Training in progress, step 282
Browse files- config.json +1 -1
- model.safetensors +1 -1
- run-uvutz7m4/checkpoint-282/config.json +22 -0
- run-uvutz7m4/checkpoint-282/model.safetensors +3 -0
- run-uvutz7m4/checkpoint-282/optimizer.pt +3 -0
- run-uvutz7m4/checkpoint-282/rng_state.pth +3 -0
- run-uvutz7m4/checkpoint-282/scheduler.pt +3 -0
- run-uvutz7m4/checkpoint-282/trainer_state.json +1450 -0
- run-uvutz7m4/checkpoint-282/training_args.bin +3 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"model_type": "clip_text_model"
|
| 15 |
},
|
| 16 |
"torch_dtype": "float32",
|
| 17 |
-
"transformers_version": "4.
|
| 18 |
"vision_config": {
|
| 19 |
"dropout": 0.0,
|
| 20 |
"model_type": "clip_vision_model"
|
|
|
|
| 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"
|
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 sha256:4a1abd032526e5f4fffe0063cf80e91a324d3851d30f3c75d382f89d765a88ca
|
| 3 |
size 605156676
|
run-uvutz7m4/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-uvutz7m4/checkpoint-282/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a1abd032526e5f4fffe0063cf80e91a324d3851d30f3c75d382f89d765a88ca
|
| 3 |
+
size 605156676
|
run-uvutz7m4/checkpoint-282/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be8553d6e35985483ee460dd8c52ca6f199469d0f519fa272ebe99ae216bc545
|
| 3 |
+
size 1210551612
|
run-uvutz7m4/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-uvutz7m4/checkpoint-282/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dbf15241ea53e753c099b6c41f41ea10b1a1c3f134b63fa7d33f098390887a6
|
| 3 |
+
size 1064
|
run-uvutz7m4/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": 212.81973266601562,
|
| 14 |
+
"learning_rate": 3.7450394203144474e-05,
|
| 15 |
+
"loss": 2.2611,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.031914893617021274,
|
| 20 |
+
"eval_loss": 1.6954327821731567,
|
| 21 |
+
"eval_runtime": 90.1393,
|
| 22 |
+
"eval_samples_per_second": 3.328,
|
| 23 |
+
"eval_steps_per_second": 0.111,
|
| 24 |
+
"step": 3
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06382978723404255,
|
| 28 |
+
"grad_norm": 94.31295776367188,
|
| 29 |
+
"learning_rate": 3.704770179235797e-05,
|
| 30 |
+
"loss": 2.1851,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06382978723404255,
|
| 35 |
+
"eval_loss": 1.83690345287323,
|
| 36 |
+
"eval_runtime": 45.0365,
|
| 37 |
+
"eval_samples_per_second": 6.661,
|
| 38 |
+
"eval_steps_per_second": 0.222,
|
| 39 |
+
"step": 6
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.09574468085106383,
|
| 43 |
+
"grad_norm": 88.24703216552734,
|
| 44 |
+
"learning_rate": 3.6645009381571474e-05,
|
| 45 |
+
"loss": 1.9095,
|
| 46 |
+
"step": 9
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.09574468085106383,
|
| 50 |
+
"eval_loss": 1.8263834714889526,
|
| 51 |
+
"eval_runtime": 44.4544,
|
| 52 |
+
"eval_samples_per_second": 6.748,
|
| 53 |
+
"eval_steps_per_second": 0.225,
|
| 54 |
+
"step": 9
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.1276595744680851,
|
| 58 |
+
"grad_norm": 73.16114044189453,
|
| 59 |
+
"learning_rate": 3.6242316970784977e-05,
|
| 60 |
+
"loss": 1.6022,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.1276595744680851,
|
| 65 |
+
"eval_loss": 1.6566990613937378,
|
| 66 |
+
"eval_runtime": 45.0842,
|
| 67 |
+
"eval_samples_per_second": 6.654,
|
| 68 |
+
"eval_steps_per_second": 0.222,
|
| 69 |
+
"step": 12
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1595744680851064,
|
| 73 |
+
"grad_norm": 74.73725128173828,
|
| 74 |
+
"learning_rate": 3.583962455999847e-05,
|
| 75 |
+
"loss": 1.5181,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.1595744680851064,
|
| 80 |
+
"eval_loss": 1.6280070543289185,
|
| 81 |
+
"eval_runtime": 45.1381,
|
| 82 |
+
"eval_samples_per_second": 6.646,
|
| 83 |
+
"eval_steps_per_second": 0.222,
|
| 84 |
+
"step": 15
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.19148936170212766,
|
| 88 |
+
"grad_norm": 79.7146987915039,
|
| 89 |
+
"learning_rate": 3.5436932149211976e-05,
|
| 90 |
+
"loss": 1.8478,
|
| 91 |
+
"step": 18
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.19148936170212766,
|
| 95 |
+
"eval_loss": 1.5796161890029907,
|
| 96 |
+
"eval_runtime": 45.9387,
|
| 97 |
+
"eval_samples_per_second": 6.53,
|
| 98 |
+
"eval_steps_per_second": 0.218,
|
| 99 |
+
"step": 18
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.22340425531914893,
|
| 103 |
+
"grad_norm": 65.3478775024414,
|
| 104 |
+
"learning_rate": 3.503423973842547e-05,
|
| 105 |
+
"loss": 1.3884,
|
| 106 |
+
"step": 21
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.22340425531914893,
|
| 110 |
+
"eval_loss": 1.5002487897872925,
|
| 111 |
+
"eval_runtime": 45.7227,
|
| 112 |
+
"eval_samples_per_second": 6.561,
|
| 113 |
+
"eval_steps_per_second": 0.219,
|
| 114 |
+
"step": 21
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2553191489361702,
|
| 118 |
+
"grad_norm": 66.32596588134766,
|
| 119 |
+
"learning_rate": 3.4631547327638975e-05,
|
| 120 |
+
"loss": 1.4368,
|
| 121 |
+
"step": 24
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2553191489361702,
|
| 125 |
+
"eval_loss": 1.5191569328308105,
|
| 126 |
+
"eval_runtime": 44.4497,
|
| 127 |
+
"eval_samples_per_second": 6.749,
|
| 128 |
+
"eval_steps_per_second": 0.225,
|
| 129 |
+
"step": 24
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2872340425531915,
|
| 133 |
+
"grad_norm": 67.5133056640625,
|
| 134 |
+
"learning_rate": 3.422885491685248e-05,
|
| 135 |
+
"loss": 1.6515,
|
| 136 |
+
"step": 27
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2872340425531915,
|
| 140 |
+
"eval_loss": 1.4516819715499878,
|
| 141 |
+
"eval_runtime": 44.968,
|
| 142 |
+
"eval_samples_per_second": 6.671,
|
| 143 |
+
"eval_steps_per_second": 0.222,
|
| 144 |
+
"step": 27
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3191489361702128,
|
| 148 |
+
"grad_norm": 56.178218841552734,
|
| 149 |
+
"learning_rate": 3.3826162506065975e-05,
|
| 150 |
+
"loss": 1.5518,
