Upload 7 files
Browse files- config.json +24 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2424 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 12,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.18.0",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 50000
|
24 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78f0588f987f1944536b513378c8a7f3cfadb50f715b3f21fe99cd34a5e742eb
|
3 |
+
size 996060569
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76afbf0ad54e517e22fc3e2119a33b33d6ed1c73d131541cb3635ae3c220ee8e
|
3 |
+
size 498043179
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ea9684e3fb5f6a59c19b5b4c8328ee6cae6e625f1fd728c7254b05c7f2b0d7e
|
3 |
+
size 15523
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95b61338c78fe14431c26ae634649ae774aeeb381ad7b30f6f9118bcb34277c8
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,2424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 116.47855530474041,
|
5 |
+
"global_step": 774000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.68,
|
12 |
+
"learning_rate": 4.988713318284425e-05,
|
13 |
+
"loss": 6.9537,
|
14 |
+
"step": 4500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.68,
|
18 |
+
"eval_loss": 6.797055244445801,
|
19 |
+
"eval_runtime": 118.7849,
|
20 |
+
"eval_samples_per_second": 103.456,
|
21 |
+
"eval_steps_per_second": 6.474,
|
22 |
+
"step": 4500
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.35,
|
26 |
+
"learning_rate": 4.9774266365688486e-05,
|
27 |
+
"loss": 6.6451,
|
28 |
+
"step": 9000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.35,
|
32 |
+
"eval_loss": 6.689827919006348,
|
33 |
+
"eval_runtime": 118.3538,
|
34 |
+
"eval_samples_per_second": 103.833,
|
35 |
+
"eval_steps_per_second": 6.497,
|
36 |
+
"step": 9000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.03,
|
40 |
+
"learning_rate": 4.966139954853273e-05,
|
41 |
+
"loss": 6.5518,
|
42 |
+
"step": 13500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.03,
|
46 |
+
"eval_loss": 6.630918979644775,
|
47 |
+
"eval_runtime": 118.3302,
|
48 |
+
"eval_samples_per_second": 103.853,
|
49 |
+
"eval_steps_per_second": 6.499,
|
50 |
+
"step": 13500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.71,
|
54 |
+
"learning_rate": 4.954853273137698e-05,
|
55 |
+
"loss": 6.4713,
|
56 |
+
"step": 18000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.71,
|
60 |
+
"eval_loss": 6.497533798217773,
|
61 |
+
"eval_runtime": 118.3323,
|
62 |
+
"eval_samples_per_second": 103.852,
|
63 |
+
"eval_steps_per_second": 6.499,
|
64 |
+
"step": 18000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.39,
|
68 |
+
"learning_rate": 4.9435665914221216e-05,
|
69 |
+
"loss": 6.0827,
|
70 |
+
"step": 22500
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 3.39,
|
74 |
+
"eval_loss": 5.684892654418945,
|
75 |
+
"eval_runtime": 118.3572,
|
76 |
+
"eval_samples_per_second": 103.83,
|
77 |
+
"eval_steps_per_second": 6.497,
|
78 |
+
"step": 22500
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 4.06,
|
82 |
+
"learning_rate": 4.932279909706546e-05,
|
83 |
+
"loss": 5.0663,
|
84 |
+
"step": 27000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 4.06,
|
88 |
+
"eval_loss": 4.617100715637207,
|
89 |
+
"eval_runtime": 118.3432,
|
90 |
+
"eval_samples_per_second": 103.842,
|
91 |
+
"eval_steps_per_second": 6.498,
|
92 |
+
"step": 27000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 4.74,
|
96 |
+
"learning_rate": 4.920993227990971e-05,
|
97 |
+
"loss": 4.3025,
|
98 |
+
"step": 31500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 4.74,
|
102 |
+
"eval_loss": 4.159748077392578,
|
103 |
+
"eval_runtime": 118.3398,
|
104 |
+
"eval_samples_per_second": 103.845,
|
105 |
+
"eval_steps_per_second": 6.498,
|
106 |
+
"step": 31500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 5.42,
|
110 |
+
"learning_rate": 4.909706546275395e-05,
|
111 |
+
"loss": 3.9214,
|
112 |
+
"step": 36000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 5.42,
|
116 |
+
"eval_loss": 3.8544375896453857,
|
117 |
+
"eval_runtime": 118.3517,
|
118 |
+
"eval_samples_per_second": 103.835,
|
119 |
+
"eval_steps_per_second": 6.498,
|
120 |
+
"step": 36000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 6.09,
|
124 |
+
"learning_rate": 4.89841986455982e-05,
|
125 |
+
"loss": 3.6779,
|
126 |
+
"step": 40500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.09,
|
130 |
+
"eval_loss": 3.664363384246826,
|
131 |
+
"eval_runtime": 118.2895,
|
132 |
+
"eval_samples_per_second": 103.889,
|
133 |
+
"eval_steps_per_second": 6.501,
|
134 |
+
"step": 40500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 6.77,
|
138 |
+
"learning_rate": 4.887133182844244e-05,
|
139 |
+
"loss": 3.502,
|
140 |
+
"step": 45000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 6.77,
|
144 |
+
"eval_loss": 3.5141005516052246,
|
145 |
+
"eval_runtime": 118.2983,
|
146 |
+
"eval_samples_per_second": 103.881,
|
147 |
+
"eval_steps_per_second": 6.501,
|
148 |
+
"step": 45000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 7.45,
|
152 |
+
"learning_rate": 4.875846501128669e-05,
|
153 |
+
"loss": 3.366,
|
154 |
+
"step": 49500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 7.45,
|
158 |
+
"eval_loss": 3.4036142826080322,
|
159 |
+
"eval_runtime": 118.3098,
|
160 |
+
"eval_samples_per_second": 103.871,
|
161 |
+
"eval_steps_per_second": 6.5,
|
162 |
+
"step": 49500
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 8.13,
|
166 |
+
"learning_rate": 4.864559819413093e-05,
|
167 |
+
"loss": 3.2695,
|
168 |
+
"step": 54000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 8.13,
|
172 |
+
"eval_loss": 3.321831226348877,
|
173 |
+
"eval_runtime": 118.3723,
|
174 |
+
"eval_samples_per_second": 103.817,
|
175 |
+
"eval_steps_per_second": 6.496,
|
176 |
+
"step": 54000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 8.8,
|
180 |
+
"learning_rate": 4.853273137697517e-05,
|
181 |
+
"loss": 3.1758,
|
182 |
+
"step": 58500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 8.8,
|
186 |
+
"eval_loss": 3.2432045936584473,
|
187 |
+
"eval_runtime": 118.355,
|
188 |
+
"eval_samples_per_second": 103.832,
|
189 |
+
"eval_steps_per_second": 6.497,
|
190 |
+
"step": 58500
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 9.48,
|
194 |
+
"learning_rate": 4.841986455981942e-05,
|
195 |
+
"loss": 3.1008,
|
196 |
+
"step": 63000
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 9.48,
|
200 |
+
"eval_loss": 3.186511754989624,
|
201 |
+
"eval_runtime": 118.3602,
|
202 |
+
"eval_samples_per_second": 103.827,
|
203 |
+
"eval_steps_per_second": 6.497,
|
204 |
+
"step": 63000
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 10.16,
|
208 |
+
"learning_rate": 4.830699774266366e-05,
|
209 |
+
"loss": 3.0354,
|
210 |
+
"step": 67500
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 10.16,
|
214 |
+
"eval_loss": 3.115652561187744,
|
215 |
+
"eval_runtime": 118.3431,
|
216 |
+
"eval_samples_per_second": 103.842,
|
217 |
+
"eval_steps_per_second": 6.498,
|
218 |
+
"step": 67500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 10.84,
|
222 |
+
"learning_rate": 4.81941309255079e-05,
|
223 |
+
"loss": 2.9798,
|
224 |
+
"step": 72000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 10.84,
|
228 |
+
"eval_loss": 3.0752041339874268,
|
229 |
+
"eval_runtime": 118.2033,
|
230 |
+
"eval_samples_per_second": 103.965,
|
231 |
+
"eval_steps_per_second": 6.506,
|
232 |
+
"step": 72000
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 11.51,
|
236 |
+
"learning_rate": 4.808126410835215e-05,
|
237 |
+
"loss": 2.9252,
|
238 |
+
"step": 76500
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 11.51,
|
242 |
+
"eval_loss": 3.028315305709839,
|
243 |
+
"eval_runtime": 118.2129,
|
244 |
+
"eval_samples_per_second": 103.956,
|
245 |
+
"eval_steps_per_second": 6.505,
|
246 |
+
"step": 76500
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 12.19,
|
250 |
+
"learning_rate": 4.796839729119639e-05,
|
251 |
+
"loss": 2.881,
|
252 |
+
"step": 81000
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 12.19,
|
256 |
+
"eval_loss": 2.9871439933776855,
|
257 |
+
"eval_runtime": 118.1982,
|
258 |
+
"eval_samples_per_second": 103.969,
|
259 |
+
"eval_steps_per_second": 6.506,
|
260 |
+
"step": 81000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 12.87,
|
264 |
+
"learning_rate": 4.785553047404063e-05,
|
265 |
+
"loss": 2.8366,
|
266 |
+
"step": 85500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 12.87,
|
270 |
+
"eval_loss": 2.9422881603240967,
|
271 |
+
"eval_runtime": 118.1796,
|
272 |
+
"eval_samples_per_second": 103.986,
|
273 |
+
"eval_steps_per_second": 6.507,
|
274 |
+
"step": 85500
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 13.54,
|
278 |
+
"learning_rate": 4.774266365688488e-05,
|
279 |
+
"loss": 2.7917,
|
280 |
+
"step": 90000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 13.54,
|
284 |
+
"eval_loss": 2.9027907848358154,
|
285 |
+
"eval_runtime": 118.1933,
|
286 |
+
"eval_samples_per_second": 103.974,
|
287 |
+
"eval_steps_per_second": 6.506,
|
288 |
+
"step": 90000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 14.22,
