Upload folder using huggingface_hub
Browse files- checkpoint-750/optimizer.pt +3 -0
- checkpoint-750/pytorch_model.bin +3 -0
- checkpoint-750/rng_state_0.pth +3 -0
- checkpoint-750/rng_state_1.pth +3 -0
- checkpoint-750/rng_state_2.pth +3 -0
- checkpoint-750/rng_state_3.pth +3 -0
- checkpoint-750/rng_state_4.pth +3 -0
- checkpoint-750/rng_state_5.pth +3 -0
- checkpoint-750/rng_state_6.pth +3 -0
- checkpoint-750/rng_state_7.pth +3 -0
- checkpoint-750/scheduler.pt +3 -0
- checkpoint-750/special_tokens_map.json +1 -0
- checkpoint-750/tokenizer_config.json +1 -0
- checkpoint-750/trainer_state.json +3076 -0
- checkpoint-750/training_args.bin +3 -0
- checkpoint-750/vocab.txt +9 -0
checkpoint-750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5debeaf42a8a41121560614c58dad6dd53a6d86eed7a90a96c5c594048f8995b
|
| 3 |
+
size 552346635
|
checkpoint-750/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1909db58f0359d721742b26b72fed148f1de9eda7b2f1159aa77f46e7cfcf27
|
| 3 |
+
size 276176643
|
checkpoint-750/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f469fb6a869fe76761e1194ed0a7948ca397689bbc8ac0a9ea85a077fd50929
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77e31efd49e7c2510fff79f966c879db58740a4187714c13003ffa53d0d441c5
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:755aba68d004de8b7239e4451f96d8aaad4274ed7f03ec57d204f73d7b768a54
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1e57948798e97ec4bd65e4f2bab0090fd58ab95e9d421be20702021446d2636
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7930f1c6dd64fe161f166b710675bea007029bf2a54e835287c8517c8d61b7e
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c098b3d19df4c6a4261105183eb9357e2715d784d681c1426e4bb88c847c317
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c914eacfcdfa6cf1a18175490235b8bf14f4521cc8ebda28a827fb8611e2958d
|
| 3 |
+
size 16389
|
checkpoint-750/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad02907448ab52a0de6407d8cc85b4523850947654c14a8ca1a3772f6c8c9cf8
|
| 3 |
+
size 16389
|
checkpoint-750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:250c04174320e66f5f7eaee01ad684ce12f065ca29fd0733eba66aa1ef265854
|
| 3 |
+
size 1465
|
checkpoint-750/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-750/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "MxDNATokenizer"}
|
checkpoint-750/trainer_state.json
ADDED
|
@@ -0,0 +1,3076 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 750,
|
| 3 |
+
"best_metric": 1.2186306715011597,
|
| 4 |
+
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/Gencode-MxDNA/checkpoint-750",
|
| 5 |
+
"epoch": 0.21275086873271398,
|
| 6 |
+
"eval_steps": 125,
|
| 7 |
+
"global_step": 750,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0005673356499539039,
|
| 14 |
+
"grad_norm": 8450.4345703125,
|
| 15 |
+
"loss": 876.9911,
|
| 16 |
+
"lr": 2e-06,
|
| 17 |
+
"step": 2,
|
| 18 |
+
"tokens_trained": 0.000985992
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0011346712999078079,
|
| 22 |
+
"grad_norm": 8980.888671875,
|
| 23 |
+
"loss": 779.4711,
|
| 24 |
+
"lr": 6e-06,
|
| 25 |
+
"step": 4,
|
| 26 |
+
"tokens_trained": 0.001968088
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.001702006949861712,
|
| 30 |
+
"grad_norm": 7489.92529296875,
|
| 31 |
+
"loss": 488.6157,
|
| 32 |
+
"lr": 1e-05,
|
| 33 |
+
"step": 6,
|
| 34 |
+
"tokens_trained": 0.002953808
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.0022693425998156157,
|
| 38 |
+
"grad_norm": 1952.1917724609375,
|
| 39 |
+
"loss": 237.0602,
|
| 40 |
+
"lr": 1.4e-05,
|
| 41 |
+
"step": 8,
|
| 42 |
+
"tokens_trained": 0.003935728
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0028366782497695198,
|
| 46 |
+
"grad_norm": 1418.443603515625,
|
| 47 |
+
"loss": 159.0854,
|
| 48 |
+
"lr": 1.8e-05,
|
| 49 |
+
"step": 10,
|
| 50 |
+
"tokens_trained": 0.004916488
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.003404013899723424,
|
| 54 |
+
"grad_norm": 874.7195434570312,
|
| 55 |
+
"loss": 91.9563,
|
| 56 |
+
"lr": 2.2e-05,
|
| 57 |
+
"step": 12,
|
| 58 |
+
"tokens_trained": 0.005902792
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.003971349549677328,
|
| 62 |
+
"grad_norm": 1339.8248291015625,
|
| 63 |
+
"loss": 40.3366,
|
| 64 |
+
"lr": 2.6e-05,
|
| 65 |
+
"step": 14,
|
| 66 |
+
"tokens_trained": 0.0068856
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0045386851996312315,
|
| 70 |
+
"grad_norm": 2936.7607421875,
|
| 71 |
+
"loss": 22.7436,
|
| 72 |
+
"lr": 3e-05,
|
| 73 |
+
"step": 16,
|
| 74 |
+
"tokens_trained": 0.007868248
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.005106020849585136,
|
| 78 |
+
"grad_norm": 1531.3807373046875,
|
| 79 |
+
"loss": 23.4797,
|
| 80 |
+
"lr": 3.4000000000000007e-05,
|
| 81 |
+
"step": 18,
|
| 82 |
+
"tokens_trained": 0.008849296
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0056733564995390395,
|
| 86 |
+
"grad_norm": 3027.4189453125,
|
| 87 |
+
"loss": 38.7379,
|
| 88 |
+
"lr": 3.8e-05,
|
| 89 |
+
"step": 20,
|
| 90 |
+
"tokens_trained": 0.009830984
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.006240692149492944,
|
| 94 |
+
"grad_norm": 2435.890625,
|
| 95 |
+
"loss": 26.2427,
|
| 96 |
+
"lr": 4.2000000000000004e-05,
|
| 97 |
+
"step": 22,
|
| 98 |
+
"tokens_trained": 0.01081364
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.006808027799446848,
|
| 102 |
+
"grad_norm": 3217.990478515625,
|
| 103 |
+
"loss": 31.0263,
|
| 104 |
+
"lr": 4.6e-05,
|
| 105 |
+
"step": 24,
|
| 106 |
+
"tokens_trained": 0.01179036
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.007375363449400752,
|
| 110 |
+
"grad_norm": 3854.00634765625,
|
| 111 |
+
"loss": 33.8781,
|
| 112 |
+
"lr": 5e-05,
|
| 113 |
+
"step": 26,
|
| 114 |
+
"tokens_trained": 0.012774504
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.007942699099354656,
|
| 118 |
+
"grad_norm": 3197.489990234375,
|
| 119 |
+
"loss": 27.7927,
|
| 120 |
+
"lr": 5.4e-05,
|
| 121 |
+
"step": 28,
|
| 122 |
+
"tokens_trained": 0.013759992
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.00851003474930856,
|
| 126 |
+
"grad_norm": 3034.156494140625,
|
| 127 |
+
"loss": 37.9083,
|
| 128 |
+
"lr": 5.800000000000001e-05,
|
| 129 |
+
"step": 30,
|
| 130 |
+
"tokens_trained": 0.014740536
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.009077370399262463,
|
| 134 |
+
"grad_norm": 3040.314453125,
|
| 135 |
+
"loss": 34.0659,
|
| 136 |
+
"lr": 6.2e-05,
|
| 137 |
+
"step": 32,
|
| 138 |
+
"tokens_trained": 0.015725984
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.009644706049216368,
|
| 142 |
+
"grad_norm": 3065.5791015625,
|
| 143 |
+
"loss": 27.7768,
|
| 144 |
+
"lr": 6.6e-05,
|
| 145 |
+
"step": 34,
|
| 146 |
+
"tokens_trained": 0.016706864
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.010212041699170272,
|
| 150 |
+
"grad_norm": 2454.293701171875,
|
| 151 |
+
"loss": 35.1143,
|
| 152 |
+
"lr": 7.000000000000001e-05,
|
| 153 |
+
"step": 36,
|
| 154 |
+
"tokens_trained": 0.017688816
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.010779377349124175,
|
| 158 |
+
"grad_norm": 3100.7802734375,
|
| 159 |
+
"loss": 42.2603,
|
| 160 |
+
"lr": 7.4e-05,
|
| 161 |
+
"step": 38,
|
| 162 |
+
"tokens_trained": 0.018669072
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.011346712999078079,
|
| 166 |
+
"grad_norm": 2749.84423828125,
|
| 167 |
+
"loss": 39.3879,
|
| 168 |
+
"lr": 7.8e-05,
|
| 169 |
+
"step": 40,
|
| 170 |
+
"tokens_trained": 0.019652072
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.011914048649031984,
|
| 174 |
+
"grad_norm": 1519.9908447265625,
|
| 175 |
+
"loss": 35.0735,
|
| 176 |
+
"lr": 8.2e-05,
|
| 177 |
+
"step": 42,
|
| 178 |
+
"tokens_trained": 0.020633112
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.012481384298985888,
|
| 182 |
+
"grad_norm": 1474.4244384765625,
|
| 183 |
+
"loss": 25.8965,
|
| 184 |
+
"lr": 8.599999999999999e-05,
|
| 185 |
+
"step": 44,
|
| 186 |
+
"tokens_trained": 0.021616192
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.013048719948939792,
|
| 190 |
+
"grad_norm": 2962.500244140625,
|
| 191 |
+
"loss": 51.0784,
|
| 192 |
+
"lr": 8.999999999999999e-05,
|
| 193 |
+
"step": 46,
|
| 194 |
+
"tokens_trained": 0.022597288
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.013616055598893695,
|
| 198 |
+
"grad_norm": 2419.41455078125,
|
| 199 |
+
"loss": 43.0334,
|
| 200 |
+
"lr": 9.400000000000001e-05,
|
| 201 |
+
"step": 48,
|
| 202 |
+
"tokens_trained": 0.02357572
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.014183391248847599,
|
| 206 |
+
"grad_norm": 1267.87451171875,
|
| 207 |
+
"loss": 21.8063,
|
| 208 |
+
"lr": 9.800000000000001e-05,
|
| 209 |
+
"step": 50,
|
| 210 |
+
"tokens_trained": 0.024553376
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.014750726898801504,
|
| 214 |
+
"grad_norm": 1573.944091796875,
|
| 215 |
+
"loss": 52.9693,
|
| 216 |
+
"lr": 0.000102,
|
| 217 |
+
"step": 52,
|
| 218 |
+
"tokens_trained": 0.025536728
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.015318062548755408,
|
| 222 |
+
"grad_norm": 1509.650146484375,
|
| 223 |
+
"loss": 50.0825,
|
| 224 |
+
"lr": 0.000106,
|
| 225 |
+
"step": 54,
|
| 226 |
+
"tokens_trained": 0.026517
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.01588539819870931,
|
| 230 |
+
"grad_norm": 2334.765380859375,
|
| 231 |
+
"loss": 42.1982,
|
| 232 |
+
"lr": 0.00011,
|
| 233 |
+
"step": 56,
|
| 234 |
+
"tokens_trained": 0.027504728
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.016452733848663217,
|
| 238 |
+
"grad_norm": 1594.16259765625,
|
| 239 |
+
"loss": 39.0562,
|
| 240 |
+
"lr": 0.000114,
|
| 241 |
+
"step": 58,
|
| 242 |
+
"tokens_trained": 0.028485416
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.01702006949861712,
|
| 246 |
+
"grad_norm": 1628.082275390625,
|
| 247 |
+
"loss": 35.0488,
|
| 248 |
+
"lr": 0.000118,
|
| 249 |
+
"step": 60,
|
| 250 |
+
"tokens_trained": 0.029468696
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.017587405148571024,
|
| 254 |
+
"grad_norm": 2496.6455078125,
|
| 255 |
+
"loss": 49.4241,
|
| 256 |
+
"lr": 0.000122,
|
| 257 |
+
"step": 62,
|
| 258 |
+
"tokens_trained": 0.030453584
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.018154740798524926,
|
| 262 |
+
"grad_norm": 2521.721435546875,
|
| 263 |
+
"loss": 69.0275,
|
| 264 |
+
"lr": 0.000126,
|
| 265 |
+
"step": 64,
|
| 266 |
+
"tokens_trained": 0.031432864
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.01872207644847883,
|
| 270 |
+
"grad_norm": 2179.571533203125,
|
| 271 |
+
"loss": 63.1409,
|
| 272 |
+
"lr": 0.00013000000000000002,
|
| 273 |
+
"step": 66,
|
| 274 |
+
"tokens_trained": 0.032418416
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.019289412098432736,
|
| 278 |
+
"grad_norm": 899.7137451171875,
|
| 279 |
+
"loss": 38.4131,
|
| 280 |
+
"lr": 0.000134,
|
| 281 |
+
"step": 68,
|
| 282 |
+
"tokens_trained": 0.033402136
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.01985674774838664,
|
| 286 |
+
"grad_norm": 2109.377685546875,
|
| 287 |
+
"loss": 51.0044,
|
| 288 |
+
"lr": 0.00013800000000000002,
|
| 289 |
+
"step": 70,
|
| 290 |
+
"tokens_trained": 0.03438832
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.020424083398340544,
|
| 294 |
+
"grad_norm": 1649.1873779296875,
|
| 295 |
+
"loss": 32.1408,
|
| 296 |
+
"lr": 0.00014199999999999998,
|
| 297 |
+
"step": 72,
|
| 298 |
+
"tokens_trained": 0.035374464
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.020991419048294446,
|
| 302 |
+
"grad_norm": 1807.994140625,
|
| 303 |
+
"loss": 28.8357,
|
| 304 |
+
"lr": 0.000146,
|
| 305 |
+
"step": 74,
|
| 306 |
+
"tokens_trained": 0.03635784
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.02155875469824835,
|
| 310 |
+
"grad_norm": 998.9485473632812,
|
| 311 |
+
"loss": 23.0343,
|
| 312 |
+
"lr": 0.00015,
|
| 313 |
+
"step": 76,
|
| 314 |
+
"tokens_trained": 0.037340248
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.022126090348202256,
|
| 318 |
+
"grad_norm": 2240.17578125,
|
| 319 |
+
"loss": 32.0397,
|
| 320 |
+
"lr": 0.000154,
|
| 321 |
+
"step": 78,
|
| 322 |
+
"tokens_trained": 0.038321968
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.022693425998156158,
|
| 326 |
+
"grad_norm": 1606.0067138671875,
|
| 327 |
+
"loss": 32.1776,
|
| 328 |
+
"lr": 0.000158,
|
| 329 |
+
"step": 80,
|
| 330 |
+
"tokens_trained": 0.039304992
