Upload . with huggingface_hub
Browse files- config.json +38 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2256 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/m2m100_418M",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"M2M100ForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"d_model": 1024,
|
| 11 |
+
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 4096,
|
| 13 |
+
"decoder_layerdrop": 0.05,
|
| 14 |
+
"decoder_layers": 12,
|
| 15 |
+
"decoder_start_token_id": 2,
|
| 16 |
+
"dropout": 0.1,
|
| 17 |
+
"early_stopping": true,
|
| 18 |
+
"encoder_attention_heads": 16,
|
| 19 |
+
"encoder_ffn_dim": 4096,
|
| 20 |
+
"encoder_layerdrop": 0.05,
|
| 21 |
+
"encoder_layers": 12,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"forced_bos_token_id": 128028,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_length": 200,
|
| 28 |
+
"max_position_embeddings": 1024,
|
| 29 |
+
"model_type": "m2m_100",
|
| 30 |
+
"num_beams": 5,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 1,
|
| 33 |
+
"scale_embedding": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.22.2",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 151434
|
| 38 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f154ae89fe3abb024e8f540e3b980443b5a2329876810220015640ac1ac818a
|
| 3 |
+
size 4062595807
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2c78e35b93f180595b7849c7b762bd6034c62d7b2cec4e9cd88afea3b036699
|
| 3 |
+
size 2031318983
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f41859c4bcaa1ece2d1ae44c5612cc1ca6a576b8a0a4fa53f58642a6626e411
|
| 3 |
+
size 14503
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd83df1571e4b870cbc056b878afbec7e0deb01f59c309d8a438f888c455735
|
| 3 |
+
size 14503
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f324a322c1c2b99d36f8612b0e56e801980174cf74edf2db4c264950f0d17cd
|
| 3 |
+
size 14503
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67b8ca9472b9bf80ec115c03f29442831ac68e7ddb75deea5992edd8aed00af9
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcdb47ea9a67a3b9ca698388655b2e32e42fb5bd42eee322bba8129d13b560b3
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8553540706634521,
|
| 3 |
+
"best_model_checkpoint": "/data/kabanda/result_en_fr/checkpoint-70000",
|
| 4 |
+
"epoch": 3.464660463274599,
|
| 5 |
+
"global_step": 70000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.9876262126311625e-05,
|
| 13 |
+
"loss": 5.2926,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"eval_bleu": 4.1544,
|
| 19 |
+
"eval_gen_len": 19.7843,
|
| 20 |
+
"eval_loss": 4.638627529144287,
|
| 21 |
+
"eval_runtime": 1532.3805,
|
| 22 |
+
"eval_samples_per_second": 4.661,
|
| 23 |
+
"eval_steps_per_second": 0.389,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"learning_rate": 4.975252425262325e-05,
|
| 29 |
+
"loss": 4.2117,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"eval_bleu": 5.0944,
|
| 35 |
+
"eval_gen_len": 25.8076,
|
| 36 |
+
"eval_loss": 3.982415199279785,
|
| 37 |
+
"eval_runtime": 2306.4168,
|
| 38 |
+
"eval_samples_per_second": 3.097,
|
| 39 |
+
"eval_steps_per_second": 0.258,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.07,
|
| 44 |
+
"learning_rate": 4.962878637893486e-05,
|
| 45 |
+
"loss": 3.6754,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.07,
|
| 50 |
+
"eval_bleu": 9.7913,
|
| 51 |
+
"eval_gen_len": 18.5118,
|
| 52 |
+
"eval_loss": 3.528294801712036,
|
| 53 |
+
"eval_runtime": 1473.4816,
|
| 54 |
+
"eval_samples_per_second": 4.848,
|
| 55 |
+
"eval_steps_per_second": 0.404,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.1,
|
| 60 |
+
"learning_rate": 4.9505048505246485e-05,
|
| 61 |
+
"loss": 3.2658,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.1,
|
| 66 |
+
"eval_bleu": 11.9905,
|
| 67 |
+
"eval_gen_len": 18.3529,
|
| 68 |
+
"eval_loss": 3.1733100414276123,
|
| 69 |
+
"eval_runtime": 1495.811,
|
| 70 |
+
"eval_samples_per_second": 4.775,
|
| 71 |
+
"eval_steps_per_second": 0.398,
|
| 72 |
+
"step": 2000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12,
|
| 76 |
+
"learning_rate": 4.938131063155811e-05,
|
| 77 |
+
"loss": 2.9666,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.12,
|
| 82 |
+
"eval_bleu": 14.6761,
|
| 83 |
+
"eval_gen_len": 17.3686,
|
| 84 |
+
"eval_loss": 2.8982934951782227,
|
| 85 |
+
"eval_runtime": 1369.1732,
|
| 86 |
+
"eval_samples_per_second": 5.217,
|
| 87 |
+
"eval_steps_per_second": 0.435,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.15,
|
| 92 |
+
"learning_rate": 4.925757275786973e-05,
|
| 93 |
+
"loss": 2.7349,
|
| 94 |
+
"step": 3000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"eval_bleu": 16.3199,
|
| 99 |
+
"eval_gen_len": 17.9567,
|
| 100 |
+
"eval_loss": 2.693359613418579,
|
| 101 |
+
"eval_runtime": 1446.9239,
|
| 102 |
+
"eval_samples_per_second": 4.937,
|
| 103 |
+
"eval_steps_per_second": 0.412,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.17,
|
| 108 |
+
"learning_rate": 4.913383488418135e-05,
|
| 109 |
+
"loss": 2.5024,
|
| 110 |
+
"step": 3500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.17,
|
| 114 |
+
"eval_bleu": 18.1705,
|
| 115 |
+
"eval_gen_len": 18.0659,
|
| 116 |
+
"eval_loss": 2.521655321121216,
|
| 117 |
+
"eval_runtime": 1477.4963,
|
| 118 |
+
"eval_samples_per_second": 4.835,
|
| 119 |
+
"eval_steps_per_second": 0.403,
|
| 120 |
+
"step": 3500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2,
|
| 124 |
+
"learning_rate": 4.9010097010492975e-05,
|
| 125 |
+
"loss": 2.3656,
|
| 126 |
+
"step": 4000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.2,
|
| 130 |
+
"eval_bleu": 19.9036,
|
| 131 |
+
"eval_gen_len": 17.349,
|
| 132 |
+
"eval_loss": 2.388259172439575,
|
| 133 |
+
"eval_runtime": 1363.4598,
|
| 134 |
+
"eval_samples_per_second": 5.239,
|
| 135 |
+
"eval_steps_per_second": 0.437,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.22,
|
| 140 |
+
"learning_rate": 4.888635913680459e-05,
|
| 141 |
+
"loss": 2.2392,
|
| 142 |
+
"step": 4500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.22,
|
| 146 |
+
"eval_bleu": 21.2018,
|
| 147 |
+
"eval_gen_len": 17.771,
|
| 148 |
+
"eval_loss": 2.2573838233947754,
|
| 149 |
+
"eval_runtime": 1439.0867,
|
| 150 |
+
"eval_samples_per_second": 4.964,
|
| 151 |
+
"eval_steps_per_second": 0.414,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.25,
|
| 156 |
+
"learning_rate": 4.876262126311621e-05,
|
| 157 |
+
"loss": 2.0961,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.25,
|
| 162 |
+
"eval_bleu": 22.5424,
|
| 163 |
+
"eval_gen_len": 17.0724,
|
| 164 |
+
"eval_loss": 2.15091609954834,
|
| 165 |
+
"eval_runtime": 1354.3029,
|
| 166 |
+
"eval_samples_per_second": 5.274,
|
| 167 |
+
"eval_steps_per_second": 0.44,
|
| 168 |
+
"step": 5000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.27,
|
| 172 |
+
"learning_rate": 4.8638883389427836e-05,
|
| 173 |
+
"loss": 1.9984,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.27,
|
| 178 |
+
"eval_bleu": 22.8122,
|
| 179 |
+
"eval_gen_len": 18.099,
|
| 180 |
+
"eval_loss": 2.0877768993377686,
|
| 181 |
+
"eval_runtime": 1398.4571,
|
| 182 |
+
"eval_samples_per_second": 5.108,
|
| 183 |
+
"eval_steps_per_second": 0.426,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3,
|
| 188 |
+
"learning_rate": 4.851514551573946e-05,
|
| 189 |
+
"loss": 1.9071,
|
| 190 |
+
"step": 6000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.3,
|
| 194 |
+
"eval_bleu": 25.4086,
|
| 195 |
+
"eval_gen_len": 17.1431,
|
| 196 |
+
"eval_loss": 1.975221872329712,
|
| 197 |
+
"eval_runtime": 1364.3455,
|
| 198 |
+
"eval_samples_per_second": 5.235,
|
| 199 |
+
"eval_steps_per_second": 0.437,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.32,
|
| 204 |
+
"learning_rate": 4.839140764205108e-05,
|
| 205 |
+
"loss": 1.8419,
|
| 206 |
+
"step": 6500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.32,
|
| 210 |
+
"eval_bleu": 26.1858,
|
| 211 |
+
"eval_gen_len": 17.5429,
|
| 212 |
+
"eval_loss": 1.896142601966858,
|
| 213 |
+
"eval_runtime": 1384.4266,
|
| 214 |
+
"eval_samples_per_second": 5.16,
|
| 215 |
+
"eval_steps_per_second": 0.431,
|
| 216 |
+
"step": 6500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.35,
|
| 220 |
+
"learning_rate": 4.82676697683627e-05,
|
| 221 |
+
"loss": 1.7696,
|
| 222 |
+
"step": 7000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.35,
|
| 226 |
+
"eval_bleu": 26.7992,
|
| 227 |
+
"eval_gen_len": 17.5017,
|
| 228 |
+
"eval_loss": 1.835010051727295,
|
| 229 |
+
"eval_runtime": 1380.8355,
|
| 230 |
+
"eval_samples_per_second": 5.173,
|
| 231 |
+
"eval_steps_per_second": 0.432,
|
| 232 |
+
"step": 7000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.37,
|
| 236 |
+
"learning_rate": 4.8143931894674325e-05,
|
| 237 |
+
"loss": 1.709,
|
| 238 |
+
"step": 7500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.37,
|
| 242 |
+
"eval_bleu": 28.566,
|
| 243 |
+
"eval_gen_len": 17.306,
|
| 244 |
+
"eval_loss": 1.754841923713684,
|
