Upload folder using huggingface_hub
Browse files- checkpoints-v1.0-discrete-conditional/checkpoint-17408/eval_state.json +0 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/model.safetensors +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/optimizer.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/rng_state.pth +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/scaler.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/scheduler.pt +3 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/trainer_state.json +1666 -0
- checkpoints-v1.0-discrete-conditional/checkpoint-17408/training_args.bin +3 -0
checkpoints-v1.0-discrete-conditional/checkpoint-17408/eval_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc31f28b0ea5c62b685ddd596ce5fed49b346a27060e1b6e93f94be5d5f8a97c
|
| 3 |
+
size 24241232
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec4ee78893e9f39e65e86f7843daba68c8bfd45b406f19e30dcc0f66b505ccf
|
| 3 |
+
size 2090059
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0739b3a970faad0d589a62a7a595cf9f866f732667fe74765b74541d0a34d6af
|
| 3 |
+
size 14645
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c53268a9215ff59d3aab5a33f851ef0dc985dada500f7ff05bc12c9cc0cc70
|
| 3 |
+
size 1383
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13634da0e14d59a9a1f04fd9706598ed135e83841713d3c714af88199dc202f8
|
| 3 |
+
size 1465
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/trainer_state.json
ADDED
|
@@ -0,0 +1,1666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.596543209876543,
|
| 6 |
+
"eval_steps": 256,
|
| 7 |
+
"global_step": 17408,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.12641975308641976,
|
| 14 |
+
"grad_norm": 0.49028417468070984,
|
| 15 |
+
"learning_rate": 0.000498046875,
|
| 16 |
+
"loss": 1.2244819402694702,
|
| 17 |
+
"step": 256
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12641975308641976,
|
| 21 |
+
"eval_bleu": 0.023714342494794382,
|
| 22 |
+
"eval_loss": 1.1823350772625063,
|
| 23 |
+
"eval_mse_loss": 1.1823350772625063,
|
| 24 |
+
"step": 256
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12641975308641976,
|
| 28 |
+
"eval_bleu": 0.023714342494794382,
|
| 29 |
+
"eval_loss": 1.1823350772625063,
|
| 30 |
+
"eval_mse_loss": 1.1823350772625063,
|
| 31 |
+
"eval_runtime": 7.3875,
|
| 32 |
+
"eval_samples_per_second": 354.383,
|
| 33 |
+
"eval_steps_per_second": 5.55,
|
| 34 |
+
"step": 256
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.2528395061728395,
|
| 38 |
+
"grad_norm": 0.578209638595581,
|
| 39 |
+
"learning_rate": 0.000998046875,
|
| 40 |
+
"loss": 1.1352403163909912,
|
| 41 |
+
"step": 512
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.2528395061728395,
|
| 45 |
+
"eval_bleu": 0.022467213421973074,
|
| 46 |
+
"eval_loss": 1.0758944168323423,
|
| 47 |
+
"eval_mse_loss": 1.0758944168323423,
|
| 48 |
+
"step": 512
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.2528395061728395,
|
| 52 |
+
"eval_bleu": 0.022467213421973074,
|
| 53 |
+
"eval_loss": 1.0758944168323423,
|
| 54 |
+
"eval_mse_loss": 1.0758944168323423,
|
| 55 |
+
"eval_runtime": 7.512,
|
| 56 |
+
"eval_samples_per_second": 348.51,
|
| 57 |
+
"eval_steps_per_second": 5.458,
|
| 58 |
+
"step": 512
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.37925925925925924,
|
| 62 |
+
"grad_norm": 1.1504969596862793,
|
| 63 |
+
"learning_rate": 0.0009995882304697813,
|
| 64 |
+
"loss": 1.0155020952224731,
|
| 65 |
+
"step": 768
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.37925925925925924,
|
| 69 |
+
"eval_bleu": 0.03303487719486685,
|
| 70 |
+
"eval_loss": 0.9521724465416699,
|
| 71 |
+
"eval_mse_loss": 0.9521724465416699,
|
| 72 |
+
"step": 768
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.37925925925925924,
|
| 76 |
+
"eval_bleu": 0.03303487719486685,
|
| 77 |
+
"eval_loss": 0.9521724465416699,
|
| 78 |
+
"eval_mse_loss": 0.9521724465416699,
|
| 79 |
+
"eval_runtime": 7.3269,
|
| 80 |
+
"eval_samples_per_second": 357.313,
|
| 81 |
+
"eval_steps_per_second": 5.596,
|
| 82 |
+
"step": 768
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.505679012345679,
|
| 86 |
+
"grad_norm": 0.9992234706878662,
|
| 87 |
+
"learning_rate": 0.0009983471408586747,
|
| 88 |
+
"loss": 0.9070967435836792,
|
| 89 |
+
"step": 1024
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.505679012345679,
|
| 93 |
+
"eval_bleu": 0.05283670615976002,
|
| 94 |
+
"eval_loss": 0.8704100134896069,
|
| 95 |
+
"eval_mse_loss": 0.8704100134896069,
|
| 96 |
+
"step": 1024
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.505679012345679,
|
| 100 |
+
"eval_bleu": 0.05283670615976002,
|
| 101 |
+
"eval_loss": 0.8704100134896069,
|
| 102 |
+
"eval_mse_loss": 0.8704100134896069,
|
| 103 |
+
"eval_runtime": 7.9933,
|
| 104 |
+
"eval_samples_per_second": 327.523,
|
| 105 |
+
"eval_steps_per_second": 5.129,
|
| 106 |
+
"step": 1024
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.6320987654320988,
|
| 110 |
+
"grad_norm": 0.931308925151825,
|
| 111 |
+
"learning_rate": 0.000996278785066807,
|
| 112 |
+
"loss": 0.8445582389831543,
|
| 113 |
+
"step": 1280
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.6320987654320988,
|
| 117 |
+
"eval_bleu": 0.062080457666779255,
|
| 118 |
+
"eval_loss": 0.8229870461836094,
|
| 119 |
+
"eval_mse_loss": 0.8229870461836094,
|
| 120 |
+
"step": 1280
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.6320987654320988,
|
| 124 |
+
"eval_bleu": 0.062080457666779255,
|
| 125 |
+
"eval_loss": 0.8229870461836094,
|
| 126 |
+
"eval_mse_loss": 0.8229870461836094,
|
| 127 |
+
"eval_runtime": 8.2397,
|
| 128 |
+
"eval_samples_per_second": 317.731,
|
| 129 |
+
"eval_steps_per_second": 4.976,
|
| 130 |
+
"step": 1280
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.7585185185185185,
|
| 134 |
+
"grad_norm": 1.1758294105529785,
|
| 135 |
+
"learning_rate": 0.0009933865966059944,
|
| 136 |
+
"loss": 0.7974789142608643,
|
| 137 |
+
"step": 1536
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.7585185185185185,
|
| 141 |
+
"eval_bleu": 0.08761458974204005,
|
| 142 |
+
"eval_loss": 0.7755879759788513,
|
| 143 |
+
"eval_mse_loss": 0.7755879759788513,
|
| 144 |
+
"step": 1536
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.7585185185185185,
|
| 148 |
+
"eval_bleu": 0.08761458974204005,
|
| 149 |
+
"eval_loss": 0.7755879759788513,
|
| 150 |
+
"eval_mse_loss": 0.7755879759788513,
|
| 151 |
+
"eval_runtime": 7.2349,
|
| 152 |
+
"eval_samples_per_second": 361.856,
|
| 153 |
+
"eval_steps_per_second": 5.667,
|
| 154 |
+
"step": 1536
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.8849382716049383,
|
| 158 |
+
"grad_norm": 1.6121838092803955,
|
| 159 |
+
"learning_rate": 0.0009896753765666925,
|
| 160 |
+
"loss": 0.7649396657943726,
|
| 161 |
+
"step": 1792
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.8849382716049383,
|
| 165 |
+
"eval_bleu": 0.09849079764244906,
|
| 166 |
+
"eval_loss": 0.7508636625801645,
|
| 167 |
+
"eval_mse_loss": 0.7508636625801645,
|
| 168 |
+
"step": 1792
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.8849382716049383,
|
| 172 |
+
"eval_bleu": 0.09849079764244906,
|
| 173 |
+
"eval_loss": 0.7508636625801645,
|
| 174 |
+
"eval_mse_loss": 0.7508636625801645,
|
| 175 |
+
"eval_runtime": 7.7694,
|
| 176 |
+
"eval_samples_per_second": 336.963,
|
| 177 |
+
"eval_steps_per_second": 5.277,
|
| 178 |
+
"step": 1792
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.011358024691358,
|
