667,
|
| 1403 |
+
"step": 114500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 8.34,
|
| 1407 |
+
"learning_rate": 8.884861664854416e-06,
|
| 1408 |
+
"loss": 2.1004,
|
| 1409 |
+
"step": 115000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 8.37,
|
| 1413 |
+
"learning_rate": 8.83653497644074e-06,
|
| 1414 |
+
"loss": 2.099,
|
| 1415 |
+
"step": 115500
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 8.41,
|
| 1419 |
+
"learning_rate": 8.788208288027064e-06,
|
| 1420 |
+
"loss": 2.0988,
|
| 1421 |
+
"step": 116000
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 8.45,
|
| 1425 |
+
"learning_rate": 8.739881599613387e-06,
|
| 1426 |
+
"loss": 2.0861,
|
| 1427 |
+
"step": 116500
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 8.48,
|
| 1431 |
+
"learning_rate": 8.69155491119971e-06,
|
| 1432 |
+
"loss": 2.0722,
|
| 1433 |
+
"step": 117000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 8.52,
|
| 1437 |
+
"learning_rate": 8.643228222786034e-06,
|
| 1438 |
+
"loss": 2.0951,
|
| 1439 |
+
"step": 117500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 8.55,
|
| 1443 |
+
"learning_rate": 8.594901534372357e-06,
|
| 1444 |
+
"loss": 2.0915,
|
| 1445 |
+
"step": 118000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 8.59,
|
| 1449 |
+
"learning_rate": 8.546574845958682e-06,
|
| 1450 |
+
"loss": 2.099,
|
| 1451 |
+
"step": 118500
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 8.63,
|
| 1455 |
+
"learning_rate": 8.498248157545005e-06,
|
| 1456 |
+
"loss": 2.0805,
|
| 1457 |
+
"step": 119000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 8.66,
|
| 1461 |
+
"learning_rate": 8.449921469131328e-06,
|
| 1462 |
+
"loss": 2.0857,
|
| 1463 |
+
"step": 119500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 8.7,
|
| 1467 |
+
"learning_rate": 8.401594780717651e-06,
|
| 1468 |
+
"loss": 2.0849,
|
| 1469 |
+
"step": 120000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 8.74,
|
| 1473 |
+
"learning_rate": 8.353268092303975e-06,
|
| 1474 |
+
"loss": 2.0936,
|
| 1475 |
+
"step": 120500
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 8.77,
|
| 1479 |
+
"learning_rate": 8.304941403890298e-06,
|
| 1480 |
+
"loss": 2.0781,
|
| 1481 |
+
"step": 121000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 8.81,
|
| 1485 |
+
"learning_rate": 8.256614715476623e-06,
|
| 1486 |
+
"loss": 2.0824,
|
| 1487 |
+
"step": 121500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 8.84,
|
| 1491 |
+
"learning_rate": 8.208288027062946e-06,
|
| 1492 |
+
"loss": 2.0824,
|
| 1493 |
+
"step": 122000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 8.88,
|
| 1497 |
+
"learning_rate": 8.15996133864927e-06,
|
| 1498 |
+
"loss": 2.0822,
|
| 1499 |
+
"step": 122500
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 8.92,
|
| 1503 |
+
"learning_rate": 8.111634650235594e-06,
|
| 1504 |
+
"loss": 2.0873,
|
| 1505 |
+
"step": 123000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 8.95,
|
| 1509 |
+
"learning_rate": 8.063307961821917e-06,
|
| 1510 |
+
"loss": 2.0679,
|
| 1511 |
+
"step": 123500
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 8.99,
|
| 1515 |
+
"learning_rate": 8.01498127340824e-06,
|
| 1516 |
+
"loss": 2.077,
|
| 1517 |
+
"step": 124000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 9.03,
|
| 1521 |
+
"learning_rate": 7.966654584994564e-06,
|
| 1522 |
+
"loss": 2.0701,
|
| 1523 |
+
"step": 124500
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 9.06,
|
| 1527 |
+
"learning_rate": 7.918327896580887e-06,
|
| 1528 |
+
"loss": 2.0566,
|
| 1529 |
+
"step": 125000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 9.1,
|
| 1533 |
+
"learning_rate": 7.87000120816721e-06,
|
| 1534 |
+
"loss": 2.0904,
|
| 1535 |
+
"step": 125500
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 9.13,