|
| 151 |
+
"step": 30
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3191489361702128,
|
| 155 |
+
"eval_loss": 1.4015744924545288,
|
| 156 |
+
"eval_runtime": 44.5216,
|
| 157 |
+
"eval_samples_per_second": 6.738,
|
| 158 |
+
"eval_steps_per_second": 0.225,
|
| 159 |
+
"step": 30
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.35106382978723405,
|
| 163 |
+
"grad_norm": 62.902313232421875,
|
| 164 |
+
"learning_rate": 3.342347009527948e-05,
|
| 165 |
+
"loss": 1.339,
|
| 166 |
+
"step": 33
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.35106382978723405,
|
| 170 |
+
"eval_loss": 1.3566683530807495,
|
| 171 |
+
"eval_runtime": 44.9809,
|
| 172 |
+
"eval_samples_per_second": 6.669,
|
| 173 |
+
"eval_steps_per_second": 0.222,
|
| 174 |
+
"step": 33
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.3829787234042553,
|
| 178 |
+
"grad_norm": 57.751197814941406,
|
| 179 |
+
"learning_rate": 3.3020777684492974e-05,
|
| 180 |
+
"loss": 1.6338,
|
| 181 |
+
"step": 36
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3829787234042553,
|
| 185 |
+
"eval_loss": 1.396578073501587,
|
| 186 |
+
"eval_runtime": 45.3817,
|
| 187 |
+
"eval_samples_per_second": 6.611,
|
| 188 |
+
"eval_steps_per_second": 0.22,
|
| 189 |
+
"step": 36
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4148936170212766,
|
| 193 |
+
"grad_norm": 57.7042121887207,
|
| 194 |
+
"learning_rate": 3.261808527370648e-05,
|
| 195 |
+
"loss": 1.4372,
|
| 196 |
+
"step": 39
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.4148936170212766,
|
| 200 |
+
"eval_loss": 1.3969274759292603,
|
| 201 |
+
"eval_runtime": 63.0438,
|
| 202 |
+
"eval_samples_per_second": 4.759,
|
| 203 |
+
"eval_steps_per_second": 0.159,
|
| 204 |
+
"step": 39
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.44680851063829785,
|
| 208 |
+
"grad_norm": 43.087100982666016,
|
| 209 |
+
"learning_rate": 3.221539286291997e-05,
|
| 210 |
+
"loss": 1.2751,
|
| 211 |
+
"step": 42
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.44680851063829785,
|
| 215 |
+
"eval_loss": 1.3432629108428955,
|
| 216 |
+
"eval_runtime": 43.0776,
|
| 217 |
+
"eval_samples_per_second": 6.964,
|
| 218 |
+
"eval_steps_per_second": 0.232,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4787234042553192,
|
| 223 |
+
"grad_norm": 58.544620513916016,
|
| 224 |
+
"learning_rate": 3.1812700452133476e-05,
|
| 225 |
+
"loss": 1.484,
|
| 226 |
+
"step": 45
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4787234042553192,
|
| 230 |
+
"eval_loss": 1.389102578163147,
|
| 231 |
+
"eval_runtime": 42.2187,
|
| 232 |
+
"eval_samples_per_second": 7.106,
|
| 233 |
+
"eval_steps_per_second": 0.237,
|
| 234 |
+
"step": 45
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5106382978723404,
|
| 238 |
+
"grad_norm": 40.23255920410156,
|
| 239 |
+
"learning_rate": 3.141000804134697e-05,
|
| 240 |
+
"loss": 1.4936,
|
| 241 |
+
"step": 48
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5106382978723404,
|
| 245 |
+
"eval_loss": 1.408040165901184,
|
| 246 |
+
"eval_runtime": 42.8634,
|
| 247 |
+
"eval_samples_per_second": 6.999,
|
| 248 |
+
"eval_steps_per_second": 0.233,
|
| 249 |
+
"step": 48
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5425531914893617,
|
| 253 |
+
"grad_norm": 58.45737075805664,
|
| 254 |
+
"learning_rate": 3.1007315630560475e-05,
|
| 255 |
+
"loss": 1.6771,
|
| 256 |
+
"step": 51
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.5425531914893617,
|
| 260 |
+
"eval_loss": 1.3876069784164429,
|
| 261 |
+
"eval_runtime": 47.7351,
|
| 262 |
+
"eval_samples_per_second": 6.285,
|
| 263 |
+
"eval_steps_per_second": 0.209,
|
| 264 |
+
"step": 51
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.574468085106383,
|
| 268 |
+
"grad_norm": 59.58686447143555,
|
| 269 |
+
"learning_rate": 3.060462321977397e-05,
|
| 270 |
+
"loss": 1.7328,
|
| 271 |
+
"step": 54
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.574468085106383,
|
| 275 |
+
"eval_loss": 1.3280422687530518,
|
| 276 |
+
"eval_runtime": 45.1191,
|
| 277 |
+
"eval_samples_per_second": 6.649,
|
| 278 |
+
"eval_steps_per_second": 0.222,
|
| 279 |
+
"step": 54
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6063829787234043,
|
| 283 |
+
"grad_norm": 49.796451568603516,
|
| 284 |
+
"learning_rate": 3.0201930808987475e-05,
|
| 285 |
+
"loss": 1.3566,
|
| 286 |
+
"step": 57
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6063829787234043,
|
| 290 |
+
"eval_loss": 1.3299312591552734,
|
| 291 |
+
"eval_runtime": 45.4372,
|
| 292 |
+
"eval_samples_per_second": 6.603,
|
| 293 |
+
"eval_steps_per_second": 0.22,
|
| 294 |
+
"step": 57
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.6382978723404256,
|
| 298 |
+
"grad_norm": 47.63386154174805,
|
| 299 |
+
"learning_rate": 2.9799238398200978e-05,
|
| 300 |
+
"loss": 1.1698,
|
| 301 |
+
"step": 60
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.6382978723404256,
|
| 305 |
+
"eval_loss": 1.3619319200515747,
|
| 306 |
+
"eval_runtime": 44.5898,
|
| 307 |
+
"eval_samples_per_second": 6.728,
|
| 308 |
+
"eval_steps_per_second": 0.224,
|
| 309 |
+
"step": 60
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.6702127659574468,
|
| 313 |
+
"grad_norm": 51.1750602722168,
|
| 314 |
+
"learning_rate": 2.9396545987414478e-05,
|
| 315 |
+
"loss": 1.4553,
|
| 316 |
+
"step": 63
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.6702127659574468,
|
| 320 |
+
"eval_loss": 1.2944597005844116,
|
| 321 |
+
"eval_runtime": 44.0116,
|
| 322 |
+
"eval_samples_per_second": 6.816,
|
| 323 |
+
"eval_steps_per_second": 0.227,
|
| 324 |
+
"step": 63
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7021276595744681,
|
| 328 |
+
"grad_norm": 56.35239028930664,
|
| 329 |
+
"learning_rate": 2.8993853576627977e-05,
|
| 330 |
+
"loss": 1.4532,
|
| 331 |
+
"step": 66
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7021276595744681,
|
| 335 |
+
"eval_loss": 1.3396683931350708,
|
| 336 |
+
