Upload 8 files
Browse files- config.json +24 -0
- generation_config.json +5 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2998 -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": "4.31.0.dev0",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 25000
|
| 24 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.31.0.dev0"
|
| 5 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d133c3e1ac2c7ef31adce9cf90e3afce10c61f849c2edfe65bffa30166d8e835
|
| 3 |
+
size 842261893
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad54a90cb78ea6a9491a6f4af3d21d7342688d95d95adb4d2d549af2a225b6a
|
| 3 |
+
size 421140469
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02e29bbcb191babe0f791c119b69dd312ca8d4866b369d33575214fb149ca312
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d69e3e23c58d6170f086f97000e221404c20c804d656240f153e7073c7c6bcf9
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2998 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.4363410472869873,
|
| 3 |
+
"best_model_checkpoint": "/home/seemdog/manchu_BERT/1002_BERT_DA_1.0/checkpoint-86000",
|
| 4 |
+
"epoch": 9.964620917517031,
|
| 5 |
+
"global_step": 213000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.9766081871345035e-05,
|
| 13 |
+
"loss": 6.1581,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_loss": 5.5598931312561035,
|
| 19 |
+
"eval_runtime": 54.891,
|
| 20 |
+
"eval_samples_per_second": 120.767,
|
| 21 |
+
"eval_steps_per_second": 1.895,
|
| 22 |
+
"step": 1000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.09,
|
| 26 |
+
"learning_rate": 4.953216374269006e-05,
|
| 27 |
+
"loss": 5.3713,
|
| 28 |
+
"step": 2000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.09,
|
| 32 |
+
"eval_loss": 4.843267440795898,
|
| 33 |
+
"eval_runtime": 54.8945,
|
| 34 |
+
"eval_samples_per_second": 120.759,
|
| 35 |
+
"eval_steps_per_second": 1.895,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.14,
|
| 40 |
+
"learning_rate": 4.9298245614035086e-05,
|
| 41 |
+
"loss": 4.7624,
|
| 42 |
+
"step": 3000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.14,
|
| 46 |
+
"eval_loss": 4.427705764770508,
|
| 47 |
+
"eval_runtime": 54.9095,
|
| 48 |
+
"eval_samples_per_second": 120.726,
|
| 49 |
+
"eval_steps_per_second": 1.894,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 4.906432748538012e-05,
|
| 55 |
+
"loss": 4.2884,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.19,
|
| 60 |
+
"eval_loss": 4.152446746826172,
|
| 61 |
+
"eval_runtime": 54.9536,
|
| 62 |
+
"eval_samples_per_second": 120.629,
|
| 63 |
+
"eval_steps_per_second": 1.893,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.23,
|
| 68 |
+
"learning_rate": 4.883040935672515e-05,
|
| 69 |
+
"loss": 3.908,
|
| 70 |
+
"step": 5000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.23,
|
| 74 |
+
"eval_loss": 3.943004608154297,
|
| 75 |
+
"eval_runtime": 54.9769,
|
| 76 |
+
"eval_samples_per_second": 120.578,
|
| 77 |
+
"eval_steps_per_second": 1.892,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.28,
|
| 82 |
+
"learning_rate": 4.859649122807018e-05,
|
| 83 |
+
"loss": 3.6357,
|
| 84 |
+
"step": 6000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.28,
|
| 88 |
+
"eval_loss": 3.7840378284454346,
|
| 89 |
+
"eval_runtime": 54.9612,
|
| 90 |
+
"eval_samples_per_second": 120.612,
|
| 91 |
+
"eval_steps_per_second": 1.892,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 4.836257309941521e-05,
|
| 97 |
+
"loss": 3.442,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.33,
|
| 102 |
+
"eval_loss": 3.6515119075775146,
|
| 103 |
+
"eval_runtime": 55.0182,
|
| 104 |
+
"eval_samples_per_second": 120.487,
|
| 105 |
+
"eval_steps_per_second": 1.89,
|
| 106 |
+
"step": 7000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.37,
|
| 110 |
+
"learning_rate": 4.8128654970760235e-05,
|
| 111 |
+
"loss": 3.2982,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.37,
|
| 116 |
+
"eval_loss": 3.5147831439971924,
|
| 117 |
+
"eval_runtime": 54.9459,
|
| 118 |
+
"eval_samples_per_second": 120.646,
|
| 119 |
+
"eval_steps_per_second": 1.893,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.42,
|
| 124 |
+
"learning_rate": 4.789473684210526e-05,
|
| 125 |
+
"loss": 3.1681,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.42,
|
| 130 |
+
"eval_loss": 3.4453866481781006,
|
| 131 |
+
"eval_runtime": 54.9741,
|
| 132 |
+
"eval_samples_per_second": 120.584,
|
| 133 |
+
"eval_steps_per_second": 1.892,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.47,
|
| 138 |
+
"learning_rate": 4.7660818713450294e-05,
|
| 139 |
+
"loss": 3.0515,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.47,
|
| 144 |
+
"eval_loss": 3.3482985496520996,
|
| 145 |
+
"eval_runtime": 54.9922,
|
| 146 |
+
"eval_samples_per_second": 120.544,
|
| 147 |
+
"eval_steps_per_second": 1.891,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.51,
|
| 152 |
+
"learning_rate": 4.7426900584795326e-05,
|
| 153 |
+
"loss": 2.9408,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.51,
|
| 158 |
+
"eval_loss": 3.274308919906616,
|
| 159 |
+
"eval_runtime": 55.0307,
|
| 160 |
+
"eval_samples_per_second": 120.46,
|
| 161 |
+
"eval_steps_per_second": 1.89,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.56,
|
| 166 |
+
"learning_rate": 4.719298245614036e-05,
|
| 167 |
+
"loss": 2.8601,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.56,
|
| 172 |
+
"eval_loss": 3.2094714641571045,
|
| 173 |
+
"eval_runtime": 54.9444,
|
| 174 |
+
"eval_samples_per_second": 120.649,
|
| 175 |
+
"eval_steps_per_second": 1.893,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.61,
|
| 180 |
+
"learning_rate": 4.695906432748538e-05,
|
| 181 |
+
"loss": 2.7866,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.61,
|
| 186 |
+
"eval_loss": 3.1299281120300293,
|
| 187 |
+
"eval_runtime": 54.9484,
|
| 188 |
+
"eval_samples_per_second": 120.64,
|
| 189 |
+
"eval_steps_per_second": 1.893,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.65,
|
| 194 |
+
"learning_rate": 4.672514619883041e-05,
|
| 195 |
+
"loss": 2.7094,
|
| 196 |
+
"step": 14000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.65,
|
| 200 |
+
"eval_loss": 3.096022844314575,
|
| 201 |
+
"eval_runtime": 55.155,
|
| 202 |
+
"eval_samples_per_second": 120.189,
|
| 203 |
+
"eval_steps_per_second": 1.886,
|
| 204 |
+
"step": 14000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.7,
|
| 208 |
+
"learning_rate": 4.649122807017544e-05,
|
| 209 |
+
"loss": 2.6424,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.7,
|
| 214 |
+
"eval_loss": 3.060807228088379,
|
| 215 |
+
"eval_runtime": 55.1935,
|
| 216 |
+
"eval_samples_per_second": 120.105,
|
| 217 |
+
"eval_steps_per_second": 1.884,
|
| 218 |
+
"step": 15000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.75,
|
| 222 |
+
"learning_rate": 4.625730994152047e-05,
|
| 223 |
+
"loss": 2.5729,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"eval_loss": 3.0170695781707764,
|
| 229 |
+
"eval_runtime": 55.2064,
|
| 230 |
+
"eval_samples_per_second": 120.077,
|
| 231 |
+
"eval_steps_per_second": 1.884,
|
| 232 |
+
"step": 16000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8,
|
| 236 |
+
"learning_rate": 4.60233918128655e-05,
|
| 237 |
+
"loss": 2.5108,
|
| 238 |
+
"step": 17000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.8,
|
| 242 |
+
"eval_loss": 2.9729015827178955,
|
| 243 |
+
"eval_runtime": 55.2048,
|
| 244 |
+
"eval_samples_per_second": 120.08,
|
| 245 |
+
"eval_steps_per_second": 1.884,
|
| 246 |
+
"step": 17000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.84,
|
| 250 |
+
"learning_rate": 4.5789473684210527e-05,
|
| 251 |
+
"loss": 2.4538,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.84,
|
| 256 |
+
"eval_loss": 2.9392964839935303,
|
| 257 |
+
"eval_runtime": 55.2009,
|
| 258 |
+
"eval_samples_per_second": 120.089,
|
| 259 |
+
"eval_steps_per_second": 1.884,
|
| 260 |
+
"step": 18000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.89,
|
| 264 |
+
"learning_rate": 4.555555555555556e-05,
|
| 265 |
+
"loss": 2.3941,
|
| 266 |
+
"step": 19000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.89,
|
| 270 |
+
"eval_loss": 2.900946617126465,
|
| 271 |
+
"eval_runtime": 55.1868,
|
| 272 |
+
"eval_samples_per_second": 120.119,
|
| 273 |
+
"eval_steps_per_second": 1.885,
|
| 274 |
+
"step": 19000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.94,
|
| 278 |
+
"learning_rate": 4.5321637426900585e-05,
|
| 279 |
+
"loss": 2.3341,
|
| 280 |
+
"step": 20000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.94,
|
| 284 |
+
"eval_loss": 2.87040376663208,
|
| 285 |
+
"eval_runtime": 55.0611,
|
| 286 |
+
"eval_samples_per_second": 120.393,
|
| 287 |
+
"eval_steps_per_second": 1.889,
|
| 288 |
+
"step": 20000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.98,
|
| 292 |
+
"learning_rate": 4.508771929824562e-05,
|
| 293 |
+
"loss": 2.2797,
|
| 294 |
+
"step": 21000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.98,
|
| 298 |
+
"eval_loss": 2.8554604053497314,
|
| 299 |
+
"eval_runtime": 54.9944,
|
| 300 |
+
"eval_samples_per_second": 120.54,
|
| 301 |
+
"eval_steps_per_second": 1.891,
|
| 302 |
+
"step": 21000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.03,
|
| 306 |
+
"learning_rate": 4.485380116959065e-05,
|
| 307 |
+
"loss": 2.2284,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.03,
|
| 312 |
+
"eval_loss": 2.8280177116394043,
|
| 313 |
+
"eval_runtime": 54.9695,
|
| 314 |
+
"eval_samples_per_second": 120.594,
|
| 315 |
+
"eval_steps_per_second": 1.892,
|
| 316 |
+
"step": 22000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.08,
|
| 320 |
+
"learning_rate": 4.4619883040935676e-05,
|
| 321 |
+
"loss": 2.1651,
|
| 322 |
+
"step": 23000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.08,
|
| 326 |
+
"eval_loss": 2.7877776622772217,
|
| 327 |
+
"eval_runtime": 54.9786,
|
| 328 |
+
"eval_samples_per_second": 120.574,
|
| 329 |
+
"eval_steps_per_second": 1.892,
|
| 330 |
+
"step": 23000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.12,
|
| 334 |
+
"learning_rate": 4.43859649122807e-05,
|
| 335 |
+
"loss": 2.1267,
|
| 336 |
+
"step": 24000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.12,
|
| 340 |
+
"eval_loss": 2.7796318531036377,
|
| 341 |
+
"eval_runtime": 55.0112,
|
| 342 |
+
"eval_samples_per_second": 120.503,
|
| 343 |
+
"eval_steps_per_second": 1.891,
|
| 344 |
+
"step": 24000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.17,
|
| 348 |
+
"learning_rate": 4.4152046783625734e-05,
|
| 349 |
+
"loss": 2.0887,
|
| 350 |
+
"step": 25000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.17,
|
| 354 |
+
"eval_loss": 2.7155935764312744,
|
| 355 |
+
"eval_runtime": 54.9846,
|
| 356 |
+
"eval_samples_per_second": 120.561,
|
| 357 |
+
"eval_steps_per_second": 1.891,
|
| 358 |
+
"step": 25000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.22,
|
| 362 |
+
"learning_rate": 4.3918128654970766e-05,
|
| 363 |
+
"loss": 2.0477,
|
| 364 |
+
"step": 26000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.22,
|
| 368 |
+
"eval_loss": 2.7347090244293213,
|
| 369 |
+
"eval_runtime": 54.9797,
|
| 370 |
+
"eval_samples_per_second": 120.572,
|
| 371 |
+
"eval_steps_per_second": 1.892,
|
| 372 |
+
"step": 26000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.26,
|
| 376 |
+
"learning_rate": 4.368421052631579e-05,
|
| 377 |
+
"loss": 2.0055,
|
| 378 |
+
"step": 27000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.26,
|
| 382 |
+
"eval_loss": 2.7260184288024902,