|
| 1539 |
+
"learning_rate": 7.821674519753535e-06,
|
| 1540 |
+
"loss": 2.0787,
|
| 1541 |
+
"step": 126000
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 9.17,
|
| 1545 |
+
"learning_rate": 7.773347831339859e-06,
|
| 1546 |
+
"loss": 2.0832,
|
| 1547 |
+
"step": 126500
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 9.21,
|
| 1551 |
+
"learning_rate": 7.725021142926182e-06,
|
| 1552 |
+
"loss": 2.0615,
|
| 1553 |
+
"step": 127000
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 9.24,
|
| 1557 |
+
"learning_rate": 7.676694454512505e-06,
|
| 1558 |
+
"loss": 2.0707,
|
| 1559 |
+
"step": 127500
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 9.28,
|
| 1563 |
+
"learning_rate": 7.628367766098828e-06,
|
| 1564 |
+
"loss": 2.0756,
|
| 1565 |
+
"step": 128000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 9.31,
|
| 1569 |
+
"learning_rate": 7.5800410776851515e-06,
|
| 1570 |
+
"loss": 2.0687,
|
| 1571 |
+
"step": 128500
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 9.35,
|
| 1575 |
+
"learning_rate": 7.531714389271476e-06,
|
| 1576 |
+
"loss": 2.0657,
|
| 1577 |
+
"step": 129000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 9.39,
|
| 1581 |
+
"learning_rate": 7.4833877008578e-06,
|
| 1582 |
+
"loss": 2.0559,
|
| 1583 |
+
"step": 129500
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 9.42,
|
| 1587 |
+
"learning_rate": 7.435061012444123e-06,
|
| 1588 |
+
"loss": 2.0727,
|
| 1589 |
+
"step": 130000
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 9.46,
|
| 1593 |
+
"learning_rate": 7.386734324030447e-06,
|
| 1594 |
+
"loss": 2.0532,
|
| 1595 |
+
"step": 130500
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 9.5,
|
| 1599 |
+
"learning_rate": 7.33840763561677e-06,
|
| 1600 |
+
"loss": 2.0783,
|
| 1601 |
+
"step": 131000
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 9.53,
|
| 1605 |
+
"learning_rate": 7.290080947203093e-06,
|
| 1606 |
+
"loss": 2.0657,
|
| 1607 |
+
"step": 131500
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 9.57,
|
| 1611 |
+
"learning_rate": 7.2417542587894175e-06,
|
| 1612 |
+
"loss": 2.0554,
|
| 1613 |
+
"step": 132000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 9.6,
|
| 1617 |
+
"learning_rate": 7.193427570375741e-06,
|
| 1618 |
+
"loss": 2.0649,
|
| 1619 |
+
"step": 132500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 9.64,
|
| 1623 |
+
"learning_rate": 7.145100881962064e-06,
|
| 1624 |
+
"loss": 2.0642,
|
| 1625 |
+
"step": 133000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 9.68,
|
| 1629 |
+
"learning_rate": 7.096774193548388e-06,
|
| 1630 |
+
"loss": 2.0416,
|
| 1631 |
+
"step": 133500
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 9.71,
|
| 1635 |
+
"learning_rate": 7.048447505134711e-06,
|
| 1636 |
+
"loss": 2.0413,
|
| 1637 |
+
"step": 134000
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 9.75,
|
| 1641 |
+
"learning_rate": 7.0001208167210345e-06,
|
| 1642 |
+
"loss": 2.0675,
|
| 1643 |
+
"step": 134500
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 9.79,
|
| 1647 |
+
"learning_rate": 6.9517941283073586e-06,
|
| 1648 |
+
"loss": 2.034,
|
| 1649 |
+
"step": 135000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 9.82,
|
| 1653 |
+
"learning_rate": 6.903467439893682e-06,
|
| 1654 |
+
"loss": 2.0619,
|
| 1655 |
+
"step": 135500
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 9.86,
|
| 1659 |
+
"learning_rate": 6.855140751480005e-06,
|
| 1660 |
+
"loss": 2.0584,
|
| 1661 |
+
"step": 136000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 9.89,
|
| 1665 |
+
"learning_rate": 6.806814063066329e-06,
|
| 1666 |
+
"loss": 2.0691,
|
| 1667 |
+
"step": 136500
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 9.93,
|
| 1671 |
+
"learning_rate": 6.758487374652652e-06,
|
