Training in progress, epoch 98, checkpoint
Browse files- checkpoint-20776/README.md +9 -0
- checkpoint-20776/adapter_config.json +26 -0
- checkpoint-20776/adapter_model.bin +3 -0
- checkpoint-20776/optimizer.pt +3 -0
- checkpoint-20776/rng_state.pth +3 -0
- checkpoint-20776/scheduler.pt +3 -0
- checkpoint-20776/sentencepiece.bpe.model +3 -0
- checkpoint-20776/special_tokens_map.json +19 -0
- checkpoint-20776/tokenizer.json +0 -0
- checkpoint-20776/tokenizer_config.json +24 -0
- checkpoint-20776/trainer_state.json +1391 -0
- checkpoint-20776/training_args.bin +3 -0
checkpoint-20776/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
checkpoint-20776/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "camembert/camembert-large",
|
| 4 |
+
"bias": "all",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": [
|
| 13 |
+
"classifier.bias",
|
| 14 |
+
"classifier.weight"
|
| 15 |
+
],
|
| 16 |
+
"peft_type": "LORA",
|
| 17 |
+
"r": 16,
|
| 18 |
+
"revision": null,
|
| 19 |
+
"target_modules": [
|
| 20 |
+
"query",
|
| 21 |
+
"key",
|
| 22 |
+
"value",
|
| 23 |
+
"dense"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "TOKEN_CLS"
|
| 26 |
+
}
|
checkpoint-20776/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9ee20b26dddc0eb663d2f8dc7391cfc1106280d3529a06ef40e0a8c3bef3054
|
| 3 |
+
size 32369117
|
checkpoint-20776/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2e34748742960de61fdaeadfea2957d53893093b221d56842de92870e25fb6
|
| 3 |
+
size 64782278
|
checkpoint-20776/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64c8336a46fc2504f6987f27df54ea96a24c73440b63e3b81a5a27d5f3cfcbb0
|
| 3 |
+
size 14575
|
checkpoint-20776/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e90c6ecec0f1848cebad3c41cdb154a87c593b00353392b7d00434dbdb91b7
|
| 3 |
+
size 627
|
checkpoint-20776/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
| 3 |
+
size 808767
|
checkpoint-20776/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
checkpoint-20776/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20776/tokenizer_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"clean_up_tokenization_spaces": true,
|
| 8 |
+
"cls_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"mask_token": {
|
| 11 |
+
"__type": "AddedToken",
|
| 12 |
+
"content": "<mask>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"sep_token": "</s>",
|
| 21 |
+
"sp_model_kwargs": {},
|
| 22 |
+
"tokenizer_class": "CamembertTokenizer",
|
| 23 |
+
"unk_token": "<unk>"
|
| 24 |
+
}
|
checkpoint-20776/trainer_state.json
ADDED
|
@@ -0,0 +1,1391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 98.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20776,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 9.95e-05,
|
| 14 |
+
"loss": 6.3597,
|
| 15 |
+
"step": 212
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 5.853069305419922,
|
| 20 |
+
"eval_runtime": 3.5937,
|
| 21 |
+
"eval_samples_per_second": 188.106,
|
| 22 |
+
"eval_steps_per_second": 23.652,
|
| 23 |
+
"step": 212
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 9.900000000000001e-05,
|
| 28 |
+
"loss": 5.5629,
|
| 29 |
+
"step": 424
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 4.915834903717041,
|
| 34 |
+
"eval_runtime": 3.704,
|
| 35 |
+
"eval_samples_per_second": 182.506,
|
| 36 |
+
"eval_steps_per_second": 22.948,
|
| 37 |
+
"step": 424
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.0,
|
| 41 |
+
"learning_rate": 9.850000000000001e-05,
|
| 42 |
+
"loss": 4.8228,
|
| 43 |
+
"step": 636
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 4.177055835723877,
|
| 48 |
+
"eval_runtime": 3.7104,
|
| 49 |
+
"eval_samples_per_second": 182.193,
|
| 50 |
+
"eval_steps_per_second": 22.909,
|
| 51 |
+
"step": 636
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"learning_rate": 9.8e-05,
|
| 56 |
+
"loss": 4.1035,
|
| 57 |
+
"step": 848
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_loss": 3.462527275085449,
|
| 62 |
+
"eval_runtime": 3.1205,
|
| 63 |
+
"eval_samples_per_second": 216.633,
|
| 64 |
+
"eval_steps_per_second": 27.239,
|
| 65 |
+
"step": 848
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.0,
|
| 69 |
+
"learning_rate": 9.75e-05,
|
| 70 |
+
"loss": 3.467,
|
| 71 |
+
"step": 1060
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_loss": 2.8398332595825195,
|
| 76 |
+
"eval_runtime": 3.3235,
|
| 77 |
+
"eval_samples_per_second": 203.402,
|
| 78 |
+
"eval_steps_per_second": 25.576,
|
| 79 |
+
"step": 1060
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.0,
|
| 83 |
+
"learning_rate": 9.7e-05,
|
| 84 |
+
"loss": 2.8887,
|
| 85 |
+
"step": 1272
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6.0,
|
| 89 |
+
"eval_loss": 2.3201420307159424,
|
| 90 |
+
"eval_runtime": 3.4255,
|
| 91 |
+
"eval_samples_per_second": 197.342,
|
| 92 |
+
"eval_steps_per_second": 24.814,
|
| 93 |
+
"step": 1272
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"learning_rate": 9.65e-05,
|
| 98 |
+
"loss": 2.4003,
|
| 99 |
+
"step": 1484
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"eval_loss": 1.8698177337646484,
|
| 104 |
+
"eval_runtime": 3.5218,
|
| 105 |
+
"eval_samples_per_second": 191.945,
|
| 106 |
+
"eval_steps_per_second": 24.135,
|
| 107 |
+
"step": 1484
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"learning_rate": 9.6e-05,
|
| 112 |
+
"loss": 1.9919,
|
| 113 |
+
"step": 1696
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 1.532776951789856,