|
| 383 |
+
"eval_runtime": 54.9686,
|
| 384 |
+
"eval_samples_per_second": 120.596,
|
| 385 |
+
"eval_steps_per_second": 1.892,
|
| 386 |
+
"step": 27000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.31,
|
| 390 |
+
"learning_rate": 4.345029239766082e-05,
|
| 391 |
+
"loss": 1.9738,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.31,
|
| 396 |
+
"eval_loss": 2.7053301334381104,
|
| 397 |
+
"eval_runtime": 54.975,
|
| 398 |
+
"eval_samples_per_second": 120.582,
|
| 399 |
+
"eval_steps_per_second": 1.892,
|
| 400 |
+
"step": 28000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.36,
|
| 404 |
+
"learning_rate": 4.321637426900585e-05,
|
| 405 |
+
"loss": 1.9336,
|
| 406 |
+
"step": 29000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.36,
|
| 410 |
+
"eval_loss": 2.6540746688842773,
|
| 411 |
+
"eval_runtime": 54.9866,
|
| 412 |
+
"eval_samples_per_second": 120.557,
|
| 413 |
+
"eval_steps_per_second": 1.891,
|
| 414 |
+
"step": 29000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.4,
|
| 418 |
+
"learning_rate": 4.298245614035088e-05,
|
| 419 |
+
"loss": 1.9008,
|
| 420 |
+
"step": 30000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.4,
|
| 424 |
+
"eval_loss": 2.6721866130828857,
|
| 425 |
+
"eval_runtime": 54.9707,
|
| 426 |
+
"eval_samples_per_second": 120.592,
|
| 427 |
+
"eval_steps_per_second": 1.892,
|
| 428 |
+
"step": 30000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.45,
|
| 432 |
+
"learning_rate": 4.274853801169591e-05,
|
| 433 |
+
"loss": 1.8603,
|
| 434 |
+
"step": 31000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.45,
|
| 438 |
+
"eval_loss": 2.6387619972229004,
|
| 439 |
+
"eval_runtime": 54.9719,
|
| 440 |
+
"eval_samples_per_second": 120.589,
|
| 441 |
+
"eval_steps_per_second": 1.892,
|
| 442 |
+
"step": 31000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.5,
|
| 446 |
+
"learning_rate": 4.251461988304094e-05,
|
| 447 |
+
"loss": 1.8291,
|
| 448 |
+
"step": 32000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.5,
|
| 452 |
+
"eval_loss": 2.640782594680786,
|
| 453 |
+
"eval_runtime": 54.9643,
|
| 454 |
+
"eval_samples_per_second": 120.606,
|
| 455 |
+
"eval_steps_per_second": 1.892,
|
| 456 |
+
"step": 32000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.54,
|
| 460 |
+
"learning_rate": 4.228070175438597e-05,
|
| 461 |
+
"loss": 1.8059,
|
| 462 |
+
"step": 33000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.54,
|
| 466 |
+
"eval_loss": 2.614128589630127,
|
| 467 |
+
"eval_runtime": 54.9538,
|
| 468 |
+
"eval_samples_per_second": 120.629,
|
| 469 |
+
"eval_steps_per_second": 1.893,
|
| 470 |
+
"step": 33000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.59,
|
| 474 |
+
"learning_rate": 4.204678362573099e-05,
|
| 475 |
+
"loss": 1.7663,
|
| 476 |
+
"step": 34000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.59,
|
| 480 |
+
"eval_loss": 2.618607997894287,
|
| 481 |
+
"eval_runtime": 55.0051,
|
| 482 |
+
"eval_samples_per_second": 120.516,
|
| 483 |
+
"eval_steps_per_second": 1.891,
|
| 484 |
+
"step": 34000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.64,
|
| 488 |
+
"learning_rate": 4.1812865497076025e-05,
|
| 489 |
+
"loss": 1.7322,
|
| 490 |
+
"step": 35000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.64,
|
| 494 |
+
"eval_loss": 2.6462574005126953,
|
| 495 |
+
"eval_runtime": 54.9802,
|
| 496 |
+
"eval_samples_per_second": 120.571,
|
| 497 |
+
"eval_steps_per_second": 1.892,
|
| 498 |
+
"step": 35000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.68,
|
| 502 |
+
"learning_rate": 4.157894736842106e-05,
|
| 503 |
+
"loss": 1.7187,
|
| 504 |
+
"step": 36000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.68,
|
| 508 |
+
"eval_loss": 2.5989272594451904,
|
| 509 |
+
"eval_runtime": 54.9619,
|
| 510 |
+
"eval_samples_per_second": 120.611,
|
| 511 |
+
"eval_steps_per_second": 1.892,
|
| 512 |
+
"step": 36000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.73,
|
| 516 |
+
"learning_rate": 4.134502923976608e-05,
|
| 517 |
+
"loss": 1.6852,
|
| 518 |
+
"step": 37000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.73,
|
| 522 |
+
"eval_loss": 2.5719058513641357,
|
| 523 |
+
"eval_runtime": 54.9667,
|
| 524 |
+
"eval_samples_per_second": 120.6,
|
| 525 |
+
"eval_steps_per_second": 1.892,
|
| 526 |
+
"step": 37000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.78,
|
| 530 |
+
"learning_rate": 4.111111111111111e-05,
|
| 531 |
+
"loss": 1.6649,
|
| 532 |
+
"step": 38000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.78,
|
| 536 |
+
"eval_loss": 2.57804012298584,
|
| 537 |
+
"eval_runtime": 54.9675,
|
| 538 |
+
"eval_samples_per_second": 120.598,
|
| 539 |
+
"eval_steps_per_second": 1.892,
|
| 540 |
+
"step": 38000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.82,
|
| 544 |
+
"learning_rate": 4.087719298245614e-05,
|
| 545 |
+
"loss": 1.6285,
|
| 546 |
+
"step": 39000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.82,
|
| 550 |
+
"eval_loss": 2.5606088638305664,
|
| 551 |
+
"eval_runtime": 55.1929,
|
| 552 |
+
"eval_samples_per_second": 120.106,
|
| 553 |
+
"eval_steps_per_second": 1.884,
|
| 554 |
+
"step": 39000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.87,
|
| 558 |
+
"learning_rate": 4.0643274853801174e-05,
|
| 559 |
+
"loss": 1.6033,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.87,
|
| 564 |
+
"eval_loss": 2.570094585418701,
|
| 565 |
+
"eval_runtime": 55.1572,
|
| 566 |
+
"eval_samples_per_second": 120.184,
|
| 567 |
+
"eval_steps_per_second": 1.886,
|
| 568 |
+
"step": 40000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.92,
|
| 572 |
+
"learning_rate": 4.04093567251462e-05,
|
| 573 |
+
"loss": 1.5833,
|
| 574 |
+
"step": 41000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.92,
|
| 578 |
+
"eval_loss": 2.5516393184661865,
|
| 579 |
+
"eval_runtime": 55.1223,
|
| 580 |
+
"eval_samples_per_second": 120.26,
|
| 581 |
+
"eval_steps_per_second": 1.887,
|
| 582 |
+
"step": 41000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.96,
|
| 586 |
+
"learning_rate": 4.017543859649123e-05,
|
| 587 |
+
"loss": 1.5701,
|
| 588 |
+
"step": 42000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.96,
|
| 592 |
+
"eval_loss": 2.544060707092285,
|
| 593 |
+
"eval_runtime": 54.9919,
|
| 594 |
+
"eval_samples_per_second": 120.545,
|
| 595 |
+
"eval_steps_per_second": 1.891,
|
| 596 |
+
"step": 42000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.01,
|
| 600 |
+
"learning_rate": 3.994152046783626e-05,
|
| 601 |
+
"loss": 1.5252,
|
| 602 |
+
"step": 43000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.01,
|
| 606 |
+
"eval_loss": 2.545295476913452,
|
| 607 |
+
"eval_runtime": 54.9924,
|
| 608 |
+
"eval_samples_per_second": 120.544,
|
| 609 |
+
"eval_steps_per_second": 1.891,
|
| 610 |
+
"step": 43000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.06,
|
| 614 |
+
"learning_rate": 3.970760233918129e-05,
|
| 615 |
+
"loss": 1.5019,
|
| 616 |
+
"step": 44000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.06,
|
| 620 |
+
"eval_loss": 2.547807216644287,
|
| 621 |
+
"eval_runtime": 55.007,
|
| 622 |
+
"eval_samples_per_second": 120.512,
|
| 623 |
+
"eval_steps_per_second": 1.891,
|
| 624 |
+
"step": 44000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.11,
|
| 628 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 629 |
+
"loss": 1.4789,
|
| 630 |
+
"step": 45000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.11,
|
| 634 |
+
"eval_loss": 2.541635036468506,
|
| 635 |
+
"eval_runtime": 54.9822,
|
| 636 |
+
"eval_samples_per_second": 120.566,
|
| 637 |
+
"eval_steps_per_second": 1.892,
|
| 638 |
+
"step": 45000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.15,
|
| 642 |
+
"learning_rate": 3.923976608187135e-05,
|
| 643 |
+
"loss": 1.4611,
|
| 644 |
+
"step": 46000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.15,
|
| 648 |
+
"eval_loss": 2.526390790939331,
|
| 649 |
+
"eval_runtime": 54.9826,
|
| 650 |
+
"eval_samples_per_second": 120.565,
|
| 651 |
+
"eval_steps_per_second": 1.892,
|
| 652 |
+
"step": 46000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.2,
|
| 656 |
+
"learning_rate": 3.9005847953216374e-05,
|
| 657 |
+
"loss": 1.4413,
|
| 658 |
+
"step": 47000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.2,
|
| 662 |
+
"eval_loss": 2.5193886756896973,
|
| 663 |
+
"eval_runtime": 54.9793,
|
| 664 |
+
"eval_samples_per_second": 120.573,
|
| 665 |
+
"eval_steps_per_second": 1.892,
|
| 666 |
+
"step": 47000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.25,
|
| 670 |
+
"learning_rate": 3.877192982456141e-05,
|
| 671 |
+
"loss": 1.4106,
|
| 672 |
+
"step": 48000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.25,
|
| 676 |
+
"eval_loss": 2.504810094833374,
|
| 677 |
+
"eval_runtime": 55.0248,
|
| 678 |
+
"eval_samples_per_second": 120.473,
|
| 679 |
+
"eval_steps_per_second": 1.89,
|
| 680 |
+
"step": 48000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.29,
|
| 684 |
+
"learning_rate": 3.853801169590643e-05,
|
| 685 |
+
"loss": 1.3928,
|
| 686 |
+
"step": 49000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.29,
|
| 690 |
+
"eval_loss": 2.5266056060791016,
|
| 691 |
+
"eval_runtime": 55.1287,
|
| 692 |
+
"eval_samples_per_second": 120.246,
|
| 693 |
+
"eval_steps_per_second": 1.886,
|
| 694 |
+
"step": 49000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.34,
|
| 698 |
+
"learning_rate": 3.8304093567251465e-05,
|
| 699 |
+
"loss": 1.3857,
|
| 700 |
+
"step": 50000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.34,
|
| 704 |
+
"eval_loss": 2.5026743412017822,
|
| 705 |
+
"eval_runtime": 55.0968,
|
| 706 |
+
"eval_samples_per_second": 120.315,
|
| 707 |
+
"eval_steps_per_second": 1.888,
|
| 708 |
+
"step": 50000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.39,
|
| 712 |
+
"learning_rate": 3.80701754385965e-05,
|
| 713 |
+
"loss": 1.3682,
|
| 714 |
+
"step": 51000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.39,
|
| 718 |
+
"eval_loss": 2.5191988945007324,
|
| 719 |
+
"eval_runtime": 55.0835,
|
| 720 |
+
"eval_samples_per_second": 120.345,
|
| 721 |
+
"eval_steps_per_second": 1.888,
|
| 722 |
+
"step": 51000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.43,
|
| 726 |
+
"learning_rate": 3.783625730994152e-05,
|
| 727 |
+
"loss": 1.337,
|
| 728 |
+
"step": 52000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.43,
|
| 732 |
+
"eval_loss": 2.4917993545532227,
|
| 733 |
+
"eval_runtime": 55.1615,
|
| 734 |
+
"eval_samples_per_second": 120.175,
|
| 735 |
+
"eval_steps_per_second": 1.885,
|
| 736 |
+
"step": 52000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.48,
|
| 740 |
+
"learning_rate": 3.760233918128655e-05,
|
| 741 |
+
"loss": 1.3314,
|
| 742 |
+
"step": 53000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.48,
|
| 746 |
+
"eval_loss": 2.503882646560669,
|
| 747 |
+
"eval_runtime": 55.1711,
|
| 748 |
+
"eval_samples_per_second": 120.153,
|
| 749 |
+
"eval_steps_per_second": 1.885,
|
| 750 |
+
"step": 53000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.53,
|
| 754 |
+
"learning_rate": 3.736842105263158e-05,
|
| 755 |
+
"loss": 1.3213,
|
| 756 |
+
"step": 54000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.53,
|
| 760 |
+
"eval_loss": 2.5335164070129395,
|
| 761 |
+
"eval_runtime": 55.1504,
|
| 762 |
+
"eval_samples_per_second": 120.199,
|
| 763 |
+
"eval_steps_per_second": 1.886,
|
| 764 |
+
"step": 54000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.57,
|
| 768 |
+