| 245 |
+
"eval_runtime": 1381.6803,
|
| 246 |
+
"eval_samples_per_second": 5.17,
|
| 247 |
+
"eval_steps_per_second": 0.431,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4,
|
| 252 |
+
"learning_rate": 4.802019402098595e-05,
|
| 253 |
+
"loss": 1.6455,
|
| 254 |
+
"step": 8000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4,
|
| 258 |
+
"eval_bleu": 28.9268,
|
| 259 |
+
"eval_gen_len": 17.2583,
|
| 260 |
+
"eval_loss": 1.7277344465255737,
|
| 261 |
+
"eval_runtime": 1383.5791,
|
| 262 |
+
"eval_samples_per_second": 5.163,
|
| 263 |
+
"eval_steps_per_second": 0.431,
|
| 264 |
+
"step": 8000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.42,
|
| 268 |
+
"learning_rate": 4.789645614729757e-05,
|
| 269 |
+
"loss": 1.5882,
|
| 270 |
+
"step": 8500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.42,
|
| 274 |
+
"eval_bleu": 29.6493,
|
| 275 |
+
"eval_gen_len": 17.3461,
|
| 276 |
+
"eval_loss": 1.6740621328353882,
|
| 277 |
+
"eval_runtime": 1382.0901,
|
| 278 |
+
"eval_samples_per_second": 5.168,
|
| 279 |
+
"eval_steps_per_second": 0.431,
|
| 280 |
+
"step": 8500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.45,
|
| 284 |
+
"learning_rate": 4.777271827360919e-05,
|
| 285 |
+
"loss": 1.5327,
|
| 286 |
+
"step": 9000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.45,
|
| 290 |
+
"eval_bleu": 30.4256,
|
| 291 |
+
"eval_gen_len": 17.1523,
|
| 292 |
+
"eval_loss": 1.6332658529281616,
|
| 293 |
+
"eval_runtime": 1358.5029,
|
| 294 |
+
"eval_samples_per_second": 5.258,
|
| 295 |
+
"eval_steps_per_second": 0.439,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.47,
|
| 300 |
+
"learning_rate": 4.7648980399920815e-05,
|
| 301 |
+
"loss": 1.4922,
|
| 302 |
+
"step": 9500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.47,
|
| 306 |
+
"eval_bleu": 31.3386,
|
| 307 |
+
"eval_gen_len": 17.1382,
|
| 308 |
+
"eval_loss": 1.5828430652618408,
|
| 309 |
+
"eval_runtime": 1370.5696,
|
| 310 |
+
"eval_samples_per_second": 5.212,
|
| 311 |
+
"eval_steps_per_second": 0.435,
|
| 312 |
+
"step": 9500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.49,
|
| 316 |
+
"learning_rate": 4.752524252623243e-05,
|
| 317 |
+
"loss": 1.4468,
|
| 318 |
+
"step": 10000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.49,
|
| 322 |
+
"eval_bleu": 32.089,
|
| 323 |
+
"eval_gen_len": 17.0442,
|
| 324 |
+
"eval_loss": 1.5548750162124634,
|
| 325 |
+
"eval_runtime": 1350.7323,
|
| 326 |
+
"eval_samples_per_second": 5.288,
|
| 327 |
+
"eval_steps_per_second": 0.441,
|
| 328 |
+
"step": 10000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.52,
|
| 332 |
+
"learning_rate": 4.740150465254405e-05,
|
| 333 |
+
"loss": 1.4125,
|
| 334 |
+
"step": 10500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.52,
|
| 338 |
+
"eval_bleu": 32.4293,
|
| 339 |
+
"eval_gen_len": 16.9427,
|
| 340 |
+
"eval_loss": 1.52163827419281,
|
| 341 |
+
"eval_runtime": 1355.6836,
|
| 342 |
+
"eval_samples_per_second": 5.269,
|
| 343 |
+
"eval_steps_per_second": 0.44,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.54,
|
| 348 |
+
"learning_rate": 4.7277766778855676e-05,
|
| 349 |
+
"loss": 1.411,
|
| 350 |
+
"step": 11000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.54,
|
| 354 |
+
"eval_bleu": 33.0258,
|
| 355 |
+
"eval_gen_len": 16.7907,
|
| 356 |
+
"eval_loss": 1.4887491464614868,
|
| 357 |
+
"eval_runtime": 1353.9121,
|
| 358 |
+
"eval_samples_per_second": 5.276,
|
| 359 |
+
"eval_steps_per_second": 0.44,
|
| 360 |
+
"step": 11000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.57,
|
| 364 |
+
"learning_rate": 4.71540289051673e-05,
|
| 365 |
+
"loss": 1.3452,
|
| 366 |
+
"step": 11500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.57,
|
| 370 |
+
"eval_bleu": 33.4866,
|
| 371 |
+
"eval_gen_len": 16.9954,
|
| 372 |
+
"eval_loss": 1.4632903337478638,
|
| 373 |
+
"eval_runtime": 1372.2724,
|
| 374 |
+
"eval_samples_per_second": 5.205,
|
| 375 |
+
"eval_steps_per_second": 0.434,
|
| 376 |
+
"step": 11500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.59,
|
| 380 |
+
"learning_rate": 4.703029103147892e-05,
|
| 381 |
+
"loss": 1.3275,
|
| 382 |
+
"step": 12000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.59,
|
| 386 |
+
"eval_bleu": 34.0579,
|
| 387 |
+
"eval_gen_len": 16.8965,
|
| 388 |
+
"eval_loss": 1.4243967533111572,
|
| 389 |
+
"eval_runtime": 1354.7775,
|
| 390 |
+
"eval_samples_per_second": 5.272,
|
| 391 |
+
"eval_steps_per_second": 0.44,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.62,
|
| 396 |
+
"learning_rate": 4.6906553157790536e-05,
|
| 397 |
+
"loss": 1.3073,
|
| 398 |
+
"step": 12500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.62,
|
| 402 |
+
"eval_bleu": 34.2442,
|
| 403 |
+
"eval_gen_len": 16.8726,
|
| 404 |
+
"eval_loss": 1.405735969543457,
|
| 405 |
+
"eval_runtime": 1344.8184,
|
| 406 |
+
"eval_samples_per_second": 5.311,
|
| 407 |
+
"eval_steps_per_second": 0.443,
|
| 408 |
+
"step": 12500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.64,
|
| 412 |
+
"learning_rate": 4.678281528410216e-05,
|
| 413 |
+
"loss": 1.283,
|
| 414 |
+
"step": 13000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.64,
|
| 418 |
+
"eval_bleu": 35.3879,
|
| 419 |
+
"eval_gen_len": 17.1285,
|
| 420 |
+
"eval_loss": 1.3807507753372192,
|
| 421 |
+
"eval_runtime": 1352.5706,
|
| 422 |
+
"eval_samples_per_second": 5.281,
|
| 423 |
+
"eval_steps_per_second": 0.441,
|
| 424 |
+
"step": 13000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.67,
|
| 428 |
+
"learning_rate": 4.665907741041378e-05,
|
| 429 |
+
"loss": 1.2526,
|
| 430 |
+
"step": 13500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.67,
|
| 434 |
+
"eval_bleu": 35.286,
|
| 435 |
+
"eval_gen_len": 17.0997,
|
| 436 |
+
"eval_loss": 1.3556008338928223,
|
| 437 |
+
"eval_runtime": 1360.8433,
|
| 438 |
+
"eval_samples_per_second": 5.249,
|
| 439 |
+
"eval_steps_per_second": 0.438,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.69,
|
| 444 |
+
"learning_rate": 4.65353395367254e-05,
|
| 445 |
+
"loss": 1.2355,
|
| 446 |
+
"step": 14000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.69,
|
| 450 |
+
"eval_bleu": 35.5153,
|
| 451 |
+
"eval_gen_len": 16.7456,
|
| 452 |
+
"eval_loss": 1.3322172164916992,
|
| 453 |
+
"eval_runtime": 1342.5622,
|
| 454 |
+
"eval_samples_per_second": 5.32,
|
| 455 |
+
"eval_steps_per_second": 0.444,
|
| 456 |
+
"step": 14000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.72,
|
| 460 |
+
"learning_rate": 4.6411601663037026e-05,
|
| 461 |
+
"loss": 1.2072,
|
| 462 |
+
"step": 14500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.72,
|
| 466 |
+
"eval_bleu": 35.9173,
|
| 467 |
+
"eval_gen_len": 16.9327,
|
| 468 |
+
"eval_loss": 1.3275119066238403,
|
| 469 |
+
"eval_runtime": 1338.7699,
|
| 470 |
+
"eval_samples_per_second": 5.335,
|
| 471 |
+
"eval_steps_per_second": 0.445,
|
| 472 |
+
"step": 14500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.74,
|
| 476 |
+
"learning_rate": 4.628786378934865e-05,
|
| 477 |
+
"loss": 1.195,
|
| 478 |
+
"step": 15000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.74,
|
| 482 |
+
"eval_bleu": 35.7681,
|
| 483 |
+
"eval_gen_len": 16.8524,
|
| 484 |
+
"eval_loss": 1.3128494024276733,
|
| 485 |
+
"eval_runtime": 1345.0353,
|
| 486 |
+
"eval_samples_per_second": 5.311,
|
| 487 |
+
"eval_steps_per_second": 0.443,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.77,
|
| 492 |
+
"learning_rate": 4.6164125915660264e-05,
|
| 493 |
+
"loss": 1.1689,
|
| 494 |
+
"step": 15500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.77,
|
| 498 |
+
"eval_bleu": 36.7489,
|
| 499 |
+
"eval_gen_len": 16.8296,
|
| 500 |
+
"eval_loss": 1.2844336032867432,
|
| 501 |
+
"eval_runtime": 1344.8016,
|
| 502 |
+
"eval_samples_per_second": 5.312,
|
| 503 |
+
"eval_steps_per_second": 0.443,
|
| 504 |
+
"step": 15500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.79,
|
| 508 |
+
"learning_rate": 4.6040388041971886e-05,
|
| 509 |
+
"loss": 1.1573,
|
| 510 |
+
"step": 16000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.79,
|
| 514 |
+
"eval_bleu": 37.2278,
|
| 515 |
+
"eval_gen_len": 16.8921,
|
| 516 |
+
"eval_loss": 1.2794346809387207,
|
| 517 |
+
"eval_runtime": 1341.0354,
|
| 518 |
+
"eval_samples_per_second": 5.326,
|
| 519 |
+
"eval_steps_per_second": 0.444,
|
| 520 |
+
"step": 16000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.82,
|
| 524 |
+
"learning_rate": 4.591665016828351e-05,
|
| 525 |
+
"loss": 1.1307,
|
| 526 |
+
"step": 16500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.82,
|
| 530 |
+
"eval_bleu": 36.748,
|
| 531 |
+
"eval_gen_len": 16.5867,
|
| 532 |
+
"eval_loss": 1.2566970586776733,
|
| 533 |
+
"eval_runtime": 1321.9093,
|
| 534 |
+
"eval_samples_per_second": 5.404,
|
| 535 |
+
"eval_steps_per_second": 0.451,
|
| 536 |
+
"step": 16500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.84,
|
| 540 |
+
"learning_rate": 4.579291229459513e-05,
|
| 541 |
+
"loss": 1.1222,
|