| 1672 |
+
"loss": 2.0519,
|
| 1673 |
+
"step": 137000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 9.97,
|
| 1677 |
+
"learning_rate": 6.7101606862389756e-06,
|
| 1678 |
+
"loss": 2.0675,
|
| 1679 |
+
"step": 137500
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 10.0,
|
| 1683 |
+
"learning_rate": 6.6618339978253e-06,
|
| 1684 |
+
"loss": 2.0675,
|
| 1685 |
+
"step": 138000
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 10.04,
|
| 1689 |
+
"learning_rate": 6.613507309411623e-06,
|
| 1690 |
+
"loss": 2.049,
|
| 1691 |
+
"step": 138500
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 10.08,
|
| 1695 |
+
"learning_rate": 6.565180620997946e-06,
|
| 1696 |
+
"loss": 2.0531,
|
| 1697 |
+
"step": 139000
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 10.11,
|
| 1701 |
+
"learning_rate": 6.51685393258427e-06,
|
| 1702 |
+
"loss": 2.0482,
|
| 1703 |
+
"step": 139500
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 10.15,
|
| 1707 |
+
"learning_rate": 6.468527244170593e-06,
|
| 1708 |
+
"loss": 2.0685,
|
| 1709 |
+
"step": 140000
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 10.18,
|
| 1713 |
+
"learning_rate": 6.420200555756917e-06,
|
| 1714 |
+
"loss": 2.0612,
|
| 1715 |
+
"step": 140500
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 10.22,
|
| 1719 |
+
"learning_rate": 6.3718738673432416e-06,
|
| 1720 |
+
"loss": 2.0456,
|
| 1721 |
+
"step": 141000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 10.26,
|
| 1725 |
+
"learning_rate": 6.323547178929564e-06,
|
| 1726 |
+
"loss": 2.0311,
|
| 1727 |
+
"step": 141500
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 10.29,
|
| 1731 |
+
"learning_rate": 6.275220490515887e-06,
|
| 1732 |
+
"loss": 2.0582,
|
| 1733 |
+
"step": 142000
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 10.33,
|
| 1737 |
+
"learning_rate": 6.226893802102212e-06,
|
| 1738 |
+
"loss": 2.0563,
|
| 1739 |
+
"step": 142500
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 10.37,
|
| 1743 |
+
"learning_rate": 6.178567113688535e-06,
|
| 1744 |
+
"loss": 2.0671,
|
| 1745 |
+
"step": 143000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 10.4,
|
| 1749 |
+
"learning_rate": 6.1302404252748586e-06,
|
| 1750 |
+
"loss": 2.0511,
|
| 1751 |
+
"step": 143500
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 10.44,
|
| 1755 |
+
"learning_rate": 6.081913736861183e-06,
|
| 1756 |
+
"loss": 2.0436,
|
| 1757 |
+
"step": 144000
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 10.47,
|
| 1761 |
+
"learning_rate": 6.033587048447506e-06,
|
| 1762 |
+
"loss": 2.0459,
|
| 1763 |
+
"step": 144500
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 10.51,
|
| 1767 |
+
"learning_rate": 5.985260360033829e-06,
|
| 1768 |
+
"loss": 2.0462,
|
| 1769 |
+
"step": 145000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 10.55,
|
| 1773 |
+
"learning_rate": 5.936933671620153e-06,
|
| 1774 |
+
"loss": 2.0258,
|
| 1775 |
+
"step": 145500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 10.58,
|
| 1779 |
+
"learning_rate": 5.888606983206476e-06,
|
| 1780 |
+
"loss": 2.0513,
|
| 1781 |
+
"step": 146000
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 10.62,
|
| 1785 |
+
"learning_rate": 5.8402802947928e-06,
|
| 1786 |
+
"loss": 2.0566,
|
| 1787 |
+
"step": 146500
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 10.66,
|
| 1791 |
+
"learning_rate": 5.791953606379124e-06,
|
| 1792 |
+
"loss": 2.0485,
|
| 1793 |
+
"step": 147000
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 10.69,
|
| 1797 |
+
"learning_rate": 5.743626917965447e-06,
|
| 1798 |
+
"loss": 2.0351,
|
| 1799 |
+
"step": 147500
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 10.73,
|
| 1803 |
+
"learning_rate": 5.69530022955177e-06,
|
| 1804 |
+
"loss": 2.0449,
|
| 1805 |
+
"step": 148000