"eval_runtime": 57.5395,
|
| 337 |
+
"eval_samples_per_second": 5.214,
|
| 338 |
+
"eval_steps_per_second": 0.174,
|
| 339 |
+
"step": 66
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.7340425531914894,
|
| 343 |
+
"grad_norm": 55.66822052001953,
|
| 344 |
+
"learning_rate": 2.859116116584148e-05,
|
| 345 |
+
"loss": 1.5623,
|
| 346 |
+
"step": 69
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7340425531914894,
|
| 350 |
+
"eval_loss": 1.3019959926605225,
|
| 351 |
+
"eval_runtime": 42.7505,
|
| 352 |
+
"eval_samples_per_second": 7.017,
|
| 353 |
+
"eval_steps_per_second": 0.234,
|
| 354 |
+
"step": 69
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.7659574468085106,
|
| 358 |
+
"grad_norm": 83.2627944946289,
|
| 359 |
+
"learning_rate": 2.8188468755054976e-05,
|
| 360 |
+
"loss": 1.5575,
|
| 361 |
+
"step": 72
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.7659574468085106,
|
| 365 |
+
"eval_loss": 1.2901865243911743,
|
| 366 |
+
"eval_runtime": 42.3414,
|
| 367 |
+
"eval_samples_per_second": 7.085,
|
| 368 |
+
"eval_steps_per_second": 0.236,
|
| 369 |
+
"step": 72
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7978723404255319,
|
| 373 |
+
"grad_norm": 66.81884002685547,
|
| 374 |
+
"learning_rate": 2.778577634426848e-05,
|
| 375 |
+
"loss": 1.4042,
|
| 376 |
+
"step": 75
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.7978723404255319,
|
| 380 |
+
"eval_loss": 1.2550606727600098,
|
| 381 |
+
"eval_runtime": 42.5955,
|
| 382 |
+
"eval_samples_per_second": 7.043,
|
| 383 |
+
"eval_steps_per_second": 0.235,
|
| 384 |
+
"step": 75
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8297872340425532,
|
| 388 |
+
"grad_norm": 47.388999938964844,
|
| 389 |
+
"learning_rate": 2.738308393348198e-05,
|
| 390 |
+
"loss": 1.3868,
|
| 391 |
+
"step": 78
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.8297872340425532,
|
| 395 |
+
"eval_loss": 1.2457486391067505,
|
| 396 |
+
"eval_runtime": 42.5244,
|
| 397 |
+
"eval_samples_per_second": 7.055,
|
| 398 |
+
"eval_steps_per_second": 0.235,
|
| 399 |
+
"step": 78
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.8617021276595744,
|
| 403 |
+
"grad_norm": 51.87979507446289,
|
| 404 |
+
"learning_rate": 2.698039152269548e-05,
|
| 405 |
+
"loss": 1.3286,
|
| 406 |
+
"step": 81
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.8617021276595744,
|
| 410 |
+
"eval_loss": 1.2376227378845215,
|
| 411 |
+
"eval_runtime": 42.3825,
|
| 412 |
+
"eval_samples_per_second": 7.078,
|
| 413 |
+
"eval_steps_per_second": 0.236,
|
| 414 |
+
"step": 81
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.8936170212765957,
|
| 418 |
+
"grad_norm": 61.56190490722656,
|
| 419 |
+
"learning_rate": 2.6577699111908982e-05,
|
| 420 |
+
"loss": 1.2435,
|
| 421 |
+
"step": 84
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.8936170212765957,
|
| 425 |
+
"eval_loss": 1.1932413578033447,
|
| 426 |
+
"eval_runtime": 43.0229,
|
| 427 |
+
"eval_samples_per_second": 6.973,
|
| 428 |
+
"eval_steps_per_second": 0.232,
|
| 429 |
+
"step": 84
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.925531914893617,
|
| 433 |
+
"grad_norm": 56.688331604003906,
|
| 434 |
+
"learning_rate": 2.617500670112248e-05,
|
| 435 |
+
"loss": 1.1201,
|
| 436 |
+
"step": 87
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.925531914893617,
|
| 440 |
+
"eval_loss": 1.1663594245910645,
|
| 441 |
+
"eval_runtime": 42.6963,
|
| 442 |
+
"eval_samples_per_second": 7.026,
|
| 443 |
+
"eval_steps_per_second": 0.234,
|
| 444 |
+
"step": 87
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.9574468085106383,
|
| 448 |
+
"grad_norm": 54.14950180053711,
|
| 449 |
+
"learning_rate": 2.577231429033598e-05,
|
| 450 |
+
"loss": 1.386,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.9574468085106383,
|
| 455 |
+
"eval_loss": 1.1541115045547485,
|
| 456 |
+
"eval_runtime": 42.4377,
|
| 457 |
+
"eval_samples_per_second": 7.069,
|
| 458 |
+
"eval_steps_per_second": 0.236,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.9893617021276596,
|
| 463 |
+
"grad_norm": 63.0470085144043,
|
| 464 |
+
"learning_rate": 2.536962187954948e-05,
|
| 465 |
+
"loss": 1.0404,
|
| 466 |
+
"step": 93
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.9893617021276596,
|
| 470 |
+
"eval_loss": 1.1485306024551392,
|
| 471 |
+
"eval_runtime": 42.3281,
|
| 472 |
+
"eval_samples_per_second": 7.087,
|
| 473 |
+
"eval_steps_per_second": 0.236,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.0212765957446808,
|
| 478 |
+
"grad_norm": 29.81873321533203,
|
| 479 |
+
"learning_rate": 2.496692946876298e-05,
|
| 480 |
+
"loss": 0.7278,
|
| 481 |
+
"step": 96
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.0212765957446808,
|
| 485 |
+
"eval_loss": 1.1454874277114868,
|
| 486 |
+
"eval_runtime": 4.1684,
|
| 487 |
+
"eval_samples_per_second": 71.97,
|
| 488 |
+
"eval_steps_per_second": 2.399,
|
| 489 |
+
"step": 96
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.053191489361702,
|
| 493 |
+
"grad_norm": 33.473297119140625,
|
| 494 |
+
"learning_rate": 2.456423705797648e-05,
|
| 495 |
+
"loss": 0.3543,
|
| 496 |
+
"step": 99
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.053191489361702,
|
| 500 |
+
"eval_loss": 1.177135944366455,
|
| 501 |
+
"eval_runtime": 42.0082,
|
| 502 |
+
"eval_samples_per_second": 7.141,
|
| 503 |
+
"eval_steps_per_second": 0.238,
|
| 504 |
+
"step": 99
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.0851063829787233,
|
| 508 |
+
"grad_norm": 23.966768264770508,
|
| 509 |
+
"learning_rate": 2.4161544647189983e-05,
|
| 510 |
+
"loss": 0.2839,
|
| 511 |
+
"step": 102
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.0851063829787233,
|
| 515 |
+
"eval_loss": 1.2594685554504395,
|
| 516 |
+
"eval_runtime": 4.1814,
|
| 517 |
+
"eval_samples_per_second": 71.746,
|
| 518 |
+
"eval_steps_per_second": 2.392,
|
| 519 |
+
"step": 102
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.1170212765957448,
|