| 542 |
+
"step": 17000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.84,
|
| 546 |
+
"eval_bleu": 37.2793,
|
| 547 |
+
"eval_gen_len": 16.838,
|
| 548 |
+
"eval_loss": 1.2408839464187622,
|
| 549 |
+
"eval_runtime": 1339.7522,
|
| 550 |
+
"eval_samples_per_second": 5.332,
|
| 551 |
+
"eval_steps_per_second": 0.445,
|
| 552 |
+
"step": 17000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.87,
|
| 556 |
+
"learning_rate": 4.5669174420906754e-05,
|
| 557 |
+
"loss": 1.1129,
|
| 558 |
+
"step": 17500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.87,
|
| 562 |
+
"eval_bleu": 37.5801,
|
| 563 |
+
"eval_gen_len": 16.6506,
|
| 564 |
+
"eval_loss": 1.2285243272781372,
|
| 565 |
+
"eval_runtime": 1332.5485,
|
| 566 |
+
"eval_samples_per_second": 5.36,
|
| 567 |
+
"eval_steps_per_second": 0.447,
|
| 568 |
+
"step": 17500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.89,
|
| 572 |
+
"learning_rate": 4.5545436547218376e-05,
|
| 573 |
+
"loss": 1.11,
|
| 574 |
+
"step": 18000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.89,
|
| 578 |
+
"eval_bleu": 37.3726,
|
| 579 |
+
"eval_gen_len": 17.1085,
|
| 580 |
+
"eval_loss": 1.2697083950042725,
|
| 581 |
+
"eval_runtime": 1412.2634,
|
| 582 |
+
"eval_samples_per_second": 5.058,
|
| 583 |
+
"eval_steps_per_second": 0.422,
|
| 584 |
+
"step": 18000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.92,
|
| 588 |
+
"learning_rate": 4.542169867352999e-05,
|
| 589 |
+
"loss": 1.0779,
|
| 590 |
+
"step": 18500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.92,
|
| 594 |
+
"eval_bleu": 38.4744,
|
| 595 |
+
"eval_gen_len": 16.9744,
|
| 596 |
+
"eval_loss": 1.2056454420089722,
|
| 597 |
+
"eval_runtime": 1349.6935,
|
| 598 |
+
"eval_samples_per_second": 5.292,
|
| 599 |
+
"eval_steps_per_second": 0.442,
|
| 600 |
+
"step": 18500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.94,
|
| 604 |
+
"learning_rate": 4.5297960799841614e-05,
|
| 605 |
+
"loss": 1.0651,
|
| 606 |
+
"step": 19000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.94,
|
| 610 |
+
"eval_bleu": 38.3271,
|
| 611 |
+
"eval_gen_len": 17.006,
|
| 612 |
+
"eval_loss": 1.1996458768844604,
|
| 613 |
+
"eval_runtime": 1369.5468,
|
| 614 |
+
"eval_samples_per_second": 5.216,
|
| 615 |
+
"eval_steps_per_second": 0.435,
|
| 616 |
+
"step": 19000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.97,
|
| 620 |
+
"learning_rate": 4.5174222926153237e-05,
|
| 621 |
+
"loss": 1.0647,
|
| 622 |
+
"step": 19500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.97,
|
| 626 |
+
"eval_bleu": 38.6809,
|
| 627 |
+
"eval_gen_len": 16.7178,
|
| 628 |
+
"eval_loss": 1.1885197162628174,
|
| 629 |
+
"eval_runtime": 1332.8156,
|
| 630 |
+
"eval_samples_per_second": 5.359,
|
| 631 |
+
"eval_steps_per_second": 0.447,
|
| 632 |
+
"step": 19500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.99,
|
| 636 |
+
"learning_rate": 4.505048505246486e-05,
|
| 637 |
+
"loss": 1.0463,
|
| 638 |
+
"step": 20000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.99,
|
| 642 |
+
"eval_bleu": 39.0708,
|
| 643 |
+
"eval_gen_len": 16.8376,
|
| 644 |
+
"eval_loss": 1.1725914478302002,
|
| 645 |
+
"eval_runtime": 1343.3869,
|
| 646 |
+
"eval_samples_per_second": 5.317,
|
| 647 |
+
"eval_steps_per_second": 0.444,
|
| 648 |
+
"step": 20000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.01,
|
| 652 |
+
"learning_rate": 4.492674717877648e-05,
|
| 653 |
+
"loss": 0.9704,
|
| 654 |
+
"step": 20500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.01,
|
| 658 |
+
"eval_bleu": 39.6273,
|
| 659 |
+
"eval_gen_len": 16.8159,
|
| 660 |
+
"eval_loss": 1.158150315284729,
|
| 661 |
+
"eval_runtime": 1348.8721,
|
| 662 |
+
"eval_samples_per_second": 5.296,
|
| 663 |
+
"eval_steps_per_second": 0.442,
|
| 664 |
+
"step": 20500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.04,
|
| 668 |
+
"learning_rate": 4.4803009305088104e-05,
|
| 669 |
+
"loss": 0.8936,
|
| 670 |
+
"step": 21000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.04,
|
| 674 |
+
"eval_bleu": 39.3436,
|
| 675 |
+
"eval_gen_len": 16.6532,
|
| 676 |
+
"eval_loss": 1.1593575477600098,
|
| 677 |
+
"eval_runtime": 1336.9289,
|
| 678 |
+
"eval_samples_per_second": 5.343,
|
| 679 |
+
"eval_steps_per_second": 0.446,
|
| 680 |
+
"step": 21000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.06,
|
| 684 |
+
"learning_rate": 4.4679271431399726e-05,
|
| 685 |
+
"loss": 0.8839,
|
| 686 |
+
"step": 21500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.06,
|
| 690 |
+
"eval_bleu": 39.8191,
|
| 691 |
+
"eval_gen_len": 16.4936,
|
| 692 |
+
"eval_loss": 1.1491360664367676,
|
| 693 |
+
"eval_runtime": 1334.0963,
|
| 694 |
+
"eval_samples_per_second": 5.354,
|
| 695 |
+
"eval_steps_per_second": 0.447,
|
| 696 |
+
"step": 21500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.09,
|
| 700 |
+
"learning_rate": 4.455553355771135e-05,
|
| 701 |
+
"loss": 0.8823,
|
| 702 |
+
"step": 22000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.09,
|
| 706 |
+
"eval_bleu": 40.01,
|
| 707 |
+
"eval_gen_len": 16.6578,
|
| 708 |
+
"eval_loss": 1.14137601852417,
|
| 709 |
+
"eval_runtime": 1346.5689,
|
| 710 |
+
"eval_samples_per_second": 5.305,
|
| 711 |
+
"eval_steps_per_second": 0.443,
|
| 712 |
+
"step": 22000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.11,
|
| 716 |
+
"learning_rate": 4.443179568402297e-05,
|
| 717 |
+
"loss": 0.8898,
|
| 718 |
+
"step": 22500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.11,
|
| 722 |
+
"eval_bleu": 39.7192,
|
| 723 |
+
"eval_gen_len": 16.8047,
|
| 724 |
+
"eval_loss": 1.125238299369812,
|
| 725 |
+
"eval_runtime": 1349.9067,
|
| 726 |
+
"eval_samples_per_second": 5.291,
|
| 727 |
+
"eval_steps_per_second": 0.442,
|
| 728 |
+
"step": 22500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.14,
|
| 732 |
+
"learning_rate": 4.4308057810334594e-05,
|
| 733 |
+
"loss": 0.8783,
|
| 734 |
+
"step": 23000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.14,
|
| 738 |
+
"eval_bleu": 39.9004,
|
| 739 |
+
"eval_gen_len": 16.7007,
|
| 740 |
+
"eval_loss": 1.1242141723632812,
|
| 741 |
+
"eval_runtime": 1331.8043,
|
| 742 |
+
"eval_samples_per_second": 5.363,
|
| 743 |
+
"eval_steps_per_second": 0.448,
|
| 744 |
+
"step": 23000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.16,
|
| 748 |
+
"learning_rate": 4.418431993664621e-05,
|
| 749 |
+
"loss": 0.869,
|
| 750 |
+
"step": 23500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.16,
|
| 754 |
+
"eval_bleu": 40.6549,
|
| 755 |
+
"eval_gen_len": 16.8279,
|
| 756 |
+
"eval_loss": 1.1088123321533203,
|
| 757 |
+
"eval_runtime": 1337.7469,
|
| 758 |
+
"eval_samples_per_second": 5.34,
|
| 759 |
+
"eval_steps_per_second": 0.446,
|
| 760 |
+
"step": 23500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.19,
|
| 764 |
+
"learning_rate": 4.406058206295783e-05,
|
| 765 |
+
"loss": 0.8602,
|
| 766 |
+
"step": 24000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.19,
|
| 770 |
+
"eval_bleu": 40.9968,
|
| 771 |
+
"eval_gen_len": 16.7487,
|
| 772 |
+
"eval_loss": 1.100970983505249,
|
| 773 |
+
"eval_runtime": 1347.265,
|
| 774 |
+
"eval_samples_per_second": 5.302,
|
| 775 |
+
"eval_steps_per_second": 0.442,
|
| 776 |
+
"step": 24000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.21,
|
| 780 |
+
"learning_rate": 4.3936844189269454e-05,
|
| 781 |
+
"loss": 0.8617,
|
| 782 |
+
"step": 24500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.21,
|
| 786 |
+
"eval_bleu": 40.6003,
|
| 787 |
+
"eval_gen_len": 16.544,
|
| 788 |
+
"eval_loss": 1.1008094549179077,
|
| 789 |
+
"eval_runtime": 1323.7915,
|
| 790 |
+
"eval_samples_per_second": 5.396,
|
| 791 |
+
"eval_steps_per_second": 0.45,
|
| 792 |
+
"step": 24500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.24,
|
| 796 |
+
"learning_rate": 4.3813106315581076e-05,
|
| 797 |
+
"loss": 0.8571,
|
| 798 |
+
"step": 25000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.24,
|
| 802 |
+
"eval_bleu": 41.2081,
|
| 803 |
+
"eval_gen_len": 16.8625,
|
| 804 |
+
"eval_loss": 1.0926491022109985,
|
| 805 |
+
"eval_runtime": 1338.7092,
|
| 806 |
+
"eval_samples_per_second": 5.336,
|
| 807 |
+
"eval_steps_per_second": 0.445,
|
| 808 |
+
"step": 25000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.26,
|
| 812 |
+
"learning_rate": 4.36893684418927e-05,
|
| 813 |
+
"loss": 0.845,
|
| 814 |
+
"step": 25500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.26,
|
| 818 |
+
"eval_bleu": 41.0718,
|
| 819 |
+
"eval_gen_len": 16.6553,
|
| 820 |
+
"eval_loss": 1.088665246963501,
|
| 821 |
+
"eval_runtime": 1330.6533,
|
| 822 |
+
"eval_samples_per_second": 5.368,
|
| 823 |
+
"eval_steps_per_second": 0.448,
|
| 824 |
+
"step": 25500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.29,
|
| 828 |
+
"learning_rate": 4.356563056820432e-05,
|
| 829 |
+
"loss": 0.8533,
|
| 830 |
+
"step": 26000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.29,
|
| 834 |
+
"eval_bleu": 41.2884,
|
| 835 |
