Commit
·
8756167
1
Parent(s):
c082ca9
first commit
Browse files- config.json +28 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3526 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./roberta-base-model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LecbertForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.10.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:678e8d835b333d60c00ddd085c1ea770e5ca41a40e3f89756ca96e7bcadc4435
|
| 3 |
+
size 1007192453
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9de72cd063bd58ce1e0c08d72e55304a473dd512f1763c249970f343e7f91f
|
| 3 |
+
size 503624419
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c958a02037d863118133f9ac93d3b053a26b84fdb8dcae6ab0b959d755dbb103
|
| 3 |
+
size 14657
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ec12c3422314825afecf003e70891804959784f4bd08401921716fbb5632315
|
| 3 |
+
size 559
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3526 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 39.92356514024432,
|
| 5 |
+
"global_step": 585000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 8.7125,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 4.7856,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 3e-05,
|
| 25 |
+
"loss": 3.6782,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 4e-05,
|
| 31 |
+
"loss": 3.2033,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.34,
|
| 36 |
+
"learning_rate": 5e-05,
|
| 37 |
+
"loss": 3.0057,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 6e-05,
|
| 43 |
+
"loss": 2.8619,
|
| 44 |
+
"step": 6000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"learning_rate": 7e-05,
|
| 49 |
+
"loss": 2.7523,
|
| 50 |
+
"step": 7000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.55,
|
| 54 |
+
"learning_rate": 8e-05,
|
| 55 |
+
"loss": 2.6541,
|
| 56 |
+
"step": 8000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.61,
|
| 60 |
+
"learning_rate": 9e-05,
|
| 61 |
+
"loss": 2.6102,
|
| 62 |
+
"step": 9000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.68,
|
| 66 |
+
"learning_rate": 0.0001,
|
| 67 |
+
"loss": 2.5355,
|
| 68 |
+
"step": 10000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.75,
|
| 72 |
+
"learning_rate": 9.98989898989899e-05,
|
| 73 |
+
"loss": 2.465,
|
| 74 |
+
"step": 11000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.82,
|
| 78 |
+
"learning_rate": 9.97979797979798e-05,
|
| 79 |
+
"loss": 2.4072,
|
| 80 |
+
"step": 12000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.89,
|
| 84 |
+
"learning_rate": 9.96969696969697e-05,
|
| 85 |
+
"loss": 2.361,
|
| 86 |
+
"step": 13000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"learning_rate": 9.95959595959596e-05,
|
| 91 |
+
"loss": 2.3297,
|
| 92 |
+
"step": 14000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.02,
|
| 96 |
+
"learning_rate": 9.94949494949495e-05,
|
| 97 |
+
"loss": 2.3137,
|
| 98 |
+
"step": 15000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.09,
|
| 102 |
+
"learning_rate": 9.939393939393939e-05,
|
| 103 |
+
"loss": 2.2747,
|
| 104 |
+
"step": 16000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.16,
|
| 108 |
+
"learning_rate": 9.92929292929293e-05,
|
| 109 |
+
"loss": 2.2714,
|
| 110 |
+
"step": 17000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.23,
|
| 114 |
+
"learning_rate": 9.919191919191919e-05,
|
| 115 |
+
"loss": 2.2657,
|
| 116 |
+
"step": 18000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.3,
|
| 120 |
+
"learning_rate": 9.909090909090911e-05,
|
| 121 |
+
"loss": 2.2708,
|
| 122 |
+
"step": 19000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.36,
|
| 126 |
+
"learning_rate": 9.8989898989899e-05,
|
| 127 |
+
"loss": 2.2574,
|
| 128 |
+
"step": 20000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.43,
|
| 132 |
+
"learning_rate": 9.888888888888889e-05,
|
| 133 |
+
"loss": 2.246,
|
| 134 |
+
"step": 21000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.5,
|
| 138 |
+
"learning_rate": 9.87878787878788e-05,
|
| 139 |
+
"loss": 2.2485,
|
| 140 |
+
"step": 22000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.57,
|
| 144 |
+
"learning_rate": 9.868686868686869e-05,
|
| 145 |
+
"loss": 2.2516,
|
| 146 |
+
"step": 23000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.64,
|
| 150 |
+
"learning_rate": 9.85858585858586e-05,
|
| 151 |
+
"loss": 2.235,
|
| 152 |
+
"step": 24000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.71,
|
| 156 |
+
"learning_rate": 9.848484848484849e-05,
|
| 157 |
+
"loss": 2.2303,
|
| 158 |
+
"step": 25000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.77,
|
| 162 |
+
"learning_rate": 9.838383838383838e-05,
|
| 163 |
+
"loss": 2.2393,
|
| 164 |
+
"step": 26000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.84,
|
| 168 |
+
"learning_rate": 9.828282828282829e-05,
|
| 169 |
+
"loss": 2.2356,
|
| 170 |
+
"step": 27000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.91,
|
| 174 |
+
"learning_rate": 9.818181818181818e-05,
|
| 175 |
+
"loss": 2.2279,
|
| 176 |
+
"step": 28000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.98,
|
| 180 |
+
"learning_rate": 9.808080808080809e-05,
|
| 181 |
+
"loss": 2.2222,
|
| 182 |
+
"step": 29000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.05,
|
| 186 |
+
"learning_rate": 9.797979797979798e-05,
|
| 187 |
+
"loss": 2.2134,
|
| 188 |
+
"step": 30000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.12,
|
| 192 |
+
"learning_rate": 9.787878787878789e-05,
|
| 193 |
+
"loss": 2.2069,
|
| 194 |
+
"step": 31000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.18,
|
| 198 |
+
"learning_rate": 9.777777777777778e-05,
|
| 199 |
+
"loss": 2.2067,
|
| 200 |
+
"step": 32000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.25,
|
| 204 |
+
"learning_rate": 9.767676767676767e-05,
|
| 205 |
+
"loss": 2.1958,
|
| 206 |
+
"step": 33000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.32,
|
| 210 |
+
"learning_rate": 9.757575757575758e-05,
|
| 211 |
+
"loss": 2.1923,
|
| 212 |
+
"step": 34000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.39,
|
| 216 |
+
"learning_rate": 9.747474747474747e-05,
|
| 217 |
+
"loss": 2.2106,
|
| 218 |
+
"step": 35000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.46,
|
| 222 |
+
"learning_rate": 9.737373737373738e-05,
|
| 223 |
+
"loss": 2.2019,
|
| 224 |
+
"step": 36000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.53,
|
| 228 |
+
"learning_rate": 9.727272727272728e-05,
|
| 229 |
+
"loss": 2.1868,
|
| 230 |
+
"step": 37000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.59,
|
| 234 |
+
"learning_rate": 9.717171717171718e-05,
|
| 235 |
+
"loss": 2.1874,
|
| 236 |
+
"step": 38000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.66,
|
| 240 |
+
"learning_rate": 9.707070707070708e-05,
|
| 241 |
+
"loss": 2.1788,
|
| 242 |
+
"step": 39000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.73,
|
| 246 |
+
"learning_rate": 9.696969696969698e-05,
|
| 247 |
+
"loss": 2.1841,
|
| 248 |
+
"step": 40000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.8,
|
| 252 |
+
"learning_rate": 9.686868686868688e-05,
|
| 253 |
+
"loss": 2.191,
|
| 254 |
+
"step": 41000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.87,
|
| 258 |
+
"learning_rate": 9.676767676767677e-05,
|
| 259 |
+
"loss": 2.1849,
|
| 260 |
+
"step": 42000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.93,
|
| 264 |
+
"learning_rate": 9.666666666666667e-05,
|
| 265 |
+
"loss": 2.1881,
|
| 266 |
+
"step": 43000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.0,
|
| 270 |
+
"learning_rate": 9.656565656565657e-05,
|
| 271 |
+
"loss": 2.1755,
|
| 272 |
+
"step": 44000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.07,
|
| 276 |
+
"learning_rate": 9.646464646464647e-05,
|
| 277 |
+
"loss": 2.1639,
|
| 278 |
+
"step": 45000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.14,
|
| 282 |
+
"learning_rate": 9.636363636363637e-05,
|
| 283 |
+
"loss": 2.1548,
|
| 284 |
+
"step": 46000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.21,
|
| 288 |
+
"learning_rate": 9.626262626262627e-05,
|
| 289 |
+
"loss": 2.1594,
|
| 290 |
+
"step": 47000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.28,
|
| 294 |
+
"learning_rate": 9.616161616161616e-05,
|
| 295 |
+
"loss": 2.164,
|
| 296 |
+
"step": 48000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.34,
|
| 300 |
+
"learning_rate": 9.606060606060606e-05,
|
| 301 |
+
"loss": 2.1616,
|
| 302 |
+
"step": 49000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.41,
|
| 306 |
+
"learning_rate": 9.595959595959596e-05,
|
| 307 |
+
"loss": 2.151,
|
| 308 |
+
"step": 50000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.48,
|
| 312 |
+
"learning_rate": 9.585858585858586e-05,
|
| 313 |
+
"loss": 2.1597,
|
| 314 |
+
"step": 51000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.55,
|
| 318 |
+
"learning_rate": 9.575757575757576e-05,
|
| 319 |
+
"loss": 2.1545,
|
| 320 |
+
"step": 52000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.62,
|
| 324 |
+
"learning_rate": 9.565656565656566e-05,
|
| 325 |
+
"loss": 2.1496,
|
| 326 |
+
"step": 53000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.69,
|
| 330 |
+
"learning_rate": 9.555555555555557e-05,
|
| 331 |
+
"loss": 2.1531,
|
| 332 |
+
"step": 54000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.75,
|
| 336 |
+
"learning_rate": 9.545454545454546e-05,
|
| 337 |
+
"loss": 2.1487,
|
| 338 |
+
"step": 55000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.82,
|
| 342 |
+
"learning_rate": 9.535353535353537e-05,
|
| 343 |
+
"loss": 2.1546,
|
| 344 |
+
"step": 56000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.89,
|
| 348 |
+
"learning_rate": 9.525252525252526e-05,
|
| 349 |
+
"loss": 2.1565,
|
| 350 |
+
"step": 57000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.96,
|
| 354 |
+
"learning_rate": 9.515151515151515e-05,
|
| 355 |
+
"loss": 2.15,
|
| 356 |
+
"step": 58000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.03,
|
| 360 |
+
"learning_rate": 9.505050505050506e-05,
|
| 361 |
+
"loss": 2.1505,
|
| 362 |
+
"step": 59000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.09,
|
| 366 |
+
"learning_rate": 9.494949494949495e-05,
|
| 367 |
+
"loss": 2.1334,
|
| 368 |
+
"step": 60000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.16,
|
| 372 |
+
"learning_rate": 9.484848484848486e-05,
|
| 373 |
+
"loss": 2.1271,
|
| 374 |
+
"step": 61000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.23,
|
| 378 |
+
"learning_rate": 9.474747474747475e-05,
|
| 379 |
+
"loss": 2.1305,
|
| 380 |
+
"step": 62000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.3,
|
| 384 |
+
"learning_rate": 9.464646464646464e-05,
|
| 385 |
+
"loss": 2.1287,
|
| 386 |
+
"step": 63000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.37,
|
| 390 |
+
"learning_rate": 9.454545454545455e-05,
|
| 391 |
+
"loss": 2.1251,
|
| 392 |
+
"step": 64000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.44,
|
| 396 |
+
"learning_rate": 9.444444444444444e-05,
|
| 397 |
+
"loss": 2.1274,
|
| 398 |
+
"step": 65000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.5,
|
| 402 |
+
"learning_rate": 9.434343434343435e-05,
|
| 403 |
+
"loss": 2.1326,
|
| 404 |
+
"step": 66000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.57,
|
| 408 |
+
"learning_rate": 9.424242424242424e-05,
|
| 409 |
+
"loss": 2.1264,
|
| 410 |
+
"step": 67000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.64,
|
| 414 |
+
"learning_rate": 9.414141414141415e-05,
|
| 415 |
+
"loss": 2.1338,
|
| 416 |
+
"step": 68000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.71,
|
| 420 |
+
"learning_rate": 9.404040404040404e-05,
|
| 421 |
+
"loss": 2.1246,
|
| 422 |
+
"step": 69000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.78,
|
| 426 |
+
"learning_rate": 9.393939393939395e-05,
|
| 427 |
+
"loss": 2.1268,
|
| 428 |
+
"step": 70000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.85,
|
| 432 |
+
"learning_rate": 9.383838383838385e-05,
|
| 433 |
+
"loss": 2.1307,
|
| 434 |
+
"step": 71000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.91,
|
| 438 |
+
"learning_rate": 9.373737373737375e-05,
|
| 439 |
+
"loss": 2.1208,
|
| 440 |
+
"step": 72000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.98,
|
| 444 |
+
"learning_rate": 9.363636363636364e-05,
|
| 445 |
+
"loss": 2.1299,
|
| 446 |
+
"step": 73000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.05,
|
| 450 |
+