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.023260761648110063,
|
| 334 |
+
"grad_norm": 1685.1015625,
|
| 335 |
+
"loss": 24.3428,
|
| 336 |
+
"lr": 0.000162,
|
| 337 |
+
"step": 82,
|
| 338 |
+
"tokens_trained": 0.040286808
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.02382809729806397,
|
| 342 |
+
"grad_norm": 1761.7890625,
|
| 343 |
+
"loss": 23.9261,
|
| 344 |
+
"lr": 0.00016600000000000002,
|
| 345 |
+
"step": 84,
|
| 346 |
+
"tokens_trained": 0.041271776
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.02439543294801787,
|
| 350 |
+
"grad_norm": 2036.0982666015625,
|
| 351 |
+
"loss": 27.7196,
|
| 352 |
+
"lr": 0.00017,
|
| 353 |
+
"step": 86,
|
| 354 |
+
"tokens_trained": 0.042252784
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.024962768597971776,
|
| 358 |
+
"grad_norm": 1564.3870849609375,
|
| 359 |
+
"loss": 25.3722,
|
| 360 |
+
"lr": 0.000174,
|
| 361 |
+
"step": 88,
|
| 362 |
+
"tokens_trained": 0.04323596
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.025530104247925678,
|
| 366 |
+
"grad_norm": 1508.349853515625,
|
| 367 |
+
"loss": 18.4107,
|
| 368 |
+
"lr": 0.000178,
|
| 369 |
+
"step": 90,
|
| 370 |
+
"tokens_trained": 0.044218984
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.026097439897879583,
|
| 374 |
+
"grad_norm": 1955.011474609375,
|
| 375 |
+
"loss": 28.8456,
|
| 376 |
+
"lr": 0.000182,
|
| 377 |
+
"step": 92,
|
| 378 |
+
"tokens_trained": 0.045202144
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.02666477554783349,
|
| 382 |
+
"grad_norm": 1679.9423828125,
|
| 383 |
+
"loss": 23.6139,
|
| 384 |
+
"lr": 0.000186,
|
| 385 |
+
"step": 94,
|
| 386 |
+
"tokens_trained": 0.046192336
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.02723211119778739,
|
| 390 |
+
"grad_norm": 1517.5731201171875,
|
| 391 |
+
"loss": 42.145,
|
| 392 |
+
"lr": 0.00019,
|
| 393 |
+
"step": 96,
|
| 394 |
+
"tokens_trained": 0.047174312
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.027799446847741296,
|
| 398 |
+
"grad_norm": 1535.3076171875,
|
| 399 |
+
"loss": 31.9711,
|
| 400 |
+
"lr": 0.000194,
|
| 401 |
+
"step": 98,
|
| 402 |
+
"tokens_trained": 0.048158944
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.028366782497695198,
|
| 406 |
+
"grad_norm": 1475.2569580078125,
|
| 407 |
+
"loss": 37.645,
|
| 408 |
+
"lr": 0.00019800000000000002,
|
| 409 |
+
"step": 100,
|
| 410 |
+
"tokens_trained": 0.04914364
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.028934118147649103,
|
| 414 |
+
"grad_norm": 1918.4088134765625,
|
| 415 |
+
"loss": 69.4053,
|
| 416 |
+
"lr": 0.000202,
|
| 417 |
+
"step": 102,
|
| 418 |
+
"tokens_trained": 0.050123488
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.02950145379760301,
|
| 422 |
+
"grad_norm": 1631.6231689453125,
|
| 423 |
+
"loss": 50.9725,
|
| 424 |
+
"lr": 0.000206,
|
| 425 |
+
"step": 104,
|
| 426 |
+
"tokens_trained": 0.051105512
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.03006878944755691,
|
| 430 |
+
"grad_norm": 1291.6376953125,
|
| 431 |
+
"loss": 22.6527,
|
| 432 |
+
"lr": 0.00021,
|
| 433 |
+
"step": 106,
|
| 434 |
+
"tokens_trained": 0.052091704
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.030636125097510816,
|
| 438 |
+
"grad_norm": 1224.9625244140625,
|
| 439 |
+
"loss": 60.2725,
|
| 440 |
+
"lr": 0.000214,
|
| 441 |
+
"step": 108,
|
| 442 |
+
"tokens_trained": 0.053074824
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.031203460747464717,
|
| 446 |
+
"grad_norm": 1218.2022705078125,
|
| 447 |
+
"loss": 75.8728,
|
| 448 |
+
"lr": 0.000218,
|
| 449 |
+
"step": 110,
|
| 450 |
+
"tokens_trained": 0.054057104
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.03177079639741862,
|
| 454 |
+
"grad_norm": 1761.8861083984375,
|
| 455 |
+
"loss": 61.6427,
|
| 456 |
+
"lr": 0.000222,
|
| 457 |
+
"step": 112,
|
| 458 |
+
"tokens_trained": 0.055039128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.03233813204737253,
|
| 462 |
+
"grad_norm": 1482.4256591796875,
|
| 463 |
+
"loss": 35.3351,
|
| 464 |
+
"lr": 0.00022600000000000002,
|
| 465 |
+
"step": 114,
|
| 466 |
+
"tokens_trained": 0.05602388
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.03290546769732643,
|
| 470 |
+
"grad_norm": 563.6399536132812,
|
| 471 |
+
"loss": 40.1461,
|
| 472 |
+
"lr": 0.00023,
|
| 473 |
+
"step": 116,
|
| 474 |
+
"tokens_trained": 0.057005376
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.03347280334728033,
|
| 478 |
+
"grad_norm": 1266.058837890625,
|
| 479 |
+
"loss": 24.0657,
|
| 480 |
+
"lr": 0.00023400000000000002,
|
| 481 |
+
"step": 118,
|
| 482 |
+
"tokens_trained": 0.057985136
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.03404013899723424,
|
| 486 |
+
"grad_norm": 918.206298828125,
|
| 487 |
+
"loss": 23.9626,
|
| 488 |
+
"lr": 0.00023799999999999998,
|
| 489 |
+
"step": 120,
|
| 490 |
+
"tokens_trained": 0.058968288
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.03460747464718814,
|
| 494 |
+
"grad_norm": 1495.7191162109375,
|
| 495 |
+
"loss": 19.798,
|
| 496 |
+
"lr": 0.000242,
|
| 497 |
+
"step": 122,
|
| 498 |
+
"tokens_trained": 0.05995348
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.03517481029714205,
|
| 502 |
+
"grad_norm": 1264.302734375,
|
| 503 |
+
"loss": 31.5342,
|
| 504 |
+
"lr": 0.000246,
|
| 505 |
+
"step": 124,
|
| 506 |
+
"tokens_trained": 0.060935832
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.035458478122119,
|
| 510 |
+
"eval_loss": 5.312118053436279,
|
| 511 |
+
"eval_runtime": 21.3065,
|
| 512 |
+
"step": 125,
|
| 513 |
+
"tokens_trained": 0.061426608
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.03574214594709595,
|
| 517 |
+
"grad_norm": 907.4861450195312,
|
| 518 |
+
"loss": 25.1262,
|
| 519 |
+
"lr": 0.00025,
|
| 520 |
+
"step": 126,
|
| 521 |
+
"tokens_trained": 0.061918184
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.03630948159704985,
|
| 525 |
+
"grad_norm": 1287.6158447265625,
|
| 526 |
+
"loss": 26.963,
|
| 527 |
+
"lr": 0.000254,
|
| 528 |
+
"step": 128,
|
| 529 |
+
"tokens_trained": 0.062902328
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.03687681724700376,
|
| 533 |
+
"grad_norm": 1260.570556640625,
|
| 534 |
+
"loss": 24.9633,
|
| 535 |
+
"lr": 0.00025800000000000004,
|
| 536 |
+
"step": 130,
|
| 537 |
+
"tokens_trained": 0.063883456
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.03744415289695766,
|
| 541 |
+
"grad_norm": 1436.82373046875,
|
| 542 |
+
"loss": 23.1028,
|
| 543 |
+
"lr": 0.000262,
|
| 544 |
+
"step": 132,
|
| 545 |
+
"tokens_trained": 0.06486748
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.03801148854691157,
|
| 549 |
+
"grad_norm": 812.9523315429688,
|
| 550 |
+
"loss": 20.5496,
|
| 551 |
+
"lr": 0.000266,
|
| 552 |
+
"step": 134,
|
| 553 |
+
"tokens_trained": 0.065847104
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.03857882419686547,
|
| 557 |
+
"grad_norm": 1336.5322265625,
|
| 558 |
+
"loss": 23.673,
|
| 559 |
+
"lr": 0.00027,
|
| 560 |
+
"step": 136,
|
| 561 |
+
"tokens_trained": 0.066829928
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.03914615984681937,
|
| 565 |
+
"grad_norm": 1381.282470703125,
|
| 566 |
+
"loss": 32.0373,
|
| 567 |
+
"lr": 0.00027400000000000005,
|
| 568 |
+
"step": 138,
|
| 569 |
+
"tokens_trained": 0.067814024
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.03971349549677328,
|
| 573 |
+
"grad_norm": 972.7861938476562,
|
| 574 |
+
"loss": 26.9454,
|
| 575 |
+
"lr": 0.00027800000000000004,
|
| 576 |
+
"step": 140,
|
| 577 |
+
"tokens_trained": 0.068797744
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.04028083114672718,
|
| 581 |
+
"grad_norm": 1347.2249755859375,
|
| 582 |
+
"loss": 22.3578,
|
| 583 |
+
"lr": 0.00028199999999999997,
|
| 584 |
+
"step": 142,
|
| 585 |
+
"tokens_trained": 0.069780072
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.04084816679668109,
|
| 589 |
+
"grad_norm": 829.525390625,
|
| 590 |
+
"loss": 37.9879,
|
| 591 |
+
"lr": 0.00028599999999999996,
|
| 592 |
+
"step": 144,
|
| 593 |
+
"tokens_trained": 0.070759896
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.04141550244663499,
|
| 597 |
+
"grad_norm": 1094.1033935546875,
|
| 598 |
+
"loss": 21.1972,
|
| 599 |
+
"lr": 0.00029,
|
| 600 |
+
"step": 146,
|
| 601 |
+
"tokens_trained": 0.0717452
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.04198283809658889,
|
| 605 |
+
"grad_norm": 717.107421875,
|
| 606 |
+
"loss": 21.7774,
|
| 607 |
+
"lr": 0.000294,
|
| 608 |
+
"step": 148,
|
| 609 |
+
"tokens_trained": 0.072727432
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.042550173746542796,
|
| 613 |
+
"grad_norm": 744.4456787109375,
|
| 614 |
+
"loss": 20.3235,
|
| 615 |
+
"lr": 0.000298,
|
| 616 |
+
"step": 150,
|
| 617 |
+
"tokens_trained": 0.073712128
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.0431175093964967,
|
| 621 |
+
"grad_norm": 904.1460571289062,
|
| 622 |
+
"loss": 22.7878,
|
| 623 |
+
"lr": 0.000302,
|
| 624 |
+
"step": 152,
|
| 625 |
+
"tokens_trained": 0.074695296
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.04368484504645061,
|
| 629 |
+
"grad_norm": 1352.303955078125,
|
| 630 |
+
"loss": 20.9757,
|
| 631 |
+
"lr": 0.000306,
|
| 632 |
+
"step": 154,
|
| 633 |
+
"tokens_trained": 0.0756798
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.04425218069640451,
|
| 637 |
+
"grad_norm": 997.0473022460938,
|
| 638 |
+
"loss": 17.4647,
|
| 639 |
+
"lr": 0.00031,
|
| 640 |
+
"step": 156,
|
| 641 |
+
"tokens_trained": 0.076666504
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.04481951634635841,
|
| 645 |
+
"grad_norm": 1206.387939453125,
|
| 646 |
+
"loss": 21.1846,
|
| 647 |
+
"lr": 0.000314,
|
| 648 |
+
"step": 158,
|
| 649 |
+
"tokens_trained": 0.07764868
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.045386851996312316,
|
| 653 |
+
"grad_norm": 1029.6807861328125,
|
| 654 |
+
"loss": 17.8853,
|
| 655 |
+
"lr": 0.00031800000000000003,
|
| 656 |
+
"step": 160,
|
| 657 |
+
"tokens_trained": 0.07863548
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.04595418764626622,
|
| 661 |
+
"grad_norm": 1136.4635009765625,
|
| 662 |
+
"loss": 30.057,
|
| 663 |
+
"lr": 0.000322,
|
| 664 |
+
"step": 162,
|
| 665 |
+
"tokens_trained": 0.079618928
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.04652152329622013,
|
| 669 |
+
"grad_norm": 834.3464965820312,
|
| 670 |
+
"loss": 28.1782,
|
| 671 |
+
"lr": 0.000326,
|
| 672 |
+
"step": 164,
|
| 673 |
+
"tokens_trained": 0.0806032
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.04708885894617403,
|
| 677 |
+
"grad_norm": 1177.8365478515625,
|
| 678 |
+
"loss": 16.4267,
|
| 679 |
+
"lr": 0.00033,
|
| 680 |
+
"step": 166,
|
| 681 |
+
"tokens_trained": 0.081583752
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.04765619459612794,
|
| 685 |
+
"grad_norm": 572.501708984375,
|
| 686 |
+
"loss": 16.5752,
|
| 687 |
+
"lr": 0.00033400000000000004,
|
| 688 |
+
"step": 168,
|
| 689 |
+
"tokens_trained": 0.082568184
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.048223530246081836,
|
| 693 |
+
"grad_norm": 437.6822814941406,
|
| 694 |
+
"loss": 11.5509,
|
| 695 |
+
"lr": 0.00033800000000000003,
|
| 696 |
+
"step": 170,
|
| 697 |
+
"tokens_trained": 0.083553352
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.04879086589603574,
|
| 701 |
+
"grad_norm": 1119.0416259765625,
|
| 702 |
+
"loss": 16.2689,
|
| 703 |
+
"lr": 0.000342,
|
| 704 |
+
"step": 172,
|
| 705 |
+
"tokens_trained": 0.084536352
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.04935820154598965,
|
| 709 |
+
"grad_norm": 895.4021606445312,
|
| 710 |
+
"loss": 12.6663,
|
| 711 |
+
"lr": 0.000346,
|
| 712 |
+
"step": 174,
|
| 713 |
+
"tokens_trained": 0.085517312
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.04992553719594355,
|
| 717 |
+
"grad_norm": 995.6289672851562,
|
| 718 |
+
"loss": 26.0663,
|
| 719 |
+
"lr": 0.00035,
|
| 720 |
+
"step": 176,
|
| 721 |
+
"tokens_trained": 0.086496088
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.05049287284589746,
|
| 725 |
+
"grad_norm": 839.6610717773438,
|
| 726 |
+
"loss": 21.5115,
|
| 727 |
+
"lr": 0.000354,
|
| 728 |
+
"step": 178,
|
| 729 |
+
"tokens_trained": 0.087480632
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.051060208495851356,
|
| 733 |
+
"grad_norm": 734.1155395507812,
|
| 734 |
+
"loss": 29.3287,
|
| 735 |
+
"lr": 0.000358,
|
| 736 |
+
"step": 180,
|
| 737 |