+
"eval_gen_len": 16.7981,
|
| 836 |
+
"eval_loss": 1.0817835330963135,
|
| 837 |
+
"eval_runtime": 1339.6246,
|
| 838 |
+
"eval_samples_per_second": 5.332,
|
| 839 |
+
"eval_steps_per_second": 0.445,
|
| 840 |
+
"step": 26000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.31,
|
| 844 |
+
"learning_rate": 4.344189269451594e-05,
|
| 845 |
+
"loss": 0.8486,
|
| 846 |
+
"step": 26500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.31,
|
| 850 |
+
"eval_bleu": 40.9701,
|
| 851 |
+
"eval_gen_len": 16.9712,
|
| 852 |
+
"eval_loss": 1.0806611776351929,
|
| 853 |
+
"eval_runtime": 1354.0651,
|
| 854 |
+
"eval_samples_per_second": 5.275,
|
| 855 |
+
"eval_steps_per_second": 0.44,
|
| 856 |
+
"step": 26500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.34,
|
| 860 |
+
"learning_rate": 4.331815482082756e-05,
|
| 861 |
+
"loss": 0.8441,
|
| 862 |
+
"step": 27000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.34,
|
| 866 |
+
"eval_bleu": 41.3608,
|
| 867 |
+
"eval_gen_len": 16.6277,
|
| 868 |
+
"eval_loss": 1.0752187967300415,
|
| 869 |
+
"eval_runtime": 1330.2452,
|
| 870 |
+
"eval_samples_per_second": 5.37,
|
| 871 |
+
"eval_steps_per_second": 0.448,
|
| 872 |
+
"step": 27000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.36,
|
| 876 |
+
"learning_rate": 4.319441694713918e-05,
|
| 877 |
+
"loss": 0.8531,
|
| 878 |
+
"step": 27500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.36,
|
| 882 |
+
"eval_bleu": 41.5215,
|
| 883 |
+
"eval_gen_len": 16.8085,
|
| 884 |
+
"eval_loss": 1.066485047340393,
|
| 885 |
+
"eval_runtime": 1334.1554,
|
| 886 |
+
"eval_samples_per_second": 5.354,
|
| 887 |
+
"eval_steps_per_second": 0.447,
|
| 888 |
+
"step": 27500
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.39,
|
| 892 |
+
"learning_rate": 4.3070679073450804e-05,
|
| 893 |
+
"loss": 0.8371,
|
| 894 |
+
"step": 28000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.39,
|
| 898 |
+
"eval_bleu": 41.9045,
|
| 899 |
+
"eval_gen_len": 16.736,
|
| 900 |
+
"eval_loss": 1.0553510189056396,
|
| 901 |
+
"eval_runtime": 1333.8696,
|
| 902 |
+
"eval_samples_per_second": 5.355,
|
| 903 |
+
"eval_steps_per_second": 0.447,
|
| 904 |
+
"step": 28000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.41,
|
| 908 |
+
"learning_rate": 4.294694119976243e-05,
|
| 909 |
+
"loss": 0.8171,
|
| 910 |
+
"step": 28500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.41,
|
| 914 |
+
"eval_bleu": 42.0877,
|
| 915 |
+
"eval_gen_len": 16.7124,
|
| 916 |
+
"eval_loss": 1.0496976375579834,
|
| 917 |
+
"eval_runtime": 1332.4047,
|
| 918 |
+
"eval_samples_per_second": 5.361,
|
| 919 |
+
"eval_steps_per_second": 0.447,
|
| 920 |
+
"step": 28500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.44,
|
| 924 |
+
"learning_rate": 4.282320332607405e-05,
|
| 925 |
+
"loss": 0.8359,
|
| 926 |
+
"step": 29000
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.44,
|
| 930 |
+
"eval_bleu": 42.1081,
|
| 931 |
+
"eval_gen_len": 16.6317,
|
| 932 |
+
"eval_loss": 1.0442363023757935,
|
| 933 |
+
"eval_runtime": 1329.2047,
|
| 934 |
+
"eval_samples_per_second": 5.374,
|
| 935 |
+
"eval_steps_per_second": 0.448,
|
| 936 |
+
"step": 29000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.46,
|
| 940 |
+
"learning_rate": 4.2699465452385665e-05,
|
| 941 |
+
"loss": 0.8097,
|
| 942 |
+
"step": 29500
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.46,
|
| 946 |
+
"eval_bleu": 42.3305,
|
| 947 |
+
"eval_gen_len": 16.5241,
|
| 948 |
+
"eval_loss": 1.0467731952667236,
|
| 949 |
+
"eval_runtime": 1325.978,
|
| 950 |
+
"eval_samples_per_second": 5.387,
|
| 951 |
+
"eval_steps_per_second": 0.449,
|
| 952 |
+
"step": 29500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.48,
|
| 956 |
+
"learning_rate": 4.257572757869729e-05,
|
| 957 |
+
"loss": 0.8151,
|
| 958 |
+
"step": 30000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.48,
|
| 962 |
+
"eval_bleu": 42.208,
|
| 963 |
+
"eval_gen_len": 16.5507,
|
| 964 |
+
"eval_loss": 1.0358787775039673,
|
| 965 |
+
"eval_runtime": 1325.8985,
|
| 966 |
+
"eval_samples_per_second": 5.387,
|
| 967 |
+
"eval_steps_per_second": 0.45,
|
| 968 |
+
"step": 30000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.51,
|
| 972 |
+
"learning_rate": 4.245198970500891e-05,
|
| 973 |
+
"loss": 0.8008,
|
| 974 |
+
"step": 30500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.51,
|
| 978 |
+
"eval_bleu": 43.0639,
|
| 979 |
+
"eval_gen_len": 16.7362,
|
| 980 |
+
"eval_loss": 1.0226542949676514,
|
| 981 |
+
"eval_runtime": 1337.8285,
|
| 982 |
+
"eval_samples_per_second": 5.339,
|
| 983 |
+
"eval_steps_per_second": 0.445,
|
| 984 |
+
"step": 30500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.53,
|
| 988 |
+
"learning_rate": 4.232825183132053e-05,
|
| 989 |
+
"loss": 0.8105,
|
| 990 |
+
"step": 31000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.53,
|
| 994 |
+
"eval_bleu": 42.7617,
|
| 995 |
+
"eval_gen_len": 16.4645,
|
| 996 |
+
"eval_loss": 1.016375184059143,
|
| 997 |
+
"eval_runtime": 1327.3901,
|
| 998 |
+
"eval_samples_per_second": 5.381,
|
| 999 |
+
"eval_steps_per_second": 0.449,
|
| 1000 |
+
"step": 31000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.56,
|
| 1004 |
+
"learning_rate": 4.2204513957632154e-05,
|
| 1005 |
+
"loss": 0.8108,
|
| 1006 |
+
"step": 31500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.56,
|
| 1010 |
+
"eval_bleu": 42.9124,
|
| 1011 |
+
"eval_gen_len": 16.8116,
|
| 1012 |
+
"eval_loss": 1.0157625675201416,
|
| 1013 |
+
"eval_runtime": 1343.0655,
|
| 1014 |
+
"eval_samples_per_second": 5.318,
|
| 1015 |
+
"eval_steps_per_second": 0.444,
|
| 1016 |
+
"step": 31500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.58,
|
| 1020 |
+
"learning_rate": 4.208077608394378e-05,
|
| 1021 |
+
"loss": 0.8052,
|
| 1022 |
+
"step": 32000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.58,
|
| 1026 |
+
"eval_bleu": 42.8819,
|
| 1027 |
+
"eval_gen_len": 16.6151,
|
| 1028 |
+
"eval_loss": 1.0091865062713623,
|
| 1029 |
+
"eval_runtime": 1330.5695,
|
| 1030 |
+
"eval_samples_per_second": 5.368,
|
| 1031 |
+
"eval_steps_per_second": 0.448,
|
| 1032 |
+
"step": 32000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.61,
|
| 1036 |
+
"learning_rate": 4.195703821025539e-05,
|
| 1037 |
+
"loss": 0.8024,
|
| 1038 |
+
"step": 32500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.61,
|
| 1042 |
+
"eval_bleu": 43.0788,
|
| 1043 |
+
"eval_gen_len": 16.7483,
|
| 1044 |
+
"eval_loss": 1.0076141357421875,
|
| 1045 |
+
"eval_runtime": 1332.4446,
|
| 1046 |
+
"eval_samples_per_second": 5.361,
|
| 1047 |
+
"eval_steps_per_second": 0.447,
|
| 1048 |
+
"step": 32500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.63,
|
| 1052 |
+
"learning_rate": 4.1833300336567015e-05,
|
| 1053 |
+
"loss": 0.7971,
|
| 1054 |
+
"step": 33000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.63,
|
| 1058 |
+
"eval_bleu": 43.6296,
|
| 1059 |
+
"eval_gen_len": 16.7942,
|
| 1060 |
+
"eval_loss": 0.9935155510902405,
|
| 1061 |
+
"eval_runtime": 1351.7288,
|
| 1062 |
+
"eval_samples_per_second": 5.284,
|
| 1063 |
+
"eval_steps_per_second": 0.441,
|
| 1064 |
+
"step": 33000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.66,
|
| 1068 |
+
"learning_rate": 4.170956246287864e-05,
|
| 1069 |
+
"loss": 0.8006,
|
| 1070 |
+
"step": 33500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.66,
|
| 1074 |
+
"eval_bleu": 43.9739,
|
| 1075 |
+
"eval_gen_len": 16.7378,
|
| 1076 |
+
"eval_loss": 0.991138219833374,
|
| 1077 |
+
"eval_runtime": 1346.9798,
|
| 1078 |
+
"eval_samples_per_second": 5.303,
|
| 1079 |
+
"eval_steps_per_second": 0.442,
|
| 1080 |
+
"step": 33500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.68,
|
| 1084 |
+
"learning_rate": 4.158582458919026e-05,
|
| 1085 |
+
"loss": 0.7855,
|
| 1086 |
+
"step": 34000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.68,
|
| 1090 |
+
"eval_bleu": 43.5366,
|
| 1091 |
+
"eval_gen_len": 16.5919,
|
| 1092 |
+
"eval_loss": 0.991809070110321,
|
| 1093 |
+
"eval_runtime": 1337.0859,
|
| 1094 |
+
"eval_samples_per_second": 5.342,
|
| 1095 |
+
"eval_steps_per_second": 0.446,
|
| 1096 |
+
"step": 34000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.71,
|
| 1100 |
+
"learning_rate": 4.146208671550188e-05,
|
| 1101 |
+
"loss": 0.7786,
|
| 1102 |
+
"step": 34500
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.71,
|
| 1106 |
+
"eval_bleu": 43.8212,
|
| 1107 |
+
"eval_gen_len": 16.5705,
|
| 1108 |
+
"eval_loss": 0.9883202314376831,
|
| 1109 |
+
"eval_runtime": 1322.7907,
|
| 1110 |
+
"eval_samples_per_second": 5.4,
|
| 1111 |
+
"eval_steps_per_second": 0.451,
|
| 1112 |
+
"step": 34500
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.73,
|
| 1116 |
+
"learning_rate": 4.1338348841813505e-05,
|
| 1117 |
+
"loss": 0.7877,
|
| 1118 |
+
"step": 35000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.73,
|
| 1122 |
+
"eval_bleu": 43.7342,
|
| 1123 |
+
"eval_gen_len": 16.7165,
|
| 1124 |