"learning_rate": 9.353535353535354e-05,
|
| 451 |
+
"loss": 2.12,
|
| 452 |
+
"step": 74000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.12,
|
| 456 |
+
"learning_rate": 9.343434343434344e-05,
|
| 457 |
+
"loss": 2.11,
|
| 458 |
+
"step": 75000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.19,
|
| 462 |
+
"learning_rate": 9.333333333333334e-05,
|
| 463 |
+
"loss": 2.1066,
|
| 464 |
+
"step": 76000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.25,
|
| 468 |
+
"learning_rate": 9.323232323232324e-05,
|
| 469 |
+
"loss": 2.1105,
|
| 470 |
+
"step": 77000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.32,
|
| 474 |
+
"learning_rate": 9.313131313131314e-05,
|
| 475 |
+
"loss": 2.1213,
|
| 476 |
+
"step": 78000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.39,
|
| 480 |
+
"learning_rate": 9.303030303030303e-05,
|
| 481 |
+
"loss": 2.1217,
|
| 482 |
+
"step": 79000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.46,
|
| 486 |
+
"learning_rate": 9.292929292929293e-05,
|
| 487 |
+
"loss": 2.1217,
|
| 488 |
+
"step": 80000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.53,
|
| 492 |
+
"learning_rate": 9.282828282828283e-05,
|
| 493 |
+
"loss": 2.1148,
|
| 494 |
+
"step": 81000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.6,
|
| 498 |
+
"learning_rate": 9.272727272727273e-05,
|
| 499 |
+
"loss": 2.1155,
|
| 500 |
+
"step": 82000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.66,
|
| 504 |
+
"learning_rate": 9.262626262626263e-05,
|
| 505 |
+
"loss": 2.1148,
|
| 506 |
+
"step": 83000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.73,
|
| 510 |
+
"learning_rate": 9.252525252525253e-05,
|
| 511 |
+
"loss": 2.122,
|
| 512 |
+
"step": 84000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.8,
|
| 516 |
+
"learning_rate": 9.242424242424242e-05,
|
| 517 |
+
"loss": 2.124,
|
| 518 |
+
"step": 85000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.87,
|
| 522 |
+
"learning_rate": 9.232323232323232e-05,
|
| 523 |
+
"loss": 2.1017,
|
| 524 |
+
"step": 86000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 5.94,
|
| 528 |
+
"learning_rate": 9.222222222222223e-05,
|
| 529 |
+
"loss": 2.109,
|
| 530 |
+
"step": 87000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.01,
|
| 534 |
+
"learning_rate": 9.212121212121214e-05,
|
| 535 |
+
"loss": 2.1146,
|
| 536 |
+
"step": 88000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.07,
|
| 540 |
+
"learning_rate": 9.202020202020203e-05,
|
| 541 |
+
"loss": 2.0845,
|
| 542 |
+
"step": 89000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.14,
|
| 546 |
+
"learning_rate": 9.191919191919192e-05,
|
| 547 |
+
"loss": 2.0992,
|
| 548 |
+
"step": 90000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.21,
|
| 552 |
+
"learning_rate": 9.181818181818183e-05,
|
| 553 |
+
"loss": 2.0965,
|
| 554 |
+
"step": 91000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.28,
|
| 558 |
+
"learning_rate": 9.171717171717172e-05,
|
| 559 |
+
"loss": 2.0959,
|
| 560 |
+
"step": 92000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.35,
|
| 564 |
+
"learning_rate": 9.161616161616163e-05,
|
| 565 |
+
"loss": 2.1125,
|
| 566 |
+
"step": 93000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 6.42,
|
| 570 |
+
"learning_rate": 9.151515151515152e-05,
|
| 571 |
+
"loss": 2.1012,
|
| 572 |
+
"step": 94000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 6.48,
|
| 576 |
+
"learning_rate": 9.141414141414141e-05,
|
| 577 |
+
"loss": 2.0981,
|
| 578 |
+
"step": 95000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.55,
|
| 582 |
+
"learning_rate": 9.131313131313132e-05,
|
| 583 |
+
"loss": 2.1021,
|
| 584 |
+
"step": 96000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.62,
|
| 588 |
+
"learning_rate": 9.121212121212121e-05,
|
| 589 |
+
"loss": 2.0956,
|
| 590 |
+
"step": 97000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.69,
|
| 594 |
+
"learning_rate": 9.111111111111112e-05,
|
| 595 |
+
"loss": 2.0971,
|
| 596 |
+
"step": 98000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.76,
|
| 600 |
+
"learning_rate": 9.101010101010101e-05,
|
| 601 |
+
"loss": 2.0998,
|
| 602 |
+
"step": 99000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.82,
|
| 606 |
+
"learning_rate": 9.090909090909092e-05,
|
| 607 |
+
"loss": 2.0961,
|
| 608 |
+
"step": 100000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.89,
|
| 612 |
+
"learning_rate": 9.080808080808081e-05,
|
| 613 |
+
"loss": 2.1015,
|
| 614 |
+
"step": 101000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 6.96,
|
| 618 |
+
"learning_rate": 9.07070707070707e-05,
|
| 619 |
+
"loss": 2.1087,
|
| 620 |
+
"step": 102000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.03,
|
| 624 |
+
"learning_rate": 9.060606060606061e-05,
|
| 625 |
+
"loss": 2.086,
|
| 626 |
+
"step": 103000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 7.1,
|
| 630 |
+
"learning_rate": 9.050505050505052e-05,
|
| 631 |
+
"loss": 2.0822,
|
| 632 |
+
"step": 104000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.17,
|
| 636 |
+
"learning_rate": 9.040404040404041e-05,
|
| 637 |
+
"loss": 2.0788,
|
| 638 |
+
"step": 105000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.23,
|
| 642 |
+
"learning_rate": 9.030303030303031e-05,
|
| 643 |
+
"loss": 2.0808,
|
| 644 |
+
"step": 106000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.3,
|
| 648 |
+
"learning_rate": 9.02020202020202e-05,
|
| 649 |
+
"loss": 2.0758,
|
| 650 |
+
"step": 107000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.37,
|
| 654 |
+
"learning_rate": 9.010101010101011e-05,
|
| 655 |
+
"loss": 2.0863,
|
| 656 |
+
"step": 108000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 7.44,
|
| 660 |
+
"learning_rate": 9e-05,
|
| 661 |
+
"loss": 2.0818,
|
| 662 |
+
"step": 109000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 7.51,
|
| 666 |
+
"learning_rate": 8.98989898989899e-05,
|
| 667 |
+
"loss": 2.081,
|
| 668 |
+
"step": 110000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.58,
|
| 672 |
+
"learning_rate": 8.97979797979798e-05,
|
| 673 |
+
"loss": 2.0777,
|
| 674 |
+
"step": 111000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.64,
|
| 678 |
+
"learning_rate": 8.96969696969697e-05,
|
| 679 |
+
"loss": 2.0833,
|
| 680 |
+
"step": 112000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.71,
|
| 684 |
+
"learning_rate": 8.95959595959596e-05,
|
| 685 |
+
"loss": 2.0804,
|
| 686 |
+
"step": 113000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 7.78,
|
| 690 |
+
"learning_rate": 8.94949494949495e-05,
|
| 691 |
+
"loss": 2.083,
|
| 692 |
+
"step": 114000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 7.85,
|
| 696 |
+
"learning_rate": 8.93939393939394e-05,
|
| 697 |
+
"loss": 2.0699,
|
| 698 |
+
"step": 115000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 7.92,
|
| 702 |
+
"learning_rate": 8.92929292929293e-05,
|
| 703 |
+
"loss": 2.078,
|
| 704 |
+
"step": 116000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 7.98,
|
| 708 |
+
"learning_rate": 8.919191919191919e-05,
|
| 709 |
+
"loss": 2.085,
|
| 710 |
+
"step": 117000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 8.05,
|
| 714 |
+
"learning_rate": 8.90909090909091e-05,
|
| 715 |
+
"loss": 2.0635,
|
| 716 |
+
"step": 118000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 8.12,
|
| 720 |
+
"learning_rate": 8.898989898989899e-05,
|
| 721 |
+
"loss": 2.0554,
|
| 722 |
+
"step": 119000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 8.19,
|
| 726 |
+
"learning_rate": 8.888888888888889e-05,
|
| 727 |
+
"loss": 2.0632,
|
| 728 |
+
"step": 120000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.26,
|
| 732 |
+
"learning_rate": 8.87878787878788e-05,
|
| 733 |
+
"loss": 2.0563,
|
| 734 |
+
"step": 121000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.33,
|
| 738 |
+
"learning_rate": 8.868686868686869e-05,
|
| 739 |
+
"loss": 2.0661,
|
| 740 |
+
"step": 122000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 8.39,
|
| 744 |
+
"learning_rate": 8.85858585858586e-05,
|
| 745 |
+
"loss": 2.0752,
|
| 746 |
+
"step": 123000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.46,
|
| 750 |
+
"learning_rate": 8.848484848484849e-05,
|
| 751 |
+
"loss": 2.0623,
|
| 752 |
+
"step": 124000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.53,
|
| 756 |
+
"learning_rate": 8.83838383838384e-05,
|
| 757 |
+
"loss": 2.0757,
|
| 758 |
+
"step": 125000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.6,
|
| 762 |
+
"learning_rate": 8.828282828282829e-05,
|
| 763 |
+
"loss": 2.0676,
|
| 764 |
+
"step": 126000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.67,
|
| 768 |
+
"learning_rate": 8.818181818181818e-05,
|
| 769 |
+
"loss": 2.0663,
|
| 770 |
+
"step": 127000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.74,
|
| 774 |
+
"learning_rate": 8.808080808080809e-05,
|
| 775 |
+
"loss": 2.0558,
|
| 776 |
+
"step": 128000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.8,
|
| 780 |
+
"learning_rate": 8.797979797979798e-05,
|
| 781 |
+
"loss": 2.0652,
|
| 782 |
+
"step": 129000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.87,
|
| 786 |
+
"learning_rate": 8.787878787878789e-05,
|
| 787 |
+
"loss": 2.0695,
|
| 788 |
+
"step": 130000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 8.94,
|
| 792 |
+
"learning_rate": 8.777777777777778e-05,
|
| 793 |
+
"loss": 2.0697,
|
| 794 |
+
"step": 131000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 9.01,
|
| 798 |
+
"learning_rate": 8.767676767676767e-05,
|
| 799 |
+
"loss": 2.0678,
|
| 800 |
+
"step": 132000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 9.08,
|
| 804 |
+
"learning_rate": 8.757575757575758e-05,
|
| 805 |
+
"loss": 2.0623,
|
| 806 |
+
"step": 133000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 9.14,
|
| 810 |
+
"learning_rate": 8.747474747474747e-05,
|
| 811 |
+
"loss": 2.0422,
|
| 812 |
+
"step": 134000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 9.21,
|
| 816 |
+
"learning_rate": 8.737373737373738e-05,
|
| 817 |
+
"loss": 2.0517,
|
| 818 |
+
"step": 135000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.28,
|
| 822 |
+
"learning_rate": 8.727272727272727e-05,
|
| 823 |
+
"loss": 2.049,
|
| 824 |
+
"step": 136000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.35,
|
| 828 |
+
"learning_rate": 8.717171717171718e-05,
|
| 829 |
+
"loss": 2.0583,
|
| 830 |
+
"step": 137000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 9.42,
|
| 834 |
+
"learning_rate": 8.707070707070707e-05,
|
| 835 |
+
"loss": 2.0535,
|
| 836 |
+
"step": 138000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 9.49,
|
| 840 |
+
"learning_rate": 8.696969696969698e-05,
|
| 841 |
+
"loss": 2.0547,
|
| 842 |
+
"step": 139000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 9.55,
|
| 846 |
+
"learning_rate": 8.686868686868688e-05,
|
| 847 |
+
"loss": 2.0537,
|
| 848 |
+
"step": 140000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.62,
|
| 852 |
+
"learning_rate": 8.676767676767678e-05,
|
| 853 |
+
"loss": 2.0546,
|
| 854 |
+
"step": 141000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 9.69,
|
| 858 |
+
"learning_rate": 8.666666666666667e-05,
|
| 859 |
+
"loss": 2.047,
|
| 860 |
+
"step": 142000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 9.76,
|
| 864 |
+
"learning_rate": 8.656565656565657e-05,
|
| 865 |
+
"loss": 2.0523,
|
| 866 |
+
"step": 143000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 9.83,
|
| 870 |
+
"learning_rate": 8.646464646464647e-05,
|
| 871 |
+
"loss": 2.0412,
|
| 872 |
+
"step": 144000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 9.9,
|
| 876 |
+
"learning_rate": 8.636363636363637e-05,
|
| 877 |
+
"loss": 2.0561,
|
| 878 |
+
"step": 145000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 9.96,
|
| 882 |
+
"learning_rate": 8.626262626262627e-05,
|
| 883 |
+
"loss": 2.0521,
|
| 884 |
+
"step": 146000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 10.03,
|
| 888 |
+
"learning_rate": 8.616161616161616e-05,
|
| 889 |
+
"loss": 2.0443,
|
| 890 |
+
"step": 147000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 10.1,
|
| 894 |
+
"learning_rate": 8.606060606060606e-05,
|
| 895 |
+
"loss": 2.0359,
|
| 896 |
+
"step": 148000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 10.17,
|
| 900 |
+
"learning_rate": 8.595959595959596e-05,
|
| 901 |
+
"loss": 2.0426,
|
| 902 |
+
"step": 149000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 10.24,