|
292 |
+
"learning_rate": 4.762979683972912e-05,
|
293 |
+
"loss": 2.7592,
|
294 |
+
"step": 94500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 14.22,
|
298 |
+
"eval_loss": 2.8720462322235107,
|
299 |
+
"eval_runtime": 118.2133,
|
300 |
+
"eval_samples_per_second": 103.956,
|
301 |
+
"eval_steps_per_second": 6.505,
|
302 |
+
"step": 94500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 14.9,
|
306 |
+
"learning_rate": 4.751693002257336e-05,
|
307 |
+
"loss": 2.7278,
|
308 |
+
"step": 99000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 14.9,
|
312 |
+
"eval_loss": 2.8500328063964844,
|
313 |
+
"eval_runtime": 118.2044,
|
314 |
+
"eval_samples_per_second": 103.964,
|
315 |
+
"eval_steps_per_second": 6.506,
|
316 |
+
"step": 99000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 15.58,
|
320 |
+
"learning_rate": 4.740406320541761e-05,
|
321 |
+
"loss": 2.693,
|
322 |
+
"step": 103500
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 15.58,
|
326 |
+
"eval_loss": 2.817178249359131,
|
327 |
+
"eval_runtime": 118.1867,
|
328 |
+
"eval_samples_per_second": 103.98,
|
329 |
+
"eval_steps_per_second": 6.507,
|
330 |
+
"step": 103500
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 16.25,
|
334 |
+
"learning_rate": 4.729119638826185e-05,
|
335 |
+
"loss": 2.6645,
|
336 |
+
"step": 108000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 16.25,
|
340 |
+
"eval_loss": 2.786304235458374,
|
341 |
+
"eval_runtime": 118.2219,
|
342 |
+
"eval_samples_per_second": 103.949,
|
343 |
+
"eval_steps_per_second": 6.505,
|
344 |
+
"step": 108000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 16.93,
|
348 |
+
"learning_rate": 4.71783295711061e-05,
|
349 |
+
"loss": 2.6361,
|
350 |
+
"step": 112500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 16.93,
|
354 |
+
"eval_loss": 2.770569324493408,
|
355 |
+
"eval_runtime": 118.2234,
|
356 |
+
"eval_samples_per_second": 103.947,
|
357 |
+
"eval_steps_per_second": 6.505,
|
358 |
+
"step": 112500
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 17.61,
|
362 |
+
"learning_rate": 4.706546275395034e-05,
|
363 |
+
"loss": 2.6083,
|
364 |
+
"step": 117000
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 17.61,
|
368 |
+
"eval_loss": 2.7391059398651123,
|
369 |
+
"eval_runtime": 118.2576,
|
370 |
+
"eval_samples_per_second": 103.917,
|
371 |
+
"eval_steps_per_second": 6.503,
|
372 |
+
"step": 117000
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 18.28,
|
376 |
+
"learning_rate": 4.695259593679459e-05,
|
377 |
+
"loss": 2.5847,
|
378 |
+
"step": 121500
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 18.28,
|
382 |
+
"eval_loss": 2.718665838241577,
|
383 |
+
"eval_runtime": 118.2124,
|
384 |
+
"eval_samples_per_second": 103.957,
|
385 |
+
"eval_steps_per_second": 6.505,
|
386 |
+
"step": 121500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 18.96,
|
390 |
+
"learning_rate": 4.6839729119638834e-05,
|
391 |
+
"loss": 2.5619,
|
392 |
+
"step": 126000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 18.96,
|
396 |
+
"eval_loss": 2.7032158374786377,
|
397 |
+
"eval_runtime": 118.2283,
|
398 |
+
"eval_samples_per_second": 103.943,
|
399 |
+
"eval_steps_per_second": 6.504,
|
400 |
+
"step": 126000
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 19.64,
|
404 |
+
"learning_rate": 4.672686230248307e-05,
|
405 |
+
"loss": 2.5368,
|
406 |
+
"step": 130500
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 19.64,
|
410 |
+
"eval_loss": 2.6911468505859375,
|
411 |
+
"eval_runtime": 118.3184,
|
412 |
+
"eval_samples_per_second": 103.864,
|
413 |
+
"eval_steps_per_second": 6.499,
|
414 |
+
"step": 130500
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 20.32,
|
418 |
+
"learning_rate": 4.661399548532732e-05,
|
419 |
+
"loss": 2.5203,
|
420 |
+
"step": 135000
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 20.32,
|
424 |
+
"eval_loss": 2.666966676712036,
|
425 |
+
"eval_runtime": 118.3095,
|
426 |
+
"eval_samples_per_second": 103.872,
|
427 |
+
"eval_steps_per_second": 6.5,
|
428 |
+
"step": 135000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 20.99,
|
432 |
+
"learning_rate": 4.6501128668171564e-05,
|
433 |
+
"loss": 2.4997,
|
434 |
+
"step": 139500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 20.99,
|
438 |
+
"eval_loss": 2.6472320556640625,
|
439 |
+
"eval_runtime": 118.1415,
|
440 |
+
"eval_samples_per_second": 104.019,
|
441 |
+
"eval_steps_per_second": 6.509,
|
442 |
+
"step": 139500
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 21.67,
|
446 |
+
"learning_rate": 4.63882618510158e-05,
|
447 |
+
"loss": 2.4755,
|
448 |
+
"step": 144000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 21.67,
|
452 |
+
"eval_loss": 2.6281678676605225,
|
453 |
+
"eval_runtime": 118.147,
|
454 |
+
"eval_samples_per_second": 104.014,
|
455 |
+
"eval_steps_per_second": 6.509,
|
456 |
+
"step": 144000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 22.35,
|
460 |
+
"learning_rate": 4.627539503386005e-05,
|
461 |
+
"loss": 2.4593,
|
462 |
+
"step": 148500
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 22.35,
|
466 |
+
"eval_loss": 2.6077518463134766,
|
467 |
+
"eval_runtime": 118.4066,
|
468 |
+
"eval_samples_per_second": 103.786,
|
469 |
+
"eval_steps_per_second": 6.495,
|
470 |
+
"step": 148500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 23.02,
|
474 |
+
"learning_rate": 4.616252821670429e-05,
|
475 |
+
"loss": 2.4468,
|
476 |
+
"step": 153000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 23.02,
|
480 |
+
"eval_loss": 2.60119366645813,
|
481 |
+
"eval_runtime": 118.2017,
|
482 |
+
"eval_samples_per_second": 103.966,
|
483 |
+
"eval_steps_per_second": 6.506,
|
484 |
+
"step": 153000
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 23.7,
|
488 |
+
"learning_rate": 4.604966139954853e-05,
|
489 |
+
"loss": 2.4243,
|
490 |
+
"step": 157500
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 23.7,
|
494 |
+
"eval_loss": 2.583709239959717,
|
495 |
+
"eval_runtime": 118.0992,
|
496 |
+
"eval_samples_per_second": 104.057,
|
497 |
+
"eval_steps_per_second": 6.511,
|
498 |
+
"step": 157500
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 24.38,
|
502 |
+
"learning_rate": 4.593679458239278e-05,
|
503 |
+
"loss": 2.4093,
|
504 |
+
"step": 162000
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 24.38,
|
508 |
+
"eval_loss": 2.5716421604156494,
|
509 |
+
"eval_runtime": 118.1155,
|
510 |
+
"eval_samples_per_second": 104.042,
|
511 |
+
"eval_steps_per_second": 6.511,
|
512 |
+
"step": 162000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 25.06,
|
516 |
+
"learning_rate": 4.582392776523702e-05,
|
517 |
+
"loss": 2.396,
|
518 |
+
"step": 166500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 25.06,
|
522 |
+
"eval_loss": 2.561039686203003,
|
523 |
+
"eval_runtime": 118.1545,
|
524 |
+
"eval_samples_per_second": 104.008,
|
525 |
+
"eval_steps_per_second": 6.508,
|
526 |
+
"step": 166500
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 25.73,
|
530 |
+
"learning_rate": 4.571106094808127e-05,
|
531 |
+
"loss": 2.3764,
|
532 |
+
"step": 171000
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 25.73,
|
536 |
+
"eval_loss": 2.543470859527588,
|
537 |
+
"eval_runtime": 118.1796,
|
538 |
+
"eval_samples_per_second": 103.986,
|
539 |
+
"eval_steps_per_second": 6.507,
|
540 |
+
"step": 171000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 26.41,
|
544 |
+
"learning_rate": 4.559819413092551e-05,
|
545 |
+
"loss": 2.3623,
|
546 |
+
"step": 175500
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 26.41,
|
550 |
+
"eval_loss": 2.5341155529022217,
|
551 |
+
"eval_runtime": 118.1214,
|
552 |
+
"eval_samples_per_second": 104.037,
|
553 |
+
"eval_steps_per_second": 6.51,
|
554 |
+
"step": 175500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 27.09,
|
558 |
+
"learning_rate": 4.548532731376975e-05,
|
559 |
+
"loss": 2.3529,
|
560 |
+
"step": 180000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 27.09,
|
564 |
+
"eval_loss": 2.5200819969177246,
|
565 |
+
"eval_runtime": 118.324,
|
566 |
+
"eval_samples_per_second": 103.859,
|
567 |
+
"eval_steps_per_second": 6.499,
|
568 |
+
"step": 180000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 27.77,
|
572 |
+
"learning_rate": 4.5372460496614e-05,
|
573 |
+
"loss": 2.3393,
|
574 |
+
"step": 184500
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 27.77,
|
578 |
+
"eval_loss": 2.5085155963897705,
|
579 |
+
"eval_runtime": 118.3431,
|
580 |
+
"eval_samples_per_second": 103.842,
|
581 |
+
"eval_steps_per_second": 6.498,
|
582 |
+
"step": 184500
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 28.44,
|
586 |
+
"learning_rate": 4.525959367945824e-05,
|
587 |
+
"loss": 2.3247,
|
588 |
+
"step": 189000
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 28.44,
|
592 |
+
"eval_loss": 2.5002756118774414,
|
593 |
+
"eval_runtime": 118.3427,
|
594 |
+
"eval_samples_per_second": 103.842,
|
595 |
+
"eval_steps_per_second": 6.498,
|
596 |
+
"step": 189000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 29.12,
|
600 |
+
"learning_rate": 4.514672686230249e-05,