+
"eval_loss": 0.9775007963180542,
|
| 1125 |
+
"eval_runtime": 1338.9365,
|
| 1126 |
+
"eval_samples_per_second": 5.335,
|
| 1127 |
+
"eval_steps_per_second": 0.445,
|
| 1128 |
+
"step": 35000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 1.76,
|
| 1132 |
+
"learning_rate": 4.121461096812513e-05,
|
| 1133 |
+
"loss": 0.7832,
|
| 1134 |
+
"step": 35500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.76,
|
| 1138 |
+
"eval_bleu": 43.8512,
|
| 1139 |
+
"eval_gen_len": 16.712,
|
| 1140 |
+
"eval_loss": 0.9759693145751953,
|
| 1141 |
+
"eval_runtime": 1341.6352,
|
| 1142 |
+
"eval_samples_per_second": 5.324,
|
| 1143 |
+
"eval_steps_per_second": 0.444,
|
| 1144 |
+
"step": 35500
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.78,
|
| 1148 |
+
"learning_rate": 4.109087309443675e-05,
|
| 1149 |
+
"loss": 0.7812,
|
| 1150 |
+
"step": 36000
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.78,
|
| 1154 |
+
"eval_bleu": 44.606,
|
| 1155 |
+
"eval_gen_len": 16.7719,
|
| 1156 |
+
"eval_loss": 0.9725255370140076,
|
| 1157 |
+
"eval_runtime": 1344.5964,
|
| 1158 |
+
"eval_samples_per_second": 5.312,
|
| 1159 |
+
"eval_steps_per_second": 0.443,
|
| 1160 |
+
"step": 36000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.81,
|
| 1164 |
+
"learning_rate": 4.096713522074837e-05,
|
| 1165 |
+
"loss": 0.766,
|
| 1166 |
+
"step": 36500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.81,
|
| 1170 |
+
"eval_bleu": 44.1586,
|
| 1171 |
+
"eval_gen_len": 16.568,
|
| 1172 |
+
"eval_loss": 0.9698735475540161,
|
| 1173 |
+
"eval_runtime": 1331.8223,
|
| 1174 |
+
"eval_samples_per_second": 5.363,
|
| 1175 |
+
"eval_steps_per_second": 0.448,
|
| 1176 |
+
"step": 36500
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.83,
|
| 1180 |
+
"learning_rate": 4.0843397347059994e-05,
|
| 1181 |
+
"loss": 0.7688,
|
| 1182 |
+
"step": 37000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.83,
|
| 1186 |
+
"eval_bleu": 44.5813,
|
| 1187 |
+
"eval_gen_len": 16.7396,
|
| 1188 |
+
"eval_loss": 0.9606902599334717,
|
| 1189 |
+
"eval_runtime": 1334.582,
|
| 1190 |
+
"eval_samples_per_second": 5.352,
|
| 1191 |
+
"eval_steps_per_second": 0.447,
|
| 1192 |
+
"step": 37000
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.86,
|
| 1196 |
+
"learning_rate": 4.071965947337161e-05,
|
| 1197 |
+
"loss": 0.7727,
|
| 1198 |
+
"step": 37500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.86,
|
| 1202 |
+
"eval_bleu": 44.1615,
|
| 1203 |
+
"eval_gen_len": 16.707,
|
| 1204 |
+
"eval_loss": 0.962368369102478,
|
| 1205 |
+
"eval_runtime": 1341.1556,
|
| 1206 |
+
"eval_samples_per_second": 5.326,
|
| 1207 |
+
"eval_steps_per_second": 0.444,
|
| 1208 |
+
"step": 37500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.88,
|
| 1212 |
+
"learning_rate": 4.059592159968323e-05,
|
| 1213 |
+
"loss": 0.7645,
|
| 1214 |
+
"step": 38000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.88,
|
| 1218 |
+
"eval_bleu": 44.1652,
|
| 1219 |
+
"eval_gen_len": 16.5927,
|
| 1220 |
+
"eval_loss": 0.9592034220695496,
|
| 1221 |
+
"eval_runtime": 1336.4184,
|
| 1222 |
+
"eval_samples_per_second": 5.345,
|
| 1223 |
+
"eval_steps_per_second": 0.446,
|
| 1224 |
+
"step": 38000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.91,
|
| 1228 |
+
"learning_rate": 4.0472183725994855e-05,
|
| 1229 |
+
"loss": 0.7638,
|
| 1230 |
+
"step": 38500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.91,
|
| 1234 |
+
"eval_bleu": 44.4663,
|
| 1235 |
+
"eval_gen_len": 16.6448,
|
| 1236 |
+
"eval_loss": 0.9551029205322266,
|
| 1237 |
+
"eval_runtime": 1335.4927,
|
| 1238 |
+
"eval_samples_per_second": 5.349,
|
| 1239 |
+
"eval_steps_per_second": 0.446,
|
| 1240 |
+
"step": 38500
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 1.93,
|
| 1244 |
+
"learning_rate": 4.034844585230648e-05,
|
| 1245 |
+
"loss": 0.7544,
|
| 1246 |
+
"step": 39000
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.93,
|
| 1250 |
+
"eval_bleu": 44.3807,
|
| 1251 |
+
"eval_gen_len": 16.7161,
|
| 1252 |
+
"eval_loss": 0.9564537405967712,
|
| 1253 |
+
"eval_runtime": 1335.4847,
|
| 1254 |
+
"eval_samples_per_second": 5.349,
|
| 1255 |
+
"eval_steps_per_second": 0.446,
|
| 1256 |
+
"step": 39000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.96,
|
| 1260 |
+
"learning_rate": 4.02247079786181e-05,
|
| 1261 |
+
"loss": 0.7513,
|
| 1262 |
+
"step": 39500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.96,
|
| 1266 |
+
"eval_bleu": 44.9465,
|
| 1267 |
+
"eval_gen_len": 16.6132,
|
| 1268 |
+
"eval_loss": 0.9481050372123718,
|
| 1269 |
+
"eval_runtime": 1327.2386,
|
| 1270 |
+
"eval_samples_per_second": 5.382,
|
| 1271 |
+
"eval_steps_per_second": 0.449,
|
| 1272 |
+
"step": 39500
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 1.98,
|
| 1276 |
+
"learning_rate": 4.010097010492972e-05,
|
| 1277 |
+
"loss": 0.7563,
|
| 1278 |
+
"step": 40000
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.98,
|
| 1282 |
+
"eval_bleu": 45.5396,
|
| 1283 |
+
"eval_gen_len": 16.8183,
|
| 1284 |
+
"eval_loss": 0.939414381980896,
|
| 1285 |
+
"eval_runtime": 1341.9443,
|
| 1286 |
+
"eval_samples_per_second": 5.323,
|
| 1287 |
+
"eval_steps_per_second": 0.444,
|
| 1288 |
+
"step": 40000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 2.0,
|
| 1292 |
+
"learning_rate": 3.997723223124134e-05,
|
| 1293 |
+
"loss": 0.7206,
|
| 1294 |
+
"step": 40500
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.0,
|
| 1298 |
+
"eval_bleu": 44.6231,
|
| 1299 |
+
"eval_gen_len": 16.5586,
|
| 1300 |
+
"eval_loss": 0.9512418508529663,
|
| 1301 |
+
"eval_runtime": 1333.952,
|
| 1302 |
+
"eval_samples_per_second": 5.355,
|
| 1303 |
+
"eval_steps_per_second": 0.447,
|
| 1304 |
+
"step": 40500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.03,
|
| 1308 |
+
"learning_rate": 3.985349435755296e-05,
|
| 1309 |
+
"loss": 0.5864,
|
| 1310 |
+
"step": 41000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 2.03,
|
| 1314 |
+
"eval_bleu": 45.4858,
|
| 1315 |
+
"eval_gen_len": 16.784,
|
| 1316 |
+
"eval_loss": 0.9353885650634766,
|
| 1317 |
+
"eval_runtime": 1336.3848,
|
| 1318 |
+
"eval_samples_per_second": 5.345,
|
| 1319 |
+
"eval_steps_per_second": 0.446,
|
| 1320 |
+
"step": 41000
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.05,
|
| 1324 |
+
"learning_rate": 3.972975648386458e-05,
|
| 1325 |
+
"loss": 0.5916,
|
| 1326 |
+
"step": 41500
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.05,
|
| 1330 |
+
"eval_bleu": 45.1704,
|
| 1331 |
+
"eval_gen_len": 16.6795,
|
| 1332 |
+
"eval_loss": 0.9400736689567566,
|
| 1333 |
+
"eval_runtime": 1337.6062,
|
| 1334 |
+
"eval_samples_per_second": 5.34,
|
| 1335 |
+
"eval_steps_per_second": 0.446,
|
| 1336 |
+
"step": 41500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.08,
|
| 1340 |
+
"learning_rate": 3.9606018610176205e-05,
|
| 1341 |
+
"loss": 0.5907,
|
| 1342 |
+
"step": 42000
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.08,
|
| 1346 |
+
"eval_bleu": 45.0619,
|
| 1347 |
+
"eval_gen_len": 16.6905,
|
| 1348 |
+
"eval_loss": 0.9472643733024597,
|
| 1349 |
+
"eval_runtime": 1332.9894,
|
| 1350 |
+
"eval_samples_per_second": 5.359,
|
| 1351 |
+
"eval_steps_per_second": 0.447,
|
| 1352 |
+
"step": 42000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 2.1,
|
| 1356 |
+
"learning_rate": 3.948228073648783e-05,
|
| 1357 |
+
"loss": 0.584,
|
| 1358 |
+
"step": 42500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 2.1,
|
| 1362 |
+
"eval_bleu": 45.072,
|
| 1363 |
+
"eval_gen_len": 16.7739,
|
| 1364 |
+
"eval_loss": 0.943854808807373,
|
| 1365 |
+
"eval_runtime": 1336.6571,
|
| 1366 |
+
"eval_samples_per_second": 5.344,
|
| 1367 |
+
"eval_steps_per_second": 0.446,
|
| 1368 |
+
"step": 42500
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.13,
|
| 1372 |
+
"learning_rate": 3.935854286279945e-05,
|
| 1373 |
+
"loss": 0.5979,
|
| 1374 |
+
"step": 43000
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.13,
|
| 1378 |
+
"eval_bleu": 45.1267,
|
| 1379 |
+
"eval_gen_len": 16.9086,
|
| 1380 |
+
"eval_loss": 0.9410138726234436,
|
| 1381 |
+
"eval_runtime": 1338.7702,
|
| 1382 |
+
"eval_samples_per_second": 5.335,
|
| 1383 |
+
"eval_steps_per_second": 0.445,
|
| 1384 |
+
"step": 43000
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.15,
|
| 1388 |
+
"learning_rate": 3.9234804989111066e-05,
|
| 1389 |
+
"loss": 0.5929,
|
| 1390 |
+
"step": 43500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.15,
|
| 1394 |
+
"eval_bleu": 45.3207,
|
| 1395 |
+
"eval_gen_len": 16.6486,
|
| 1396 |
+
"eval_loss": 0.9384570121765137,
|
| 1397 |
+
"eval_runtime": 1333.0456,
|
| 1398 |
+
"eval_samples_per_second": 5.358,
|
| 1399 |
+
"eval_steps_per_second": 0.447,
|
| 1400 |
+
"step": 43500
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 2.18,
|
| 1404 |
+
"learning_rate": 3.911106711542269e-05,
|
| 1405 |
+
"loss": 0.588,
|
| 1406 |
+
"step": 44000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.18,