|
| 906 |
+
"learning_rate": 8.585858585858586e-05,
|
| 907 |
+
"loss": 2.032,
|
| 908 |
+
"step": 150000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 10.31,
|
| 912 |
+
"learning_rate": 8.575757575757576e-05,
|
| 913 |
+
"loss": 2.0389,
|
| 914 |
+
"step": 151000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 10.37,
|
| 918 |
+
"learning_rate": 8.565656565656566e-05,
|
| 919 |
+
"loss": 2.0431,
|
| 920 |
+
"step": 152000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 10.44,
|
| 924 |
+
"learning_rate": 8.555555555555556e-05,
|
| 925 |
+
"loss": 2.0374,
|
| 926 |
+
"step": 153000
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 10.51,
|
| 930 |
+
"learning_rate": 8.545454545454545e-05,
|
| 931 |
+
"loss": 2.0466,
|
| 932 |
+
"step": 154000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 10.58,
|
| 936 |
+
"learning_rate": 8.535353535353535e-05,
|
| 937 |
+
"loss": 2.0332,
|
| 938 |
+
"step": 155000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 10.65,
|
| 942 |
+
"learning_rate": 8.525252525252526e-05,
|
| 943 |
+
"loss": 2.0467,
|
| 944 |
+
"step": 156000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 10.71,
|
| 948 |
+
"learning_rate": 8.515151515151515e-05,
|
| 949 |
+
"loss": 2.0389,
|
| 950 |
+
"step": 157000
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 10.78,
|
| 954 |
+
"learning_rate": 8.505050505050506e-05,
|
| 955 |
+
"loss": 2.0432,
|
| 956 |
+
"step": 158000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 10.85,
|
| 960 |
+
"learning_rate": 8.494949494949495e-05,
|
| 961 |
+
"loss": 2.0386,
|
| 962 |
+
"step": 159000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 10.92,
|
| 966 |
+
"learning_rate": 8.484848484848486e-05,
|
| 967 |
+
"loss": 2.0393,
|
| 968 |
+
"step": 160000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 10.99,
|
| 972 |
+
"learning_rate": 8.474747474747475e-05,
|
| 973 |
+
"loss": 2.0373,
|
| 974 |
+
"step": 161000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 11.06,
|
| 978 |
+
"learning_rate": 8.464646464646466e-05,
|
| 979 |
+
"loss": 2.0287,
|
| 980 |
+
"step": 162000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 11.12,
|
| 984 |
+
"learning_rate": 8.454545454545455e-05,
|
| 985 |
+
"loss": 2.0278,
|
| 986 |
+
"step": 163000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 11.19,
|
| 990 |
+
"learning_rate": 8.444444444444444e-05,
|
| 991 |
+
"loss": 2.0278,
|
| 992 |
+
"step": 164000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 11.26,
|
| 996 |
+
"learning_rate": 8.434343434343435e-05,
|
| 997 |
+
"loss": 2.0263,
|
| 998 |
+
"step": 165000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 11.33,
|
| 1002 |
+
"learning_rate": 8.424242424242424e-05,
|
| 1003 |
+
"loss": 2.029,
|
| 1004 |
+
"step": 166000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 11.4,
|
| 1008 |
+
"learning_rate": 8.414141414141415e-05,
|
| 1009 |
+
"loss": 2.0313,
|
| 1010 |
+
"step": 167000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 11.47,
|
| 1014 |
+
"learning_rate": 8.404040404040404e-05,
|
| 1015 |
+
"loss": 2.0263,
|
| 1016 |
+
"step": 168000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 11.53,
|
| 1020 |
+
"learning_rate": 8.393939393939393e-05,
|
| 1021 |
+
"loss": 2.0403,
|
| 1022 |
+
"step": 169000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 11.6,
|
| 1026 |
+
"learning_rate": 8.383838383838384e-05,
|
| 1027 |
+
"loss": 2.0248,
|
| 1028 |
+
"step": 170000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 11.67,
|
| 1032 |
+
"learning_rate": 8.373737373737373e-05,
|
| 1033 |
+
"loss": 2.0308,
|
| 1034 |
+
"step": 171000
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 11.74,
|
| 1038 |
+
"learning_rate": 8.363636363636364e-05,
|
| 1039 |
+
"loss": 2.0331,
|
| 1040 |
+
"step": 172000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 11.81,
|
| 1044 |
+
"learning_rate": 8.353535353535355e-05,
|
| 1045 |
+
"loss": 2.0219,
|
| 1046 |
+
"step": 173000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 11.87,
|
| 1050 |
+
"learning_rate": 8.343434343434344e-05,
|
| 1051 |
+
"loss": 2.0305,
|
| 1052 |
+
"step": 174000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 11.94,
|
| 1056 |
+
"learning_rate": 8.333333333333334e-05,
|
| 1057 |
+
"loss": 2.0285,
|
| 1058 |
+
"step": 175000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 12.01,
|
| 1062 |
+
"learning_rate": 8.323232323232324e-05,
|
| 1063 |
+
"loss": 2.0276,
|
| 1064 |
+
"step": 176000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 12.08,
|
| 1068 |
+
"learning_rate": 8.313131313131314e-05,
|
| 1069 |
+
"loss": 2.0082,
|
| 1070 |
+
"step": 177000
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 12.15,
|
| 1074 |
+
"learning_rate": 8.303030303030304e-05,
|
| 1075 |
+
"loss": 2.0207,
|
| 1076 |
+
"step": 178000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 12.22,
|
| 1080 |
+
"learning_rate": 8.292929292929293e-05,
|
| 1081 |
+
"loss": 2.0116,
|
| 1082 |
+
"step": 179000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 12.28,
|
| 1086 |
+
"learning_rate": 8.282828282828283e-05,
|
| 1087 |
+
"loss": 2.017,
|
| 1088 |
+
"step": 180000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 12.35,
|
| 1092 |
+
"learning_rate": 8.272727272727273e-05,
|
| 1093 |
+
"loss": 2.0176,
|
| 1094 |
+
"step": 181000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 12.42,
|
| 1098 |
+
"learning_rate": 8.262626262626263e-05,
|
| 1099 |
+
"loss": 2.0143,
|
| 1100 |
+
"step": 182000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 12.49,
|
| 1104 |
+
"learning_rate": 8.252525252525253e-05,
|
| 1105 |
+
"loss": 2.0222,
|
| 1106 |
+
"step": 183000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 12.56,
|
| 1110 |
+
"learning_rate": 8.242424242424243e-05,
|
| 1111 |
+
"loss": 2.0214,
|
| 1112 |
+
"step": 184000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 12.63,
|
| 1116 |
+
"learning_rate": 8.232323232323233e-05,
|
| 1117 |
+
"loss": 2.0192,
|
| 1118 |
+
"step": 185000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 12.69,
|
| 1122 |
+
"learning_rate": 8.222222222222222e-05,
|
| 1123 |
+
"loss": 2.0139,
|
| 1124 |
+
"step": 186000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 12.76,
|
| 1128 |
+
"learning_rate": 8.212121212121212e-05,
|
| 1129 |
+
"loss": 2.0328,
|
| 1130 |
+
"step": 187000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 12.83,
|
| 1134 |
+
"learning_rate": 8.202020202020202e-05,
|
| 1135 |
+
"loss": 2.0146,
|
| 1136 |
+
"step": 188000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 12.9,
|
| 1140 |
+
"learning_rate": 8.191919191919192e-05,
|
| 1141 |
+
"loss": 2.0265,
|
| 1142 |
+
"step": 189000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 12.97,
|
| 1146 |
+
"learning_rate": 8.181818181818183e-05,
|
| 1147 |
+
"loss": 2.0229,
|
| 1148 |
+
"step": 190000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 13.03,
|
| 1152 |
+
"learning_rate": 8.171717171717172e-05,
|
| 1153 |
+
"loss": 2.0149,
|
| 1154 |
+
"step": 191000
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 13.1,
|
| 1158 |
+
"learning_rate": 8.161616161616163e-05,
|
| 1159 |
+
"loss": 1.998,
|
| 1160 |
+
"step": 192000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 13.17,
|
| 1164 |
+
"learning_rate": 8.151515151515152e-05,
|
| 1165 |
+
"loss": 2.0079,
|
| 1166 |
+
"step": 193000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 13.24,
|
| 1170 |
+
"learning_rate": 8.141414141414141e-05,
|
| 1171 |
+
"loss": 2.0109,
|
| 1172 |
+
"step": 194000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 13.31,
|
| 1176 |
+
"learning_rate": 8.131313131313132e-05,
|
| 1177 |
+
"loss": 2.0047,
|
| 1178 |
+
"step": 195000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 13.38,
|
| 1182 |
+
"learning_rate": 8.121212121212121e-05,
|
| 1183 |
+
"loss": 2.0052,
|
| 1184 |
+
"step": 196000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 13.44,
|
| 1188 |
+
"learning_rate": 8.111111111111112e-05,
|
| 1189 |
+
"loss": 2.0011,
|
| 1190 |
+
"step": 197000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 13.51,
|
| 1194 |
+
"learning_rate": 8.101010101010101e-05,
|
| 1195 |
+
"loss": 2.0056,
|
| 1196 |
+
"step": 198000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 13.58,
|
| 1200 |
+
"learning_rate": 8.090909090909092e-05,
|
| 1201 |
+
"loss": 2.0019,
|
| 1202 |
+
"step": 199000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 13.65,
|
| 1206 |
+
"learning_rate": 8.080808080808081e-05,
|
| 1207 |
+
"loss": 2.0061,
|
| 1208 |
+
"step": 200000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 13.72,
|
| 1212 |
+
"learning_rate": 8.07070707070707e-05,
|
| 1213 |
+
"loss": 2.0082,
|
| 1214 |
+
"step": 201000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 13.79,
|
| 1218 |
+
"learning_rate": 8.060606060606061e-05,
|
| 1219 |
+
"loss": 2.0041,
|
| 1220 |
+
"step": 202000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 13.85,
|
| 1224 |
+
"learning_rate": 8.05050505050505e-05,
|
| 1225 |
+
"loss": 2.0162,
|
| 1226 |
+
"step": 203000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 13.92,
|
| 1230 |
+
"learning_rate": 8.040404040404041e-05,
|
| 1231 |
+
"loss": 2.0059,
|
| 1232 |
+
"step": 204000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 13.99,
|
| 1236 |
+
"learning_rate": 8.03030303030303e-05,
|
| 1237 |
+
"loss": 2.0168,
|
| 1238 |
+
"step": 205000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 14.06,
|
| 1242 |
+
"learning_rate": 8.02020202020202e-05,
|
| 1243 |
+
"loss": 1.9914,
|
| 1244 |
+
"step": 206000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 14.13,
|
| 1248 |
+
"learning_rate": 8.010101010101011e-05,
|
| 1249 |
+
"loss": 1.9906,
|
| 1250 |
+
"step": 207000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 14.2,
|
| 1254 |
+
"learning_rate": 8e-05,
|
| 1255 |
+
"loss": 1.9841,
|
| 1256 |
+
"step": 208000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 14.26,
|
| 1260 |
+
"learning_rate": 7.989898989898991e-05,
|
| 1261 |
+
"loss": 2.0038,
|
| 1262 |
+
"step": 209000
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 14.33,
|
| 1266 |
+
"learning_rate": 7.97979797979798e-05,
|
| 1267 |
+
"loss": 1.9909,
|
| 1268 |
+
"step": 210000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 14.4,
|
| 1272 |
+
"learning_rate": 7.96969696969697e-05,
|
| 1273 |
+
"loss": 1.9961,
|
| 1274 |
+
"step": 211000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 14.47,
|
| 1278 |
+
"learning_rate": 7.95959595959596e-05,
|
| 1279 |
+
"loss": 1.9962,
|
| 1280 |
+
"step": 212000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 14.54,
|
| 1284 |
+
"learning_rate": 7.94949494949495e-05,
|
| 1285 |
+
"loss": 2.003,
|
| 1286 |
+
"step": 213000
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 14.6,
|
| 1290 |
+
"learning_rate": 7.93939393939394e-05,
|
| 1291 |
+
"loss": 1.9987,
|
| 1292 |
+
"step": 214000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 14.67,
|
| 1296 |
+
"learning_rate": 7.92929292929293e-05,
|
| 1297 |
+
"loss": 2.004,
|
| 1298 |
+
"step": 215000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 14.74,
|
| 1302 |
+
"learning_rate": 7.919191919191919e-05,
|
| 1303 |
+
"loss": 1.9994,
|
| 1304 |
+
"step": 216000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 14.81,
|
| 1308 |
+
"learning_rate": 7.90909090909091e-05,
|
| 1309 |
+
"loss": 2.001,
|
| 1310 |
+
"step": 217000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 14.88,
|
| 1314 |
+
"learning_rate": 7.898989898989899e-05,
|
| 1315 |
+
"loss": 1.998,
|
| 1316 |
+
"step": 218000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 14.95,
|
| 1320 |
+
"learning_rate": 7.88888888888889e-05,
|
| 1321 |
+
"loss": 2.0076,
|
| 1322 |
+
"step": 219000
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 15.01,
|
| 1326 |
+
"learning_rate": 7.878787878787879e-05,
|
| 1327 |
+
"loss": 2.0047,
|
| 1328 |
+
"step": 220000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 15.08,
|
| 1332 |
+
"learning_rate": 7.868686868686869e-05,
|
| 1333 |
+
"loss": 1.9923,
|
| 1334 |
+
"step": 221000
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 15.15,
|
| 1338 |
+
"learning_rate": 7.858585858585859e-05,
|
| 1339 |
+
"loss": 1.9828,
|
| 1340 |
+
"step": 222000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 15.22,
|
| 1344 |
+
"learning_rate": 7.848484848484848e-05,
|
| 1345 |
+