"learning_rate": 3.713450292397661e-05,
|
| 769 |
+
"loss": 1.2901,
|
| 770 |
+
"step": 55000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.57,
|
| 774 |
+
"eval_loss": 2.5040109157562256,
|
| 775 |
+
"eval_runtime": 55.1836,
|
| 776 |
+
"eval_samples_per_second": 120.126,
|
| 777 |
+
"eval_steps_per_second": 1.885,
|
| 778 |
+
"step": 55000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.62,
|
| 782 |
+
"learning_rate": 3.690058479532164e-05,
|
| 783 |
+
"loss": 1.2927,
|
| 784 |
+
"step": 56000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.62,
|
| 788 |
+
"eval_loss": 2.4990580081939697,
|
| 789 |
+
"eval_runtime": 55.1982,
|
| 790 |
+
"eval_samples_per_second": 120.095,
|
| 791 |
+
"eval_steps_per_second": 1.884,
|
| 792 |
+
"step": 56000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.67,
|
| 796 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 797 |
+
"loss": 1.2631,
|
| 798 |
+
"step": 57000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.67,
|
| 802 |
+
"eval_loss": 2.500002861022949,
|
| 803 |
+
"eval_runtime": 55.1671,
|
| 804 |
+
"eval_samples_per_second": 120.162,
|
| 805 |
+
"eval_steps_per_second": 1.885,
|
| 806 |
+
"step": 57000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.71,
|
| 810 |
+
"learning_rate": 3.64327485380117e-05,
|
| 811 |
+
"loss": 1.2526,
|
| 812 |
+
"step": 58000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.71,
|
| 816 |
+
"eval_loss": 2.484260320663452,
|
| 817 |
+
"eval_runtime": 55.0693,
|
| 818 |
+
"eval_samples_per_second": 120.376,
|
| 819 |
+
"eval_steps_per_second": 1.889,
|
| 820 |
+
"step": 58000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.76,
|
| 824 |
+
"learning_rate": 3.6198830409356724e-05,
|
| 825 |
+
"loss": 1.2371,
|
| 826 |
+
"step": 59000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.76,
|
| 830 |
+
"eval_loss": 2.480639696121216,
|
| 831 |
+
"eval_runtime": 55.0676,
|
| 832 |
+
"eval_samples_per_second": 120.379,
|
| 833 |
+
"eval_steps_per_second": 1.889,
|
| 834 |
+
"step": 59000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.81,
|
| 838 |
+
"learning_rate": 3.5964912280701756e-05,
|
| 839 |
+
"loss": 1.2194,
|
| 840 |
+
"step": 60000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.81,
|
| 844 |
+
"eval_loss": 2.480283498764038,
|
| 845 |
+
"eval_runtime": 54.981,
|
| 846 |
+
"eval_samples_per_second": 120.569,
|
| 847 |
+
"eval_steps_per_second": 1.892,
|
| 848 |
+
"step": 60000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.85,
|
| 852 |
+
"learning_rate": 3.573099415204679e-05,
|
| 853 |
+
"loss": 1.2103,
|
| 854 |
+
"step": 61000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.85,
|
| 858 |
+
"eval_loss": 2.4655823707580566,
|
| 859 |
+
"eval_runtime": 54.9896,
|
| 860 |
+
"eval_samples_per_second": 120.55,
|
| 861 |
+
"eval_steps_per_second": 1.891,
|
| 862 |
+
"step": 61000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.9,
|
| 866 |
+
"learning_rate": 3.5497076023391815e-05,
|
| 867 |
+
"loss": 1.1954,
|
| 868 |
+
"step": 62000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.9,
|
| 872 |
+
"eval_loss": 2.467862367630005,
|
| 873 |
+
"eval_runtime": 55.0349,
|
| 874 |
+
"eval_samples_per_second": 120.451,
|
| 875 |
+
"eval_steps_per_second": 1.89,
|
| 876 |
+
"step": 62000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.95,
|
| 880 |
+
"learning_rate": 3.526315789473684e-05,
|
| 881 |
+
"loss": 1.1841,
|
| 882 |
+
"step": 63000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.95,
|
| 886 |
+
"eval_loss": 2.4734864234924316,
|
| 887 |
+
"eval_runtime": 55.0767,
|
| 888 |
+
"eval_samples_per_second": 120.359,
|
| 889 |
+
"eval_steps_per_second": 1.888,
|
| 890 |
+
"step": 63000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.99,
|
| 894 |
+
"learning_rate": 3.502923976608187e-05,
|
| 895 |
+
"loss": 1.1697,
|
| 896 |
+
"step": 64000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.99,
|
| 900 |
+
"eval_loss": 2.4691245555877686,
|
| 901 |
+
"eval_runtime": 55.01,
|
| 902 |
+
"eval_samples_per_second": 120.505,
|
| 903 |
+
"eval_steps_per_second": 1.891,
|
| 904 |
+
"step": 64000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.04,
|
| 908 |
+
"learning_rate": 3.4795321637426905e-05,
|
| 909 |
+
"loss": 1.1488,
|
| 910 |
+
"step": 65000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.04,
|
| 914 |
+
"eval_loss": 2.50709867477417,
|
| 915 |
+
"eval_runtime": 55.0061,
|
| 916 |
+
"eval_samples_per_second": 120.514,
|
| 917 |
+
"eval_steps_per_second": 1.891,
|
| 918 |
+
"step": 65000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.09,
|
| 922 |
+
"learning_rate": 3.456140350877193e-05,
|
| 923 |
+
"loss": 1.1343,
|
| 924 |
+
"step": 66000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 3.09,
|
| 928 |
+
"eval_loss": 2.464665412902832,
|
| 929 |
+
"eval_runtime": 54.9972,
|
| 930 |
+
"eval_samples_per_second": 120.533,
|
| 931 |
+
"eval_steps_per_second": 1.891,
|
| 932 |
+
"step": 66000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.13,
|
| 936 |
+
"learning_rate": 3.432748538011696e-05,
|
| 937 |
+
"loss": 1.1285,
|
| 938 |
+
"step": 67000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.13,
|
| 942 |
+
"eval_loss": 2.4716575145721436,
|
| 943 |
+
"eval_runtime": 54.9735,
|
| 944 |
+
"eval_samples_per_second": 120.585,
|
| 945 |
+
"eval_steps_per_second": 1.892,
|
| 946 |
+
"step": 67000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.18,
|
| 950 |
+
"learning_rate": 3.409356725146199e-05,
|
| 951 |
+
"loss": 1.1124,
|
| 952 |
+
"step": 68000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.18,
|
| 956 |
+
"eval_loss": 2.476966619491577,
|
| 957 |
+
"eval_runtime": 55.0007,
|
| 958 |
+
"eval_samples_per_second": 120.526,
|
| 959 |
+
"eval_steps_per_second": 1.891,
|
| 960 |
+
"step": 68000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.23,
|
| 964 |
+
"learning_rate": 3.385964912280702e-05,
|
| 965 |
+
"loss": 1.1097,
|
| 966 |
+
"step": 69000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.23,
|
| 970 |
+
"eval_loss": 2.487794876098633,
|
| 971 |
+
"eval_runtime": 54.9919,
|
| 972 |
+
"eval_samples_per_second": 120.545,
|
| 973 |
+
"eval_steps_per_second": 1.891,
|
| 974 |
+
"step": 69000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.27,
|
| 978 |
+
"learning_rate": 3.362573099415205e-05,
|
| 979 |
+
"loss": 1.0956,
|
| 980 |
+
"step": 70000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.27,
|
| 984 |
+
"eval_loss": 2.4818880558013916,
|
| 985 |
+
"eval_runtime": 55.0269,
|
| 986 |
+
"eval_samples_per_second": 120.468,
|
| 987 |
+
"eval_steps_per_second": 1.89,
|
| 988 |
+
"step": 70000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.32,
|
| 992 |
+
"learning_rate": 3.339181286549708e-05,
|
| 993 |
+
"loss": 1.088,
|
| 994 |
+
"step": 71000
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.32,
|
| 998 |
+
"eval_loss": 2.4609289169311523,
|
| 999 |
+
"eval_runtime": 54.9477,
|
| 1000 |
+
"eval_samples_per_second": 120.642,
|
| 1001 |
+
"eval_steps_per_second": 1.893,
|
| 1002 |
+
"step": 71000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.37,
|
| 1006 |
+
"learning_rate": 3.3157894736842106e-05,
|
| 1007 |
+
"loss": 1.0728,
|
| 1008 |
+
"step": 72000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.37,
|
| 1012 |
+
"eval_loss": 2.4839322566986084,
|
| 1013 |
+
"eval_runtime": 54.9672,
|
| 1014 |
+
"eval_samples_per_second": 120.599,
|
| 1015 |
+
"eval_steps_per_second": 1.892,
|
| 1016 |
+
"step": 72000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.42,
|
| 1020 |
+
"learning_rate": 3.292397660818713e-05,
|
| 1021 |
+
"loss": 1.0587,
|
| 1022 |
+
"step": 73000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.42,
|
| 1026 |
+
"eval_loss": 2.4727675914764404,
|
| 1027 |
+
"eval_runtime": 55.0507,
|
| 1028 |
+
"eval_samples_per_second": 120.416,
|
| 1029 |
+
"eval_steps_per_second": 1.889,
|
| 1030 |
+
"step": 73000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.46,
|
| 1034 |
+
"learning_rate": 3.2690058479532164e-05,
|
| 1035 |
+
"loss": 1.0534,
|
| 1036 |
+
"step": 74000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.46,
|
| 1040 |
+
"eval_loss": 2.4812207221984863,
|
| 1041 |
+
"eval_runtime": 54.9899,
|
| 1042 |
+
"eval_samples_per_second": 120.549,
|
| 1043 |
+
"eval_steps_per_second": 1.891,
|
| 1044 |
+
"step": 74000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.51,
|
| 1048 |
+
"learning_rate": 3.24561403508772e-05,
|
| 1049 |
+
"loss": 1.0455,
|
| 1050 |
+
"step": 75000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.51,
|
| 1054 |
+
"eval_loss": 2.469550609588623,
|
| 1055 |
+
"eval_runtime": 54.9765,
|
| 1056 |
+
"eval_samples_per_second": 120.579,
|
| 1057 |
+
"eval_steps_per_second": 1.892,
|
| 1058 |
+
"step": 75000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.56,
|
| 1062 |
+
"learning_rate": 3.222222222222223e-05,
|
| 1063 |
+
"loss": 1.0402,
|
| 1064 |
+
"step": 76000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.56,
|
| 1068 |
+
"eval_loss": 2.458113431930542,
|
| 1069 |
+
"eval_runtime": 54.9925,
|
| 1070 |
+
"eval_samples_per_second": 120.544,
|
| 1071 |
+
"eval_steps_per_second": 1.891,
|
| 1072 |
+
"step": 76000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.6,
|
| 1076 |
+
"learning_rate": 3.198830409356725e-05,
|
| 1077 |
+
"loss": 1.0227,
|
| 1078 |
+
"step": 77000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.6,
|
| 1082 |
+
"eval_loss": 2.4712133407592773,
|
| 1083 |
+
"eval_runtime": 54.9707,
|
| 1084 |
+
"eval_samples_per_second": 120.592,
|
| 1085 |
+
"eval_steps_per_second": 1.892,
|
| 1086 |
+
"step": 77000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 3.65,
|
| 1090 |
+
"learning_rate": 3.175438596491228e-05,
|
| 1091 |
+
"loss": 1.0172,
|
| 1092 |
+
"step": 78000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.65,
|
| 1096 |
+
"eval_loss": 2.4822046756744385,
|
| 1097 |
+
"eval_runtime": 54.9842,
|
| 1098 |
+
"eval_samples_per_second": 120.562,
|
| 1099 |
+
"eval_steps_per_second": 1.891,
|
| 1100 |
+
"step": 78000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.7,
|
| 1104 |
+
"learning_rate": 3.152046783625731e-05,
|
| 1105 |
+
"loss": 0.9947,
|
| 1106 |
+
"step": 79000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.7,
|
| 1110 |
+
"eval_loss": 2.455008029937744,
|
| 1111 |
+
"eval_runtime": 54.9636,
|
| 1112 |
+
"eval_samples_per_second": 120.607,
|
| 1113 |
+
"eval_steps_per_second": 1.892,
|
| 1114 |
+
"step": 79000
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 3.74,
|
| 1118 |
+
"learning_rate": 3.128654970760234e-05,
|
| 1119 |
+
"loss": 0.9924,
|
| 1120 |
+
"step": 80000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.74,
|
| 1124 |
+
"eval_loss": 2.440960168838501,
|
| 1125 |
+
"eval_runtime": 54.9708,
|
| 1126 |
+
"eval_samples_per_second": 120.591,
|
| 1127 |
+
"eval_steps_per_second": 1.892,
|
| 1128 |
+
"step": 80000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 3.79,
|
| 1132 |
+
"learning_rate": 3.105263157894737e-05,
|
| 1133 |
+
"loss": 0.9863,
|
| 1134 |
+
"step": 81000
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.79,
|
| 1138 |
+
"eval_loss": 2.454493761062622,
|
| 1139 |
+
"eval_runtime": 54.966,
|
| 1140 |
+
"eval_samples_per_second": 120.602,
|
| 1141 |
+
"eval_steps_per_second": 1.892,
|
| 1142 |
+
"step": 81000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.84,
|
| 1146 |
+
"learning_rate": 3.08187134502924e-05,
|
| 1147 |
+
"loss": 0.9793,
|
| 1148 |
+