|
| 1410 |
+
"eval_bleu": 45.3945,
|
| 1411 |
+
"eval_gen_len": 16.7284,
|
| 1412 |
+
"eval_loss": 0.9332572817802429,
|
| 1413 |
+
"eval_runtime": 1330.0518,
|
| 1414 |
+
"eval_samples_per_second": 5.37,
|
| 1415 |
+
"eval_steps_per_second": 0.448,
|
| 1416 |
+
"step": 44000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.2,
|
| 1420 |
+
"learning_rate": 3.898732924173431e-05,
|
| 1421 |
+
"loss": 0.594,
|
| 1422 |
+
"step": 44500
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 2.2,
|
| 1426 |
+
"eval_bleu": 45.3986,
|
| 1427 |
+
"eval_gen_len": 16.6814,
|
| 1428 |
+
"eval_loss": 0.9292554259300232,
|
| 1429 |
+
"eval_runtime": 1334.5426,
|
| 1430 |
+
"eval_samples_per_second": 5.352,
|
| 1431 |
+
"eval_steps_per_second": 0.447,
|
| 1432 |
+
"step": 44500
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.23,
|
| 1436 |
+
"learning_rate": 3.886359136804593e-05,
|
| 1437 |
+
"loss": 0.5983,
|
| 1438 |
+
"step": 45000
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.23,
|
| 1442 |
+
"eval_bleu": 45.6357,
|
| 1443 |
+
"eval_gen_len": 16.617,
|
| 1444 |
+
"eval_loss": 0.920947253704071,
|
| 1445 |
+
"eval_runtime": 1332.827,
|
| 1446 |
+
"eval_samples_per_second": 5.359,
|
| 1447 |
+
"eval_steps_per_second": 0.447,
|
| 1448 |
+
"step": 45000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 2.25,
|
| 1452 |
+
"learning_rate": 3.8739853494357555e-05,
|
| 1453 |
+
"loss": 0.6063,
|
| 1454 |
+
"step": 45500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 2.25,
|
| 1458 |
+
"eval_bleu": 45.8697,
|
| 1459 |
+
"eval_gen_len": 16.7532,
|
| 1460 |
+
"eval_loss": 0.9304359555244446,
|
| 1461 |
+
"eval_runtime": 1340.1007,
|
| 1462 |
+
"eval_samples_per_second": 5.33,
|
| 1463 |
+
"eval_steps_per_second": 0.445,
|
| 1464 |
+
"step": 45500
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.28,
|
| 1468 |
+
"learning_rate": 3.861611562066917e-05,
|
| 1469 |
+
"loss": 0.6004,
|
| 1470 |
+
"step": 46000
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.28,
|
| 1474 |
+
"eval_bleu": 45.8707,
|
| 1475 |
+
"eval_gen_len": 16.6399,
|
| 1476 |
+
"eval_loss": 0.9174883961677551,
|
| 1477 |
+
"eval_runtime": 1333.508,
|
| 1478 |
+
"eval_samples_per_second": 5.357,
|
| 1479 |
+
"eval_steps_per_second": 0.447,
|
| 1480 |
+
"step": 46000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.3,
|
| 1484 |
+
"learning_rate": 3.8492377746980794e-05,
|
| 1485 |
+
"loss": 0.5951,
|
| 1486 |
+
"step": 46500
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.3,
|
| 1490 |
+
"eval_bleu": 45.0087,
|
| 1491 |
+
"eval_gen_len": 16.5349,
|
| 1492 |
+
"eval_loss": 0.9316369295120239,
|
| 1493 |
+
"eval_runtime": 1331.8005,
|
| 1494 |
+
"eval_samples_per_second": 5.363,
|
| 1495 |
+
"eval_steps_per_second": 0.448,
|
| 1496 |
+
"step": 46500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 2.33,
|
| 1500 |
+
"learning_rate": 3.8368639873292416e-05,
|
| 1501 |
+
"loss": 0.5908,
|
| 1502 |
+
"step": 47000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.33,
|
| 1506 |
+
"eval_bleu": 45.485,
|
| 1507 |
+
"eval_gen_len": 16.5745,
|
| 1508 |
+
"eval_loss": 0.9216477870941162,
|
| 1509 |
+
"eval_runtime": 1328.0985,
|
| 1510 |
+
"eval_samples_per_second": 5.378,
|
| 1511 |
+
"eval_steps_per_second": 0.449,
|
| 1512 |
+
"step": 47000
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.35,
|
| 1516 |
+
"learning_rate": 3.824490199960404e-05,
|
| 1517 |
+
"loss": 0.5847,
|
| 1518 |
+
"step": 47500
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 2.35,
|
| 1522 |
+
"eval_bleu": 45.9099,
|
| 1523 |
+
"eval_gen_len": 16.6137,
|
| 1524 |
+
"eval_loss": 0.9153968691825867,
|
| 1525 |
+
"eval_runtime": 1331.7962,
|
| 1526 |
+
"eval_samples_per_second": 5.363,
|
| 1527 |
+
"eval_steps_per_second": 0.448,
|
| 1528 |
+
"step": 47500
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.38,
|
| 1532 |
+
"learning_rate": 3.812116412591566e-05,
|
| 1533 |
+
"loss": 0.5897,
|
| 1534 |
+
"step": 48000
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 2.38,
|
| 1538 |
+
"eval_bleu": 46.0344,
|
| 1539 |
+
"eval_gen_len": 16.5282,
|
| 1540 |
+
"eval_loss": 0.9067392945289612,
|
| 1541 |
+
"eval_runtime": 1320.4869,
|
| 1542 |
+
"eval_samples_per_second": 5.409,
|
| 1543 |
+
"eval_steps_per_second": 0.451,
|
| 1544 |
+
"step": 48000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.4,
|
| 1548 |
+
"learning_rate": 3.799742625222728e-05,
|
| 1549 |
+
"loss": 0.5951,
|
| 1550 |
+
"step": 48500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.4,
|
| 1554 |
+
"eval_bleu": 45.9988,
|
| 1555 |
+
"eval_gen_len": 16.6501,
|
| 1556 |
+
"eval_loss": 0.9071055054664612,
|
| 1557 |
+
"eval_runtime": 1333.3527,
|
| 1558 |
+
"eval_samples_per_second": 5.357,
|
| 1559 |
+
"eval_steps_per_second": 0.447,
|
| 1560 |
+
"step": 48500
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.43,
|
| 1564 |
+
"learning_rate": 3.7873688378538906e-05,
|
| 1565 |
+
"loss": 0.5781,
|
| 1566 |
+
"step": 49000
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.43,
|
| 1570 |
+
"eval_bleu": 46.0018,
|
| 1571 |
+
"eval_gen_len": 16.7336,
|
| 1572 |
+
"eval_loss": 0.9073439240455627,
|
| 1573 |
+
"eval_runtime": 1334.0382,
|
| 1574 |
+
"eval_samples_per_second": 5.354,
|
| 1575 |
+
"eval_steps_per_second": 0.447,
|
| 1576 |
+
"step": 49000
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 2.45,
|
| 1580 |
+
"learning_rate": 3.774995050485053e-05,
|
| 1581 |
+
"loss": 0.5934,
|
| 1582 |
+
"step": 49500
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 2.45,
|
| 1586 |
+
"eval_bleu": 46.5706,
|
| 1587 |
+
"eval_gen_len": 16.8471,
|
| 1588 |
+
"eval_loss": 0.9027701616287231,
|
| 1589 |
+
"eval_runtime": 1336.5927,
|
| 1590 |
+
"eval_samples_per_second": 5.344,
|
| 1591 |
+
"eval_steps_per_second": 0.446,
|
| 1592 |
+
"step": 49500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.47,
|
| 1596 |
+
"learning_rate": 3.762621263116215e-05,
|
| 1597 |
+
"loss": 0.5883,
|
| 1598 |
+
"step": 50000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.47,
|
| 1602 |
+
"eval_bleu": 46.6303,
|
| 1603 |
+
"eval_gen_len": 16.8614,
|
| 1604 |
+
"eval_loss": 0.9047964215278625,
|
| 1605 |
+
"eval_runtime": 1340.8517,
|
| 1606 |
+
"eval_samples_per_second": 5.327,
|
| 1607 |
+
"eval_steps_per_second": 0.444,
|
| 1608 |
+
"step": 50000
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.5,
|
| 1612 |
+
"learning_rate": 3.750247475747377e-05,
|
| 1613 |
+
"loss": 0.5964,
|
| 1614 |
+
"step": 50500
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.5,
|
| 1618 |
+
"eval_bleu": 46.087,
|
| 1619 |
+
"eval_gen_len": 16.6417,
|
| 1620 |
+
"eval_loss": 0.8980411887168884,
|
| 1621 |
+
"eval_runtime": 1332.5501,
|
| 1622 |
+
"eval_samples_per_second": 5.36,
|
| 1623 |
+
"eval_steps_per_second": 0.447,
|
| 1624 |
+
"step": 50500
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 2.52,
|
| 1628 |
+
"learning_rate": 3.7378736883785395e-05,
|
| 1629 |
+
"loss": 0.5924,
|
| 1630 |
+
"step": 51000
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 2.52,
|
| 1634 |
+
"eval_bleu": 47.0224,
|
| 1635 |
+
"eval_gen_len": 16.6821,
|
| 1636 |
+
"eval_loss": 0.9017878770828247,
|
| 1637 |
+
"eval_runtime": 1333.0812,
|
| 1638 |
+
"eval_samples_per_second": 5.358,
|
| 1639 |
+
"eval_steps_per_second": 0.447,
|
| 1640 |
+
"step": 51000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.55,
|
| 1644 |
+
"learning_rate": 3.725499901009701e-05,
|
| 1645 |
+
"loss": 0.5866,
|
| 1646 |
+
"step": 51500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 2.55,
|
| 1650 |
+
"eval_bleu": 46.244,
|
| 1651 |
+
"eval_gen_len": 16.7493,
|
| 1652 |
+
"eval_loss": 0.8992940187454224,
|
| 1653 |
+
"eval_runtime": 1343.2842,
|
| 1654 |
+
"eval_samples_per_second": 5.318,
|
| 1655 |
+
"eval_steps_per_second": 0.444,
|
| 1656 |
+
"step": 51500
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.57,
|
| 1660 |
+
"learning_rate": 3.7131261136408633e-05,
|
| 1661 |
+
"loss": 0.5764,
|
| 1662 |
+
"step": 52000
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.57,
|
| 1666 |
+
"eval_bleu": 46.3888,
|
| 1667 |
+
"eval_gen_len": 16.6049,
|
| 1668 |
+
"eval_loss": 0.9019588828086853,
|
| 1669 |
+
"eval_runtime": 1338.9531,
|
| 1670 |
+
"eval_samples_per_second": 5.335,
|
| 1671 |
+
"eval_steps_per_second": 0.445,
|
| 1672 |
+
"step": 52000
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 2.6,
|
| 1676 |
+
"learning_rate": 3.7007523262720256e-05,
|
| 1677 |
+
"loss": 0.5865,
|
| 1678 |
+
"step": 52500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.6,
|
| 1682 |
+
"eval_bleu": 46.8308,
|
| 1683 |
+
"eval_gen_len": 16.7173,
|
| 1684 |
+
"eval_loss": 0.8952421545982361,
|
| 1685 |
+
"eval_runtime": 1352.2564,
|
| 1686 |
+
"eval_samples_per_second": 5.282,
|
| 1687 |
+
"eval_steps_per_second": 0.441,
|
| 1688 |
+
"step": 52500
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 2.62,
|
| 1692 |
+
"learning_rate": 3.688378538903188e-05,
|
| 1693 |