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 10.76,
|
| 1809 |
+
"learning_rate": 5.646973541138094e-06,
|
| 1810 |
+
"loss": 2.0635,
|
| 1811 |
+
"step": 148500
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 10.8,
|
| 1815 |
+
"learning_rate": 5.5986468527244175e-06,
|
| 1816 |
+
"loss": 2.0325,
|
| 1817 |
+
"step": 149000
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 10.84,
|
| 1821 |
+
"learning_rate": 5.550320164310741e-06,
|
| 1822 |
+
"loss": 2.0581,
|
| 1823 |
+
"step": 149500
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 10.87,
|
| 1827 |
+
"learning_rate": 5.501993475897065e-06,
|
| 1828 |
+
"loss": 2.0223,
|
| 1829 |
+
"step": 150000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 10.87,
|
| 1833 |
+
"eval_bleu": 26.2063,
|
| 1834 |
+
"eval_gen_len": 24.6095,
|
| 1835 |
+
"eval_loss": 1.7641891241073608,
|
| 1836 |
+
"eval_runtime": 4661.5713,
|
| 1837 |
+
"eval_samples_per_second": 11.837,
|
| 1838 |
+
"eval_steps_per_second": 1.48,
|
| 1839 |
+
"step": 150000
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 10.91,
|
| 1843 |
+
"learning_rate": 5.453666787483388e-06,
|
| 1844 |
+
"loss": 2.0329,
|
| 1845 |
+
"step": 150500
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 10.95,
|
| 1849 |
+
"learning_rate": 5.405340099069711e-06,
|
| 1850 |
+
"loss": 2.0588,
|
| 1851 |
+
"step": 151000
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 10.98,
|
| 1855 |
+
"learning_rate": 5.357013410656035e-06,
|
| 1856 |
+
"loss": 2.0424,
|
| 1857 |
+
"step": 151500
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 11.02,
|
| 1861 |
+
"learning_rate": 5.3086867222423586e-06,
|
| 1862 |
+
"loss": 2.0397,
|
| 1863 |
+
"step": 152000
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 11.05,
|
| 1867 |
+
"learning_rate": 5.260360033828682e-06,
|
| 1868 |
+
"loss": 2.0162,
|
| 1869 |
+
"step": 152500
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 11.09,
|
| 1873 |
+
"learning_rate": 5.212033345415006e-06,
|
| 1874 |
+
"loss": 2.0444,
|
| 1875 |
+
"step": 153000
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 11.13,
|
| 1879 |
+
"learning_rate": 5.163706657001329e-06,
|
| 1880 |
+
"loss": 2.0421,
|
| 1881 |
+
"step": 153500
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 11.16,
|
| 1885 |
+
"learning_rate": 5.115379968587652e-06,
|
| 1886 |
+
"loss": 2.0251,
|
| 1887 |
+
"step": 154000
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 11.2,
|
| 1891 |
+
"learning_rate": 5.067053280173977e-06,
|
| 1892 |
+
"loss": 2.0599,
|
| 1893 |
+
"step": 154500
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 11.24,
|
| 1897 |
+
"learning_rate": 5.0187265917603005e-06,
|
| 1898 |
+
"loss": 2.0569,
|
| 1899 |
+
"step": 155000
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 11.27,
|
| 1903 |
+
"learning_rate": 4.970399903346624e-06,
|
| 1904 |
+
"loss": 2.0439,
|
| 1905 |
+
"step": 155500
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 11.31,
|
| 1909 |
+
"learning_rate": 4.922073214932947e-06,
|
| 1910 |
+
"loss": 2.0327,
|
| 1911 |
+
"step": 156000
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 11.34,
|
| 1915 |
+
"learning_rate": 4.873746526519271e-06,
|
| 1916 |
+
"loss": 2.0487,
|
| 1917 |
+
"step": 156500
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 11.38,
|
| 1921 |
+
"learning_rate": 4.825419838105594e-06,
|
| 1922 |
+
"loss": 2.0561,
|
| 1923 |
+
"step": 157000
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 11.42,
|
| 1927 |
+
"learning_rate": 4.7770931496919175e-06,
|
| 1928 |
+
"loss": 2.0341,
|
| 1929 |
+
"step": 157500
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 11.45,
|
| 1933 |
+
"learning_rate": 4.7287664612782416e-06,
|
| 1934 |
+
"loss": 2.0343,
|
| 1935 |
+
"step": 158000
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 11.49,