+
"tokens_trained": 0.088460408
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.05162754414580526,
|
| 741 |
+
"grad_norm": 721.4505615234375,
|
| 742 |
+
"loss": 26.0801,
|
| 743 |
+
"lr": 0.000362,
|
| 744 |
+
"step": 182,
|
| 745 |
+
"tokens_trained": 0.08944248
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.052194879795759166,
|
| 749 |
+
"grad_norm": 845.9672241210938,
|
| 750 |
+
"loss": 19.0639,
|
| 751 |
+
"lr": 0.000366,
|
| 752 |
+
"step": 184,
|
| 753 |
+
"tokens_trained": 0.090427832
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.05276221544571307,
|
| 757 |
+
"grad_norm": 1210.9969482421875,
|
| 758 |
+
"loss": 23.9036,
|
| 759 |
+
"lr": 0.00037,
|
| 760 |
+
"step": 186,
|
| 761 |
+
"tokens_trained": 0.091411504
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.05332955109566698,
|
| 765 |
+
"grad_norm": 1079.1690673828125,
|
| 766 |
+
"loss": 23.5588,
|
| 767 |
+
"lr": 0.000374,
|
| 768 |
+
"step": 188,
|
| 769 |
+
"tokens_trained": 0.092392672
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.053896886745620876,
|
| 773 |
+
"grad_norm": 596.111328125,
|
| 774 |
+
"loss": 20.8275,
|
| 775 |
+
"lr": 0.000378,
|
| 776 |
+
"step": 190,
|
| 777 |
+
"tokens_trained": 0.093374696
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.05446422239557478,
|
| 781 |
+
"grad_norm": 761.8096923828125,
|
| 782 |
+
"loss": 22.512,
|
| 783 |
+
"lr": 0.000382,
|
| 784 |
+
"step": 192,
|
| 785 |
+
"tokens_trained": 0.094361912
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.055031558045528686,
|
| 789 |
+
"grad_norm": 1081.9832763671875,
|
| 790 |
+
"loss": 32.335,
|
| 791 |
+
"lr": 0.000386,
|
| 792 |
+
"step": 194,
|
| 793 |
+
"tokens_trained": 0.095342992
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.05559889369548259,
|
| 797 |
+
"grad_norm": 304.3534240722656,
|
| 798 |
+
"loss": 11.5275,
|
| 799 |
+
"lr": 0.00039000000000000005,
|
| 800 |
+
"step": 196,
|
| 801 |
+
"tokens_trained": 0.096323512
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.0561662293454365,
|
| 805 |
+
"grad_norm": 586.6314086914062,
|
| 806 |
+
"loss": 16.2663,
|
| 807 |
+
"lr": 0.00039400000000000004,
|
| 808 |
+
"step": 198,
|
| 809 |
+
"tokens_trained": 0.097308864
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.056733564995390395,
|
| 813 |
+
"grad_norm": 624.9953002929688,
|
| 814 |
+
"loss": 16.627,
|
| 815 |
+
"lr": 0.000398,
|
| 816 |
+
"step": 200,
|
| 817 |
+
"tokens_trained": 0.098289064
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.0573009006453443,
|
| 821 |
+
"grad_norm": 585.9645385742188,
|
| 822 |
+
"loss": 15.8359,
|
| 823 |
+
"lr": 0.000402,
|
| 824 |
+
"step": 202,
|
| 825 |
+
"tokens_trained": 0.099269696
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.057868236295298206,
|
| 829 |
+
"grad_norm": 537.9913330078125,
|
| 830 |
+
"loss": 20.0779,
|
| 831 |
+
"lr": 0.00040600000000000006,
|
| 832 |
+
"step": 204,
|
| 833 |
+
"tokens_trained": 0.100248448
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.05843557194525211,
|
| 837 |
+
"grad_norm": 805.04931640625,
|
| 838 |
+
"loss": 21.4524,
|
| 839 |
+
"lr": 0.00041,
|
| 840 |
+
"step": 206,
|
| 841 |
+
"tokens_trained": 0.101231248
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.05900290759520602,
|
| 845 |
+
"grad_norm": 439.1418151855469,
|
| 846 |
+
"loss": 23.9852,
|
| 847 |
+
"lr": 0.000414,
|
| 848 |
+
"step": 208,
|
| 849 |
+
"tokens_trained": 0.102210688
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.059570243245159915,
|
| 853 |
+
"grad_norm": 502.684814453125,
|
| 854 |
+
"loss": 17.6273,
|
| 855 |
+
"lr": 0.00041799999999999997,
|
| 856 |
+
"step": 210,
|
| 857 |
+
"tokens_trained": 0.103192176
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.06013757889511382,
|
| 861 |
+
"grad_norm": 849.9979858398438,
|
| 862 |
+
"loss": 33.7517,
|
| 863 |
+
"lr": 0.000422,
|
| 864 |
+
"step": 212,
|
| 865 |
+
"tokens_trained": 0.104172824
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.060704914545067726,
|
| 869 |
+
"grad_norm": 939.583740234375,
|
| 870 |
+
"loss": 26.2559,
|
| 871 |
+
"lr": 0.000426,
|
| 872 |
+
"step": 214,
|
| 873 |
+
"tokens_trained": 0.105156672
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.06127225019502163,
|
| 877 |
+
"grad_norm": 525.0505981445312,
|
| 878 |
+
"loss": 20.0923,
|
| 879 |
+
"lr": 0.00043,
|
| 880 |
+
"step": 216,
|
| 881 |
+
"tokens_trained": 0.106141368
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.061839585844975536,
|
| 885 |
+
"grad_norm": 420.296630859375,
|
| 886 |
+
"loss": 17.9608,
|
| 887 |
+
"lr": 0.00043400000000000003,
|
| 888 |
+
"step": 218,
|
| 889 |
+
"tokens_trained": 0.107124088
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.062406921494929435,
|
| 893 |
+
"grad_norm": 711.3380737304688,
|
| 894 |
+
"loss": 19.387,
|
| 895 |
+
"lr": 0.000438,
|
| 896 |
+
"step": 220,
|
| 897 |
+
"tokens_trained": 0.108112632
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.06297425714488335,
|
| 901 |
+
"grad_norm": 759.183349609375,
|
| 902 |
+
"loss": 17.8061,
|
| 903 |
+
"lr": 0.000442,
|
| 904 |
+
"step": 222,
|
| 905 |
+
"tokens_trained": 0.1090934
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.06354159279483725,
|
| 909 |
+
"grad_norm": 790.025146484375,
|
| 910 |
+
"loss": 13.8539,
|
| 911 |
+
"lr": 0.000446,
|
| 912 |
+
"step": 224,
|
| 913 |
+
"tokens_trained": 0.110079512
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.06410892844479114,
|
| 917 |
+
"grad_norm": 769.8306274414062,
|
| 918 |
+
"loss": 22.1258,
|
| 919 |
+
"lr": 0.00045000000000000004,
|
| 920 |
+
"step": 226,
|
| 921 |
+
"tokens_trained": 0.111060152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.06467626409474506,
|
| 925 |
+
"grad_norm": 656.8352661132812,
|
| 926 |
+
"loss": 14.8646,
|
| 927 |
+
"lr": 0.00045400000000000003,
|
| 928 |
+
"step": 228,
|
| 929 |
+
"tokens_trained": 0.112044144
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.06524359974469895,
|
| 933 |
+
"grad_norm": 498.92010498046875,
|
| 934 |
+
"loss": 23.1558,
|
| 935 |
+
"lr": 0.000458,
|
| 936 |
+
"step": 230,
|
| 937 |
+
"tokens_trained": 0.113022928
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.06581093539465287,
|
| 941 |
+
"grad_norm": 764.0186157226562,
|
| 942 |
+
"loss": 16.7089,
|
| 943 |
+
"lr": 0.000462,
|
| 944 |
+
"step": 232,
|
| 945 |
+
"tokens_trained": 0.114003832
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.06637827104460677,
|
| 949 |
+
"grad_norm": 491.5793762207031,
|
| 950 |
+
"loss": 12.3979,
|
| 951 |
+
"lr": 0.00046600000000000005,
|
| 952 |
+
"step": 234,
|
| 953 |
+
"tokens_trained": 0.114991008
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.06694560669456066,
|
| 957 |
+
"grad_norm": 679.9217529296875,
|
| 958 |
+
"loss": 14.9037,
|
| 959 |
+
"lr": 0.00047,
|
| 960 |
+
"step": 236,
|
| 961 |
+
"tokens_trained": 0.115971888
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.06751294234451458,
|
| 965 |
+
"grad_norm": 491.0369567871094,
|
| 966 |
+
"loss": 7.7603,
|
| 967 |
+
"lr": 0.000474,
|
| 968 |
+
"step": 238,
|
| 969 |
+
"tokens_trained": 0.116952616
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.06808027799446847,
|
| 973 |
+
"grad_norm": 369.2186279296875,
|
| 974 |
+
"loss": 8.2256,
|
| 975 |
+
"lr": 0.00047799999999999996,
|
| 976 |
+
"step": 240,
|
| 977 |
+
"tokens_trained": 0.117935816
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.06864761364442239,
|
| 981 |
+
"grad_norm": 312.72137451171875,
|
| 982 |
+
"loss": 7.5486,
|
| 983 |
+
"lr": 0.000482,
|
| 984 |
+
"step": 242,
|
| 985 |
+
"tokens_trained": 0.118919392
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.06921494929437629,
|
| 989 |
+
"grad_norm": 596.1439208984375,
|
| 990 |
+
"loss": 11.7351,
|
| 991 |
+
"lr": 0.000486,
|
| 992 |
+
"step": 244,
|
| 993 |
+
"tokens_trained": 0.119901856
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.06978228494433018,
|
| 997 |
+
"grad_norm": 467.5667419433594,
|
| 998 |
+
"loss": 11.8403,
|
| 999 |
+
"lr": 0.00049,
|
| 1000 |
+
"step": 246,
|
| 1001 |
+
"tokens_trained": 0.120884624
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.0703496205942841,
|
| 1005 |
+
"grad_norm": 430.50048828125,
|
| 1006 |
+
"loss": 13.8081,
|
| 1007 |
+
"lr": 0.000494,
|
| 1008 |
+
"step": 248,
|
| 1009 |
+
"tokens_trained": 0.121869224
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.070916956244238,
|
| 1013 |
+
"grad_norm": 522.242919921875,
|
| 1014 |
+
"loss": 14.1892,
|
| 1015 |
+
"lr": 0.000498,
|
| 1016 |
+
"step": 250,
|
| 1017 |
+
"tokens_trained": 0.122853584
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.070916956244238,
|
| 1021 |
+
"eval_loss": 1.9294606447219849,
|
| 1022 |
+
"eval_runtime": 20.4162,
|
| 1023 |
+
"step": 250,
|
| 1024 |
+
"tokens_trained": 0.122853584
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.0714842918941919,
|
| 1028 |
+
"grad_norm": 835.2765502929688,
|
| 1029 |
+
"loss": 13.2462,
|
| 1030 |
+
"lr": 0.0005020000000000001,
|
| 1031 |
+
"step": 252,
|
| 1032 |
+
"tokens_trained": 0.123835544
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.0720516275441458,
|
| 1036 |
+
"grad_norm": 714.8098754882812,
|
| 1037 |
+
"loss": 20.0498,
|
| 1038 |
+
"lr": 0.000506,
|
| 1039 |
+
"step": 254,
|
| 1040 |
+
"tokens_trained": 0.124821616
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.0726189631940997,
|
| 1044 |
+
"grad_norm": 701.512939453125,
|
| 1045 |
+
"loss": 18.3664,
|
| 1046 |
+
"lr": 0.00051,
|
| 1047 |
+
"step": 256,
|
| 1048 |
+
"tokens_trained": 0.125807608
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.07318629884405362,
|
| 1052 |
+
"grad_norm": 773.987060546875,
|
| 1053 |
+
"loss": 21.3807,
|
| 1054 |
+
"lr": 0.000514,
|
| 1055 |
+
"step": 258,
|
| 1056 |
+
"tokens_trained": 0.126791464
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.07375363449400751,
|
| 1060 |
+
"grad_norm": 826.422119140625,
|
| 1061 |
+
"loss": 22.6403,
|
| 1062 |
+
"lr": 0.000518,
|
| 1063 |
+
"step": 260,
|
| 1064 |
+
"tokens_trained": 0.127771752
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.07432097014396143,
|
| 1068 |
+
"grad_norm": 742.8673095703125,
|
| 1069 |
+
"loss": 20.1504,
|
| 1070 |
+
"lr": 0.000522,
|
| 1071 |
+
"step": 262,
|
| 1072 |
+
"tokens_trained": 0.128755448
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.07488830579391532,
|
| 1076 |
+
"grad_norm": 797.79296875,
|
| 1077 |
+
"loss": 26.7343,
|
| 1078 |
+
"lr": 0.000526,
|
| 1079 |
+
"step": 264,
|
| 1080 |
+
"tokens_trained": 0.129741088
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.07545564144386922,
|
| 1084 |
+
"grad_norm": 673.9141235351562,
|
| 1085 |
+
"loss": 12.505,
|
| 1086 |
+
"lr": 0.0005300000000000001,
|
| 1087 |
+
"step": 266,
|
| 1088 |
+
"tokens_trained": 0.130727504
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.07602297709382314,
|
| 1092 |
+
"grad_norm": 310.6510925292969,
|
| 1093 |
+
"loss": 12.6344,
|
| 1094 |
+
"lr": 0.0005340000000000001,
|
| 1095 |
+
"step": 268,
|
| 1096 |
+
"tokens_trained": 0.131710296
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.07659031274377703,
|
| 1100 |
+
"grad_norm": 312.40966796875,
|
| 1101 |
+
"loss": 14.254,
|
| 1102 |
+
"lr": 0.0005380000000000001,
|
| 1103 |
+
"step": 270,
|
| 1104 |
+
"tokens_trained": 0.132695352
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.07715764839373095,
|
| 1108 |
+
"grad_norm": 492.2834777832031,
|
| 1109 |
+
"loss": 19.0979,
|
| 1110 |
+
"lr": 0.0005420000000000001,
|
| 1111 |
+
"step": 272,
|
| 1112 |
+
"tokens_trained": 0.133677928
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.07772498404368484,
|
| 1116 |
+
"grad_norm": 628.457763671875,
|
| 1117 |
+
"loss": 21.7735,
|
| 1118 |
+
"lr": 0.000546,
|
| 1119 |
+
"step": 274,
|
| 1120 |
+
"tokens_trained": 0.134655504
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.07829231969363874,
|
| 1124 |
+
"grad_norm": 382.8389892578125,
|
| 1125 |
+
"loss": 12.5128,
|
| 1126 |
+
"lr": 0.00055,
|
| 1127 |
+
"step": 276,
|
| 1128 |
+
"tokens_trained": 0.135640208
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.07885965534359266,
|
| 1132 |
+
"grad_norm": 483.12335205078125,
|
| 1133 |
+
"loss": 15.2589,
|
| 1134 |
+
"lr": 0.000554,
|
| 1135 |
+
"step": 278,
|
| 1136 |
+
"tokens_trained": 0.136624232
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.07942699099354655,