+
"loss": 0.6016,
|
| 1694 |
+
"step": 53000
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 2.62,
|
| 1698 |
+
"eval_bleu": 47.0928,
|
| 1699 |
+
"eval_gen_len": 16.7008,
|
| 1700 |
+
"eval_loss": 0.8945097923278809,
|
| 1701 |
+
"eval_runtime": 1354.2335,
|
| 1702 |
+
"eval_samples_per_second": 5.275,
|
| 1703 |
+
"eval_steps_per_second": 0.44,
|
| 1704 |
+
"step": 53000
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.65,
|
| 1708 |
+
"learning_rate": 3.67600475153435e-05,
|
| 1709 |
+
"loss": 0.5902,
|
| 1710 |
+
"step": 53500
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.65,
|
| 1714 |
+
"eval_bleu": 46.6548,
|
| 1715 |
+
"eval_gen_len": 16.7439,
|
| 1716 |
+
"eval_loss": 0.8932007551193237,
|
| 1717 |
+
"eval_runtime": 1382.9624,
|
| 1718 |
+
"eval_samples_per_second": 5.165,
|
| 1719 |
+
"eval_steps_per_second": 0.431,
|
| 1720 |
+
"step": 53500
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.67,
|
| 1724 |
+
"learning_rate": 3.663630964165512e-05,
|
| 1725 |
+
"loss": 0.587,
|
| 1726 |
+
"step": 54000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.67,
|
| 1730 |
+
"eval_bleu": 46.9113,
|
| 1731 |
+
"eval_gen_len": 16.6783,
|
| 1732 |
+
"eval_loss": 0.8879196047782898,
|
| 1733 |
+
"eval_runtime": 1386.1138,
|
| 1734 |
+
"eval_samples_per_second": 5.153,
|
| 1735 |
+
"eval_steps_per_second": 0.43,
|
| 1736 |
+
"step": 54000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.7,
|
| 1740 |
+
"learning_rate": 3.651257176796674e-05,
|
| 1741 |
+
"loss": 0.5968,
|
| 1742 |
+
"step": 54500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 2.7,
|
| 1746 |
+
"eval_bleu": 47.0957,
|
| 1747 |
+
"eval_gen_len": 16.5933,
|
| 1748 |
+
"eval_loss": 0.8864062428474426,
|
| 1749 |
+
"eval_runtime": 1383.0254,
|
| 1750 |
+
"eval_samples_per_second": 5.165,
|
| 1751 |
+
"eval_steps_per_second": 0.431,
|
| 1752 |
+
"step": 54500
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.72,
|
| 1756 |
+
"learning_rate": 3.638883389427836e-05,
|
| 1757 |
+
"loss": 0.5853,
|
| 1758 |
+
"step": 55000
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 2.72,
|
| 1762 |
+
"eval_bleu": 47.1709,
|
| 1763 |
+
"eval_gen_len": 16.6479,
|
| 1764 |
+
"eval_loss": 0.8836300373077393,
|
| 1765 |
+
"eval_runtime": 1390.1185,
|
| 1766 |
+
"eval_samples_per_second": 5.138,
|
| 1767 |
+
"eval_steps_per_second": 0.429,
|
| 1768 |
+
"step": 55000
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.75,
|
| 1772 |
+
"learning_rate": 3.6265096020589984e-05,
|
| 1773 |
+
"loss": 0.5943,
|
| 1774 |
+
"step": 55500
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.75,
|
| 1778 |
+
"eval_bleu": 47.184,
|
| 1779 |
+
"eval_gen_len": 16.6594,
|
| 1780 |
+
"eval_loss": 0.8828004598617554,
|
| 1781 |
+
"eval_runtime": 1374.4327,
|
| 1782 |
+
"eval_samples_per_second": 5.197,
|
| 1783 |
+
"eval_steps_per_second": 0.434,
|
| 1784 |
+
"step": 55500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 2.77,
|
| 1788 |
+
"learning_rate": 3.6141358146901606e-05,
|
| 1789 |
+
"loss": 0.5891,
|
| 1790 |
+
"step": 56000
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.77,
|
| 1794 |
+
"eval_bleu": 46.7804,
|
| 1795 |
+
"eval_gen_len": 16.7312,
|
| 1796 |
+
"eval_loss": 0.8724841475486755,
|
| 1797 |
+
"eval_runtime": 1340.042,
|
| 1798 |
+
"eval_samples_per_second": 5.33,
|
| 1799 |
+
"eval_steps_per_second": 0.445,
|
| 1800 |
+
"step": 56000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 2.8,
|
| 1804 |
+
"learning_rate": 3.601762027321323e-05,
|
| 1805 |
+
"loss": 0.585,
|
| 1806 |
+
"step": 56500
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 2.8,
|
| 1810 |
+
"eval_bleu": 46.8152,
|
| 1811 |
+
"eval_gen_len": 16.6263,
|
| 1812 |
+
"eval_loss": 0.8797315955162048,
|
| 1813 |
+
"eval_runtime": 1333.5752,
|
| 1814 |
+
"eval_samples_per_second": 5.356,
|
| 1815 |
+
"eval_steps_per_second": 0.447,
|
| 1816 |
+
"step": 56500
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.82,
|
| 1820 |
+
"learning_rate": 3.5893882399524844e-05,
|
| 1821 |
+
"loss": 0.5889,
|
| 1822 |
+
"step": 57000
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.82,
|
| 1826 |
+
"eval_bleu": 47.3674,
|
| 1827 |
+
"eval_gen_len": 16.7459,
|
| 1828 |
+
"eval_loss": 0.8741356134414673,
|
| 1829 |
+
"eval_runtime": 1336.3135,
|
| 1830 |
+
"eval_samples_per_second": 5.345,
|
| 1831 |
+
"eval_steps_per_second": 0.446,
|
| 1832 |
+
"step": 57000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.85,
|
| 1836 |
+
"learning_rate": 3.577014452583647e-05,
|
| 1837 |
+
"loss": 0.5841,
|
| 1838 |
+
"step": 57500
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.85,
|
| 1842 |
+
"eval_bleu": 46.9029,
|
| 1843 |
+
"eval_gen_len": 16.742,
|
| 1844 |
+
"eval_loss": 0.875153124332428,
|
| 1845 |
+
"eval_runtime": 1335.6996,
|
| 1846 |
+
"eval_samples_per_second": 5.348,
|
| 1847 |
+
"eval_steps_per_second": 0.446,
|
| 1848 |
+
"step": 57500
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 2.87,
|
| 1852 |
+
"learning_rate": 3.564640665214809e-05,
|
| 1853 |
+
"loss": 0.5786,
|
| 1854 |
+
"step": 58000
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 2.87,
|
| 1858 |
+
"eval_bleu": 47.4711,
|
| 1859 |
+
"eval_gen_len": 16.6132,
|
| 1860 |
+
"eval_loss": 0.8668653964996338,
|
| 1861 |
+
"eval_runtime": 1333.4019,
|
| 1862 |
+
"eval_samples_per_second": 5.357,
|
| 1863 |
+
"eval_steps_per_second": 0.447,
|
| 1864 |
+
"step": 58000
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.9,
|
| 1868 |
+
"learning_rate": 3.552266877845971e-05,
|
| 1869 |
+
"loss": 0.5784,
|
| 1870 |
+
"step": 58500
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 2.9,
|
| 1874 |
+
"eval_bleu": 47.3049,
|
| 1875 |
+
"eval_gen_len": 16.6745,
|
| 1876 |
+
"eval_loss": 0.8657991290092468,
|
| 1877 |
+
"eval_runtime": 1339.6294,
|
| 1878 |
+
"eval_samples_per_second": 5.332,
|
| 1879 |
+
"eval_steps_per_second": 0.445,
|
| 1880 |
+
"step": 58500
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.92,
|
| 1884 |
+
"learning_rate": 3.5398930904771334e-05,
|
| 1885 |
+
"loss": 0.5807,
|
| 1886 |
+
"step": 59000
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.92,
|
| 1890 |
+
"eval_bleu": 47.2634,
|
| 1891 |
+
"eval_gen_len": 16.6962,
|
| 1892 |
+
"eval_loss": 0.8614685535430908,
|
| 1893 |
+
"eval_runtime": 1334.3541,
|
| 1894 |
+
"eval_samples_per_second": 5.353,
|
| 1895 |
+
"eval_steps_per_second": 0.447,
|
| 1896 |
+
"step": 59000
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 2.94,
|
| 1900 |
+
"learning_rate": 3.5275193031082956e-05,
|
| 1901 |
+
"loss": 0.5856,
|
| 1902 |
+
"step": 59500
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.94,
|
| 1906 |
+
"eval_bleu": 47.8743,
|
| 1907 |
+
"eval_gen_len": 16.7721,
|
| 1908 |
+
"eval_loss": 0.8591042757034302,
|
| 1909 |
+
"eval_runtime": 1335.7672,
|
| 1910 |
+
"eval_samples_per_second": 5.347,
|
| 1911 |
+
"eval_steps_per_second": 0.446,
|
| 1912 |
+
"step": 59500
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 2.97,
|
| 1916 |
+
"learning_rate": 3.515145515739457e-05,
|
| 1917 |
+
"loss": 0.58,
|
| 1918 |
+
"step": 60000
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 2.97,
|
| 1922 |
+
"eval_bleu": 47.6119,
|
| 1923 |
+
"eval_gen_len": 16.6251,
|
| 1924 |
+
"eval_loss": 0.8595740795135498,
|
| 1925 |
+
"eval_runtime": 1332.2154,
|
| 1926 |
+
"eval_samples_per_second": 5.362,
|
| 1927 |
+
"eval_steps_per_second": 0.447,
|
| 1928 |
+
"step": 60000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.99,
|
| 1932 |
+
"learning_rate": 3.5027717283706194e-05,
|
| 1933 |
+
"loss": 0.5802,
|
| 1934 |
+
"step": 60500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.99,
|
| 1938 |
+
"eval_bleu": 47.703,
|
| 1939 |
+
"eval_gen_len": 16.6114,
|
| 1940 |
+
"eval_loss": 0.8570582270622253,
|
| 1941 |
+
"eval_runtime": 1325.8364,
|
| 1942 |
+
"eval_samples_per_second": 5.388,
|
| 1943 |
+
"eval_steps_per_second": 0.45,
|
| 1944 |
+
"step": 60500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.02,
|
| 1948 |
+
"learning_rate": 3.490397941001782e-05,
|
| 1949 |
+
"loss": 0.4491,
|
| 1950 |
+
"step": 61000
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 3.02,
|
| 1954 |
+
"eval_bleu": 47.8822,
|
| 1955 |
+
"eval_gen_len": 16.732,
|
| 1956 |
+
"eval_loss": 0.859774649143219,
|
| 1957 |
+
"eval_runtime": 1336.5318,
|
| 1958 |
+
"eval_samples_per_second": 5.344,
|
| 1959 |
+
"eval_steps_per_second": 0.446,
|
| 1960 |
+
"step": 61000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 3.04,
|
| 1964 |
+
"learning_rate": 3.478024153632944e-05,
|
| 1965 |
+
"loss": 0.4305,
|
| 1966 |
+
"step": 61500
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 3.04,
|
| 1970 |
+
"eval_bleu": 47.6096,
|
| 1971 |
+
"eval_gen_len": 16.5932,
|
| 1972 |
+
"eval_loss": 0.8659536242485046,
|
| 1973 |
+
"eval_runtime": 1328.147,
|
| 1974 |
+
"eval_samples_per_second": 5.378,
|
| 1975 |
+
"eval_steps_per_second": 0.449,
|
| 1976 |
+
"step": 61500