|
| 118 |
+
"eval_runtime": 3.5514,
|
| 119 |
+
"eval_samples_per_second": 190.345,
|
| 120 |
+
"eval_steps_per_second": 23.934,
|
| 121 |
+
"step": 1696
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 9.0,
|
| 125 |
+
"learning_rate": 9.55e-05,
|
| 126 |
+
"loss": 1.6656,
|
| 127 |
+
"step": 1908
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 9.0,
|
| 131 |
+
"eval_loss": 1.2841078042984009,
|
| 132 |
+
"eval_runtime": 3.622,
|
| 133 |
+
"eval_samples_per_second": 186.637,
|
| 134 |
+
"eval_steps_per_second": 23.468,
|
| 135 |
+
"step": 1908
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.0,
|
| 139 |
+
"learning_rate": 9.5e-05,
|
| 140 |
+
"loss": 1.4036,
|
| 141 |
+
"step": 2120
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.0,
|
| 145 |
+
"eval_loss": 1.107720971107483,
|
| 146 |
+
"eval_runtime": 3.6471,
|
| 147 |
+
"eval_samples_per_second": 185.353,
|
| 148 |
+
"eval_steps_per_second": 23.306,
|
| 149 |
+
"step": 2120
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 11.0,
|
| 153 |
+
"learning_rate": 9.449999999999999e-05,
|
| 154 |
+
"loss": 1.2091,
|
| 155 |
+
"step": 2332
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.0,
|
| 159 |
+
"eval_loss": 0.9709760546684265,
|
| 160 |
+
"eval_runtime": 3.7402,
|
| 161 |
+
"eval_samples_per_second": 180.741,
|
| 162 |
+
"eval_steps_per_second": 22.726,
|
| 163 |
+
"step": 2332
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 12.0,
|
| 167 |
+
"learning_rate": 9.4e-05,
|
| 168 |
+
"loss": 1.0379,
|
| 169 |
+
"step": 2544
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 12.0,
|
| 173 |
+
"eval_loss": 0.8528622984886169,
|
| 174 |
+
"eval_runtime": 3.734,
|
| 175 |
+
"eval_samples_per_second": 181.041,
|
| 176 |
+
"eval_steps_per_second": 22.764,
|
| 177 |
+
"step": 2544
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 9.350000000000001e-05,
|
| 182 |
+
"loss": 0.8994,
|
| 183 |
+
"step": 2756
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_loss": 0.7617917060852051,
|
| 188 |
+
"eval_runtime": 3.7153,
|
| 189 |
+
"eval_samples_per_second": 181.95,
|
| 190 |
+
"eval_steps_per_second": 22.878,
|
| 191 |
+
"step": 2756
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"learning_rate": 9.300000000000001e-05,
|
| 196 |
+
"loss": 0.7828,
|
| 197 |
+
"step": 2968
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 0.6774648427963257,
|
| 202 |
+
"eval_runtime": 3.6994,
|
| 203 |
+
"eval_samples_per_second": 182.734,
|
| 204 |
+
"eval_steps_per_second": 22.977,
|
| 205 |
+
"step": 2968
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"learning_rate": 9.250000000000001e-05,
|
| 210 |
+
"loss": 0.6788,
|
| 211 |
+
"step": 3180
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 15.0,
|
| 215 |
+
"eval_loss": 0.6361714005470276,
|
| 216 |
+
"eval_runtime": 3.6581,
|
| 217 |
+
"eval_samples_per_second": 184.796,
|
| 218 |
+
"eval_steps_per_second": 23.236,
|
| 219 |
+
"step": 3180
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"learning_rate": 9.200000000000001e-05,
|
| 224 |
+
"loss": 0.5819,
|
| 225 |
+
"step": 3392
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.0,
|
| 229 |
+
"eval_loss": 0.5761357545852661,
|
| 230 |
+
"eval_runtime": 3.7378,
|
| 231 |
+
"eval_samples_per_second": 180.853,
|
| 232 |
+
"eval_steps_per_second": 22.74,
|
| 233 |
+
"step": 3392
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 17.0,
|
| 237 |
+
"learning_rate": 9.15e-05,
|
| 238 |
+
"loss": 0.5104,
|
| 239 |
+
"step": 3604
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.0,
|
| 243 |
+
"eval_loss": 0.5219044089317322,
|
| 244 |
+
"eval_runtime": 3.7453,
|
| 245 |
+
"eval_samples_per_second": 180.495,
|
| 246 |
+
"eval_steps_per_second": 22.695,
|
| 247 |
+
"step": 3604
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 18.0,
|
| 251 |
+
"learning_rate": 9.1e-05,
|
| 252 |
+
"loss": 0.4343,
|
| 253 |
+
"step": 3816
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_loss": 0.4844624102115631,
|
| 258 |
+
"eval_runtime": 3.7695,
|
| 259 |
+
"eval_samples_per_second": 179.335,
|
| 260 |
+
"eval_steps_per_second": 22.55,
|
| 261 |
+
"step": 3816
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"learning_rate": 9.05e-05,
|
| 266 |
+
"loss": 0.3784,
|
| 267 |
+
"step": 4028
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 19.0,
|
| 271 |
+
"eval_loss": 0.44724151492118835,
|
| 272 |
+
"eval_runtime": 3.7703,
|
| 273 |
+
"eval_samples_per_second": 179.296,
|
| 274 |
+
"eval_steps_per_second": 22.545,
|
| 275 |
+
"step": 4028
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"learning_rate": 9e-05,
|
| 280 |
+
"loss": 0.3224,
|
| 281 |
+
"step": 4240
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"eval_loss": 0.45848363637924194,
|
| 286 |
+
"eval_runtime": 3.6822,
|
| 287 |
+
"eval_samples_per_second": 183.584,
|
| 288 |
+
"eval_steps_per_second": 23.084,
|
| 289 |
+
"step": 4240
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.0,
|
| 293 |
+
"learning_rate": 8.950000000000001e-05,
|
| 294 |
+
"loss": 0.2768,
|
| 295 |
+
"step": 4452
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 21.0,
|
| 299 |
+
"eval_loss": 0.4251560866832733,
|
| 300 |
+
"eval_runtime": 3.9348,
|
| 301 |
+
"eval_samples_per_second": 171.802,
|
| 302 |
+
"eval_steps_per_second": 21.602,
|
| 303 |
+
"step": 4452
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"learning_rate": 8.900000000000001e-05,