|
| 1140 |
+
"grad_norm": 640.658447265625,
|
| 1141 |
+
"loss": 12.1341,
|
| 1142 |
+
"lr": 0.000558,
|
| 1143 |
+
"step": 280,
|
| 1144 |
+
"tokens_trained": 0.13760628
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.07999432664350047,
|
| 1148 |
+
"grad_norm": 410.0824279785156,
|
| 1149 |
+
"loss": 12.5723,
|
| 1150 |
+
"lr": 0.0005620000000000001,
|
| 1151 |
+
"step": 282,
|
| 1152 |
+
"tokens_trained": 0.13858832
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.08056166229345436,
|
| 1156 |
+
"grad_norm": 513.2861328125,
|
| 1157 |
+
"loss": 14.8461,
|
| 1158 |
+
"lr": 0.000566,
|
| 1159 |
+
"step": 284,
|
| 1160 |
+
"tokens_trained": 0.139568424
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.08112899794340826,
|
| 1164 |
+
"grad_norm": 564.547607421875,
|
| 1165 |
+
"loss": 12.5792,
|
| 1166 |
+
"lr": 0.00057,
|
| 1167 |
+
"step": 286,
|
| 1168 |
+
"tokens_trained": 0.140557016
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.08169633359336217,
|
| 1172 |
+
"grad_norm": 451.3592834472656,
|
| 1173 |
+
"loss": 16.5433,
|
| 1174 |
+
"lr": 0.000574,
|
| 1175 |
+
"step": 288,
|
| 1176 |
+
"tokens_trained": 0.141540248
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.08226366924331607,
|
| 1180 |
+
"grad_norm": 404.2495422363281,
|
| 1181 |
+
"loss": 16.4138,
|
| 1182 |
+
"lr": 0.000578,
|
| 1183 |
+
"step": 290,
|
| 1184 |
+
"tokens_trained": 0.142528272
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.08283100489326999,
|
| 1188 |
+
"grad_norm": 566.5219116210938,
|
| 1189 |
+
"loss": 16.4743,
|
| 1190 |
+
"lr": 0.0005819999999999999,
|
| 1191 |
+
"step": 292,
|
| 1192 |
+
"tokens_trained": 0.143513096
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.08339834054322388,
|
| 1196 |
+
"grad_norm": 559.6517333984375,
|
| 1197 |
+
"loss": 16.421,
|
| 1198 |
+
"lr": 0.0005859999999999999,
|
| 1199 |
+
"step": 294,
|
| 1200 |
+
"tokens_trained": 0.144494472
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.08396567619317778,
|
| 1204 |
+
"grad_norm": 260.874755859375,
|
| 1205 |
+
"loss": 11.2214,
|
| 1206 |
+
"lr": 0.00059,
|
| 1207 |
+
"step": 296,
|
| 1208 |
+
"tokens_trained": 0.14547876
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.0845330118431317,
|
| 1212 |
+
"grad_norm": 272.02899169921875,
|
| 1213 |
+
"loss": 10.3491,
|
| 1214 |
+
"lr": 0.000594,
|
| 1215 |
+
"step": 298,
|
| 1216 |
+
"tokens_trained": 0.146465864
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.08510034749308559,
|
| 1220 |
+
"grad_norm": 556.9845581054688,
|
| 1221 |
+
"loss": 10.4348,
|
| 1222 |
+
"lr": 0.000598,
|
| 1223 |
+
"step": 300,
|
| 1224 |
+
"tokens_trained": 0.147446344
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0856676831430395,
|
| 1228 |
+
"grad_norm": 273.35772705078125,
|
| 1229 |
+
"loss": 8.3292,
|
| 1230 |
+
"lr": 0.000602,
|
| 1231 |
+
"step": 302,
|
| 1232 |
+
"tokens_trained": 0.14843244
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.0862350187929934,
|
| 1236 |
+
"grad_norm": 246.6316680908203,
|
| 1237 |
+
"loss": 9.9362,
|
| 1238 |
+
"lr": 0.000606,
|
| 1239 |
+
"step": 304,
|
| 1240 |
+
"tokens_trained": 0.149415976
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.0868023544429473,
|
| 1244 |
+
"grad_norm": 564.4365844726562,
|
| 1245 |
+
"loss": 9.2621,
|
| 1246 |
+
"lr": 0.00061,
|
| 1247 |
+
"step": 306,
|
| 1248 |
+
"tokens_trained": 0.150398728
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.08736969009290121,
|
| 1252 |
+
"grad_norm": 396.0948791503906,
|
| 1253 |
+
"loss": 11.8526,
|
| 1254 |
+
"lr": 0.000614,
|
| 1255 |
+
"step": 308,
|
| 1256 |
+
"tokens_trained": 0.151385104
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.08793702574285511,
|
| 1260 |
+
"grad_norm": 488.6072692871094,
|
| 1261 |
+
"loss": 11.8473,
|
| 1262 |
+
"lr": 0.0006180000000000001,
|
| 1263 |
+
"step": 310,
|
| 1264 |
+
"tokens_trained": 0.152373672
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.08850436139280903,
|
| 1268 |
+
"grad_norm": 346.70660400390625,
|
| 1269 |
+
"loss": 12.0897,
|
| 1270 |
+
"lr": 0.000622,
|
| 1271 |
+
"step": 312,
|
| 1272 |
+
"tokens_trained": 0.153356256
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.08907169704276292,
|
| 1276 |
+
"grad_norm": 382.40679931640625,
|
| 1277 |
+
"loss": 9.271,
|
| 1278 |
+
"lr": 0.000626,
|
| 1279 |
+
"step": 314,
|
| 1280 |
+
"tokens_trained": 0.154342632
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.08963903269271682,
|
| 1284 |
+
"grad_norm": 288.7908935546875,
|
| 1285 |
+
"loss": 9.185,
|
| 1286 |
+
"lr": 0.00063,
|
| 1287 |
+
"step": 316,
|
| 1288 |
+
"tokens_trained": 0.1553238
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.09020636834267073,
|
| 1292 |
+
"grad_norm": 337.5335388183594,
|
| 1293 |
+
"loss": 12.0555,
|
| 1294 |
+
"lr": 0.000634,
|
| 1295 |
+
"step": 318,
|
| 1296 |
+
"tokens_trained": 0.156313168
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 0.09077370399262463,
|
| 1300 |
+
"grad_norm": 349.25531005859375,
|
| 1301 |
+
"loss": 8.51,
|
| 1302 |
+
"lr": 0.000638,
|
| 1303 |
+
"step": 320,
|
| 1304 |
+
"tokens_trained": 0.157299448
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.09134103964257854,
|
| 1308 |
+
"grad_norm": 471.7824401855469,
|
| 1309 |
+
"loss": 14.1888,
|
| 1310 |
+
"lr": 0.000642,
|
| 1311 |
+
"step": 322,
|
| 1312 |
+
"tokens_trained": 0.158285264
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.09190837529253244,
|
| 1316 |
+
"grad_norm": 284.94036865234375,
|
| 1317 |
+
"loss": 10.1593,
|
| 1318 |
+
"lr": 0.000646,
|
| 1319 |
+
"step": 324,
|
| 1320 |
+
"tokens_trained": 0.159267512
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.09247571094248634,
|
| 1324 |
+
"grad_norm": 510.90478515625,
|
| 1325 |
+
"loss": 13.5744,
|
| 1326 |
+
"lr": 0.0006500000000000001,
|
| 1327 |
+
"step": 326,
|
| 1328 |
+
"tokens_trained": 0.160250856
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.09304304659244025,
|
| 1332 |
+
"grad_norm": 373.82965087890625,
|
| 1333 |
+
"loss": 8.4999,
|
| 1334 |
+
"lr": 0.0006540000000000001,
|
| 1335 |
+
"step": 328,
|
| 1336 |
+
"tokens_trained": 0.161231832
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.09361038224239415,
|
| 1340 |
+
"grad_norm": 219.3827362060547,
|
| 1341 |
+
"loss": 8.4436,
|
| 1342 |
+
"lr": 0.0006580000000000001,
|
| 1343 |
+
"step": 330,
|
| 1344 |
+
"tokens_trained": 0.162217656
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.09417771789234806,
|
| 1348 |
+
"grad_norm": 433.0914001464844,
|
| 1349 |
+
"loss": 11.2019,
|
| 1350 |
+
"lr": 0.000662,
|
| 1351 |
+
"step": 332,
|
| 1352 |
+
"tokens_trained": 0.163199096
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.09474505354230196,
|
| 1356 |
+
"grad_norm": 242.65907287597656,
|
| 1357 |
+
"loss": 9.0666,
|
| 1358 |
+
"lr": 0.000666,
|
| 1359 |
+
"step": 334,
|
| 1360 |
+
"tokens_trained": 0.164178512
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.09531238919225588,
|
| 1364 |
+
"grad_norm": 446.07916259765625,
|
| 1365 |
+
"loss": 8.6546,
|
| 1366 |
+
"lr": 0.00067,
|
| 1367 |
+
"step": 336,
|
| 1368 |
+
"tokens_trained": 0.165162464
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.09587972484220977,
|
| 1372 |
+
"grad_norm": 231.8892364501953,
|
| 1373 |
+
"loss": 7.5819,
|
| 1374 |
+
"lr": 0.000674,
|
| 1375 |
+
"step": 338,
|
| 1376 |
+
"tokens_trained": 0.166141536
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.09644706049216367,
|
| 1380 |
+
"grad_norm": 100.7306137084961,
|
| 1381 |
+
"loss": 6.7047,
|
| 1382 |
+
"lr": 0.0006780000000000001,
|
| 1383 |
+
"step": 340,
|
| 1384 |
+
"tokens_trained": 0.167123944
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.09701439614211758,
|
| 1388 |
+
"grad_norm": 78.11279296875,
|
| 1389 |
+
"loss": 5.9308,
|
| 1390 |
+
"lr": 0.0006820000000000001,
|
| 1391 |
+
"step": 342,
|
| 1392 |
+
"tokens_trained": 0.168105264
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.09758173179207148,
|
| 1396 |
+
"grad_norm": 271.466064453125,
|
| 1397 |
+
"loss": 6.9141,
|
| 1398 |
+
"lr": 0.0006860000000000001,
|
| 1399 |
+
"step": 344,
|
| 1400 |
+
"tokens_trained": 0.169088912
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.0981490674420254,
|
| 1404 |
+
"grad_norm": 252.54478454589844,
|
| 1405 |
+
"loss": 6.3281,
|
| 1406 |
+
"lr": 0.00069,
|
| 1407 |
+
"step": 346,
|
| 1408 |
+
"tokens_trained": 0.170077368
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.0987164030919793,
|
| 1412 |
+
"grad_norm": 305.8559875488281,
|
| 1413 |
+
"loss": 6.443,
|
| 1414 |
+
"lr": 0.000694,
|
| 1415 |
+
"step": 348,
|
| 1416 |
+
"tokens_trained": 0.171057232
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.09928373874193319,
|
| 1420 |
+
"grad_norm": 227.74374389648438,
|
| 1421 |
+
"loss": 6.552,
|
| 1422 |
+
"lr": 0.0006979999999999999,
|
| 1423 |
+
"step": 350,
|
| 1424 |
+
"tokens_trained": 0.172041376
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.0998510743918871,
|
| 1428 |
+
"grad_norm": 446.7601623535156,
|
| 1429 |
+
"loss": 10.8184,
|
| 1430 |
+
"lr": 0.0007019999999999999,
|
| 1431 |
+
"step": 352,
|
| 1432 |
+
"tokens_trained": 0.173023624
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.100418410041841,
|
| 1436 |
+
"grad_norm": 353.0849609375,
|
| 1437 |
+
"loss": 8.6327,
|
| 1438 |
+
"lr": 0.0007059999999999999,
|
| 1439 |
+
"step": 354,
|
| 1440 |
+
"tokens_trained": 0.174005992
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.10098574569179491,
|
| 1444 |
+
"grad_norm": 367.9427185058594,
|
| 1445 |
+
"loss": 9.3898,
|
| 1446 |
+
"lr": 0.00071,
|
| 1447 |
+
"step": 356,
|
| 1448 |
+
"tokens_trained": 0.174988304
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.10155308134174881,
|
| 1452 |
+
"grad_norm": 224.4961700439453,
|
| 1453 |
+
"loss": 8.284,
|
| 1454 |
+
"lr": 0.000714,
|
| 1455 |
+
"step": 358,
|
| 1456 |
+
"tokens_trained": 0.175969816
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.10212041699170271,
|
| 1460 |
+
"grad_norm": 221.86537170410156,
|
| 1461 |
+
"loss": 7.0578,
|
| 1462 |
+
"lr": 0.000718,
|
| 1463 |
+
"step": 360,
|
| 1464 |
+
"tokens_trained": 0.176952688
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.10268775264165662,
|
| 1468 |
+
"grad_norm": 331.0989685058594,
|
| 1469 |
+
"loss": 6.9561,
|
| 1470 |
+
"lr": 0.000722,
|
| 1471 |
+
"step": 362,
|
| 1472 |
+
"tokens_trained": 0.177935144
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.10325508829161052,
|
| 1476 |
+
"grad_norm": 171.6498260498047,
|
| 1477 |
+
"loss": 7.203,
|
| 1478 |
+
"lr": 0.000726,
|
| 1479 |
+
"step": 364,
|
| 1480 |
+
"tokens_trained": 0.178916776
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.10382242394156443,
|
| 1484 |
+
"grad_norm": 284.2208557128906,
|
| 1485 |
+
"loss": 10.3517,
|
| 1486 |
+
"lr": 0.00073,
|
| 1487 |
+
"step": 366,
|
| 1488 |
+
"tokens_trained": 0.179903432
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.10438975959151833,
|
| 1492 |
+
"grad_norm": 354.8574523925781,
|
| 1493 |
+
"loss": 9.3888,
|
| 1494 |
+
"lr": 0.000734,
|
| 1495 |
+
"step": 368,
|
| 1496 |
+
"tokens_trained": 0.180883224
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.10495709524147223,
|
| 1500 |
+
"grad_norm": 344.82574462890625,
|
| 1501 |
+
"loss": 10.5933,
|
| 1502 |
+
"lr": 0.000738,
|
| 1503 |
+
"step": 370,
|
| 1504 |
+
"tokens_trained": 0.181863808
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.10552443089142614,
|
| 1508 |
+
"grad_norm": 302.6838073730469,
|
| 1509 |
+
"loss": 10.2832,
|
| 1510 |
+
"lr": 0.000742,
|
| 1511 |
+
"step": 372,
|
| 1512 |
+
"tokens_trained": 0.182843712
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.10609176654138004,
|
| 1516 |
+
"grad_norm": 323.0387878417969,
|
| 1517 |
+
"loss": 6.4864,
|
| 1518 |
+
"lr": 0.000746,
|
| 1519 |
+
"step": 374,
|
| 1520 |
+
"tokens_trained": 0.183825832
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.10637543436635699,
|
| 1524 |
+
"eval_loss": 1.4430732727050781,
|
| 1525 |
+
"eval_runtime": 20.5468,
|
| 1526 |
+
"step": 375,
|
| 1527 |
+
"tokens_trained": 0.184317744
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.10665910219133395,
|
| 1531 |
+
"grad_norm": 133.74822998046875,
|
| 1532 |
+
"loss": 5.4176,
|
| 1533 |
+
"lr": 0.00075,
|
| 1534 |
+
"step": 376,
|
| 1535 |
+
"tokens_trained": 0.184811352