| 523 |
+
"grad_norm": 23.973447799682617,
|
| 524 |
+
"learning_rate": 2.375885223640348e-05,
|
| 525 |
+
"loss": 0.2303,
|
| 526 |
+
"step": 105
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.1170212765957448,
|
| 530 |
+
"eval_loss": 1.3750962018966675,
|
| 531 |
+
"eval_runtime": 42.0396,
|
| 532 |
+
"eval_samples_per_second": 7.136,
|
| 533 |
+
"eval_steps_per_second": 0.238,
|
| 534 |
+
"step": 105
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.148936170212766,
|
| 538 |
+
"grad_norm": 36.35573959350586,
|
| 539 |
+
"learning_rate": 2.3356159825616983e-05,
|
| 540 |
+
"loss": 0.3702,
|
| 541 |
+
"step": 108
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.148936170212766,
|
| 545 |
+
"eval_loss": 1.4052996635437012,
|
| 546 |
+
"eval_runtime": 4.1732,
|
| 547 |
+
"eval_samples_per_second": 71.887,
|
| 548 |
+
"eval_steps_per_second": 2.396,
|
| 549 |
+
"step": 108
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.1808510638297873,
|
| 553 |
+
"grad_norm": 37.33869171142578,
|
| 554 |
+
"learning_rate": 2.2953467414830486e-05,
|
| 555 |
+
"loss": 0.37,
|
| 556 |
+
"step": 111
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.1808510638297873,
|
| 560 |
+
"eval_loss": 1.4478391408920288,
|
| 561 |
+
"eval_runtime": 42.2951,
|
| 562 |
+
"eval_samples_per_second": 7.093,
|
| 563 |
+
"eval_steps_per_second": 0.236,
|
| 564 |
+
"step": 111
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.2127659574468086,
|
| 568 |
+
"grad_norm": 32.96900177001953,
|
| 569 |
+
"learning_rate": 2.2550775004043982e-05,
|
| 570 |
+
"loss": 0.2412,
|
| 571 |
+
"step": 114
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.2127659574468086,
|
| 575 |
+
"eval_loss": 1.4774221181869507,
|
| 576 |
+
"eval_runtime": 5.0258,
|
| 577 |
+
"eval_samples_per_second": 59.693,
|
| 578 |
+
"eval_steps_per_second": 1.99,
|
| 579 |
+
"step": 114
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.2446808510638299,
|
| 583 |
+
"grad_norm": 45.11040496826172,
|
| 584 |
+
"learning_rate": 2.2148082593257485e-05,
|
| 585 |
+
"loss": 0.3028,
|
| 586 |
+
"step": 117
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.2446808510638299,
|
| 590 |
+
"eval_loss": 1.4591237306594849,
|
| 591 |
+
"eval_runtime": 41.5496,
|
| 592 |
+
"eval_samples_per_second": 7.22,
|
| 593 |
+
"eval_steps_per_second": 0.241,
|
| 594 |
+
"step": 117
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.2765957446808511,
|
| 598 |
+
"grad_norm": 31.62494659423828,
|
| 599 |
+
"learning_rate": 2.1745390182470985e-05,
|
| 600 |
+
"loss": 0.322,
|
| 601 |
+
"step": 120
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.2765957446808511,
|
| 605 |
+
"eval_loss": 1.483196496963501,
|
| 606 |
+
"eval_runtime": 4.901,
|
| 607 |
+
"eval_samples_per_second": 61.212,
|
| 608 |
+
"eval_steps_per_second": 2.04,
|
| 609 |
+
"step": 120
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.3085106382978724,
|
| 613 |
+
"grad_norm": 53.78076934814453,
|
| 614 |
+
"learning_rate": 2.1342697771684484e-05,
|
| 615 |
+
"loss": 0.4919,
|
| 616 |
+
"step": 123
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.3085106382978724,
|
| 620 |
+
"eval_loss": 1.4939560890197754,
|
| 621 |
+
"eval_runtime": 41.6747,
|
| 622 |
+
"eval_samples_per_second": 7.199,
|
| 623 |
+
"eval_steps_per_second": 0.24,
|
| 624 |
+
"step": 123
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.3404255319148937,
|
| 628 |
+
"grad_norm": 54.71748352050781,
|
| 629 |
+
"learning_rate": 2.0940005360897984e-05,
|
| 630 |
+
"loss": 0.3868,
|
| 631 |
+
"step": 126
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.3404255319148937,
|
| 635 |
+
"eval_loss": 1.4461126327514648,
|
| 636 |
+
"eval_runtime": 4.3166,
|
| 637 |
+
"eval_samples_per_second": 69.498,
|
| 638 |
+
"eval_steps_per_second": 2.317,
|
| 639 |
+
"step": 126
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.372340425531915,
|
| 643 |
+
"grad_norm": 39.04596710205078,
|
| 644 |
+
"learning_rate": 2.0537312950111484e-05,
|
| 645 |
+
"loss": 0.3795,
|
| 646 |
+
"step": 129
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.372340425531915,
|
| 650 |
+
"eval_loss": 1.421697735786438,
|
| 651 |
+
"eval_runtime": 41.8322,
|
| 652 |
+
"eval_samples_per_second": 7.172,
|
| 653 |
+
"eval_steps_per_second": 0.239,
|
| 654 |
+
"step": 129
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.4042553191489362,
|
| 658 |
+
"grad_norm": 43.464900970458984,
|
| 659 |
+
"learning_rate": 2.0134620539324983e-05,
|
| 660 |
+
"loss": 0.2185,
|
| 661 |
+
"step": 132
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.4042553191489362,
|
| 665 |
+
"eval_loss": 1.4404044151306152,
|
| 666 |
+
"eval_runtime": 4.1662,
|
| 667 |
+
"eval_samples_per_second": 72.008,
|
| 668 |
+
"eval_steps_per_second": 2.4,
|
| 669 |
+
"step": 132
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.4361702127659575,
|
| 673 |
+
"grad_norm": 39.858341217041016,
|
| 674 |
+
"learning_rate": 1.9731928128538486e-05,
|
| 675 |
+
"loss": 0.361,
|
| 676 |
+
"step": 135
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.4361702127659575,
|
| 680 |
+
"eval_loss": 1.445768117904663,
|
| 681 |
+
"eval_runtime": 41.5719,
|
| 682 |
+
"eval_samples_per_second": 7.216,
|
| 683 |
+
"eval_steps_per_second": 0.241,
|
| 684 |
+
"step": 135
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.4680851063829787,
|
| 688 |
+
"grad_norm": 35.612701416015625,
|
| 689 |
+
"learning_rate": 1.9329235717751983e-05,
|
| 690 |
+
"loss": 0.3308,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.4680851063829787,
|
| 695 |
+
"eval_loss": 1.447102665901184,
|
| 696 |
+
"eval_runtime": 4.2095,
|
| 697 |
+
"eval_samples_per_second": 71.267,
|
| 698 |
+
"eval_steps_per_second": 2.376,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.5,
|
| 703 |
+
"grad_norm": 40.08439636230469,
|
| 704 |
+
"learning_rate": 1.8926543306965486e-05,
|
| 705 |
+
"loss": 0.29,
|
| 706 |
+
"step": 141
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.5,