"step": 82000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.84,
|
| 1152 |
+
"eval_loss": 2.482584238052368,
|
| 1153 |
+
"eval_runtime": 55.0651,
|
| 1154 |
+
"eval_samples_per_second": 120.385,
|
| 1155 |
+
"eval_steps_per_second": 1.889,
|
| 1156 |
+
"step": 82000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 3.88,
|
| 1160 |
+
"learning_rate": 3.058479532163743e-05,
|
| 1161 |
+
"loss": 0.9639,
|
| 1162 |
+
"step": 83000
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.88,
|
| 1166 |
+
"eval_loss": 2.4847776889801025,
|
| 1167 |
+
"eval_runtime": 55.089,
|
| 1168 |
+
"eval_samples_per_second": 120.332,
|
| 1169 |
+
"eval_steps_per_second": 1.888,
|
| 1170 |
+
"step": 83000
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 3.93,
|
| 1174 |
+
"learning_rate": 3.035087719298246e-05,
|
| 1175 |
+
"loss": 0.9584,
|
| 1176 |
+
"step": 84000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.93,
|
| 1180 |
+
"eval_loss": 2.4647934436798096,
|
| 1181 |
+
"eval_runtime": 55.1206,
|
| 1182 |
+
"eval_samples_per_second": 120.263,
|
| 1183 |
+
"eval_steps_per_second": 1.887,
|
| 1184 |
+
"step": 84000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 3.98,
|
| 1188 |
+
"learning_rate": 3.0116959064327488e-05,
|
| 1189 |
+
"loss": 0.9508,
|
| 1190 |
+
"step": 85000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.98,
|
| 1194 |
+
"eval_loss": 2.445103406906128,
|
| 1195 |
+
"eval_runtime": 55.0978,
|
| 1196 |
+
"eval_samples_per_second": 120.313,
|
| 1197 |
+
"eval_steps_per_second": 1.888,
|
| 1198 |
+
"step": 85000
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 4.02,
|
| 1202 |
+
"learning_rate": 2.9883040935672517e-05,
|
| 1203 |
+
"loss": 0.9425,
|
| 1204 |
+
"step": 86000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 4.02,
|
| 1208 |
+
"eval_loss": 2.4363410472869873,
|
| 1209 |
+
"eval_runtime": 55.0773,
|
| 1210 |
+
"eval_samples_per_second": 120.358,
|
| 1211 |
+
"eval_steps_per_second": 1.888,
|
| 1212 |
+
"step": 86000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 4.07,
|
| 1216 |
+
"learning_rate": 2.9649122807017543e-05,
|
| 1217 |
+
"loss": 0.9301,
|
| 1218 |
+
"step": 87000
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 4.07,
|
| 1222 |
+
"eval_loss": 2.4576821327209473,
|
| 1223 |
+
"eval_runtime": 55.0908,
|
| 1224 |
+
"eval_samples_per_second": 120.329,
|
| 1225 |
+
"eval_steps_per_second": 1.888,
|
| 1226 |
+
"step": 87000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.12,
|
| 1230 |
+
"learning_rate": 2.9415204678362572e-05,
|
| 1231 |
+
"loss": 0.922,
|
| 1232 |
+
"step": 88000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.12,
|
| 1236 |
+
"eval_loss": 2.487666130065918,
|
| 1237 |
+
"eval_runtime": 55.1028,
|
| 1238 |
+
"eval_samples_per_second": 120.302,
|
| 1239 |
+
"eval_steps_per_second": 1.887,
|
| 1240 |
+
"step": 88000
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 4.16,
|
| 1244 |
+
"learning_rate": 2.9181286549707604e-05,
|
| 1245 |
+
"loss": 0.9102,
|
| 1246 |
+
"step": 89000
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.16,
|
| 1250 |
+
"eval_loss": 2.462902784347534,
|
| 1251 |
+
"eval_runtime": 55.0955,
|
| 1252 |
+
"eval_samples_per_second": 120.318,
|
| 1253 |
+
"eval_steps_per_second": 1.888,
|
| 1254 |
+
"step": 89000
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 4.21,
|
| 1258 |
+
"learning_rate": 2.8947368421052634e-05,
|
| 1259 |
+
"loss": 0.9081,
|
| 1260 |
+
"step": 90000
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.21,
|
| 1264 |
+
"eval_loss": 2.4494595527648926,
|
| 1265 |
+
"eval_runtime": 55.0849,
|
| 1266 |
+
"eval_samples_per_second": 120.341,
|
| 1267 |
+
"eval_steps_per_second": 1.888,
|
| 1268 |
+
"step": 90000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.26,
|
| 1272 |
+
"learning_rate": 2.8713450292397666e-05,
|
| 1273 |
+
"loss": 0.8956,
|
| 1274 |
+
"step": 91000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.26,
|
| 1278 |
+
"eval_loss": 2.466681718826294,
|
| 1279 |
+
"eval_runtime": 55.0767,
|
| 1280 |
+
"eval_samples_per_second": 120.359,
|
| 1281 |
+
"eval_steps_per_second": 1.888,
|
| 1282 |
+
"step": 91000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 4.3,
|
| 1286 |
+
"learning_rate": 2.847953216374269e-05,
|
| 1287 |
+
"loss": 0.8932,
|
| 1288 |
+
"step": 92000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.3,
|
| 1292 |
+
"eval_loss": 2.4637372493743896,
|
| 1293 |
+
"eval_runtime": 55.0713,
|
| 1294 |
+
"eval_samples_per_second": 120.371,
|
| 1295 |
+
"eval_steps_per_second": 1.888,
|
| 1296 |
+
"step": 92000
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 4.35,
|
| 1300 |
+
"learning_rate": 2.824561403508772e-05,
|
| 1301 |
+
"loss": 0.8845,
|
| 1302 |
+
"step": 93000
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.35,
|
| 1306 |
+
"eval_loss": 2.4586174488067627,
|
| 1307 |
+
"eval_runtime": 55.0741,
|
| 1308 |
+
"eval_samples_per_second": 120.365,
|
| 1309 |
+
"eval_steps_per_second": 1.888,
|
| 1310 |
+
"step": 93000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.4,
|
| 1314 |
+
"learning_rate": 2.801169590643275e-05,
|
| 1315 |
+
"loss": 0.877,
|
| 1316 |
+
"step": 94000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.4,
|
| 1320 |
+
"eval_loss": 2.471717357635498,
|
| 1321 |
+
"eval_runtime": 55.0727,
|
| 1322 |
+
"eval_samples_per_second": 120.368,
|
| 1323 |
+
"eval_steps_per_second": 1.888,
|
| 1324 |
+
"step": 94000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 4.44,
|
| 1328 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1329 |
+
"loss": 0.8713,
|
| 1330 |
+
"step": 95000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.44,
|
| 1334 |
+
"eval_loss": 2.4618284702301025,
|
| 1335 |
+
"eval_runtime": 55.0799,
|
| 1336 |
+
"eval_samples_per_second": 120.352,
|
| 1337 |
+
"eval_steps_per_second": 1.888,
|
| 1338 |
+
"step": 95000
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 4.49,
|
| 1342 |
+
"learning_rate": 2.754385964912281e-05,
|
| 1343 |
+
"loss": 0.8768,
|
| 1344 |
+
"step": 96000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.49,
|
| 1348 |
+
"eval_loss": 2.4480040073394775,
|
| 1349 |
+
"eval_runtime": 55.1696,
|
| 1350 |
+
"eval_samples_per_second": 120.157,
|
| 1351 |
+
"eval_steps_per_second": 1.885,
|
| 1352 |
+
"step": 96000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 4.54,
|
| 1356 |
+
"learning_rate": 2.7309941520467834e-05,
|
| 1357 |
+
"loss": 0.8662,
|
| 1358 |
+
"step": 97000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.54,
|
| 1362 |
+
"eval_loss": 2.468902349472046,
|
| 1363 |
+
"eval_runtime": 55.1714,
|
| 1364 |
+
"eval_samples_per_second": 120.153,
|
| 1365 |
+
"eval_steps_per_second": 1.885,
|
| 1366 |
+
"step": 97000
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 4.58,
|
| 1370 |
+
"learning_rate": 2.7076023391812866e-05,
|
| 1371 |
+
"loss": 0.8622,
|
| 1372 |
+
"step": 98000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 4.58,
|
| 1376 |
+
"eval_loss": 2.4613983631134033,
|
| 1377 |
+
"eval_runtime": 55.1613,
|
| 1378 |
+
"eval_samples_per_second": 120.175,
|
| 1379 |
+
"eval_steps_per_second": 1.885,
|
| 1380 |
+
"step": 98000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 4.63,
|
| 1384 |
+
"learning_rate": 2.6842105263157896e-05,
|
| 1385 |
+
"loss": 0.8497,
|
| 1386 |
+
"step": 99000
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.63,
|
| 1390 |
+
"eval_loss": 2.488284111022949,
|
| 1391 |
+
"eval_runtime": 55.1664,
|
| 1392 |
+
"eval_samples_per_second": 120.164,
|
| 1393 |
+
"eval_steps_per_second": 1.885,
|
| 1394 |
+
"step": 99000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 4.68,
|
| 1398 |
+
"learning_rate": 2.6608187134502928e-05,
|
| 1399 |
+
"loss": 0.8399,
|
| 1400 |
+
"step": 100000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.68,
|
| 1404 |
+
"eval_loss": 2.486598253250122,
|
| 1405 |
+
"eval_runtime": 55.142,
|
| 1406 |
+
"eval_samples_per_second": 120.217,
|
| 1407 |
+
"eval_steps_per_second": 1.886,
|
| 1408 |
+
"step": 100000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 4.73,
|
| 1412 |
+
"learning_rate": 2.6374269005847957e-05,
|
| 1413 |
+
"loss": 0.8397,
|
| 1414 |
+
"step": 101000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 4.73,
|
| 1418 |
+
"eval_loss": 2.490933895111084,
|
| 1419 |
+
"eval_runtime": 55.1377,
|
| 1420 |
+
"eval_samples_per_second": 120.226,
|
| 1421 |
+
"eval_steps_per_second": 1.886,
|
| 1422 |
+
"step": 101000
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 4.77,
|
| 1426 |
+
"learning_rate": 2.6140350877192983e-05,
|
| 1427 |
+
"loss": 0.8266,
|
| 1428 |
+
"step": 102000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.77,
|
| 1432 |
+
"eval_loss": 2.4587643146514893,
|
| 1433 |
+
"eval_runtime": 55.0944,
|
| 1434 |
+
"eval_samples_per_second": 120.321,
|
| 1435 |
+
"eval_steps_per_second": 1.888,
|
| 1436 |
+
"step": 102000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 4.82,
|
| 1440 |
+
"learning_rate": 2.5906432748538012e-05,
|
| 1441 |
+
"loss": 0.8231,
|
| 1442 |
+
"step": 103000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 4.82,
|
| 1446 |
+
"eval_loss": 2.4951488971710205,
|
| 1447 |
+
"eval_runtime": 55.155,
|
| 1448 |
+
"eval_samples_per_second": 120.189,
|
| 1449 |
+
"eval_steps_per_second": 1.886,
|
| 1450 |
+
"step": 103000
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 4.87,
|
| 1454 |
+
"learning_rate": 2.567251461988304e-05,
|
| 1455 |
+
"loss": 0.8189,
|
| 1456 |
+
"step": 104000
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 4.87,
|
| 1460 |
+
"eval_loss": 2.458134889602661,
|
| 1461 |
+
"eval_runtime": 55.0735,
|
| 1462 |
+
"eval_samples_per_second": 120.366,
|
| 1463 |
+
"eval_steps_per_second": 1.888,
|
| 1464 |
+
"step": 104000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 4.91,
|
| 1468 |
+
"learning_rate": 2.5438596491228074e-05,
|
| 1469 |
+
"loss": 0.8155,
|
| 1470 |
+
"step": 105000
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 4.91,
|
| 1474 |
+
"eval_loss": 2.448225736618042,
|
| 1475 |
+
"eval_runtime": 55.0955,
|
| 1476 |
+
"eval_samples_per_second": 120.318,
|
| 1477 |
+
"eval_steps_per_second": 1.888,
|
| 1478 |
+
"step": 105000
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 4.96,
|
| 1482 |
+
"learning_rate": 2.5204678362573103e-05,
|
| 1483 |
+
"loss": 0.8059,
|
| 1484 |
+
"step": 106000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 4.96,
|
| 1488 |
+
"eval_loss": 2.489133358001709,
|
| 1489 |
+
"eval_runtime": 55.1106,
|
| 1490 |
+
"eval_samples_per_second": 120.285,
|
| 1491 |
+
"eval_steps_per_second": 1.887,
|
| 1492 |
+
"step": 106000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 5.01,
|
| 1496 |
+
"learning_rate": 2.4970760233918132e-05,
|
| 1497 |
+
"loss": 0.8085,
|
| 1498 |
+
"step": 107000
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 5.01,
|
| 1502 |
+
"eval_loss": 2.491405487060547,
|
| 1503 |
+
"eval_runtime": 55.0557,
|
| 1504 |
+
"eval_samples_per_second": 120.405,
|
| 1505 |
+
"eval_steps_per_second": 1.889,
|
| 1506 |
+
"step": 107000
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 5.05,
|
| 1510 |
+
"learning_rate": 2.4736842105263158e-05,
|
| 1511 |
+
"loss": 0.7851,
|
| 1512 |
+
"step": 108000
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 5.05,
|
| 1516 |
+
"eval_loss": 2.486567735671997,
|
| 1517 |
+
"eval_runtime": 55.0714,
|
| 1518 |
+
"eval_samples_per_second": 120.371,
|
| 1519 |
+
"eval_steps_per_second": 1.888,
|
| 1520 |
+
"step": 108000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.1,