|
| 1939 |
+
"learning_rate": 4.680439772864565e-06,
|
| 1940 |
+
"loss": 2.0393,
|
| 1941 |
+
"step": 158500
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 11.53,
|
| 1945 |
+
"learning_rate": 4.632113084450888e-06,
|
| 1946 |
+
"loss": 2.0165,
|
| 1947 |
+
"step": 159000
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 11.56,
|
| 1951 |
+
"learning_rate": 4.583786396037212e-06,
|
| 1952 |
+
"loss": 2.0432,
|
| 1953 |
+
"step": 159500
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 11.6,
|
| 1957 |
+
"learning_rate": 4.535459707623535e-06,
|
| 1958 |
+
"loss": 2.0254,
|
| 1959 |
+
"step": 160000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 11.63,
|
| 1963 |
+
"learning_rate": 4.4871330192098586e-06,
|
| 1964 |
+
"loss": 2.0027,
|
| 1965 |
+
"step": 160500
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 11.67,
|
| 1969 |
+
"learning_rate": 4.438806330796183e-06,
|
| 1970 |
+
"loss": 2.0255,
|
| 1971 |
+
"step": 161000
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 11.71,
|
| 1975 |
+
"learning_rate": 4.390479642382507e-06,
|
| 1976 |
+
"loss": 2.0347,
|
| 1977 |
+
"step": 161500
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 11.74,
|
| 1981 |
+
"learning_rate": 4.342152953968829e-06,
|
| 1982 |
+
"loss": 2.0265,
|
| 1983 |
+
"step": 162000
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 11.78,
|
| 1987 |
+
"learning_rate": 4.293826265555153e-06,
|
| 1988 |
+
"loss": 2.0319,
|
| 1989 |
+
"step": 162500
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 11.82,
|
| 1993 |
+
"learning_rate": 4.245499577141477e-06,
|
| 1994 |
+
"loss": 2.0332,
|
| 1995 |
+
"step": 163000
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 11.85,
|
| 1999 |
+
"learning_rate": 4.1971728887278005e-06,
|
| 2000 |
+
"loss": 2.0418,
|
| 2001 |
+
"step": 163500
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 11.89,
|
| 2005 |
+
"learning_rate": 4.148846200314124e-06,
|
| 2006 |
+
"loss": 2.0511,
|
| 2007 |
+
"step": 164000
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 11.92,
|
| 2011 |
+
"learning_rate": 4.100519511900448e-06,
|
| 2012 |
+
"loss": 2.0353,
|
| 2013 |
+
"step": 164500
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 11.96,
|
| 2017 |
+
"learning_rate": 4.052192823486771e-06,
|
| 2018 |
+
"loss": 2.0393,
|
| 2019 |
+
"step": 165000
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 12.0,
|
| 2023 |
+
"learning_rate": 4.003866135073094e-06,
|
| 2024 |
+
"loss": 2.016,
|
| 2025 |
+
"step": 165500
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 12.03,
|
| 2029 |
+
"learning_rate": 3.955539446659418e-06,
|
| 2030 |
+
"loss": 2.0318,
|
| 2031 |
+
"step": 166000
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 12.07,
|
| 2035 |
+
"learning_rate": 3.9072127582457416e-06,
|
| 2036 |
+
"loss": 2.0342,
|
| 2037 |
+
"step": 166500
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 12.11,
|
| 2041 |
+
"learning_rate": 3.858886069832065e-06,
|
| 2042 |
+
"loss": 1.9975,
|
| 2043 |
+
"step": 167000
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 12.14,
|
| 2047 |
+
"learning_rate": 3.810559381418389e-06,
|
| 2048 |
+
"loss": 2.0222,
|
| 2049 |
+
"step": 167500
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 12.18,
|
| 2053 |
+
"learning_rate": 3.762232693004712e-06,
|
| 2054 |
+
"loss": 2.0455,
|
| 2055 |
+
"step": 168000
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 12.21,
|
| 2059 |
+
"learning_rate": 3.7139060045910358e-06,
|
| 2060 |
+
"loss": 2.028,
|
| 2061 |
+
"step": 168500
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 12.25,
|
| 2065 |
+
"learning_rate": 3.6655793161773594e-06,
|
| 2066 |
+
"loss": 2.0267,
|
| 2067 |
+
"step": 169000
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 12.29,
|
| 2071 |