|
| 710 |
+
"eval_loss": 1.4261672496795654,
|
| 711 |
+
"eval_runtime": 41.3155,
|
| 712 |
+
"eval_samples_per_second": 7.261,
|
| 713 |
+
"eval_steps_per_second": 0.242,
|
| 714 |
+
"step": 141
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.5319148936170213,
|
| 718 |
+
"grad_norm": 34.78931427001953,
|
| 719 |
+
"learning_rate": 1.8523850896178985e-05,
|
| 720 |
+
"loss": 0.2372,
|
| 721 |
+
"step": 144
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.5319148936170213,
|
| 725 |
+
"eval_loss": 1.4144420623779297,
|
| 726 |
+
"eval_runtime": 4.1971,
|
| 727 |
+
"eval_samples_per_second": 71.478,
|
| 728 |
+
"eval_steps_per_second": 2.383,
|
| 729 |
+
"step": 144
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.5638297872340425,
|
| 733 |
+
"grad_norm": 45.00236892700195,
|
| 734 |
+
"learning_rate": 1.8121158485392488e-05,
|
| 735 |
+
"loss": 0.2666,
|
| 736 |
+
"step": 147
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.5638297872340425,
|
| 740 |
+
"eval_loss": 1.4330610036849976,
|
| 741 |
+
"eval_runtime": 41.5952,
|
| 742 |
+
"eval_samples_per_second": 7.212,
|
| 743 |
+
"eval_steps_per_second": 0.24,
|
| 744 |
+
"step": 147
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5957446808510638,
|
| 748 |
+
"grad_norm": 53.813011169433594,
|
| 749 |
+
"learning_rate": 1.7718466074605988e-05,
|
| 750 |
+
"loss": 0.357,
|
| 751 |
+
"step": 150
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5957446808510638,
|
| 755 |
+
"eval_loss": 1.49522864818573,
|
| 756 |
+
"eval_runtime": 4.8438,
|
| 757 |
+
"eval_samples_per_second": 61.935,
|
| 758 |
+
"eval_steps_per_second": 2.065,
|
| 759 |
+
"step": 150
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.627659574468085,
|
| 763 |
+
"grad_norm": 50.32698440551758,
|
| 764 |
+
"learning_rate": 1.7315773663819488e-05,
|
| 765 |
+
"loss": 0.3668,
|
| 766 |
+
"step": 153
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.627659574468085,
|
| 770 |
+
"eval_loss": 1.5075035095214844,
|
| 771 |
+
"eval_runtime": 42.1649,
|
| 772 |
+
"eval_samples_per_second": 7.115,
|
| 773 |
+
"eval_steps_per_second": 0.237,
|
| 774 |
+
"step": 153
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.6595744680851063,
|
| 778 |
+
"grad_norm": 29.047195434570312,
|
| 779 |
+
"learning_rate": 1.6913081253032987e-05,
|
| 780 |
+
"loss": 0.257,
|
| 781 |
+
"step": 156
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.6595744680851063,
|
| 785 |
+
"eval_loss": 1.499000072479248,
|
| 786 |
+
"eval_runtime": 5.1976,
|
| 787 |
+
"eval_samples_per_second": 57.719,
|
| 788 |
+
"eval_steps_per_second": 1.924,
|
| 789 |
+
"step": 156
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.6914893617021276,
|
| 793 |
+
"grad_norm": 44.64079666137695,
|
| 794 |
+
"learning_rate": 1.6510388842246487e-05,
|
| 795 |
+
"loss": 0.2812,
|
| 796 |
+
"step": 159
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.6914893617021276,
|
| 800 |
+
"eval_loss": 1.5078258514404297,
|
| 801 |
+
"eval_runtime": 41.7195,
|
| 802 |
+
"eval_samples_per_second": 7.191,
|
| 803 |
+
"eval_steps_per_second": 0.24,
|
| 804 |
+
"step": 159
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.7234042553191489,
|
| 808 |
+
"grad_norm": 45.4018669128418,
|
| 809 |
+
"learning_rate": 1.6107696431459987e-05,
|
| 810 |
+
"loss": 0.3697,
|
| 811 |
+
"step": 162
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.7234042553191489,
|
| 815 |
+
"eval_loss": 1.4968957901000977,
|
| 816 |
+
"eval_runtime": 4.6701,
|
| 817 |
+
"eval_samples_per_second": 64.239,
|
| 818 |
+
"eval_steps_per_second": 2.141,
|
| 819 |
+
"step": 162
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.7553191489361701,
|
| 823 |
+
"grad_norm": 23.335609436035156,
|
| 824 |
+
"learning_rate": 1.5705004020673486e-05,
|
| 825 |
+
"loss": 0.2935,
|
| 826 |
+
"step": 165
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.7553191489361701,
|
| 830 |
+
"eval_loss": 1.4559073448181152,
|
| 831 |
+
"eval_runtime": 41.376,
|
| 832 |
+
"eval_samples_per_second": 7.251,
|
| 833 |
+
"eval_steps_per_second": 0.242,
|
| 834 |
+
"step": 165
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.7872340425531914,
|
| 838 |
+
"grad_norm": 38.07520294189453,
|
| 839 |
+
"learning_rate": 1.5302311609886986e-05,
|
| 840 |
+
"loss": 0.2622,
|
| 841 |
+
"step": 168
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.7872340425531914,
|
| 845 |
+
"eval_loss": 1.4034123420715332,
|
| 846 |
+
"eval_runtime": 4.1798,
|
| 847 |
+
"eval_samples_per_second": 71.773,
|
| 848 |
+
"eval_steps_per_second": 2.392,
|
| 849 |
+
"step": 168
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.8191489361702127,
|
| 853 |
+
"grad_norm": 79.16899871826172,
|
| 854 |
+
"learning_rate": 1.4899619199100489e-05,
|
| 855 |
+
"loss": 0.4383,
|
| 856 |
+
"step": 171
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.8191489361702127,
|
| 860 |
+
"eval_loss": 1.379632830619812,
|
| 861 |
+
"eval_runtime": 41.4885,
|
| 862 |
+
"eval_samples_per_second": 7.231,
|
| 863 |
+
"eval_steps_per_second": 0.241,
|
| 864 |
+
"step": 171
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.851063829787234,
|
| 868 |
+
"grad_norm": 56.25248718261719,
|
| 869 |
+
"learning_rate": 1.4496926788313989e-05,
|
| 870 |
+
"loss": 0.2953,
|
| 871 |
+
"step": 174
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.851063829787234,
|
| 875 |
+
"eval_loss": 1.3718376159667969,
|
| 876 |
+
"eval_runtime": 4.2567,
|
| 877 |
+
"eval_samples_per_second": 70.478,
|
| 878 |
+
"eval_steps_per_second": 2.349,
|
| 879 |
+
"step": 174
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.8829787234042552,
|
| 883 |
+
"grad_norm": 45.190975189208984,
|
| 884 |
+
"learning_rate": 1.4094234377527488e-05,
|
| 885 |
+
"loss": 0.3427,
|
| 886 |
+
"step": 177
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.8829787234042552,
|
| 890 |
+
"eval_loss": 1.3516465425491333,
|
| 891 |
+
"eval_runtime": 41.6735,
|