|
| 1524 |
+
"learning_rate": 2.450292397660819e-05,
|
| 1525 |
+
"loss": 0.7827,
|
| 1526 |
+
"step": 109000
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 5.1,
|
| 1530 |
+
"eval_loss": 2.480097532272339,
|
| 1531 |
+
"eval_runtime": 55.0814,
|
| 1532 |
+
"eval_samples_per_second": 120.349,
|
| 1533 |
+
"eval_steps_per_second": 1.888,
|
| 1534 |
+
"step": 109000
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 5.15,
|
| 1538 |
+
"learning_rate": 2.4269005847953216e-05,
|
| 1539 |
+
"loss": 0.7813,
|
| 1540 |
+
"step": 110000
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 5.15,
|
| 1544 |
+
"eval_loss": 2.4855968952178955,
|
| 1545 |
+
"eval_runtime": 55.078,
|
| 1546 |
+
"eval_samples_per_second": 120.357,
|
| 1547 |
+
"eval_steps_per_second": 1.888,
|
| 1548 |
+
"step": 110000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 5.19,
|
| 1552 |
+
"learning_rate": 2.4035087719298245e-05,
|
| 1553 |
+
"loss": 0.7829,
|
| 1554 |
+
"step": 111000
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 5.19,
|
| 1558 |
+
"eval_loss": 2.462341785430908,
|
| 1559 |
+
"eval_runtime": 55.0705,
|
| 1560 |
+
"eval_samples_per_second": 120.373,
|
| 1561 |
+
"eval_steps_per_second": 1.888,
|
| 1562 |
+
"step": 111000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 5.24,
|
| 1566 |
+
"learning_rate": 2.3801169590643278e-05,
|
| 1567 |
+
"loss": 0.7724,
|
| 1568 |
+
"step": 112000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 5.24,
|
| 1572 |
+
"eval_loss": 2.478029251098633,
|
| 1573 |
+
"eval_runtime": 55.0837,
|
| 1574 |
+
"eval_samples_per_second": 120.344,
|
| 1575 |
+
"eval_steps_per_second": 1.888,
|
| 1576 |
+
"step": 112000
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 5.29,
|
| 1580 |
+
"learning_rate": 2.3567251461988303e-05,
|
| 1581 |
+
"loss": 0.7646,
|
| 1582 |
+
"step": 113000
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 5.29,
|
| 1586 |
+
"eval_loss": 2.4587323665618896,
|
| 1587 |
+
"eval_runtime": 55.1053,
|
| 1588 |
+
"eval_samples_per_second": 120.297,
|
| 1589 |
+
"eval_steps_per_second": 1.887,
|
| 1590 |
+
"step": 113000
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 5.33,
|
| 1594 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 1595 |
+
"loss": 0.7604,
|
| 1596 |
+
"step": 114000
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 5.33,
|
| 1600 |
+
"eval_loss": 2.453984498977661,
|
| 1601 |
+
"eval_runtime": 55.0903,
|
| 1602 |
+
"eval_samples_per_second": 120.33,
|
| 1603 |
+
"eval_steps_per_second": 1.888,
|
| 1604 |
+
"step": 114000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.38,
|
| 1608 |
+
"learning_rate": 2.309941520467836e-05,
|
| 1609 |
+
"loss": 0.7518,
|
| 1610 |
+
"step": 115000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 5.38,
|
| 1614 |
+
"eval_loss": 2.488924026489258,
|
| 1615 |
+
"eval_runtime": 55.1009,
|
| 1616 |
+
"eval_samples_per_second": 120.307,
|
| 1617 |
+
"eval_steps_per_second": 1.887,
|
| 1618 |
+
"step": 115000
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 5.43,
|
| 1622 |
+
"learning_rate": 2.2865497076023394e-05,
|
| 1623 |
+
"loss": 0.7515,
|
| 1624 |
+
"step": 116000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 5.43,
|
| 1628 |
+
"eval_loss": 2.4510860443115234,
|
| 1629 |
+
"eval_runtime": 55.088,
|
| 1630 |
+
"eval_samples_per_second": 120.335,
|
| 1631 |
+
"eval_steps_per_second": 1.888,
|
| 1632 |
+
"step": 116000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 5.47,
|
| 1636 |
+
"learning_rate": 2.2631578947368423e-05,
|
| 1637 |
+
"loss": 0.7511,
|
| 1638 |
+
"step": 117000
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 5.47,
|
| 1642 |
+
"eval_loss": 2.468933343887329,
|
| 1643 |
+
"eval_runtime": 55.0676,
|
| 1644 |
+
"eval_samples_per_second": 120.379,
|
| 1645 |
+
"eval_steps_per_second": 1.889,
|
| 1646 |
+
"step": 117000
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 5.52,
|
| 1650 |
+
"learning_rate": 2.2397660818713452e-05,
|
| 1651 |
+
"loss": 0.7424,
|
| 1652 |
+
"step": 118000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 5.52,
|
| 1656 |
+
"eval_loss": 2.4676008224487305,
|
| 1657 |
+
"eval_runtime": 55.1052,
|
| 1658 |
+
"eval_samples_per_second": 120.297,
|
| 1659 |
+
"eval_steps_per_second": 1.887,
|
| 1660 |
+
"step": 118000
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 5.57,
|
| 1664 |
+
"learning_rate": 2.216374269005848e-05,
|
| 1665 |
+
"loss": 0.7327,
|
| 1666 |
+
"step": 119000
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 5.57,
|
| 1670 |
+
"eval_loss": 2.482384443283081,
|
| 1671 |
+
"eval_runtime": 55.0883,
|
| 1672 |
+
"eval_samples_per_second": 120.334,
|
| 1673 |
+
"eval_steps_per_second": 1.888,
|
| 1674 |
+
"step": 119000
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 5.61,
|
| 1678 |
+
"learning_rate": 2.1929824561403507e-05,
|
| 1679 |
+
"loss": 0.7349,
|
| 1680 |
+
"step": 120000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 5.61,
|
| 1684 |
+
"eval_loss": 2.450364351272583,
|
| 1685 |
+
"eval_runtime": 55.0642,
|
| 1686 |
+
"eval_samples_per_second": 120.387,
|
| 1687 |
+
"eval_steps_per_second": 1.889,
|
| 1688 |
+
"step": 120000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 5.66,
|
| 1692 |
+
"learning_rate": 2.169590643274854e-05,
|
| 1693 |
+
"loss": 0.7307,
|
| 1694 |
+
"step": 121000
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 5.66,
|
| 1698 |
+
"eval_loss": 2.4753456115722656,
|
| 1699 |
+
"eval_runtime": 55.0827,
|
| 1700 |
+
"eval_samples_per_second": 120.346,
|
| 1701 |
+
"eval_steps_per_second": 1.888,
|
| 1702 |
+
"step": 121000
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 5.71,
|
| 1706 |
+
"learning_rate": 2.146198830409357e-05,
|
| 1707 |
+
"loss": 0.7269,
|
| 1708 |
+
"step": 122000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 5.71,
|
| 1712 |
+
"eval_loss": 2.463690757751465,
|
| 1713 |
+
"eval_runtime": 55.087,
|
| 1714 |
+
"eval_samples_per_second": 120.337,
|
| 1715 |
+
"eval_steps_per_second": 1.888,
|
| 1716 |
+
"step": 122000
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 5.75,
|
| 1720 |
+
"learning_rate": 2.1228070175438598e-05,
|
| 1721 |
+
"loss": 0.7175,
|
| 1722 |
+
"step": 123000
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 5.75,
|
| 1726 |
+
"eval_loss": 2.4744393825531006,
|
| 1727 |
+
"eval_runtime": 55.0809,
|
| 1728 |
+
"eval_samples_per_second": 120.35,
|
| 1729 |
+
"eval_steps_per_second": 1.888,
|
| 1730 |
+
"step": 123000
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 5.8,
|
| 1734 |
+
"learning_rate": 2.0994152046783627e-05,
|
| 1735 |
+
"loss": 0.7178,
|
| 1736 |
+
"step": 124000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 5.8,
|
| 1740 |
+
"eval_loss": 2.4851980209350586,
|
| 1741 |
+
"eval_runtime": 55.0877,
|
| 1742 |
+
"eval_samples_per_second": 120.335,
|
| 1743 |
+
"eval_steps_per_second": 1.888,
|
| 1744 |
+
"step": 124000
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 5.85,
|
| 1748 |
+
"learning_rate": 2.0760233918128656e-05,
|
| 1749 |
+
"loss": 0.7048,
|
| 1750 |
+
"step": 125000
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 5.85,
|
| 1754 |
+
"eval_loss": 2.5102007389068604,
|
| 1755 |
+
"eval_runtime": 55.1078,
|
| 1756 |
+
"eval_samples_per_second": 120.291,
|
| 1757 |
+
"eval_steps_per_second": 1.887,
|
| 1758 |
+
"step": 125000
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 5.89,
|
| 1762 |
+
"learning_rate": 2.0526315789473685e-05,
|
| 1763 |
+
"loss": 0.7072,
|
| 1764 |
+
"step": 126000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 5.89,
|
| 1768 |
+
"eval_loss": 2.5026237964630127,
|
| 1769 |
+
"eval_runtime": 55.1176,
|
| 1770 |
+
"eval_samples_per_second": 120.27,
|
| 1771 |
+
"eval_steps_per_second": 1.887,
|
| 1772 |
+
"step": 126000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 5.94,
|
| 1776 |
+
"learning_rate": 2.0292397660818714e-05,
|
| 1777 |
+
"loss": 0.7054,
|
| 1778 |
+
"step": 127000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 5.94,
|
| 1782 |
+
"eval_loss": 2.4804298877716064,
|
| 1783 |
+
"eval_runtime": 55.0663,
|
| 1784 |
+
"eval_samples_per_second": 120.382,
|
| 1785 |
+
"eval_steps_per_second": 1.889,
|
| 1786 |
+
"step": 127000
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 5.99,
|
| 1790 |
+
"learning_rate": 2.0058479532163744e-05,
|
| 1791 |
+
"loss": 0.7019,
|
| 1792 |
+
"step": 128000
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 5.99,
|
| 1796 |
+
"eval_loss": 2.4398744106292725,
|
| 1797 |
+
"eval_runtime": 54.9972,
|
| 1798 |
+
"eval_samples_per_second": 120.533,
|
| 1799 |
+
"eval_steps_per_second": 1.891,
|
| 1800 |
+
"step": 128000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 6.03,
|
| 1804 |
+
"learning_rate": 1.9824561403508773e-05,
|
| 1805 |
+
"loss": 0.6942,
|
| 1806 |
+
"step": 129000
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 6.03,
|
| 1810 |
+
"eval_loss": 2.4618844985961914,
|
| 1811 |
+
"eval_runtime": 55.1004,
|
| 1812 |
+
"eval_samples_per_second": 120.308,
|
| 1813 |
+
"eval_steps_per_second": 1.887,
|
| 1814 |
+
"step": 129000
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 6.08,
|
| 1818 |
+
"learning_rate": 1.9590643274853802e-05,
|
| 1819 |
+
"loss": 0.6842,
|
| 1820 |
+
"step": 130000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 6.08,
|
| 1824 |
+
"eval_loss": 2.496403217315674,
|
| 1825 |
+
"eval_runtime": 55.0871,
|
| 1826 |
+
"eval_samples_per_second": 120.337,
|
| 1827 |
+
"eval_steps_per_second": 1.888,
|
| 1828 |
+
"step": 130000
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 6.13,
|
| 1832 |
+
"learning_rate": 1.935672514619883e-05,
|
| 1833 |
+
"loss": 0.6859,
|
| 1834 |
+
"step": 131000
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 6.13,
|
| 1838 |
+
"eval_loss": 2.483705520629883,
|
| 1839 |
+
"eval_runtime": 55.0869,
|
| 1840 |
+
"eval_samples_per_second": 120.337,
|
| 1841 |
+
"eval_steps_per_second": 1.888,
|
| 1842 |
+
"step": 131000
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 6.18,
|
| 1846 |
+
"learning_rate": 1.9122807017543863e-05,
|
| 1847 |
+
"loss": 0.6742,
|
| 1848 |
+
"step": 132000
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 6.18,
|
| 1852 |
+
"eval_loss": 2.489377498626709,
|
| 1853 |
+
"eval_runtime": 55.1198,
|
| 1854 |
+
"eval_samples_per_second": 120.265,
|
| 1855 |
+
"eval_steps_per_second": 1.887,
|
| 1856 |
+
"step": 132000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 6.22,
|
| 1860 |
+
"learning_rate": 1.888888888888889e-05,
|
| 1861 |
+
"loss": 0.6818,
|
| 1862 |
+
"step": 133000
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 6.22,
|
| 1866 |
+
"eval_loss": 2.507904052734375,
|
| 1867 |
+
"eval_runtime": 55.1222,
|
| 1868 |
+
"eval_samples_per_second": 120.26,
|
| 1869 |
+
"eval_steps_per_second": 1.887,
|
| 1870 |
+
"step": 133000
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 6.27,
|
| 1874 |
+
"learning_rate": 1.8654970760233918e-05,
|
| 1875 |
+
"loss": 0.6742,
|
| 1876 |
+
"step": 134000
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 6.27,
|
| 1880 |
+
"eval_loss": 2.4935832023620605,
|
| 1881 |
+
"eval_runtime": 55.1223,
|
| 1882 |
+
"eval_samples_per_second": 120.26,
|
| 1883 |
+
"eval_steps_per_second": 1.887,
|
| 1884 |
+
"step": 134000
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 6.32,
|
| 1888 |
+
"learning_rate": 1.8421052631578947e-05,
|
| 1889 |
+
"loss": 0.6756,
|
| 1890 |
+
"step": 135000
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 6.32,
|
| 1894 |