| 182 |
+
"grad_norm": 1.966202974319458,
|
| 183 |
+
"learning_rate": 0.0009851512856480936,
|
| 184 |
+
"loss": 0.7395287156105042,
|
| 185 |
+
"step": 2048
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.011358024691358,
|
| 189 |
+
"eval_bleu": 0.11072005270411464,
|
| 190 |
+
"eval_loss": 0.7292228166649981,
|
| 191 |
+
"eval_mse_loss": 0.7292228166649981,
|
| 192 |
+
"step": 2048
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.011358024691358,
|
| 196 |
+
"eval_bleu": 0.11072005270411464,
|
| 197 |
+
"eval_loss": 0.7292228166649981,
|
| 198 |
+
"eval_mse_loss": 0.7292228166649981,
|
| 199 |
+
"eval_runtime": 7.9736,
|
| 200 |
+
"eval_samples_per_second": 328.334,
|
| 201 |
+
"eval_steps_per_second": 5.142,
|
| 202 |
+
"step": 2048
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.1377777777777778,
|
| 206 |
+
"grad_norm": 1.720017433166504,
|
| 207 |
+
"learning_rate": 0.0009798218339312412,
|
| 208 |
+
"loss": 0.7159179449081421,
|
| 209 |
+
"step": 2304
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.1377777777777778,
|
| 213 |
+
"eval_bleu": 0.11064736251702126,
|
| 214 |
+
"eval_loss": 0.7017144793417396,
|
| 215 |
+
"eval_mse_loss": 0.7017144793417396,
|
| 216 |
+
"step": 2304
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.1377777777777778,
|
| 220 |
+
"eval_bleu": 0.11064736251702126,
|
| 221 |
+
"eval_loss": 0.7017144793417396,
|
| 222 |
+
"eval_mse_loss": 0.7017144793417396,
|
| 223 |
+
"eval_runtime": 7.2741,
|
| 224 |
+
"eval_samples_per_second": 359.908,
|
| 225 |
+
"eval_steps_per_second": 5.636,
|
| 226 |
+
"step": 2304
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2641975308641975,
|
| 230 |
+
"grad_norm": 1.0777727365493774,
|
| 231 |
+
"learning_rate": 0.0009736958684121462,
|
| 232 |
+
"loss": 0.6964433789253235,
|
| 233 |
+
"step": 2560
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2641975308641975,
|
| 237 |
+
"eval_bleu": 0.1276517391343738,
|
| 238 |
+
"eval_loss": 0.6854300062830855,
|
| 239 |
+
"eval_mse_loss": 0.6854300062830855,
|
| 240 |
+
"step": 2560
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2641975308641975,
|
| 244 |
+
"eval_bleu": 0.1276517391343738,
|
| 245 |
+
"eval_loss": 0.6854300062830855,
|
| 246 |
+
"eval_mse_loss": 0.6854300062830855,
|
| 247 |
+
"eval_runtime": 7.5038,
|
| 248 |
+
"eval_samples_per_second": 348.888,
|
| 249 |
+
"eval_steps_per_second": 5.464,
|
| 250 |
+
"step": 2560
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.3906172839506172,
|
| 254 |
+
"grad_norm": 2.31036639213562,
|
| 255 |
+
"learning_rate": 0.0009667835583155982,
|
| 256 |
+
"loss": 0.6787664890289307,
|
| 257 |
+
"step": 2816
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.3906172839506172,
|
| 261 |
+
"eval_bleu": 0.14606448546092324,
|
| 262 |
+
"eval_loss": 0.6666799565640892,
|
| 263 |
+
"eval_mse_loss": 0.6666799565640892,
|
| 264 |
+
"step": 2816
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.3906172839506172,
|
| 268 |
+
"eval_bleu": 0.14606448546092324,
|
| 269 |
+
"eval_loss": 0.6666799565640892,
|
| 270 |
+
"eval_mse_loss": 0.6666799565640892,
|
| 271 |
+
"eval_runtime": 8.1414,
|
| 272 |
+
"eval_samples_per_second": 321.565,
|
| 273 |
+
"eval_steps_per_second": 5.036,
|
| 274 |
+
"step": 2816
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5170370370370372,
|
| 278 |
+
"grad_norm": 1.8440918922424316,
|
| 279 |
+
"learning_rate": 0.0009590963782140483,
|
| 280 |
+
"loss": 0.6634169220924377,
|
| 281 |
+
"step": 3072
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.5170370370370372,
|
| 285 |
+
"eval_bleu": 0.14900832500200872,
|
| 286 |
+
"eval_loss": 0.6537455029603911,
|
| 287 |
+
"eval_mse_loss": 0.6537455029603911,
|
| 288 |
+
"step": 3072
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.5170370370370372,
|
| 292 |
+
"eval_bleu": 0.14900832500200872,
|
| 293 |
+
"eval_loss": 0.6537455029603911,
|
| 294 |
+
"eval_mse_loss": 0.6537455029603911,
|
| 295 |
+
"eval_runtime": 8.5409,
|
| 296 |
+
"eval_samples_per_second": 306.525,
|
| 297 |
+
"eval_steps_per_second": 4.8,
|
| 298 |
+
"step": 3072
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.643456790123457,
|
| 302 |
+
"grad_norm": 2.082489013671875,
|
| 303 |
+
"learning_rate": 0.0009506470889795917,
|
| 304 |
+
"loss": 0.6479848027229309,
|
| 305 |
+
"step": 3328
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.643456790123457,
|
| 309 |
+
"eval_bleu": 0.15870707580244742,
|
| 310 |
+
"eval_loss": 0.6412253728727015,
|
| 311 |
+
"eval_mse_loss": 0.6412253728727015,
|
| 312 |
+
"step": 3328
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.643456790123457,
|
| 316 |
+
"eval_bleu": 0.15870707580244742,
|
| 317 |
+
"eval_loss": 0.6412253728727015,
|
| 318 |
+
"eval_mse_loss": 0.6412253728727015,
|
| 319 |
+
"eval_runtime": 7.43,
|
| 320 |
+
"eval_samples_per_second": 352.355,
|
| 321 |
+
"eval_steps_per_second": 5.518,
|
| 322 |
+
"step": 3328
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.7698765432098766,
|
| 326 |
+
"grad_norm": 2.5578348636627197,
|
| 327 |
+
"learning_rate": 0.0009414497166006652,
|
| 328 |
+
"loss": 0.6374112963676453,
|
| 329 |
+
"step": 3584
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.7698765432098766,
|
| 333 |
+
"eval_bleu": 0.16517790474378305,
|
| 334 |
+
"eval_loss": 0.6340285481476202,
|
| 335 |
+
"eval_mse_loss": 0.6340285481476202,
|
| 336 |
+
"step": 3584
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.7698765432098766,
|
| 340 |
+
"eval_bleu": 0.16517790474378305,
|
| 341 |
+
"eval_loss": 0.6340285481476202,
|
| 342 |
+
"eval_mse_loss": 0.6340285481476202,
|
| 343 |
+
"eval_runtime": 7.8092,
|
| 344 |
+
"eval_samples_per_second": 335.246,
|
| 345 |
+
"eval_steps_per_second": 5.25,
|
| 346 |
+
"step": 3584
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.8962962962962964,
|
| 350 |
+
"grad_norm": 1.9383974075317383,
|
| 351 |
+
"learning_rate": 0.0009315195288986269,
|
| 352 |
+
"loss": 0.623887836933136,
|
| 353 |
+
"step": 3840
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.8962962962962964,
|
| 357 |
+
"eval_bleu": 0.17847564897785617,
|
| 358 |
+
"eval_loss": 0.6204298661976326,
|
| 359 |
+
"eval_mse_loss": 0.6204298661976326,
|
| 360 |
+
"step": 3840
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.8962962962962964,
|
| 364 |
+
"eval_bleu": 0.17847564897785617,
|
| 365 |
+
"eval_loss": 0.6204298661976326,
|
| 366 |
+
"eval_mse_loss": 0.6204298661976326,
|
| 367 |
+
"eval_runtime": 7.8808,
|
| 368 |
+
"eval_samples_per_second": 332.2,
|
| 369 |
+
"eval_steps_per_second": 5.203,
|
| 370 |
+
"step": 3840
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.022716049382716,
|
| 374 |
+
"grad_norm": 2.074370861053467,
|
| 375 |
+
"learning_rate": 0.0009208730101828687,
|
| 376 |
+
"loss": 0.612588107585907,
|
| 377 |
+
"step": 4096
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.022716049382716,
|
| 381 |
+
"eval_bleu": 0.20019494813992078,
|
| 382 |
+
"eval_loss": 0.6014744639396667,
|
| 383 |
+
"eval_mse_loss": 0.6014744639396667,
|
| 384 |
+
"step": 4096
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.022716049382716,
|
| 388 |
+
"eval_bleu": 0.20019494813992078,
|
| 389 |
+
"eval_loss": 0.6014744639396667,
|
| 390 |
+
"eval_mse_loss": 0.6014744639396667,
|
| 391 |
+
"eval_runtime": 8.3023,
|
| 392 |
+
"eval_samples_per_second": 315.333,
|
| 393 |
+
"eval_steps_per_second": 4.938,
|
| 394 |
+
"step": 4096
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.149135802469136,