+
"learning_rate": 3.6172526277636827e-06,
|
| 2072 |
+
"loss": 2.0249,
|
| 2073 |
+
"step": 169500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 12.32,
|
| 2077 |
+
"learning_rate": 3.5689259393500063e-06,
|
| 2078 |
+
"loss": 2.0451,
|
| 2079 |
+
"step": 170000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 12.36,
|
| 2083 |
+
"learning_rate": 3.52059925093633e-06,
|
| 2084 |
+
"loss": 2.0133,
|
| 2085 |
+
"step": 170500
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 12.4,
|
| 2089 |
+
"learning_rate": 3.472272562522653e-06,
|
| 2090 |
+
"loss": 2.0377,
|
| 2091 |
+
"step": 171000
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 12.43,
|
| 2095 |
+
"learning_rate": 3.423945874108977e-06,
|
| 2096 |
+
"loss": 2.024,
|
| 2097 |
+
"step": 171500
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 12.47,
|
| 2101 |
+
"learning_rate": 3.375619185695301e-06,
|
| 2102 |
+
"loss": 2.0368,
|
| 2103 |
+
"step": 172000
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 12.5,
|
| 2107 |
+
"learning_rate": 3.327292497281624e-06,
|
| 2108 |
+
"loss": 2.0463,
|
| 2109 |
+
"step": 172500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 12.54,
|
| 2113 |
+
"learning_rate": 3.278965808867948e-06,
|
| 2114 |
+
"loss": 2.0359,
|
| 2115 |
+
"step": 173000
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 12.58,
|
| 2119 |
+
"learning_rate": 3.230639120454271e-06,
|
| 2120 |
+
"loss": 2.0283,
|
| 2121 |
+
"step": 173500
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 12.61,
|
| 2125 |
+
"learning_rate": 3.1823124320405947e-06,
|
| 2126 |
+
"loss": 2.035,
|
| 2127 |
+
"step": 174000
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 12.65,
|
| 2131 |
+
"learning_rate": 3.1339857436269183e-06,
|
| 2132 |
+
"loss": 2.0163,
|
| 2133 |
+
"step": 174500
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 12.69,
|
| 2137 |
+
"learning_rate": 3.0856590552132416e-06,
|
| 2138 |
+
"loss": 2.0234,
|
| 2139 |
+
"step": 175000
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 12.72,
|
| 2143 |
+
"learning_rate": 3.0373323667995652e-06,
|
| 2144 |
+
"loss": 2.0273,
|
| 2145 |
+
"step": 175500
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 12.76,
|
| 2149 |
+
"learning_rate": 2.989005678385889e-06,
|
| 2150 |
+
"loss": 2.0323,
|
| 2151 |
+
"step": 176000
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 12.79,
|
| 2155 |
+
"learning_rate": 2.940678989972212e-06,
|
| 2156 |
+
"loss": 2.019,
|
| 2157 |
+
"step": 176500
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 12.83,
|
| 2161 |
+
"learning_rate": 2.8923523015585358e-06,
|
| 2162 |
+
"loss": 2.0145,
|
| 2163 |
+
"step": 177000
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 12.87,
|
| 2167 |
+
"learning_rate": 2.8440256131448594e-06,
|
| 2168 |
+
"loss": 2.0078,
|
| 2169 |
+
"step": 177500
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 12.9,
|
| 2173 |
+
"learning_rate": 2.7956989247311827e-06,
|
| 2174 |
+
"loss": 2.0162,
|
| 2175 |
+
"step": 178000
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 12.94,
|
| 2179 |
+
"learning_rate": 2.7473722363175063e-06,
|
| 2180 |
+
"loss": 2.0227,
|
| 2181 |
+
"step": 178500
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 12.98,
|
| 2185 |
+
"learning_rate": 2.6990455479038304e-06,
|
| 2186 |
+
"loss": 2.0291,
|
| 2187 |
+
"step": 179000
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 13.01,
|
| 2191 |
+
"learning_rate": 2.650718859490153e-06,
|
| 2192 |
+
"loss": 2.0248,
|
| 2193 |
+
"step": 179500
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 13.05,
|
| 2197 |
+
"learning_rate": 2.6023921710764773e-06,
|
| 2198 |
+
"loss": 1.996,
|
| 2199 |
+
"step": 180000
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 13.08,
|
| 2203 |
+
"learning_rate": 2.554065482662801e-06,
