Training in progress, step 282
Browse files- model.safetensors +1 -1
- run-nk1o8cuk/checkpoint-282/config.json +22 -0
- run-nk1o8cuk/checkpoint-282/model.safetensors +3 -0
- run-nk1o8cuk/checkpoint-282/optimizer.pt +3 -0
- run-nk1o8cuk/checkpoint-282/rng_state.pth +3 -0
- run-nk1o8cuk/checkpoint-282/scheduler.pt +3 -0
- run-nk1o8cuk/checkpoint-282/trainer_state.json +1450 -0
- run-nk1o8cuk/checkpoint-282/training_args.bin +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 605156676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7479e4640aa8b3ee33e7cfabc86c5808c4ce220f08794cbde2199f6097706825
|
| 3 |
size 605156676
|
run-nk1o8cuk/checkpoint-282/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"model_type": "clip_text_model"
|
| 15 |
+
},
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"transformers_version": "4.42.0.dev0",
|
| 18 |
+
"vision_config": {
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"model_type": "clip_vision_model"
|
| 21 |
+
}
|
| 22 |
+
}
|
run-nk1o8cuk/checkpoint-282/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7479e4640aa8b3ee33e7cfabc86c5808c4ce220f08794cbde2199f6097706825
|
| 3 |
+
size 605156676
|
run-nk1o8cuk/checkpoint-282/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d377ce2bbb5da61d2a36dcd3a7f235162bf61d5197350d98e36b334ad59cc004
|
| 3 |
+
size 1210551612
|
run-nk1o8cuk/checkpoint-282/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69c50a2d44302b65e4b4af5269ec9392f104b2d5402ccbb461786bead4e2de18
|
| 3 |
+
size 14244
|
run-nk1o8cuk/checkpoint-282/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd28ea38f05f57d905282e2cf19832ae3cd4218351b888feb45c97f26b5a88d
|
| 3 |
+
size 1064
|
run-nk1o8cuk/checkpoint-282/trainer_state.json
ADDED
|
@@ -0,0 +1,1450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 3,
|
| 6 |
+
"global_step": 282,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.031914893617021274,
|
| 13 |
+
"grad_norm": 219.1436309814453,
|
| 14 |
+
"learning_rate": 4.687722050568071e-06,
|
| 15 |
+
"loss": 1.6437,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.031914893617021274,
|
| 20 |
+
"eval_loss": 1.2238304615020752,
|
| 21 |
+
"eval_runtime": 49.6348,
|
| 22 |
+
"eval_samples_per_second": 6.044,
|
| 23 |
+
"eval_steps_per_second": 0.201,
|
| 24 |
+
"step": 3
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06382978723404255,
|
| 28 |
+
"grad_norm": 151.3193817138672,
|
| 29 |
+
"learning_rate": 4.637316437121103e-06,
|
| 30 |
+
"loss": 1.5519,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06382978723404255,
|
| 35 |
+
"eval_loss": 1.166587471961975,
|
| 36 |
+
"eval_runtime": 43.6496,
|
| 37 |
+
"eval_samples_per_second": 6.873,
|
| 38 |
+
"eval_steps_per_second": 0.229,
|
| 39 |
+
"step": 6
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.09574468085106383,
|
| 43 |
+
"grad_norm": 151.81333923339844,
|
| 44 |
+
"learning_rate": 4.586910823674134e-06,
|
| 45 |
+
"loss": 1.1065,
|
| 46 |
+
"step": 9
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.09574468085106383,
|
| 50 |
+
"eval_loss": 1.167779803276062,
|
| 51 |
+
"eval_runtime": 43.8309,
|
| 52 |
+
"eval_samples_per_second": 6.844,
|
| 53 |
+
"eval_steps_per_second": 0.228,
|
| 54 |
+
"step": 9
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.1276595744680851,
|
| 58 |
+
"grad_norm": 216.54078674316406,
|
| 59 |
+
"learning_rate": 4.536505210227166e-06,
|
| 60 |
+
"loss": 1.0103,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.1276595744680851,
|
| 65 |
+
"eval_loss": 1.1300101280212402,
|
| 66 |
+
"eval_runtime": 42.8188,
|
| 67 |
+
"eval_samples_per_second": 7.006,
|
| 68 |
+
"eval_steps_per_second": 0.234,
|
| 69 |
+
"step": 12
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1595744680851064,
|
| 73 |
+
"grad_norm": 96.97032928466797,
|
| 74 |
+
"learning_rate": 4.486099596780197e-06,
|
| 75 |
+
"loss": 1.1391,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.1595744680851064,
|
| 80 |
+
"eval_loss": 1.093359351158142,
|
| 81 |
+
"eval_runtime": 43.7071,
|
| 82 |
+
"eval_samples_per_second": 6.864,
|
| 83 |
+
"eval_steps_per_second": 0.229,
|
| 84 |
+
"step": 15
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.19148936170212766,
|
| 88 |
+
"grad_norm": 93.6313247680664,
|
| 89 |
+
"learning_rate": 4.435693983333229e-06,
|
| 90 |
+
"loss": 1.1749,
|
| 91 |
+
"step": 18
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.19148936170212766,
|
| 95 |
+
"eval_loss": 1.0837420225143433,
|
| 96 |
+
"eval_runtime": 42.6236,
|
| 97 |
+
"eval_samples_per_second": 7.038,
|
| 98 |
+
"eval_steps_per_second": 0.235,
|
| 99 |
+
"step": 18
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.22340425531914893,
|
| 103 |
+
"grad_norm": 128.5612030029297,
|
| 104 |
+
"learning_rate": 4.38528836988626e-06,
|
| 105 |
+
"loss": 1.0878,
|
| 106 |
+
"step": 21
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.22340425531914893,
|
| 110 |
+
"eval_loss": 1.0713236331939697,
|
| 111 |
+
"eval_runtime": 43.1057,
|
| 112 |
+
"eval_samples_per_second": 6.96,
|
| 113 |
+
"eval_steps_per_second": 0.232,
|
| 114 |
+
"step": 21
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2553191489361702,
|
| 118 |
+
"grad_norm": 106.38141632080078,
|
| 119 |
+
"learning_rate": 4.334882756439292e-06,
|
| 120 |
+
"loss": 0.8829,
|
| 121 |
+
"step": 24
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2553191489361702,
|
| 125 |
+
"eval_loss": 1.0457205772399902,
|
| 126 |
+
"eval_runtime": 43.4262,
|
| 127 |
+
"eval_samples_per_second": 6.908,
|
| 128 |
+
"eval_steps_per_second": 0.23,
|
| 129 |
+
"step": 24
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2872340425531915,
|
| 133 |
+
"grad_norm": 109.02174377441406,
|
| 134 |
+
"learning_rate": 4.284477142992323e-06,
|
| 135 |
+
"loss": 1.3004,
|
| 136 |
+
"step": 27
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2872340425531915,
|
| 140 |
+
"eval_loss": 1.015425205230713,
|
| 141 |
+
"eval_runtime": 42.8448,
|
| 142 |
+
"eval_samples_per_second": 7.002,
|
| 143 |
+
"eval_steps_per_second": 0.233,
|
| 144 |
+
"step": 27