|
| 398 |
+
"grad_norm": 2.1671674251556396,
|
| 399 |
+
"learning_rate": 0.0009095278338865343,
|
| 400 |
+
"loss": 0.5997830629348755,
|
| 401 |
+
"step": 4352
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.149135802469136,
|
| 405 |
+
"eval_bleu": 0.1987893921535938,
|
| 406 |
+
"eval_loss": 0.5986893453249117,
|
| 407 |
+
"eval_mse_loss": 0.5986893453249117,
|
| 408 |
+
"step": 4352
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.149135802469136,
|
| 412 |
+
"eval_bleu": 0.1987893921535938,
|
| 413 |
+
"eval_loss": 0.5986893453249117,
|
| 414 |
+
"eval_mse_loss": 0.5986893453249117,
|
| 415 |
+
"eval_runtime": 7.4027,
|
| 416 |
+
"eval_samples_per_second": 353.653,
|
| 417 |
+
"eval_steps_per_second": 5.538,
|
| 418 |
+
"step": 4352
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.2755555555555556,
|
| 422 |
+
"grad_norm": 3.125169038772583,
|
| 423 |
+
"learning_rate": 0.0008975028332282684,
|
| 424 |
+
"loss": 0.5991740822792053,
|
| 425 |
+
"step": 4608
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.2755555555555556,
|
| 429 |
+
"eval_bleu": 0.20658330468877353,
|
| 430 |
+
"eval_loss": 0.6155260525098661,
|
| 431 |
+
"eval_mse_loss": 0.6155260525098661,
|
| 432 |
+
"step": 4608
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.2755555555555556,
|
| 436 |
+
"eval_bleu": 0.20658330468877353,
|
| 437 |
+
"eval_loss": 0.6155260525098661,
|
| 438 |
+
"eval_mse_loss": 0.6155260525098661,
|
| 439 |
+
"eval_runtime": 7.4818,
|
| 440 |
+
"eval_samples_per_second": 349.915,
|
| 441 |
+
"eval_steps_per_second": 5.48,
|
| 442 |
+
"step": 4608
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.4019753086419753,
|
| 446 |
+
"grad_norm": 4.6324992179870605,
|
| 447 |
+
"learning_rate": 0.0008848179699486985,
|
| 448 |
+
"loss": 0.6436169147491455,
|
| 449 |
+
"step": 4864
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.4019753086419753,
|
| 453 |
+
"eval_bleu": 0.19786110402686427,
|
| 454 |
+
"eval_loss": 0.6434223041301821,
|
| 455 |
+
"eval_mse_loss": 0.6434223041301821,
|
| 456 |
+
"step": 4864
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.4019753086419753,
|
| 460 |
+
"eval_bleu": 0.19786110402686427,
|
| 461 |
+
"eval_loss": 0.6434223041301821,
|
| 462 |
+
"eval_mse_loss": 0.6434223041301821,
|
| 463 |
+
"eval_runtime": 8.06,
|
| 464 |
+
"eval_samples_per_second": 324.813,
|
| 465 |
+
"eval_steps_per_second": 5.087,
|
| 466 |
+
"step": 4864
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.528395061728395,
|
| 470 |
+
"grad_norm": 4.647606372833252,
|
| 471 |
+
"learning_rate": 0.0008714943011735476,
|
| 472 |
+
"loss": 0.6646981239318848,
|
| 473 |
+
"step": 5120
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.528395061728395,
|
| 477 |
+
"eval_bleu": 0.17652369495305426,
|
| 478 |
+
"eval_loss": 0.6581660363732315,
|
| 479 |
+
"eval_mse_loss": 0.6581660363732315,
|
| 480 |
+
"step": 5120
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.528395061728395,
|
| 484 |
+
"eval_bleu": 0.17652369495305426,
|
| 485 |
+
"eval_loss": 0.6581660363732315,
|
| 486 |
+
"eval_mse_loss": 0.6581660363732315,
|
| 487 |
+
"eval_runtime": 8.4642,
|
| 488 |
+
"eval_samples_per_second": 309.304,
|
| 489 |
+
"eval_steps_per_second": 4.844,
|
| 490 |
+
"step": 5120
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.6548148148148147,
|
| 494 |
+
"grad_norm": 4.655036926269531,
|
| 495 |
+
"learning_rate": 0.000857553944458386,
|
| 496 |
+
"loss": 0.670133650302887,
|
| 497 |
+
"step": 5376
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.6548148148148147,
|
| 501 |
+
"eval_bleu": 0.16665801459747773,
|
| 502 |
+
"eval_loss": 0.6649525950594646,
|
| 503 |
+
"eval_mse_loss": 0.6649525950594646,
|
| 504 |
+
"step": 5376
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.6548148148148147,
|
| 508 |
+
"eval_bleu": 0.16665801459747773,
|
| 509 |
+
"eval_loss": 0.6649525950594646,
|
| 510 |
+
"eval_mse_loss": 0.6649525950594646,
|
| 511 |
+
"eval_runtime": 7.3082,
|
| 512 |
+
"eval_samples_per_second": 358.23,
|
| 513 |
+
"eval_steps_per_second": 5.61,
|
| 514 |
+
"step": 5376
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.7812345679012345,
|
| 518 |
+
"grad_norm": 6.748809814453125,
|
| 519 |
+
"learning_rate": 0.000843020041073049,
|
| 520 |
+
"loss": 0.6625139117240906,
|
| 521 |
+
"step": 5632
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.7812345679012345,
|
| 525 |
+
"eval_bleu": 0.173997037607852,
|
| 526 |
+
"eval_loss": 0.6807852968937014,
|
| 527 |
+
"eval_mse_loss": 0.6807852968937014,
|
| 528 |
+
"step": 5632
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.7812345679012345,
|
| 532 |
+
"eval_bleu": 0.173997037607852,
|
| 533 |
+
"eval_loss": 0.6807852968937014,
|
| 534 |
+
"eval_mse_loss": 0.6807852968937014,
|
| 535 |
+
"eval_runtime": 7.5532,
|
| 536 |
+
"eval_samples_per_second": 346.607,
|
| 537 |
+
"eval_steps_per_second": 5.428,
|
| 538 |
+
"step": 5632
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.907654320987654,
|
| 542 |
+
"grad_norm": 4.406154632568359,
|
| 543 |
+
"learning_rate": 0.0008279167175866678,
|
| 544 |
+
"loss": 0.6519719958305359,
|
| 545 |
+
"step": 5888
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.907654320987654,
|
| 549 |
+
"eval_bleu": 0.19570266564584513,
|
| 550 |
+
"eval_loss": 0.6394063074414323,
|
| 551 |
+
"eval_mse_loss": 0.6394063074414323,
|
| 552 |
+
"step": 5888
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.907654320987654,
|
| 556 |
+
"eval_bleu": 0.19570266564584513,
|
| 557 |
+
"eval_loss": 0.6394063074414323,
|
| 558 |
+
"eval_mse_loss": 0.6394063074414323,
|
| 559 |
+
"eval_runtime": 7.9229,
|
| 560 |
+
"eval_samples_per_second": 330.434,
|
| 561 |
+
"eval_steps_per_second": 5.175,
|
| 562 |
+
"step": 5888
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.034074074074074,
|
| 566 |
+
"grad_norm": 4.702131271362305,
|
| 567 |
+
"learning_rate": 0.0008122690458170833,
|
| 568 |
+
"loss": 0.6394258737564087,
|
| 569 |
+
"step": 6144
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.034074074074074,
|
| 573 |
+
"eval_bleu": 0.18025210346558498,
|
| 574 |
+
"eval_loss": 0.6386287488588472,
|
| 575 |
+
"eval_mse_loss": 0.6386287488588472,
|
| 576 |
+
"step": 6144
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.034074074074074,
|
| 580 |
+
"eval_bleu": 0.18025210346558498,
|
| 581 |
+
"eval_loss": 0.6386287488588472,
|
| 582 |
+
"eval_mse_loss": 0.6386287488588472,
|
| 583 |
+
"eval_runtime": 8.212,
|
| 584 |
+
"eval_samples_per_second": 318.804,
|
| 585 |
+
"eval_steps_per_second": 4.993,
|
| 586 |
+
"step": 6144
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 3.1604938271604937,
|
| 590 |
+
"grad_norm": 3.3306374549865723,
|
| 591 |
+
"learning_rate": 0.0007961030012111305,
|
| 592 |
+
"loss": 0.6313198208808899,
|
| 593 |
+
"step": 6400
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.1604938271604937,
|
| 597 |
+
"eval_bleu": 0.19600803362588348,
|
| 598 |
+
"eval_loss": 0.6227354814366597,
|
| 599 |
+
"eval_mse_loss": 0.6227354814366597,
|
| 600 |
+
"step": 6400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.1604938271604937,
|
| 604 |
+
"eval_bleu": 0.19600803362588348,
|
| 605 |
+
"eval_loss": 0.6227354814366597,
|
| 606 |
+
"eval_mse_loss": 0.6227354814366597,
|
| 607 |
+
"eval_runtime": 7.9462,
|
| 608 |
+
"eval_samples_per_second": 329.467,
|
| 609 |
+
"eval_steps_per_second": 5.16,
|
| 610 |
+
"step": 6400