"loss": 1.9744,
|
| 1346 |
+
"step": 223000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 15.29,
|
| 1350 |
+
"learning_rate": 7.83838383838384e-05,
|
| 1351 |
+
"loss": 1.9851,
|
| 1352 |
+
"step": 224000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 15.36,
|
| 1356 |
+
"learning_rate": 7.828282828282829e-05,
|
| 1357 |
+
"loss": 1.9855,
|
| 1358 |
+
"step": 225000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 15.42,
|
| 1362 |
+
"learning_rate": 7.818181818181818e-05,
|
| 1363 |
+
"loss": 1.994,
|
| 1364 |
+
"step": 226000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 15.49,
|
| 1368 |
+
"learning_rate": 7.808080808080809e-05,
|
| 1369 |
+
"loss": 1.9845,
|
| 1370 |
+
"step": 227000
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 15.56,
|
| 1374 |
+
"learning_rate": 7.797979797979798e-05,
|
| 1375 |
+
"loss": 1.9871,
|
| 1376 |
+
"step": 228000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 15.63,
|
| 1380 |
+
"learning_rate": 7.787878787878789e-05,
|
| 1381 |
+
"loss": 1.9895,
|
| 1382 |
+
"step": 229000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 15.7,
|
| 1386 |
+
"learning_rate": 7.777777777777778e-05,
|
| 1387 |
+
"loss": 2.0003,
|
| 1388 |
+
"step": 230000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 15.76,
|
| 1392 |
+
"learning_rate": 7.767676767676769e-05,
|
| 1393 |
+
"loss": 2.0049,
|
| 1394 |
+
"step": 231000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 15.83,
|
| 1398 |
+
"learning_rate": 7.757575757575758e-05,
|
| 1399 |
+
"loss": 1.9929,
|
| 1400 |
+
"step": 232000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 15.9,
|
| 1404 |
+
"learning_rate": 7.747474747474747e-05,
|
| 1405 |
+
"loss": 1.9928,
|
| 1406 |
+
"step": 233000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 15.97,
|
| 1410 |
+
"learning_rate": 7.737373737373738e-05,
|
| 1411 |
+
"loss": 1.9938,
|
| 1412 |
+
"step": 234000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 16.04,
|
| 1416 |
+
"learning_rate": 7.727272727272727e-05,
|
| 1417 |
+
"loss": 1.9929,
|
| 1418 |
+
"step": 235000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 16.11,
|
| 1422 |
+
"learning_rate": 7.717171717171718e-05,
|
| 1423 |
+
"loss": 1.9688,
|
| 1424 |
+
"step": 236000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 16.17,
|
| 1428 |
+
"learning_rate": 7.707070707070707e-05,
|
| 1429 |
+
"loss": 1.9788,
|
| 1430 |
+
"step": 237000
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 16.24,
|
| 1434 |
+
"learning_rate": 7.696969696969696e-05,
|
| 1435 |
+
"loss": 1.9745,
|
| 1436 |
+
"step": 238000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 16.31,
|
| 1440 |
+
"learning_rate": 7.686868686868687e-05,
|
| 1441 |
+
"loss": 1.9982,
|
| 1442 |
+
"step": 239000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 16.38,
|
| 1446 |
+
"learning_rate": 7.676767676767676e-05,
|
| 1447 |
+
"loss": 1.9925,
|
| 1448 |
+
"step": 240000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 16.45,
|
| 1452 |
+
"learning_rate": 7.666666666666667e-05,
|
| 1453 |
+
"loss": 1.9876,
|
| 1454 |
+
"step": 241000
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 16.52,
|
| 1458 |
+
"learning_rate": 7.656565656565658e-05,
|
| 1459 |
+
"loss": 1.9761,
|
| 1460 |
+
"step": 242000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 16.58,
|
| 1464 |
+
"learning_rate": 7.646464646464647e-05,
|
| 1465 |
+
"loss": 1.9833,
|
| 1466 |
+
"step": 243000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 16.65,
|
| 1470 |
+
"learning_rate": 7.636363636363637e-05,
|
| 1471 |
+
"loss": 1.9863,
|
| 1472 |
+
"step": 244000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 16.72,
|
| 1476 |
+
"learning_rate": 7.626262626262627e-05,
|
| 1477 |
+
"loss": 1.9841,
|
| 1478 |
+
"step": 245000
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 16.79,
|
| 1482 |
+
"learning_rate": 7.616161616161617e-05,
|
| 1483 |
+
"loss": 1.9776,
|
| 1484 |
+
"step": 246000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 16.86,
|
| 1488 |
+
"learning_rate": 7.606060606060607e-05,
|
| 1489 |
+
"loss": 1.9947,
|
| 1490 |
+
"step": 247000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 16.92,
|
| 1494 |
+
"learning_rate": 7.595959595959596e-05,
|
| 1495 |
+
"loss": 1.9729,
|
| 1496 |
+
"step": 248000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 16.99,
|
| 1500 |
+
"learning_rate": 7.585858585858586e-05,
|
| 1501 |
+
"loss": 1.9813,
|
| 1502 |
+
"step": 249000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 17.06,
|
| 1506 |
+
"learning_rate": 7.575757575757576e-05,
|
| 1507 |
+
"loss": 1.9689,
|
| 1508 |
+
"step": 250000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 17.13,
|
| 1512 |
+
"learning_rate": 7.565656565656566e-05,
|
| 1513 |
+
"loss": 1.9626,
|
| 1514 |
+
"step": 251000
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 17.2,
|
| 1518 |
+
"learning_rate": 7.555555555555556e-05,
|
| 1519 |
+
"loss": 1.9661,
|
| 1520 |
+
"step": 252000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 17.27,
|
| 1524 |
+
"learning_rate": 7.545454545454545e-05,
|
| 1525 |
+
"loss": 1.9777,
|
| 1526 |
+
"step": 253000
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 17.33,
|
| 1530 |
+
"learning_rate": 7.535353535353536e-05,
|
| 1531 |
+
"loss": 1.9788,
|
| 1532 |
+
"step": 254000
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 17.4,
|
| 1536 |
+
"learning_rate": 7.525252525252525e-05,
|
| 1537 |
+
"loss": 1.9721,
|
| 1538 |
+
"step": 255000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 17.47,
|
| 1542 |
+
"learning_rate": 7.515151515151515e-05,
|
| 1543 |
+
"loss": 1.9779,
|
| 1544 |
+
"step": 256000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 17.54,
|
| 1548 |
+
"learning_rate": 7.505050505050505e-05,
|
| 1549 |
+
"loss": 1.9763,
|
| 1550 |
+
"step": 257000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 17.61,
|
| 1554 |
+
"learning_rate": 7.494949494949495e-05,
|
| 1555 |
+
"loss": 1.9768,
|
| 1556 |
+
"step": 258000
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 17.68,
|
| 1560 |
+
"learning_rate": 7.484848484848486e-05,
|
| 1561 |
+
"loss": 1.9626,
|
| 1562 |
+
"step": 259000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 17.74,
|
| 1566 |
+
"learning_rate": 7.474747474747475e-05,
|
| 1567 |
+
"loss": 1.9703,
|
| 1568 |
+
"step": 260000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 17.81,
|
| 1572 |
+
"learning_rate": 7.464646464646466e-05,
|
| 1573 |
+
"loss": 1.9747,
|
| 1574 |
+
"step": 261000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 17.88,
|
| 1578 |
+
"learning_rate": 7.454545454545455e-05,
|
| 1579 |
+
"loss": 1.9698,
|
| 1580 |
+
"step": 262000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 17.95,
|
| 1584 |
+
"learning_rate": 7.444444444444444e-05,
|
| 1585 |
+
"loss": 1.982,
|
| 1586 |
+
"step": 263000
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 18.02,
|
| 1590 |
+
"learning_rate": 7.434343434343435e-05,
|
| 1591 |
+
"loss": 1.9721,
|
| 1592 |
+
"step": 264000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 18.09,
|
| 1596 |
+
"learning_rate": 7.424242424242424e-05,
|
| 1597 |
+
"loss": 1.9554,
|
| 1598 |
+
"step": 265000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 18.15,
|
| 1602 |
+
"learning_rate": 7.414141414141415e-05,
|
| 1603 |
+
"loss": 1.9615,
|
| 1604 |
+
"step": 266000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 18.22,
|
| 1608 |
+
"learning_rate": 7.404040404040404e-05,
|
| 1609 |
+
"loss": 1.9592,
|
| 1610 |
+
"step": 267000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 18.29,
|
| 1614 |
+
"learning_rate": 7.393939393939395e-05,
|
| 1615 |
+
"loss": 1.9548,
|
| 1616 |
+
"step": 268000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 18.36,
|
| 1620 |
+
"learning_rate": 7.383838383838384e-05,
|
| 1621 |
+
"loss": 1.9535,
|
| 1622 |
+
"step": 269000
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 18.43,
|
| 1626 |
+
"learning_rate": 7.373737373737373e-05,
|
| 1627 |
+
"loss": 1.9606,
|
| 1628 |
+
"step": 270000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 18.49,
|
| 1632 |
+
"learning_rate": 7.363636363636364e-05,
|
| 1633 |
+
"loss": 1.9567,
|
| 1634 |
+
"step": 271000
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 18.56,
|
| 1638 |
+
"learning_rate": 7.353535353535353e-05,
|
| 1639 |
+
"loss": 1.9641,
|
| 1640 |
+
"step": 272000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 18.63,
|
| 1644 |
+
"learning_rate": 7.343434343434344e-05,
|
| 1645 |
+
"loss": 1.9645,
|
| 1646 |
+
"step": 273000
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 18.7,
|
| 1650 |
+
"learning_rate": 7.333333333333333e-05,
|
| 1651 |
+
"loss": 1.9537,
|
| 1652 |
+
"step": 274000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 18.77,
|
| 1656 |
+
"learning_rate": 7.323232323232324e-05,
|
| 1657 |
+
"loss": 1.9603,
|
| 1658 |
+
"step": 275000
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 18.84,
|
| 1662 |
+
"learning_rate": 7.313131313131314e-05,
|
| 1663 |
+
"loss": 1.9613,
|
| 1664 |
+
"step": 276000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 18.9,
|
| 1668 |
+
"learning_rate": 7.303030303030304e-05,
|
| 1669 |
+
"loss": 1.9673,
|
| 1670 |
+
"step": 277000
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 18.97,
|
| 1674 |
+
"learning_rate": 7.292929292929293e-05,
|
| 1675 |
+
"loss": 1.9685,
|
| 1676 |
+
"step": 278000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 19.04,
|
| 1680 |
+
"learning_rate": 7.282828282828284e-05,
|
| 1681 |
+
"loss": 1.953,
|
| 1682 |
+
"step": 279000
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 19.11,
|
| 1686 |
+
"learning_rate": 7.272727272727273e-05,
|
| 1687 |
+
"loss": 1.9428,
|
| 1688 |
+
"step": 280000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 19.18,
|
| 1692 |
+
"learning_rate": 7.262626262626263e-05,
|
| 1693 |
+
"loss": 1.9426,
|
| 1694 |
+
"step": 281000
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 19.25,
|
| 1698 |
+
"learning_rate": 7.252525252525253e-05,
|
| 1699 |
+
"loss": 1.9503,
|
| 1700 |
+
"step": 282000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 19.31,
|
| 1704 |
+
"learning_rate": 7.242424242424243e-05,
|
| 1705 |
+
"loss": 1.9517,
|
| 1706 |
+
"step": 283000
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 19.38,
|
| 1710 |
+
"learning_rate": 7.232323232323233e-05,
|
| 1711 |
+
"loss": 1.9556,
|
| 1712 |
+
"step": 284000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 19.45,
|
| 1716 |
+
"learning_rate": 7.222222222222222e-05,
|
| 1717 |
+
"loss": 1.9592,
|
| 1718 |
+
"step": 285000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 19.52,
|
| 1722 |
+
"learning_rate": 7.212121212121213e-05,
|
| 1723 |
+
"loss": 1.9499,
|
| 1724 |
+
"step": 286000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 19.59,
|
| 1728 |
+
"learning_rate": 7.202020202020202e-05,
|
| 1729 |
+
"loss": 1.9604,
|
| 1730 |
+
"step": 287000
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 19.65,
|
| 1734 |
+
"learning_rate": 7.191919191919192e-05,
|
| 1735 |
+
"loss": 1.9599,
|
| 1736 |
+
"step": 288000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 19.72,
|
| 1740 |
+
"learning_rate": 7.181818181818182e-05,
|
| 1741 |
+
"loss": 1.9466,
|
| 1742 |
+
"step": 289000
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 19.79,
|
| 1746 |
+
"learning_rate": 7.171717171717171e-05,
|
| 1747 |
+
"loss": 1.9581,
|
| 1748 |
+
"step": 290000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 19.86,
|
| 1752 |
+
"learning_rate": 7.161616161616162e-05,
|
| 1753 |
+
"loss": 1.9576,
|
| 1754 |
+
"step": 291000
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 19.93,
|
| 1758 |
+
"learning_rate": 7.151515151515152e-05,
|
| 1759 |
+
"loss": 1.9606,
|
| 1760 |
+
"step": 292000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 20.0,
|
| 1764 |
+
"learning_rate": 7.141414141414143e-05,
|
| 1765 |
+
"loss": 1.9705,
|
| 1766 |
+
"step": 293000
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 20.06,
|
| 1770 |
+
"learning_rate": 7.131313131313132e-05,
|
| 1771 |
+
"loss": 1.9444,
|
| 1772 |
+
"step": 294000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 20.13,
|
| 1776 |
+
"learning_rate": 7.121212121212121e-05,
|
| 1777 |
+
"loss": 1.939,
|
| 1778 |
+
"step": 295000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 20.2,
|
| 1782 |
+
"learning_rate": 7.111111111111112e-05,
|
| 1783 |
+