|
601 |
+
"loss": 2.3127,
|
602 |
+
"step": 193500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 29.12,
|
606 |
+
"eval_loss": 2.4838666915893555,
|
607 |
+
"eval_runtime": 118.3361,
|
608 |
+
"eval_samples_per_second": 103.848,
|
609 |
+
"eval_steps_per_second": 6.498,
|
610 |
+
"step": 193500
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 29.8,
|
614 |
+
"learning_rate": 4.5033860045146734e-05,
|
615 |
+
"loss": 2.3006,
|
616 |
+
"step": 198000
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 29.8,
|
620 |
+
"eval_loss": 2.480976104736328,
|
621 |
+
"eval_runtime": 118.3346,
|
622 |
+
"eval_samples_per_second": 103.85,
|
623 |
+
"eval_steps_per_second": 6.499,
|
624 |
+
"step": 198000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 30.47,
|
628 |
+
"learning_rate": 4.492099322799097e-05,
|
629 |
+
"loss": 2.2896,
|
630 |
+
"step": 202500
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 30.47,
|
634 |
+
"eval_loss": 2.4641942977905273,
|
635 |
+
"eval_runtime": 118.3398,
|
636 |
+
"eval_samples_per_second": 103.845,
|
637 |
+
"eval_steps_per_second": 6.498,
|
638 |
+
"step": 202500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 31.15,
|
642 |
+
"learning_rate": 4.480812641083522e-05,
|
643 |
+
"loss": 2.2789,
|
644 |
+
"step": 207000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 31.15,
|
648 |
+
"eval_loss": 2.4657058715820312,
|
649 |
+
"eval_runtime": 118.3281,
|
650 |
+
"eval_samples_per_second": 103.855,
|
651 |
+
"eval_steps_per_second": 6.499,
|
652 |
+
"step": 207000
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 31.83,
|
656 |
+
"learning_rate": 4.4695259593679463e-05,
|
657 |
+
"loss": 2.2665,
|
658 |
+
"step": 211500
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 31.83,
|
662 |
+
"eval_loss": 2.4447216987609863,
|
663 |
+
"eval_runtime": 118.3432,
|
664 |
+
"eval_samples_per_second": 103.842,
|
665 |
+
"eval_steps_per_second": 6.498,
|
666 |
+
"step": 211500
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 32.51,
|
670 |
+
"learning_rate": 4.45823927765237e-05,
|
671 |
+
"loss": 2.2545,
|
672 |
+
"step": 216000
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 32.51,
|
676 |
+
"eval_loss": 2.4484477043151855,
|
677 |
+
"eval_runtime": 118.3442,
|
678 |
+
"eval_samples_per_second": 103.841,
|
679 |
+
"eval_steps_per_second": 6.498,
|
680 |
+
"step": 216000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 33.18,
|
684 |
+
"learning_rate": 4.446952595936795e-05,
|
685 |
+
"loss": 2.2446,
|
686 |
+
"step": 220500
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 33.18,
|
690 |
+
"eval_loss": 2.4324302673339844,
|
691 |
+
"eval_runtime": 118.3492,
|
692 |
+
"eval_samples_per_second": 103.837,
|
693 |
+
"eval_steps_per_second": 6.498,
|
694 |
+
"step": 220500
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 33.86,
|
698 |
+
"learning_rate": 4.435665914221219e-05,
|
699 |
+
"loss": 2.2352,
|
700 |
+
"step": 225000
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 33.86,
|
704 |
+
"eval_loss": 2.426417827606201,
|
705 |
+
"eval_runtime": 118.3545,
|
706 |
+
"eval_samples_per_second": 103.832,
|
707 |
+
"eval_steps_per_second": 6.497,
|
708 |
+
"step": 225000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 34.54,
|
712 |
+
"learning_rate": 4.424379232505644e-05,
|
713 |
+
"loss": 2.2218,
|
714 |
+
"step": 229500
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 34.54,
|
718 |
+
"eval_loss": 2.4175431728363037,
|
719 |
+
"eval_runtime": 121.4712,
|
720 |
+
"eval_samples_per_second": 101.168,
|
721 |
+
"eval_steps_per_second": 6.331,
|
722 |
+
"step": 229500
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 35.21,
|
726 |
+
"learning_rate": 4.413092550790068e-05,
|
727 |
+
"loss": 2.2153,
|
728 |
+
"step": 234000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 35.21,
|
732 |
+
"eval_loss": 2.4122180938720703,
|
733 |
+
"eval_runtime": 121.3685,
|
734 |
+
"eval_samples_per_second": 101.254,
|
735 |
+
"eval_steps_per_second": 6.336,
|
736 |
+
"step": 234000
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 35.89,
|
740 |
+
"learning_rate": 4.401805869074492e-05,
|
741 |
+
"loss": 2.206,
|
742 |
+
"step": 238500
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 35.89,
|
746 |
+
"eval_loss": 2.392340660095215,
|
747 |
+
"eval_runtime": 121.4694,
|
748 |
+
"eval_samples_per_second": 101.169,
|
749 |
+
"eval_steps_per_second": 6.331,
|
750 |
+
"step": 238500
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 36.57,
|
754 |
+
"learning_rate": 4.390519187358917e-05,
|
755 |
+
"loss": 2.1931,
|
756 |
+
"step": 243000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 36.57,
|
760 |
+
"eval_loss": 2.386526584625244,
|
761 |
+
"eval_runtime": 121.4241,
|
762 |
+
"eval_samples_per_second": 101.207,
|
763 |
+
"eval_steps_per_second": 6.333,
|
764 |
+
"step": 243000
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 37.25,
|
768 |
+
"learning_rate": 4.379232505643341e-05,
|
769 |
+
"loss": 2.1876,
|
770 |
+
"step": 247500
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 37.25,
|
774 |
+
"eval_loss": 2.383101224899292,
|
775 |
+
"eval_runtime": 121.3529,
|
776 |
+
"eval_samples_per_second": 101.267,
|
777 |
+
"eval_steps_per_second": 6.337,
|
778 |
+
"step": 247500
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 37.92,
|
782 |
+
"learning_rate": 4.367945823927765e-05,
|
783 |
+
"loss": 2.1817,
|
784 |
+
"step": 252000
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 37.92,
|
788 |
+
"eval_loss": 2.3782711029052734,
|
789 |
+
"eval_runtime": 121.4029,
|
790 |
+
"eval_samples_per_second": 101.225,
|
791 |
+
"eval_steps_per_second": 6.334,
|
792 |
+
"step": 252000
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 38.6,
|
796 |
+
"learning_rate": 4.35665914221219e-05,
|
797 |
+
"loss": 2.1661,
|
798 |
+
"step": 256500
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 38.6,
|
802 |
+
"eval_loss": 2.3761754035949707,
|
803 |
+
"eval_runtime": 121.5223,
|
804 |
+
"eval_samples_per_second": 101.126,
|
805 |
+
"eval_steps_per_second": 6.328,
|
806 |
+
"step": 256500
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 39.28,
|
810 |
+
"learning_rate": 4.3453724604966136e-05,
|
811 |
+
"loss": 2.1635,
|
812 |
+
"step": 261000
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 39.28,
|
816 |
+
"eval_loss": 2.365755319595337,
|
817 |
+
"eval_runtime": 121.4762,
|
818 |
+
"eval_samples_per_second": 101.164,
|
819 |
+
"eval_steps_per_second": 6.33,
|
820 |
+
"step": 261000
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 39.95,
|
824 |
+
"learning_rate": 4.334085778781038e-05,
|
825 |
+
"loss": 2.1533,
|
826 |
+
"step": 265500
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 39.95,
|
830 |
+
"eval_loss": 2.359434127807617,
|
831 |
+
"eval_runtime": 121.2612,
|
832 |
+
"eval_samples_per_second": 101.343,
|
833 |
+
"eval_steps_per_second": 6.342,
|
834 |
+
"step": 265500
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 40.63,
|
838 |
+
"learning_rate": 4.322799097065463e-05,
|
839 |
+
"loss": 2.1444,
|
840 |
+
"step": 270000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 40.63,
|
844 |
+
"eval_loss": 2.3534085750579834,
|
845 |
+
"eval_runtime": 121.4588,
|
846 |
+
"eval_samples_per_second": 101.178,
|
847 |
+
"eval_steps_per_second": 6.331,
|
848 |
+
"step": 270000
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 41.31,
|
852 |
+
"learning_rate": 4.311512415349887e-05,
|
853 |
+
"loss": 2.1389,
|
854 |
+
"step": 274500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 41.31,
|
858 |
+
"eval_loss": 2.3499608039855957,
|
859 |
+
"eval_runtime": 121.4347,
|
860 |
+
"eval_samples_per_second": 101.198,
|
861 |
+
"eval_steps_per_second": 6.333,
|
862 |
+
"step": 274500
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 41.99,
|
866 |
+
"learning_rate": 4.300225733634312e-05,
|
867 |
+
"loss": 2.1343,
|
868 |
+
"step": 279000
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 41.99,
|
872 |
+
"eval_loss": 2.33479642868042,
|
873 |
+
"eval_runtime": 121.4769,
|
874 |
+
"eval_samples_per_second": 101.163,
|
875 |
+
"eval_steps_per_second": 6.33,
|
876 |
+
"step": 279000
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 42.66,
|
880 |
+
"learning_rate": 4.2889390519187363e-05,
|
881 |
+
"loss": 2.1204,
|
882 |
+
"step": 283500
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 42.66,
|
886 |
+
"eval_loss": 2.338609457015991,
|
887 |
+
"eval_runtime": 119.9199,
|
888 |
+
"eval_samples_per_second": 102.477,
|
889 |
+
"eval_steps_per_second": 6.413,
|
890 |
+
"step": 283500
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 43.34,
|
894 |
+
"learning_rate": 4.277652370203161e-05,
|
895 |
+
"loss": 2.1149,
|
896 |
+
"step": 288000
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 43.34,
|
900 |
+
"eval_loss": 2.3366451263427734,
|
901 |
+
"eval_runtime": 121.3615,
|
902 |
+
"eval_samples_per_second": 101.259,
|
903 |
+
"eval_steps_per_second": 6.336,
|
904 |
+
"step": 288000
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 44.02,
|
908 |
+
"learning_rate": 4.266365688487585e-05,
|
909 |
+