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3191489361702128,
|
| 148 |
+
"grad_norm": 93.8167495727539,
|
| 149 |
+
"learning_rate": 4.234071529545355e-06,
|
| 150 |
+
"loss": 1.0768,
|
| 151 |
+
"step": 30
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3191489361702128,
|
| 155 |
+
"eval_loss": 0.9899512529373169,
|
| 156 |
+
"eval_runtime": 62.0193,
|
| 157 |
+
"eval_samples_per_second": 4.837,
|
| 158 |
+
"eval_steps_per_second": 0.161,
|
| 159 |
+
"step": 30
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.35106382978723405,
|
| 163 |
+
"grad_norm": 117.0296401977539,
|
| 164 |
+
"learning_rate": 4.183665916098386e-06,
|
| 165 |
+
"loss": 0.8761,
|
| 166 |
+
"step": 33
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.35106382978723405,
|
| 170 |
+
"eval_loss": 0.9733409881591797,
|
| 171 |
+
"eval_runtime": 43.6195,
|
| 172 |
+
"eval_samples_per_second": 6.878,
|
| 173 |
+
"eval_steps_per_second": 0.229,
|
| 174 |
+
"step": 33
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.3829787234042553,
|
| 178 |
+
"grad_norm": 97.06668090820312,
|
| 179 |
+
"learning_rate": 4.1332603026514175e-06,
|
| 180 |
+
"loss": 1.0648,
|
| 181 |
+
"step": 36
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3829787234042553,
|
| 185 |
+
"eval_loss": 0.9584157466888428,
|
| 186 |
+
"eval_runtime": 43.1964,
|
| 187 |
+
"eval_samples_per_second": 6.945,
|
| 188 |
+
"eval_steps_per_second": 0.232,
|
| 189 |
+
"step": 36
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4148936170212766,
|
| 193 |
+
"grad_norm": 69.0722427368164,
|
| 194 |
+
"learning_rate": 4.082854689204449e-06,
|
| 195 |
+
"loss": 0.8425,
|
| 196 |
+
"step": 39
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.4148936170212766,
|
| 200 |
+
"eval_loss": 0.9429272413253784,
|
| 201 |
+
"eval_runtime": 43.4379,
|
| 202 |
+
"eval_samples_per_second": 6.906,
|
| 203 |
+
"eval_steps_per_second": 0.23,
|
| 204 |
+
"step": 39
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.44680851063829785,
|
| 208 |
+
"grad_norm": 72.62019348144531,
|
| 209 |
+
"learning_rate": 4.032449075757481e-06,
|
| 210 |
+
"loss": 0.8714,
|
| 211 |
+
"step": 42
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.44680851063829785,
|
| 215 |
+
"eval_loss": 0.9335389137268066,
|
| 216 |
+
"eval_runtime": 42.713,
|
| 217 |
+
"eval_samples_per_second": 7.024,
|
| 218 |
+
"eval_steps_per_second": 0.234,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4787234042553192,
|
| 223 |
+
"grad_norm": 91.91283416748047,
|
| 224 |
+
"learning_rate": 3.982043462310513e-06,
|
| 225 |
+
"loss": 0.9101,
|
| 226 |
+
"step": 45
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4787234042553192,
|
| 230 |
+
"eval_loss": 0.9222455024719238,
|
| 231 |
+
"eval_runtime": 43.5273,
|
| 232 |
+
"eval_samples_per_second": 6.892,
|
| 233 |
+
"eval_steps_per_second": 0.23,
|
| 234 |
+
"step": 45
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5106382978723404,
|
| 238 |
+
"grad_norm": 71.0954360961914,
|
| 239 |
+
"learning_rate": 3.931637848863544e-06,
|
| 240 |
+
"loss": 1.0336,
|
| 241 |
+
"step": 48
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5106382978723404,
|
| 245 |
+
"eval_loss": 0.9134926199913025,
|
| 246 |
+
"eval_runtime": 46.5111,
|
| 247 |
+
"eval_samples_per_second": 6.45,
|
| 248 |
+
"eval_steps_per_second": 0.215,
|
| 249 |
+
"step": 48
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5425531914893617,
|
| 253 |
+
"grad_norm": 92.62516021728516,
|
| 254 |
+
"learning_rate": 3.881232235416575e-06,
|
| 255 |
+
"loss": 0.941,
|
| 256 |
+
"step": 51
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.5425531914893617,
|
| 260 |
+
"eval_loss": 0.9049246311187744,
|
| 261 |
+
"eval_runtime": 43.2332,
|
| 262 |
+
"eval_samples_per_second": 6.939,
|
| 263 |
+
"eval_steps_per_second": 0.231,
|
| 264 |
+
"step": 51
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.574468085106383,
|
| 268 |
+
"grad_norm": 87.83678436279297,
|
| 269 |
+
"learning_rate": 3.830826621969607e-06,
|
| 270 |
+
"loss": 1.1561,
|
| 271 |
+
"step": 54
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.574468085106383,
|
| 275 |
+
"eval_loss": 0.9015933275222778,
|
| 276 |
+
"eval_runtime": 43.95,
|
| 277 |
+
"eval_samples_per_second": 6.826,
|
| 278 |
+
"eval_steps_per_second": 0.228,
|
| 279 |
+
"step": 54
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6063829787234043,
|
| 283 |
+
"grad_norm": 81.34359741210938,
|
| 284 |
+
"learning_rate": 3.780421008522638e-06,
|
| 285 |
+
"loss": 0.9756,
|
| 286 |
+
"step": 57
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6063829787234043,
|
| 290 |
+
"eval_loss": 0.8971786499023438,
|
| 291 |
+
"eval_runtime": 43.2014,
|
| 292 |
+
"eval_samples_per_second": 6.944,
|
| 293 |
+
"eval_steps_per_second": 0.231,
|
| 294 |
+
"step": 57
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.6382978723404256,
|
| 298 |
+
"grad_norm": 64.89433288574219,
|
| 299 |
+
"learning_rate": 3.73001539507567e-06,
|
| 300 |
+
"loss": 0.749,
|
| 301 |
+
"step": 60
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.6382978723404256,
|
| 305 |
+
"eval_loss": 0.8940334916114807,
|
| 306 |
+
"eval_runtime": 50.073,
|
| 307 |
+
"eval_samples_per_second": 5.991,
|
| 308 |
+
"eval_steps_per_second": 0.2,
|
| 309 |
+
"step": 60
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.6702127659574468,
|
| 313 |
+
"grad_norm": 92.25138854980469,
|
| 314 |
+
"learning_rate": 3.679609781628701e-06,
|
| 315 |
+
"loss": 0.9315,
|
| 316 |
+
"step": 63
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.6702127659574468,
|
| 320 |
+
"eval_loss": 0.8884549736976624,
|
| 321 |
+
"eval_runtime": 46.5461,
|
| 322 |
+
"eval_samples_per_second": 6.445,
|
| 323 |
+
"eval_steps_per_second": 0.215,
|
| 324 |
+
"step": 63
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7021276595744681,
|
| 328 |
+
"grad_norm": 86.6369400024414,
|
| 329 |
+
"learning_rate": 3.629204168181733e-06,
|
| 330 |
+
"loss": 1.1571,
|
| 331 |
+
"step": 66
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7021276595744681,
|
| 335 |
+
"eval_loss": 0.883185625076294,
|
| 336 |
+