|
| 308 |
+
"loss": 0.2269,
|
| 309 |
+
"step": 4664
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.0,
|
| 313 |
+
"eval_loss": 0.39140933752059937,
|
| 314 |
+
"eval_runtime": 3.6907,
|
| 315 |
+
"eval_samples_per_second": 183.165,
|
| 316 |
+
"eval_steps_per_second": 23.031,
|
| 317 |
+
"step": 4664
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 23.0,
|
| 321 |
+
"learning_rate": 8.850000000000001e-05,
|
| 322 |
+
"loss": 0.1868,
|
| 323 |
+
"step": 4876
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.0,
|
| 327 |
+
"eval_loss": 0.4142400920391083,
|
| 328 |
+
"eval_runtime": 3.8669,
|
| 329 |
+
"eval_samples_per_second": 174.815,
|
| 330 |
+
"eval_steps_per_second": 21.981,
|
| 331 |
+
"step": 4876
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 24.0,
|
| 335 |
+
"learning_rate": 8.800000000000001e-05,
|
| 336 |
+
"loss": 0.1539,
|
| 337 |
+
"step": 5088
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.0,
|
| 341 |
+
"eval_loss": 0.3828276991844177,
|
| 342 |
+
"eval_runtime": 3.7873,
|
| 343 |
+
"eval_samples_per_second": 178.493,
|
| 344 |
+
"eval_steps_per_second": 22.444,
|
| 345 |
+
"step": 5088
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"learning_rate": 8.75e-05,
|
| 350 |
+
"loss": 0.1298,
|
| 351 |
+
"step": 5300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 25.0,
|
| 355 |
+
"eval_loss": 0.40518617630004883,
|
| 356 |
+
"eval_runtime": 3.9459,
|
| 357 |
+
"eval_samples_per_second": 171.319,
|
| 358 |
+
"eval_steps_per_second": 21.542,
|
| 359 |
+
"step": 5300
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 26.0,
|
| 363 |
+
"learning_rate": 8.7e-05,
|
| 364 |
+
"loss": 0.1098,
|
| 365 |
+
"step": 5512
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 26.0,
|
| 369 |
+
"eval_loss": 0.420820027589798,
|
| 370 |
+
"eval_runtime": 3.7042,
|
| 371 |
+
"eval_samples_per_second": 182.497,
|
| 372 |
+
"eval_steps_per_second": 22.947,
|
| 373 |
+
"step": 5512
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 27.0,
|
| 377 |
+
"learning_rate": 8.65e-05,
|
| 378 |
+
"loss": 0.0905,
|
| 379 |
+
"step": 5724
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 27.0,
|
| 383 |
+
"eval_loss": 0.39528989791870117,
|
| 384 |
+
"eval_runtime": 3.784,
|
| 385 |
+
"eval_samples_per_second": 178.645,
|
| 386 |
+
"eval_steps_per_second": 22.463,
|
| 387 |
+
"step": 5724
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.0,
|
| 391 |
+
"learning_rate": 8.6e-05,
|
| 392 |
+
"loss": 0.0731,
|
| 393 |
+
"step": 5936
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.0,
|
| 397 |
+
"eval_loss": 0.41354966163635254,
|
| 398 |
+
"eval_runtime": 3.7338,
|
| 399 |
+
"eval_samples_per_second": 181.047,
|
| 400 |
+
"eval_steps_per_second": 22.765,
|
| 401 |
+
"step": 5936
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"learning_rate": 8.55e-05,
|
| 406 |
+
"loss": 0.063,
|
| 407 |
+
"step": 6148
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 29.0,
|
| 411 |
+
"eval_loss": 0.39981818199157715,
|
| 412 |
+
"eval_runtime": 3.6841,
|
| 413 |
+
"eval_samples_per_second": 183.489,
|
| 414 |
+
"eval_steps_per_second": 23.072,
|
| 415 |
+
"step": 6148
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 30.0,
|
| 419 |
+
"learning_rate": 8.5e-05,
|
| 420 |
+
"loss": 0.0543,
|
| 421 |
+
"step": 6360
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 30.0,
|
| 425 |
+
"eval_loss": 0.4148443043231964,
|
| 426 |
+
"eval_runtime": 3.9507,
|
| 427 |
+
"eval_samples_per_second": 171.111,
|
| 428 |
+
"eval_steps_per_second": 21.515,
|
| 429 |
+
"step": 6360
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 31.0,
|
| 433 |
+
"learning_rate": 8.450000000000001e-05,
|
| 434 |
+
"loss": 0.0452,
|
| 435 |
+
"step": 6572
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 31.0,
|
| 439 |
+
"eval_loss": 0.4315831959247589,
|
| 440 |
+
"eval_runtime": 4.0598,
|
| 441 |
+
"eval_samples_per_second": 166.511,
|
| 442 |
+
"eval_steps_per_second": 20.937,
|
| 443 |
+
"step": 6572
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 8.4e-05,
|
| 448 |
+
"loss": 0.0411,
|
| 449 |
+
"step": 6784
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.0,
|
| 453 |
+
"eval_loss": 0.4563623070716858,
|
| 454 |
+
"eval_runtime": 3.7904,
|
| 455 |
+
"eval_samples_per_second": 178.346,
|
| 456 |
+
"eval_steps_per_second": 22.425,
|
| 457 |
+
"step": 6784
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 33.0,
|
| 461 |
+
"learning_rate": 8.35e-05,
|
| 462 |
+
"loss": 0.0342,
|
| 463 |
+
"step": 6996
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 33.0,
|
| 467 |
+
"eval_loss": 0.4423569142818451,
|
| 468 |
+
"eval_runtime": 3.6613,
|
| 469 |
+
"eval_samples_per_second": 184.635,
|
| 470 |
+
"eval_steps_per_second": 23.216,
|
| 471 |
+
"step": 6996
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 34.0,
|
| 475 |
+
"learning_rate": 8.3e-05,
|
| 476 |
+
"loss": 0.0285,
|
| 477 |
+
"step": 7208
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 34.0,
|
| 481 |
+
"eval_loss": 0.45883628726005554,
|
| 482 |
+
"eval_runtime": 3.8854,
|
| 483 |
+
"eval_samples_per_second": 173.985,
|
| 484 |
+
"eval_steps_per_second": 21.877,
|
| 485 |
+
"step": 7208
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.0,
|
| 489 |
+
"learning_rate": 8.25e-05,
|
| 490 |
+
"loss": 0.0261,
|
| 491 |
+
"step": 7420
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 35.0,
|
| 495 |