"loss": 1.9402,
|
| 1784 |
+
"step": 296000
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 20.27,
|
| 1788 |
+
"learning_rate": 7.101010101010101e-05,
|
| 1789 |
+
"loss": 1.9451,
|
| 1790 |
+
"step": 297000
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 20.34,
|
| 1794 |
+
"learning_rate": 7.090909090909092e-05,
|
| 1795 |
+
"loss": 1.9454,
|
| 1796 |
+
"step": 298000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 20.41,
|
| 1800 |
+
"learning_rate": 7.080808080808081e-05,
|
| 1801 |
+
"loss": 1.9405,
|
| 1802 |
+
"step": 299000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 20.47,
|
| 1806 |
+
"learning_rate": 7.07070707070707e-05,
|
| 1807 |
+
"loss": 1.944,
|
| 1808 |
+
"step": 300000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 20.54,
|
| 1812 |
+
"learning_rate": 7.060606060606061e-05,
|
| 1813 |
+
"loss": 1.948,
|
| 1814 |
+
"step": 301000
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 20.61,
|
| 1818 |
+
"learning_rate": 7.05050505050505e-05,
|
| 1819 |
+
"loss": 1.9418,
|
| 1820 |
+
"step": 302000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 20.68,
|
| 1824 |
+
"learning_rate": 7.040404040404041e-05,
|
| 1825 |
+
"loss": 1.9508,
|
| 1826 |
+
"step": 303000
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 20.75,
|
| 1830 |
+
"learning_rate": 7.03030303030303e-05,
|
| 1831 |
+
"loss": 1.9472,
|
| 1832 |
+
"step": 304000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 20.81,
|
| 1836 |
+
"learning_rate": 7.020202020202021e-05,
|
| 1837 |
+
"loss": 1.9414,
|
| 1838 |
+
"step": 305000
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 20.88,
|
| 1842 |
+
"learning_rate": 7.01010101010101e-05,
|
| 1843 |
+
"loss": 1.946,
|
| 1844 |
+
"step": 306000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 20.95,
|
| 1848 |
+
"learning_rate": 7e-05,
|
| 1849 |
+
"loss": 1.9558,
|
| 1850 |
+
"step": 307000
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 21.02,
|
| 1854 |
+
"learning_rate": 6.98989898989899e-05,
|
| 1855 |
+
"loss": 1.9465,
|
| 1856 |
+
"step": 308000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 21.09,
|
| 1860 |
+
"learning_rate": 6.97979797979798e-05,
|
| 1861 |
+
"loss": 1.9275,
|
| 1862 |
+
"step": 309000
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 21.16,
|
| 1866 |
+
"learning_rate": 6.96969696969697e-05,
|
| 1867 |
+
"loss": 1.9293,
|
| 1868 |
+
"step": 310000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 21.22,
|
| 1872 |
+
"learning_rate": 6.95959595959596e-05,
|
| 1873 |
+
"loss": 1.9273,
|
| 1874 |
+
"step": 311000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 21.29,
|
| 1878 |
+
"learning_rate": 6.94949494949495e-05,
|
| 1879 |
+
"loss": 1.9307,
|
| 1880 |
+
"step": 312000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 21.36,
|
| 1884 |
+
"learning_rate": 6.93939393939394e-05,
|
| 1885 |
+
"loss": 1.9341,
|
| 1886 |
+
"step": 313000
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 21.43,
|
| 1890 |
+
"learning_rate": 6.92929292929293e-05,
|
| 1891 |
+
"loss": 1.9504,
|
| 1892 |
+
"step": 314000
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 21.5,
|
| 1896 |
+
"learning_rate": 6.91919191919192e-05,
|
| 1897 |
+
"loss": 1.9366,
|
| 1898 |
+
"step": 315000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 21.57,
|
| 1902 |
+
"learning_rate": 6.90909090909091e-05,
|
| 1903 |
+
"loss": 1.9418,
|
| 1904 |
+
"step": 316000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 21.63,
|
| 1908 |
+
"learning_rate": 6.898989898989899e-05,
|
| 1909 |
+
"loss": 1.9473,
|
| 1910 |
+
"step": 317000
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 21.7,
|
| 1914 |
+
"learning_rate": 6.88888888888889e-05,
|
| 1915 |
+
"loss": 1.9403,
|
| 1916 |
+
"step": 318000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 21.77,
|
| 1920 |
+
"learning_rate": 6.878787878787879e-05,
|
| 1921 |
+
"loss": 1.9409,
|
| 1922 |
+
"step": 319000
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 21.84,
|
| 1926 |
+
"learning_rate": 6.86868686868687e-05,
|
| 1927 |
+
"loss": 1.9383,
|
| 1928 |
+
"step": 320000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 21.91,
|
| 1932 |
+
"learning_rate": 6.858585858585859e-05,
|
| 1933 |
+
"loss": 1.9433,
|
| 1934 |
+
"step": 321000
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 21.98,
|
| 1938 |
+
"learning_rate": 6.848484848484848e-05,
|
| 1939 |
+
"loss": 1.9449,
|
| 1940 |
+
"step": 322000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 22.04,
|
| 1944 |
+
"learning_rate": 6.838383838383839e-05,
|
| 1945 |
+
"loss": 1.9287,
|
| 1946 |
+
"step": 323000
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 22.11,
|
| 1950 |
+
"learning_rate": 6.828282828282828e-05,
|
| 1951 |
+
"loss": 1.9251,
|
| 1952 |
+
"step": 324000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 22.18,
|
| 1956 |
+
"learning_rate": 6.818181818181818e-05,
|
| 1957 |
+
"loss": 1.943,
|
| 1958 |
+
"step": 325000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 22.25,
|
| 1962 |
+
"learning_rate": 6.808080808080809e-05,
|
| 1963 |
+
"loss": 1.9316,
|
| 1964 |
+
"step": 326000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 22.32,
|
| 1968 |
+
"learning_rate": 6.797979797979798e-05,
|
| 1969 |
+
"loss": 1.935,
|
| 1970 |
+
"step": 327000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 22.38,
|
| 1974 |
+
"learning_rate": 6.787878787878789e-05,
|
| 1975 |
+
"loss": 1.9294,
|
| 1976 |
+
"step": 328000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 22.45,
|
| 1980 |
+
"learning_rate": 6.777777777777778e-05,
|
| 1981 |
+
"loss": 1.9458,
|
| 1982 |
+
"step": 329000
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 22.52,
|
| 1986 |
+
"learning_rate": 6.767676767676769e-05,
|
| 1987 |
+
"loss": 1.9334,
|
| 1988 |
+
"step": 330000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 22.59,
|
| 1992 |
+
"learning_rate": 6.757575757575758e-05,
|
| 1993 |
+
"loss": 1.9595,
|
| 1994 |
+
"step": 331000
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 22.66,
|
| 1998 |
+
"learning_rate": 6.747474747474747e-05,
|
| 1999 |
+
"loss": 1.9662,
|
| 2000 |
+
"step": 332000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 22.73,
|
| 2004 |
+
"learning_rate": 6.737373737373738e-05,
|
| 2005 |
+
"loss": 1.9576,
|
| 2006 |
+
"step": 333000
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 22.79,
|
| 2010 |
+
"learning_rate": 6.727272727272727e-05,
|
| 2011 |
+
"loss": 1.9432,
|
| 2012 |
+
"step": 334000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 22.86,
|
| 2016 |
+
"learning_rate": 6.717171717171718e-05,
|
| 2017 |
+
"loss": 1.933,
|
| 2018 |
+
"step": 335000
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 22.93,
|
| 2022 |
+
"learning_rate": 6.707070707070707e-05,
|
| 2023 |
+
"loss": 1.948,
|
| 2024 |
+
"step": 336000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 23.0,
|
| 2028 |
+
"learning_rate": 6.696969696969696e-05,
|
| 2029 |
+
"loss": 1.9438,
|
| 2030 |
+
"step": 337000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 23.07,
|
| 2034 |
+
"learning_rate": 6.686868686868687e-05,
|
| 2035 |
+
"loss": 1.9149,
|
| 2036 |
+
"step": 338000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 23.14,
|
| 2040 |
+
"learning_rate": 6.676767676767676e-05,
|
| 2041 |
+
"loss": 1.9162,
|
| 2042 |
+
"step": 339000
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 23.2,
|
| 2046 |
+
"learning_rate": 6.666666666666667e-05,
|
| 2047 |
+
"loss": 1.9097,
|
| 2048 |
+
"step": 340000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 23.27,
|
| 2052 |
+
"learning_rate": 6.656565656565656e-05,
|
| 2053 |
+
"loss": 1.9195,
|
| 2054 |
+
"step": 341000
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 23.34,
|
| 2058 |
+
"learning_rate": 6.646464646464647e-05,
|
| 2059 |
+
"loss": 1.925,
|
| 2060 |
+
"step": 342000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 23.41,
|
| 2064 |
+
"learning_rate": 6.636363636363638e-05,
|
| 2065 |
+
"loss": 1.9224,
|
| 2066 |
+
"step": 343000
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 23.48,
|
| 2070 |
+
"learning_rate": 6.626262626262627e-05,
|
| 2071 |
+
"loss": 1.9144,
|
| 2072 |
+
"step": 344000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 23.54,
|
| 2076 |
+
"learning_rate": 6.616161616161617e-05,
|
| 2077 |
+
"loss": 1.9156,
|
| 2078 |
+
"step": 345000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 23.61,
|
| 2082 |
+
"learning_rate": 6.606060606060607e-05,
|
| 2083 |
+
"loss": 1.9179,
|
| 2084 |
+
"step": 346000
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 23.68,
|
| 2088 |
+
"learning_rate": 6.595959595959596e-05,
|
| 2089 |
+
"loss": 1.9291,
|
| 2090 |
+
"step": 347000
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 23.75,
|
| 2094 |
+
"learning_rate": 6.585858585858587e-05,
|
| 2095 |
+
"loss": 1.9177,
|
| 2096 |
+
"step": 348000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 23.82,
|
| 2100 |
+
"learning_rate": 6.575757575757576e-05,
|
| 2101 |
+
"loss": 1.92,
|
| 2102 |
+
"step": 349000
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 23.89,
|
| 2106 |
+
"learning_rate": 6.565656565656566e-05,
|
| 2107 |
+
"loss": 1.9278,
|
| 2108 |
+
"step": 350000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 23.95,
|
| 2112 |
+
"learning_rate": 6.555555555555556e-05,
|
| 2113 |
+
"loss": 1.927,
|
| 2114 |
+
"step": 351000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 24.02,
|
| 2118 |
+
"learning_rate": 6.545454545454546e-05,
|
| 2119 |
+
"loss": 1.9263,
|
| 2120 |
+
"step": 352000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 24.09,
|
| 2124 |
+
"learning_rate": 6.535353535353536e-05,
|
| 2125 |
+
"loss": 1.9008,
|
| 2126 |
+
"step": 353000
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 24.16,
|
| 2130 |
+
"learning_rate": 6.525252525252525e-05,
|
| 2131 |
+
"loss": 1.9071,
|
| 2132 |
+
"step": 354000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 24.23,
|
| 2136 |
+
"learning_rate": 6.515151515151516e-05,
|
| 2137 |
+
"loss": 1.9203,
|
| 2138 |
+
"step": 355000
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 24.3,
|
| 2142 |
+
"learning_rate": 6.505050505050505e-05,
|
| 2143 |
+
"loss": 1.903,
|
| 2144 |
+
"step": 356000
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 24.36,
|
| 2148 |
+
"learning_rate": 6.494949494949495e-05,
|
| 2149 |
+
"loss": 1.907,
|
| 2150 |
+
"step": 357000
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 24.43,
|
| 2154 |
+
"learning_rate": 6.484848484848485e-05,
|
| 2155 |
+
"loss": 1.9137,
|
| 2156 |
+
"step": 358000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 24.5,
|
| 2160 |
+
"learning_rate": 6.474747474747474e-05,
|
| 2161 |
+
"loss": 1.9095,
|
| 2162 |
+
"step": 359000
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 24.57,
|
| 2166 |
+
"learning_rate": 6.464646464646466e-05,
|
| 2167 |
+
"loss": 1.908,
|
| 2168 |
+
"step": 360000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 24.64,
|
| 2172 |
+
"learning_rate": 6.454545454545455e-05,
|
| 2173 |
+
"loss": 1.9124,
|
| 2174 |
+
"step": 361000
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 24.7,
|
| 2178 |
+
"learning_rate": 6.444444444444446e-05,
|
| 2179 |
+
"loss": 1.9199,
|
| 2180 |
+
"step": 362000
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 24.77,
|
| 2184 |
+
"learning_rate": 6.434343434343435e-05,
|
| 2185 |
+
"loss": 1.9144,
|
| 2186 |
+
"step": 363000
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 24.84,
|
| 2190 |
+
"learning_rate": 6.424242424242424e-05,
|
| 2191 |
+
"loss": 1.9174,
|
| 2192 |
+
"step": 364000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 24.91,
|
| 2196 |
+
"learning_rate": 6.414141414141415e-05,
|
| 2197 |
+
"loss": 1.9205,
|
| 2198 |
+
"step": 365000
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 24.98,
|
| 2202 |
+
"learning_rate": 6.404040404040404e-05,
|
| 2203 |
+
"loss": 1.9046,
|
| 2204 |
+
"step": 366000
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 25.05,
|
| 2208 |
+
"learning_rate": 6.393939393939395e-05,
|
| 2209 |
+
"loss": 1.9036,
|
| 2210 |
+
"step": 367000
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 25.11,
|
| 2214 |
+
"learning_rate": 6.383838383838384e-05,
|
| 2215 |
+
"loss": 1.8938,
|
| 2216 |
+
"step": 368000
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 25.18,
|
| 2220 |
+
"learning_rate": 6.373737373737373e-05,
|
| 2221 |
+
"loss": 1.898,
|
| 2222 |
+
"step": 369000