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.10722643784128785,
|
| 1539 |
+
"grad_norm": 180.3372344970703,
|
| 1540 |
+
"loss": 5.5641,
|
| 1541 |
+
"lr": 0.000754,
|
| 1542 |
+
"step": 378,
|
| 1543 |
+
"tokens_trained": 0.185792528
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.10779377349124175,
|
| 1547 |
+
"grad_norm": 250.83999633789062,
|
| 1548 |
+
"loss": 5.8612,
|
| 1549 |
+
"lr": 0.000758,
|
| 1550 |
+
"step": 380,
|
| 1551 |
+
"tokens_trained": 0.186777112
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.10836110914119566,
|
| 1555 |
+
"grad_norm": 293.51959228515625,
|
| 1556 |
+
"loss": 6.0418,
|
| 1557 |
+
"lr": 0.000762,
|
| 1558 |
+
"step": 382,
|
| 1559 |
+
"tokens_trained": 0.18775724
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.10892844479114956,
|
| 1563 |
+
"grad_norm": 292.56207275390625,
|
| 1564 |
+
"loss": 6.1812,
|
| 1565 |
+
"lr": 0.0007660000000000001,
|
| 1566 |
+
"step": 384,
|
| 1567 |
+
"tokens_trained": 0.188733568
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.10949578044110347,
|
| 1571 |
+
"grad_norm": 121.82467651367188,
|
| 1572 |
+
"loss": 6.0855,
|
| 1573 |
+
"lr": 0.0007700000000000001,
|
| 1574 |
+
"step": 386,
|
| 1575 |
+
"tokens_trained": 0.189718512
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.11006311609105737,
|
| 1579 |
+
"grad_norm": 124.30497741699219,
|
| 1580 |
+
"loss": 5.7734,
|
| 1581 |
+
"lr": 0.0007740000000000001,
|
| 1582 |
+
"step": 388,
|
| 1583 |
+
"tokens_trained": 0.190703776
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.11063045174101127,
|
| 1587 |
+
"grad_norm": 143.64004516601562,
|
| 1588 |
+
"loss": 5.7641,
|
| 1589 |
+
"lr": 0.000778,
|
| 1590 |
+
"step": 390,
|
| 1591 |
+
"tokens_trained": 0.191689888
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.11119778739096518,
|
| 1595 |
+
"grad_norm": 160.06784057617188,
|
| 1596 |
+
"loss": 5.6025,
|
| 1597 |
+
"lr": 0.000782,
|
| 1598 |
+
"step": 392,
|
| 1599 |
+
"tokens_trained": 0.192673992
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.11176512304091908,
|
| 1603 |
+
"grad_norm": 226.97988891601562,
|
| 1604 |
+
"loss": 6.0049,
|
| 1605 |
+
"lr": 0.000786,
|
| 1606 |
+
"step": 394,
|
| 1607 |
+
"tokens_trained": 0.193656272
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.112332458690873,
|
| 1611 |
+
"grad_norm": 223.26898193359375,
|
| 1612 |
+
"loss": 5.6972,
|
| 1613 |
+
"lr": 0.00079,
|
| 1614 |
+
"step": 396,
|
| 1615 |
+
"tokens_trained": 0.194639144
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.11289979434082689,
|
| 1619 |
+
"grad_norm": 249.34912109375,
|
| 1620 |
+
"loss": 5.7348,
|
| 1621 |
+
"lr": 0.0007940000000000001,
|
| 1622 |
+
"step": 398,
|
| 1623 |
+
"tokens_trained": 0.195621256
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.11346712999078079,
|
| 1627 |
+
"grad_norm": 161.34271240234375,
|
| 1628 |
+
"loss": 5.6689,
|
| 1629 |
+
"lr": 0.0007980000000000001,
|
| 1630 |
+
"step": 400,
|
| 1631 |
+
"tokens_trained": 0.196604136
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.1140344656407347,
|
| 1635 |
+
"grad_norm": 148.53176879882812,
|
| 1636 |
+
"loss": 5.702,
|
| 1637 |
+
"lr": 0.0008020000000000001,
|
| 1638 |
+
"step": 402,
|
| 1639 |
+
"tokens_trained": 0.197586784
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.1146018012906886,
|
| 1643 |
+
"grad_norm": 144.40835571289062,
|
| 1644 |
+
"loss": 6.2402,
|
| 1645 |
+
"lr": 0.0008060000000000001,
|
| 1646 |
+
"step": 404,
|
| 1647 |
+
"tokens_trained": 0.198570824
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.11516913694064251,
|
| 1651 |
+
"grad_norm": 306.57562255859375,
|
| 1652 |
+
"loss": 7.1739,
|
| 1653 |
+
"lr": 0.0008100000000000001,
|
| 1654 |
+
"step": 406,
|
| 1655 |
+
"tokens_trained": 0.199548328
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.11573647259059641,
|
| 1659 |
+
"grad_norm": 308.79180908203125,
|
| 1660 |
+
"loss": 6.0972,
|
| 1661 |
+
"lr": 0.0008139999999999999,
|
| 1662 |
+
"step": 408,
|
| 1663 |
+
"tokens_trained": 0.200532496
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.11630380824055031,
|
| 1667 |
+
"grad_norm": 197.76791381835938,
|
| 1668 |
+
"loss": 6.3533,
|
| 1669 |
+
"lr": 0.0008179999999999999,
|
| 1670 |
+
"step": 410,
|
| 1671 |
+
"tokens_trained": 0.201514648
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.11687114389050422,
|
| 1675 |
+
"grad_norm": 129.5694580078125,
|
| 1676 |
+
"loss": 6.9628,
|
| 1677 |
+
"lr": 0.0008219999999999999,
|
| 1678 |
+
"step": 412,
|
| 1679 |
+
"tokens_trained": 0.2024994
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.11743847954045812,
|
| 1683 |
+
"grad_norm": 446.0195617675781,
|
| 1684 |
+
"loss": 11.7562,
|
| 1685 |
+
"lr": 0.000826,
|
| 1686 |
+
"step": 414,
|
| 1687 |
+
"tokens_trained": 0.20348012
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.11800581519041203,
|
| 1691 |
+
"grad_norm": 355.5342712402344,
|
| 1692 |
+
"loss": 8.8055,
|
| 1693 |
+
"lr": 0.00083,
|
| 1694 |
+
"step": 416,
|
| 1695 |
+
"tokens_trained": 0.20446356
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.11857315084036593,
|
| 1699 |
+
"grad_norm": 456.2491149902344,
|
| 1700 |
+
"loss": 9.606,
|
| 1701 |
+
"lr": 0.000834,
|
| 1702 |
+
"step": 418,
|
| 1703 |
+
"tokens_trained": 0.205445288
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.11914048649031983,
|
| 1707 |
+
"grad_norm": 369.8676452636719,
|
| 1708 |
+
"loss": 8.385,
|
| 1709 |
+
"lr": 0.000838,
|
| 1710 |
+
"step": 420,
|
| 1711 |
+
"tokens_trained": 0.206427832
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.11970782214027374,
|
| 1715 |
+
"grad_norm": 262.19073486328125,
|
| 1716 |
+
"loss": 9.0956,
|
| 1717 |
+
"lr": 0.000842,
|
| 1718 |
+
"step": 422,
|
| 1719 |
+
"tokens_trained": 0.207409848
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.12027515779022764,
|
| 1723 |
+
"grad_norm": 120.3193130493164,
|
| 1724 |
+
"loss": 5.4937,
|
| 1725 |
+
"lr": 0.000846,
|
| 1726 |
+
"step": 424,
|
| 1727 |
+
"tokens_trained": 0.208391752
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 0.12084249344018155,
|
| 1731 |
+
"grad_norm": 222.1111297607422,
|
| 1732 |
+
"loss": 8.9367,
|
| 1733 |
+
"lr": 0.00085,
|
| 1734 |
+
"step": 426,
|
| 1735 |
+
"tokens_trained": 0.20937384
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.12140982909013545,
|
| 1739 |
+
"grad_norm": 137.16819763183594,
|
| 1740 |
+
"loss": 7.5876,
|
| 1741 |
+
"lr": 0.000854,
|
| 1742 |
+
"step": 428,
|
| 1743 |
+
"tokens_trained": 0.210358576
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.12197716474008935,
|
| 1747 |
+
"grad_norm": 267.61846923828125,
|
| 1748 |
+
"loss": 8.817,
|
| 1749 |
+
"lr": 0.000858,
|
| 1750 |
+
"step": 430,
|
| 1751 |
+
"tokens_trained": 0.211340064
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.12254450039004326,
|
| 1755 |
+
"grad_norm": 472.72906494140625,
|
| 1756 |
+
"loss": 8.203,
|
| 1757 |
+
"lr": 0.000862,
|
| 1758 |
+
"step": 432,
|
| 1759 |
+
"tokens_trained": 0.212321144
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.12311183603999716,
|
| 1763 |
+
"grad_norm": 297.1420593261719,
|
| 1764 |
+
"loss": 10.987,
|
| 1765 |
+
"lr": 0.000866,
|
| 1766 |
+
"step": 434,
|
| 1767 |
+
"tokens_trained": 0.213300312
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.12367917168995107,
|
| 1771 |
+
"grad_norm": 281.7297668457031,
|
| 1772 |
+
"loss": 7.6117,
|
| 1773 |
+
"lr": 0.00087,
|
| 1774 |
+
"step": 436,
|
| 1775 |
+
"tokens_trained": 0.214287624
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.12424650733990497,
|
| 1779 |
+
"grad_norm": 203.09678649902344,
|
| 1780 |
+
"loss": 6.5638,
|
| 1781 |
+
"lr": 0.000874,
|
| 1782 |
+
"step": 438,
|
| 1783 |
+
"tokens_trained": 0.215272136
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.12481384298985887,
|
| 1787 |
+
"grad_norm": 155.7823944091797,
|
| 1788 |
+
"loss": 6.1131,
|
| 1789 |
+
"lr": 0.000878,
|
| 1790 |
+
"step": 440,
|
| 1791 |
+
"tokens_trained": 0.216256392
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.12538117863981277,
|
| 1795 |
+
"grad_norm": 189.86196899414062,
|
| 1796 |
+
"loss": 8.2565,
|
| 1797 |
+
"lr": 0.000882,
|
| 1798 |
+
"step": 442,
|
| 1799 |
+
"tokens_trained": 0.217242504
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 0.1259485142897667,
|
| 1803 |
+
"grad_norm": 247.4568634033203,
|
| 1804 |
+
"loss": 7.1005,
|
| 1805 |
+
"lr": 0.0008860000000000001,
|
| 1806 |
+
"step": 444,
|
| 1807 |
+
"tokens_trained": 0.218226008
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.1265158499397206,
|
| 1811 |
+
"grad_norm": 179.72825622558594,
|
| 1812 |
+
"loss": 6.3379,
|
| 1813 |
+
"lr": 0.0008900000000000001,
|
| 1814 |
+
"step": 446,
|
| 1815 |
+
"tokens_trained": 0.219210584
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.1270831855896745,
|
| 1819 |
+
"grad_norm": 212.96356201171875,
|
| 1820 |
+
"loss": 7.2514,
|
| 1821 |
+
"lr": 0.000894,
|
| 1822 |
+
"step": 448,
|
| 1823 |
+
"tokens_trained": 0.220193952
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.1276505212396284,
|
| 1827 |
+
"grad_norm": 105.67095947265625,
|
| 1828 |
+
"loss": 5.456,
|
| 1829 |
+
"lr": 0.000898,
|
| 1830 |
+
"step": 450,
|
| 1831 |
+
"tokens_trained": 0.221176936
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.1282178568895823,
|
| 1835 |
+
"grad_norm": 302.9122619628906,
|
| 1836 |
+
"loss": 6.4018,
|
| 1837 |
+
"lr": 0.000902,
|
| 1838 |
+
"step": 452,
|
| 1839 |
+
"tokens_trained": 0.222161952
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.12878519253953621,
|
| 1843 |
+
"grad_norm": 215.66561889648438,
|
| 1844 |
+
"loss": 6.2853,
|
| 1845 |
+
"lr": 0.000906,
|
| 1846 |
+
"step": 454,
|
| 1847 |
+
"tokens_trained": 0.223144912
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.1293525281894901,
|
| 1851 |
+
"grad_norm": 272.9984130859375,
|
| 1852 |
+
"loss": 7.3902,
|
| 1853 |
+
"lr": 0.00091,
|
| 1854 |
+
"step": 456,
|
| 1855 |
+
"tokens_trained": 0.224127392
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.129919863839444,
|
| 1859 |
+
"grad_norm": 200.7503662109375,
|
| 1860 |
+
"loss": 6.1637,
|
| 1861 |
+
"lr": 0.0009140000000000001,
|
| 1862 |
+
"step": 458,
|
| 1863 |
+
"tokens_trained": 0.22511648
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.1304871994893979,
|
| 1867 |
+
"grad_norm": 93.23990631103516,
|
| 1868 |
+
"loss": 6.4867,
|
| 1869 |
+
"lr": 0.0009180000000000001,
|
| 1870 |
+
"step": 460,
|
| 1871 |
+
"tokens_trained": 0.226098144
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.1310545351393518,
|
| 1875 |
+
"grad_norm": 274.37164306640625,
|
| 1876 |
+
"loss": 8.99,
|
| 1877 |
+
"lr": 0.0009220000000000001,
|
| 1878 |
+
"step": 462,
|
| 1879 |
+
"tokens_trained": 0.227081848
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.13162187078930573,
|
| 1883 |
+
"grad_norm": 186.66322326660156,
|
| 1884 |
+
"loss": 8.7122,
|
| 1885 |
+
"lr": 0.0009260000000000001,
|
| 1886 |
+
"step": 464,
|
| 1887 |
+
"tokens_trained": 0.22806636
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.13218920643925963,
|
| 1891 |
+
"grad_norm": 586.1035766601562,
|
| 1892 |
+
"loss": 9.1045,
|
| 1893 |
+
"lr": 0.00093,
|
| 1894 |
+
"step": 466,
|
| 1895 |
+
"tokens_trained": 0.229047872
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 0.13275654208921353,
|
| 1899 |
+
"grad_norm": 227.55996704101562,
|
| 1900 |
+
"loss": 9.7276,
|
| 1901 |
+
"lr": 0.000934,
|
| 1902 |
+
"step": 468,
|
| 1903 |
+
"tokens_trained": 0.230031144
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.13332387773916743,
|
| 1907 |
+
"grad_norm": 229.26609802246094,
|
| 1908 |
+
"loss": 6.6244,
|
| 1909 |
+
"lr": 0.0009379999999999999,
|
| 1910 |
+
"step": 470,
|
| 1911 |
+
"tokens_trained": 0.2310158
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.13389121338912133,
|
| 1915 |
+
"grad_norm": 145.16331481933594,
|
| 1916 |
+
"loss": 5.759,
|
| 1917 |
+
"lr": 0.000942,
|
| 1918 |
+
"step": 472,
|
| 1919 |
+
"tokens_trained": 0.2319996
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.13445854903907525,
|
| 1923 |
+
"grad_norm": 109.9937744140625,
|
| 1924 |
+
"loss": 5.4838,
|
| 1925 |
+
"lr": 0.000946,
|
| 1926 |
+
"step": 474,
|
| 1927 |
+
"tokens_trained": 0.232983808
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.13502588468902915,
|
| 1931 |
+
"grad_norm": 135.74899291992188,
|
| 1932 |
+
"loss": 6.2738,