+
"eval_loss": 0.4722530245780945,
|
| 496 |
+
"eval_runtime": 3.9505,
|
| 497 |
+
"eval_samples_per_second": 171.117,
|
| 498 |
+
"eval_steps_per_second": 21.516,
|
| 499 |
+
"step": 7420
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"learning_rate": 8.2e-05,
|
| 504 |
+
"loss": 0.0261,
|
| 505 |
+
"step": 7632
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 36.0,
|
| 509 |
+
"eval_loss": 0.4807146191596985,
|
| 510 |
+
"eval_runtime": 3.7918,
|
| 511 |
+
"eval_samples_per_second": 178.279,
|
| 512 |
+
"eval_steps_per_second": 22.417,
|
| 513 |
+
"step": 7632
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 37.0,
|
| 517 |
+
"learning_rate": 8.15e-05,
|
| 518 |
+
"loss": 0.0199,
|
| 519 |
+
"step": 7844
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 37.0,
|
| 523 |
+
"eval_loss": 0.46007126569747925,
|
| 524 |
+
"eval_runtime": 3.8954,
|
| 525 |
+
"eval_samples_per_second": 173.536,
|
| 526 |
+
"eval_steps_per_second": 21.82,
|
| 527 |
+
"step": 7844
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 38.0,
|
| 531 |
+
"learning_rate": 8.1e-05,
|
| 532 |
+
"loss": 0.0169,
|
| 533 |
+
"step": 8056
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.0,
|
| 537 |
+
"eval_loss": 0.4729515314102173,
|
| 538 |
+
"eval_runtime": 3.8647,
|
| 539 |
+
"eval_samples_per_second": 174.918,
|
| 540 |
+
"eval_steps_per_second": 21.994,
|
| 541 |
+
"step": 8056
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 39.0,
|
| 545 |
+
"learning_rate": 8.05e-05,
|
| 546 |
+
"loss": 0.0164,
|
| 547 |
+
"step": 8268
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 39.0,
|
| 551 |
+
"eval_loss": 0.4991854131221771,
|
| 552 |
+
"eval_runtime": 3.8642,
|
| 553 |
+
"eval_samples_per_second": 174.937,
|
| 554 |
+
"eval_steps_per_second": 21.997,
|
| 555 |
+
"step": 8268
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 40.0,
|
| 559 |
+
"learning_rate": 8e-05,
|
| 560 |
+
"loss": 0.0152,
|
| 561 |
+
"step": 8480
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"eval_loss": 0.48734694719314575,
|
| 566 |
+
"eval_runtime": 3.8857,
|
| 567 |
+
"eval_samples_per_second": 173.971,
|
| 568 |
+
"eval_steps_per_second": 21.875,
|
| 569 |
+
"step": 8480
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 41.0,
|
| 573 |
+
"learning_rate": 7.950000000000001e-05,
|
| 574 |
+
"loss": 0.0109,
|
| 575 |
+
"step": 8692
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 41.0,
|
| 579 |
+
"eval_loss": 0.49513980746269226,
|
| 580 |
+
"eval_runtime": 3.8249,
|
| 581 |
+
"eval_samples_per_second": 176.736,
|
| 582 |
+
"eval_steps_per_second": 22.223,
|
| 583 |
+
"step": 8692
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 42.0,
|
| 587 |
+
"learning_rate": 7.900000000000001e-05,
|
| 588 |
+
"loss": 0.0132,
|
| 589 |
+
"step": 8904
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 42.0,
|
| 593 |
+
"eval_loss": 0.4910328984260559,
|
| 594 |
+
"eval_runtime": 3.823,
|
| 595 |
+
"eval_samples_per_second": 176.826,
|
| 596 |
+
"eval_steps_per_second": 22.234,
|
| 597 |
+
"step": 8904
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 43.0,
|
| 601 |
+
"learning_rate": 7.850000000000001e-05,
|
| 602 |
+
"loss": 0.0086,
|
| 603 |
+
"step": 9116
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 43.0,
|
| 607 |
+
"eval_loss": 0.5066259503364563,
|
| 608 |
+
"eval_runtime": 3.8604,
|
| 609 |
+
"eval_samples_per_second": 175.11,
|
| 610 |
+
"eval_steps_per_second": 22.018,
|
| 611 |
+
"step": 9116
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 44.0,
|
| 615 |
+
"learning_rate": 7.800000000000001e-05,
|
| 616 |
+
"loss": 0.0084,
|
| 617 |
+
"step": 9328
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 44.0,
|
| 621 |
+
"eval_loss": 0.5218311548233032,
|
| 622 |
+
"eval_runtime": 3.8685,
|
| 623 |
+
"eval_samples_per_second": 174.744,
|
| 624 |
+
"eval_steps_per_second": 21.972,
|
| 625 |
+
"step": 9328
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 45.0,
|
| 629 |
+
"learning_rate": 7.75e-05,
|
| 630 |
+
"loss": 0.0082,
|
| 631 |
+
"step": 9540
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.0,
|
| 635 |
+
"eval_loss": 0.5277370810508728,
|
| 636 |
+
"eval_runtime": 3.8269,
|
| 637 |
+
"eval_samples_per_second": 176.644,
|
| 638 |
+
"eval_steps_per_second": 22.211,
|
| 639 |
+
"step": 9540
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 46.0,
|
| 643 |
+
"learning_rate": 7.7e-05,
|
| 644 |
+
"loss": 0.0094,
|
| 645 |
+
"step": 9752
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 46.0,
|
| 649 |
+
"eval_loss": 0.5367192029953003,
|
| 650 |
+
"eval_runtime": 3.8012,
|
| 651 |
+
"eval_samples_per_second": 177.838,
|
| 652 |
+
"eval_steps_per_second": 22.361,
|
| 653 |
+
"step": 9752
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 47.0,
|
| 657 |
+
"learning_rate": 7.65e-05,
|
| 658 |
+
"loss": 0.0117,
|
| 659 |
+
"step": 9964
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 47.0,
|
| 663 |
+
"eval_loss": 0.5425814390182495,
|
| 664 |
+
"eval_runtime": 3.8527,
|
| 665 |
+
"eval_samples_per_second": 175.46,
|
| 666 |
+
"eval_steps_per_second": 22.062,
|
| 667 |
+
"step": 9964
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 48.0,
|
| 671 |
+
"learning_rate": 7.6e-05,
|
| 672 |
+
"loss": 0.0073,
|
| 673 |
+
"step": 10176
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 48.0,
|
| 677 |
+
"eval_loss": 0.5633374452590942,
|
| 678 |
+
"eval_runtime": 3.8494,