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.286913580246914,
|
| 614 |
+
"grad_norm": 4.519600868225098,
|
| 615 |
+
"learning_rate": 0.0007794454197248784,
|
| 616 |
+
"loss": 0.6270281672477722,
|
| 617 |
+
"step": 6656
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.286913580246914,
|
| 621 |
+
"eval_bleu": 0.21406015637359221,
|
| 622 |
+
"eval_loss": 0.6298785456796971,
|
| 623 |
+
"eval_mse_loss": 0.6298785456796971,
|
| 624 |
+
"step": 6656
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.286913580246914,
|
| 628 |
+
"eval_bleu": 0.21406015637359221,
|
| 629 |
+
"eval_loss": 0.6298785456796971,
|
| 630 |
+
"eval_mse_loss": 0.6298785456796971,
|
| 631 |
+
"eval_runtime": 7.1729,
|
| 632 |
+
"eval_samples_per_second": 364.985,
|
| 633 |
+
"eval_steps_per_second": 5.716,
|
| 634 |
+
"step": 6656
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.413333333333333,
|
| 638 |
+
"grad_norm": 4.557300090789795,
|
| 639 |
+
"learning_rate": 0.0007623239532754083,
|
| 640 |
+
"loss": 0.6133501529693604,
|
| 641 |
+
"step": 6912
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.413333333333333,
|
| 645 |
+
"eval_bleu": 0.21008851882230098,
|
| 646 |
+
"eval_loss": 0.6231076019566234,
|
| 647 |
+
"eval_mse_loss": 0.6231076019566234,
|
| 648 |
+
"step": 6912
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.413333333333333,
|
| 652 |
+
"eval_bleu": 0.21008851882230098,
|
| 653 |
+
"eval_loss": 0.6231076019566234,
|
| 654 |
+
"eval_mse_loss": 0.6231076019566234,
|
| 655 |
+
"eval_runtime": 7.9356,
|
| 656 |
+
"eval_samples_per_second": 329.904,
|
| 657 |
+
"eval_steps_per_second": 5.167,
|
| 658 |
+
"step": 6912
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 3.5397530864197533,
|
| 662 |
+
"grad_norm": 4.322099208831787,
|
| 663 |
+
"learning_rate": 0.0007447670238380815,
|
| 664 |
+
"loss": 0.6112697720527649,
|
| 665 |
+
"step": 7168
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.5397530864197533,
|
| 669 |
+
"eval_bleu": 0.2060799623946906,
|
| 670 |
+
"eval_loss": 0.6111486045325675,
|
| 671 |
+
"eval_mse_loss": 0.6111486045325675,
|
| 672 |
+
"step": 7168
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.5397530864197533,
|
| 676 |
+
"eval_bleu": 0.2060799623946906,
|
| 677 |
+
"eval_loss": 0.6111486045325675,
|
| 678 |
+
"eval_mse_loss": 0.6111486045325675,
|
| 679 |
+
"eval_runtime": 8.1866,
|
| 680 |
+
"eval_samples_per_second": 319.793,
|
| 681 |
+
"eval_steps_per_second": 5.008,
|
| 682 |
+
"step": 7168
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.6661728395061726,
|
| 686 |
+
"grad_norm": 4.115531921386719,
|
| 687 |
+
"learning_rate": 0.0007268037762654929,
|
| 688 |
+
"loss": 0.6039376854896545,
|
| 689 |
+
"step": 7424
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.6661728395061726,
|
| 693 |
+
"eval_bleu": 0.21503632161601938,
|
| 694 |
+
"eval_loss": 0.6128283637325939,
|
| 695 |
+
"eval_mse_loss": 0.6128283637325939,
|
| 696 |
+
"step": 7424
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.6661728395061726,
|
| 700 |
+
"eval_bleu": 0.21503632161601938,
|
| 701 |
+
"eval_loss": 0.6128283637325939,
|
| 702 |
+
"eval_mse_loss": 0.6128283637325939,
|
| 703 |
+
"eval_runtime": 8.2856,
|
| 704 |
+
"eval_samples_per_second": 315.97,
|
| 705 |
+
"eval_steps_per_second": 4.948,
|
| 706 |
+
"step": 7424
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.7925925925925927,
|
| 710 |
+
"grad_norm": 4.654777526855469,
|
| 711 |
+
"learning_rate": 0.0007084640299064357,
|
| 712 |
+
"loss": 0.5996431708335876,
|
| 713 |
+
"step": 7680
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.7925925925925927,
|
| 717 |
+
"eval_bleu": 0.22869408936536856,
|
| 718 |
+
"eval_loss": 0.5915597095722105,
|
| 719 |
+
"eval_mse_loss": 0.5915597095722105,
|
| 720 |
+
"step": 7680
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.7925925925925927,
|
| 724 |
+
"eval_bleu": 0.22869408936536856,
|
| 725 |
+
"eval_loss": 0.5915597095722105,
|
| 726 |
+
"eval_mse_loss": 0.5915597095722105,
|
| 727 |
+
"eval_runtime": 8.2255,
|
| 728 |
+
"eval_samples_per_second": 318.278,
|
| 729 |
+
"eval_steps_per_second": 4.984,
|
| 730 |
+
"step": 7680
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.9190123456790125,
|
| 734 |
+
"grad_norm": 3.9882354736328125,
|
| 735 |
+
"learning_rate": 0.0006897782291051889,
|
| 736 |
+
"loss": 0.5931000709533691,
|
| 737 |
+
"step": 7936
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 3.9190123456790125,
|
| 741 |
+
"eval_bleu": 0.2349496066220062,
|
| 742 |
+
"eval_loss": 0.5926558040991062,
|
| 743 |
+
"eval_mse_loss": 0.5926558040991062,
|
| 744 |
+
"step": 7936
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.9190123456790125,
|
| 748 |
+
"eval_bleu": 0.2349496066220062,
|
| 749 |
+
"eval_loss": 0.5926558040991062,
|
| 750 |
+
"eval_mse_loss": 0.5926558040991062,
|
| 751 |
+
"eval_runtime": 8.1758,
|
| 752 |
+
"eval_samples_per_second": 320.212,
|
| 753 |
+
"eval_steps_per_second": 5.015,
|
| 754 |
+
"step": 7936
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.045432098765432,
|
| 758 |
+
"grad_norm": 4.266123294830322,
|
| 759 |
+
"learning_rate": 0.000670777392663298,
|
| 760 |
+
"loss": 0.5860158205032349,
|
| 761 |
+
"step": 8192
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.045432098765432,
|
| 765 |
+
"eval_bleu": 0.25634671575676854,
|
| 766 |
+
"eval_loss": 0.5731269004868298,
|
| 767 |
+
"eval_mse_loss": 0.5731269004868298,
|
| 768 |
+
"step": 8192
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.045432098765432,
|
| 772 |
+
"eval_bleu": 0.25634671575676854,
|
| 773 |
+
"eval_loss": 0.5731269004868298,
|
| 774 |
+
"eval_mse_loss": 0.5731269004868298,
|
| 775 |
+
"eval_runtime": 7.4662,
|
| 776 |
+
"eval_samples_per_second": 350.648,
|
| 777 |
+
"eval_steps_per_second": 5.491,
|
| 778 |
+
"step": 8192
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.1718518518518515,
|
| 782 |
+
"grad_norm": 5.411952018737793,
|
| 783 |
+
"learning_rate": 0.0006514930623477486,
|
| 784 |
+
"loss": 0.5818273425102234,
|
| 785 |
+
"step": 8448
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 4.1718518518518515,
|
| 789 |
+
"eval_bleu": 0.2520441554433453,
|
| 790 |
+
"eval_loss": 0.5782059794519006,
|
| 791 |
+
"eval_mse_loss": 0.5782059794519006,
|
| 792 |
+
"step": 8448
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 4.1718518518518515,
|
| 796 |
+
"eval_bleu": 0.2520441554433453,
|
| 797 |
+
"eval_loss": 0.5782059794519006,
|
| 798 |
+
"eval_mse_loss": 0.5782059794519006,
|
| 799 |
+
"eval_runtime": 7.4057,
|
| 800 |
+
"eval_samples_per_second": 353.512,
|
| 801 |
+
"eval_steps_per_second": 5.536,
|
| 802 |
+
"step": 8448
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.298271604938272,
|
| 806 |
+
"grad_norm": 3.5435891151428223,
|
| 807 |
+
"learning_rate": 0.0006319572505310022,
|
| 808 |
+
"loss": 0.5773241519927979,
|
| 809 |
+
"step": 8704
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.298271604938272,
|
| 813 |
+
"eval_bleu": 0.2534190472706376,
|
| 814 |
+
"eval_loss": 0.5589999033183586,
|
| 815 |
+
"eval_mse_loss": 0.5589999033183586,
|
| 816 |
+
"step": 8704
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 4.298271604938272,
|
| 820 |
+
"eval_bleu": 0.2534190472706376,
|
| 821 |
+
"eval_loss": 0.5589999033183586,
|
| 822 |
+
"eval_mse_loss": 0.5589999033183586,
|
| 823 |
+
"eval_runtime": 7.7623,
|
| 824 |
+
"eval_samples_per_second": 337.273,
|
| 825 |
+