"eval_runtime": 43.0575,
|
| 337 |
+
"eval_samples_per_second": 6.967,
|
| 338 |
+
"eval_steps_per_second": 0.232,
|
| 339 |
+
"step": 66
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.7340425531914894,
|
| 343 |
+
"grad_norm": 87.74919128417969,
|
| 344 |
+
"learning_rate": 3.5787985547347642e-06,
|
| 345 |
+
"loss": 1.3094,
|
| 346 |
+
"step": 69
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7340425531914894,
|
| 350 |
+
"eval_loss": 0.8721677660942078,
|
| 351 |
+
"eval_runtime": 43.1156,
|
| 352 |
+
"eval_samples_per_second": 6.958,
|
| 353 |
+
"eval_steps_per_second": 0.232,
|
| 354 |
+
"step": 69
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7659574468085106,
|
| 358 |
+
"grad_norm": 81.59742736816406,
|
| 359 |
+
"learning_rate": 3.5283929412877956e-06,
|
| 360 |
+
"loss": 1.0689,
|
| 361 |
+
"step": 72
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.7659574468085106,
|
| 365 |
+
"eval_loss": 0.8642645478248596,
|
| 366 |
+
"eval_runtime": 43.5775,
|
| 367 |
+
"eval_samples_per_second": 6.884,
|
| 368 |
+
"eval_steps_per_second": 0.229,
|
| 369 |
+
"step": 72
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7978723404255319,
|
| 373 |
+
"grad_norm": 81.44770050048828,
|
| 374 |
+
"learning_rate": 3.477987327840827e-06,
|
| 375 |
+
"loss": 0.8599,
|
| 376 |
+
"step": 75
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.7978723404255319,
|
| 380 |
+
"eval_loss": 0.8605104684829712,
|
| 381 |
+
"eval_runtime": 43.731,
|
| 382 |
+
"eval_samples_per_second": 6.86,
|
| 383 |
+
"eval_steps_per_second": 0.229,
|
| 384 |
+
"step": 75
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8297872340425532,
|
| 388 |
+
"grad_norm": 74.29925537109375,
|
| 389 |
+
"learning_rate": 3.427581714393859e-06,
|
| 390 |
+
"loss": 1.0591,
|
| 391 |
+
"step": 78
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.8297872340425532,
|
| 395 |
+
"eval_loss": 0.8572540283203125,
|
| 396 |
+
"eval_runtime": 43.0132,
|
| 397 |
+
"eval_samples_per_second": 6.975,
|
| 398 |
+
"eval_steps_per_second": 0.232,
|
| 399 |
+
"step": 78
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.8617021276595744,
|
| 403 |
+
"grad_norm": 80.95857238769531,
|
| 404 |
+
"learning_rate": 3.37717610094689e-06,
|
| 405 |
+
"loss": 0.8628,
|
| 406 |
+
"step": 81
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.8617021276595744,
|
| 410 |
+
"eval_loss": 0.854705810546875,
|
| 411 |
+
"eval_runtime": 43.5041,
|
| 412 |
+
"eval_samples_per_second": 6.896,
|
| 413 |
+
"eval_steps_per_second": 0.23,
|
| 414 |
+
"step": 81
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.8936170212765957,
|
| 418 |
+
"grad_norm": 73.22078704833984,
|
| 419 |
+
"learning_rate": 3.3267704874999216e-06,
|
| 420 |
+
"loss": 0.8449,
|
| 421 |
+
"step": 84
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.8936170212765957,
|
| 425 |
+
"eval_loss": 0.8551430106163025,
|
| 426 |
+
"eval_runtime": 43.3103,
|
| 427 |
+
"eval_samples_per_second": 6.927,
|
| 428 |
+
"eval_steps_per_second": 0.231,
|
| 429 |
+
"step": 84
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.925531914893617,
|
| 433 |
+
"grad_norm": 81.8653564453125,
|
| 434 |
+
"learning_rate": 3.2763648740529535e-06,
|
| 435 |
+
"loss": 0.8565,
|
| 436 |
+
"step": 87
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.925531914893617,
|
| 440 |
+
"eval_loss": 0.8558651804924011,
|
| 441 |
+
"eval_runtime": 43.4899,
|
| 442 |
+
"eval_samples_per_second": 6.898,
|
| 443 |
+
"eval_steps_per_second": 0.23,
|
| 444 |
+
"step": 87
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.9574468085106383,
|
| 448 |
+
"grad_norm": 97.51951599121094,
|
| 449 |
+
"learning_rate": 3.2259592606059844e-06,
|
| 450 |
+
"loss": 0.8928,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.9574468085106383,
|
| 455 |
+
"eval_loss": 0.8567631244659424,
|
| 456 |
+
"eval_runtime": 43.4864,
|
| 457 |
+
"eval_samples_per_second": 6.899,
|
| 458 |
+
"eval_steps_per_second": 0.23,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.9893617021276596,
|
| 463 |
+
"grad_norm": 60.12514114379883,
|
| 464 |
+
"learning_rate": 3.1755536471590163e-06,
|
| 465 |
+
"loss": 0.7314,
|
| 466 |
+
"step": 93
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.9893617021276596,
|
| 470 |
+
"eval_loss": 0.8565493822097778,
|
| 471 |
+
"eval_runtime": 22.6087,
|
| 472 |
+
"eval_samples_per_second": 13.269,
|
| 473 |
+
"eval_steps_per_second": 0.442,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.0212765957446808,
|
| 478 |
+
"grad_norm": 57.255775451660156,
|
| 479 |
+
"learning_rate": 3.1251480337120472e-06,
|
| 480 |
+
"loss": 0.7931,
|
| 481 |
+
"step": 96
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.0212765957446808,
|
| 485 |
+
"eval_loss": 0.8531547784805298,
|
| 486 |
+
"eval_runtime": 23.9019,
|
| 487 |
+
"eval_samples_per_second": 12.551,
|
| 488 |
+
"eval_steps_per_second": 0.418,
|
| 489 |
+
"step": 96
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.053191489361702,
|
| 493 |
+
"grad_norm": 43.00119400024414,
|
| 494 |
+
"learning_rate": 3.074742420265079e-06,
|
| 495 |
+
"loss": 0.3847,
|
| 496 |
+
"step": 99
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.053191489361702,
|
| 500 |
+
"eval_loss": 0.84489506483078,
|
| 501 |
+
"eval_runtime": 23.0798,
|
| 502 |
+
"eval_samples_per_second": 12.998,
|
| 503 |
+
"eval_steps_per_second": 0.433,
|
| 504 |
+
"step": 99
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.0851063829787233,
|
| 508 |
+
"grad_norm": 21.35872459411621,
|
| 509 |
+
"learning_rate": 3.024336806818111e-06,
|
| 510 |
+
"loss": 0.252,
|
| 511 |
+
"step": 102
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.0851063829787233,
|
| 515 |
+
"eval_loss": 0.8377478122711182,
|
| 516 |
+
"eval_runtime": 23.6666,
|
| 517 |
+
"eval_samples_per_second": 12.676,
|
| 518 |
+
"eval_steps_per_second": 0.423,
|
| 519 |
+
"step": 102
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.1170212765957448,
|
| 523 |
+
"grad_norm": 42.683170318603516,
|
| 524 |
+
"learning_rate": 2.973931193371142e-06,
|
| 525 |
+
"loss": 0.2581,
|