| 892 |
+
"eval_samples_per_second": 7.199,
|
| 893 |
+
"eval_steps_per_second": 0.24,
|
| 894 |
+
"step": 177
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.9148936170212765,
|
| 898 |
+
"grad_norm": 28.82175064086914,
|
| 899 |
+
"learning_rate": 1.369154196674099e-05,
|
| 900 |
+
"loss": 0.2204,
|
| 901 |
+
"step": 180
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.9148936170212765,
|
| 905 |
+
"eval_loss": 1.3585424423217773,
|
| 906 |
+
"eval_runtime": 4.1577,
|
| 907 |
+
"eval_samples_per_second": 72.155,
|
| 908 |
+
"eval_steps_per_second": 2.405,
|
| 909 |
+
"step": 180
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.9468085106382977,
|
| 913 |
+
"grad_norm": 46.982139587402344,
|
| 914 |
+
"learning_rate": 1.3288849555954491e-05,
|
| 915 |
+
"loss": 0.2,
|
| 916 |
+
"step": 183
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.9468085106382977,
|
| 920 |
+
"eval_loss": 1.3777296543121338,
|
| 921 |
+
"eval_runtime": 41.8859,
|
| 922 |
+
"eval_samples_per_second": 7.162,
|
| 923 |
+
"eval_steps_per_second": 0.239,
|
| 924 |
+
"step": 183
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.978723404255319,
|
| 928 |
+
"grad_norm": 22.6469669342041,
|
| 929 |
+
"learning_rate": 1.288615714516799e-05,
|
| 930 |
+
"loss": 0.2074,
|
| 931 |
+
"step": 186
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.978723404255319,
|
| 935 |
+
"eval_loss": 1.3690061569213867,
|
| 936 |
+
"eval_runtime": 4.6763,
|
| 937 |
+
"eval_samples_per_second": 64.154,
|
| 938 |
+
"eval_steps_per_second": 2.138,
|
| 939 |
+
"step": 186
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.0106382978723403,
|
| 943 |
+
"grad_norm": 12.022841453552246,
|
| 944 |
+
"learning_rate": 1.248346473438149e-05,
|
| 945 |
+
"loss": 0.0972,
|
| 946 |
+
"step": 189
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.0106382978723403,
|
| 950 |
+
"eval_loss": 1.354335069656372,
|
| 951 |
+
"eval_runtime": 55.4961,
|
| 952 |
+
"eval_samples_per_second": 5.406,
|
| 953 |
+
"eval_steps_per_second": 0.18,
|
| 954 |
+
"step": 189
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.0425531914893615,
|
| 958 |
+
"grad_norm": 32.32695007324219,
|
| 959 |
+
"learning_rate": 1.2080772323594992e-05,
|
| 960 |
+
"loss": 0.1505,
|
| 961 |
+
"step": 192
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.0425531914893615,
|
| 965 |
+
"eval_loss": 1.3698673248291016,
|
| 966 |
+
"eval_runtime": 34.6113,
|
| 967 |
+
"eval_samples_per_second": 8.668,
|
| 968 |
+
"eval_steps_per_second": 0.289,
|
| 969 |
+
"step": 192
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.074468085106383,
|
| 973 |
+
"grad_norm": 20.132957458496094,
|
| 974 |
+
"learning_rate": 1.1678079912808491e-05,
|
| 975 |
+
"loss": 0.0651,
|
| 976 |
+
"step": 195
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.074468085106383,
|
| 980 |
+
"eval_loss": 1.4110251665115356,
|
| 981 |
+
"eval_runtime": 12.5667,
|
| 982 |
+
"eval_samples_per_second": 23.873,
|
| 983 |
+
"eval_steps_per_second": 0.796,
|
| 984 |
+
"step": 195
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.106382978723404,
|
| 988 |
+
"grad_norm": 16.97626495361328,
|
| 989 |
+
"learning_rate": 1.1275387502021991e-05,
|
| 990 |
+
"loss": 0.045,
|
| 991 |
+
"step": 198
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.106382978723404,
|
| 995 |
+
"eval_loss": 1.4494677782058716,
|
| 996 |
+
"eval_runtime": 34.2066,
|
| 997 |
+
"eval_samples_per_second": 8.77,
|
| 998 |
+
"eval_steps_per_second": 0.292,
|
| 999 |
+
"step": 198
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.1382978723404253,
|
| 1003 |
+
"grad_norm": 27.48331642150879,
|
| 1004 |
+
"learning_rate": 1.0872695091235492e-05,
|
| 1005 |
+
"loss": 0.1105,
|
| 1006 |
+
"step": 201
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.1382978723404253,
|
| 1010 |
+
"eval_loss": 1.4678298234939575,
|
| 1011 |
+
"eval_runtime": 12.6413,
|
| 1012 |
+
"eval_samples_per_second": 23.732,
|
| 1013 |
+
"eval_steps_per_second": 0.791,
|
| 1014 |
+
"step": 201
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.1702127659574466,
|
| 1018 |
+
"grad_norm": 9.6218900680542,
|
| 1019 |
+
"learning_rate": 1.0470002680448992e-05,
|
| 1020 |
+
"loss": 0.0703,
|
| 1021 |
+
"step": 204
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.1702127659574466,
|
| 1025 |
+
"eval_loss": 1.4693076610565186,
|
| 1026 |
+
"eval_runtime": 33.7057,
|
| 1027 |
+
"eval_samples_per_second": 8.901,
|
| 1028 |
+
"eval_steps_per_second": 0.297,
|
| 1029 |
+
"step": 204
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.202127659574468,
|
| 1033 |
+
"grad_norm": 12.747748374938965,
|
| 1034 |
+
"learning_rate": 1.0067310269662492e-05,
|
| 1035 |
+
"loss": 0.0793,
|
| 1036 |
+
"step": 207
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 2.202127659574468,
|
| 1040 |
+
"eval_loss": 1.4696707725524902,
|
| 1041 |
+
"eval_runtime": 11.7313,
|
| 1042 |
+
"eval_samples_per_second": 25.573,
|
| 1043 |
+
"eval_steps_per_second": 0.852,
|
| 1044 |
+
"step": 207
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.2340425531914896,
|
| 1048 |
+
"grad_norm": 18.998815536499023,
|
| 1049 |
+
"learning_rate": 9.664617858875991e-06,
|
| 1050 |
+
"loss": 0.0709,
|
| 1051 |
+
"step": 210
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.2340425531914896,
|
| 1055 |
+
"eval_loss": 1.4826494455337524,
|
| 1056 |
+
"eval_runtime": 33.8588,
|
| 1057 |
+
"eval_samples_per_second": 8.86,
|
| 1058 |
+
"eval_steps_per_second": 0.295,
|
| 1059 |
+
"step": 210
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.2659574468085104,
|
| 1063 |
+
"grad_norm": 26.24040412902832,
|
| 1064 |
+
"learning_rate": 9.261925448089493e-06,
|
| 1065 |
+
"loss": 0.133,
|
| 1066 |
+
"step": 213
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.2659574468085104,
|
| 1070 |
+
"eval_loss": 1.484723687171936,
|
| 1071 |
+
"eval_runtime": 11.9592,
|
| 1072 |
+
"eval_samples_per_second": 25.085,
|
| 1073 |
+