"eval_steps_per_second": 5.282,
|
| 826 |
+
"step": 8704
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.424691358024692,
|
| 830 |
+
"grad_norm": 3.660297155380249,
|
| 831 |
+
"learning_rate": 0.000612202387049823,
|
| 832 |
+
"loss": 0.5752817988395691,
|
| 833 |
+
"step": 8960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 4.424691358024692,
|
| 837 |
+
"eval_bleu": 0.25405581690850026,
|
| 838 |
+
"eval_loss": 0.5717670982930718,
|
| 839 |
+
"eval_mse_loss": 0.5717670982930718,
|
| 840 |
+
"step": 8960
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 4.424691358024692,
|
| 844 |
+
"eval_bleu": 0.25405581690850026,
|
| 845 |
+
"eval_loss": 0.5717670982930718,
|
| 846 |
+
"eval_mse_loss": 0.5717670982930718,
|
| 847 |
+
"eval_runtime": 8.0671,
|
| 848 |
+
"eval_samples_per_second": 324.527,
|
| 849 |
+
"eval_steps_per_second": 5.082,
|
| 850 |
+
"step": 8960
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.551111111111111,
|
| 854 |
+
"grad_norm": 4.61627197265625,
|
| 855 |
+
"learning_rate": 0.0005922612653711009,
|
| 856 |
+
"loss": 0.5677421689033508,
|
| 857 |
+
"step": 9216
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.551111111111111,
|
| 861 |
+
"eval_bleu": 0.2616680879763428,
|
| 862 |
+
"eval_loss": 0.5714971786592065,
|
| 863 |
+
"eval_mse_loss": 0.5714971786592065,
|
| 864 |
+
"step": 9216
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.551111111111111,
|
| 868 |
+
"eval_bleu": 0.2616680879763428,
|
| 869 |
+
"eval_loss": 0.5714971786592065,
|
| 870 |
+
"eval_mse_loss": 0.5714971786592065,
|
| 871 |
+
"eval_runtime": 8.2747,
|
| 872 |
+
"eval_samples_per_second": 316.384,
|
| 873 |
+
"eval_steps_per_second": 4.955,
|
| 874 |
+
"step": 9216
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 4.67753086419753,
|
| 878 |
+
"grad_norm": 4.289632797241211,
|
| 879 |
+
"learning_rate": 0.0005721669881540442,
|
| 880 |
+
"loss": 0.5655048489570618,
|
| 881 |
+
"step": 9472
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 4.67753086419753,
|
| 885 |
+
"eval_bleu": 0.27326453853008387,
|
| 886 |
+
"eval_loss": 0.5655288245619797,
|
| 887 |
+
"eval_mse_loss": 0.5655288245619797,
|
| 888 |
+
"step": 9472
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 4.67753086419753,
|
| 892 |
+
"eval_bleu": 0.27326453853008387,
|
| 893 |
+
"eval_loss": 0.5655288245619797,
|
| 894 |
+
"eval_mse_loss": 0.5655288245619797,
|
| 895 |
+
"eval_runtime": 8.1079,
|
| 896 |
+
"eval_samples_per_second": 322.895,
|
| 897 |
+
"eval_steps_per_second": 5.057,
|
| 898 |
+
"step": 9472
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.803950617283951,
|
| 902 |
+
"grad_norm": 4.95919132232666,
|
| 903 |
+
"learning_rate": 0.0005519529122991056,
|
| 904 |
+
"loss": 0.5713540315628052,
|
| 905 |
+
"step": 9728
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.803950617283951,
|
| 909 |
+
"eval_bleu": 0.2627683773991363,
|
| 910 |
+
"eval_loss": 0.5628622283295888,
|
| 911 |
+
"eval_mse_loss": 0.5628622283295888,
|
| 912 |
+
"step": 9728
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 4.803950617283951,
|
| 916 |
+
"eval_bleu": 0.2627683773991363,
|
| 917 |
+
"eval_loss": 0.5628622283295888,
|
| 918 |
+
"eval_mse_loss": 0.5628622283295888,
|
| 919 |
+
"eval_runtime": 7.9584,
|
| 920 |
+
"eval_samples_per_second": 328.962,
|
| 921 |
+
"eval_steps_per_second": 5.152,
|
| 922 |
+
"step": 9728
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 4.930370370370371,
|
| 926 |
+
"grad_norm": 6.370813369750977,
|
| 927 |
+
"learning_rate": 0.0005316525935748631,
|
| 928 |
+
"loss": 0.5834425687789917,
|
| 929 |
+
"step": 9984
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.930370370370371,
|
| 933 |
+
"eval_bleu": 0.26641828019601,
|
| 934 |
+
"eval_loss": 0.5816229349229394,
|
| 935 |
+
"eval_mse_loss": 0.5816229349229394,
|
| 936 |
+
"step": 9984
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 4.930370370370371,
|
| 940 |
+
"eval_bleu": 0.26641828019601,
|
| 941 |
+
"eval_loss": 0.5816229349229394,
|
| 942 |
+
"eval_mse_loss": 0.5816229349229394,
|
| 943 |
+
"eval_runtime": 7.1012,
|
| 944 |
+
"eval_samples_per_second": 368.672,
|
| 945 |
+
"eval_steps_per_second": 5.774,
|
| 946 |
+
"step": 9984
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 5.05679012345679,
|
| 950 |
+
"grad_norm": 6.872233867645264,
|
| 951 |
+
"learning_rate": 0.0005112997309147753,
|
| 952 |
+
"loss": 0.5829513669013977,
|
| 953 |
+
"step": 10240
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 5.05679012345679,
|
| 957 |
+
"eval_bleu": 0.2556546592309415,
|
| 958 |
+
"eval_loss": 0.5965675159198481,
|
| 959 |
+
"eval_mse_loss": 0.5965675159198481,
|
| 960 |
+
"step": 10240
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.05679012345679,
|
| 964 |
+
"eval_bleu": 0.2556546592309415,
|
| 965 |
+
"eval_loss": 0.5965675159198481,
|
| 966 |
+
"eval_mse_loss": 0.5965675159198481,
|
| 967 |
+
"eval_runtime": 7.6184,
|
| 968 |
+
"eval_samples_per_second": 343.643,
|
| 969 |
+
"eval_steps_per_second": 5.382,
|
| 970 |
+
"step": 10240
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 5.18320987654321,
|
| 974 |
+
"grad_norm": 6.554806232452393,
|
| 975 |
+
"learning_rate": 0.0004909281104762817,
|
| 976 |
+
"loss": 0.5979596376419067,
|
| 977 |
+
"step": 10496
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.18320987654321,
|
| 981 |
+
"eval_bleu": 0.24496216459175849,
|
| 982 |
+
"eval_loss": 0.5925210903330547,
|
| 983 |
+
"eval_mse_loss": 0.5925210903330547,
|
| 984 |
+
"step": 10496
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.18320987654321,
|
| 988 |
+
"eval_bleu": 0.24496216459175849,
|
| 989 |
+
"eval_loss": 0.5925210903330547,
|
| 990 |
+
"eval_mse_loss": 0.5925210903330547,
|
| 991 |
+
"eval_runtime": 8.1186,
|
| 992 |
+
"eval_samples_per_second": 322.468,
|
| 993 |
+
"eval_steps_per_second": 5.05,
|
| 994 |
+
"step": 10496
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 5.3096296296296295,
|
| 998 |
+
"grad_norm": 8.099956512451172,
|
| 999 |
+
"learning_rate": 0.0004705715495551068,
|
| 1000 |
+
"loss": 0.5981637835502625,
|
| 1001 |
+
"step": 10752
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.3096296296296295,
|
| 1005 |
+
"eval_bleu": 0.24892557597714382,
|
| 1006 |
+
"eval_loss": 0.6025734194895116,
|
| 1007 |
+
"eval_mse_loss": 0.6025734194895116,
|
| 1008 |
+
"step": 10752
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.3096296296296295,
|
| 1012 |
+
"eval_bleu": 0.24892557597714382,
|
| 1013 |
+
"eval_loss": 0.6025734194895116,
|
| 1014 |
+
"eval_mse_loss": 0.6025734194895116,
|
| 1015 |
+
"eval_runtime": 8.3839,
|
| 1016 |
+
"eval_samples_per_second": 312.265,
|
| 1017 |
+
"eval_steps_per_second": 4.89,
|
| 1018 |
+
"step": 10752
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 5.43604938271605,
|
| 1022 |
+
"grad_norm": 6.063875675201416,
|
| 1023 |
+
"learning_rate": 0.00045026384044787715,
|
| 1024 |
+
"loss": 0.600553572177887,
|
| 1025 |
+
"step": 11008
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 5.43604938271605,
|
| 1029 |
+
"eval_bleu": 0.2584749312819124,
|
| 1030 |
+
"eval_loss": 0.5978762725504433,
|
| 1031 |
+
"eval_mse_loss": 0.5978762725504433,
|
| 1032 |
+
"step": 11008
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.43604938271605,
|
| 1036 |
+
"eval_bleu": 0.2584749312819124,
|
| 1037 |
+
"eval_loss": 0.5978762725504433,
|
| 1038 |
+
"eval_mse_loss": 0.5978762725504433,
|
| 1039 |
+
"eval_runtime": 8.4473,
|
| 1040 |