| 526 |
+
"step": 105
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.1170212765957448,
|
| 530 |
+
"eval_loss": 0.832615315914154,
|
| 531 |
+
"eval_runtime": 22.1568,
|
| 532 |
+
"eval_samples_per_second": 13.54,
|
| 533 |
+
"eval_steps_per_second": 0.451,
|
| 534 |
+
"step": 105
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.148936170212766,
|
| 538 |
+
"grad_norm": 36.07487487792969,
|
| 539 |
+
"learning_rate": 2.9235255799241737e-06,
|
| 540 |
+
"loss": 0.272,
|
| 541 |
+
"step": 108
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.148936170212766,
|
| 545 |
+
"eval_loss": 0.8290462493896484,
|
| 546 |
+
"eval_runtime": 23.4484,
|
| 547 |
+
"eval_samples_per_second": 12.794,
|
| 548 |
+
"eval_steps_per_second": 0.426,
|
| 549 |
+
"step": 108
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.1808510638297873,
|
| 553 |
+
"grad_norm": 25.169939041137695,
|
| 554 |
+
"learning_rate": 2.873119966477205e-06,
|
| 555 |
+
"loss": 0.3822,
|
| 556 |
+
"step": 111
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.1808510638297873,
|
| 560 |
+
"eval_loss": 0.8273450136184692,
|
| 561 |
+
"eval_runtime": 22.2076,
|
| 562 |
+
"eval_samples_per_second": 13.509,
|
| 563 |
+
"eval_steps_per_second": 0.45,
|
| 564 |
+
"step": 111
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.2127659574468086,
|
| 568 |
+
"grad_norm": 43.500083923339844,
|
| 569 |
+
"learning_rate": 2.8227143530302365e-06,
|
| 570 |
+
"loss": 0.3555,
|
| 571 |
+
"step": 114
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.2127659574468086,
|
| 575 |
+
"eval_loss": 0.825173020362854,
|
| 576 |
+
"eval_runtime": 23.9364,
|
| 577 |
+
"eval_samples_per_second": 12.533,
|
| 578 |
+
"eval_steps_per_second": 0.418,
|
| 579 |
+
"step": 114
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.2446808510638299,
|
| 583 |
+
"grad_norm": 47.19260787963867,
|
| 584 |
+
"learning_rate": 2.772308739583268e-06,
|
| 585 |
+
"loss": 0.2687,
|
| 586 |
+
"step": 117
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.2446808510638299,
|
| 590 |
+
"eval_loss": 0.8255329132080078,
|
| 591 |
+
"eval_runtime": 22.128,
|
| 592 |
+
"eval_samples_per_second": 13.558,
|
| 593 |
+
"eval_steps_per_second": 0.452,
|
| 594 |
+
"step": 117
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.2765957446808511,
|
| 598 |
+
"grad_norm": 47.747982025146484,
|
| 599 |
+
"learning_rate": 2.7219031261362997e-06,
|
| 600 |
+
"loss": 0.2614,
|
| 601 |
+
"step": 120
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.2765957446808511,
|
| 605 |
+
"eval_loss": 0.8268000483512878,
|
| 606 |
+
"eval_runtime": 23.832,
|
| 607 |
+
"eval_samples_per_second": 12.588,
|
| 608 |
+
"eval_steps_per_second": 0.42,
|
| 609 |
+
"step": 120
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.3085106382978724,
|
| 613 |
+
"grad_norm": 52.21699142456055,
|
| 614 |
+
"learning_rate": 2.671497512689331e-06,
|
| 615 |
+
"loss": 0.3726,
|
| 616 |
+
"step": 123
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.3085106382978724,
|
| 620 |
+
"eval_loss": 0.8281159400939941,
|
| 621 |
+
"eval_runtime": 22.7023,
|
| 622 |
+
"eval_samples_per_second": 13.215,
|
| 623 |
+
"eval_steps_per_second": 0.44,
|
| 624 |
+
"step": 123
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.3404255319148937,
|
| 628 |
+
"grad_norm": 43.84182357788086,
|
| 629 |
+
"learning_rate": 2.6210918992423625e-06,
|
| 630 |
+
"loss": 0.2081,
|
| 631 |
+
"step": 126
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.3404255319148937,
|
| 635 |
+
"eval_loss": 0.8298842310905457,
|
| 636 |
+
"eval_runtime": 23.5811,
|
| 637 |
+
"eval_samples_per_second": 12.722,
|
| 638 |
+
"eval_steps_per_second": 0.424,
|
| 639 |
+
"step": 126
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.372340425531915,
|
| 643 |
+
"grad_norm": 35.47488021850586,
|
| 644 |
+
"learning_rate": 2.570686285795394e-06,
|
| 645 |
+
"loss": 0.2363,
|
| 646 |
+
"step": 129
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.372340425531915,
|
| 650 |
+
"eval_loss": 0.8358010053634644,
|
| 651 |
+
"eval_runtime": 22.1111,
|
| 652 |
+
"eval_samples_per_second": 13.568,
|
| 653 |
+
"eval_steps_per_second": 0.452,
|
| 654 |
+
"step": 129
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.4042553191489362,
|
| 658 |
+
"grad_norm": 47.503395080566406,
|
| 659 |
+
"learning_rate": 2.5202806723484253e-06,
|
| 660 |
+
"loss": 0.3497,
|
| 661 |
+
"step": 132
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.4042553191489362,
|
| 665 |
+
"eval_loss": 0.8382316827774048,
|
| 666 |
+
"eval_runtime": 23.6168,
|
| 667 |
+
"eval_samples_per_second": 12.703,
|
| 668 |
+
"eval_steps_per_second": 0.423,
|
| 669 |
+
"step": 132
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.4361702127659575,
|
| 673 |
+
"grad_norm": 43.59933853149414,
|
| 674 |
+
"learning_rate": 2.469875058901457e-06,
|
| 675 |
+
"loss": 0.2927,
|
| 676 |
+
"step": 135
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.4361702127659575,
|
| 680 |
+
"eval_loss": 0.8399573564529419,
|
| 681 |
+
"eval_runtime": 22.1313,
|
| 682 |
+
"eval_samples_per_second": 13.555,
|
| 683 |
+
"eval_steps_per_second": 0.452,
|
| 684 |
+
"step": 135
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.4680851063829787,
|
| 688 |
+
"grad_norm": 46.75539779663086,
|
| 689 |
+
"learning_rate": 2.419469445454488e-06,
|
| 690 |
+
"loss": 0.3142,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.4680851063829787,
|
| 695 |
+
"eval_loss": 0.841060996055603,
|
| 696 |
+
"eval_runtime": 24.0437,
|
| 697 |
+
"eval_samples_per_second": 12.477,
|
| 698 |
+
"eval_steps_per_second": 0.416,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.5,
|
| 703 |
+
"grad_norm": 47.08267593383789,
|
| 704 |
+
"learning_rate": 2.36906383200752e-06,
|
| 705 |
+
"loss": 0.2303,
|
| 706 |
+
"step": 141
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.5,
|
| 710 |
+
"eval_loss": 0.8422343730926514,
|
| 711 |
+
"eval_runtime": 21.8892,
|
| 712 |
+
"eval_samples_per_second": 13.705,
|
| 713 |
+
"eval_steps_per_second": 0.457,
|
| 714 |
+
"step": 141