|
| 1933 |
+
"lr": 0.00095,
|
| 1934 |
+
"step": 476,
|
| 1935 |
+
"tokens_trained": 0.233963016
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.13559322033898305,
|
| 1939 |
+
"grad_norm": 142.99449157714844,
|
| 1940 |
+
"loss": 5.8459,
|
| 1941 |
+
"lr": 0.000954,
|
| 1942 |
+
"step": 478,
|
| 1943 |
+
"tokens_trained": 0.234948864
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 0.13616055598893695,
|
| 1947 |
+
"grad_norm": 198.66883850097656,
|
| 1948 |
+
"loss": 6.6626,
|
| 1949 |
+
"lr": 0.000958,
|
| 1950 |
+
"step": 480,
|
| 1951 |
+
"tokens_trained": 0.235932392
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.13672789163889085,
|
| 1955 |
+
"grad_norm": 260.76507568359375,
|
| 1956 |
+
"loss": 6.9299,
|
| 1957 |
+
"lr": 0.000962,
|
| 1958 |
+
"step": 482,
|
| 1959 |
+
"tokens_trained": 0.236915664
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.13729522728884477,
|
| 1963 |
+
"grad_norm": 267.97589111328125,
|
| 1964 |
+
"loss": 6.4343,
|
| 1965 |
+
"lr": 0.000966,
|
| 1966 |
+
"step": 484,
|
| 1967 |
+
"tokens_trained": 0.237896904
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.13786256293879867,
|
| 1971 |
+
"grad_norm": 89.8781967163086,
|
| 1972 |
+
"loss": 6.3203,
|
| 1973 |
+
"lr": 0.0009699999999999999,
|
| 1974 |
+
"step": 486,
|
| 1975 |
+
"tokens_trained": 0.238874528
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.13842989858875257,
|
| 1979 |
+
"grad_norm": 225.62985229492188,
|
| 1980 |
+
"loss": 6.2778,
|
| 1981 |
+
"lr": 0.000974,
|
| 1982 |
+
"step": 488,
|
| 1983 |
+
"tokens_trained": 0.2398588
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.13899723423870647,
|
| 1987 |
+
"grad_norm": 85.84110260009766,
|
| 1988 |
+
"loss": 5.2786,
|
| 1989 |
+
"lr": 0.000978,
|
| 1990 |
+
"step": 490,
|
| 1991 |
+
"tokens_trained": 0.240839968
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.13956456988866037,
|
| 1995 |
+
"grad_norm": 141.4368438720703,
|
| 1996 |
+
"loss": 5.5525,
|
| 1997 |
+
"lr": 0.000982,
|
| 1998 |
+
"step": 492,
|
| 1999 |
+
"tokens_trained": 0.241823544
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 0.1401319055386143,
|
| 2003 |
+
"grad_norm": 94.9535140991211,
|
| 2004 |
+
"loss": 5.4386,
|
| 2005 |
+
"lr": 0.0009860000000000001,
|
| 2006 |
+
"step": 494,
|
| 2007 |
+
"tokens_trained": 0.242805456
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.1406992411885682,
|
| 2011 |
+
"grad_norm": 157.4557647705078,
|
| 2012 |
+
"loss": 5.9786,
|
| 2013 |
+
"lr": 0.00099,
|
| 2014 |
+
"step": 496,
|
| 2015 |
+
"tokens_trained": 0.243792496
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.1412665768385221,
|
| 2019 |
+
"grad_norm": 319.5025634765625,
|
| 2020 |
+
"loss": 7.04,
|
| 2021 |
+
"lr": 0.000994,
|
| 2022 |
+
"step": 498,
|
| 2023 |
+
"tokens_trained": 0.244772472
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.141833912488476,
|
| 2027 |
+
"grad_norm": 282.26824951171875,
|
| 2028 |
+
"loss": 9.4037,
|
| 2029 |
+
"lr": 0.000998,
|
| 2030 |
+
"step": 500,
|
| 2031 |
+
"tokens_trained": 0.245758968
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.141833912488476,
|
| 2035 |
+
"eval_loss": 2.152184247970581,
|
| 2036 |
+
"eval_runtime": 21.2772,
|
| 2037 |
+
"step": 500,
|
| 2038 |
+
"tokens_trained": 0.245758968
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.1424012481384299,
|
| 2042 |
+
"grad_norm": 306.0666809082031,
|
| 2043 |
+
"loss": 7.8845,
|
| 2044 |
+
"lr": 0.00099986013986014,
|
| 2045 |
+
"step": 502,
|
| 2046 |
+
"tokens_trained": 0.246739024
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.1429685837883838,
|
| 2050 |
+
"grad_norm": 188.89024353027344,
|
| 2051 |
+
"loss": 6.8118,
|
| 2052 |
+
"lr": 0.0009995804195804196,
|
| 2053 |
+
"step": 504,
|
| 2054 |
+
"tokens_trained": 0.247726552
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.1435359194383377,
|
| 2058 |
+
"grad_norm": 228.97474670410156,
|
| 2059 |
+
"loss": 6.8475,
|
| 2060 |
+
"lr": 0.0009993006993006994,
|
| 2061 |
+
"step": 506,
|
| 2062 |
+
"tokens_trained": 0.24870688
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.1441032550882916,
|
| 2066 |
+
"grad_norm": 229.80029296875,
|
| 2067 |
+
"loss": 6.2171,
|
| 2068 |
+
"lr": 0.000999020979020979,
|
| 2069 |
+
"step": 508,
|
| 2070 |
+
"tokens_trained": 0.249689096
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 0.1446705907382455,
|
| 2074 |
+
"grad_norm": 157.30340576171875,
|
| 2075 |
+
"loss": 6.2281,
|
| 2076 |
+
"lr": 0.0009987412587412587,
|
| 2077 |
+
"step": 510,
|
| 2078 |
+
"tokens_trained": 0.250671768
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.1452379263881994,
|
| 2082 |
+
"grad_norm": 176.64683532714844,
|
| 2083 |
+
"loss": 6.5993,
|
| 2084 |
+
"lr": 0.0009984615384615386,
|
| 2085 |
+
"step": 512,
|
| 2086 |
+
"tokens_trained": 0.25165608
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.14580526203815333,
|
| 2090 |
+
"grad_norm": 197.20526123046875,
|
| 2091 |
+
"loss": 5.7267,
|
| 2092 |
+
"lr": 0.0009981818181818182,
|
| 2093 |
+
"step": 514,
|
| 2094 |
+
"tokens_trained": 0.252639712
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.14637259768810723,
|
| 2098 |
+
"grad_norm": 54.713260650634766,
|
| 2099 |
+
"loss": 5.7911,
|
| 2100 |
+
"lr": 0.000997902097902098,
|
| 2101 |
+
"step": 516,
|
| 2102 |
+
"tokens_trained": 0.253622816
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.14693993333806113,
|
| 2106 |
+
"grad_norm": 185.74923706054688,
|
| 2107 |
+
"loss": 7.0055,
|
| 2108 |
+
"lr": 0.0009976223776223777,
|
| 2109 |
+
"step": 518,
|
| 2110 |
+
"tokens_trained": 0.254602792
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.14750726898801503,
|
| 2114 |
+
"grad_norm": 240.31021118164062,
|
| 2115 |
+
"loss": 6.452,
|
| 2116 |
+
"lr": 0.0009973426573426573,
|
| 2117 |
+
"step": 520,
|
| 2118 |
+
"tokens_trained": 0.255584736
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.14807460463796893,
|
| 2122 |
+
"grad_norm": 160.2477264404297,
|
| 2123 |
+
"loss": 7.6556,
|
| 2124 |
+
"lr": 0.000997062937062937,
|
| 2125 |
+
"step": 522,
|
| 2126 |
+
"tokens_trained": 0.256563792
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.14864194028792285,
|
| 2130 |
+
"grad_norm": 283.0034484863281,
|
| 2131 |
+
"loss": 6.5345,
|
| 2132 |
+
"lr": 0.0009967832167832168,
|
| 2133 |
+
"step": 524,
|
| 2134 |
+
"tokens_trained": 0.257546656
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.14920927593787675,
|
| 2138 |
+
"grad_norm": 245.537109375,
|
| 2139 |
+
"loss": 6.3281,
|
| 2140 |
+
"lr": 0.0009965034965034964,
|
| 2141 |
+
"step": 526,
|
| 2142 |
+
"tokens_trained": 0.258530832
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.14977661158783065,
|
| 2146 |
+
"grad_norm": 162.1538848876953,
|
| 2147 |
+
"loss": 7.4072,
|
| 2148 |
+
"lr": 0.0009962237762237763,
|
| 2149 |
+
"step": 528,
|
| 2150 |
+
"tokens_trained": 0.259514528
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.15034394723778455,
|
| 2154 |
+
"grad_norm": 107.25792694091797,
|
| 2155 |
+
"loss": 5.356,
|
| 2156 |
+
"lr": 0.000995944055944056,
|
| 2157 |
+
"step": 530,
|
| 2158 |
+
"tokens_trained": 0.260500912
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.15091128288773845,
|
| 2162 |
+
"grad_norm": 173.73353576660156,
|
| 2163 |
+
"loss": 6.8625,
|
| 2164 |
+
"lr": 0.0009956643356643356,
|
| 2165 |
+
"step": 532,
|
| 2166 |
+
"tokens_trained": 0.26148632
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.15147861853769237,
|
| 2170 |
+
"grad_norm": 178.33541870117188,
|
| 2171 |
+
"loss": 5.8794,
|
| 2172 |
+
"lr": 0.0009953846153846154,
|
| 2173 |
+
"step": 534,
|
| 2174 |
+
"tokens_trained": 0.262468816
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 0.15204595418764627,
|
| 2178 |
+
"grad_norm": 181.2533416748047,
|
| 2179 |
+
"loss": 7.0243,
|
| 2180 |
+
"lr": 0.000995104895104895,
|
| 2181 |
+
"step": 536,
|
| 2182 |
+
"tokens_trained": 0.263446696
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 0.15261328983760017,
|
| 2186 |
+
"grad_norm": 208.79293823242188,
|
| 2187 |
+
"loss": 5.8908,
|
| 2188 |
+
"lr": 0.000994825174825175,
|
| 2189 |
+
"step": 538,
|
| 2190 |
+
"tokens_trained": 0.26443108
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 0.15318062548755407,
|
| 2194 |
+
"grad_norm": 148.66285705566406,
|
| 2195 |
+
"loss": 6.0831,
|
| 2196 |
+
"lr": 0.0009945454545454546,
|
| 2197 |
+
"step": 540,
|
| 2198 |
+
"tokens_trained": 0.265414496
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.15374796113750797,
|
| 2202 |
+
"grad_norm": 165.044189453125,
|
| 2203 |
+
"loss": 5.5594,
|
| 2204 |
+
"lr": 0.0009942657342657344,
|
| 2205 |
+
"step": 542,
|
| 2206 |
+
"tokens_trained": 0.266394128
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.1543152967874619,
|
| 2210 |
+
"grad_norm": 124.5405502319336,
|
| 2211 |
+
"loss": 5.2442,
|
| 2212 |
+
"lr": 0.000993986013986014,
|
| 2213 |
+
"step": 544,
|
| 2214 |
+
"tokens_trained": 0.267378768
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.1548826324374158,
|
| 2218 |
+
"grad_norm": 68.66510772705078,
|
| 2219 |
+
"loss": 5.1173,
|
| 2220 |
+
"lr": 0.0009937062937062937,
|
| 2221 |
+
"step": 546,
|
| 2222 |
+
"tokens_trained": 0.268360184
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.1554499680873697,
|
| 2226 |
+
"grad_norm": 57.052860260009766,
|
| 2227 |
+
"loss": 5.2348,
|
| 2228 |
+
"lr": 0.0009934265734265735,
|
| 2229 |
+
"step": 548,
|
| 2230 |
+
"tokens_trained": 0.269345672
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.1560173037373236,
|
| 2234 |
+
"grad_norm": 184.9175567626953,
|
| 2235 |
+
"loss": 6.7748,
|
| 2236 |
+
"lr": 0.0009931468531468532,
|
| 2237 |
+
"step": 550,
|
| 2238 |
+
"tokens_trained": 0.2703288
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 0.15658463938727749,
|
| 2242 |
+
"grad_norm": 72.9861831665039,
|
| 2243 |
+
"loss": 5.7387,
|
| 2244 |
+
"lr": 0.000992867132867133,
|
| 2245 |
+
"step": 552,
|
| 2246 |
+
"tokens_trained": 0.271309176
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.1571519750372314,
|
| 2250 |
+
"grad_norm": 135.864501953125,
|
| 2251 |
+
"loss": 6.3035,
|
| 2252 |
+
"lr": 0.0009925874125874127,
|
| 2253 |
+
"step": 554,
|
| 2254 |
+
"tokens_trained": 0.27229644
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 0.1577193106871853,
|
| 2258 |
+
"grad_norm": 130.579833984375,
|
| 2259 |
+
"loss": 5.4434,
|
| 2260 |
+
"lr": 0.0009923076923076923,
|
| 2261 |
+
"step": 556,
|
| 2262 |
+
"tokens_trained": 0.273277904
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.1582866463371392,
|
| 2266 |
+
"grad_norm": 206.77345275878906,
|
| 2267 |
+
"loss": 5.8649,
|
| 2268 |
+
"lr": 0.000992027972027972,
|
| 2269 |
+
"step": 558,
|
| 2270 |
+
"tokens_trained": 0.274261712
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.1588539819870931,
|
| 2274 |
+
"grad_norm": 144.0505828857422,
|
| 2275 |
+
"loss": 5.3459,
|
| 2276 |
+
"lr": 0.0009917482517482518,
|
| 2277 |
+
"step": 560,
|
| 2278 |
+
"tokens_trained": 0.2752468
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.159421317637047,
|
| 2282 |
+
"grad_norm": 87.56634521484375,
|
| 2283 |
+
"loss": 5.6321,
|
| 2284 |
+
"lr": 0.0009914685314685314,
|
| 2285 |
+
"step": 562,
|
| 2286 |
+
"tokens_trained": 0.276232384
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.15998865328700093,
|
| 2290 |
+
"grad_norm": 275.2727355957031,
|
| 2291 |
+
"loss": 6.7515,
|
| 2292 |
+
"lr": 0.0009911888111888113,
|
| 2293 |
+
"step": 564,
|
| 2294 |
+
"tokens_trained": 0.277211608
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.16055598893695483,
|
| 2298 |
+
"grad_norm": 97.00019836425781,
|
| 2299 |
+
"loss": 5.4374,
|
| 2300 |
+
"lr": 0.000990909090909091,
|
| 2301 |
+
"step": 566,
|
| 2302 |
+
"tokens_trained": 0.278196336
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 0.16112332458690873,
|
| 2306 |
+
"grad_norm": 102.91439056396484,
|
| 2307 |
+
"loss": 5.729,
|
| 2308 |
+
"lr": 0.0009906293706293705,
|
| 2309 |
+
"step": 568,
|
| 2310 |
+
"tokens_trained": 0.279175672
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 0.16169066023686263,
|
| 2314 |
+
"grad_norm": 151.12432861328125,
|
| 2315 |
+
"loss": 5.4189,
|
| 2316 |
+
"lr": 0.0009903496503496504,
|
| 2317 |
+
"step": 570,
|
| 2318 |
+
"tokens_trained": 0.280161088
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.16225799588681653,