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 25.25,
|
| 2226 |
+
"learning_rate": 6.363636363636364e-05,
|
| 2227 |
+
"loss": 1.896,
|
| 2228 |
+
"step": 370000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 25.32,
|
| 2232 |
+
"learning_rate": 6.353535353535353e-05,
|
| 2233 |
+
"loss": 1.9085,
|
| 2234 |
+
"step": 371000
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 25.39,
|
| 2238 |
+
"learning_rate": 6.343434343434344e-05,
|
| 2239 |
+
"loss": 1.9156,
|
| 2240 |
+
"step": 372000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 25.46,
|
| 2244 |
+
"learning_rate": 6.333333333333333e-05,
|
| 2245 |
+
"loss": 1.9199,
|
| 2246 |
+
"step": 373000
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 25.52,
|
| 2250 |
+
"learning_rate": 6.323232323232323e-05,
|
| 2251 |
+
"loss": 1.9125,
|
| 2252 |
+
"step": 374000
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 25.59,
|
| 2256 |
+
"learning_rate": 6.313131313131313e-05,
|
| 2257 |
+
"loss": 1.9183,
|
| 2258 |
+
"step": 375000
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 25.66,
|
| 2262 |
+
"learning_rate": 6.303030303030302e-05,
|
| 2263 |
+
"loss": 1.913,
|
| 2264 |
+
"step": 376000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 25.73,
|
| 2268 |
+
"learning_rate": 6.292929292929294e-05,
|
| 2269 |
+
"loss": 1.9045,
|
| 2270 |
+
"step": 377000
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 25.8,
|
| 2274 |
+
"learning_rate": 6.282828282828284e-05,
|
| 2275 |
+
"loss": 1.909,
|
| 2276 |
+
"step": 378000
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 25.87,
|
| 2280 |
+
"learning_rate": 6.272727272727273e-05,
|
| 2281 |
+
"loss": 1.9037,
|
| 2282 |
+
"step": 379000
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 25.93,
|
| 2286 |
+
"learning_rate": 6.262626262626264e-05,
|
| 2287 |
+
"loss": 1.9099,
|
| 2288 |
+
"step": 380000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 26.0,
|
| 2292 |
+
"learning_rate": 6.252525252525253e-05,
|
| 2293 |
+
"loss": 1.9088,
|
| 2294 |
+
"step": 381000
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 26.07,
|
| 2298 |
+
"learning_rate": 6.242424242424243e-05,
|
| 2299 |
+
"loss": 1.8777,
|
| 2300 |
+
"step": 382000
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 26.14,
|
| 2304 |
+
"learning_rate": 6.232323232323233e-05,
|
| 2305 |
+
"loss": 1.8821,
|
| 2306 |
+
"step": 383000
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 26.21,
|
| 2310 |
+
"learning_rate": 6.222222222222222e-05,
|
| 2311 |
+
"loss": 1.8967,
|
| 2312 |
+
"step": 384000
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 26.27,
|
| 2316 |
+
"learning_rate": 6.212121212121213e-05,
|
| 2317 |
+
"loss": 1.8927,
|
| 2318 |
+
"step": 385000
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 26.34,
|
| 2322 |
+
"learning_rate": 6.202020202020202e-05,
|
| 2323 |
+
"loss": 1.8913,
|
| 2324 |
+
"step": 386000
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 26.41,
|
| 2328 |
+
"learning_rate": 6.191919191919192e-05,
|
| 2329 |
+
"loss": 1.8924,
|
| 2330 |
+
"step": 387000
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 26.48,
|
| 2334 |
+
"learning_rate": 6.181818181818182e-05,
|
| 2335 |
+
"loss": 1.8934,
|
| 2336 |
+
"step": 388000
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 26.55,
|
| 2340 |
+
"learning_rate": 6.171717171717172e-05,
|
| 2341 |
+
"loss": 1.8967,
|
| 2342 |
+
"step": 389000
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 26.62,
|
| 2346 |
+
"learning_rate": 6.161616161616162e-05,
|
| 2347 |
+
"loss": 1.8984,
|
| 2348 |
+
"step": 390000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 26.68,
|
| 2352 |
+
"learning_rate": 6.151515151515151e-05,
|
| 2353 |
+
"loss": 1.896,
|
| 2354 |
+
"step": 391000
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 26.75,
|
| 2358 |
+
"learning_rate": 6.141414141414142e-05,
|
| 2359 |
+
"loss": 1.9051,
|
| 2360 |
+
"step": 392000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 26.82,
|
| 2364 |
+
"learning_rate": 6.131313131313131e-05,
|
| 2365 |
+
"loss": 1.9027,
|
| 2366 |
+
"step": 393000
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 26.89,
|
| 2370 |
+
"learning_rate": 6.121212121212121e-05,
|
| 2371 |
+
"loss": 1.8934,
|
| 2372 |
+
"step": 394000
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 26.96,
|
| 2376 |
+
"learning_rate": 6.111111111111112e-05,
|
| 2377 |
+
"loss": 1.9082,
|
| 2378 |
+
"step": 395000
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 27.03,
|
| 2382 |
+
"learning_rate": 6.101010101010102e-05,
|
| 2383 |
+
"loss": 1.8962,
|
| 2384 |
+
"step": 396000
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 27.09,
|
| 2388 |
+
"learning_rate": 6.090909090909091e-05,
|
| 2389 |
+
"loss": 1.8776,
|
| 2390 |
+
"step": 397000
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 27.16,
|
| 2394 |
+
"learning_rate": 6.080808080808081e-05,
|
| 2395 |
+
"loss": 1.8818,
|
| 2396 |
+
"step": 398000
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 27.23,
|
| 2400 |
+
"learning_rate": 6.070707070707071e-05,
|
| 2401 |
+
"loss": 1.8873,
|
| 2402 |
+
"step": 399000
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 27.3,
|
| 2406 |
+
"learning_rate": 6.060606060606061e-05,
|
| 2407 |
+
"loss": 1.8836,
|
| 2408 |
+
"step": 400000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 27.37,
|
| 2412 |
+
"learning_rate": 6.050505050505051e-05,
|
| 2413 |
+
"loss": 1.8855,
|
| 2414 |
+
"step": 401000
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 27.43,
|
| 2418 |
+
"learning_rate": 6.040404040404041e-05,
|
| 2419 |
+
"loss": 1.8858,
|
| 2420 |
+
"step": 402000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 27.5,
|
| 2424 |
+
"learning_rate": 6.03030303030303e-05,
|
| 2425 |
+
"loss": 1.8853,
|
| 2426 |
+
"step": 403000
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 27.57,
|
| 2430 |
+
"learning_rate": 6.02020202020202e-05,
|
| 2431 |
+
"loss": 1.8919,
|
| 2432 |
+
"step": 404000
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 27.64,
|
| 2436 |
+
"learning_rate": 6.01010101010101e-05,
|
| 2437 |
+
"loss": 1.896,
|
| 2438 |
+
"step": 405000
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 27.71,
|
| 2442 |
+
"learning_rate": 6e-05,
|
| 2443 |
+
"loss": 1.896,
|
| 2444 |
+
"step": 406000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 27.78,
|
| 2448 |
+
"learning_rate": 5.98989898989899e-05,
|
| 2449 |
+
"loss": 1.8899,
|
| 2450 |
+
"step": 407000
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 27.84,
|
| 2454 |
+
"learning_rate": 5.97979797979798e-05,
|
| 2455 |
+
"loss": 1.8864,
|
| 2456 |
+
"step": 408000
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 27.91,
|
| 2460 |
+
"learning_rate": 5.969696969696969e-05,
|
| 2461 |
+
"loss": 1.8934,
|
| 2462 |
+
"step": 409000
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 27.98,
|
| 2466 |
+
"learning_rate": 5.959595959595959e-05,
|
| 2467 |
+
"loss": 1.8943,
|
| 2468 |
+
"step": 410000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 28.05,
|
| 2472 |
+
"learning_rate": 5.949494949494949e-05,
|
| 2473 |
+
"loss": 1.8819,
|
| 2474 |
+
"step": 411000
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 28.12,
|
| 2478 |
+
"learning_rate": 5.93939393939394e-05,
|
| 2479 |
+
"loss": 1.8619,
|
| 2480 |
+
"step": 412000
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 28.19,
|
| 2484 |
+
"learning_rate": 5.92929292929293e-05,
|
| 2485 |
+
"loss": 1.8659,
|
| 2486 |
+
"step": 413000
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 28.25,
|
| 2490 |
+
"learning_rate": 5.91919191919192e-05,
|
| 2491 |
+
"loss": 1.871,
|
| 2492 |
+
"step": 414000
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 28.32,
|
| 2496 |
+
"learning_rate": 5.90909090909091e-05,
|
| 2497 |
+
"loss": 1.8764,
|
| 2498 |
+
"step": 415000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 28.39,
|
| 2502 |
+
"learning_rate": 5.8989898989898996e-05,
|
| 2503 |
+
"loss": 1.8786,
|
| 2504 |
+
"step": 416000
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 28.46,
|
| 2508 |
+
"learning_rate": 5.8888888888888896e-05,
|
| 2509 |
+
"loss": 1.8813,
|
| 2510 |
+
"step": 417000
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 28.53,
|
| 2514 |
+
"learning_rate": 5.878787878787879e-05,
|
| 2515 |
+
"loss": 1.8769,
|
| 2516 |
+
"step": 418000
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 28.59,
|
| 2520 |
+
"learning_rate": 5.868686868686869e-05,
|
| 2521 |
+
"loss": 1.8842,
|
| 2522 |
+
"step": 419000
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 28.66,
|
| 2526 |
+
"learning_rate": 5.858585858585859e-05,
|
| 2527 |
+
"loss": 1.8805,
|
| 2528 |
+
"step": 420000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 28.73,
|
| 2532 |
+
"learning_rate": 5.848484848484849e-05,
|
| 2533 |
+
"loss": 1.8778,
|
| 2534 |
+
"step": 421000
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 28.8,
|
| 2538 |
+
"learning_rate": 5.8383838383838386e-05,
|
| 2539 |
+
"loss": 1.8847,
|
| 2540 |
+
"step": 422000
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 28.87,
|
| 2544 |
+
"learning_rate": 5.8282828282828286e-05,
|
| 2545 |
+
"loss": 1.8862,
|
| 2546 |
+
"step": 423000
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 28.94,
|
| 2550 |
+
"learning_rate": 5.818181818181818e-05,
|
| 2551 |
+
"loss": 1.8858,
|
| 2552 |
+
"step": 424000
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 29.0,
|
| 2556 |
+
"learning_rate": 5.808080808080808e-05,
|
| 2557 |
+
"loss": 1.8838,
|
| 2558 |
+
"step": 425000
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 29.07,
|
| 2562 |
+
"learning_rate": 5.797979797979798e-05,
|
| 2563 |
+
"loss": 1.8534,
|
| 2564 |
+
"step": 426000
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 29.14,
|
| 2568 |
+
"learning_rate": 5.787878787878788e-05,
|
| 2569 |
+
"loss": 1.8667,
|
| 2570 |
+
"step": 427000
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 29.21,
|
| 2574 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 2575 |
+
"loss": 1.8682,
|
| 2576 |
+
"step": 428000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 29.28,
|
| 2580 |
+
"learning_rate": 5.767676767676768e-05,
|
| 2581 |
+
"loss": 1.8787,
|
| 2582 |
+
"step": 429000
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 29.35,
|
| 2586 |
+
"learning_rate": 5.757575757575758e-05,
|
| 2587 |
+
"loss": 1.8761,
|
| 2588 |
+
"step": 430000
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 29.41,
|
| 2592 |
+
"learning_rate": 5.747474747474748e-05,
|
| 2593 |
+
"loss": 1.88,
|
| 2594 |
+
"step": 431000
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 29.48,
|
| 2598 |
+
"learning_rate": 5.737373737373738e-05,
|
| 2599 |
+
"loss": 1.8679,
|
| 2600 |
+
"step": 432000
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 29.55,
|
| 2604 |
+
"learning_rate": 5.727272727272728e-05,
|
| 2605 |
+
"loss": 1.87,
|
| 2606 |
+
"step": 433000
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 29.62,
|
| 2610 |
+
"learning_rate": 5.717171717171717e-05,
|
| 2611 |
+
"loss": 1.8662,
|
| 2612 |
+
"step": 434000
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 29.69,
|
| 2616 |
+
"learning_rate": 5.707070707070707e-05,
|
| 2617 |
+
"loss": 1.8798,
|
| 2618 |
+
"step": 435000
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 29.75,
|
| 2622 |
+
"learning_rate": 5.696969696969697e-05,
|
| 2623 |
+
"loss": 1.8779,
|
| 2624 |
+
"step": 436000
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 29.82,
|
| 2628 |
+
"learning_rate": 5.686868686868687e-05,
|
| 2629 |
+
"loss": 1.8739,
|
| 2630 |
+
"step": 437000
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 29.89,
|
| 2634 |
+
"learning_rate": 5.676767676767677e-05,
|
| 2635 |
+
"loss": 1.8757,
|
| 2636 |
+
"step": 438000
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 29.96,
|
| 2640 |
+
"learning_rate": 5.666666666666667e-05,
|
| 2641 |
+
"loss": 1.8833,
|
| 2642 |
+
"step": 439000
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 30.03,
|
| 2646 |
+
"learning_rate": 5.6565656565656563e-05,
|
| 2647 |
+
"loss": 1.8713,
|
| 2648 |
+
"step": 440000
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 30.1,
|
| 2652 |
+
"learning_rate": 5.646464646464646e-05,
|
| 2653 |
+
"loss": 1.8733,
|
| 2654 |
+
"step": 441000
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 30.16,
|
| 2658 |
+
"learning_rate": 5.636363636363636e-05,
|
| 2659 |
+
"loss": 1.8555,
|