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.5319148936170213,
|
| 718 |
+
"grad_norm": 59.37859344482422,
|
| 719 |
+
"learning_rate": 2.3186582185605513e-06,
|
| 720 |
+
"loss": 0.2628,
|
| 721 |
+
"step": 144
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.5319148936170213,
|
| 725 |
+
"eval_loss": 0.843423068523407,
|
| 726 |
+
"eval_runtime": 23.5581,
|
| 727 |
+
"eval_samples_per_second": 12.735,
|
| 728 |
+
"eval_steps_per_second": 0.424,
|
| 729 |
+
"step": 144
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.5638297872340425,
|
| 733 |
+
"grad_norm": 66.62377166748047,
|
| 734 |
+
"learning_rate": 2.268252605113583e-06,
|
| 735 |
+
"loss": 0.2734,
|
| 736 |
+
"step": 147
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.5638297872340425,
|
| 740 |
+
"eval_loss": 0.8458875417709351,
|
| 741 |
+
"eval_runtime": 22.7309,
|
| 742 |
+
"eval_samples_per_second": 13.198,
|
| 743 |
+
"eval_steps_per_second": 0.44,
|
| 744 |
+
"step": 147
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5957446808510638,
|
| 748 |
+
"grad_norm": 65.94501495361328,
|
| 749 |
+
"learning_rate": 2.2178469916666146e-06,
|
| 750 |
+
"loss": 0.2989,
|
| 751 |
+
"step": 150
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5957446808510638,
|
| 755 |
+
"eval_loss": 0.8469556570053101,
|
| 756 |
+
"eval_runtime": 23.6111,
|
| 757 |
+
"eval_samples_per_second": 12.706,
|
| 758 |
+
"eval_steps_per_second": 0.424,
|
| 759 |
+
"step": 150
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.627659574468085,
|
| 763 |
+
"grad_norm": 99.2269287109375,
|
| 764 |
+
"learning_rate": 2.167441378219646e-06,
|
| 765 |
+
"loss": 0.3895,
|
| 766 |
+
"step": 153
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.627659574468085,
|
| 770 |
+
"eval_loss": 0.8473237752914429,
|
| 771 |
+
"eval_runtime": 22.2962,
|
| 772 |
+
"eval_samples_per_second": 13.455,
|
| 773 |
+
"eval_steps_per_second": 0.449,
|
| 774 |
+
"step": 153
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.6595744680851063,
|
| 778 |
+
"grad_norm": 45.91320037841797,
|
| 779 |
+
"learning_rate": 2.1170357647726774e-06,
|
| 780 |
+
"loss": 0.3273,
|
| 781 |
+
"step": 156
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.6595744680851063,
|
| 785 |
+
"eval_loss": 0.8420724868774414,
|
| 786 |
+
"eval_runtime": 24.0122,
|
| 787 |
+
"eval_samples_per_second": 12.494,
|
| 788 |
+
"eval_steps_per_second": 0.416,
|
| 789 |
+
"step": 156
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.6914893617021276,
|
| 793 |
+
"grad_norm": 52.12400817871094,
|
| 794 |
+
"learning_rate": 2.0666301513257088e-06,
|
| 795 |
+
"loss": 0.2508,
|
| 796 |
+
"step": 159
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.6914893617021276,
|
| 800 |
+
"eval_loss": 0.8369884490966797,
|
| 801 |
+
"eval_runtime": 22.131,
|
| 802 |
+
"eval_samples_per_second": 13.556,
|
| 803 |
+
"eval_steps_per_second": 0.452,
|
| 804 |
+
"step": 159
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.7234042553191489,
|
| 808 |
+
"grad_norm": 59.420372009277344,
|
| 809 |
+
"learning_rate": 2.0162245378787406e-06,
|
| 810 |
+
"loss": 0.2143,
|
| 811 |
+
"step": 162
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.7234042553191489,
|
| 815 |
+
"eval_loss": 0.8358878493309021,
|
| 816 |
+
"eval_runtime": 23.6554,
|
| 817 |
+
"eval_samples_per_second": 12.682,
|
| 818 |
+
"eval_steps_per_second": 0.423,
|
| 819 |
+
"step": 162
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.7553191489361701,
|
| 823 |
+
"grad_norm": 53.903350830078125,
|
| 824 |
+
"learning_rate": 1.965818924431772e-06,
|
| 825 |
+
"loss": 0.2337,
|
| 826 |
+
"step": 165
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.7553191489361701,
|
| 830 |
+
"eval_loss": 0.8342965841293335,
|
| 831 |
+
"eval_runtime": 22.1781,
|
| 832 |
+
"eval_samples_per_second": 13.527,
|
| 833 |
+
"eval_steps_per_second": 0.451,
|
| 834 |
+
"step": 165
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.7872340425531914,
|
| 838 |
+
"grad_norm": 37.46884536743164,
|
| 839 |
+
"learning_rate": 1.9154133109848034e-06,
|
| 840 |
+
"loss": 0.1867,
|
| 841 |
+
"step": 168
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.7872340425531914,
|
| 845 |
+
"eval_loss": 0.8319395184516907,
|
| 846 |
+
"eval_runtime": 23.6724,
|
| 847 |
+
"eval_samples_per_second": 12.673,
|
| 848 |
+
"eval_steps_per_second": 0.422,
|
| 849 |
+
"step": 168
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.8191489361702127,
|
| 853 |
+
"grad_norm": 73.817138671875,
|
| 854 |
+
"learning_rate": 1.865007697537835e-06,
|
| 855 |
+
"loss": 0.3836,
|
| 856 |
+
"step": 171
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.8191489361702127,
|
| 860 |
+
"eval_loss": 0.8294512033462524,
|
| 861 |
+
"eval_runtime": 22.7496,
|
| 862 |
+
"eval_samples_per_second": 13.187,
|
| 863 |
+
"eval_steps_per_second": 0.44,
|
| 864 |
+
"step": 171
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.851063829787234,
|
| 868 |
+
"grad_norm": 66.78804016113281,
|
| 869 |
+
"learning_rate": 1.8146020840908664e-06,
|
| 870 |
+
"loss": 0.2939,
|
| 871 |
+
"step": 174
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.851063829787234,
|
| 875 |
+
"eval_loss": 0.8301381468772888,
|
| 876 |
+
"eval_runtime": 23.7921,
|
| 877 |
+
"eval_samples_per_second": 12.609,
|
| 878 |
+
"eval_steps_per_second": 0.42,
|
| 879 |
+
"step": 174
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.8829787234042552,
|
| 883 |
+
"grad_norm": 27.3295841217041,
|
| 884 |
+
"learning_rate": 1.7641964706438978e-06,
|
| 885 |
+
"loss": 0.2702,
|
| 886 |
+
"step": 177
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.8829787234042552,
|
| 890 |
+
"eval_loss": 0.8287379741668701,
|
| 891 |
+
"eval_runtime": 22.3208,
|
| 892 |
+
"eval_samples_per_second": 13.44,
|
| 893 |
+
"eval_steps_per_second": 0.448,
|
| 894 |
+
"step": 177
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.9148936170212765,
|
| 898 |
+
"grad_norm": 34.200496673583984,
|
| 899 |
+
"learning_rate": 1.7137908571969294e-06,
|
| 900 |
+
"loss": 0.1949,
|
| 901 |
+
"step": 180