+
"eval_samples_per_second": 309.921,
|
| 1041 |
+
"eval_steps_per_second": 4.854,
|
| 1042 |
+
"step": 11008
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 5.562469135802469,
|
| 1046 |
+
"grad_norm": 6.819189071655273,
|
| 1047 |
+
"learning_rate": 0.0004300386943562342,
|
| 1048 |
+
"loss": 0.6050165891647339,
|
| 1049 |
+
"step": 11264
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.562469135802469,
|
| 1053 |
+
"eval_bleu": 0.23936172268263006,
|
| 1054 |
+
"eval_loss": 0.6197842156014791,
|
| 1055 |
+
"eval_mse_loss": 0.6197842156014791,
|
| 1056 |
+
"step": 11264
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.562469135802469,
|
| 1060 |
+
"eval_bleu": 0.23936172268263006,
|
| 1061 |
+
"eval_loss": 0.6197842156014791,
|
| 1062 |
+
"eval_mse_loss": 0.6197842156014791,
|
| 1063 |
+
"eval_runtime": 7.275,
|
| 1064 |
+
"eval_samples_per_second": 359.864,
|
| 1065 |
+
"eval_steps_per_second": 5.636,
|
| 1066 |
+
"step": 11264
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 5.688888888888889,
|
| 1070 |
+
"grad_norm": 8.074504852294922,
|
| 1071 |
+
"learning_rate": 0.0004099296854255696,
|
| 1072 |
+
"loss": 0.6032764315605164,
|
| 1073 |
+
"step": 11520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 5.688888888888889,
|
| 1077 |
+
"eval_bleu": 0.2563038856939558,
|
| 1078 |
+
"eval_loss": 0.5922774854229718,
|
| 1079 |
+
"eval_mse_loss": 0.5922774854229718,
|
| 1080 |
+
"step": 11520
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 5.688888888888889,
|
| 1084 |
+
"eval_bleu": 0.2563038856939558,
|
| 1085 |
+
"eval_loss": 0.5922774854229718,
|
| 1086 |
+
"eval_mse_loss": 0.5922774854229718,
|
| 1087 |
+
"eval_runtime": 7.7562,
|
| 1088 |
+
"eval_samples_per_second": 337.535,
|
| 1089 |
+
"eval_steps_per_second": 5.286,
|
| 1090 |
+
"step": 11520
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 5.815308641975308,
|
| 1094 |
+
"grad_norm": 7.949519157409668,
|
| 1095 |
+
"learning_rate": 0.00038997019501127406,
|
| 1096 |
+
"loss": 0.5983560681343079,
|
| 1097 |
+
"step": 11776
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 5.815308641975308,
|
| 1101 |
+
"eval_bleu": 0.25476493381302434,
|
| 1102 |
+
"eval_loss": 0.6024370585999838,
|
| 1103 |
+
"eval_mse_loss": 0.6024370585999838,
|
| 1104 |
+
"step": 11776
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.815308641975308,
|
| 1108 |
+
"eval_bleu": 0.25476493381302434,
|
| 1109 |
+
"eval_loss": 0.6024370585999838,
|
| 1110 |
+
"eval_mse_loss": 0.6024370585999838,
|
| 1111 |
+
"eval_runtime": 7.9866,
|
| 1112 |
+
"eval_samples_per_second": 327.799,
|
| 1113 |
+
"eval_steps_per_second": 5.134,
|
| 1114 |
+
"step": 11776
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 5.941728395061729,
|
| 1118 |
+
"grad_norm": 7.21051025390625,
|
| 1119 |
+
"learning_rate": 0.00037019335626502263,
|
| 1120 |
+
"loss": 0.5926205515861511,
|
| 1121 |
+
"step": 12032
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 5.941728395061729,
|
| 1125 |
+
"eval_bleu": 0.2579463063130564,
|
| 1126 |
+
"eval_loss": 0.5958762241572868,
|
| 1127 |
+
"eval_mse_loss": 0.5958762241572868,
|
| 1128 |
+
"step": 12032
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 5.941728395061729,
|
| 1132 |
+
"eval_bleu": 0.2579463063130564,
|
| 1133 |
+
"eval_loss": 0.5958762241572868,
|
| 1134 |
+
"eval_mse_loss": 0.5958762241572868,
|
| 1135 |
+
"eval_runtime": 8.1465,
|
| 1136 |
+
"eval_samples_per_second": 321.364,
|
| 1137 |
+
"eval_steps_per_second": 5.033,
|
| 1138 |
+
"step": 12032
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 6.068148148148148,
|
| 1142 |
+
"grad_norm": 6.125677108764648,
|
| 1143 |
+
"learning_rate": 0.0003506319991330833,
|
| 1144 |
+
"loss": 0.5896713137626648,
|
| 1145 |
+
"step": 12288
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 6.068148148148148,
|
| 1149 |
+
"eval_bleu": 0.2633499094850468,
|
| 1150 |
+
"eval_loss": 0.5901360758920995,
|
| 1151 |
+
"eval_mse_loss": 0.5901360758920995,
|
| 1152 |
+
"step": 12288
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 6.068148148148148,
|
| 1156 |
+
"eval_bleu": 0.2633499094850468,
|
| 1157 |
+
"eval_loss": 0.5901360758920995,
|
| 1158 |
+
"eval_mse_loss": 0.5901360758920995,
|
| 1159 |
+
"eval_runtime": 7.4076,
|
| 1160 |
+
"eval_samples_per_second": 353.421,
|
| 1161 |
+
"eval_steps_per_second": 5.535,
|
| 1162 |
+
"step": 12288
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 6.194567901234568,
|
| 1166 |
+
"grad_norm": 8.257464408874512,
|
| 1167 |
+
"learning_rate": 0.00033131859585795183,
|
| 1168 |
+
"loss": 0.5833750367164612,
|
| 1169 |
+
"step": 12544
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 6.194567901234568,
|
| 1173 |
+
"eval_bleu": 0.2632131293368136,
|
| 1174 |
+
"eval_loss": 0.5901335754045626,
|
| 1175 |
+
"eval_mse_loss": 0.5901335754045626,
|
| 1176 |
+
"step": 12544
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 6.194567901234568,
|
| 1180 |
+
"eval_bleu": 0.2632131293368136,
|
| 1181 |
+
"eval_loss": 0.5901335754045626,
|
| 1182 |
+
"eval_mse_loss": 0.5901335754045626,
|
| 1183 |
+
"eval_runtime": 7.4243,
|
| 1184 |
+
"eval_samples_per_second": 352.625,
|
| 1185 |
+
"eval_steps_per_second": 5.522,
|
| 1186 |
+
"step": 12544
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 6.320987654320987,
|
| 1190 |
+
"grad_norm": 4.863134384155273,
|
| 1191 |
+
"learning_rate": 0.0003122852070737825,
|
| 1192 |
+
"loss": 0.581442654132843,
|
| 1193 |
+
"step": 12800
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 6.320987654320987,
|
| 1197 |
+
"eval_bleu": 0.26764936587915455,
|
| 1198 |
+
"eval_loss": 0.5768222677998427,
|
| 1199 |
+
"eval_mse_loss": 0.5768222677998427,
|
| 1200 |
+
"step": 12800
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.320987654320987,
|
| 1204 |
+
"eval_bleu": 0.26764936587915455,
|
| 1205 |
+
"eval_loss": 0.5768222677998427,
|
| 1206 |
+
"eval_mse_loss": 0.5768222677998427,
|
| 1207 |
+
"eval_runtime": 7.9069,
|
| 1208 |
+
"eval_samples_per_second": 331.105,
|
| 1209 |
+
"eval_steps_per_second": 5.185,
|
| 1210 |
+
"step": 12800
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 6.4474074074074075,
|
| 1214 |
+
"grad_norm": 8.697264671325684,
|
| 1215 |
+
"learning_rate": 0.00029356342858509677,
|
| 1216 |
+
"loss": 0.5772220492362976,
|
| 1217 |
+
"step": 13056
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 6.4474074074074075,
|
| 1221 |
+
"eval_bleu": 0.27568777700132663,
|
| 1222 |
+
"eval_loss": 0.584543146738192,
|
| 1223 |
+
"eval_mse_loss": 0.584543146738192,
|
| 1224 |
+
"step": 13056
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 6.4474074074074075,
|
| 1228 |
+
"eval_bleu": 0.27568777700132663,
|
| 1229 |
+
"eval_loss": 0.584543146738192,
|
| 1230 |
+
"eval_mse_loss": 0.584543146738192,
|
| 1231 |
+
"eval_runtime": 8.0062,
|
| 1232 |
+
"eval_samples_per_second": 326.995,
|
| 1233 |
+
"eval_steps_per_second": 5.121,
|
| 1234 |
+
"step": 13056
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 6.573827160493828,
|
| 1238 |
+
"grad_norm": 6.309488773345947,
|
| 1239 |
+
"learning_rate": 0.0002751843389171185,
|
| 1240 |
+
"loss": 0.5722501277923584,
|
| 1241 |
+
"step": 13312
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 6.573827160493828,
|
| 1245 |
+
"eval_bleu": 0.27306378384191476,
|
| 1246 |
+
"eval_loss": 0.5755636982801484,
|
| 1247 |
+
"eval_mse_loss": 0.5755636982801484,
|
| 1248 |
+
"step": 13312