"eval_steps_per_second": 0.836,
|
| 1074 |
+
"step": 213
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.297872340425532,
|
| 1078 |
+
"grad_norm": 38.74705123901367,
|
| 1079 |
+
"learning_rate": 8.859233037302994e-06,
|
| 1080 |
+
"loss": 0.1055,
|
| 1081 |
+
"step": 216
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.297872340425532,
|
| 1085 |
+
"eval_loss": 1.4781628847122192,
|
| 1086 |
+
"eval_runtime": 34.0608,
|
| 1087 |
+
"eval_samples_per_second": 8.808,
|
| 1088 |
+
"eval_steps_per_second": 0.294,
|
| 1089 |
+
"step": 216
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.329787234042553,
|
| 1093 |
+
"grad_norm": 51.491939544677734,
|
| 1094 |
+
"learning_rate": 8.456540626516494e-06,
|
| 1095 |
+
"loss": 0.106,
|
| 1096 |
+
"step": 219
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.329787234042553,
|
| 1100 |
+
"eval_loss": 1.4520379304885864,
|
| 1101 |
+
"eval_runtime": 12.1072,
|
| 1102 |
+
"eval_samples_per_second": 24.779,
|
| 1103 |
+
"eval_steps_per_second": 0.826,
|
| 1104 |
+
"step": 219
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.3617021276595747,
|
| 1108 |
+
"grad_norm": 15.932838439941406,
|
| 1109 |
+
"learning_rate": 8.053848215729993e-06,
|
| 1110 |
+
"loss": 0.0553,
|
| 1111 |
+
"step": 222
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.3617021276595747,
|
| 1115 |
+
"eval_loss": 1.4323525428771973,
|
| 1116 |
+
"eval_runtime": 34.1547,
|
| 1117 |
+
"eval_samples_per_second": 8.784,
|
| 1118 |
+
"eval_steps_per_second": 0.293,
|
| 1119 |
+
"step": 222
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.393617021276596,
|
| 1123 |
+
"grad_norm": 14.132286071777344,
|
| 1124 |
+
"learning_rate": 7.651155804943493e-06,
|
| 1125 |
+
"loss": 0.0598,
|
| 1126 |
+
"step": 225
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.393617021276596,
|
| 1130 |
+
"eval_loss": 1.4186018705368042,
|
| 1131 |
+
"eval_runtime": 12.5329,
|
| 1132 |
+
"eval_samples_per_second": 23.937,
|
| 1133 |
+
"eval_steps_per_second": 0.798,
|
| 1134 |
+
"step": 225
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.425531914893617,
|
| 1138 |
+
"grad_norm": 43.08507537841797,
|
| 1139 |
+
"learning_rate": 7.248463394156994e-06,
|
| 1140 |
+
"loss": 0.0903,
|
| 1141 |
+
"step": 228
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.425531914893617,
|
| 1145 |
+
"eval_loss": 1.4079523086547852,
|
| 1146 |
+
"eval_runtime": 33.5371,
|
| 1147 |
+
"eval_samples_per_second": 8.945,
|
| 1148 |
+
"eval_steps_per_second": 0.298,
|
| 1149 |
+
"step": 228
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.4574468085106385,
|
| 1153 |
+
"grad_norm": 18.148130416870117,
|
| 1154 |
+
"learning_rate": 6.845770983370495e-06,
|
| 1155 |
+
"loss": 0.0379,
|
| 1156 |
+
"step": 231
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.4574468085106385,
|
| 1160 |
+
"eval_loss": 1.402553677558899,
|
| 1161 |
+
"eval_runtime": 12.5951,
|
| 1162 |
+
"eval_samples_per_second": 23.819,
|
| 1163 |
+
"eval_steps_per_second": 0.794,
|
| 1164 |
+
"step": 231
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.4893617021276597,
|
| 1168 |
+
"grad_norm": 18.774492263793945,
|
| 1169 |
+
"learning_rate": 6.443078572583995e-06,
|
| 1170 |
+
"loss": 0.056,
|
| 1171 |
+
"step": 234
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.4893617021276597,
|
| 1175 |
+
"eval_loss": 1.4105722904205322,
|
| 1176 |
+
"eval_runtime": 34.0705,
|
| 1177 |
+
"eval_samples_per_second": 8.805,
|
| 1178 |
+
"eval_steps_per_second": 0.294,
|
| 1179 |
+
"step": 234
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.521276595744681,
|
| 1183 |
+
"grad_norm": 21.43934440612793,
|
| 1184 |
+
"learning_rate": 6.040386161797496e-06,
|
| 1185 |
+
"loss": 0.0753,
|
| 1186 |
+
"step": 237
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.521276595744681,
|
| 1190 |
+
"eval_loss": 1.429024338722229,
|
| 1191 |
+
"eval_runtime": 11.7342,
|
| 1192 |
+
"eval_samples_per_second": 25.566,
|
| 1193 |
+
"eval_steps_per_second": 0.852,
|
| 1194 |
+
"step": 237
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.5531914893617023,
|
| 1198 |
+
"grad_norm": 21.858001708984375,
|
| 1199 |
+
"learning_rate": 5.6376937510109955e-06,
|
| 1200 |
+
"loss": 0.0677,
|
| 1201 |
+
"step": 240
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.5531914893617023,
|
| 1205 |
+
"eval_loss": 1.449249267578125,
|
| 1206 |
+
"eval_runtime": 34.3754,
|
| 1207 |
+
"eval_samples_per_second": 8.727,
|
| 1208 |
+
"eval_steps_per_second": 0.291,
|
| 1209 |
+
"step": 240
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.5851063829787235,
|
| 1213 |
+
"grad_norm": 18.75592803955078,
|
| 1214 |
+
"learning_rate": 5.235001340224496e-06,
|
| 1215 |
+
"loss": 0.0636,
|
| 1216 |
+
"step": 243
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.5851063829787235,
|
| 1220 |
+
"eval_loss": 1.4570808410644531,
|
| 1221 |
+
"eval_runtime": 11.6793,
|
| 1222 |
+
"eval_samples_per_second": 25.687,
|
| 1223 |
+
"eval_steps_per_second": 0.856,
|
| 1224 |
+
"step": 243
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.617021276595745,
|
| 1228 |
+
"grad_norm": 23.944276809692383,
|
| 1229 |
+
"learning_rate": 4.832308929437996e-06,
|
| 1230 |
+
"loss": 0.0748,
|
| 1231 |
+
"step": 246
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.617021276595745,
|
| 1235 |
+
"eval_loss": 1.4605278968811035,
|
| 1236 |
+
"eval_runtime": 33.9241,
|
| 1237 |
+
"eval_samples_per_second": 8.843,
|
| 1238 |
+
"eval_steps_per_second": 0.295,
|
| 1239 |
+
"step": 246
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.648936170212766,
|
| 1243 |
+
"grad_norm": 9.529204368591309,
|
| 1244 |
+
"learning_rate": 4.429616518651497e-06,
|
| 1245 |
+
"loss": 0.0271,
|
| 1246 |
+
"step": 249
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 2.648936170212766,
|
| 1250 |
+
"eval_loss": 1.4531209468841553,
|
| 1251 |
+
"eval_runtime": 11.8506,
|
| 1252 |
+
"eval_samples_per_second": 25.315,
|
| 1253 |
+