"loss": 2.1124,
|
910 |
+
"step": 292500
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 44.02,
|
914 |
+
"eval_loss": 2.3272287845611572,
|
915 |
+
"eval_runtime": 121.4223,
|
916 |
+
"eval_samples_per_second": 101.209,
|
917 |
+
"eval_steps_per_second": 6.333,
|
918 |
+
"step": 292500
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 44.7,
|
922 |
+
"learning_rate": 4.255079006772009e-05,
|
923 |
+
"loss": 2.0996,
|
924 |
+
"step": 297000
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 44.7,
|
928 |
+
"eval_loss": 2.3160288333892822,
|
929 |
+
"eval_runtime": 121.4331,
|
930 |
+
"eval_samples_per_second": 101.2,
|
931 |
+
"eval_steps_per_second": 6.333,
|
932 |
+
"step": 297000
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 45.37,
|
936 |
+
"learning_rate": 4.243792325056434e-05,
|
937 |
+
"loss": 2.0954,
|
938 |
+
"step": 301500
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 45.37,
|
942 |
+
"eval_loss": 2.3165717124938965,
|
943 |
+
"eval_runtime": 121.3269,
|
944 |
+
"eval_samples_per_second": 101.288,
|
945 |
+
"eval_steps_per_second": 6.338,
|
946 |
+
"step": 301500
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 46.05,
|
950 |
+
"learning_rate": 4.232505643340858e-05,
|
951 |
+
"loss": 2.0901,
|
952 |
+
"step": 306000
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 46.05,
|
956 |
+
"eval_loss": 2.303679943084717,
|
957 |
+
"eval_runtime": 121.3845,
|
958 |
+
"eval_samples_per_second": 101.24,
|
959 |
+
"eval_steps_per_second": 6.335,
|
960 |
+
"step": 306000
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 46.73,
|
964 |
+
"learning_rate": 4.221218961625282e-05,
|
965 |
+
"loss": 2.0819,
|
966 |
+
"step": 310500
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 46.73,
|
970 |
+
"eval_loss": 2.2977073192596436,
|
971 |
+
"eval_runtime": 121.4379,
|
972 |
+
"eval_samples_per_second": 101.196,
|
973 |
+
"eval_steps_per_second": 6.332,
|
974 |
+
"step": 310500
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 47.4,
|
978 |
+
"learning_rate": 4.209932279909707e-05,
|
979 |
+
"loss": 2.0725,
|
980 |
+
"step": 315000
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 47.4,
|
984 |
+
"eval_loss": 2.3036298751831055,
|
985 |
+
"eval_runtime": 121.4278,
|
986 |
+
"eval_samples_per_second": 101.204,
|
987 |
+
"eval_steps_per_second": 6.333,
|
988 |
+
"step": 315000
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 48.08,
|
992 |
+
"learning_rate": 4.198645598194131e-05,
|
993 |
+
"loss": 2.0729,
|
994 |
+
"step": 319500
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 48.08,
|
998 |
+
"eval_loss": 2.2955193519592285,
|
999 |
+
"eval_runtime": 121.3513,
|
1000 |
+
"eval_samples_per_second": 101.268,
|
1001 |
+
"eval_steps_per_second": 6.337,
|
1002 |
+
"step": 319500
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 48.76,
|
1006 |
+
"learning_rate": 4.187358916478555e-05,
|
1007 |
+
"loss": 2.0621,
|
1008 |
+
"step": 324000
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 48.76,
|
1012 |
+
"eval_loss": 2.284827947616577,
|
1013 |
+
"eval_runtime": 121.3713,
|
1014 |
+
"eval_samples_per_second": 101.251,
|
1015 |
+
"eval_steps_per_second": 6.336,
|
1016 |
+
"step": 324000
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 49.44,
|
1020 |
+
"learning_rate": 4.17607223476298e-05,
|
1021 |
+
"loss": 2.055,
|
1022 |
+
"step": 328500
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 49.44,
|
1026 |
+
"eval_loss": 2.2865021228790283,
|
1027 |
+
"eval_runtime": 121.4042,
|
1028 |
+
"eval_samples_per_second": 101.224,
|
1029 |
+
"eval_steps_per_second": 6.334,
|
1030 |
+
"step": 328500
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 50.11,
|
1034 |
+
"learning_rate": 4.164785553047404e-05,
|
1035 |
+
"loss": 2.0514,
|
1036 |
+
"step": 333000
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 50.11,
|
1040 |
+
"eval_loss": 2.2722549438476562,
|
1041 |
+
"eval_runtime": 121.3871,
|
1042 |
+
"eval_samples_per_second": 101.238,
|
1043 |
+
"eval_steps_per_second": 6.335,
|
1044 |
+
"step": 333000
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 50.79,
|
1048 |
+
"learning_rate": 4.153498871331828e-05,
|
1049 |
+
"loss": 2.0427,
|
1050 |
+
"step": 337500
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 50.79,
|
1054 |
+
"eval_loss": 2.2747364044189453,
|
1055 |
+
"eval_runtime": 121.4348,
|
1056 |
+
"eval_samples_per_second": 101.198,
|
1057 |
+
"eval_steps_per_second": 6.333,
|
1058 |
+
"step": 337500
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 51.47,
|
1062 |
+
"learning_rate": 4.142212189616253e-05,
|
1063 |
+
"loss": 2.0398,
|
1064 |
+
"step": 342000
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 51.47,
|
1068 |
+
"eval_loss": 2.275329113006592,
|
1069 |
+
"eval_runtime": 121.4165,
|
1070 |
+
"eval_samples_per_second": 101.214,
|
1071 |
+
"eval_steps_per_second": 6.334,
|
1072 |
+
"step": 342000
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 52.14,
|
1076 |
+
"learning_rate": 4.130925507900677e-05,
|
1077 |
+
"loss": 2.0373,
|
1078 |
+
"step": 346500
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 52.14,
|
1082 |
+
"eval_loss": 2.263934850692749,
|
1083 |
+
"eval_runtime": 121.4832,
|
1084 |
+
"eval_samples_per_second": 101.158,
|
1085 |
+
"eval_steps_per_second": 6.33,
|
1086 |
+
"step": 346500
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 52.82,
|
1090 |
+
"learning_rate": 4.119638826185102e-05,
|
1091 |
+
"loss": 2.0293,
|
1092 |
+
"step": 351000
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 52.82,
|
1096 |
+
"eval_loss": 2.2591116428375244,
|
1097 |
+
"eval_runtime": 121.453,
|
1098 |
+
"eval_samples_per_second": 101.183,
|
1099 |
+
"eval_steps_per_second": 6.332,
|
1100 |
+
"step": 351000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 53.5,
|
1104 |
+
"learning_rate": 4.108352144469526e-05,
|
1105 |
+
"loss": 2.0222,
|
1106 |
+
"step": 355500
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 53.5,
|
1110 |
+
"eval_loss": 2.251147508621216,
|
1111 |
+
"eval_runtime": 121.2819,
|
1112 |
+
"eval_samples_per_second": 101.326,
|
1113 |
+
"eval_steps_per_second": 6.341,
|
1114 |
+
"step": 355500
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 54.18,
|
1118 |
+
"learning_rate": 4.097065462753951e-05,
|
1119 |
+
"loss": 2.018,
|
1120 |
+
"step": 360000
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 54.18,
|
1124 |
+
"eval_loss": 2.2465593814849854,
|
1125 |
+
"eval_runtime": 121.4341,
|
1126 |
+
"eval_samples_per_second": 101.199,
|
1127 |
+
"eval_steps_per_second": 6.333,
|
1128 |
+
"step": 360000
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 54.85,
|
1132 |
+
"learning_rate": 4.085778781038375e-05,
|
1133 |
+
"loss": 2.0129,
|
1134 |
+
"step": 364500
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 54.85,
|
1138 |
+
"eval_loss": 2.244495153427124,
|
1139 |
+
"eval_runtime": 121.4224,
|
1140 |
+
"eval_samples_per_second": 101.209,
|
1141 |
+
"eval_steps_per_second": 6.333,
|
1142 |
+
"step": 364500
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 55.53,
|
1146 |
+
"learning_rate": 4.074492099322799e-05,
|
1147 |
+
"loss": 2.0071,
|
1148 |
+
"step": 369000
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 55.53,
|
1152 |
+
"eval_loss": 2.244058609008789,
|
1153 |
+
"eval_runtime": 121.4271,
|
1154 |
+
"eval_samples_per_second": 101.205,
|
1155 |
+
"eval_steps_per_second": 6.333,
|
1156 |
+
"step": 369000
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 56.21,
|
1160 |
+
"learning_rate": 4.063205417607224e-05,
|
1161 |
+
"loss": 2.0026,
|
1162 |
+
"step": 373500
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 56.21,
|
1166 |
+
"eval_loss": 2.2374625205993652,
|
1167 |
+
"eval_runtime": 121.4591,
|
1168 |
+
"eval_samples_per_second": 101.178,
|
1169 |
+
"eval_steps_per_second": 6.331,
|
1170 |
+
"step": 373500
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 56.88,
|
1174 |
+
"learning_rate": 4.0519187358916484e-05,
|
1175 |
+
"loss": 1.9989,
|
1176 |
+
"step": 378000
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 56.88,
|
1180 |
+
"eval_loss": 2.2266647815704346,
|
1181 |
+
"eval_runtime": 121.4333,
|
1182 |
+
"eval_samples_per_second": 101.2,
|
1183 |
+
"eval_steps_per_second": 6.333,
|
1184 |
+
"step": 378000
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 57.56,
|
1188 |
+
"learning_rate": 4.040632054176072e-05,
|
1189 |
+
"loss": 1.9917,
|
1190 |
+
"step": 382500
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 57.56,
|
1194 |
+
"eval_loss": 2.2338218688964844,
|
1195 |
+
"eval_runtime": 121.4506,
|
1196 |
+
"eval_samples_per_second": 101.185,
|
1197 |
+
"eval_steps_per_second": 6.332,
|
1198 |
+
"step": 382500
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 58.24,
|
1202 |
+
"learning_rate": 4.029345372460497e-05,
|
1203 |
+
"loss": 1.9869,
|
1204 |
+
"step": 387000
|
1205 |
+
},
|
1206 |
+
{
|
1207 |
+
"epoch": 58.24,
|
1208 |
+
"eval_loss": 2.226421594619751,
|
1209 |
+
"eval_runtime": 121.395,
|
1210 |
+
"eval_samples_per_second": 101.232,
|
1211 |
+
"eval_steps_per_second": 6.335,
|
1212 |
+
"step": 387000
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 58.92,