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 6.573827160493828,
|
| 1252 |
+
"eval_bleu": 0.27306378384191476,
|
| 1253 |
+
"eval_loss": 0.5755636982801484,
|
| 1254 |
+
"eval_mse_loss": 0.5755636982801484,
|
| 1255 |
+
"eval_runtime": 8.591,
|
| 1256 |
+
"eval_samples_per_second": 304.738,
|
| 1257 |
+
"eval_steps_per_second": 4.772,
|
| 1258 |
+
"step": 13312
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 6.700246913580247,
|
| 1262 |
+
"grad_norm": 5.390190601348877,
|
| 1263 |
+
"learning_rate": 0.0002571784477248029,
|
| 1264 |
+
"loss": 0.5714833736419678,
|
| 1265 |
+
"step": 13568
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 6.700246913580247,
|
| 1269 |
+
"eval_bleu": 0.2848300030499236,
|
| 1270 |
+
"eval_loss": 0.570485861563101,
|
| 1271 |
+
"eval_mse_loss": 0.570485861563101,
|
| 1272 |
+
"step": 13568
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 6.700246913580247,
|
| 1276 |
+
"eval_bleu": 0.2848300030499236,
|
| 1277 |
+
"eval_loss": 0.570485861563101,
|
| 1278 |
+
"eval_mse_loss": 0.570485861563101,
|
| 1279 |
+
"eval_runtime": 7.2761,
|
| 1280 |
+
"eval_samples_per_second": 359.808,
|
| 1281 |
+
"eval_steps_per_second": 5.635,
|
| 1282 |
+
"step": 13568
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 6.826666666666666,
|
| 1286 |
+
"grad_norm": 7.215004920959473,
|
| 1287 |
+
"learning_rate": 0.0002395756451462014,
|
| 1288 |
+
"loss": 0.5674658417701721,
|
| 1289 |
+
"step": 13824
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.826666666666666,
|
| 1293 |
+
"eval_bleu": 0.2756130503152812,
|
| 1294 |
+
"eval_loss": 0.5792907963438731,
|
| 1295 |
+
"eval_mse_loss": 0.5792907963438731,
|
| 1296 |
+
"step": 13824
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 6.826666666666666,
|
| 1300 |
+
"eval_bleu": 0.2756130503152812,
|
| 1301 |
+
"eval_loss": 0.5792907963438731,
|
| 1302 |
+
"eval_mse_loss": 0.5792907963438731,
|
| 1303 |
+
"eval_runtime": 7.3879,
|
| 1304 |
+
"eval_samples_per_second": 354.362,
|
| 1305 |
+
"eval_steps_per_second": 5.55,
|
| 1306 |
+
"step": 13824
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 6.953086419753086,
|
| 1310 |
+
"grad_norm": 6.6079816818237305,
|
| 1311 |
+
"learning_rate": 0.00022240515218423758,
|
| 1312 |
+
"loss": 0.5638896226882935,
|
| 1313 |
+
"step": 14080
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 6.953086419753086,
|
| 1317 |
+
"eval_bleu": 0.2958995495334816,
|
| 1318 |
+
"eval_loss": 0.5594088427904176,
|
| 1319 |
+
"eval_mse_loss": 0.5594088427904176,
|
| 1320 |
+
"step": 14080
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 6.953086419753086,
|
| 1324 |
+
"eval_bleu": 0.2958995495334816,
|
| 1325 |
+
"eval_loss": 0.5594088427904176,
|
| 1326 |
+
"eval_mse_loss": 0.5594088427904176,
|
| 1327 |
+
"eval_runtime": 7.9094,
|
| 1328 |
+
"eval_samples_per_second": 330.998,
|
| 1329 |
+
"eval_steps_per_second": 5.184,
|
| 1330 |
+
"step": 14080
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 7.079506172839507,
|
| 1334 |
+
"grad_norm": 6.562555313110352,
|
| 1335 |
+
"learning_rate": 0.00020569547219925934,
|
| 1336 |
+
"loss": 0.5631716251373291,
|
| 1337 |
+
"step": 14336
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 7.079506172839507,
|
| 1341 |
+
"eval_bleu": 0.2905136606672008,
|
| 1342 |
+
"eval_loss": 0.5631622737500726,
|
| 1343 |
+
"eval_mse_loss": 0.5631622737500726,
|
| 1344 |
+
"step": 14336
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 7.079506172839507,
|
| 1348 |
+
"eval_bleu": 0.2905136606672008,
|
| 1349 |
+
"eval_loss": 0.5631622737500726,
|
| 1350 |
+
"eval_mse_loss": 0.5631622737500726,
|
| 1351 |
+
"eval_runtime": 8.3002,
|
| 1352 |
+
"eval_samples_per_second": 315.415,
|
| 1353 |
+
"eval_steps_per_second": 4.94,
|
| 1354 |
+
"step": 14336
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 7.205925925925926,
|
| 1358 |
+
"grad_norm": 5.195821285247803,
|
| 1359 |
+
"learning_rate": 0.00018947434359289434,
|
| 1360 |
+
"loss": 0.5603777170181274,
|
| 1361 |
+
"step": 14592
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 7.205925925925926,
|
| 1365 |
+
"eval_bleu": 0.29437709495493225,
|
| 1366 |
+
"eval_loss": 0.5465006559360318,
|
| 1367 |
+
"eval_mse_loss": 0.5465006559360318,
|
| 1368 |
+
"step": 14592
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 7.205925925925926,
|
| 1372 |
+
"eval_bleu": 0.29437709495493225,
|
| 1373 |
+
"eval_loss": 0.5465006559360318,
|
| 1374 |
+
"eval_mse_loss": 0.5465006559360318,
|
| 1375 |
+
"eval_runtime": 7.1426,
|
| 1376 |
+
"eval_samples_per_second": 366.535,
|
| 1377 |
+
"eval_steps_per_second": 5.74,
|
| 1378 |
+
"step": 14592
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 7.332345679012346,
|
| 1382 |
+
"grad_norm": 8.156927108764648,
|
| 1383 |
+
"learning_rate": 0.0001737686937617491,
|
| 1384 |
+
"loss": 0.5557982325553894,
|
| 1385 |
+
"step": 14848
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 7.332345679012346,
|
| 1389 |
+
"eval_bleu": 0.29449963629268144,
|
| 1390 |
+
"eval_loss": 0.557792792959911,
|
| 1391 |
+
"eval_mse_loss": 0.557792792959911,
|
| 1392 |
+
"step": 14848
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 7.332345679012346,
|
| 1396 |
+
"eval_bleu": 0.29449963629268144,
|
| 1397 |
+
"eval_loss": 0.557792792959911,
|
| 1398 |
+
"eval_mse_loss": 0.557792792959911,
|
| 1399 |
+
"eval_runtime": 7.7275,
|
| 1400 |
+
"eval_samples_per_second": 338.789,
|
| 1401 |
+
"eval_steps_per_second": 5.306,
|
| 1402 |
+
"step": 14848
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 7.458765432098765,
|
| 1406 |
+
"grad_norm": 5.172349452972412,
|
| 1407 |
+
"learning_rate": 0.00015860459439739582,
|
| 1408 |
+
"loss": 0.5558417439460754,
|
| 1409 |
+
"step": 15104
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 7.458765432098765,
|
| 1413 |
+
"eval_bleu": 0.31102631980865114,
|
| 1414 |
+
"eval_loss": 0.5469118814642836,
|
| 1415 |
+
"eval_mse_loss": 0.5469118814642836,
|
| 1416 |
+
"step": 15104
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 7.458765432098765,
|
| 1420 |
+
"eval_bleu": 0.31102631980865114,
|
| 1421 |
+
"eval_loss": 0.5469118814642836,
|
| 1422 |
+
"eval_mse_loss": 0.5469118814642836,
|
| 1423 |
+
"eval_runtime": 7.9676,
|
| 1424 |
+
"eval_samples_per_second": 328.58,
|
| 1425 |
+
"eval_steps_per_second": 5.146,
|
| 1426 |
+
"step": 15104
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 7.5851851851851855,
|
| 1430 |
+
"grad_norm": 5.335220813751221,
|
| 1431 |
+
"learning_rate": 0.0001440072182068436,
|
| 1432 |
+
"loss": 0.5527888536453247,
|
| 1433 |
+
"step": 15360
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 7.5851851851851855,
|
| 1437 |
+
"eval_bleu": 0.3040853321881768,
|
| 1438 |
+
"eval_loss": 0.5505978399660529,
|
| 1439 |
+
"eval_mse_loss": 0.5505978399660529,
|
| 1440 |
+
"step": 15360
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 7.5851851851851855,
|
| 1444 |
+
"eval_bleu": 0.3040853321881768,
|
| 1445 |
+
"eval_loss": 0.5505978399660529,
|
| 1446 |
+
"eval_mse_loss": 0.5505978399660529,
|
| 1447 |
+
"eval_runtime": 8.0279,
|
| 1448 |
+
"eval_samples_per_second": 326.113,
|
| 1449 |
+
"eval_steps_per_second": 5.107,
|
| 1450 |
+
"step": 15360
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 7.711604938271605,
|
| 1454 |
+
"grad_norm": 3.120297908782959,
|
| 1455 |
+
"learning_rate": 0.00013000079712534475,
|
| 1456 |
+
"loss": 0.5498585104942322,
|
| 1457 |
+
"step": 15616
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 7.711604938271605,