|
| 679 |
+
"eval_samples_per_second": 175.614,
|
| 680 |
+
"eval_steps_per_second": 22.082,
|
| 681 |
+
"step": 10176
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 49.0,
|
| 685 |
+
"learning_rate": 7.55e-05,
|
| 686 |
+
"loss": 0.0064,
|
| 687 |
+
"step": 10388
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 49.0,
|
| 691 |
+
"eval_loss": 0.558996319770813,
|
| 692 |
+
"eval_runtime": 3.8307,
|
| 693 |
+
"eval_samples_per_second": 176.467,
|
| 694 |
+
"eval_steps_per_second": 22.189,
|
| 695 |
+
"step": 10388
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 50.0,
|
| 699 |
+
"learning_rate": 7.500000000000001e-05,
|
| 700 |
+
"loss": 0.0047,
|
| 701 |
+
"step": 10600
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 50.0,
|
| 705 |
+
"eval_loss": 0.5562776923179626,
|
| 706 |
+
"eval_runtime": 3.8234,
|
| 707 |
+
"eval_samples_per_second": 176.804,
|
| 708 |
+
"eval_steps_per_second": 22.231,
|
| 709 |
+
"step": 10600
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 51.0,
|
| 713 |
+
"learning_rate": 7.450000000000001e-05,
|
| 714 |
+
"loss": 0.0107,
|
| 715 |
+
"step": 10812
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 51.0,
|
| 719 |
+
"eval_loss": 0.5780841708183289,
|
| 720 |
+
"eval_runtime": 3.8575,
|
| 721 |
+
"eval_samples_per_second": 175.242,
|
| 722 |
+
"eval_steps_per_second": 22.035,
|
| 723 |
+
"step": 10812
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 52.0,
|
| 727 |
+
"learning_rate": 7.4e-05,
|
| 728 |
+
"loss": 0.0084,
|
| 729 |
+
"step": 11024
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 52.0,
|
| 733 |
+
"eval_loss": 0.5766631364822388,
|
| 734 |
+
"eval_runtime": 3.9223,
|
| 735 |
+
"eval_samples_per_second": 172.35,
|
| 736 |
+
"eval_steps_per_second": 21.671,
|
| 737 |
+
"step": 11024
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 53.0,
|
| 741 |
+
"learning_rate": 7.35e-05,
|
| 742 |
+
"loss": 0.005,
|
| 743 |
+
"step": 11236
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 53.0,
|
| 747 |
+
"eval_loss": 0.5684217810630798,
|
| 748 |
+
"eval_runtime": 3.8567,
|
| 749 |
+
"eval_samples_per_second": 175.281,
|
| 750 |
+
"eval_steps_per_second": 22.04,
|
| 751 |
+
"step": 11236
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 54.0,
|
| 755 |
+
"learning_rate": 7.3e-05,
|
| 756 |
+
"loss": 0.0036,
|
| 757 |
+
"step": 11448
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 54.0,
|
| 761 |
+
"eval_loss": 0.5706903338432312,
|
| 762 |
+
"eval_runtime": 3.8702,
|
| 763 |
+
"eval_samples_per_second": 174.67,
|
| 764 |
+
"eval_steps_per_second": 21.963,
|
| 765 |
+
"step": 11448
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 55.0,
|
| 769 |
+
"learning_rate": 7.25e-05,
|
| 770 |
+
"loss": 0.0049,
|
| 771 |
+
"step": 11660
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 55.0,
|
| 775 |
+
"eval_loss": 0.6319368481636047,
|
| 776 |
+
"eval_runtime": 3.8576,
|
| 777 |
+
"eval_samples_per_second": 175.24,
|
| 778 |
+
"eval_steps_per_second": 22.035,
|
| 779 |
+
"step": 11660
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 56.0,
|
| 783 |
+
"learning_rate": 7.2e-05,
|
| 784 |
+
"loss": 0.0104,
|
| 785 |
+
"step": 11872
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 56.0,
|
| 789 |
+
"eval_loss": 0.5811020731925964,
|
| 790 |
+
"eval_runtime": 3.8577,
|
| 791 |
+
"eval_samples_per_second": 175.232,
|
| 792 |
+
"eval_steps_per_second": 22.034,
|
| 793 |
+
"step": 11872
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 57.0,
|
| 797 |
+
"learning_rate": 7.15e-05,
|
| 798 |
+
"loss": 0.0062,
|
| 799 |
+
"step": 12084
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 57.0,
|
| 803 |
+
"eval_loss": 0.5707266330718994,
|
| 804 |
+
"eval_runtime": 3.9635,
|
| 805 |
+
"eval_samples_per_second": 170.555,
|
| 806 |
+
"eval_steps_per_second": 21.446,
|
| 807 |
+
"step": 12084
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 58.0,
|
| 811 |
+
"learning_rate": 7.1e-05,
|
| 812 |
+
"loss": 0.0048,
|
| 813 |
+
"step": 12296
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 58.0,
|
| 817 |
+
"eval_loss": 0.5851640701293945,
|
| 818 |
+
"eval_runtime": 3.9016,
|
| 819 |
+
"eval_samples_per_second": 173.261,
|
| 820 |
+
"eval_steps_per_second": 21.786,
|
| 821 |
+
"step": 12296
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 59.0,
|
| 825 |
+
"learning_rate": 7.05e-05,
|
| 826 |
+
"loss": 0.0068,
|
| 827 |
+
"step": 12508
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 59.0,
|
| 831 |
+
"eval_loss": 0.5783529877662659,
|
| 832 |
+
"eval_runtime": 3.8183,
|
| 833 |
+
"eval_samples_per_second": 177.042,
|
| 834 |
+
"eval_steps_per_second": 22.261,
|
| 835 |
+
"step": 12508
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 60.0,
|
| 839 |
+
"learning_rate": 7e-05,
|
| 840 |
+
"loss": 0.0048,
|
| 841 |
+
"step": 12720
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 60.0,
|
| 845 |
+
"eval_loss": 0.6140020489692688,
|
| 846 |
+
"eval_runtime": 3.7856,
|
| 847 |
+
"eval_samples_per_second": 178.57,
|
| 848 |
+
"eval_steps_per_second": 22.453,
|
| 849 |
+
"step": 12720
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 61.0,
|
| 853 |
+
"learning_rate": 6.95e-05,
|
| 854 |
+
"loss": 0.009,
|
| 855 |
+
"step": 12932
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 61.0,
|
| 859 |
+
"eval_loss": 0.5918340682983398,
|
| 860 |
+
"eval_runtime": 3.8592,
|
| 861 |
+
"eval_samples_per_second": 175.164,