+
"eval_loss": 2.512763023376465,
|
| 1895 |
+
"eval_runtime": 55.167,
|
| 1896 |
+
"eval_samples_per_second": 120.162,
|
| 1897 |
+
"eval_steps_per_second": 1.885,
|
| 1898 |
+
"step": 135000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 6.36,
|
| 1902 |
+
"learning_rate": 1.8187134502923976e-05,
|
| 1903 |
+
"loss": 0.6635,
|
| 1904 |
+
"step": 136000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 6.36,
|
| 1908 |
+
"eval_loss": 2.5170469284057617,
|
| 1909 |
+
"eval_runtime": 55.1756,
|
| 1910 |
+
"eval_samples_per_second": 120.144,
|
| 1911 |
+
"eval_steps_per_second": 1.885,
|
| 1912 |
+
"step": 136000
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 6.41,
|
| 1916 |
+
"learning_rate": 1.795321637426901e-05,
|
| 1917 |
+
"loss": 0.6645,
|
| 1918 |
+
"step": 137000
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 6.41,
|
| 1922 |
+
"eval_loss": 2.5008370876312256,
|
| 1923 |
+
"eval_runtime": 55.1095,
|
| 1924 |
+
"eval_samples_per_second": 120.288,
|
| 1925 |
+
"eval_steps_per_second": 1.887,
|
| 1926 |
+
"step": 137000
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 6.46,
|
| 1930 |
+
"learning_rate": 1.7719298245614035e-05,
|
| 1931 |
+
"loss": 0.6617,
|
| 1932 |
+
"step": 138000
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 6.46,
|
| 1936 |
+
"eval_loss": 2.503709316253662,
|
| 1937 |
+
"eval_runtime": 55.1047,
|
| 1938 |
+
"eval_samples_per_second": 120.298,
|
| 1939 |
+
"eval_steps_per_second": 1.887,
|
| 1940 |
+
"step": 138000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 6.5,
|
| 1944 |
+
"learning_rate": 1.7485380116959067e-05,
|
| 1945 |
+
"loss": 0.6574,
|
| 1946 |
+
"step": 139000
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 6.5,
|
| 1950 |
+
"eval_loss": 2.4953572750091553,
|
| 1951 |
+
"eval_runtime": 55.0727,
|
| 1952 |
+
"eval_samples_per_second": 120.368,
|
| 1953 |
+
"eval_steps_per_second": 1.888,
|
| 1954 |
+
"step": 139000
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 6.55,
|
| 1958 |
+
"learning_rate": 1.7251461988304093e-05,
|
| 1959 |
+
"loss": 0.6519,
|
| 1960 |
+
"step": 140000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 6.55,
|
| 1964 |
+
"eval_loss": 2.519571304321289,
|
| 1965 |
+
"eval_runtime": 55.1072,
|
| 1966 |
+
"eval_samples_per_second": 120.293,
|
| 1967 |
+
"eval_steps_per_second": 1.887,
|
| 1968 |
+
"step": 140000
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 6.6,
|
| 1972 |
+
"learning_rate": 1.7017543859649125e-05,
|
| 1973 |
+
"loss": 0.6453,
|
| 1974 |
+
"step": 141000
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 6.6,
|
| 1978 |
+
"eval_loss": 2.485342502593994,
|
| 1979 |
+
"eval_runtime": 55.0939,
|
| 1980 |
+
"eval_samples_per_second": 120.322,
|
| 1981 |
+
"eval_steps_per_second": 1.888,
|
| 1982 |
+
"step": 141000
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 6.64,
|
| 1986 |
+
"learning_rate": 1.6783625730994155e-05,
|
| 1987 |
+
"loss": 0.6445,
|
| 1988 |
+
"step": 142000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 6.64,
|
| 1992 |
+
"eval_loss": 2.485079765319824,
|
| 1993 |
+
"eval_runtime": 55.093,
|
| 1994 |
+
"eval_samples_per_second": 120.324,
|
| 1995 |
+
"eval_steps_per_second": 1.888,
|
| 1996 |
+
"step": 142000
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 6.69,
|
| 2000 |
+
"learning_rate": 1.654970760233918e-05,
|
| 2001 |
+
"loss": 0.643,
|
| 2002 |
+
"step": 143000
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 6.69,
|
| 2006 |
+
"eval_loss": 2.4923973083496094,
|
| 2007 |
+
"eval_runtime": 55.1032,
|
| 2008 |
+
"eval_samples_per_second": 120.302,
|
| 2009 |
+
"eval_steps_per_second": 1.887,
|
| 2010 |
+
"step": 143000
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 6.74,
|
| 2014 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 2015 |
+
"loss": 0.6373,
|
| 2016 |
+
"step": 144000
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 6.74,
|
| 2020 |
+
"eval_loss": 2.5037529468536377,
|
| 2021 |
+
"eval_runtime": 55.0798,
|
| 2022 |
+
"eval_samples_per_second": 120.353,
|
| 2023 |
+
"eval_steps_per_second": 1.888,
|
| 2024 |
+
"step": 144000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 6.78,
|
| 2028 |
+
"learning_rate": 1.608187134502924e-05,
|
| 2029 |
+
"loss": 0.6292,
|
| 2030 |
+
"step": 145000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 6.78,
|
| 2034 |
+
"eval_loss": 2.488449811935425,
|
| 2035 |
+
"eval_runtime": 55.097,
|
| 2036 |
+
"eval_samples_per_second": 120.315,
|
| 2037 |
+
"eval_steps_per_second": 1.888,
|
| 2038 |
+
"step": 145000
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 6.83,
|
| 2042 |
+
"learning_rate": 1.584795321637427e-05,
|
| 2043 |
+
"loss": 0.6386,
|
| 2044 |
+
"step": 146000
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 6.83,
|
| 2048 |
+
"eval_loss": 2.482603073120117,
|
| 2049 |
+
"eval_runtime": 55.1088,
|
| 2050 |
+
"eval_samples_per_second": 120.289,
|
| 2051 |
+
"eval_steps_per_second": 1.887,
|
| 2052 |
+
"step": 146000
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 6.88,
|
| 2056 |
+
"learning_rate": 1.56140350877193e-05,
|
| 2057 |
+
"loss": 0.6357,
|
| 2058 |
+
"step": 147000
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 6.88,
|
| 2062 |
+
"eval_loss": 2.482375144958496,
|
| 2063 |
+
"eval_runtime": 55.1247,
|
| 2064 |
+
"eval_samples_per_second": 120.255,
|
| 2065 |
+
"eval_steps_per_second": 1.887,
|
| 2066 |
+
"step": 147000
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 6.92,
|
| 2070 |
+
"learning_rate": 1.538011695906433e-05,
|
| 2071 |
+
"loss": 0.6251,
|
| 2072 |
+
"step": 148000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 6.92,
|
| 2076 |
+
"eval_loss": 2.4937736988067627,
|
| 2077 |
+
"eval_runtime": 55.1287,
|
| 2078 |
+
"eval_samples_per_second": 120.246,
|
| 2079 |
+
"eval_steps_per_second": 1.886,
|
| 2080 |
+
"step": 148000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 6.97,
|
| 2084 |
+
"learning_rate": 1.5146198830409358e-05,
|
| 2085 |
+
"loss": 0.624,
|
| 2086 |
+
"step": 149000
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 6.97,
|
| 2090 |
+
"eval_loss": 2.5023653507232666,
|
| 2091 |
+
"eval_runtime": 55.1273,
|
| 2092 |
+
"eval_samples_per_second": 120.249,
|
| 2093 |
+
"eval_steps_per_second": 1.887,
|
| 2094 |
+
"step": 149000
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 7.02,
|
| 2098 |
+
"learning_rate": 1.4912280701754386e-05,
|
| 2099 |
+
"loss": 0.6238,
|
| 2100 |
+
"step": 150000
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 7.02,
|
| 2104 |
+
"eval_loss": 2.520798444747925,
|
| 2105 |
+
"eval_runtime": 55.0799,
|
| 2106 |
+
"eval_samples_per_second": 120.352,
|
| 2107 |
+
"eval_steps_per_second": 1.888,
|
| 2108 |
+
"step": 150000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 7.06,
|
| 2112 |
+
"learning_rate": 1.4678362573099417e-05,
|
| 2113 |
+
"loss": 0.6165,
|
| 2114 |
+
"step": 151000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 7.06,
|
| 2118 |
+
"eval_loss": 2.5339748859405518,
|
| 2119 |
+
"eval_runtime": 55.1169,
|
| 2120 |
+
"eval_samples_per_second": 120.272,
|
| 2121 |
+
"eval_steps_per_second": 1.887,
|
| 2122 |
+
"step": 151000
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 7.11,
|
| 2126 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 2127 |
+
"loss": 0.6119,
|
| 2128 |
+
"step": 152000
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 7.11,
|
| 2132 |
+
"eval_loss": 2.5113964080810547,
|
| 2133 |
+
"eval_runtime": 55.0891,
|
| 2134 |
+
"eval_samples_per_second": 120.332,
|
| 2135 |
+
"eval_steps_per_second": 1.888,
|
| 2136 |
+
"step": 152000
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 7.16,
|
| 2140 |
+
"learning_rate": 1.4210526315789475e-05,
|
| 2141 |
+
"loss": 0.6089,
|
| 2142 |
+
"step": 153000
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 7.16,
|
| 2146 |
+
"eval_loss": 2.52811861038208,
|
| 2147 |
+
"eval_runtime": 55.112,
|
| 2148 |
+
"eval_samples_per_second": 120.282,
|
| 2149 |
+
"eval_steps_per_second": 1.887,
|
| 2150 |
+
"step": 153000
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 7.2,
|
| 2154 |
+
"learning_rate": 1.3976608187134504e-05,
|
| 2155 |
+
"loss": 0.6035,
|
| 2156 |
+
"step": 154000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 7.2,
|
| 2160 |
+
"eval_loss": 2.5194358825683594,
|
| 2161 |
+
"eval_runtime": 55.1145,
|
| 2162 |
+
"eval_samples_per_second": 120.277,
|
| 2163 |
+
"eval_steps_per_second": 1.887,
|
| 2164 |
+
"step": 154000
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 7.25,
|
| 2168 |
+
"learning_rate": 1.3742690058479531e-05,
|
| 2169 |
+
"loss": 0.6018,
|
| 2170 |
+
"step": 155000
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 7.25,
|
| 2174 |
+
"eval_loss": 2.5066628456115723,
|
| 2175 |
+
"eval_runtime": 55.0979,
|
| 2176 |
+
"eval_samples_per_second": 120.313,
|
| 2177 |
+
"eval_steps_per_second": 1.888,
|
| 2178 |
+
"step": 155000
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 7.3,
|
| 2182 |
+
"learning_rate": 1.3508771929824562e-05,
|
| 2183 |
+
"loss": 0.6016,
|
| 2184 |
+
"step": 156000
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 7.3,
|
| 2188 |
+
"eval_loss": 2.490973711013794,
|
| 2189 |
+
"eval_runtime": 54.9953,
|
| 2190 |
+
"eval_samples_per_second": 120.538,
|
| 2191 |
+
"eval_steps_per_second": 1.891,
|
| 2192 |
+
"step": 156000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 7.34,
|
| 2196 |
+
"learning_rate": 1.327485380116959e-05,
|
| 2197 |
+
"loss": 0.6013,
|
| 2198 |
+
"step": 157000
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 7.34,
|
| 2202 |
+
"eval_loss": 2.489246368408203,
|
| 2203 |
+
"eval_runtime": 54.9888,
|
| 2204 |
+
"eval_samples_per_second": 120.552,
|
| 2205 |
+
"eval_steps_per_second": 1.891,
|
| 2206 |
+
"step": 157000
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 7.39,
|
| 2210 |
+
"learning_rate": 1.304093567251462e-05,
|
| 2211 |
+
"loss": 0.5958,
|
| 2212 |
+
"step": 158000
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 7.39,
|
| 2216 |
+
"eval_loss": 2.528749704360962,
|
| 2217 |
+
"eval_runtime": 54.994,
|
| 2218 |
+
"eval_samples_per_second": 120.54,
|
| 2219 |
+
"eval_steps_per_second": 1.891,
|
| 2220 |
+
"step": 158000
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 7.44,
|
| 2224 |
+
"learning_rate": 1.2807017543859651e-05,
|
| 2225 |
+
"loss": 0.5925,
|
| 2226 |
+
"step": 159000
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 7.44,
|
| 2230 |
+
"eval_loss": 2.528515100479126,
|
| 2231 |
+
"eval_runtime": 54.9798,
|
| 2232 |
+
"eval_samples_per_second": 120.571,
|
| 2233 |
+
"eval_steps_per_second": 1.892,
|
| 2234 |
+
"step": 159000
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 7.49,
|
| 2238 |
+
"learning_rate": 1.2573099415204679e-05,
|
| 2239 |
+
"loss": 0.5908,
|
| 2240 |
+
"step": 160000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 7.49,
|
| 2244 |
+
"eval_loss": 2.510267734527588,
|
| 2245 |
+
"eval_runtime": 55.0014,
|
| 2246 |
+
"eval_samples_per_second": 120.524,
|
| 2247 |
+
"eval_steps_per_second": 1.891,
|
| 2248 |
+
"step": 160000
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 7.53,
|
| 2252 |
+
"learning_rate": 1.2339181286549708e-05,
|
| 2253 |
+
"loss": 0.587,
|
| 2254 |
+
"step": 161000
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 7.53,
|
| 2258 |
+
"eval_loss": 2.533625602722168,
|
| 2259 |
+
"eval_runtime": 54.9987,
|
| 2260 |
+
"eval_samples_per_second": 120.53,
|
| 2261 |
+
"eval_steps_per_second": 1.891,
|
| 2262 |
+
"step": 161000