|
1216 |
+
"learning_rate": 4.018058690744921e-05,
|
1217 |
+
"loss": 1.9855,
|
1218 |
+
"step": 391500
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 58.92,
|
1222 |
+
"eval_loss": 2.22316837310791,
|
1223 |
+
"eval_runtime": 121.4361,
|
1224 |
+
"eval_samples_per_second": 101.197,
|
1225 |
+
"eval_steps_per_second": 6.333,
|
1226 |
+
"step": 391500
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 59.59,
|
1230 |
+
"learning_rate": 4.006772009029345e-05,
|
1231 |
+
"loss": 1.975,
|
1232 |
+
"step": 396000
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 59.59,
|
1236 |
+
"eval_loss": 2.221580743789673,
|
1237 |
+
"eval_runtime": 121.4217,
|
1238 |
+
"eval_samples_per_second": 101.209,
|
1239 |
+
"eval_steps_per_second": 6.333,
|
1240 |
+
"step": 396000
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 60.27,
|
1244 |
+
"learning_rate": 3.99548532731377e-05,
|
1245 |
+
"loss": 1.9738,
|
1246 |
+
"step": 400500
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 60.27,
|
1250 |
+
"eval_loss": 2.2099127769470215,
|
1251 |
+
"eval_runtime": 121.4414,
|
1252 |
+
"eval_samples_per_second": 101.193,
|
1253 |
+
"eval_steps_per_second": 6.332,
|
1254 |
+
"step": 400500
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 60.95,
|
1258 |
+
"learning_rate": 3.984198645598194e-05,
|
1259 |
+
"loss": 1.9724,
|
1260 |
+
"step": 405000
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 60.95,
|
1264 |
+
"eval_loss": 2.217116355895996,
|
1265 |
+
"eval_runtime": 121.4225,
|
1266 |
+
"eval_samples_per_second": 101.209,
|
1267 |
+
"eval_steps_per_second": 6.333,
|
1268 |
+
"step": 405000
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 61.63,
|
1272 |
+
"learning_rate": 3.972911963882618e-05,
|
1273 |
+
"loss": 1.9643,
|
1274 |
+
"step": 409500
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 61.63,
|
1278 |
+
"eval_loss": 2.2091891765594482,
|
1279 |
+
"eval_runtime": 121.3749,
|
1280 |
+
"eval_samples_per_second": 101.248,
|
1281 |
+
"eval_steps_per_second": 6.336,
|
1282 |
+
"step": 409500
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 62.3,
|
1286 |
+
"learning_rate": 3.961625282167043e-05,
|
1287 |
+
"loss": 1.9582,
|
1288 |
+
"step": 414000
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 62.3,
|
1292 |
+
"eval_loss": 2.2050740718841553,
|
1293 |
+
"eval_runtime": 121.3877,
|
1294 |
+
"eval_samples_per_second": 101.238,
|
1295 |
+
"eval_steps_per_second": 6.335,
|
1296 |
+
"step": 414000
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 62.98,
|
1300 |
+
"learning_rate": 3.950338600451467e-05,
|
1301 |
+
"loss": 1.9596,
|
1302 |
+
"step": 418500
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 62.98,
|
1306 |
+
"eval_loss": 2.2095320224761963,
|
1307 |
+
"eval_runtime": 121.3734,
|
1308 |
+
"eval_samples_per_second": 101.25,
|
1309 |
+
"eval_steps_per_second": 6.336,
|
1310 |
+
"step": 418500
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 63.66,
|
1314 |
+
"learning_rate": 3.939051918735892e-05,
|
1315 |
+
"loss": 1.9491,
|
1316 |
+
"step": 423000
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 63.66,
|
1320 |
+
"eval_loss": 2.201195478439331,
|
1321 |
+
"eval_runtime": 121.4462,
|
1322 |
+
"eval_samples_per_second": 101.189,
|
1323 |
+
"eval_steps_per_second": 6.332,
|
1324 |
+
"step": 423000
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 64.33,
|
1328 |
+
"learning_rate": 3.927765237020316e-05,
|
1329 |
+
"loss": 1.9493,
|
1330 |
+
"step": 427500
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 64.33,
|
1334 |
+
"eval_loss": 2.1953182220458984,
|
1335 |
+
"eval_runtime": 121.4109,
|
1336 |
+
"eval_samples_per_second": 101.218,
|
1337 |
+
"eval_steps_per_second": 6.334,
|
1338 |
+
"step": 427500
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 65.01,
|
1342 |
+
"learning_rate": 3.916478555304741e-05,
|
1343 |
+
"loss": 1.946,
|
1344 |
+
"step": 432000
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 65.01,
|
1348 |
+
"eval_loss": 2.1867878437042236,
|
1349 |
+
"eval_runtime": 119.4236,
|
1350 |
+
"eval_samples_per_second": 102.903,
|
1351 |
+
"eval_steps_per_second": 6.439,
|
1352 |
+
"step": 432000
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 65.69,
|
1356 |
+
"learning_rate": 3.9051918735891654e-05,
|
1357 |
+
"loss": 1.9359,
|
1358 |
+
"step": 436500
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 65.69,
|
1362 |
+
"eval_loss": 2.1980998516082764,
|
1363 |
+
"eval_runtime": 121.4109,
|
1364 |
+
"eval_samples_per_second": 101.218,
|
1365 |
+
"eval_steps_per_second": 6.334,
|
1366 |
+
"step": 436500
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 66.37,
|
1370 |
+
"learning_rate": 3.893905191873589e-05,
|
1371 |
+
"loss": 1.9333,
|
1372 |
+
"step": 441000
|
1373 |
+
},
|
1374 |
+
{
|
1375 |
+
"epoch": 66.37,
|
1376 |
+
"eval_loss": 2.1945624351501465,
|
1377 |
+
"eval_runtime": 121.3328,
|
1378 |
+
"eval_samples_per_second": 101.283,
|
1379 |
+
"eval_steps_per_second": 6.338,
|
1380 |
+
"step": 441000
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 67.04,
|
1384 |
+
"learning_rate": 3.882618510158014e-05,
|
1385 |
+
"loss": 1.9327,
|
1386 |
+
"step": 445500
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 67.04,
|
1390 |
+
"eval_loss": 2.1841721534729004,
|
1391 |
+
"eval_runtime": 121.4364,
|
1392 |
+
"eval_samples_per_second": 101.197,
|
1393 |
+
"eval_steps_per_second": 6.333,
|
1394 |
+
"step": 445500
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 67.72,
|
1398 |
+
"learning_rate": 3.8713318284424384e-05,
|
1399 |
+
"loss": 1.9243,
|
1400 |
+
"step": 450000
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 67.72,
|
1404 |
+
"eval_loss": 2.189509391784668,
|
1405 |
+
"eval_runtime": 121.4244,
|
1406 |
+
"eval_samples_per_second": 101.207,
|
1407 |
+
"eval_steps_per_second": 6.333,
|
1408 |
+
"step": 450000
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 68.4,
|
1412 |
+
"learning_rate": 3.860045146726862e-05,
|
1413 |
+
"loss": 1.9241,
|
1414 |
+
"step": 454500
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 68.4,
|
1418 |
+
"eval_loss": 2.170930862426758,
|
1419 |
+
"eval_runtime": 121.4233,
|
1420 |
+
"eval_samples_per_second": 101.208,
|
1421 |
+
"eval_steps_per_second": 6.333,
|
1422 |
+
"step": 454500
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 69.07,
|
1426 |
+
"learning_rate": 3.848758465011287e-05,
|
1427 |
+
"loss": 1.9183,
|
1428 |
+
"step": 459000
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 69.07,
|
1432 |
+
"eval_loss": 2.18388032913208,
|
1433 |
+
"eval_runtime": 121.4294,
|
1434 |
+
"eval_samples_per_second": 101.203,
|
1435 |
+
"eval_steps_per_second": 6.333,
|
1436 |
+
"step": 459000
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 69.75,
|
1440 |
+
"learning_rate": 3.837471783295711e-05,
|
1441 |
+
"loss": 1.916,
|
1442 |
+
"step": 463500
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 69.75,
|
1446 |
+
"eval_loss": 2.179508686065674,
|
1447 |
+
"eval_runtime": 121.3882,
|
1448 |
+
"eval_samples_per_second": 101.237,
|
1449 |
+
"eval_steps_per_second": 6.335,
|
1450 |
+
"step": 463500
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 70.43,
|
1454 |
+
"learning_rate": 3.826185101580136e-05,
|
1455 |
+
"loss": 1.9105,
|
1456 |
+
"step": 468000
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 70.43,
|
1460 |
+
"eval_loss": 2.1771745681762695,
|
1461 |
+
"eval_runtime": 121.4394,
|
1462 |
+
"eval_samples_per_second": 101.194,
|
1463 |
+
"eval_steps_per_second": 6.332,
|
1464 |
+
"step": 468000
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 71.11,
|
1468 |
+
"learning_rate": 3.81489841986456e-05,
|
1469 |
+
"loss": 1.9117,
|
1470 |
+
"step": 472500
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 71.11,
|
1474 |
+
"eval_loss": 2.181852340698242,
|
1475 |
+
"eval_runtime": 121.3465,
|
1476 |
+
"eval_samples_per_second": 101.272,
|
1477 |
+
"eval_steps_per_second": 6.337,
|
1478 |
+
"step": 472500
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 71.78,
|
1482 |
+
"learning_rate": 3.803611738148984e-05,
|
1483 |
+
"loss": 1.9041,
|
1484 |
+
"step": 477000
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 71.78,
|
1488 |
+
"eval_loss": 2.1662580966949463,
|
1489 |
+
"eval_runtime": 121.4449,
|
1490 |
+
"eval_samples_per_second": 101.19,
|
1491 |
+
"eval_steps_per_second": 6.332,
|
1492 |
+
"step": 477000
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 72.46,
|
1496 |
+
"learning_rate": 3.792325056433409e-05,
|
1497 |
+
"loss": 1.9021,
|
1498 |
+
"step": 481500
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 72.46,
|
1502 |
+
"eval_loss": 2.165590524673462,
|
1503 |
+
"eval_runtime": 121.4569,
|
1504 |
+
"eval_samples_per_second": 101.18,
|
1505 |
+
"eval_steps_per_second": 6.331,
|
1506 |
+
"step": 481500
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 73.14,
|
1510 |
+
"learning_rate": 3.781038374717833e-05,
|
1511 |
+
"loss": 1.8995,
|
1512 |
+
"step": 486000
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 73.14,
|
1516 |
+
"eval_loss": 2.1610703468322754,
|
1517 |
+
"eval_runtime": 121.4207,
|
1518 |