"eval_steps_per_second": 0.844,
|
| 1254 |
+
"step": 249
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.6808510638297873,
|
| 1258 |
+
"grad_norm": 3.7583017349243164,
|
| 1259 |
+
"learning_rate": 4.026924107864997e-06,
|
| 1260 |
+
"loss": 0.0542,
|
| 1261 |
+
"step": 252
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.6808510638297873,
|
| 1265 |
+
"eval_loss": 1.4430041313171387,
|
| 1266 |
+
"eval_runtime": 33.7906,
|
| 1267 |
+
"eval_samples_per_second": 8.878,
|
| 1268 |
+
"eval_steps_per_second": 0.296,
|
| 1269 |
+
"step": 252
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.7127659574468086,
|
| 1273 |
+
"grad_norm": 12.694750785827637,
|
| 1274 |
+
"learning_rate": 3.624231697078497e-06,
|
| 1275 |
+
"loss": 0.0332,
|
| 1276 |
+
"step": 255
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.7127659574468086,
|
| 1280 |
+
"eval_loss": 1.4361652135849,
|
| 1281 |
+
"eval_runtime": 11.6664,
|
| 1282 |
+
"eval_samples_per_second": 25.715,
|
| 1283 |
+
"eval_steps_per_second": 0.857,
|
| 1284 |
+
"step": 255
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.74468085106383,
|
| 1288 |
+
"grad_norm": 36.67692184448242,
|
| 1289 |
+
"learning_rate": 3.2215392862919977e-06,
|
| 1290 |
+
"loss": 0.1035,
|
| 1291 |
+
"step": 258
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.74468085106383,
|
| 1295 |
+
"eval_loss": 1.430528998374939,
|
| 1296 |
+
"eval_runtime": 33.9464,
|
| 1297 |
+
"eval_samples_per_second": 8.837,
|
| 1298 |
+
"eval_steps_per_second": 0.295,
|
| 1299 |
+
"step": 258
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.776595744680851,
|
| 1303 |
+
"grad_norm": 30.15072250366211,
|
| 1304 |
+
"learning_rate": 2.8188468755054977e-06,
|
| 1305 |
+
"loss": 0.0643,
|
| 1306 |
+
"step": 261
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.776595744680851,
|
| 1310 |
+
"eval_loss": 1.4278947114944458,
|
| 1311 |
+
"eval_runtime": 12.1733,
|
| 1312 |
+
"eval_samples_per_second": 24.644,
|
| 1313 |
+
"eval_steps_per_second": 0.821,
|
| 1314 |
+
"step": 261
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.8085106382978724,
|
| 1318 |
+
"grad_norm": 5.219892978668213,
|
| 1319 |
+
"learning_rate": 2.416154464718998e-06,
|
| 1320 |
+
"loss": 0.0549,
|
| 1321 |
+
"step": 264
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.8085106382978724,
|
| 1325 |
+
"eval_loss": 1.4259532690048218,
|
| 1326 |
+
"eval_runtime": 33.872,
|
| 1327 |
+
"eval_samples_per_second": 8.857,
|
| 1328 |
+
"eval_steps_per_second": 0.295,
|
| 1329 |
+
"step": 264
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.8404255319148937,
|
| 1333 |
+
"grad_norm": 20.615497589111328,
|
| 1334 |
+
"learning_rate": 2.0134620539324983e-06,
|
| 1335 |
+
"loss": 0.0495,
|
| 1336 |
+
"step": 267
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.8404255319148937,
|
| 1340 |
+
"eval_loss": 1.4268009662628174,
|
| 1341 |
+
"eval_runtime": 12.5283,
|
| 1342 |
+
"eval_samples_per_second": 23.946,
|
| 1343 |
+
"eval_steps_per_second": 0.798,
|
| 1344 |
+
"step": 267
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.872340425531915,
|
| 1348 |
+
"grad_norm": 0.853824257850647,
|
| 1349 |
+
"learning_rate": 1.6107696431459988e-06,
|
| 1350 |
+
"loss": 0.0152,
|
| 1351 |
+
"step": 270
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.872340425531915,
|
| 1355 |
+
"eval_loss": 1.427072525024414,
|
| 1356 |
+
"eval_runtime": 33.8909,
|
| 1357 |
+
"eval_samples_per_second": 8.852,
|
| 1358 |
+
"eval_steps_per_second": 0.295,
|
| 1359 |
+
"step": 270
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.904255319148936,
|
| 1363 |
+
"grad_norm": 6.235328197479248,
|
| 1364 |
+
"learning_rate": 1.208077232359499e-06,
|
| 1365 |
+
"loss": 0.0806,
|
| 1366 |
+
"step": 273
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 2.904255319148936,
|
| 1370 |
+
"eval_loss": 1.4273793697357178,
|
| 1371 |
+
"eval_runtime": 12.4911,
|
| 1372 |
+
"eval_samples_per_second": 24.017,
|
| 1373 |
+
"eval_steps_per_second": 0.801,
|
| 1374 |
+
"step": 273
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.9361702127659575,
|
| 1378 |
+
"grad_norm": 17.21672248840332,
|
| 1379 |
+
"learning_rate": 8.053848215729994e-07,
|
| 1380 |
+
"loss": 0.0564,
|
| 1381 |
+
"step": 276
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.9361702127659575,
|
| 1385 |
+
"eval_loss": 1.4273569583892822,
|
| 1386 |
+
"eval_runtime": 33.6977,
|
| 1387 |
+
"eval_samples_per_second": 8.903,
|
| 1388 |
+
"eval_steps_per_second": 0.297,
|
| 1389 |
+
"step": 276
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.9680851063829787,
|
| 1393 |
+
"grad_norm": 23.0670166015625,
|
| 1394 |
+
"learning_rate": 4.026924107864997e-07,
|
| 1395 |
+
"loss": 0.0726,
|
| 1396 |
+
"step": 279
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.9680851063829787,
|
| 1400 |
+
"eval_loss": 1.4270917177200317,
|
| 1401 |
+
"eval_runtime": 11.7754,
|
| 1402 |
+
"eval_samples_per_second": 25.477,
|
| 1403 |
+
"eval_steps_per_second": 0.849,
|
| 1404 |
+
"step": 279
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 3.0,
|
| 1408 |
+
"grad_norm": 20.24632453918457,
|
| 1409 |
+
"learning_rate": 0.0,
|
| 1410 |
+
"loss": 0.0332,
|
| 1411 |
+
"step": 282
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 3.0,
|
| 1415 |
+
"eval_loss": 1.427086591720581,
|
| 1416 |
+
"eval_runtime": 34.0405,
|
| 1417 |
+
"eval_samples_per_second": 8.813,
|
| 1418 |
+
"eval_steps_per_second": 0.294,
|
| 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": 0.1,
|
| 1446 |
+
"learning_rate": 3.785308661393097e-05,
|
| 1447 |
+
"metric": "eval/loss",
|
| 1448 |
+
"per_device_train_batch_size": 32
|
| 1449 |
+
}
|
| 1450 |
+
}
|
run-uvutz7m4/checkpoint-282/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447e4faf04da62a1e8de9c9f0b845d6e65b908e90be81f0d49261dfef45fea3f
|
| 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 sha256:447e4faf04da62a1e8de9c9f0b845d6e65b908e90be81f0d49261dfef45fea3f
|
| 3 |
size 5112
|