|
| 2322 |
+
"grad_norm": 86.6823959350586,
|
| 2323 |
+
"loss": 5.1704,
|
| 2324 |
+
"lr": 0.00099006993006993,
|
| 2325 |
+
"step": 572,
|
| 2326 |
+
"tokens_trained": 0.28114256
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.16282533153677045,
|
| 2330 |
+
"grad_norm": 90.7052230834961,
|
| 2331 |
+
"loss": 5.3673,
|
| 2332 |
+
"lr": 0.0009897902097902099,
|
| 2333 |
+
"step": 574,
|
| 2334 |
+
"tokens_trained": 0.282128904
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.16339266718672435,
|
| 2338 |
+
"grad_norm": 146.92874145507812,
|
| 2339 |
+
"loss": 5.5971,
|
| 2340 |
+
"lr": 0.0009895104895104895,
|
| 2341 |
+
"step": 576,
|
| 2342 |
+
"tokens_trained": 0.28311528
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.16396000283667825,
|
| 2346 |
+
"grad_norm": 189.76296997070312,
|
| 2347 |
+
"loss": 5.3109,
|
| 2348 |
+
"lr": 0.0009892307692307694,
|
| 2349 |
+
"step": 578,
|
| 2350 |
+
"tokens_trained": 0.284098528
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.16452733848663215,
|
| 2354 |
+
"grad_norm": 174.48092651367188,
|
| 2355 |
+
"loss": 5.68,
|
| 2356 |
+
"lr": 0.000988951048951049,
|
| 2357 |
+
"step": 580,
|
| 2358 |
+
"tokens_trained": 0.285081064
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 0.16509467413658604,
|
| 2362 |
+
"grad_norm": 154.10816955566406,
|
| 2363 |
+
"loss": 5.3307,
|
| 2364 |
+
"lr": 0.0009886713286713286,
|
| 2365 |
+
"step": 582,
|
| 2366 |
+
"tokens_trained": 0.286067952
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.16566200978653997,
|
| 2370 |
+
"grad_norm": 64.28263092041016,
|
| 2371 |
+
"loss": 5.1676,
|
| 2372 |
+
"lr": 0.0009883916083916085,
|
| 2373 |
+
"step": 584,
|
| 2374 |
+
"tokens_trained": 0.287051384
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.16622934543649387,
|
| 2378 |
+
"grad_norm": 103.81795501708984,
|
| 2379 |
+
"loss": 5.3436,
|
| 2380 |
+
"lr": 0.0009881118881118881,
|
| 2381 |
+
"step": 586,
|
| 2382 |
+
"tokens_trained": 0.28803284
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.16679668108644777,
|
| 2386 |
+
"grad_norm": 144.0076904296875,
|
| 2387 |
+
"loss": 5.3033,
|
| 2388 |
+
"lr": 0.000987832167832168,
|
| 2389 |
+
"step": 588,
|
| 2390 |
+
"tokens_trained": 0.289014824
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.16736401673640167,
|
| 2394 |
+
"grad_norm": 88.31237030029297,
|
| 2395 |
+
"loss": 5.0609,
|
| 2396 |
+
"lr": 0.0009875524475524476,
|
| 2397 |
+
"step": 590,
|
| 2398 |
+
"tokens_trained": 0.289999864
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 0.16793135238635556,
|
| 2402 |
+
"grad_norm": 68.4583740234375,
|
| 2403 |
+
"loss": 5.0702,
|
| 2404 |
+
"lr": 0.0009872727272727273,
|
| 2405 |
+
"step": 592,
|
| 2406 |
+
"tokens_trained": 0.290983888
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.1684986880363095,
|
| 2410 |
+
"grad_norm": 135.28665161132812,
|
| 2411 |
+
"loss": 5.3962,
|
| 2412 |
+
"lr": 0.000986993006993007,
|
| 2413 |
+
"step": 594,
|
| 2414 |
+
"tokens_trained": 0.291965752
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.1690660236862634,
|
| 2418 |
+
"grad_norm": 80.0412368774414,
|
| 2419 |
+
"loss": 5.0246,
|
| 2420 |
+
"lr": 0.0009867132867132867,
|
| 2421 |
+
"step": 596,
|
| 2422 |
+
"tokens_trained": 0.292946952
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 0.1696333593362173,
|
| 2426 |
+
"grad_norm": 43.29194641113281,
|
| 2427 |
+
"loss": 5.0051,
|
| 2428 |
+
"lr": 0.0009864335664335664,
|
| 2429 |
+
"step": 598,
|
| 2430 |
+
"tokens_trained": 0.293928976
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 0.17020069498617119,
|
| 2434 |
+
"grad_norm": 220.88687133789062,
|
| 2435 |
+
"loss": 6.0798,
|
| 2436 |
+
"lr": 0.0009861538461538462,
|
| 2437 |
+
"step": 600,
|
| 2438 |
+
"tokens_trained": 0.294912408
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.17076803063612508,
|
| 2442 |
+
"grad_norm": 102.58654022216797,
|
| 2443 |
+
"loss": 5.1271,
|
| 2444 |
+
"lr": 0.0009858741258741259,
|
| 2445 |
+
"step": 602,
|
| 2446 |
+
"tokens_trained": 0.29589416
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.171335366286079,
|
| 2450 |
+
"grad_norm": 119.0067138671875,
|
| 2451 |
+
"loss": 5.7402,
|
| 2452 |
+
"lr": 0.0009855944055944055,
|
| 2453 |
+
"step": 604,
|
| 2454 |
+
"tokens_trained": 0.296878584
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.1719027019360329,
|
| 2458 |
+
"grad_norm": 138.8656005859375,
|
| 2459 |
+
"loss": 5.1951,
|
| 2460 |
+
"lr": 0.0009853146853146854,
|
| 2461 |
+
"step": 606,
|
| 2462 |
+
"tokens_trained": 0.297864552
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.1724700375859868,
|
| 2466 |
+
"grad_norm": 73.5890884399414,
|
| 2467 |
+
"loss": 5.2522,
|
| 2468 |
+
"lr": 0.000985034965034965,
|
| 2469 |
+
"step": 608,
|
| 2470 |
+
"tokens_trained": 0.298854088
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 0.1730373732359407,
|
| 2474 |
+
"grad_norm": 113.78330993652344,
|
| 2475 |
+
"loss": 5.6683,
|
| 2476 |
+
"lr": 0.0009847552447552449,
|
| 2477 |
+
"step": 610,
|
| 2478 |
+
"tokens_trained": 0.299835024
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 0.1736047088858946,
|
| 2482 |
+
"grad_norm": 125.20297241210938,
|
| 2483 |
+
"loss": 5.1812,
|
| 2484 |
+
"lr": 0.0009844755244755245,
|
| 2485 |
+
"step": 612,
|
| 2486 |
+
"tokens_trained": 0.30082032
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.17417204453584853,
|
| 2490 |
+
"grad_norm": 67.46041870117188,
|
| 2491 |
+
"loss": 5.0417,
|
| 2492 |
+
"lr": 0.0009841958041958043,
|
| 2493 |
+
"step": 614,
|
| 2494 |
+
"tokens_trained": 0.301808456
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.17473938018580243,
|
| 2498 |
+
"grad_norm": 117.30754852294922,
|
| 2499 |
+
"loss": 5.3064,
|
| 2500 |
+
"lr": 0.000983916083916084,
|
| 2501 |
+
"step": 616,
|
| 2502 |
+
"tokens_trained": 0.302794456
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.17530671583575633,
|
| 2506 |
+
"grad_norm": 124.30754089355469,
|
| 2507 |
+
"loss": 5.1614,
|
| 2508 |
+
"lr": 0.0009836363636363636,
|
| 2509 |
+
"step": 618,
|
| 2510 |
+
"tokens_trained": 0.303777376
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.17587405148571023,
|
| 2514 |
+
"grad_norm": 102.72042083740234,
|
| 2515 |
+
"loss": 5.1265,
|
| 2516 |
+
"lr": 0.0009833566433566435,
|
| 2517 |
+
"step": 620,
|
| 2518 |
+
"tokens_trained": 0.304758864
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 0.17644138713566412,
|
| 2522 |
+
"grad_norm": 39.332252502441406,
|
| 2523 |
+
"loss": 5.1078,
|
| 2524 |
+
"lr": 0.000983076923076923,
|
| 2525 |
+
"step": 622,
|
| 2526 |
+
"tokens_trained": 0.30574392
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 0.17700872278561805,
|
| 2530 |
+
"grad_norm": 153.84811401367188,
|
| 2531 |
+
"loss": 5.7696,
|
| 2532 |
+
"lr": 0.000982797202797203,
|
| 2533 |
+
"step": 624,
|
| 2534 |
+
"tokens_trained": 0.306727584
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.17729239061059499,
|
| 2538 |
+
"eval_loss": 1.3463915586471558,
|
| 2539 |
+
"eval_runtime": 20.8357,
|
| 2540 |
+
"step": 625,
|
| 2541 |
+
"tokens_trained": 0.307220496
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 0.17757605843557195,
|
| 2545 |
+
"grad_norm": 160.2552490234375,
|
| 2546 |
+
"loss": 5.2283,
|
| 2547 |
+
"lr": 0.0009825174825174826,
|
| 2548 |
+
"step": 626,
|
| 2549 |
+
"tokens_trained": 0.307713024
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 0.17814339408552585,
|
| 2553 |
+
"grad_norm": 186.77407836914062,
|
| 2554 |
+
"loss": 5.2866,
|
| 2555 |
+
"lr": 0.0009822377622377622,
|
| 2556 |
+
"step": 628,
|
| 2557 |
+
"tokens_trained": 0.308700128
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.17871072973547975,
|
| 2561 |
+
"grad_norm": 84.55519104003906,
|
| 2562 |
+
"loss": 5.1106,
|
| 2563 |
+
"lr": 0.0009819580419580419,
|
| 2564 |
+
"step": 630,
|
| 2565 |
+
"tokens_trained": 0.309681208
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.17927806538543364,
|
| 2569 |
+
"grad_norm": 20.617040634155273,
|
| 2570 |
+
"loss": 4.8327,
|
| 2571 |
+
"lr": 0.0009816783216783217,
|
| 2572 |
+
"step": 632,
|
| 2573 |
+
"tokens_trained": 0.310662224
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 0.17984540103538757,
|
| 2577 |
+
"grad_norm": 168.06039428710938,
|
| 2578 |
+
"loss": 6.0704,
|
| 2579 |
+
"lr": 0.0009813986013986014,
|
| 2580 |
+
"step": 634,
|
| 2581 |
+
"tokens_trained": 0.31164064
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.18041273668534147,
|
| 2585 |
+
"grad_norm": 238.23736572265625,
|
| 2586 |
+
"loss": 5.6188,
|
| 2587 |
+
"lr": 0.0009811188811188812,
|
| 2588 |
+
"step": 636,
|
| 2589 |
+
"tokens_trained": 0.312622568
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.18098007233529537,
|
| 2593 |
+
"grad_norm": 140.0707550048828,
|
| 2594 |
+
"loss": 6.4034,
|
| 2595 |
+
"lr": 0.0009808391608391608,
|
| 2596 |
+
"step": 638,
|
| 2597 |
+
"tokens_trained": 0.313604944
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 0.18154740798524927,
|
| 2601 |
+
"grad_norm": 161.19302368164062,
|
| 2602 |
+
"loss": 5.4906,
|
| 2603 |
+
"lr": 0.0009805594405594405,
|
| 2604 |
+
"step": 640,
|
| 2605 |
+
"tokens_trained": 0.314592072
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.18211474363520316,
|
| 2609 |
+
"grad_norm": 121.9577407836914,
|
| 2610 |
+
"loss": 5.2097,
|
| 2611 |
+
"lr": 0.0009802797202797203,
|
| 2612 |
+
"step": 642,
|
| 2613 |
+
"tokens_trained": 0.315574392
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.1826820792851571,
|
| 2617 |
+
"grad_norm": 121.25574493408203,
|
| 2618 |
+
"loss": 5.0317,
|
| 2619 |
+
"lr": 0.00098,
|
| 2620 |
+
"step": 644,
|
| 2621 |
+
"tokens_trained": 0.316559008
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.183249414935111,
|
| 2625 |
+
"grad_norm": 28.328269958496094,
|
| 2626 |
+
"loss": 4.932,
|
| 2627 |
+
"lr": 0.0009797202797202798,
|
| 2628 |
+
"step": 646,
|
| 2629 |
+
"tokens_trained": 0.317538776
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 0.1838167505850649,
|
| 2633 |
+
"grad_norm": 127.77408599853516,
|
| 2634 |
+
"loss": 5.8335,
|
| 2635 |
+
"lr": 0.0009794405594405595,
|
| 2636 |
+
"step": 648,
|
| 2637 |
+
"tokens_trained": 0.31851792
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 0.18438408623501878,
|
| 2641 |
+
"grad_norm": 94.9522933959961,
|
| 2642 |
+
"loss": 5.1948,
|
| 2643 |
+
"lr": 0.000979160839160839,
|
| 2644 |
+
"step": 650,
|
| 2645 |
+
"tokens_trained": 0.319501576
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 0.18495142188497268,
|
| 2649 |
+
"grad_norm": 110.33658599853516,
|
| 2650 |
+
"loss": 5.098,
|
| 2651 |
+
"lr": 0.000978881118881119,
|
| 2652 |
+
"step": 652,
|
| 2653 |
+
"tokens_trained": 0.320482392
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 0.1855187575349266,
|
| 2657 |
+
"grad_norm": 67.23124694824219,
|
| 2658 |
+
"loss": 4.7723,
|
| 2659 |
+
"lr": 0.0009786013986013986,
|
| 2660 |
+
"step": 654,
|
| 2661 |
+
"tokens_trained": 0.32146712
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 0.1860860931848805,
|
| 2665 |
+
"grad_norm": 61.519866943359375,
|
| 2666 |
+
"loss": 4.7245,
|
| 2667 |
+
"lr": 0.0009783216783216782,
|
| 2668 |
+
"step": 656,
|
| 2669 |
+
"tokens_trained": 0.322449576
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.1866534288348344,
|
| 2673 |
+
"grad_norm": 99.51078033447266,
|
| 2674 |
+
"loss": 4.783,
|
| 2675 |
+
"lr": 0.000978041958041958,
|
| 2676 |
+
"step": 658,
|
| 2677 |
+
"tokens_trained": 0.323432688
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.1872207644847883,
|
| 2681 |
+
"grad_norm": 44.619197845458984,
|
| 2682 |
+
"loss": 4.7495,
|
| 2683 |
+
"lr": 0.000977762237762238,
|
| 2684 |
+
"step": 660,
|
| 2685 |
+
"tokens_trained": 0.324413952
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 0.18778810013474223,
|
| 2689 |
+
"grad_norm": 114.5891342163086,
|
| 2690 |
+
"loss": 5.1261,
|
| 2691 |
+
"lr": 0.0009774825174825176,
|
| 2692 |
+
"step": 662,
|
| 2693 |
+
"tokens_trained": 0.325394536
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 0.18835543578469613,
|
| 2697 |
+
"grad_norm": 100.3728256225586,
|
| 2698 |
+
"loss": 4.7883,
|
| 2699 |
+
"lr": 0.0009772027972027972,
|
| 2700 |
+
"step": 664,
|
| 2701 |
+
"tokens_trained": 0.326374672
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 0.18892277143465003,