+
"eval_samples_per_second": 101.21,
|
1519 |
+
"eval_steps_per_second": 6.333,
|
1520 |
+
"step": 486000
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 73.81,
|
1524 |
+
"learning_rate": 3.769751693002257e-05,
|
1525 |
+
"loss": 1.896,
|
1526 |
+
"step": 490500
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 73.81,
|
1530 |
+
"eval_loss": 2.1603007316589355,
|
1531 |
+
"eval_runtime": 121.3989,
|
1532 |
+
"eval_samples_per_second": 101.228,
|
1533 |
+
"eval_steps_per_second": 6.334,
|
1534 |
+
"step": 490500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 74.49,
|
1538 |
+
"learning_rate": 3.758465011286682e-05,
|
1539 |
+
"loss": 1.8901,
|
1540 |
+
"step": 495000
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 74.49,
|
1544 |
+
"eval_loss": 2.158705711364746,
|
1545 |
+
"eval_runtime": 121.4675,
|
1546 |
+
"eval_samples_per_second": 101.171,
|
1547 |
+
"eval_steps_per_second": 6.331,
|
1548 |
+
"step": 495000
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 75.17,
|
1552 |
+
"learning_rate": 3.747178329571106e-05,
|
1553 |
+
"loss": 1.8887,
|
1554 |
+
"step": 499500
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 75.17,
|
1558 |
+
"eval_loss": 2.152022123336792,
|
1559 |
+
"eval_runtime": 121.4184,
|
1560 |
+
"eval_samples_per_second": 101.212,
|
1561 |
+
"eval_steps_per_second": 6.333,
|
1562 |
+
"step": 499500
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 75.85,
|
1566 |
+
"learning_rate": 3.735891647855531e-05,
|
1567 |
+
"loss": 1.8855,
|
1568 |
+
"step": 504000
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 75.85,
|
1572 |
+
"eval_loss": 2.1545896530151367,
|
1573 |
+
"eval_runtime": 121.4036,
|
1574 |
+
"eval_samples_per_second": 101.224,
|
1575 |
+
"eval_steps_per_second": 6.334,
|
1576 |
+
"step": 504000
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 76.52,
|
1580 |
+
"learning_rate": 3.7246049661399554e-05,
|
1581 |
+
"loss": 1.8802,
|
1582 |
+
"step": 508500
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 76.52,
|
1586 |
+
"eval_loss": 2.1495370864868164,
|
1587 |
+
"eval_runtime": 121.4898,
|
1588 |
+
"eval_samples_per_second": 101.153,
|
1589 |
+
"eval_steps_per_second": 6.33,
|
1590 |
+
"step": 508500
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 77.2,
|
1594 |
+
"learning_rate": 3.71331828442438e-05,
|
1595 |
+
"loss": 1.8783,
|
1596 |
+
"step": 513000
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 77.2,
|
1600 |
+
"eval_loss": 2.1447861194610596,
|
1601 |
+
"eval_runtime": 121.3997,
|
1602 |
+
"eval_samples_per_second": 101.228,
|
1603 |
+
"eval_steps_per_second": 6.334,
|
1604 |
+
"step": 513000
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 77.88,
|
1608 |
+
"learning_rate": 3.702031602708804e-05,
|
1609 |
+
"loss": 1.8743,
|
1610 |
+
"step": 517500
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 77.88,
|
1614 |
+
"eval_loss": 2.1373064517974854,
|
1615 |
+
"eval_runtime": 121.3755,
|
1616 |
+
"eval_samples_per_second": 101.248,
|
1617 |
+
"eval_steps_per_second": 6.336,
|
1618 |
+
"step": 517500
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 78.56,
|
1622 |
+
"learning_rate": 3.6907449209932284e-05,
|
1623 |
+
"loss": 1.8679,
|
1624 |
+
"step": 522000
|
1625 |
+
},
|
1626 |
+
{
|
1627 |
+
"epoch": 78.56,
|
1628 |
+
"eval_loss": 2.1462478637695312,
|
1629 |
+
"eval_runtime": 121.3988,
|
1630 |
+
"eval_samples_per_second": 101.228,
|
1631 |
+
"eval_steps_per_second": 6.334,
|
1632 |
+
"step": 522000
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 79.23,
|
1636 |
+
"learning_rate": 3.679458239277653e-05,
|
1637 |
+
"loss": 1.8681,
|
1638 |
+
"step": 526500
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 79.23,
|
1642 |
+
"eval_loss": 2.14402174949646,
|
1643 |
+
"eval_runtime": 121.4163,
|
1644 |
+
"eval_samples_per_second": 101.214,
|
1645 |
+
"eval_steps_per_second": 6.334,
|
1646 |
+
"step": 526500
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 79.91,
|
1650 |
+
"learning_rate": 3.668171557562077e-05,
|
1651 |
+
"loss": 1.8649,
|
1652 |
+
"step": 531000
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 79.91,
|
1656 |
+
"eval_loss": 2.1338822841644287,
|
1657 |
+
"eval_runtime": 121.3916,
|
1658 |
+
"eval_samples_per_second": 101.234,
|
1659 |
+
"eval_steps_per_second": 6.335,
|
1660 |
+
"step": 531000
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"epoch": 80.59,
|
1664 |
+
"learning_rate": 3.656884875846501e-05,
|
1665 |
+
"loss": 1.8593,
|
1666 |
+
"step": 535500
|
1667 |
+
},
|
1668 |
+
{
|
1669 |
+
"epoch": 80.59,
|
1670 |
+
"eval_loss": 2.139404296875,
|
1671 |
+
"eval_runtime": 121.4277,
|
1672 |
+
"eval_samples_per_second": 101.204,
|
1673 |
+
"eval_steps_per_second": 6.333,
|
1674 |
+
"step": 535500
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 81.26,
|
1678 |
+
"learning_rate": 3.645598194130926e-05,
|
1679 |
+
"loss": 1.8592,
|
1680 |
+
"step": 540000
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 81.26,
|
1684 |
+
"eval_loss": 2.1354503631591797,
|
1685 |
+
"eval_runtime": 121.402,
|
1686 |
+
"eval_samples_per_second": 101.226,
|
1687 |
+
"eval_steps_per_second": 6.334,
|
1688 |
+
"step": 540000
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 81.94,
|
1692 |
+
"learning_rate": 3.63431151241535e-05,
|
1693 |
+
"loss": 1.8569,
|
1694 |
+
"step": 544500
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 81.94,
|
1698 |
+
"eval_loss": 2.135469436645508,
|
1699 |
+
"eval_runtime": 121.3789,
|
1700 |
+
"eval_samples_per_second": 101.245,
|
1701 |
+
"eval_steps_per_second": 6.336,
|
1702 |
+
"step": 544500
|
1703 |
+
},
|
1704 |
+
{
|
1705 |
+
"epoch": 82.62,
|
1706 |
+
"learning_rate": 3.623024830699774e-05,
|
1707 |
+
"loss": 1.849,
|
1708 |
+
"step": 549000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 82.62,
|
1712 |
+
"eval_loss": 2.1346044540405273,
|
1713 |
+
"eval_runtime": 121.4745,
|
1714 |
+
"eval_samples_per_second": 101.165,
|
1715 |
+
"eval_steps_per_second": 6.331,
|
1716 |
+
"step": 549000
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 83.3,
|
1720 |
+
"learning_rate": 3.611738148984199e-05,
|
1721 |
+
"loss": 1.8481,
|
1722 |
+
"step": 553500
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 83.3,
|
1726 |
+
"eval_loss": 2.1314146518707275,
|
1727 |
+
"eval_runtime": 121.3262,
|
1728 |
+
"eval_samples_per_second": 101.289,
|
1729 |
+
"eval_steps_per_second": 6.338,
|
1730 |
+
"step": 553500
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 83.97,
|
1734 |
+
"learning_rate": 3.600451467268623e-05,
|
1735 |
+
"loss": 1.8499,
|
1736 |
+
"step": 558000
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 83.97,
|
1740 |
+
"eval_loss": 2.126936197280884,
|
1741 |
+
"eval_runtime": 121.4278,
|
1742 |
+
"eval_samples_per_second": 101.204,
|
1743 |
+
"eval_steps_per_second": 6.333,
|
1744 |
+
"step": 558000
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 84.65,
|
1748 |
+
"learning_rate": 3.589164785553047e-05,
|
1749 |
+
"loss": 1.8394,
|
1750 |
+
"step": 562500
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 84.65,
|
1754 |
+
"eval_loss": 2.118168592453003,
|
1755 |
+
"eval_runtime": 121.4516,
|
1756 |
+
"eval_samples_per_second": 101.184,
|
1757 |
+
"eval_steps_per_second": 6.332,
|
1758 |
+
"step": 562500
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 85.33,
|
1762 |
+
"learning_rate": 3.577878103837472e-05,
|
1763 |
+
"loss": 1.8394,
|
1764 |
+
"step": 567000
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 85.33,
|
1768 |
+
"eval_loss": 2.1206483840942383,
|
1769 |
+
"eval_runtime": 121.4259,
|
1770 |
+
"eval_samples_per_second": 101.206,
|
1771 |
+
"eval_steps_per_second": 6.333,
|
1772 |
+
"step": 567000
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 86.0,
|
1776 |
+
"learning_rate": 3.566591422121896e-05,
|
1777 |
+
"loss": 1.8408,
|
1778 |
+
"step": 571500
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 86.0,
|
1782 |
+
"eval_loss": 2.1219327449798584,
|
1783 |
+
"eval_runtime": 118.4077,
|
1784 |
+
"eval_samples_per_second": 103.785,
|
1785 |
+
"eval_steps_per_second": 6.495,
|
1786 |
+
"step": 571500
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 86.68,
|
1790 |
+
"learning_rate": 3.555304740406321e-05,
|
1791 |
+
"loss": 1.832,
|
1792 |
+
"step": 576000
|
1793 |
+
},
|
1794 |
+
{
|
1795 |
+
"epoch": 86.68,
|
1796 |
+
"eval_loss": 2.1104817390441895,
|
1797 |
+
"eval_runtime": 118.1444,
|
1798 |
+
"eval_samples_per_second": 104.017,
|
1799 |
+
"eval_steps_per_second": 6.509,
|
1800 |
+
"step": 576000
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 87.36,
|
1804 |
+
"learning_rate": 3.5440180586907454e-05,
|
1805 |
+
"loss": 1.8305,
|
1806 |
+
"step": 580500
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 87.36,
|
1810 |
+
"eval_loss": 2.1246631145477295,
|
1811 |
+
"eval_runtime": 118.1028,
|
1812 |
+
"eval_samples_per_second": 104.053,
|
1813 |
+
"eval_steps_per_second": 6.511,
|
1814 |
+
"step": 580500
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 88.04,
|
1818 |
+
"learning_rate": 3.53273137697517e-05,
|
1819 |
+
"loss": 1.8333,
|
1820 |
+
"step": 585000