| 2660 |
+
"step": 442000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 30.23,
|
| 2664 |
+
"learning_rate": 5.626262626262626e-05,
|
| 2665 |
+
"loss": 1.8639,
|
| 2666 |
+
"step": 443000
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 30.3,
|
| 2670 |
+
"learning_rate": 5.616161616161616e-05,
|
| 2671 |
+
"loss": 1.8654,
|
| 2672 |
+
"step": 444000
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 30.37,
|
| 2676 |
+
"learning_rate": 5.606060606060606e-05,
|
| 2677 |
+
"loss": 1.8597,
|
| 2678 |
+
"step": 445000
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 30.44,
|
| 2682 |
+
"learning_rate": 5.595959595959597e-05,
|
| 2683 |
+
"loss": 1.8625,
|
| 2684 |
+
"step": 446000
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 30.51,
|
| 2688 |
+
"learning_rate": 5.5858585858585867e-05,
|
| 2689 |
+
"loss": 1.8686,
|
| 2690 |
+
"step": 447000
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 30.57,
|
| 2694 |
+
"learning_rate": 5.5757575757575766e-05,
|
| 2695 |
+
"loss": 1.8881,
|
| 2696 |
+
"step": 448000
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 30.64,
|
| 2700 |
+
"learning_rate": 5.5656565656565666e-05,
|
| 2701 |
+
"loss": 1.9063,
|
| 2702 |
+
"step": 449000
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 30.71,
|
| 2706 |
+
"learning_rate": 5.555555555555556e-05,
|
| 2707 |
+
"loss": 1.9019,
|
| 2708 |
+
"step": 450000
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 30.78,
|
| 2712 |
+
"learning_rate": 5.545454545454546e-05,
|
| 2713 |
+
"loss": 1.93,
|
| 2714 |
+
"step": 451000
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 30.85,
|
| 2718 |
+
"learning_rate": 5.535353535353536e-05,
|
| 2719 |
+
"loss": 1.9213,
|
| 2720 |
+
"step": 452000
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 30.92,
|
| 2724 |
+
"learning_rate": 5.525252525252526e-05,
|
| 2725 |
+
"loss": 1.9301,
|
| 2726 |
+
"step": 453000
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 30.98,
|
| 2730 |
+
"learning_rate": 5.5151515151515156e-05,
|
| 2731 |
+
"loss": 1.9074,
|
| 2732 |
+
"step": 454000
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 31.05,
|
| 2736 |
+
"learning_rate": 5.5050505050505056e-05,
|
| 2737 |
+
"loss": 1.8867,
|
| 2738 |
+
"step": 455000
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 31.12,
|
| 2742 |
+
"learning_rate": 5.494949494949495e-05,
|
| 2743 |
+
"loss": 1.8717,
|
| 2744 |
+
"step": 456000
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 31.19,
|
| 2748 |
+
"learning_rate": 5.484848484848485e-05,
|
| 2749 |
+
"loss": 1.8738,
|
| 2750 |
+
"step": 457000
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 31.26,
|
| 2754 |
+
"learning_rate": 5.474747474747475e-05,
|
| 2755 |
+
"loss": 1.8762,
|
| 2756 |
+
"step": 458000
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 31.32,
|
| 2760 |
+
"learning_rate": 5.464646464646465e-05,
|
| 2761 |
+
"loss": 1.8793,
|
| 2762 |
+
"step": 459000
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 31.39,
|
| 2766 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 2767 |
+
"loss": 1.8792,
|
| 2768 |
+
"step": 460000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 31.46,
|
| 2772 |
+
"learning_rate": 5.4444444444444446e-05,
|
| 2773 |
+
"loss": 1.8754,
|
| 2774 |
+
"step": 461000
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 31.53,
|
| 2778 |
+
"learning_rate": 5.434343434343434e-05,
|
| 2779 |
+
"loss": 1.889,
|
| 2780 |
+
"step": 462000
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 31.6,
|
| 2784 |
+
"learning_rate": 5.424242424242425e-05,
|
| 2785 |
+
"loss": 1.888,
|
| 2786 |
+
"step": 463000
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 31.67,
|
| 2790 |
+
"learning_rate": 5.414141414141415e-05,
|
| 2791 |
+
"loss": 1.8847,
|
| 2792 |
+
"step": 464000
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 31.73,
|
| 2796 |
+
"learning_rate": 5.4040404040404044e-05,
|
| 2797 |
+
"loss": 1.8827,
|
| 2798 |
+
"step": 465000
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 31.8,
|
| 2802 |
+
"learning_rate": 5.393939393939394e-05,
|
| 2803 |
+
"loss": 1.8847,
|
| 2804 |
+
"step": 466000
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 31.87,
|
| 2808 |
+
"learning_rate": 5.383838383838384e-05,
|
| 2809 |
+
"loss": 1.8872,
|
| 2810 |
+
"step": 467000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 31.94,
|
| 2814 |
+
"learning_rate": 5.373737373737374e-05,
|
| 2815 |
+
"loss": 1.8853,
|
| 2816 |
+
"step": 468000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 32.01,
|
| 2820 |
+
"learning_rate": 5.363636363636364e-05,
|
| 2821 |
+
"loss": 1.8751,
|
| 2822 |
+
"step": 469000
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 32.08,
|
| 2826 |
+
"learning_rate": 5.353535353535354e-05,
|
| 2827 |
+
"loss": 1.8578,
|
| 2828 |
+
"step": 470000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 32.14,
|
| 2832 |
+
"learning_rate": 5.3434343434343434e-05,
|
| 2833 |
+
"loss": 1.8641,
|
| 2834 |
+
"step": 471000
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 32.21,
|
| 2838 |
+
"learning_rate": 5.333333333333333e-05,
|
| 2839 |
+
"loss": 1.8604,
|
| 2840 |
+
"step": 472000
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 32.28,
|
| 2844 |
+
"learning_rate": 5.323232323232323e-05,
|
| 2845 |
+
"loss": 1.8562,
|
| 2846 |
+
"step": 473000
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 32.35,
|
| 2850 |
+
"learning_rate": 5.313131313131313e-05,
|
| 2851 |
+
"loss": 1.8676,
|
| 2852 |
+
"step": 474000
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 32.42,
|
| 2856 |
+
"learning_rate": 5.303030303030303e-05,
|
| 2857 |
+
"loss": 1.8777,
|
| 2858 |
+
"step": 475000
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 32.48,
|
| 2862 |
+
"learning_rate": 5.292929292929293e-05,
|
| 2863 |
+
"loss": 1.871,
|
| 2864 |
+
"step": 476000
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 32.55,
|
| 2868 |
+
"learning_rate": 5.2828282828282824e-05,
|
| 2869 |
+
"loss": 1.8754,
|
| 2870 |
+
"step": 477000
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 32.62,
|
| 2874 |
+
"learning_rate": 5.272727272727272e-05,
|
| 2875 |
+
"loss": 1.8745,
|
| 2876 |
+
"step": 478000
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 32.69,
|
| 2880 |
+
"learning_rate": 5.262626262626262e-05,
|
| 2881 |
+
"loss": 1.862,
|
| 2882 |
+
"step": 479000
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 32.76,
|
| 2886 |
+
"learning_rate": 5.2525252525252536e-05,
|
| 2887 |
+
"loss": 1.8573,
|
| 2888 |
+
"step": 480000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 32.83,
|
| 2892 |
+
"learning_rate": 5.242424242424243e-05,
|
| 2893 |
+
"loss": 1.8736,
|
| 2894 |
+
"step": 481000
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 32.89,
|
| 2898 |
+
"learning_rate": 5.232323232323233e-05,
|
| 2899 |
+
"loss": 1.8789,
|
| 2900 |
+
"step": 482000
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 32.96,
|
| 2904 |
+
"learning_rate": 5.222222222222223e-05,
|
| 2905 |
+
"loss": 1.8713,
|
| 2906 |
+
"step": 483000
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 33.03,
|
| 2910 |
+
"learning_rate": 5.212121212121213e-05,
|
| 2911 |
+
"loss": 1.8554,
|
| 2912 |
+
"step": 484000
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 33.1,
|
| 2916 |
+
"learning_rate": 5.2020202020202026e-05,
|
| 2917 |
+
"loss": 1.8639,
|
| 2918 |
+
"step": 485000
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 33.17,
|
| 2922 |
+
"learning_rate": 5.1919191919191926e-05,
|
| 2923 |
+
"loss": 1.8765,
|
| 2924 |
+
"step": 486000
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 33.24,
|
| 2928 |
+
"learning_rate": 5.181818181818182e-05,
|
| 2929 |
+
"loss": 1.8711,
|
| 2930 |
+
"step": 487000
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 33.3,
|
| 2934 |
+
"learning_rate": 5.171717171717172e-05,
|
| 2935 |
+
"loss": 1.8657,
|
| 2936 |
+
"step": 488000
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 33.37,
|
| 2940 |
+
"learning_rate": 5.161616161616162e-05,
|
| 2941 |
+
"loss": 1.8547,
|
| 2942 |
+
"step": 489000
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 33.44,
|
| 2946 |
+
"learning_rate": 5.151515151515152e-05,
|
| 2947 |
+
"loss": 1.8535,
|
| 2948 |
+
"step": 490000
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 33.51,
|
| 2952 |
+
"learning_rate": 5.1414141414141416e-05,
|
| 2953 |
+
"loss": 1.8606,
|
| 2954 |
+
"step": 491000
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 33.58,
|
| 2958 |
+
"learning_rate": 5.1313131313131316e-05,
|
| 2959 |
+
"loss": 1.8564,
|
| 2960 |
+
"step": 492000
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 33.64,
|
| 2964 |
+
"learning_rate": 5.121212121212121e-05,
|
| 2965 |
+
"loss": 1.8529,
|
| 2966 |
+
"step": 493000
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 33.71,
|
| 2970 |
+
"learning_rate": 5.111111111111111e-05,
|
| 2971 |
+
"loss": 1.8678,
|
| 2972 |
+
"step": 494000
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 33.78,
|
| 2976 |
+
"learning_rate": 5.101010101010101e-05,
|
| 2977 |
+
"loss": 1.869,
|
| 2978 |
+
"step": 495000
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 33.85,
|
| 2982 |
+
"learning_rate": 5.090909090909091e-05,
|
| 2983 |
+
"loss": 1.8669,
|
| 2984 |
+
"step": 496000
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 33.92,
|
| 2988 |
+
"learning_rate": 5.080808080808081e-05,
|
| 2989 |
+
"loss": 1.8564,
|
| 2990 |
+
"step": 497000
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 33.99,
|
| 2994 |
+
"learning_rate": 5.070707070707071e-05,
|
| 2995 |
+
"loss": 1.8517,
|
| 2996 |
+
"step": 498000
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 34.05,
|
| 3000 |
+
"learning_rate": 5.060606060606061e-05,
|
| 3001 |
+
"loss": 1.842,
|
| 3002 |
+
"step": 499000
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 34.12,
|
| 3006 |
+
"learning_rate": 5.050505050505051e-05,
|
| 3007 |
+
"loss": 1.8367,
|
| 3008 |
+
"step": 500000
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 34.19,
|
| 3012 |
+
"learning_rate": 5.040404040404041e-05,
|
| 3013 |
+
"loss": 1.8419,
|
| 3014 |
+
"step": 501000
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 34.26,
|
| 3018 |
+
"learning_rate": 5.030303030303031e-05,
|
| 3019 |
+
"loss": 1.859,
|
| 3020 |
+
"step": 502000
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 34.33,
|
| 3024 |
+
"learning_rate": 5.0202020202020203e-05,
|
| 3025 |
+
"loss": 1.8429,
|
| 3026 |
+
"step": 503000
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 34.4,
|
| 3030 |
+
"learning_rate": 5.01010101010101e-05,
|
| 3031 |
+
"loss": 1.8482,
|
| 3032 |
+
"step": 504000
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 34.46,
|
| 3036 |
+
"learning_rate": 5e-05,
|
| 3037 |
+
"loss": 1.8443,
|
| 3038 |
+
"step": 505000
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 34.53,
|
| 3042 |
+
"learning_rate": 4.98989898989899e-05,
|
| 3043 |
+
"loss": 1.8703,
|
| 3044 |
+
"step": 506000
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 34.6,
|
| 3048 |
+
"learning_rate": 4.97979797979798e-05,
|
| 3049 |
+
"loss": 1.8624,
|
| 3050 |
+
"step": 507000
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 34.67,
|
| 3054 |
+
"learning_rate": 4.9696969696969694e-05,
|
| 3055 |
+
"loss": 1.8535,
|
| 3056 |
+
"step": 508000
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 34.74,
|
| 3060 |
+
"learning_rate": 4.9595959595959594e-05,
|
| 3061 |
+
"loss": 1.853,
|
| 3062 |
+
"step": 509000
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 34.81,
|
| 3066 |
+
"learning_rate": 4.94949494949495e-05,
|
| 3067 |
+
"loss": 1.8532,
|
| 3068 |
+
"step": 510000
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 34.87,
|
| 3072 |
+
"learning_rate": 4.93939393939394e-05,
|
| 3073 |
+
"loss": 1.8566,
|
| 3074 |
+
"step": 511000
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 34.94,
|
| 3078 |
+
"learning_rate": 4.92929292929293e-05,
|
| 3079 |
+
"loss": 1.8706,
|
| 3080 |
+
"step": 512000
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 35.01,
|
| 3084 |
+
"learning_rate": 4.919191919191919e-05,
|
| 3085 |
+
"loss": 1.8669,
|
| 3086 |
+
"step": 513000
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 35.08,
|
| 3090 |
+
"learning_rate": 4.909090909090909e-05,
|
| 3091 |
+
"loss": 1.8427,
|
| 3092 |
+
"step": 514000
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 35.15,
|
| 3096 |
+
"learning_rate": 4.898989898989899e-05,