|
| 2705 |
+
"grad_norm": 51.883033752441406,
|
| 2706 |
+
"loss": 4.7249,
|
| 2707 |
+
"lr": 0.0009769230769230768,
|
| 2708 |
+
"step": 666,
|
| 2709 |
+
"tokens_trained": 0.327357152
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 0.18949010708460393,
|
| 2713 |
+
"grad_norm": 82.27507019042969,
|
| 2714 |
+
"loss": 4.8277,
|
| 2715 |
+
"lr": 0.0009766433566433567,
|
| 2716 |
+
"step": 668,
|
| 2717 |
+
"tokens_trained": 0.328342088
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 0.19005744273455782,
|
| 2721 |
+
"grad_norm": 83.53064727783203,
|
| 2722 |
+
"loss": 4.8338,
|
| 2723 |
+
"lr": 0.0009763636363636363,
|
| 2724 |
+
"step": 670,
|
| 2725 |
+
"tokens_trained": 0.329319248
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.19062477838451175,
|
| 2729 |
+
"grad_norm": 76.18387603759766,
|
| 2730 |
+
"loss": 4.6958,
|
| 2731 |
+
"lr": 0.0009760839160839161,
|
| 2732 |
+
"step": 672,
|
| 2733 |
+
"tokens_trained": 0.330305968
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.19119211403446565,
|
| 2737 |
+
"grad_norm": 27.401426315307617,
|
| 2738 |
+
"loss": 4.6929,
|
| 2739 |
+
"lr": 0.0009758041958041958,
|
| 2740 |
+
"step": 674,
|
| 2741 |
+
"tokens_trained": 0.3312912
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 0.19175944968441955,
|
| 2745 |
+
"grad_norm": 186.770263671875,
|
| 2746 |
+
"loss": 5.5089,
|
| 2747 |
+
"lr": 0.0009755244755244756,
|
| 2748 |
+
"step": 676,
|
| 2749 |
+
"tokens_trained": 0.332275224
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 0.19232678533437345,
|
| 2753 |
+
"grad_norm": 105.02385711669922,
|
| 2754 |
+
"loss": 4.8876,
|
| 2755 |
+
"lr": 0.0009752447552447553,
|
| 2756 |
+
"step": 678,
|
| 2757 |
+
"tokens_trained": 0.33325588
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 0.19289412098432734,
|
| 2761 |
+
"grad_norm": 94.96269989013672,
|
| 2762 |
+
"loss": 5.1235,
|
| 2763 |
+
"lr": 0.0009749650349650349,
|
| 2764 |
+
"step": 680,
|
| 2765 |
+
"tokens_trained": 0.334238408
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 0.19346145663428127,
|
| 2769 |
+
"grad_norm": 92.29356384277344,
|
| 2770 |
+
"loss": 4.8194,
|
| 2771 |
+
"lr": 0.0009746853146853148,
|
| 2772 |
+
"step": 682,
|
| 2773 |
+
"tokens_trained": 0.335219368
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 0.19402879228423517,
|
| 2777 |
+
"grad_norm": 59.1584358215332,
|
| 2778 |
+
"loss": 4.7511,
|
| 2779 |
+
"lr": 0.0009744055944055944,
|
| 2780 |
+
"step": 684,
|
| 2781 |
+
"tokens_trained": 0.336207136
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.19459612793418907,
|
| 2785 |
+
"grad_norm": 54.759002685546875,
|
| 2786 |
+
"loss": 4.777,
|
| 2787 |
+
"lr": 0.0009741258741258742,
|
| 2788 |
+
"step": 686,
|
| 2789 |
+
"tokens_trained": 0.337193536
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.19516346358414297,
|
| 2793 |
+
"grad_norm": 92.20452880859375,
|
| 2794 |
+
"loss": 4.8225,
|
| 2795 |
+
"lr": 0.0009738461538461538,
|
| 2796 |
+
"step": 688,
|
| 2797 |
+
"tokens_trained": 0.338179224
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 0.19573079923409686,
|
| 2801 |
+
"grad_norm": 75.97005462646484,
|
| 2802 |
+
"loss": 4.655,
|
| 2803 |
+
"lr": 0.0009735664335664336,
|
| 2804 |
+
"step": 690,
|
| 2805 |
+
"tokens_trained": 0.339162168
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 0.1962981348840508,
|
| 2809 |
+
"grad_norm": 58.19076919555664,
|
| 2810 |
+
"loss": 4.6446,
|
| 2811 |
+
"lr": 0.0009732867132867133,
|
| 2812 |
+
"step": 692,
|
| 2813 |
+
"tokens_trained": 0.340138904
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 0.1968654705340047,
|
| 2817 |
+
"grad_norm": 50.81512451171875,
|
| 2818 |
+
"loss": 4.5866,
|
| 2819 |
+
"lr": 0.000973006993006993,
|
| 2820 |
+
"step": 694,
|
| 2821 |
+
"tokens_trained": 0.34112288
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 0.1974328061839586,
|
| 2825 |
+
"grad_norm": 61.683372497558594,
|
| 2826 |
+
"loss": 4.6018,
|
| 2827 |
+
"lr": 0.0009727272727272728,
|
| 2828 |
+
"step": 696,
|
| 2829 |
+
"tokens_trained": 0.342111992
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.19800014183391249,
|
| 2833 |
+
"grad_norm": 61.01798629760742,
|
| 2834 |
+
"loss": 4.6007,
|
| 2835 |
+
"lr": 0.0009724475524475524,
|
| 2836 |
+
"step": 698,
|
| 2837 |
+
"tokens_trained": 0.343095912
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.19856747748386638,
|
| 2841 |
+
"grad_norm": 96.49671936035156,
|
| 2842 |
+
"loss": 4.7035,
|
| 2843 |
+
"lr": 0.0009721678321678323,
|
| 2844 |
+
"step": 700,
|
| 2845 |
+
"tokens_trained": 0.344078632
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.1991348131338203,
|
| 2849 |
+
"grad_norm": 64.7771224975586,
|
| 2850 |
+
"loss": 4.8341,
|
| 2851 |
+
"lr": 0.0009718881118881119,
|
| 2852 |
+
"step": 702,
|
| 2853 |
+
"tokens_trained": 0.345060576
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.1997021487837742,
|
| 2857 |
+
"grad_norm": 90.1478042602539,
|
| 2858 |
+
"loss": 4.7739,
|
| 2859 |
+
"lr": 0.0009716083916083917,
|
| 2860 |
+
"step": 704,
|
| 2861 |
+
"tokens_trained": 0.34604112
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 0.2002694844337281,
|
| 2865 |
+
"grad_norm": 67.6308822631836,
|
| 2866 |
+
"loss": 4.6218,
|
| 2867 |
+
"lr": 0.0009713286713286713,
|
| 2868 |
+
"step": 706,
|
| 2869 |
+
"tokens_trained": 0.347023496
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 0.200836820083682,
|
| 2873 |
+
"grad_norm": 40.50175094604492,
|
| 2874 |
+
"loss": 4.6008,
|
| 2875 |
+
"lr": 0.000971048951048951,
|
| 2876 |
+
"step": 708,
|
| 2877 |
+
"tokens_trained": 0.348005416
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 0.2014041557336359,
|
| 2881 |
+
"grad_norm": 33.6448860168457,
|
| 2882 |
+
"loss": 4.5307,
|
| 2883 |
+
"lr": 0.0009707692307692308,
|
| 2884 |
+
"step": 710,
|
| 2885 |
+
"tokens_trained": 0.3489886
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 0.20197149138358983,
|
| 2889 |
+
"grad_norm": 15.484851837158203,
|
| 2890 |
+
"loss": 4.5065,
|
| 2891 |
+
"lr": 0.0009704895104895105,
|
| 2892 |
+
"step": 712,
|
| 2893 |
+
"tokens_trained": 0.34997024
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.20253882703354373,
|
| 2897 |
+
"grad_norm": 109.26301574707031,
|
| 2898 |
+
"loss": 4.9613,
|
| 2899 |
+
"lr": 0.0009702097902097903,
|
| 2900 |
+
"step": 714,
|
| 2901 |
+
"tokens_trained": 0.350958496
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.20310616268349763,
|
| 2905 |
+
"grad_norm": 150.07492065429688,
|
| 2906 |
+
"loss": 4.8507,
|
| 2907 |
+
"lr": 0.0009699300699300699,
|
| 2908 |
+
"step": 716,
|
| 2909 |
+
"tokens_trained": 0.35193892
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 0.20367349833345152,
|
| 2913 |
+
"grad_norm": 113.43978881835938,
|
| 2914 |
+
"loss": 5.4494,
|
| 2915 |
+
"lr": 0.0009696503496503498,
|
| 2916 |
+
"step": 718,
|
| 2917 |
+
"tokens_trained": 0.35291908
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.20424083398340542,
|
| 2921 |
+
"grad_norm": 123.0071792602539,
|
| 2922 |
+
"loss": 4.9475,
|
| 2923 |
+
"lr": 0.0009693706293706294,
|
| 2924 |
+
"step": 720,
|
| 2925 |
+
"tokens_trained": 0.353896072
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 0.20480816963335935,
|
| 2929 |
+
"grad_norm": 65.55500793457031,
|
| 2930 |
+
"loss": 4.7585,
|
| 2931 |
+
"lr": 0.0009690909090909091,
|
| 2932 |
+
"step": 722,
|
| 2933 |
+
"tokens_trained": 0.354878992
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 0.20537550528331325,
|
| 2937 |
+
"grad_norm": 36.11159896850586,
|
| 2938 |
+
"loss": 4.6323,
|
| 2939 |
+
"lr": 0.0009688111888111888,
|
| 2940 |
+
"step": 724,
|
| 2941 |
+
"tokens_trained": 0.355863728
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 0.20594284093326715,
|
| 2945 |
+
"grad_norm": 30.566436767578125,
|
| 2946 |
+
"loss": 4.53,
|
| 2947 |
+
"lr": 0.0009685314685314685,
|
| 2948 |
+
"step": 726,
|
| 2949 |
+
"tokens_trained": 0.356845272
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.20651017658322104,
|
| 2953 |
+
"grad_norm": 59.01853561401367,
|
| 2954 |
+
"loss": 4.5283,
|
| 2955 |
+
"lr": 0.0009682517482517483,
|
| 2956 |
+
"step": 728,
|
| 2957 |
+
"tokens_trained": 0.357826656
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.20707751223317494,
|
| 2961 |
+
"grad_norm": 91.78115844726562,
|
| 2962 |
+
"loss": 4.6149,
|
| 2963 |
+
"lr": 0.000967972027972028,
|
| 2964 |
+
"step": 730,
|
| 2965 |
+
"tokens_trained": 0.358809896
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 0.20764484788312887,
|
| 2969 |
+
"grad_norm": 67.97398376464844,
|
| 2970 |
+
"loss": 4.617,
|
| 2971 |
+
"lr": 0.0009676923076923078,
|
| 2972 |
+
"step": 732,
|
| 2973 |
+
"tokens_trained": 0.359788736
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 0.20821218353308277,
|
| 2977 |
+
"grad_norm": 42.82001876831055,
|
| 2978 |
+
"loss": 4.6134,
|
| 2979 |
+
"lr": 0.0009674125874125874,
|
| 2980 |
+
"step": 734,
|
| 2981 |
+
"tokens_trained": 0.360771744
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.20877951918303667,
|
| 2985 |
+
"grad_norm": 63.52122116088867,
|
| 2986 |
+
"loss": 4.6995,
|
| 2987 |
+
"lr": 0.0009671328671328672,
|
| 2988 |
+
"step": 736,
|
| 2989 |
+
"tokens_trained": 0.361757656
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 0.20934685483299056,
|
| 2993 |
+
"grad_norm": 116.39544677734375,
|
| 2994 |
+
"loss": 4.7153,
|
| 2995 |
+
"lr": 0.0009668531468531469,
|
| 2996 |
+
"step": 738,
|
| 2997 |
+
"tokens_trained": 0.362744008
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 0.20991419048294446,
|
| 3001 |
+
"grad_norm": 40.74269485473633,
|
| 3002 |
+
"loss": 4.7978,
|
| 3003 |
+
"lr": 0.0009665734265734266,
|
| 3004 |
+
"step": 740,
|
| 3005 |
+
"tokens_trained": 0.36372872
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.2104815261328984,
|
| 3009 |
+
"grad_norm": 114.29917907714844,
|
| 3010 |
+
"loss": 5.1683,
|
| 3011 |
+
"lr": 0.0009662937062937063,
|
| 3012 |
+
"step": 742,
|
| 3013 |
+
"tokens_trained": 0.364710536
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.2110488617828523,
|
| 3017 |
+
"grad_norm": 115.83326721191406,
|
| 3018 |
+
"loss": 4.7642,
|
| 3019 |
+
"lr": 0.000966013986013986,
|
| 3020 |
+
"step": 744,
|
| 3021 |
+
"tokens_trained": 0.3656912
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 0.21161619743280619,
|
| 3025 |
+
"grad_norm": 21.708093643188477,
|
| 3026 |
+
"loss": 4.8244,
|
| 3027 |
+
"lr": 0.0009657342657342657,
|
| 3028 |
+
"step": 746,
|
| 3029 |
+
"tokens_trained": 0.36667388
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.21218353308276008,
|
| 3033 |
+
"grad_norm": 182.01918029785156,
|
| 3034 |
+
"loss": 5.6045,
|
| 3035 |
+
"lr": 0.0009654545454545455,
|
| 3036 |
+
"step": 748,
|
| 3037 |
+
"tokens_trained": 0.3676634
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 0.21275086873271398,
|
| 3041 |
+
"grad_norm": 47.119319915771484,
|
| 3042 |
+
"loss": 4.7929,
|
| 3043 |
+
"lr": 0.0009651748251748252,
|
| 3044 |
+
"step": 750,
|
| 3045 |
+
"tokens_trained": 0.368647288
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"epoch": 0.21275086873271398,
|
| 3049 |
+
"eval_loss": 1.2186306715011597,
|
| 3050 |
+
"eval_runtime": 20.9362,
|
| 3051 |
+
"step": 750,
|
| 3052 |
+
"tokens_trained": 0.368647288
|
| 3053 |
+
}
|
| 3054 |
+
],
|
| 3055 |
+
"logging_steps": 2,
|
| 3056 |
+
"max_steps": 7650,
|
| 3057 |
+
"num_input_tokens_seen": 0,
|
| 3058 |
+
"num_train_epochs": 3,
|
| 3059 |
+
"save_steps": 750,
|
| 3060 |
+
"stateful_callbacks": {
|
| 3061 |
+
"TrainerControl": {
|
| 3062 |
+
"args": {
|
| 3063 |
+
"should_epoch_stop": false,
|
| 3064 |
+
"should_evaluate": false,
|
| 3065 |
+
"should_log": false,
|
| 3066 |
+
"should_save": true,
|
| 3067 |
+
"should_training_stop": false
|
| 3068 |
+
},
|
| 3069 |
+
"attributes": {}
|
| 3070 |
+
}
|
| 3071 |
+
},
|
| 3072 |
+
"total_flos": 0.0,
|
| 3073 |
+
"train_batch_size": 8,
|
| 3074 |
+
"trial_name": null,
|
| 3075 |
+
"trial_params": null
|
| 3076 |
+
}
|
checkpoint-750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0df9c39c3704f9c2475fd4a49152e008024525bb74f4d870fbdda9dd1cd6809
|
| 3 |
+
size 5969
|
checkpoint-750/vocab.txt
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
+
[UNK]
|
| 3 |
+
[CLS]
|
| 4 |
+
[SEP]
|
| 5 |
+
[MASK]
|
| 6 |
+
A
|
| 7 |
+
T
|
| 8 |
+
C
|
| 9 |
+
G
|