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 7.58,
|
| 2266 |
+
"learning_rate": 1.2105263157894737e-05,
|
| 2267 |
+
"loss": 0.5851,
|
| 2268 |
+
"step": 162000
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 7.58,
|
| 2272 |
+
"eval_loss": 2.538762331008911,
|
| 2273 |
+
"eval_runtime": 54.9696,
|
| 2274 |
+
"eval_samples_per_second": 120.594,
|
| 2275 |
+
"eval_steps_per_second": 1.892,
|
| 2276 |
+
"step": 162000
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 7.63,
|
| 2280 |
+
"learning_rate": 1.1871345029239766e-05,
|
| 2281 |
+
"loss": 0.579,
|
| 2282 |
+
"step": 163000
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 7.63,
|
| 2286 |
+
"eval_loss": 2.5098183155059814,
|
| 2287 |
+
"eval_runtime": 54.9924,
|
| 2288 |
+
"eval_samples_per_second": 120.544,
|
| 2289 |
+
"eval_steps_per_second": 1.891,
|
| 2290 |
+
"step": 163000
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 7.67,
|
| 2294 |
+
"learning_rate": 1.1637426900584795e-05,
|
| 2295 |
+
"loss": 0.5764,
|
| 2296 |
+
"step": 164000
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 7.67,
|
| 2300 |
+
"eval_loss": 2.5329983234405518,
|
| 2301 |
+
"eval_runtime": 55.0148,
|
| 2302 |
+
"eval_samples_per_second": 120.495,
|
| 2303 |
+
"eval_steps_per_second": 1.89,
|
| 2304 |
+
"step": 164000
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 7.72,
|
| 2308 |
+
"learning_rate": 1.1403508771929824e-05,
|
| 2309 |
+
"loss": 0.5781,
|
| 2310 |
+
"step": 165000
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 7.72,
|
| 2314 |
+
"eval_loss": 2.512319803237915,
|
| 2315 |
+
"eval_runtime": 54.9674,
|
| 2316 |
+
"eval_samples_per_second": 120.599,
|
| 2317 |
+
"eval_steps_per_second": 1.892,
|
| 2318 |
+
"step": 165000
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 7.77,
|
| 2322 |
+
"learning_rate": 1.1169590643274855e-05,
|
| 2323 |
+
"loss": 0.5758,
|
| 2324 |
+
"step": 166000
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 7.77,
|
| 2328 |
+
"eval_loss": 2.5034148693084717,
|
| 2329 |
+
"eval_runtime": 54.9854,
|
| 2330 |
+
"eval_samples_per_second": 120.559,
|
| 2331 |
+
"eval_steps_per_second": 1.891,
|
| 2332 |
+
"step": 166000
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 7.81,
|
| 2336 |
+
"learning_rate": 1.0935672514619884e-05,
|
| 2337 |
+
"loss": 0.5792,
|
| 2338 |
+
"step": 167000
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 7.81,
|
| 2342 |
+
"eval_loss": 2.525723934173584,
|
| 2343 |
+
"eval_runtime": 55.017,
|
| 2344 |
+
"eval_samples_per_second": 120.49,
|
| 2345 |
+
"eval_steps_per_second": 1.89,
|
| 2346 |
+
"step": 167000
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 7.86,
|
| 2350 |
+
"learning_rate": 1.0701754385964913e-05,
|
| 2351 |
+
"loss": 0.5745,
|
| 2352 |
+
"step": 168000
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 7.86,
|
| 2356 |
+
"eval_loss": 2.526042938232422,
|
| 2357 |
+
"eval_runtime": 54.987,
|
| 2358 |
+
"eval_samples_per_second": 120.556,
|
| 2359 |
+
"eval_steps_per_second": 1.891,
|
| 2360 |
+
"step": 168000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 7.91,
|
| 2364 |
+
"learning_rate": 1.0467836257309941e-05,
|
| 2365 |
+
"loss": 0.5702,
|
| 2366 |
+
"step": 169000
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 7.91,
|
| 2370 |
+
"eval_loss": 2.5171217918395996,
|
| 2371 |
+
"eval_runtime": 54.976,
|
| 2372 |
+
"eval_samples_per_second": 120.58,
|
| 2373 |
+
"eval_steps_per_second": 1.892,
|
| 2374 |
+
"step": 169000
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 7.95,
|
| 2378 |
+
"learning_rate": 1.023391812865497e-05,
|
| 2379 |
+
"loss": 0.5714,
|
| 2380 |
+
"step": 170000
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 7.95,
|
| 2384 |
+
"eval_loss": 2.509648323059082,
|
| 2385 |
+
"eval_runtime": 54.9828,
|
| 2386 |
+
"eval_samples_per_second": 120.565,
|
| 2387 |
+
"eval_steps_per_second": 1.892,
|
| 2388 |
+
"step": 170000
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 8.0,
|
| 2392 |
+
"learning_rate": 1e-05,
|
| 2393 |
+
"loss": 0.5692,
|
| 2394 |
+
"step": 171000
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 8.0,
|
| 2398 |
+
"eval_loss": 2.4963207244873047,
|
| 2399 |
+
"eval_runtime": 54.9818,
|
| 2400 |
+
"eval_samples_per_second": 120.567,
|
| 2401 |
+
"eval_steps_per_second": 1.892,
|
| 2402 |
+
"step": 171000
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 8.05,
|
| 2406 |
+
"learning_rate": 9.76608187134503e-06,
|
| 2407 |
+
"loss": 0.5541,
|
| 2408 |
+
"step": 172000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 8.05,
|
| 2412 |
+
"eval_loss": 2.5158822536468506,
|
| 2413 |
+
"eval_runtime": 54.9875,
|
| 2414 |
+
"eval_samples_per_second": 120.555,
|
| 2415 |
+
"eval_steps_per_second": 1.891,
|
| 2416 |
+
"step": 172000
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 8.09,
|
| 2420 |
+
"learning_rate": 9.532163742690059e-06,
|
| 2421 |
+
"loss": 0.5609,
|
| 2422 |
+
"step": 173000
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 8.09,
|
| 2426 |
+
"eval_loss": 2.52651047706604,
|
| 2427 |
+
"eval_runtime": 54.9727,
|
| 2428 |
+
"eval_samples_per_second": 120.587,
|
| 2429 |
+
"eval_steps_per_second": 1.892,
|
| 2430 |
+
"step": 173000
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 8.14,
|
| 2434 |
+
"learning_rate": 9.298245614035088e-06,
|
| 2435 |
+
"loss": 0.5567,
|
| 2436 |
+
"step": 174000
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 8.14,
|
| 2440 |
+
"eval_loss": 2.529944658279419,
|
| 2441 |
+
"eval_runtime": 54.9646,
|
| 2442 |
+
"eval_samples_per_second": 120.605,
|
| 2443 |
+
"eval_steps_per_second": 1.892,
|
| 2444 |
+
"step": 174000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 8.19,
|
| 2448 |
+
"learning_rate": 9.064327485380117e-06,
|
| 2449 |
+
"loss": 0.5593,
|
| 2450 |
+
"step": 175000
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 8.19,
|
| 2454 |
+
"eval_loss": 2.5352935791015625,
|
| 2455 |
+
"eval_runtime": 54.9969,
|
| 2456 |
+
"eval_samples_per_second": 120.534,
|
| 2457 |
+
"eval_steps_per_second": 1.891,
|
| 2458 |
+
"step": 175000
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 8.23,
|
| 2462 |
+
"learning_rate": 8.830409356725146e-06,
|
| 2463 |
+
"loss": 0.5537,
|
| 2464 |
+
"step": 176000
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 8.23,
|
| 2468 |
+
"eval_loss": 2.5415403842926025,
|
| 2469 |
+
"eval_runtime": 54.9924,
|
| 2470 |
+
"eval_samples_per_second": 120.544,
|
| 2471 |
+
"eval_steps_per_second": 1.891,
|
| 2472 |
+
"step": 176000
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 8.28,
|
| 2476 |
+
"learning_rate": 8.596491228070176e-06,
|
| 2477 |
+
"loss": 0.5465,
|
| 2478 |
+
"step": 177000
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 8.28,
|
| 2482 |
+
"eval_loss": 2.5204358100891113,
|
| 2483 |
+
"eval_runtime": 55.0062,
|
| 2484 |
+
"eval_samples_per_second": 120.514,
|
| 2485 |
+
"eval_steps_per_second": 1.891,
|
| 2486 |
+
"step": 177000
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 8.33,
|
| 2490 |
+
"learning_rate": 8.362573099415205e-06,
|
| 2491 |
+
"loss": 0.548,
|
| 2492 |
+
"step": 178000
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 8.33,
|
| 2496 |
+
"eval_loss": 2.5008552074432373,
|
| 2497 |
+
"eval_runtime": 54.9691,
|
| 2498 |
+
"eval_samples_per_second": 120.595,
|
| 2499 |
+
"eval_steps_per_second": 1.892,
|
| 2500 |
+
"step": 178000
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 8.37,
|
| 2504 |
+
"learning_rate": 8.128654970760234e-06,
|
| 2505 |
+
"loss": 0.5477,
|
| 2506 |
+
"step": 179000
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 8.37,
|
| 2510 |
+
"eval_loss": 2.5255722999572754,
|
| 2511 |
+
"eval_runtime": 54.9912,
|
| 2512 |
+
"eval_samples_per_second": 120.547,
|
| 2513 |
+
"eval_steps_per_second": 1.891,
|
| 2514 |
+
"step": 179000
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 8.42,
|
| 2518 |
+
"learning_rate": 7.894736842105263e-06,
|
| 2519 |
+
"loss": 0.5393,
|
| 2520 |
+
"step": 180000
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 8.42,
|
| 2524 |
+
"eval_loss": 2.49310564994812,
|
| 2525 |
+
"eval_runtime": 54.9871,
|
| 2526 |
+
"eval_samples_per_second": 120.556,
|
| 2527 |
+
"eval_steps_per_second": 1.891,
|
| 2528 |
+
"step": 180000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 8.47,
|
| 2532 |
+
"learning_rate": 7.660818713450294e-06,
|
| 2533 |
+
"loss": 0.5441,
|
| 2534 |
+
"step": 181000
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 8.47,
|
| 2538 |
+
"eval_loss": 2.5206234455108643,
|
| 2539 |
+
"eval_runtime": 54.9863,
|
| 2540 |
+
"eval_samples_per_second": 120.557,
|
| 2541 |
+
"eval_steps_per_second": 1.891,
|
| 2542 |
+
"step": 181000
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 8.51,
|
| 2546 |
+
"learning_rate": 7.426900584795322e-06,
|
| 2547 |
+
"loss": 0.5419,
|
| 2548 |
+
"step": 182000
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 8.51,
|
| 2552 |
+
"eval_loss": 2.511657476425171,
|
| 2553 |
+
"eval_runtime": 54.9931,
|
| 2554 |
+
"eval_samples_per_second": 120.542,
|
| 2555 |
+
"eval_steps_per_second": 1.891,
|
| 2556 |
+
"step": 182000
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 8.56,
|
| 2560 |
+
"learning_rate": 7.192982456140351e-06,
|
| 2561 |
+
"loss": 0.5377,
|
| 2562 |
+
"step": 183000
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 8.56,
|
| 2566 |
+
"eval_loss": 2.534726142883301,
|
| 2567 |
+
"eval_runtime": 55.0074,
|
| 2568 |
+
"eval_samples_per_second": 120.511,
|
| 2569 |
+
"eval_steps_per_second": 1.891,
|
| 2570 |
+
"step": 183000
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 8.61,
|
| 2574 |
+
"learning_rate": 6.95906432748538e-06,
|
| 2575 |
+
"loss": 0.5375,
|
| 2576 |
+
"step": 184000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 8.61,
|
| 2580 |
+
"eval_loss": 2.4978044033050537,
|
| 2581 |
+
"eval_runtime": 55.0077,
|
| 2582 |
+
"eval_samples_per_second": 120.51,
|
| 2583 |
+
"eval_steps_per_second": 1.891,
|
| 2584 |
+
"step": 184000
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 8.65,
|
| 2588 |
+
"learning_rate": 6.725146198830409e-06,
|
| 2589 |
+
"loss": 0.5375,
|
| 2590 |
+
"step": 185000
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 8.65,
|
| 2594 |
+
"eval_loss": 2.4929347038269043,
|
| 2595 |
+
"eval_runtime": 54.9953,
|
| 2596 |
+
"eval_samples_per_second": 120.537,
|
| 2597 |
+
"eval_steps_per_second": 1.891,
|
| 2598 |
+
"step": 185000
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 8.7,
|
| 2602 |
+
"learning_rate": 6.4912280701754385e-06,
|
| 2603 |
+
"loss": 0.5354,
|
| 2604 |
+
"step": 186000
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 8.7,
|
| 2608 |
+
"eval_loss": 2.4908556938171387,
|
| 2609 |
+
"eval_runtime": 55.0037,
|
| 2610 |
+
"eval_samples_per_second": 120.519,
|
| 2611 |
+
"eval_steps_per_second": 1.891,
|
| 2612 |
+
"step": 186000
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 8.75,
|
| 2616 |
+
"learning_rate": 6.2573099415204685e-06,
|
| 2617 |
+
"loss": 0.5318,
|
| 2618 |
+
"step": 187000
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 8.75,
|
| 2622 |
+
"eval_loss": 2.531054973602295,
|
| 2623 |
+
"eval_runtime": 54.9993,
|
| 2624 |
+
"eval_samples_per_second": 120.529,
|
| 2625 |
+
"eval_steps_per_second": 1.891,
|
| 2626 |
+
"step": 187000
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 8.8,
|
| 2630 |
+
"learning_rate": 6.023391812865498e-06,
|
| 2631 |
+
"loss": 0.5338,
|
| 2632 |
+
"step": 188000
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 8.8,