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.9148936170212765,
|
| 905 |
+
"eval_loss": 0.827938437461853,
|
| 906 |
+
"eval_runtime": 23.7637,
|
| 907 |
+
"eval_samples_per_second": 12.624,
|
| 908 |
+
"eval_steps_per_second": 0.421,
|
| 909 |
+
"step": 180
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.9468085106382977,
|
| 913 |
+
"grad_norm": 57.093162536621094,
|
| 914 |
+
"learning_rate": 1.6633852437499608e-06,
|
| 915 |
+
"loss": 0.2186,
|
| 916 |
+
"step": 183
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.9468085106382977,
|
| 920 |
+
"eval_loss": 0.8297010064125061,
|
| 921 |
+
"eval_runtime": 22.4348,
|
| 922 |
+
"eval_samples_per_second": 13.372,
|
| 923 |
+
"eval_steps_per_second": 0.446,
|
| 924 |
+
"step": 183
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.978723404255319,
|
| 928 |
+
"grad_norm": 54.119667053222656,
|
| 929 |
+
"learning_rate": 1.6129796303029922e-06,
|
| 930 |
+
"loss": 0.2609,
|
| 931 |
+
"step": 186
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.978723404255319,
|
| 935 |
+
"eval_loss": 0.8327953219413757,
|
| 936 |
+
"eval_runtime": 24.1101,
|
| 937 |
+
"eval_samples_per_second": 12.443,
|
| 938 |
+
"eval_steps_per_second": 0.415,
|
| 939 |
+
"step": 186
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.0106382978723403,
|
| 943 |
+
"grad_norm": 34.58624267578125,
|
| 944 |
+
"learning_rate": 1.5625740168560236e-06,
|
| 945 |
+
"loss": 0.1952,
|
| 946 |
+
"step": 189
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.0106382978723403,
|
| 950 |
+
"eval_loss": 0.8341763615608215,
|
| 951 |
+
"eval_runtime": 45.5245,
|
| 952 |
+
"eval_samples_per_second": 6.59,
|
| 953 |
+
"eval_steps_per_second": 0.22,
|
| 954 |
+
"step": 189
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.0425531914893615,
|
| 958 |
+
"grad_norm": 35.64149856567383,
|
| 959 |
+
"learning_rate": 1.5121684034090554e-06,
|
| 960 |
+
"loss": 0.0993,
|
| 961 |
+
"step": 192
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.0425531914893615,
|
| 965 |
+
"eval_loss": 0.837165355682373,
|
| 966 |
+
"eval_runtime": 13.0218,
|
| 967 |
+
"eval_samples_per_second": 23.038,
|
| 968 |
+
"eval_steps_per_second": 0.768,
|
| 969 |
+
"step": 192
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.074468085106383,
|
| 973 |
+
"grad_norm": 50.38720703125,
|
| 974 |
+
"learning_rate": 1.4617627899620868e-06,
|
| 975 |
+
"loss": 0.1409,
|
| 976 |
+
"step": 195
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.074468085106383,
|
| 980 |
+
"eval_loss": 0.8386108875274658,
|
| 981 |
+
"eval_runtime": 32.929,
|
| 982 |
+
"eval_samples_per_second": 9.11,
|
| 983 |
+
"eval_steps_per_second": 0.304,
|
| 984 |
+
"step": 195
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.106382978723404,
|
| 988 |
+
"grad_norm": 28.053754806518555,
|
| 989 |
+
"learning_rate": 1.4113571765151182e-06,
|
| 990 |
+
"loss": 0.0522,
|
| 991 |
+
"step": 198
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.106382978723404,
|
| 995 |
+
"eval_loss": 0.8413487076759338,
|
| 996 |
+
"eval_runtime": 13.422,
|
| 997 |
+
"eval_samples_per_second": 22.351,
|
| 998 |
+
"eval_steps_per_second": 0.745,
|
| 999 |
+
"step": 198
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.1382978723404253,
|
| 1003 |
+
"grad_norm": 48.99291229248047,
|
| 1004 |
+
"learning_rate": 1.3609515630681499e-06,
|
| 1005 |
+
"loss": 0.123,
|
| 1006 |
+
"step": 201
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.1382978723404253,
|
| 1010 |
+
"eval_loss": 0.8437539339065552,
|
| 1011 |
+
"eval_runtime": 32.9133,
|
| 1012 |
+
"eval_samples_per_second": 9.115,
|
| 1013 |
+
"eval_steps_per_second": 0.304,
|
| 1014 |
+
"step": 201
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.1702127659574466,
|
| 1018 |
+
"grad_norm": 30.540855407714844,
|
| 1019 |
+
"learning_rate": 1.3105459496211813e-06,
|
| 1020 |
+
"loss": 0.0946,
|
| 1021 |
+
"step": 204
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.1702127659574466,
|
| 1025 |
+
"eval_loss": 0.8469984531402588,
|
| 1026 |
+
"eval_runtime": 12.8212,
|
| 1027 |
+
"eval_samples_per_second": 23.399,
|
| 1028 |
+
"eval_steps_per_second": 0.78,
|
| 1029 |
+
"step": 204
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.202127659574468,
|
| 1033 |
+
"grad_norm": 65.50384521484375,
|
| 1034 |
+
"learning_rate": 1.2601403361742127e-06,
|
| 1035 |
+
"loss": 0.2346,
|
| 1036 |
+
"step": 207
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 2.202127659574468,
|
| 1040 |
+
"eval_loss": 0.8491196036338806,
|
| 1041 |
+
"eval_runtime": 33.0116,
|
| 1042 |
+
"eval_samples_per_second": 9.088,
|
| 1043 |
+
"eval_steps_per_second": 0.303,
|
| 1044 |
+
"step": 207
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.2340425531914896,
|
| 1048 |
+
"grad_norm": 37.9770622253418,
|
| 1049 |
+
"learning_rate": 1.209734722727244e-06,
|
| 1050 |
+
"loss": 0.1445,
|
| 1051 |
+
"step": 210
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.2340425531914896,
|
| 1055 |
+
"eval_loss": 0.8509886860847473,
|
| 1056 |
+
"eval_runtime": 12.9443,
|
| 1057 |
+
"eval_samples_per_second": 23.176,
|
| 1058 |
+
"eval_steps_per_second": 0.773,
|
| 1059 |
+
"step": 210
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.2659574468085104,
|
| 1063 |
+
"grad_norm": 34.36880111694336,
|
| 1064 |
+
"learning_rate": 1.1593291092802757e-06,
|
| 1065 |
+
"loss": 0.1112,
|
| 1066 |
+
"step": 213
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.2659574468085104,
|
| 1070 |
+
"eval_loss": 0.8533729910850525,
|
| 1071 |
+
"eval_runtime": 33.1181,
|
| 1072 |
+
"eval_samples_per_second": 9.058,
|
| 1073 |
+
"eval_steps_per_second": 0.302,
|
| 1074 |
+
"step": 213
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.297872340425532,
|
| 1078 |
+
"grad_norm": 45.28392028808594,
|
| 1079 |
+
"learning_rate": 1.1089234958333073e-06,
|
| 1080 |
+
"loss": 0.113,
|
| 1081 |
+
"step": 216
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.297872340425532,
|
| 1085 |
+
"eval_loss": 0.8565312623977661,
|
| 1086 |
+
"eval_runtime": 12.9159,
|
| 1087 |
+
"eval_samples_per_second": 23.227,
|
| 1088 |
+