|
| 862 |
+
"eval_steps_per_second": 22.025,
|
| 863 |
+
"step": 12932
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 62.0,
|
| 867 |
+
"learning_rate": 6.9e-05,
|
| 868 |
+
"loss": 0.0105,
|
| 869 |
+
"step": 13144
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 62.0,
|
| 873 |
+
"eval_loss": 0.6117520928382874,
|
| 874 |
+
"eval_runtime": 3.8639,
|
| 875 |
+
"eval_samples_per_second": 174.954,
|
| 876 |
+
"eval_steps_per_second": 21.999,
|
| 877 |
+
"step": 13144
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 63.0,
|
| 881 |
+
"learning_rate": 6.850000000000001e-05,
|
| 882 |
+
"loss": 0.0043,
|
| 883 |
+
"step": 13356
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 63.0,
|
| 887 |
+
"eval_loss": 0.6182054281234741,
|
| 888 |
+
"eval_runtime": 3.8658,
|
| 889 |
+
"eval_samples_per_second": 174.867,
|
| 890 |
+
"eval_steps_per_second": 21.988,
|
| 891 |
+
"step": 13356
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 64.0,
|
| 895 |
+
"learning_rate": 6.800000000000001e-05,
|
| 896 |
+
"loss": 0.0068,
|
| 897 |
+
"step": 13568
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 64.0,
|
| 901 |
+
"eval_loss": 0.6197443604469299,
|
| 902 |
+
"eval_runtime": 4.002,
|
| 903 |
+
"eval_samples_per_second": 168.914,
|
| 904 |
+
"eval_steps_per_second": 21.239,
|
| 905 |
+
"step": 13568
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 65.0,
|
| 909 |
+
"learning_rate": 6.750000000000001e-05,
|
| 910 |
+
"loss": 0.002,
|
| 911 |
+
"step": 13780
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 65.0,
|
| 915 |
+
"eval_loss": 0.634060263633728,
|
| 916 |
+
"eval_runtime": 3.9152,
|
| 917 |
+
"eval_samples_per_second": 172.66,
|
| 918 |
+
"eval_steps_per_second": 21.71,
|
| 919 |
+
"step": 13780
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 66.0,
|
| 923 |
+
"learning_rate": 6.7e-05,
|
| 924 |
+
"loss": 0.0017,
|
| 925 |
+
"step": 13992
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 66.0,
|
| 929 |
+
"eval_loss": 0.6460883021354675,
|
| 930 |
+
"eval_runtime": 3.7595,
|
| 931 |
+
"eval_samples_per_second": 179.81,
|
| 932 |
+
"eval_steps_per_second": 22.609,
|
| 933 |
+
"step": 13992
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 67.0,
|
| 937 |
+
"learning_rate": 6.65e-05,
|
| 938 |
+
"loss": 0.0016,
|
| 939 |
+
"step": 14204
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 67.0,
|
| 943 |
+
"eval_loss": 0.6443946361541748,
|
| 944 |
+
"eval_runtime": 3.8549,
|
| 945 |
+
"eval_samples_per_second": 175.36,
|
| 946 |
+
"eval_steps_per_second": 22.05,
|
| 947 |
+
"step": 14204
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 68.0,
|
| 951 |
+
"learning_rate": 6.6e-05,
|
| 952 |
+
"loss": 0.0018,
|
| 953 |
+
"step": 14416
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 68.0,
|
| 957 |
+
"eval_loss": 0.6701961755752563,
|
| 958 |
+
"eval_runtime": 3.8617,
|
| 959 |
+
"eval_samples_per_second": 175.054,
|
| 960 |
+
"eval_steps_per_second": 22.011,
|
| 961 |
+
"step": 14416
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 69.0,
|
| 965 |
+
"learning_rate": 6.55e-05,
|
| 966 |
+
"loss": 0.0021,
|
| 967 |
+
"step": 14628
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 69.0,
|
| 971 |
+
"eval_loss": 0.6702686548233032,
|
| 972 |
+
"eval_runtime": 3.8302,
|
| 973 |
+
"eval_samples_per_second": 176.491,
|
| 974 |
+
"eval_steps_per_second": 22.192,
|
| 975 |
+
"step": 14628
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 70.0,
|
| 979 |
+
"learning_rate": 6.500000000000001e-05,
|
| 980 |
+
"loss": 0.0021,
|
| 981 |
+
"step": 14840
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 70.0,
|
| 985 |
+
"eval_loss": 0.6920447945594788,
|
| 986 |
+
"eval_runtime": 4.0139,
|
| 987 |
+
"eval_samples_per_second": 168.416,
|
| 988 |
+
"eval_steps_per_second": 21.177,
|
| 989 |
+
"step": 14840
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 71.0,
|
| 993 |
+
"learning_rate": 6.450000000000001e-05,
|
| 994 |
+
"loss": 0.0046,
|
| 995 |
+
"step": 15052
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 71.0,
|
| 999 |
+
"eval_loss": 0.699743390083313,
|
| 1000 |
+
"eval_runtime": 3.9002,
|
| 1001 |
+
"eval_samples_per_second": 173.325,
|
| 1002 |
+
"eval_steps_per_second": 21.794,
|
| 1003 |
+
"step": 15052
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 72.0,
|
| 1007 |
+
"learning_rate": 6.400000000000001e-05,
|
| 1008 |
+
"loss": 0.0144,
|
| 1009 |
+
"step": 15264
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 72.0,
|
| 1013 |
+
"eval_loss": 0.6702250838279724,
|
| 1014 |
+
"eval_runtime": 3.7414,
|
| 1015 |
+
"eval_samples_per_second": 180.683,
|
| 1016 |
+
"eval_steps_per_second": 22.719,
|
| 1017 |
+
"step": 15264
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 73.0,
|
| 1021 |
+
"learning_rate": 6.35e-05,
|
| 1022 |
+
"loss": 0.0037,
|
| 1023 |
+
"step": 15476
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 73.0,
|
| 1027 |
+
"eval_loss": 0.7095263600349426,
|
| 1028 |
+
"eval_runtime": 3.8916,
|
| 1029 |
+
"eval_samples_per_second": 173.705,
|
| 1030 |
+
"eval_steps_per_second": 21.842,
|
| 1031 |
+
"step": 15476
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 74.0,
|
| 1035 |
+
"learning_rate": 6.3e-05,
|
| 1036 |
+
"loss": 0.0085,
|
| 1037 |
+
"step": 15688
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 74.0,
|
| 1041 |
+
"eval_loss": 0.6826157569885254,
|
| 1042 |
+
"eval_runtime": 3.9747,