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 88.04,
|
1824 |
+
"eval_loss": 2.1201488971710205,
|
1825 |
+
"eval_runtime": 118.0958,
|
1826 |
+
"eval_samples_per_second": 104.06,
|
1827 |
+
"eval_steps_per_second": 6.512,
|
1828 |
+
"step": 585000
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 88.71,
|
1832 |
+
"learning_rate": 3.521444695259594e-05,
|
1833 |
+
"loss": 1.8227,
|
1834 |
+
"step": 589500
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 88.71,
|
1838 |
+
"eval_loss": 2.104985475540161,
|
1839 |
+
"eval_runtime": 118.0975,
|
1840 |
+
"eval_samples_per_second": 104.058,
|
1841 |
+
"eval_steps_per_second": 6.512,
|
1842 |
+
"step": 589500
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 89.39,
|
1846 |
+
"learning_rate": 3.5101580135440183e-05,
|
1847 |
+
"loss": 1.8216,
|
1848 |
+
"step": 594000
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 89.39,
|
1852 |
+
"eval_loss": 2.1118545532226562,
|
1853 |
+
"eval_runtime": 118.0937,
|
1854 |
+
"eval_samples_per_second": 104.061,
|
1855 |
+
"eval_steps_per_second": 6.512,
|
1856 |
+
"step": 594000
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 90.07,
|
1860 |
+
"learning_rate": 3.498871331828443e-05,
|
1861 |
+
"loss": 1.8234,
|
1862 |
+
"step": 598500
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 90.07,
|
1866 |
+
"eval_loss": 2.109297037124634,
|
1867 |
+
"eval_runtime": 118.1025,
|
1868 |
+
"eval_samples_per_second": 104.054,
|
1869 |
+
"eval_steps_per_second": 6.511,
|
1870 |
+
"step": 598500
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 90.74,
|
1874 |
+
"learning_rate": 3.487584650112867e-05,
|
1875 |
+
"loss": 1.8162,
|
1876 |
+
"step": 603000
|
1877 |
+
},
|
1878 |
+
{
|
1879 |
+
"epoch": 90.74,
|
1880 |
+
"eval_loss": 2.0999834537506104,
|
1881 |
+
"eval_runtime": 118.0968,
|
1882 |
+
"eval_samples_per_second": 104.059,
|
1883 |
+
"eval_steps_per_second": 6.512,
|
1884 |
+
"step": 603000
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 91.42,
|
1888 |
+
"learning_rate": 3.476297968397291e-05,
|
1889 |
+
"loss": 1.8153,
|
1890 |
+
"step": 607500
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 91.42,
|
1894 |
+
"eval_loss": 2.110783576965332,
|
1895 |
+
"eval_runtime": 118.1749,
|
1896 |
+
"eval_samples_per_second": 103.99,
|
1897 |
+
"eval_steps_per_second": 6.507,
|
1898 |
+
"step": 607500
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 92.1,
|
1902 |
+
"learning_rate": 3.465011286681716e-05,
|
1903 |
+
"loss": 1.8153,
|
1904 |
+
"step": 612000
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 92.1,
|
1908 |
+
"eval_loss": 2.1009647846221924,
|
1909 |
+
"eval_runtime": 118.1986,
|
1910 |
+
"eval_samples_per_second": 103.969,
|
1911 |
+
"eval_steps_per_second": 6.506,
|
1912 |
+
"step": 612000
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 92.78,
|
1916 |
+
"learning_rate": 3.4537246049661404e-05,
|
1917 |
+
"loss": 1.8095,
|
1918 |
+
"step": 616500
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 92.78,
|
1922 |
+
"eval_loss": 2.0992209911346436,
|
1923 |
+
"eval_runtime": 118.1834,
|
1924 |
+
"eval_samples_per_second": 103.982,
|
1925 |
+
"eval_steps_per_second": 6.507,
|
1926 |
+
"step": 616500
|
1927 |
+
},
|
1928 |
+
{
|
1929 |
+
"epoch": 93.45,
|
1930 |
+
"learning_rate": 3.442437923250564e-05,
|
1931 |
+
"loss": 1.807,
|
1932 |
+
"step": 621000
|
1933 |
+
},
|
1934 |
+
{
|
1935 |
+
"epoch": 93.45,
|
1936 |
+
"eval_loss": 2.098292827606201,
|
1937 |
+
"eval_runtime": 118.1816,
|
1938 |
+
"eval_samples_per_second": 103.984,
|
1939 |
+
"eval_steps_per_second": 6.507,
|
1940 |
+
"step": 621000
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 94.13,
|
1944 |
+
"learning_rate": 3.431151241534989e-05,
|
1945 |
+
"loss": 1.805,
|
1946 |
+
"step": 625500
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 94.13,
|
1950 |
+
"eval_loss": 2.0988106727600098,
|
1951 |
+
"eval_runtime": 118.1659,
|
1952 |
+
"eval_samples_per_second": 103.998,
|
1953 |
+
"eval_steps_per_second": 6.508,
|
1954 |
+
"step": 625500
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 94.81,
|
1958 |
+
"learning_rate": 3.4198645598194133e-05,
|
1959 |
+
"loss": 1.8015,
|
1960 |
+
"step": 630000
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 94.81,
|
1964 |
+
"eval_loss": 2.0965840816497803,
|
1965 |
+
"eval_runtime": 118.1678,
|
1966 |
+
"eval_samples_per_second": 103.996,
|
1967 |
+
"eval_steps_per_second": 6.508,
|
1968 |
+
"step": 630000
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 95.49,
|
1972 |
+
"learning_rate": 3.408577878103837e-05,
|
1973 |
+
"loss": 1.7964,
|
1974 |
+
"step": 634500
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 95.49,
|
1978 |
+
"eval_loss": 2.0856127738952637,
|
1979 |
+
"eval_runtime": 118.3087,
|
1980 |
+
"eval_samples_per_second": 103.872,
|
1981 |
+
"eval_steps_per_second": 6.5,
|
1982 |
+
"step": 634500
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 96.16,
|
1986 |
+
"learning_rate": 3.397291196388262e-05,
|
1987 |
+
"loss": 1.7988,
|
1988 |
+
"step": 639000
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 96.16,
|
1992 |
+
"eval_loss": 2.0870988368988037,
|
1993 |
+
"eval_runtime": 118.2923,
|
1994 |
+
"eval_samples_per_second": 103.887,
|
1995 |
+
"eval_steps_per_second": 6.501,
|
1996 |
+
"step": 639000
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 96.84,
|
2000 |
+
"learning_rate": 3.386004514672686e-05,
|
2001 |
+
"loss": 1.794,
|
2002 |
+
"step": 643500
|
2003 |
+
},
|
2004 |
+
{
|
2005 |
+
"epoch": 96.84,
|
2006 |
+
"eval_loss": 2.092172861099243,
|
2007 |
+
"eval_runtime": 118.3047,
|
2008 |
+
"eval_samples_per_second": 103.876,
|
2009 |
+
"eval_steps_per_second": 6.5,
|
2010 |
+
"step": 643500
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 97.52,
|
2014 |
+
"learning_rate": 3.374717832957111e-05,
|
2015 |
+
"loss": 1.7917,
|
2016 |
+
"step": 648000
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 97.52,
|
2020 |
+
"eval_loss": 2.0861566066741943,
|
2021 |
+
"eval_runtime": 118.2327,
|
2022 |
+
"eval_samples_per_second": 103.939,
|
2023 |
+
"eval_steps_per_second": 6.504,
|
2024 |
+
"step": 648000
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 98.19,
|
2028 |
+
"learning_rate": 3.3634311512415354e-05,
|
2029 |
+
"loss": 1.79,
|
2030 |
+
"step": 652500
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 98.19,
|
2034 |
+
"eval_loss": 2.0844566822052,
|
2035 |
+
"eval_runtime": 118.1297,
|
2036 |
+
"eval_samples_per_second": 104.03,
|
2037 |
+
"eval_steps_per_second": 6.51,
|
2038 |
+
"step": 652500
|
2039 |
+
},
|
2040 |
+
{
|
2041 |
+
"epoch": 98.87,
|
2042 |
+
"learning_rate": 3.35214446952596e-05,
|
2043 |
+
"loss": 1.788,
|
2044 |
+
"step": 657000
|
2045 |
+
},
|
2046 |
+
{
|
2047 |
+
"epoch": 98.87,
|
2048 |
+
"eval_loss": 2.0832607746124268,
|
2049 |
+
"eval_runtime": 118.1145,
|
2050 |
+
"eval_samples_per_second": 104.043,
|
2051 |
+
"eval_steps_per_second": 6.511,
|
2052 |
+
"step": 657000
|
2053 |
+
},
|
2054 |
+
{
|
2055 |
+
"epoch": 99.55,
|
2056 |
+
"learning_rate": 3.3408577878103845e-05,
|
2057 |
+
"loss": 1.7833,
|
2058 |
+
"step": 661500
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 99.55,
|
2062 |
+
"eval_loss": 2.082475185394287,
|
2063 |
+
"eval_runtime": 118.0929,
|
2064 |
+
"eval_samples_per_second": 104.062,
|
2065 |
+
"eval_steps_per_second": 6.512,
|
2066 |
+
"step": 661500
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 100.23,
|
2070 |
+
"learning_rate": 3.3295711060948083e-05,
|
2071 |
+
"loss": 1.7821,
|
2072 |
+
"step": 666000
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 100.23,
|
2076 |
+
"eval_loss": 2.0830888748168945,
|
2077 |
+
"eval_runtime": 118.1331,
|
2078 |
+
"eval_samples_per_second": 104.027,
|
2079 |
+
"eval_steps_per_second": 6.51,
|
2080 |
+
"step": 666000
|
2081 |
+
},
|
2082 |
+
{
|
2083 |
+
"epoch": 100.9,
|
2084 |
+
"learning_rate": 3.318284424379233e-05,
|
2085 |
+
"loss": 1.7809,
|
2086 |
+
"step": 670500
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 100.9,
|
2090 |
+
"eval_loss": 2.080984115600586,
|
2091 |
+
"eval_runtime": 118.0711,
|
2092 |
+
"eval_samples_per_second": 104.081,
|
2093 |
+
"eval_steps_per_second": 6.513,
|
2094 |
+
"step": 670500
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 101.58,
|
2098 |
+
"learning_rate": 3.3069977426636574e-05,
|
2099 |
+
"loss": 1.7757,
|
2100 |
+
"step": 675000
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"epoch": 101.58,
|
2104 |
+
"eval_loss": 2.078061819076538,
|
2105 |
+
"eval_runtime": 118.0799,
|
2106 |
+
"eval_samples_per_second": 104.074,
|
2107 |
+
"eval_steps_per_second": 6.513,
|
2108 |
+
"step": 675000
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 102.26,
|
2112 |
+
"learning_rate": 3.295711060948081e-05,
|
2113 |
+
"loss": 1.7737,
|
2114 |
+
"step": 679500
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 102.26,
|
2118 |
+
"eval_loss": 2.079832077026367,
|
2119 |
+
"eval_runtime": 118.3274,
|
2120 |
+
"eval_samples_per_second": 103.856,
|
2121 |
+
"eval_steps_per_second": 6.499,
|
2122 |
+
"step": 679500
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 102.93,
|
2126 |
+