"eval_steps_per_second": 0.774,
|
| 1089 |
+
"step": 216
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.329787234042553,
|
| 1093 |
+
"grad_norm": 24.961444854736328,
|
| 1094 |
+
"learning_rate": 1.0585178823863387e-06,
|
| 1095 |
+
"loss": 0.0929,
|
| 1096 |
+
"step": 219
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.329787234042553,
|
| 1100 |
+
"eval_loss": 0.859375,
|
| 1101 |
+
"eval_runtime": 32.6853,
|
| 1102 |
+
"eval_samples_per_second": 9.178,
|
| 1103 |
+
"eval_steps_per_second": 0.306,
|
| 1104 |
+
"step": 219
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.3617021276595747,
|
| 1108 |
+
"grad_norm": 22.85188865661621,
|
| 1109 |
+
"learning_rate": 1.0081122689393703e-06,
|
| 1110 |
+
"loss": 0.1108,
|
| 1111 |
+
"step": 222
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.3617021276595747,
|
| 1115 |
+
"eval_loss": 0.8612162470817566,
|
| 1116 |
+
"eval_runtime": 13.8881,
|
| 1117 |
+
"eval_samples_per_second": 21.601,
|
| 1118 |
+
"eval_steps_per_second": 0.72,
|
| 1119 |
+
"step": 222
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.393617021276596,
|
| 1123 |
+
"grad_norm": 20.546833038330078,
|
| 1124 |
+
"learning_rate": 9.577066554924017e-07,
|
| 1125 |
+
"loss": 0.092,
|
| 1126 |
+
"step": 225
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.393617021276596,
|
| 1130 |
+
"eval_loss": 0.8626397848129272,
|
| 1131 |
+
"eval_runtime": 32.9393,
|
| 1132 |
+
"eval_samples_per_second": 9.108,
|
| 1133 |
+
"eval_steps_per_second": 0.304,
|
| 1134 |
+
"step": 225
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.425531914893617,
|
| 1138 |
+
"grad_norm": 36.019561767578125,
|
| 1139 |
+
"learning_rate": 9.073010420454332e-07,
|
| 1140 |
+
"loss": 0.0641,
|
| 1141 |
+
"step": 228
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.425531914893617,
|
| 1145 |
+
"eval_loss": 0.8644223809242249,
|
| 1146 |
+
"eval_runtime": 12.991,
|
| 1147 |
+
"eval_samples_per_second": 23.093,
|
| 1148 |
+
"eval_steps_per_second": 0.77,
|
| 1149 |
+
"step": 228
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.4574468085106385,
|
| 1153 |
+
"grad_norm": 15.907193183898926,
|
| 1154 |
+
"learning_rate": 8.568954285984647e-07,
|
| 1155 |
+
"loss": 0.0437,
|
| 1156 |
+
"step": 231
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.4574468085106385,
|
| 1160 |
+
"eval_loss": 0.8656131029129028,
|
| 1161 |
+
"eval_runtime": 33.0386,
|
| 1162 |
+
"eval_samples_per_second": 9.08,
|
| 1163 |
+
"eval_steps_per_second": 0.303,
|
| 1164 |
+
"step": 231
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.4893617021276597,
|
| 1168 |
+
"grad_norm": 30.25502586364746,
|
| 1169 |
+
"learning_rate": 8.064898151514961e-07,
|
| 1170 |
+
"loss": 0.097,
|
| 1171 |
+
"step": 234
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.4893617021276597,
|
| 1175 |
+
"eval_loss": 0.8662587404251099,
|
| 1176 |
+
"eval_runtime": 12.9969,
|
| 1177 |
+
"eval_samples_per_second": 23.082,
|
| 1178 |
+
"eval_steps_per_second": 0.769,
|
| 1179 |
+
"step": 234
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.521276595744681,
|
| 1183 |
+
"grad_norm": 34.13824462890625,
|
| 1184 |
+
"learning_rate": 7.560842017045277e-07,
|
| 1185 |
+
"loss": 0.1028,
|
| 1186 |
+
"step": 237
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.521276595744681,
|
| 1190 |
+
"eval_loss": 0.8667454123497009,
|
| 1191 |
+
"eval_runtime": 33.0579,
|
| 1192 |
+
"eval_samples_per_second": 9.075,
|
| 1193 |
+
"eval_steps_per_second": 0.302,
|
| 1194 |
+
"step": 237
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.5531914893617023,
|
| 1198 |
+
"grad_norm": 47.30521011352539,
|
| 1199 |
+
"learning_rate": 7.056785882575591e-07,
|
| 1200 |
+
"loss": 0.1503,
|
| 1201 |
+
"step": 240
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.5531914893617023,
|
| 1205 |
+
"eval_loss": 0.8677744269371033,
|
| 1206 |
+
"eval_runtime": 12.8958,
|
| 1207 |
+
"eval_samples_per_second": 23.263,
|
| 1208 |
+
"eval_steps_per_second": 0.775,
|
| 1209 |
+
"step": 240
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.5851063829787235,
|
| 1213 |
+
"grad_norm": 40.989444732666016,
|
| 1214 |
+
"learning_rate": 6.552729748105906e-07,
|
| 1215 |
+
"loss": 0.1286,
|
| 1216 |
+
"step": 243
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.5851063829787235,
|
| 1220 |
+
"eval_loss": 0.8686262965202332,
|
| 1221 |
+
"eval_runtime": 33.1611,
|
| 1222 |
+
"eval_samples_per_second": 9.047,
|
| 1223 |
+
"eval_steps_per_second": 0.302,
|
| 1224 |
+
"step": 243
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.617021276595745,
|
| 1228 |
+
"grad_norm": 58.63330841064453,
|
| 1229 |
+
"learning_rate": 6.04867361363622e-07,
|
| 1230 |
+
"loss": 0.1938,
|
| 1231 |
+
"step": 246
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.617021276595745,
|
| 1235 |
+
"eval_loss": 0.8695897459983826,
|
| 1236 |
+
"eval_runtime": 13.2572,
|
| 1237 |
+
"eval_samples_per_second": 22.629,
|
| 1238 |
+
"eval_steps_per_second": 0.754,
|
| 1239 |
+
"step": 246
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.648936170212766,
|
| 1243 |
+
"grad_norm": 25.59177017211914,
|
| 1244 |
+
"learning_rate": 5.544617479166536e-07,
|
| 1245 |
+
"loss": 0.0655,
|
| 1246 |
+
"step": 249
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 2.648936170212766,
|
| 1250 |
+
"eval_loss": 0.8699460029602051,
|
| 1251 |
+
"eval_runtime": 33.2452,
|
| 1252 |
+
"eval_samples_per_second": 9.024,
|
| 1253 |
+
"eval_steps_per_second": 0.301,
|
| 1254 |
+
"step": 249
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.6808510638297873,
|
| 1258 |
+
"grad_norm": 10.76020622253418,
|
| 1259 |
+
"learning_rate": 5.040561344696851e-07,
|
| 1260 |
+
"loss": 0.0638,
|
| 1261 |
+
"step": 252
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.6808510638297873,
|
| 1265 |
+
"eval_loss": 0.8698618412017822,
|
| 1266 |
+
"eval_runtime": 13.4624,
|
| 1267 |
+
"eval_samples_per_second": 22.284,
|
| 1268 |
+
"eval_steps_per_second": 0.743,
|
| 1269 |
+
"step": 252
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.7127659574468086,
|
| 1273 |
+