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.07,
|
| 1980 |
+
"learning_rate": 3.465650366264107e-05,
|
| 1981 |
+
"loss": 0.4268,
|
| 1982 |
+
"step": 62000
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 3.07,
|
| 1986 |
+
"eval_bleu": 48.0044,
|
| 1987 |
+
"eval_gen_len": 16.7596,
|
| 1988 |
+
"eval_loss": 0.8622444868087769,
|
| 1989 |
+
"eval_runtime": 1332.1214,
|
| 1990 |
+
"eval_samples_per_second": 5.362,
|
| 1991 |
+
"eval_steps_per_second": 0.447,
|
| 1992 |
+
"step": 62000
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 3.09,
|
| 1996 |
+
"learning_rate": 3.4532765788952684e-05,
|
| 1997 |
+
"loss": 0.4274,
|
| 1998 |
+
"step": 62500
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 3.09,
|
| 2002 |
+
"eval_bleu": 47.8272,
|
| 2003 |
+
"eval_gen_len": 16.6352,
|
| 2004 |
+
"eval_loss": 0.8669659495353699,
|
| 2005 |
+
"eval_runtime": 1330.5387,
|
| 2006 |
+
"eval_samples_per_second": 5.369,
|
| 2007 |
+
"eval_steps_per_second": 0.448,
|
| 2008 |
+
"step": 62500
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.12,
|
| 2012 |
+
"learning_rate": 3.4409027915264307e-05,
|
| 2013 |
+
"loss": 0.4383,
|
| 2014 |
+
"step": 63000
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 3.12,
|
| 2018 |
+
"eval_bleu": 47.8411,
|
| 2019 |
+
"eval_gen_len": 16.6331,
|
| 2020 |
+
"eval_loss": 0.8617204427719116,
|
| 2021 |
+
"eval_runtime": 1339.6282,
|
| 2022 |
+
"eval_samples_per_second": 5.332,
|
| 2023 |
+
"eval_steps_per_second": 0.445,
|
| 2024 |
+
"step": 63000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 3.14,
|
| 2028 |
+
"learning_rate": 3.428529004157593e-05,
|
| 2029 |
+
"loss": 0.4339,
|
| 2030 |
+
"step": 63500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.14,
|
| 2034 |
+
"eval_bleu": 48.232,
|
| 2035 |
+
"eval_gen_len": 16.839,
|
| 2036 |
+
"eval_loss": 0.8655442595481873,
|
| 2037 |
+
"eval_runtime": 1339.0945,
|
| 2038 |
+
"eval_samples_per_second": 5.334,
|
| 2039 |
+
"eval_steps_per_second": 0.445,
|
| 2040 |
+
"step": 63500
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 3.17,
|
| 2044 |
+
"learning_rate": 3.416155216788755e-05,
|
| 2045 |
+
"loss": 0.4361,
|
| 2046 |
+
"step": 64000
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.17,
|
| 2050 |
+
"eval_bleu": 47.978,
|
| 2051 |
+
"eval_gen_len": 16.7057,
|
| 2052 |
+
"eval_loss": 0.8637909889221191,
|
| 2053 |
+
"eval_runtime": 1337.5265,
|
| 2054 |
+
"eval_samples_per_second": 5.34,
|
| 2055 |
+
"eval_steps_per_second": 0.446,
|
| 2056 |
+
"step": 64000
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 3.19,
|
| 2060 |
+
"learning_rate": 3.4037814294199174e-05,
|
| 2061 |
+
"loss": 0.4373,
|
| 2062 |
+
"step": 64500
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 3.19,
|
| 2066 |
+
"eval_bleu": 48.0663,
|
| 2067 |
+
"eval_gen_len": 16.652,
|
| 2068 |
+
"eval_loss": 0.8616685271263123,
|
| 2069 |
+
"eval_runtime": 1344.0854,
|
| 2070 |
+
"eval_samples_per_second": 5.314,
|
| 2071 |
+
"eval_steps_per_second": 0.443,
|
| 2072 |
+
"step": 64500
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 3.22,
|
| 2076 |
+
"learning_rate": 3.3914076420510796e-05,
|
| 2077 |
+
"loss": 0.43,
|
| 2078 |
+
"step": 65000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 3.22,
|
| 2082 |
+
"eval_bleu": 47.8077,
|
| 2083 |
+
"eval_gen_len": 16.7621,
|
| 2084 |
+
"eval_loss": 0.8689031004905701,
|
| 2085 |
+
"eval_runtime": 1338.3656,
|
| 2086 |
+
"eval_samples_per_second": 5.337,
|
| 2087 |
+
"eval_steps_per_second": 0.445,
|
| 2088 |
+
"step": 65000
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 3.24,
|
| 2092 |
+
"learning_rate": 3.379033854682241e-05,
|
| 2093 |
+
"loss": 0.4325,
|
| 2094 |
+
"step": 65500
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 3.24,
|
| 2098 |
+
"eval_bleu": 47.9434,
|
| 2099 |
+
"eval_gen_len": 16.6489,
|
| 2100 |
+
"eval_loss": 0.870697021484375,
|
| 2101 |
+
"eval_runtime": 1329.6325,
|
| 2102 |
+
"eval_samples_per_second": 5.372,
|
| 2103 |
+
"eval_steps_per_second": 0.448,
|
| 2104 |
+
"step": 65500
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 3.27,
|
| 2108 |
+
"learning_rate": 3.3666600673134034e-05,
|
| 2109 |
+
"loss": 0.4409,
|
| 2110 |
+
"step": 66000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 3.27,
|
| 2114 |
+
"eval_bleu": 48.2346,
|
| 2115 |
+
"eval_gen_len": 16.6951,
|
| 2116 |
+
"eval_loss": 0.871823787689209,
|
| 2117 |
+
"eval_runtime": 1334.2329,
|
| 2118 |
+
"eval_samples_per_second": 5.354,
|
| 2119 |
+
"eval_steps_per_second": 0.447,
|
| 2120 |
+
"step": 66000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 3.29,
|
| 2124 |
+
"learning_rate": 3.354286279944566e-05,
|
| 2125 |
+
"loss": 0.4407,
|
| 2126 |
+
"step": 66500
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 3.29,
|
| 2130 |
+
"eval_bleu": 48.0356,
|
| 2131 |
+
"eval_gen_len": 16.7549,
|
| 2132 |
+
"eval_loss": 0.8691708445549011,
|
| 2133 |
+
"eval_runtime": 1345.0681,
|
| 2134 |
+
"eval_samples_per_second": 5.311,
|
| 2135 |
+
"eval_steps_per_second": 0.443,
|
| 2136 |
+
"step": 66500
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 3.32,
|
| 2140 |
+
"learning_rate": 3.341912492575728e-05,
|
| 2141 |
+
"loss": 0.444,
|
| 2142 |
+
"step": 67000
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 3.32,
|
| 2146 |
+
"eval_bleu": 48.295,
|
| 2147 |
+
"eval_gen_len": 16.6175,
|
| 2148 |
+
"eval_loss": 0.8652631044387817,
|
| 2149 |
+
"eval_runtime": 1333.9567,
|
| 2150 |
+
"eval_samples_per_second": 5.355,
|
| 2151 |
+
"eval_steps_per_second": 0.447,
|
| 2152 |
+
"step": 67000
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 3.34,
|
| 2156 |
+
"learning_rate": 3.32953870520689e-05,
|
| 2157 |
+
"loss": 0.4403,
|
| 2158 |
+
"step": 67500
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 3.34,
|
| 2162 |
+
"eval_bleu": 48.9108,
|
| 2163 |
+
"eval_gen_len": 16.7733,
|
| 2164 |
+
"eval_loss": 0.8616347312927246,
|
| 2165 |
+
"eval_runtime": 1343.5713,
|
| 2166 |
+
"eval_samples_per_second": 5.316,
|
| 2167 |
+
"eval_steps_per_second": 0.444,
|
| 2168 |
+
"step": 67500
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 3.37,
|
| 2172 |
+
"learning_rate": 3.317164917838052e-05,
|
| 2173 |
+
"loss": 0.4383,
|
| 2174 |
+
"step": 68000
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 3.37,
|
| 2178 |
+
"eval_bleu": 48.7693,
|
| 2179 |
+
"eval_gen_len": 16.8501,
|
| 2180 |
+
"eval_loss": 0.8552740812301636,
|
| 2181 |
+
"eval_runtime": 1342.1211,
|
| 2182 |
+
"eval_samples_per_second": 5.322,
|
| 2183 |
+
"eval_steps_per_second": 0.444,
|
| 2184 |
+
"step": 68000
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 3.39,
|
| 2188 |
+
"learning_rate": 3.304791130469214e-05,
|
| 2189 |
+
"loss": 0.4354,
|
| 2190 |
+
"step": 68500
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 3.39,
|
| 2194 |
+
"eval_bleu": 48.6325,
|
| 2195 |
+
"eval_gen_len": 16.7572,
|
| 2196 |
+
"eval_loss": 0.8553012013435364,
|
| 2197 |
+
"eval_runtime": 1337.7018,
|
| 2198 |
+
"eval_samples_per_second": 5.34,
|
| 2199 |
+
"eval_steps_per_second": 0.446,
|
| 2200 |
+
"step": 68500
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.42,
|
| 2204 |
+
"learning_rate": 3.292417343100376e-05,
|
| 2205 |
+
"loss": 0.4316,
|
| 2206 |
+
"step": 69000
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 3.42,
|
| 2210 |
+
"eval_bleu": 48.7044,
|
| 2211 |
+
"eval_gen_len": 16.7796,
|
| 2212 |
+
"eval_loss": 0.8564686179161072,
|
| 2213 |
+
"eval_runtime": 1336.7625,
|
| 2214 |
+
"eval_samples_per_second": 5.344,
|
| 2215 |
+
"eval_steps_per_second": 0.446,
|
| 2216 |
+
"step": 69000
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 3.44,
|
| 2220 |
+
"learning_rate": 3.2800435557315385e-05,
|
| 2221 |
+
"loss": 0.4465,
|
| 2222 |
+
"step": 69500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 3.44,
|
| 2226 |
+
"eval_bleu": 48.5715,
|
| 2227 |
+
"eval_gen_len": 16.6865,
|
| 2228 |
+
"eval_loss": 0.8632897138595581,
|
| 2229 |
+
"eval_runtime": 1336.3648,
|
| 2230 |
+
"eval_samples_per_second": 5.345,
|
| 2231 |
+
"eval_steps_per_second": 0.446,
|
| 2232 |
+
"step": 69500
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 3.46,
|
| 2236 |
+
"learning_rate": 3.267669768362701e-05,
|
| 2237 |
+
"loss": 0.4412,
|
| 2238 |
+
"step": 70000
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 3.46,
|
| 2242 |
+
"eval_bleu": 48.18,
|
| 2243 |
+
"eval_gen_len": 16.6885,
|
| 2244 |
+
"eval_loss": 0.8553540706634521,
|
| 2245 |
+
"eval_runtime": 1331.2155,
|
| 2246 |
+
"eval_samples_per_second": 5.366,
|
| 2247 |
+
"eval_steps_per_second": 0.448,
|
| 2248 |
+
"step": 70000
|
| 2249 |
+
}
|
| 2250 |
+
],
|
| 2251 |
+
"max_steps": 202040,
|
| 2252 |
+
"num_train_epochs": 10,
|
| 2253 |
+
"total_flos": 2.2754599026819072e+17,
|
| 2254 |
+
"trial_name": null,
|
| 2255 |
+
"trial_params": null
|
| 2256 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57b2ff615770869b2f7b6b22df099380be5ae946c87967276db821c4008b1f7f
|
| 3 |
+
size 3503
|