|
| 2636 |
+
"eval_loss": 2.5138602256774902,
|
| 2637 |
+
"eval_runtime": 54.9949,
|
| 2638 |
+
"eval_samples_per_second": 120.539,
|
| 2639 |
+
"eval_steps_per_second": 1.891,
|
| 2640 |
+
"step": 188000
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 8.84,
|
| 2644 |
+
"learning_rate": 5.789473684210527e-06,
|
| 2645 |
+
"loss": 0.5247,
|
| 2646 |
+
"step": 189000
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 8.84,
|
| 2650 |
+
"eval_loss": 2.5182831287384033,
|
| 2651 |
+
"eval_runtime": 54.9996,
|
| 2652 |
+
"eval_samples_per_second": 120.528,
|
| 2653 |
+
"eval_steps_per_second": 1.891,
|
| 2654 |
+
"step": 189000
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 8.89,
|
| 2658 |
+
"learning_rate": 5.555555555555556e-06,
|
| 2659 |
+
"loss": 0.5249,
|
| 2660 |
+
"step": 190000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 8.89,
|
| 2664 |
+
"eval_loss": 2.5073628425598145,
|
| 2665 |
+
"eval_runtime": 54.9824,
|
| 2666 |
+
"eval_samples_per_second": 120.566,
|
| 2667 |
+
"eval_steps_per_second": 1.892,
|
| 2668 |
+
"step": 190000
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 8.94,
|
| 2672 |
+
"learning_rate": 5.321637426900585e-06,
|
| 2673 |
+
"loss": 0.5266,
|
| 2674 |
+
"step": 191000
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 8.94,
|
| 2678 |
+
"eval_loss": 2.5005078315734863,
|
| 2679 |
+
"eval_runtime": 54.9464,
|
| 2680 |
+
"eval_samples_per_second": 120.645,
|
| 2681 |
+
"eval_steps_per_second": 1.893,
|
| 2682 |
+
"step": 191000
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 8.98,
|
| 2686 |
+
"learning_rate": 5.087719298245614e-06,
|
| 2687 |
+
"loss": 0.5279,
|
| 2688 |
+
"step": 192000
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"epoch": 8.98,
|
| 2692 |
+
"eval_loss": 2.5144731998443604,
|
| 2693 |
+
"eval_runtime": 54.9856,
|
| 2694 |
+
"eval_samples_per_second": 120.559,
|
| 2695 |
+
"eval_steps_per_second": 1.891,
|
| 2696 |
+
"step": 192000
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 9.03,
|
| 2700 |
+
"learning_rate": 4.853801169590644e-06,
|
| 2701 |
+
"loss": 0.5231,
|
| 2702 |
+
"step": 193000
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 9.03,
|
| 2706 |
+
"eval_loss": 2.5163862705230713,
|
| 2707 |
+
"eval_runtime": 54.965,
|
| 2708 |
+
"eval_samples_per_second": 120.604,
|
| 2709 |
+
"eval_steps_per_second": 1.892,
|
| 2710 |
+
"step": 193000
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 9.08,
|
| 2714 |
+
"learning_rate": 4.619883040935673e-06,
|
| 2715 |
+
"loss": 0.5157,
|
| 2716 |
+
"step": 194000
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 9.08,
|
| 2720 |
+
"eval_loss": 2.4902589321136475,
|
| 2721 |
+
"eval_runtime": 54.9685,
|
| 2722 |
+
"eval_samples_per_second": 120.596,
|
| 2723 |
+
"eval_steps_per_second": 1.892,
|
| 2724 |
+
"step": 194000
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 9.12,
|
| 2728 |
+
"learning_rate": 4.3859649122807014e-06,
|
| 2729 |
+
"loss": 0.5153,
|
| 2730 |
+
"step": 195000
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 9.12,
|
| 2734 |
+
"eval_loss": 2.5248496532440186,
|
| 2735 |
+
"eval_runtime": 55.0107,
|
| 2736 |
+
"eval_samples_per_second": 120.504,
|
| 2737 |
+
"eval_steps_per_second": 1.891,
|
| 2738 |
+
"step": 195000
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 9.17,
|
| 2742 |
+
"learning_rate": 4.152046783625731e-06,
|
| 2743 |
+
"loss": 0.5238,
|
| 2744 |
+
"step": 196000
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 9.17,
|
| 2748 |
+
"eval_loss": 2.4956910610198975,
|
| 2749 |
+
"eval_runtime": 54.9681,
|
| 2750 |
+
"eval_samples_per_second": 120.597,
|
| 2751 |
+
"eval_steps_per_second": 1.892,
|
| 2752 |
+
"step": 196000
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 9.22,
|
| 2756 |
+
"learning_rate": 3.9181286549707605e-06,
|
| 2757 |
+
"loss": 0.5229,
|
| 2758 |
+
"step": 197000
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 9.22,
|
| 2762 |
+
"eval_loss": 2.509634256362915,
|
| 2763 |
+
"eval_runtime": 55.0395,
|
| 2764 |
+
"eval_samples_per_second": 120.441,
|
| 2765 |
+
"eval_steps_per_second": 1.89,
|
| 2766 |
+
"step": 197000
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 9.26,
|
| 2770 |
+
"learning_rate": 3.6842105263157892e-06,
|
| 2771 |
+
"loss": 0.5099,
|
| 2772 |
+
"step": 198000
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"epoch": 9.26,
|
| 2776 |
+
"eval_loss": 2.505375862121582,
|
| 2777 |
+
"eval_runtime": 54.9659,
|
| 2778 |
+
"eval_samples_per_second": 120.602,
|
| 2779 |
+
"eval_steps_per_second": 1.892,
|
| 2780 |
+
"step": 198000
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 9.31,
|
| 2784 |
+
"learning_rate": 3.4502923976608188e-06,
|
| 2785 |
+
"loss": 0.5164,
|
| 2786 |
+
"step": 199000
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 9.31,
|
| 2790 |
+
"eval_loss": 2.512755870819092,
|
| 2791 |
+
"eval_runtime": 54.9727,
|
| 2792 |
+
"eval_samples_per_second": 120.587,
|
| 2793 |
+
"eval_steps_per_second": 1.892,
|
| 2794 |
+
"step": 199000
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 9.36,
|
| 2798 |
+
"learning_rate": 3.216374269005848e-06,
|
| 2799 |
+
"loss": 0.5147,
|
| 2800 |
+
"step": 200000
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 9.36,
|
| 2804 |
+
"eval_loss": 2.5104758739471436,
|
| 2805 |
+
"eval_runtime": 54.9829,
|
| 2806 |
+
"eval_samples_per_second": 120.565,
|
| 2807 |
+
"eval_steps_per_second": 1.891,
|
| 2808 |
+
"step": 200000
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"epoch": 9.4,
|
| 2812 |
+
"learning_rate": 2.9824561403508774e-06,
|
| 2813 |
+
"loss": 0.5092,
|
| 2814 |
+
"step": 201000
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 9.4,
|
| 2818 |
+
"eval_loss": 2.5510807037353516,
|
| 2819 |
+
"eval_runtime": 54.9886,
|
| 2820 |
+
"eval_samples_per_second": 120.552,
|
| 2821 |
+
"eval_steps_per_second": 1.891,
|
| 2822 |
+
"step": 201000
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 9.45,
|
| 2826 |
+
"learning_rate": 2.7485380116959066e-06,
|
| 2827 |
+
"loss": 0.5123,
|
| 2828 |
+
"step": 202000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 9.45,
|
| 2832 |
+
"eval_loss": 2.4837098121643066,
|
| 2833 |
+
"eval_runtime": 54.9612,
|
| 2834 |
+
"eval_samples_per_second": 120.612,
|
| 2835 |
+
"eval_steps_per_second": 1.892,
|
| 2836 |
+
"step": 202000
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 9.5,
|
| 2840 |
+
"learning_rate": 2.5146198830409357e-06,
|
| 2841 |
+
"loss": 0.5077,
|
| 2842 |
+
"step": 203000
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 9.5,
|
| 2846 |
+
"eval_loss": 2.5026121139526367,
|
| 2847 |
+
"eval_runtime": 55.0018,
|
| 2848 |
+
"eval_samples_per_second": 120.523,
|
| 2849 |
+
"eval_steps_per_second": 1.891,
|
| 2850 |
+
"step": 203000
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 9.54,
|
| 2854 |
+
"learning_rate": 2.2807017543859652e-06,
|
| 2855 |
+
"loss": 0.5112,
|
| 2856 |
+
"step": 204000
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 9.54,
|
| 2860 |
+
"eval_loss": 2.514636278152466,
|
| 2861 |
+
"eval_runtime": 54.9811,
|
| 2862 |
+
"eval_samples_per_second": 120.569,
|
| 2863 |
+
"eval_steps_per_second": 1.892,
|
| 2864 |
+
"step": 204000
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 9.59,
|
| 2868 |
+
"learning_rate": 2.0467836257309943e-06,
|
| 2869 |
+
"loss": 0.5033,
|
| 2870 |
+
"step": 205000
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 9.59,
|
| 2874 |
+
"eval_loss": 2.537416696548462,
|
| 2875 |
+
"eval_runtime": 54.983,
|
| 2876 |
+
"eval_samples_per_second": 120.565,
|
| 2877 |
+
"eval_steps_per_second": 1.891,
|
| 2878 |
+
"step": 205000
|
| 2879 |
+
},
|
| 2880 |
+
{
|
| 2881 |
+
"epoch": 9.64,
|
| 2882 |
+
"learning_rate": 1.8128654970760235e-06,
|
| 2883 |
+
"loss": 0.5111,
|
| 2884 |
+
"step": 206000
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"epoch": 9.64,
|
| 2888 |
+
"eval_loss": 2.515895366668701,
|
| 2889 |
+
"eval_runtime": 54.9923,
|
| 2890 |
+
"eval_samples_per_second": 120.544,
|
| 2891 |
+
"eval_steps_per_second": 1.891,
|
| 2892 |
+
"step": 206000
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 9.68,
|
| 2896 |
+
"learning_rate": 1.5789473684210528e-06,
|
| 2897 |
+
"loss": 0.5119,
|
| 2898 |
+
"step": 207000
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"epoch": 9.68,
|
| 2902 |
+
"eval_loss": 2.5189149379730225,
|
| 2903 |
+
"eval_runtime": 54.9887,
|
| 2904 |
+
"eval_samples_per_second": 120.552,
|
| 2905 |
+
"eval_steps_per_second": 1.891,
|
| 2906 |
+
"step": 207000
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 9.73,
|
| 2910 |
+
"learning_rate": 1.345029239766082e-06,
|
| 2911 |
+
"loss": 0.5022,
|
| 2912 |
+
"step": 208000
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 9.73,
|
| 2916 |
+
"eval_loss": 2.506300926208496,
|
| 2917 |
+
"eval_runtime": 54.9799,
|
| 2918 |
+
"eval_samples_per_second": 120.571,
|
| 2919 |
+
"eval_steps_per_second": 1.892,
|
| 2920 |
+
"step": 208000
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 9.78,
|
| 2924 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 2925 |
+
"loss": 0.5051,
|
| 2926 |
+
"step": 209000
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 9.78,
|
| 2930 |
+
"eval_loss": 2.4811651706695557,
|
| 2931 |
+
"eval_runtime": 54.958,
|
| 2932 |
+
"eval_samples_per_second": 120.619,
|
| 2933 |
+
"eval_steps_per_second": 1.892,
|
| 2934 |
+
"step": 209000
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 9.82,
|
| 2938 |
+
"learning_rate": 8.771929824561404e-07,
|
| 2939 |
+
"loss": 0.5028,
|
| 2940 |
+
"step": 210000
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 9.82,
|
| 2944 |
+
"eval_loss": 2.4914138317108154,
|
| 2945 |
+
"eval_runtime": 55.0024,
|
| 2946 |
+
"eval_samples_per_second": 120.522,
|
| 2947 |
+
"eval_steps_per_second": 1.891,
|
| 2948 |
+
"step": 210000
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 9.87,
|
| 2952 |
+
"learning_rate": 6.432748538011697e-07,
|
| 2953 |
+
"loss": 0.5066,
|
| 2954 |
+
"step": 211000
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 9.87,
|
| 2958 |
+
"eval_loss": 2.5056285858154297,
|
| 2959 |
+
"eval_runtime": 54.9649,
|
| 2960 |
+
"eval_samples_per_second": 120.604,
|
| 2961 |
+
"eval_steps_per_second": 1.892,
|
| 2962 |
+
"step": 211000
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 9.92,
|
| 2966 |
+
"learning_rate": 4.093567251461989e-07,
|
| 2967 |
+
"loss": 0.5058,
|
| 2968 |
+
"step": 212000
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 9.92,
|
| 2972 |
+
"eval_loss": 2.53446102142334,
|
| 2973 |
+
"eval_runtime": 54.9817,
|
| 2974 |
+
"eval_samples_per_second": 120.567,
|
| 2975 |
+
"eval_steps_per_second": 1.892,
|
| 2976 |
+
"step": 212000
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 9.96,
|
| 2980 |
+
"learning_rate": 1.7543859649122808e-07,
|
| 2981 |
+
"loss": 0.507,
|
| 2982 |
+
"step": 213000
|
| 2983 |
+
},
|
| 2984 |
+
{
|
| 2985 |
+
"epoch": 9.96,
|
| 2986 |
+
"eval_loss": 2.507356882095337,
|
| 2987 |
+
"eval_runtime": 55.001,
|
| 2988 |
+
"eval_samples_per_second": 120.525,
|
| 2989 |
+
"eval_steps_per_second": 1.891,
|
| 2990 |
+
"step": 213000
|
| 2991 |
+
}
|
| 2992 |
+
],
|
| 2993 |
+
"max_steps": 213750,
|
| 2994 |
+
"num_train_epochs": 10,
|
| 2995 |
+
"total_flos": 4.4847043698061394e+18,
|
| 2996 |
+
"trial_name": null,
|
| 2997 |
+
"trial_params": null
|
| 2998 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12e2447268571e43f688b3eb703ace7b3c81316654186d388a569f58461215c
|
| 3 |
+
size 3963
|