|
| 1043 |
+
"eval_samples_per_second": 170.078,
|
| 1044 |
+
"eval_steps_per_second": 21.385,
|
| 1045 |
+
"step": 15688
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 75.0,
|
| 1049 |
+
"learning_rate": 6.25e-05,
|
| 1050 |
+
"loss": 0.0039,
|
| 1051 |
+
"step": 15900
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 75.0,
|
| 1055 |
+
"eval_loss": 0.6942426562309265,
|
| 1056 |
+
"eval_runtime": 3.8678,
|
| 1057 |
+
"eval_samples_per_second": 174.778,
|
| 1058 |
+
"eval_steps_per_second": 21.977,
|
| 1059 |
+
"step": 15900
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 76.0,
|
| 1063 |
+
"learning_rate": 6.2e-05,
|
| 1064 |
+
"loss": 0.0016,
|
| 1065 |
+
"step": 16112
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 76.0,
|
| 1069 |
+
"eval_loss": 0.7053899765014648,
|
| 1070 |
+
"eval_runtime": 3.8974,
|
| 1071 |
+
"eval_samples_per_second": 173.451,
|
| 1072 |
+
"eval_steps_per_second": 21.81,
|
| 1073 |
+
"step": 16112
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 77.0,
|
| 1077 |
+
"learning_rate": 6.15e-05,
|
| 1078 |
+
"loss": 0.0011,
|
| 1079 |
+
"step": 16324
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 77.0,
|
| 1083 |
+
"eval_loss": 0.7109885811805725,
|
| 1084 |
+
"eval_runtime": 3.7815,
|
| 1085 |
+
"eval_samples_per_second": 178.764,
|
| 1086 |
+
"eval_steps_per_second": 22.478,
|
| 1087 |
+
"step": 16324
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 78.0,
|
| 1091 |
+
"learning_rate": 6.1e-05,
|
| 1092 |
+
"loss": 0.003,
|
| 1093 |
+
"step": 16536
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 78.0,
|
| 1097 |
+
"eval_loss": 0.6792702078819275,
|
| 1098 |
+
"eval_runtime": 3.8196,
|
| 1099 |
+
"eval_samples_per_second": 176.984,
|
| 1100 |
+
"eval_steps_per_second": 22.254,
|
| 1101 |
+
"step": 16536
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 79.0,
|
| 1105 |
+
"learning_rate": 6.05e-05,
|
| 1106 |
+
"loss": 0.0042,
|
| 1107 |
+
"step": 16748
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 79.0,
|
| 1111 |
+
"eval_loss": 0.7035090923309326,
|
| 1112 |
+
"eval_runtime": 3.9924,
|
| 1113 |
+
"eval_samples_per_second": 169.321,
|
| 1114 |
+
"eval_steps_per_second": 21.29,
|
| 1115 |
+
"step": 16748
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 80.0,
|
| 1119 |
+
"learning_rate": 6e-05,
|
| 1120 |
+
"loss": 0.001,
|
| 1121 |
+
"step": 16960
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 80.0,
|
| 1125 |
+
"eval_loss": 0.6862510442733765,
|
| 1126 |
+
"eval_runtime": 3.8779,
|
| 1127 |
+
"eval_samples_per_second": 174.319,
|
| 1128 |
+
"eval_steps_per_second": 21.919,
|
| 1129 |
+
"step": 16960
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 81.0,
|
| 1133 |
+
"learning_rate": 5.95e-05,
|
| 1134 |
+
"loss": 0.0046,
|
| 1135 |
+
"step": 17172
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 81.0,
|
| 1139 |
+
"eval_loss": 0.6779678463935852,
|
| 1140 |
+
"eval_runtime": 3.7417,
|
| 1141 |
+
"eval_samples_per_second": 180.666,
|
| 1142 |
+
"eval_steps_per_second": 22.717,
|
| 1143 |
+
"step": 17172
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 82.0,
|
| 1147 |
+
"learning_rate": 5.9e-05,
|
| 1148 |
+
"loss": 0.0029,
|
| 1149 |
+
"step": 17384
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 82.0,
|
| 1153 |
+
"eval_loss": 0.7126826047897339,
|
| 1154 |
+
"eval_runtime": 3.8698,
|
| 1155 |
+
"eval_samples_per_second": 174.684,
|
| 1156 |
+
"eval_steps_per_second": 21.965,
|
| 1157 |
+
"step": 17384
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 83.0,
|
| 1161 |
+
"learning_rate": 5.85e-05,
|
| 1162 |
+
"loss": 0.0037,
|
| 1163 |
+
"step": 17596
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 83.0,
|
| 1167 |
+
"eval_loss": 0.7319346070289612,
|
| 1168 |
+
"eval_runtime": 3.838,
|
| 1169 |
+
"eval_samples_per_second": 176.134,
|
| 1170 |
+
"eval_steps_per_second": 22.147,
|
| 1171 |
+
"step": 17596
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 84.0,
|
| 1175 |
+
"learning_rate": 5.8e-05,
|
| 1176 |
+
"loss": 0.0055,
|
| 1177 |
+
"step": 17808
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 84.0,
|
| 1181 |
+
"eval_loss": 0.7413457036018372,
|
| 1182 |
+
"eval_runtime": 3.8654,
|
| 1183 |
+
"eval_samples_per_second": 174.883,
|
| 1184 |
+
"eval_steps_per_second": 21.99,
|
| 1185 |
+
"step": 17808
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 85.0,
|
| 1189 |
+
"learning_rate": 5.7499999999999995e-05,
|
| 1190 |
+
"loss": 0.0044,
|
| 1191 |
+
"step": 18020
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 85.0,
|
| 1195 |
+
"eval_loss": 0.7252220511436462,
|
| 1196 |
+
"eval_runtime": 3.8294,
|
| 1197 |
+
"eval_samples_per_second": 176.528,
|
| 1198 |
+
"eval_steps_per_second": 22.197,
|
| 1199 |
+
"step": 18020
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 86.0,
|
| 1203 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 1204 |
+
"loss": 0.0071,
|
| 1205 |
+
"step": 18232
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 86.0,
|
| 1209 |
+
"eval_loss": 0.70371013879776,
|
| 1210 |
+
"eval_runtime": 3.9063,
|
| 1211 |
+
"eval_samples_per_second": 173.055,
|
| 1212 |
+
"eval_steps_per_second": 21.76,
|
| 1213 |
+
"step": 18232
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 87.0,
|
| 1217 |
+
"learning_rate": 5.65e-05,
|
| 1218 |
+
"loss": 0.0207,
|
| 1219 |
+
"step": 18444
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 87.0,
|
| 1223 |