|
| 3097 |
+
"loss": 1.8566,
|
| 3098 |
+
"step": 515000
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 35.21,
|
| 3102 |
+
"learning_rate": 4.888888888888889e-05,
|
| 3103 |
+
"loss": 1.8456,
|
| 3104 |
+
"step": 516000
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 35.28,
|
| 3108 |
+
"learning_rate": 4.878787878787879e-05,
|
| 3109 |
+
"loss": 1.8461,
|
| 3110 |
+
"step": 517000
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 35.35,
|
| 3114 |
+
"learning_rate": 4.868686868686869e-05,
|
| 3115 |
+
"loss": 1.8392,
|
| 3116 |
+
"step": 518000
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 35.42,
|
| 3120 |
+
"learning_rate": 4.858585858585859e-05,
|
| 3121 |
+
"loss": 1.8446,
|
| 3122 |
+
"step": 519000
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 35.49,
|
| 3126 |
+
"learning_rate": 4.848484848484849e-05,
|
| 3127 |
+
"loss": 1.8494,
|
| 3128 |
+
"step": 520000
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 35.56,
|
| 3132 |
+
"learning_rate": 4.838383838383839e-05,
|
| 3133 |
+
"loss": 1.8426,
|
| 3134 |
+
"step": 521000
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 35.62,
|
| 3138 |
+
"learning_rate": 4.828282828282829e-05,
|
| 3139 |
+
"loss": 1.8472,
|
| 3140 |
+
"step": 522000
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 35.69,
|
| 3144 |
+
"learning_rate": 4.8181818181818186e-05,
|
| 3145 |
+
"loss": 1.8524,
|
| 3146 |
+
"step": 523000
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 35.76,
|
| 3150 |
+
"learning_rate": 4.808080808080808e-05,
|
| 3151 |
+
"loss": 1.8464,
|
| 3152 |
+
"step": 524000
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 35.83,
|
| 3156 |
+
"learning_rate": 4.797979797979798e-05,
|
| 3157 |
+
"loss": 1.8522,
|
| 3158 |
+
"step": 525000
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 35.9,
|
| 3162 |
+
"learning_rate": 4.787878787878788e-05,
|
| 3163 |
+
"loss": 1.852,
|
| 3164 |
+
"step": 526000
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 35.97,
|
| 3168 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 3169 |
+
"loss": 1.8598,
|
| 3170 |
+
"step": 527000
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 36.03,
|
| 3174 |
+
"learning_rate": 4.7676767676767684e-05,
|
| 3175 |
+
"loss": 1.8685,
|
| 3176 |
+
"step": 528000
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 36.1,
|
| 3180 |
+
"learning_rate": 4.7575757575757576e-05,
|
| 3181 |
+
"loss": 1.8371,
|
| 3182 |
+
"step": 529000
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 36.17,
|
| 3186 |
+
"learning_rate": 4.7474747474747476e-05,
|
| 3187 |
+
"loss": 1.8453,
|
| 3188 |
+
"step": 530000
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 36.24,
|
| 3192 |
+
"learning_rate": 4.7373737373737375e-05,
|
| 3193 |
+
"loss": 1.837,
|
| 3194 |
+
"step": 531000
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 36.31,
|
| 3198 |
+
"learning_rate": 4.7272727272727275e-05,
|
| 3199 |
+
"loss": 1.8441,
|
| 3200 |
+
"step": 532000
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 36.37,
|
| 3204 |
+
"learning_rate": 4.7171717171717174e-05,
|
| 3205 |
+
"loss": 1.8605,
|
| 3206 |
+
"step": 533000
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 36.44,
|
| 3210 |
+
"learning_rate": 4.7070707070707074e-05,
|
| 3211 |
+
"loss": 1.852,
|
| 3212 |
+
"step": 534000
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 36.51,
|
| 3216 |
+
"learning_rate": 4.696969696969697e-05,
|
| 3217 |
+
"loss": 1.862,
|
| 3218 |
+
"step": 535000
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 36.58,
|
| 3222 |
+
"learning_rate": 4.686868686868687e-05,
|
| 3223 |
+
"loss": 1.8512,
|
| 3224 |
+
"step": 536000
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 36.65,
|
| 3228 |
+
"learning_rate": 4.676767676767677e-05,
|
| 3229 |
+
"loss": 1.8574,
|
| 3230 |
+
"step": 537000
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 36.72,
|
| 3234 |
+
"learning_rate": 4.666666666666667e-05,
|
| 3235 |
+
"loss": 1.8617,
|
| 3236 |
+
"step": 538000
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 36.78,
|
| 3240 |
+
"learning_rate": 4.656565656565657e-05,
|
| 3241 |
+
"loss": 1.8561,
|
| 3242 |
+
"step": 539000
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 36.85,
|
| 3246 |
+
"learning_rate": 4.6464646464646464e-05,
|
| 3247 |
+
"loss": 1.8459,
|
| 3248 |
+
"step": 540000
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 36.92,
|
| 3252 |
+
"learning_rate": 4.636363636363636e-05,
|
| 3253 |
+
"loss": 1.8547,
|
| 3254 |
+
"step": 541000
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 36.99,
|
| 3258 |
+
"learning_rate": 4.626262626262626e-05,
|
| 3259 |
+
"loss": 1.8442,
|
| 3260 |
+
"step": 542000
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 37.06,
|
| 3264 |
+
"learning_rate": 4.616161616161616e-05,
|
| 3265 |
+
"loss": 1.8388,
|
| 3266 |
+
"step": 543000
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 37.13,
|
| 3270 |
+
"learning_rate": 4.606060606060607e-05,
|
| 3271 |
+
"loss": 1.8371,
|
| 3272 |
+
"step": 544000
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 37.19,
|
| 3276 |
+
"learning_rate": 4.595959595959596e-05,
|
| 3277 |
+
"loss": 1.8328,
|
| 3278 |
+
"step": 545000
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 37.26,
|
| 3282 |
+
"learning_rate": 4.585858585858586e-05,
|
| 3283 |
+
"loss": 1.831,
|
| 3284 |
+
"step": 546000
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 37.33,
|
| 3288 |
+
"learning_rate": 4.575757575757576e-05,
|
| 3289 |
+
"loss": 1.8389,
|
| 3290 |
+
"step": 547000
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 37.4,
|
| 3294 |
+
"learning_rate": 4.565656565656566e-05,
|
| 3295 |
+
"loss": 1.8457,
|
| 3296 |
+
"step": 548000
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 37.47,
|
| 3300 |
+
"learning_rate": 4.555555555555556e-05,
|
| 3301 |
+
"loss": 1.8297,
|
| 3302 |
+
"step": 549000
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 37.53,
|
| 3306 |
+
"learning_rate": 4.545454545454546e-05,
|
| 3307 |
+
"loss": 1.8298,
|
| 3308 |
+
"step": 550000
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 37.6,
|
| 3312 |
+
"learning_rate": 4.535353535353535e-05,
|
| 3313 |
+
"loss": 1.8342,
|
| 3314 |
+
"step": 551000
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 37.67,
|
| 3318 |
+
"learning_rate": 4.525252525252526e-05,
|
| 3319 |
+
"loss": 1.8237,
|
| 3320 |
+
"step": 552000
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 37.74,
|
| 3324 |
+
"learning_rate": 4.515151515151516e-05,
|
| 3325 |
+
"loss": 1.8435,
|
| 3326 |
+
"step": 553000
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 37.81,
|
| 3330 |
+
"learning_rate": 4.5050505050505056e-05,
|
| 3331 |
+
"loss": 1.8286,
|
| 3332 |
+
"step": 554000
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 37.88,
|
| 3336 |
+
"learning_rate": 4.494949494949495e-05,
|
| 3337 |
+
"loss": 1.8331,
|
| 3338 |
+
"step": 555000
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 37.94,
|
| 3342 |
+
"learning_rate": 4.484848484848485e-05,
|
| 3343 |
+
"loss": 1.8346,
|
| 3344 |
+
"step": 556000
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 38.01,
|
| 3348 |
+
"learning_rate": 4.474747474747475e-05,
|
| 3349 |
+
"loss": 1.8207,
|
| 3350 |
+
"step": 557000
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 38.08,
|
| 3354 |
+
"learning_rate": 4.464646464646465e-05,
|
| 3355 |
+
"loss": 1.8037,
|
| 3356 |
+
"step": 558000
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 38.15,
|
| 3360 |
+
"learning_rate": 4.454545454545455e-05,
|
| 3361 |
+
"loss": 1.8067,
|
| 3362 |
+
"step": 559000
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 38.22,
|
| 3366 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 3367 |
+
"loss": 1.7991,
|
| 3368 |
+
"step": 560000
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 38.29,
|
| 3372 |
+
"learning_rate": 4.4343434343434346e-05,
|
| 3373 |
+
"loss": 1.799,
|
| 3374 |
+
"step": 561000
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 38.35,
|
| 3378 |
+
"learning_rate": 4.4242424242424246e-05,
|
| 3379 |
+
"loss": 1.8069,
|
| 3380 |
+
"step": 562000
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 38.42,
|
| 3384 |
+
"learning_rate": 4.4141414141414145e-05,
|
| 3385 |
+
"loss": 1.8146,
|
| 3386 |
+
"step": 563000
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 38.49,
|
| 3390 |
+
"learning_rate": 4.4040404040404044e-05,
|
| 3391 |
+
"loss": 1.8102,
|
| 3392 |
+
"step": 564000
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 38.56,
|
| 3396 |
+
"learning_rate": 4.3939393939393944e-05,
|
| 3397 |
+
"loss": 1.8188,
|
| 3398 |
+
"step": 565000
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 38.63,
|
| 3402 |
+
"learning_rate": 4.383838383838384e-05,
|
| 3403 |
+
"loss": 1.813,
|
| 3404 |
+
"step": 566000
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 38.7,
|
| 3408 |
+
"learning_rate": 4.3737373737373736e-05,
|
| 3409 |
+
"loss": 1.8334,
|
| 3410 |
+
"step": 567000
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 38.76,
|
| 3414 |
+
"learning_rate": 4.3636363636363636e-05,
|
| 3415 |
+
"loss": 1.8117,
|
| 3416 |
+
"step": 568000
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 38.83,
|
| 3420 |
+
"learning_rate": 4.3535353535353535e-05,
|
| 3421 |
+
"loss": 1.804,
|
| 3422 |
+
"step": 569000
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 38.9,
|
| 3426 |
+
"learning_rate": 4.343434343434344e-05,
|
| 3427 |
+
"loss": 1.8222,
|
| 3428 |
+
"step": 570000
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 38.97,
|
| 3432 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 3433 |
+
"loss": 1.816,
|
| 3434 |
+
"step": 571000
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 39.04,
|
| 3438 |
+
"learning_rate": 4.3232323232323234e-05,
|
| 3439 |
+
"loss": 1.8037,
|
| 3440 |
+
"step": 572000
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 39.1,
|
| 3444 |
+
"learning_rate": 4.313131313131313e-05,
|
| 3445 |
+
"loss": 1.796,
|
| 3446 |
+
"step": 573000
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 39.17,
|
| 3450 |
+
"learning_rate": 4.303030303030303e-05,
|
| 3451 |
+
"loss": 1.8026,
|
| 3452 |
+
"step": 574000
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 39.24,
|
| 3456 |
+
"learning_rate": 4.292929292929293e-05,
|
| 3457 |
+
"loss": 1.8142,
|
| 3458 |
+
"step": 575000
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 39.31,
|
| 3462 |
+
"learning_rate": 4.282828282828283e-05,
|
| 3463 |
+
"loss": 1.8008,
|
| 3464 |
+
"step": 576000
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 39.38,
|
| 3468 |
+
"learning_rate": 4.2727272727272724e-05,
|
| 3469 |
+
"loss": 1.8023,
|
| 3470 |
+
"step": 577000
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 39.45,
|
| 3474 |
+
"learning_rate": 4.262626262626263e-05,
|
| 3475 |
+
"loss": 1.8107,
|
| 3476 |
+
"step": 578000
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 39.51,
|
| 3480 |
+
"learning_rate": 4.252525252525253e-05,
|
| 3481 |
+
"loss": 1.8136,
|
| 3482 |
+
"step": 579000
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 39.58,
|
| 3486 |
+
"learning_rate": 4.242424242424243e-05,
|
| 3487 |
+
"loss": 1.8202,
|
| 3488 |
+
"step": 580000
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 39.65,
|
| 3492 |
+
"learning_rate": 4.232323232323233e-05,
|
| 3493 |
+
"loss": 1.8042,
|
| 3494 |
+
"step": 581000
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 39.72,
|
| 3498 |
+
"learning_rate": 4.222222222222222e-05,
|
| 3499 |
+
"loss": 1.8204,
|
| 3500 |
+
"step": 582000
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 39.79,
|
| 3504 |
+
"learning_rate": 4.212121212121212e-05,
|
| 3505 |
+
"loss": 1.8157,
|
| 3506 |
+
"step": 583000
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 39.86,
|
| 3510 |
+
"learning_rate": 4.202020202020202e-05,
|
| 3511 |
+
"loss": 1.8028,
|
| 3512 |
+
"step": 584000
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 39.92,
|
| 3516 |
+
"learning_rate": 4.191919191919192e-05,
|
| 3517 |
+
"loss": 1.8196,
|
| 3518 |
+
"step": 585000
|
| 3519 |
+
}
|
| 3520 |
+
],
|
| 3521 |
+
"max_steps": 1000000,
|
| 3522 |
+
"num_train_epochs": 69,
|
| 3523 |
+
"total_flos": 7.31875459270527e+17,
|
| 3524 |
+
"trial_name": null,
|
| 3525 |
+
"trial_params": null
|
| 3526 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6abbe519bc1f98b67999b22e779d738f3a929267331856a43c2679bfbdc9079
|
| 3 |
+
size 2671
|