"learning_rate": 3.284424379232506e-05,
|
2127 |
+
"loss": 1.7738,
|
2128 |
+
"step": 684000
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"epoch": 102.93,
|
2132 |
+
"eval_loss": 2.0702972412109375,
|
2133 |
+
"eval_runtime": 118.0753,
|
2134 |
+
"eval_samples_per_second": 104.078,
|
2135 |
+
"eval_steps_per_second": 6.513,
|
2136 |
+
"step": 684000
|
2137 |
+
},
|
2138 |
+
{
|
2139 |
+
"epoch": 103.61,
|
2140 |
+
"learning_rate": 3.2731376975169304e-05,
|
2141 |
+
"loss": 1.7701,
|
2142 |
+
"step": 688500
|
2143 |
+
},
|
2144 |
+
{
|
2145 |
+
"epoch": 103.61,
|
2146 |
+
"eval_loss": 2.0662286281585693,
|
2147 |
+
"eval_runtime": 118.9742,
|
2148 |
+
"eval_samples_per_second": 103.291,
|
2149 |
+
"eval_steps_per_second": 6.464,
|
2150 |
+
"step": 688500
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 104.29,
|
2154 |
+
"learning_rate": 3.261851015801354e-05,
|
2155 |
+
"loss": 1.7682,
|
2156 |
+
"step": 693000
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 104.29,
|
2160 |
+
"eval_loss": 2.070204973220825,
|
2161 |
+
"eval_runtime": 118.3434,
|
2162 |
+
"eval_samples_per_second": 103.842,
|
2163 |
+
"eval_steps_per_second": 6.498,
|
2164 |
+
"step": 693000
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 104.97,
|
2168 |
+
"learning_rate": 3.250564334085779e-05,
|
2169 |
+
"loss": 1.7669,
|
2170 |
+
"step": 697500
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 104.97,
|
2174 |
+
"eval_loss": 2.063176155090332,
|
2175 |
+
"eval_runtime": 118.357,
|
2176 |
+
"eval_samples_per_second": 103.83,
|
2177 |
+
"eval_steps_per_second": 6.497,
|
2178 |
+
"step": 697500
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 105.64,
|
2182 |
+
"learning_rate": 3.239277652370203e-05,
|
2183 |
+
"loss": 1.7616,
|
2184 |
+
"step": 702000
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 105.64,
|
2188 |
+
"eval_loss": 2.067533254623413,
|
2189 |
+
"eval_runtime": 118.3349,
|
2190 |
+
"eval_samples_per_second": 103.849,
|
2191 |
+
"eval_steps_per_second": 6.499,
|
2192 |
+
"step": 702000
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 106.32,
|
2196 |
+
"learning_rate": 3.227990970654628e-05,
|
2197 |
+
"loss": 1.7623,
|
2198 |
+
"step": 706500
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 106.32,
|
2202 |
+
"eval_loss": 2.0670344829559326,
|
2203 |
+
"eval_runtime": 118.3389,
|
2204 |
+
"eval_samples_per_second": 103.846,
|
2205 |
+
"eval_steps_per_second": 6.498,
|
2206 |
+
"step": 706500
|
2207 |
+
},
|
2208 |
+
{
|
2209 |
+
"epoch": 107.0,
|
2210 |
+
"learning_rate": 3.216704288939052e-05,
|
2211 |
+
"loss": 1.7623,
|
2212 |
+
"step": 711000
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 107.0,
|
2216 |
+
"eval_loss": 2.0591020584106445,
|
2217 |
+
"eval_runtime": 118.3407,
|
2218 |
+
"eval_samples_per_second": 103.844,
|
2219 |
+
"eval_steps_per_second": 6.498,
|
2220 |
+
"step": 711000
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 107.67,
|
2224 |
+
"learning_rate": 3.205417607223476e-05,
|
2225 |
+
"loss": 1.7553,
|
2226 |
+
"step": 715500
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 107.67,
|
2230 |
+
"eval_loss": 2.0580272674560547,
|
2231 |
+
"eval_runtime": 118.3269,
|
2232 |
+
"eval_samples_per_second": 103.856,
|
2233 |
+
"eval_steps_per_second": 6.499,
|
2234 |
+
"step": 715500
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 108.35,
|
2238 |
+
"learning_rate": 3.194130925507901e-05,
|
2239 |
+
"loss": 1.753,
|
2240 |
+
"step": 720000
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 108.35,
|
2244 |
+
"eval_loss": 2.0603325366973877,
|
2245 |
+
"eval_runtime": 118.3271,
|
2246 |
+
"eval_samples_per_second": 103.856,
|
2247 |
+
"eval_steps_per_second": 6.499,
|
2248 |
+
"step": 720000
|
2249 |
+
},
|
2250 |
+
{
|
2251 |
+
"epoch": 109.03,
|
2252 |
+
"learning_rate": 3.1828442437923254e-05,
|
2253 |
+
"loss": 1.7549,
|
2254 |
+
"step": 724500
|
2255 |
+
},
|
2256 |
+
{
|
2257 |
+
"epoch": 109.03,
|
2258 |
+
"eval_loss": 2.0661327838897705,
|
2259 |
+
"eval_runtime": 118.3395,
|
2260 |
+
"eval_samples_per_second": 103.845,
|
2261 |
+
"eval_steps_per_second": 6.498,
|
2262 |
+
"step": 724500
|
2263 |
+
},
|
2264 |
+
{
|
2265 |
+
"epoch": 109.71,
|
2266 |
+
"learning_rate": 3.17155756207675e-05,
|
2267 |
+
"loss": 1.7474,
|
2268 |
+
"step": 729000
|
2269 |
+
},
|
2270 |
+
{
|
2271 |
+
"epoch": 109.71,
|
2272 |
+
"eval_loss": 2.0576255321502686,
|
2273 |
+
"eval_runtime": 118.3567,
|
2274 |
+
"eval_samples_per_second": 103.83,
|
2275 |
+
"eval_steps_per_second": 6.497,
|
2276 |
+
"step": 729000
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 110.38,
|
2280 |
+
"learning_rate": 3.1602708803611745e-05,
|
2281 |
+
"loss": 1.7504,
|
2282 |
+
"step": 733500
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 110.38,
|
2286 |
+
"eval_loss": 2.0617053508758545,
|
2287 |
+
"eval_runtime": 118.3259,
|
2288 |
+
"eval_samples_per_second": 103.857,
|
2289 |
+
"eval_steps_per_second": 6.499,
|
2290 |
+
"step": 733500
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"epoch": 111.06,
|
2294 |
+
"learning_rate": 3.148984198645598e-05,
|
2295 |
+
"loss": 1.7464,
|
2296 |
+
"step": 738000
|
2297 |
+
},
|
2298 |
+
{
|
2299 |
+
"epoch": 111.06,
|
2300 |
+
"eval_loss": 2.049917459487915,
|
2301 |
+
"eval_runtime": 118.3445,
|
2302 |
+
"eval_samples_per_second": 103.841,
|
2303 |
+
"eval_steps_per_second": 6.498,
|
2304 |
+
"step": 738000
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 111.74,
|
2308 |
+
"learning_rate": 3.137697516930023e-05,
|
2309 |
+
"loss": 1.7432,
|
2310 |
+
"step": 742500
|
2311 |
+
},
|
2312 |
+
{
|
2313 |
+
"epoch": 111.74,
|
2314 |
+
"eval_loss": 2.056652069091797,
|
2315 |
+
"eval_runtime": 118.3587,
|
2316 |
+
"eval_samples_per_second": 103.828,
|
2317 |
+
"eval_steps_per_second": 6.497,
|
2318 |
+
"step": 742500
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 112.42,
|
2322 |
+
"learning_rate": 3.1264108352144474e-05,
|
2323 |
+
"loss": 1.7404,
|
2324 |
+
"step": 747000
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 112.42,
|
2328 |
+
"eval_loss": 2.0593619346618652,
|
2329 |
+
"eval_runtime": 118.3421,
|
2330 |
+
"eval_samples_per_second": 103.843,
|
2331 |
+
"eval_steps_per_second": 6.498,
|
2332 |
+
"step": 747000
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 113.09,
|
2336 |
+
"learning_rate": 3.115124153498871e-05,
|
2337 |
+
"loss": 1.7438,
|
2338 |
+
"step": 751500
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 113.09,
|
2342 |
+
"eval_loss": 2.045955181121826,
|
2343 |
+
"eval_runtime": 118.325,
|
2344 |
+
"eval_samples_per_second": 103.858,
|
2345 |
+
"eval_steps_per_second": 6.499,
|
2346 |
+
"step": 751500
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 113.77,
|
2350 |
+
"learning_rate": 3.103837471783296e-05,
|
2351 |
+
"loss": 1.7375,
|
2352 |
+
"step": 756000
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 113.77,
|
2356 |
+
"eval_loss": 2.055434465408325,
|
2357 |
+
"eval_runtime": 118.3498,
|
2358 |
+
"eval_samples_per_second": 103.836,
|
2359 |
+
"eval_steps_per_second": 6.498,
|
2360 |
+
"step": 756000
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 114.45,
|
2364 |
+
"learning_rate": 3.0925507900677204e-05,
|
2365 |
+
"loss": 1.7336,
|
2366 |
+
"step": 760500
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 114.45,
|
2370 |
+
"eval_loss": 2.040349006652832,
|
2371 |
+
"eval_runtime": 118.3546,
|
2372 |
+
"eval_samples_per_second": 103.832,
|
2373 |
+
"eval_steps_per_second": 6.497,
|
2374 |
+
"step": 760500
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 115.12,
|
2378 |
+
"learning_rate": 3.081264108352145e-05,
|
2379 |
+
"loss": 1.7344,
|
2380 |
+
"step": 765000
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 115.12,
|
2384 |
+
"eval_loss": 2.054170846939087,
|
2385 |
+
"eval_runtime": 118.3514,
|
2386 |
+
"eval_samples_per_second": 103.835,
|
2387 |
+
"eval_steps_per_second": 6.498,
|
2388 |
+
"step": 765000
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 115.8,
|
2392 |
+
"learning_rate": 3.069977426636569e-05,
|
2393 |
+
"loss": 1.7324,
|
2394 |
+
"step": 769500
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 115.8,
|
2398 |
+
"eval_loss": 2.042388439178467,
|
2399 |
+
"eval_runtime": 118.3282,
|
2400 |
+
"eval_samples_per_second": 103.855,
|
2401 |
+
"eval_steps_per_second": 6.499,
|
2402 |
+
"step": 769500
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 116.48,
|
2406 |
+
"learning_rate": 3.058690744920993e-05,
|
2407 |
+
"loss": 1.7255,
|
2408 |
+
"step": 774000
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 116.48,
|
2412 |
+
"eval_loss": 2.0501296520233154,
|
2413 |
+
"eval_runtime": 118.1548,
|
2414 |
+
"eval_samples_per_second": 104.008,
|
2415 |
+
"eval_steps_per_second": 6.508,
|
2416 |
+
"step": 774000
|
2417 |
+
}
|
2418 |
+
],
|
2419 |
+
"max_steps": 1993500,
|
2420 |
+
"num_train_epochs": 300,
|
2421 |
+
"total_flos": 6.520019673893634e+18,
|
2422 |
+
"trial_name": null,
|
2423 |
+
"trial_params": null
|
2424 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4711a71b9186331cd1e18fac6f3b227f10b844f6ca8c1166fc919684598d857a
|
3 |
+
size 3055
|