+
"eval_loss": 0.7995812296867371,
|
| 1224 |
+
"eval_runtime": 3.9263,
|
| 1225 |
+
"eval_samples_per_second": 172.174,
|
| 1226 |
+
"eval_steps_per_second": 21.649,
|
| 1227 |
+
"step": 18444
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 88.0,
|
| 1231 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 1232 |
+
"loss": 0.0078,
|
| 1233 |
+
"step": 18656
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 88.0,
|
| 1237 |
+
"eval_loss": 0.7264254689216614,
|
| 1238 |
+
"eval_runtime": 3.8379,
|
| 1239 |
+
"eval_samples_per_second": 176.139,
|
| 1240 |
+
"eval_steps_per_second": 22.148,
|
| 1241 |
+
"step": 18656
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 89.0,
|
| 1245 |
+
"learning_rate": 5.550000000000001e-05,
|
| 1246 |
+
"loss": 0.0015,
|
| 1247 |
+
"step": 18868
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 89.0,
|
| 1251 |
+
"eval_loss": 0.764296293258667,
|
| 1252 |
+
"eval_runtime": 3.8408,
|
| 1253 |
+
"eval_samples_per_second": 176.007,
|
| 1254 |
+
"eval_steps_per_second": 22.131,
|
| 1255 |
+
"step": 18868
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 90.0,
|
| 1259 |
+
"learning_rate": 5.500000000000001e-05,
|
| 1260 |
+
"loss": 0.0009,
|
| 1261 |
+
"step": 19080
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 90.0,
|
| 1265 |
+
"eval_loss": 0.7643783092498779,
|
| 1266 |
+
"eval_runtime": 3.8728,
|
| 1267 |
+
"eval_samples_per_second": 174.55,
|
| 1268 |
+
"eval_steps_per_second": 21.948,
|
| 1269 |
+
"step": 19080
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 91.0,
|
| 1273 |
+
"learning_rate": 5.45e-05,
|
| 1274 |
+
"loss": 0.0008,
|
| 1275 |
+
"step": 19292
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 91.0,
|
| 1279 |
+
"eval_loss": 0.7477757334709167,
|
| 1280 |
+
"eval_runtime": 3.7826,
|
| 1281 |
+
"eval_samples_per_second": 178.715,
|
| 1282 |
+
"eval_steps_per_second": 22.472,
|
| 1283 |
+
"step": 19292
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 92.0,
|
| 1287 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 1288 |
+
"loss": 0.0036,
|
| 1289 |
+
"step": 19504
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 92.0,
|
| 1293 |
+
"eval_loss": 0.7721669673919678,
|
| 1294 |
+
"eval_runtime": 3.6218,
|
| 1295 |
+
"eval_samples_per_second": 186.647,
|
| 1296 |
+
"eval_steps_per_second": 23.469,
|
| 1297 |
+
"step": 19504
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 93.0,
|
| 1301 |
+
"learning_rate": 5.3500000000000006e-05,
|
| 1302 |
+
"loss": 0.0018,
|
| 1303 |
+
"step": 19716
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 93.0,
|
| 1307 |
+
"eval_loss": 0.7192530035972595,
|
| 1308 |
+
"eval_runtime": 3.785,
|
| 1309 |
+
"eval_samples_per_second": 178.601,
|
| 1310 |
+
"eval_steps_per_second": 22.457,
|
| 1311 |
+
"step": 19716
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 94.0,
|
| 1315 |
+
"learning_rate": 5.300000000000001e-05,
|
| 1316 |
+
"loss": 0.0043,
|
| 1317 |
+
"step": 19928
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 94.0,
|
| 1321 |
+
"eval_loss": 0.7403692007064819,
|
| 1322 |
+
"eval_runtime": 3.769,
|
| 1323 |
+
"eval_samples_per_second": 179.356,
|
| 1324 |
+
"eval_steps_per_second": 22.552,
|
| 1325 |
+
"step": 19928
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 95.0,
|
| 1329 |
+
"learning_rate": 5.25e-05,
|
| 1330 |
+
"loss": 0.0043,
|
| 1331 |
+
"step": 20140
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 95.0,
|
| 1335 |
+
"eval_loss": 0.7470369338989258,
|
| 1336 |
+
"eval_runtime": 3.8528,
|
| 1337 |
+
"eval_samples_per_second": 175.459,
|
| 1338 |
+
"eval_steps_per_second": 22.062,
|
| 1339 |
+
"step": 20140
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 96.0,
|
| 1343 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 1344 |
+
"loss": 0.006,
|
| 1345 |
+
"step": 20352
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 96.0,
|
| 1349 |
+
"eval_loss": 0.7998442053794861,
|
| 1350 |
+
"eval_runtime": 3.9067,
|
| 1351 |
+
"eval_samples_per_second": 173.035,
|
| 1352 |
+
"eval_steps_per_second": 21.757,
|
| 1353 |
+
"step": 20352
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 97.0,
|
| 1357 |
+
"learning_rate": 5.1500000000000005e-05,
|
| 1358 |
+
"loss": 0.0027,
|
| 1359 |
+
"step": 20564
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 97.0,
|
| 1363 |
+
"eval_loss": 0.7690773010253906,
|
| 1364 |
+
"eval_runtime": 3.99,
|
| 1365 |
+
"eval_samples_per_second": 169.422,
|
| 1366 |
+
"eval_steps_per_second": 21.303,
|
| 1367 |
+
"step": 20564
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 98.0,
|
| 1371 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 1372 |
+
"loss": 0.0007,
|
| 1373 |
+
"step": 20776
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 98.0,
|
| 1377 |
+
"eval_loss": 0.7827473282814026,
|
| 1378 |
+
"eval_runtime": 3.9066,
|
| 1379 |
+
"eval_samples_per_second": 173.04,
|
| 1380 |
+
"eval_steps_per_second": 21.758,
|
| 1381 |
+
"step": 20776
|
| 1382 |
+
}
|
| 1383 |
+
],
|
| 1384 |
+
"logging_steps": 500,
|
| 1385 |
+
"max_steps": 42400,
|
| 1386 |
+
"num_train_epochs": 200,
|
| 1387 |
+
"save_steps": 500,
|
| 1388 |
+
"total_flos": 2.617228703168501e+16,
|
| 1389 |
+
"trial_name": null,
|
| 1390 |
+
"trial_params": null
|
| 1391 |
+
}
|
checkpoint-20776/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbad506d5d7c9f6e6c369455b23a5312c048f6fdad38f9f3772905289326b4f
|
| 3 |
+
size 4155
|