|
| 2204 |
+
"loss": 2.012,
|
| 2205 |
+
"step": 180500
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 13.12,
|
| 2209 |
+
"learning_rate": 2.505738794249124e-06,
|
| 2210 |
+
"loss": 2.002,
|
| 2211 |
+
"step": 181000
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 13.16,
|
| 2215 |
+
"learning_rate": 2.457412105835448e-06,
|
| 2216 |
+
"loss": 2.0191,
|
| 2217 |
+
"step": 181500
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 13.19,
|
| 2221 |
+
"learning_rate": 2.4090854174217715e-06,
|
| 2222 |
+
"loss": 2.0173,
|
| 2223 |
+
"step": 182000
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 13.23,
|
| 2227 |
+
"learning_rate": 2.360758729008095e-06,
|
| 2228 |
+
"loss": 2.0347,
|
| 2229 |
+
"step": 182500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 13.27,
|
| 2233 |
+
"learning_rate": 2.3124320405944183e-06,
|
| 2234 |
+
"loss": 2.0357,
|
| 2235 |
+
"step": 183000
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 13.3,
|
| 2239 |
+
"learning_rate": 2.264105352180742e-06,
|
| 2240 |
+
"loss": 2.0414,
|
| 2241 |
+
"step": 183500
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 13.34,
|
| 2245 |
+
"learning_rate": 2.2157786637670657e-06,
|
| 2246 |
+
"loss": 2.036,
|
| 2247 |
+
"step": 184000
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 13.37,
|
| 2251 |
+
"learning_rate": 2.167451975353389e-06,
|
| 2252 |
+
"loss": 2.0063,
|
| 2253 |
+
"step": 184500
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 13.41,
|
| 2257 |
+
"learning_rate": 2.119125286939713e-06,
|
| 2258 |
+
"loss": 2.0062,
|
| 2259 |
+
"step": 185000
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 13.45,
|
| 2263 |
+
"learning_rate": 2.070798598526036e-06,
|
| 2264 |
+
"loss": 2.0191,
|
| 2265 |
+
"step": 185500
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 13.48,
|
| 2269 |
+
"learning_rate": 2.02247191011236e-06,
|
| 2270 |
+
"loss": 2.0148,
|
| 2271 |
+
"step": 186000
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 13.52,
|
| 2275 |
+
"learning_rate": 1.9741452216986835e-06,
|
| 2276 |
+
"loss": 2.0332,
|
| 2277 |
+
"step": 186500
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 13.56,
|
| 2281 |
+
"learning_rate": 1.9258185332850067e-06,
|
| 2282 |
+
"loss": 2.0137,
|
| 2283 |
+
"step": 187000
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 13.59,
|
| 2287 |
+
"learning_rate": 1.8774918448713304e-06,
|
| 2288 |
+
"loss": 2.0341,
|
| 2289 |
+
"step": 187500
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 13.63,
|
| 2293 |
+
"learning_rate": 1.829165156457654e-06,
|
| 2294 |
+
"loss": 1.9992,
|
| 2295 |
+
"step": 188000
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 13.66,
|
| 2299 |
+
"learning_rate": 1.7808384680439775e-06,
|
| 2300 |
+
"loss": 2.0233,
|
| 2301 |
+
"step": 188500
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 13.7,
|
| 2305 |
+
"learning_rate": 1.732511779630301e-06,
|
| 2306 |
+
"loss": 2.0065,
|
| 2307 |
+
"step": 189000
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 13.74,
|
| 2311 |
+
"learning_rate": 1.6841850912166246e-06,
|
| 2312 |
+
"loss": 2.024,
|
| 2313 |
+
"step": 189500
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 13.77,
|
| 2317 |
+
"learning_rate": 1.635858402802948e-06,
|
| 2318 |
+
"loss": 2.0306,
|
| 2319 |
+
"step": 190000
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 13.81,
|
| 2323 |
+
"learning_rate": 1.5875317143892715e-06,
|
| 2324 |
+
"loss": 2.0454,
|
| 2325 |
+
"step": 190500
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 13.85,
|
| 2329 |
+
"learning_rate": 1.5392050259755951e-06,
|
| 2330 |
+
"loss": 2.0143,
|
| 2331 |
+
"step": 191000
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 13.88,
|
| 2335 |
+
"learning_rate": 1.4908783375619188e-06,
|
| 2336 |
+
"loss": 2.0186,