|
| 1461 |
+
"eval_bleu": 0.30098409224195205,
|
| 1462 |
+
"eval_loss": 0.54582195819878,
|
| 1463 |
+
"eval_mse_loss": 0.54582195819878,
|
| 1464 |
+
"step": 15616
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 7.711604938271605,
|
| 1468 |
+
"eval_bleu": 0.30098409224195205,
|
| 1469 |
+
"eval_loss": 0.54582195819878,
|
| 1470 |
+
"eval_mse_loss": 0.54582195819878,
|
| 1471 |
+
"eval_runtime": 8.0703,
|
| 1472 |
+
"eval_samples_per_second": 324.401,
|
| 1473 |
+
"eval_steps_per_second": 5.08,
|
| 1474 |
+
"step": 15616
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 7.838024691358025,
|
| 1478 |
+
"grad_norm": 4.802690029144287,
|
| 1479 |
+
"learning_rate": 0.00011660858209089819,
|
| 1480 |
+
"loss": 0.5511511564254761,
|
| 1481 |
+
"step": 15872
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 7.838024691358025,
|
| 1485 |
+
"eval_bleu": 0.3068134406523234,
|
| 1486 |
+
"eval_loss": 0.5499871998298459,
|
| 1487 |
+
"eval_mse_loss": 0.5499871998298459,
|
| 1488 |
+
"step": 15872
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 7.838024691358025,
|
| 1492 |
+
"eval_bleu": 0.3068134406523234,
|
| 1493 |
+
"eval_loss": 0.5499871998298459,
|
| 1494 |
+
"eval_mse_loss": 0.5499871998298459,
|
| 1495 |
+
"eval_runtime": 7.2713,
|
| 1496 |
+
"eval_samples_per_second": 360.046,
|
| 1497 |
+
"eval_steps_per_second": 5.639,
|
| 1498 |
+
"step": 15872
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 7.964444444444444,
|
| 1502 |
+
"grad_norm": 3.471189260482788,
|
| 1503 |
+
"learning_rate": 0.00010385280444723056,
|
| 1504 |
+
"loss": 0.5520000457763672,
|
| 1505 |
+
"step": 16128
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 7.964444444444444,
|
| 1509 |
+
"eval_bleu": 0.3052295052303889,
|
| 1510 |
+
"eval_loss": 0.5441080797009352,
|
| 1511 |
+
"eval_mse_loss": 0.5441080797009352,
|
| 1512 |
+
"step": 16128
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 7.964444444444444,
|
| 1516 |
+
"eval_bleu": 0.3052295052303889,
|
| 1517 |
+
"eval_loss": 0.5441080797009352,
|
| 1518 |
+
"eval_mse_loss": 0.5441080797009352,
|
| 1519 |
+
"eval_runtime": 7.7809,
|
| 1520 |
+
"eval_samples_per_second": 336.463,
|
| 1521 |
+
"eval_steps_per_second": 5.269,
|
| 1522 |
+
"step": 16128
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 8.090864197530864,
|
| 1526 |
+
"grad_norm": 5.1973466873168945,
|
| 1527 |
+
"learning_rate": 9.175463903932168e-05,
|
| 1528 |
+
"loss": 0.5478553771972656,
|
| 1529 |
+
"step": 16384
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 8.090864197530864,
|
| 1533 |
+
"eval_bleu": 0.2907079883758542,
|
| 1534 |
+
"eval_loss": 0.5581492403658425,
|
| 1535 |
+
"eval_mse_loss": 0.5581492403658425,
|
| 1536 |
+
"step": 16384
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 8.090864197530864,
|
| 1540 |
+
"eval_bleu": 0.2907079883758542,
|
| 1541 |
+
"eval_loss": 0.5581492403658425,
|
| 1542 |
+
"eval_mse_loss": 0.5581492403658425,
|
| 1543 |
+
"eval_runtime": 8.0444,
|
| 1544 |
+
"eval_samples_per_second": 325.444,
|
| 1545 |
+
"eval_steps_per_second": 5.097,
|
| 1546 |
+
"step": 16384
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 8.217283950617285,
|
| 1550 |
+
"grad_norm": 3.1891634464263916,
|
| 1551 |
+
"learning_rate": 8.033416906274093e-05,
|
| 1552 |
+
"loss": 0.5465660095214844,
|
| 1553 |
+
"step": 16640
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 8.217283950617285,
|
| 1557 |
+
"eval_bleu": 0.3151093389207819,
|
| 1558 |
+
"eval_loss": 0.5382588927338763,
|
| 1559 |
+
"eval_mse_loss": 0.5382588927338763,
|
| 1560 |
+
"step": 16640
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 8.217283950617285,
|
| 1564 |
+
"eval_bleu": 0.3151093389207819,
|
| 1565 |
+
"eval_loss": 0.5382588927338763,
|
| 1566 |
+
"eval_mse_loss": 0.5382588927338763,
|
| 1567 |
+
"eval_runtime": 8.1703,
|
| 1568 |
+
"eval_samples_per_second": 320.43,
|
| 1569 |
+
"eval_steps_per_second": 5.018,
|
| 1570 |
+
"step": 16640
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 8.343703703703703,
|
| 1574 |
+
"grad_norm": 3.5024101734161377,
|
| 1575 |
+
"learning_rate": 6.961035272514177e-05,
|
| 1576 |
+
"loss": 0.5455322265625,
|
| 1577 |
+
"step": 16896
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 8.343703703703703,
|
| 1581 |
+
"eval_bleu": 0.31440992086262937,
|
| 1582 |
+
"eval_loss": 0.5380844590140552,
|
| 1583 |
+
"eval_mse_loss": 0.5380844590140552,
|
| 1584 |
+
"step": 16896
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 8.343703703703703,
|
| 1588 |
+
"eval_bleu": 0.31440992086262937,
|
| 1589 |
+
"eval_loss": 0.5380844590140552,
|
| 1590 |
+
"eval_mse_loss": 0.5380844590140552,
|
| 1591 |
+
"eval_runtime": 7.1273,
|
| 1592 |
+
"eval_samples_per_second": 367.32,
|
| 1593 |
+
"eval_steps_per_second": 5.753,
|
| 1594 |
+
"step": 16896
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 8.470123456790123,
|
| 1598 |
+
"grad_norm": 3.242410659790039,
|
| 1599 |
+
"learning_rate": 5.960099177526024e-05,
|
| 1600 |
+
"loss": 0.5413248538970947,
|
| 1601 |
+
"step": 17152
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 8.470123456790123,
|
| 1605 |
+
"eval_bleu": 0.3030533280572146,
|
| 1606 |
+
"eval_loss": 0.5433335965726434,
|
| 1607 |
+
"eval_mse_loss": 0.5433335965726434,
|
| 1608 |
+
"step": 17152
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 8.470123456790123,
|
| 1612 |
+
"eval_bleu": 0.3030533280572146,
|
| 1613 |
+
"eval_loss": 0.5433335965726434,
|
| 1614 |
+
"eval_mse_loss": 0.5433335965726434,
|
| 1615 |
+
"eval_runtime": 8.049,
|
| 1616 |
+
"eval_samples_per_second": 325.26,
|
| 1617 |
+
"eval_steps_per_second": 5.094,
|
| 1618 |
+
"step": 17152
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 8.596543209876543,
|
| 1622 |
+
"grad_norm": 3.3194503784179688,
|
| 1623 |
+
"learning_rate": 5.032270195165667e-05,
|
| 1624 |
+
"loss": 0.5402602553367615,
|
| 1625 |
+
"step": 17408
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 8.596543209876543,
|
| 1629 |
+
"eval_bleu": 0.3284021854773732,
|
| 1630 |
+
"eval_loss": 0.5290337989969951,
|
| 1631 |
+
"eval_mse_loss": 0.5290337989969951,
|
| 1632 |
+
"step": 17408
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 8.596543209876543,
|
| 1636 |
+
"eval_bleu": 0.3284021854773732,
|
| 1637 |
+
"eval_loss": 0.5290337989969951,
|
| 1638 |
+
"eval_mse_loss": 0.5290337989969951,
|
| 1639 |
+
"eval_runtime": 7.8967,
|
| 1640 |
+
"eval_samples_per_second": 331.532,
|
| 1641 |
+
"eval_steps_per_second": 5.192,
|
| 1642 |
+
"step": 17408
|
| 1643 |
+
}
|
| 1644 |
+
],
|
| 1645 |
+
"logging_steps": 256,
|
| 1646 |
+
"max_steps": 20250,
|
| 1647 |
+
"num_input_tokens_seen": 0,
|
| 1648 |
+
"num_train_epochs": 10,
|
| 1649 |
+
"save_steps": 256,
|
| 1650 |
+
"stateful_callbacks": {
|
| 1651 |
+
"TrainerControl": {
|
| 1652 |
+
"args": {
|
| 1653 |
+
"should_epoch_stop": false,
|
| 1654 |
+
"should_evaluate": false,
|
| 1655 |
+
"should_log": false,
|
| 1656 |
+
"should_save": true,
|
| 1657 |
+
"should_training_stop": false
|
| 1658 |
+
},
|
| 1659 |
+
"attributes": {}
|
| 1660 |
+
}
|
| 1661 |
+
},
|
| 1662 |
+
"total_flos": 0.0,
|
| 1663 |
+
"train_batch_size": 64,
|
| 1664 |
+
"trial_name": null,
|
| 1665 |
+
"trial_params": null
|
| 1666 |
+
}
|
checkpoints-v1.0-discrete-conditional/checkpoint-17408/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32df247d3a9586ba514368d06788d79a5588a1e9b0fecddcdd25370e406c6a66
|
| 3 |
+
size 5137
|