"grad_norm": 14.23372745513916,
|
| 1274 |
+
"learning_rate": 4.536505210227166e-07,
|
| 1275 |
+
"loss": 0.04,
|
| 1276 |
+
"step": 255
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.7127659574468086,
|
| 1280 |
+
"eval_loss": 0.8700897097587585,
|
| 1281 |
+
"eval_runtime": 33.0408,
|
| 1282 |
+
"eval_samples_per_second": 9.08,
|
| 1283 |
+
"eval_steps_per_second": 0.303,
|
| 1284 |
+
"step": 255
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.74468085106383,
|
| 1288 |
+
"grad_norm": 54.65508270263672,
|
| 1289 |
+
"learning_rate": 4.0324490757574806e-07,
|
| 1290 |
+
"loss": 0.158,
|
| 1291 |
+
"step": 258
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.74468085106383,
|
| 1295 |
+
"eval_loss": 0.8706519603729248,
|
| 1296 |
+
"eval_runtime": 13.0406,
|
| 1297 |
+
"eval_samples_per_second": 23.005,
|
| 1298 |
+
"eval_steps_per_second": 0.767,
|
| 1299 |
+
"step": 258
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.776595744680851,
|
| 1303 |
+
"grad_norm": 36.574066162109375,
|
| 1304 |
+
"learning_rate": 3.5283929412877956e-07,
|
| 1305 |
+
"loss": 0.0951,
|
| 1306 |
+
"step": 261
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.776595744680851,
|
| 1310 |
+
"eval_loss": 0.871029794216156,
|
| 1311 |
+
"eval_runtime": 32.8987,
|
| 1312 |
+
"eval_samples_per_second": 9.119,
|
| 1313 |
+
"eval_steps_per_second": 0.304,
|
| 1314 |
+
"step": 261
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.8085106382978724,
|
| 1318 |
+
"grad_norm": 32.9112434387207,
|
| 1319 |
+
"learning_rate": 3.02433680681811e-07,
|
| 1320 |
+
"loss": 0.0788,
|
| 1321 |
+
"step": 264
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.8085106382978724,
|
| 1325 |
+
"eval_loss": 0.871411144733429,
|
| 1326 |
+
"eval_runtime": 12.964,
|
| 1327 |
+
"eval_samples_per_second": 23.141,
|
| 1328 |
+
"eval_steps_per_second": 0.771,
|
| 1329 |
+
"step": 264
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.8404255319148937,
|
| 1333 |
+
"grad_norm": 26.687891006469727,
|
| 1334 |
+
"learning_rate": 2.520280672348426e-07,
|
| 1335 |
+
"loss": 0.0429,
|
| 1336 |
+
"step": 267
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.8404255319148937,
|
| 1340 |
+
"eval_loss": 0.8717812299728394,
|
| 1341 |
+
"eval_runtime": 32.9027,
|
| 1342 |
+
"eval_samples_per_second": 9.118,
|
| 1343 |
+
"eval_steps_per_second": 0.304,
|
| 1344 |
+
"step": 267
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.872340425531915,
|
| 1348 |
+
"grad_norm": 25.479427337646484,
|
| 1349 |
+
"learning_rate": 2.0162245378787403e-07,
|
| 1350 |
+
"loss": 0.0809,
|
| 1351 |
+
"step": 270
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.872340425531915,
|
| 1355 |
+
"eval_loss": 0.8716564178466797,
|
| 1356 |
+
"eval_runtime": 12.9971,
|
| 1357 |
+
"eval_samples_per_second": 23.082,
|
| 1358 |
+
"eval_steps_per_second": 0.769,
|
| 1359 |
+
"step": 270
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.904255319148936,
|
| 1363 |
+
"grad_norm": 14.731446266174316,
|
| 1364 |
+
"learning_rate": 1.512168403409055e-07,
|
| 1365 |
+
"loss": 0.0942,
|
| 1366 |
+
"step": 273
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 2.904255319148936,
|
| 1370 |
+
"eval_loss": 0.8718379735946655,
|
| 1371 |
+
"eval_runtime": 33.0136,
|
| 1372 |
+
"eval_samples_per_second": 9.087,
|
| 1373 |
+
"eval_steps_per_second": 0.303,
|
| 1374 |
+
"step": 273
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.9361702127659575,
|
| 1378 |
+
"grad_norm": 23.23249053955078,
|
| 1379 |
+
"learning_rate": 1.0081122689393701e-07,
|
| 1380 |
+
"loss": 0.1419,
|
| 1381 |
+
"step": 276
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.9361702127659575,
|
| 1385 |
+
"eval_loss": 0.8720559477806091,
|
| 1386 |
+
"eval_runtime": 13.6301,
|
| 1387 |
+
"eval_samples_per_second": 22.01,
|
| 1388 |
+
"eval_steps_per_second": 0.734,
|
| 1389 |
+
"step": 276
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.9680851063829787,
|
| 1393 |
+
"grad_norm": 42.01313400268555,
|
| 1394 |
+
"learning_rate": 5.040561344696851e-08,
|
| 1395 |
+
"loss": 0.1036,
|
| 1396 |
+
"step": 279
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.9680851063829787,
|
| 1400 |
+
"eval_loss": 0.8721166253089905,
|
| 1401 |
+
"eval_runtime": 33.0448,
|
| 1402 |
+
"eval_samples_per_second": 9.079,
|
| 1403 |
+
"eval_steps_per_second": 0.303,
|
| 1404 |
+
"step": 279
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 3.0,
|
| 1408 |
+
"grad_norm": 37.830604553222656,
|
| 1409 |
+
"learning_rate": 0.0,
|
| 1410 |
+
"loss": 0.0854,
|
| 1411 |
+
"step": 282
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 3.0,
|
| 1415 |
+
"eval_loss": 0.8720741868019104,
|
| 1416 |
+
"eval_runtime": 12.8271,
|
| 1417 |
+
"eval_samples_per_second": 23.388,
|
| 1418 |
+
"eval_steps_per_second": 0.78,
|
| 1419 |
+
"step": 282
|
| 1420 |
+
}
|
| 1421 |
+
],
|
| 1422 |
+
"logging_steps": 3,
|
| 1423 |
+
"max_steps": 282,
|
| 1424 |
+
"num_input_tokens_seen": 0,
|
| 1425 |
+
"num_train_epochs": 3,
|
| 1426 |
+
"save_steps": 500,
|
| 1427 |
+
"stateful_callbacks": {
|
| 1428 |
+
"TrainerControl": {
|
| 1429 |
+
"args": {
|
| 1430 |
+
"should_epoch_stop": false,
|
| 1431 |
+
"should_evaluate": false,
|
| 1432 |
+
"should_log": false,
|
| 1433 |
+
"should_save": true,
|
| 1434 |
+
"should_training_stop": true
|
| 1435 |
+
},
|
| 1436 |
+
"attributes": {}
|
| 1437 |
+
}
|
| 1438 |
+
},
|
| 1439 |
+
"total_flos": 523328480700102.0,
|
| 1440 |
+
"train_batch_size": 32,
|
| 1441 |
+
"trial_name": null,
|
| 1442 |
+
"trial_params": {
|
| 1443 |
+
"_wandb": {},
|
| 1444 |
+
"assignments": {},
|
| 1445 |
+
"decay": 0.01,
|
| 1446 |
+
"learning_rate": 4.73812766401504e-06,
|
| 1447 |
+
"metric": "eval/loss",
|
| 1448 |
+
"per_device_train_batch_size": 32
|
| 1449 |
+
}
|
| 1450 |
+
}
|
run-nk1o8cuk/checkpoint-282/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2de738072ec265745ad8ca14cff5e9c8d4d119457b017a3a3ec0e72524183c6b
|
| 3 |
+
size 5112
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2de738072ec265745ad8ca14cff5e9c8d4d119457b017a3a3ec0e72524183c6b
|
| 3 |
size 5112
|