|
| 2337 |
+
"step": 191500
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 13.92,
|
| 2341 |
+
"learning_rate": 1.4425516491482422e-06,
|
| 2342 |
+
"loss": 2.0109,
|
| 2343 |
+
"step": 192000
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 13.95,
|
| 2347 |
+
"learning_rate": 1.3942249607345657e-06,
|
| 2348 |
+
"loss": 2.0091,
|
| 2349 |
+
"step": 192500
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 13.99,
|
| 2353 |
+
"learning_rate": 1.3458982723208893e-06,
|
| 2354 |
+
"loss": 2.0223,
|
| 2355 |
+
"step": 193000
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 14.03,
|
| 2359 |
+
"learning_rate": 1.2975715839072127e-06,
|
| 2360 |
+
"loss": 1.9994,
|
| 2361 |
+
"step": 193500
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 14.06,
|
| 2365 |
+
"learning_rate": 1.2492448954935364e-06,
|
| 2366 |
+
"loss": 2.0055,
|
| 2367 |
+
"step": 194000
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 14.1,
|
| 2371 |
+
"learning_rate": 1.20091820707986e-06,
|
| 2372 |
+
"loss": 2.0195,
|
| 2373 |
+
"step": 194500
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 14.14,
|
| 2377 |
+
"learning_rate": 1.1525915186661835e-06,
|
| 2378 |
+
"loss": 2.0082,
|
| 2379 |
+
"step": 195000
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 14.17,
|
| 2383 |
+
"learning_rate": 1.1042648302525072e-06,
|
| 2384 |
+
"loss": 2.0337,
|
| 2385 |
+
"step": 195500
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 14.21,
|
| 2389 |
+
"learning_rate": 1.0559381418388306e-06,
|
| 2390 |
+
"loss": 2.0057,
|
| 2391 |
+
"step": 196000
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 14.24,
|
| 2395 |
+
"learning_rate": 1.007611453425154e-06,
|
| 2396 |
+
"loss": 2.0224,
|
| 2397 |
+
"step": 196500
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 14.28,
|
| 2401 |
+
"learning_rate": 9.592847650114777e-07,
|
| 2402 |
+
"loss": 2.031,
|
| 2403 |
+
"step": 197000
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 14.32,
|
| 2407 |
+
"learning_rate": 9.109580765978012e-07,
|
| 2408 |
+
"loss": 2.0261,
|
| 2409 |
+
"step": 197500
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 14.35,
|
| 2413 |
+
"learning_rate": 8.626313881841247e-07,
|
| 2414 |
+
"loss": 2.0288,
|
| 2415 |
+
"step": 198000
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 14.39,
|
| 2419 |
+
"learning_rate": 8.143046997704483e-07,
|
| 2420 |
+
"loss": 2.0266,
|
| 2421 |
+
"step": 198500
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 14.43,
|
| 2425 |
+
"learning_rate": 7.659780113567718e-07,
|
| 2426 |
+
"loss": 2.0164,
|
| 2427 |
+
"step": 199000
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 14.46,
|
| 2431 |
+
"learning_rate": 7.176513229430953e-07,
|
| 2432 |
+
"loss": 2.0295,
|
| 2433 |
+
"step": 199500
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 14.5,
|
| 2437 |
+
"learning_rate": 6.69324634529419e-07,
|
| 2438 |
+
"loss": 2.0177,
|
| 2439 |
+
"step": 200000
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 14.5,
|
| 2443 |
+
"eval_bleu": 26.5388,
|
| 2444 |
+
"eval_gen_len": 24.6306,
|
| 2445 |
+
"eval_loss": 1.7493975162506104,
|
| 2446 |
+
"eval_runtime": 4655.3081,
|
| 2447 |
+
"eval_samples_per_second": 11.853,
|
| 2448 |
+
"eval_steps_per_second": 1.482,
|
| 2449 |
+
"step": 200000
|
| 2450 |
+
}
|
| 2451 |
+
],
|
| 2452 |
+
"logging_steps": 500,
|
| 2453 |
+
"max_steps": 206925,
|
| 2454 |
+
"num_input_tokens_seen": 0,
|
| 2455 |
+
"num_train_epochs": 15,
|
| 2456 |
+
"save_steps": 50000,
|
| 2457 |
+
"total_flos": 2.0776464395563008e+17,
|
| 2458 |
+
"train_batch_size": 8,
|
| 2459 |
+
"trial_name": null,
|
| 2460 |
+
"trial_params": null
|
| 2461 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:596e6df7ff73946fbdc2cbdb9d67e12494a368115bae324f52a496aacf7624ac
|
| 3 |
+
size 4856
|