Upload folder using huggingface_hub
Browse files- config.json +35 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1496 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.41.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 251000
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:547b6863464524d22d61544b990505d7ccabab3563c7baf0ac2857a8219dba7d
|
| 3 |
+
size 1115268200
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e7f87ecebb5bdbe5cdb5ef153f261676c544b271188f127cee831708826ff28
|
| 3 |
+
size 2230655994
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3ea5dab427eb64a1c419397f24fa3e4fe1992afa20bef3e387655d114c9caf7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68441ce94bbb7dbbc85ac423727c56c97d19b186275f4d446b62ed2ec268977c
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8730279414559969,
|
| 3 |
+
"best_model_checkpoint": "./MDEBERTA_MLCR-outputs/checkpoint-77000",
|
| 4 |
+
"epoch": 14.238165680473372,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 77000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1849112426035503,
|
| 13 |
+
"grad_norm": 2.0331010818481445,
|
| 14 |
+
"learning_rate": 1.849112426035503e-07,
|
| 15 |
+
"loss": 0.7187,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1849112426035503,
|
| 20 |
+
"eval_accuracy": 0.4890784272935303,
|
| 21 |
+
"eval_f1": 0.0,
|
| 22 |
+
"eval_loss": 0.7106410264968872,
|
| 23 |
+
"eval_precision": 0.0,
|
| 24 |
+
"eval_recall": 0.0,
|
| 25 |
+
"eval_runtime": 71.3076,
|
| 26 |
+
"eval_samples_per_second": 134.824,
|
| 27 |
+
"eval_steps_per_second": 8.428,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.3698224852071006,
|
| 32 |
+
"grad_norm": 3.5357959270477295,
|
| 33 |
+
"learning_rate": 3.698224852071006e-07,
|
| 34 |
+
"loss": 0.6978,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.3698224852071006,
|
| 39 |
+
"eval_accuracy": 0.5269398793426253,
|
| 40 |
+
"eval_f1": 0.6158134820070958,
|
| 41 |
+
"eval_loss": 0.6897135972976685,
|
| 42 |
+
"eval_precision": 0.526277793820387,
|
| 43 |
+
"eval_recall": 0.7420602605863192,
|
| 44 |
+
"eval_runtime": 71.4436,
|
| 45 |
+
"eval_samples_per_second": 134.568,
|
| 46 |
+
"eval_steps_per_second": 8.412,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.5547337278106509,
|
| 51 |
+
"grad_norm": 5.24600887298584,
|
| 52 |
+
"learning_rate": 5.547337278106509e-07,
|
| 53 |
+
"loss": 0.6881,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.5547337278106509,
|
| 58 |
+
"eval_accuracy": 0.5542958185978781,
|
| 59 |
+
"eval_f1": 0.6489143793527243,
|
| 60 |
+
"eval_loss": 0.6817396283149719,
|
| 61 |
+
"eval_precision": 0.5429864253393665,
|
| 62 |
+
"eval_recall": 0.8061889250814332,
|
| 63 |
+
"eval_runtime": 71.3024,
|
| 64 |
+
"eval_samples_per_second": 134.834,
|
| 65 |
+
"eval_steps_per_second": 8.429,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.7396449704142012,
|
| 70 |
+
"grad_norm": 4.388635158538818,
|
| 71 |
+
"learning_rate": 7.396449704142012e-07,
|
| 72 |
+
"loss": 0.6831,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7396449704142012,
|
| 77 |
+
"eval_accuracy": 0.5620969419596422,
|
| 78 |
+
"eval_f1": 0.666561064470141,
|
| 79 |
+
"eval_loss": 0.6732956171035767,
|
| 80 |
+
"eval_precision": 0.5455016852476018,
|
| 81 |
+
"eval_recall": 0.8566775244299675,
|
| 82 |
+
"eval_runtime": 71.4449,
|
| 83 |
+
"eval_samples_per_second": 134.565,
|
| 84 |
+
"eval_steps_per_second": 8.412,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.9245562130177515,
|
| 89 |
+
"grad_norm": 6.712058067321777,
|
| 90 |
+
"learning_rate": 9.245562130177515e-07,
|
| 91 |
+
"loss": 0.6758,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.9245562130177515,
|
| 96 |
+
"eval_accuracy": 0.5701060952777199,
|
| 97 |
+
"eval_f1": 0.47927428499433034,
|
| 98 |
+
"eval_loss": 0.6640639901161194,
|
| 99 |
+
"eval_precision": 0.6287603305785124,
|
| 100 |
+
"eval_recall": 0.38721498371335505,
|
| 101 |
+
"eval_runtime": 71.1928,
|
| 102 |
+
"eval_samples_per_second": 135.042,
|
| 103 |
+
"eval_steps_per_second": 8.442,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.1094674556213018,
|
| 108 |
+
"grad_norm": 5.304254055023193,
|
| 109 |
+
"learning_rate": 1.1094674556213018e-06,
|
| 110 |
+
"loss": 0.6636,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.1094674556213018,
|
| 115 |
+
"eval_accuracy": 0.6098398169336384,
|
| 116 |
+
"eval_f1": 0.6513616507110326,
|
| 117 |
+
"eval_loss": 0.6411445736885071,
|
| 118 |
+
"eval_precision": 0.599281682914315,
|
| 119 |
+
"eval_recall": 0.7133550488599348,
|
| 120 |
+
"eval_runtime": 71.3706,
|
| 121 |
+
"eval_samples_per_second": 134.705,
|
| 122 |
+
"eval_steps_per_second": 8.421,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2943786982248522,
|
| 127 |
+
"grad_norm": 17.199308395385742,
|
| 128 |
+
"learning_rate": 1.294378698224852e-06,
|
| 129 |
+
"loss": 0.6359,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.2943786982248522,
|
| 134 |
+
"eval_accuracy": 0.6711046390680258,
|
| 135 |
+
"eval_f1": 0.7002275312855518,
|
| 136 |
+
"eval_loss": 0.5785636901855469,
|
| 137 |
+
"eval_precision": 0.6552519517388219,
|
| 138 |
+
"eval_recall": 0.7518322475570033,
|
| 139 |
+
"eval_runtime": 71.2372,
|
| 140 |
+
"eval_samples_per_second": 134.958,
|
| 141 |
+
"eval_steps_per_second": 8.437,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.4792899408284024,
|
| 146 |
+
"grad_norm": 17.191123962402344,
|
| 147 |
+
"learning_rate": 1.4792899408284024e-06,
|
| 148 |
+
"loss": 0.5651,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.4792899408284024,
|
| 153 |
+
"eval_accuracy": 0.7214478884959434,
|
| 154 |
+
"eval_f1": 0.6973327305605787,
|
| 155 |
+
"eval_loss": 0.5006158947944641,
|
| 156 |
+
"eval_precision": 0.7837906504065041,
|
| 157 |
+
"eval_recall": 0.6280537459283387,
|
| 158 |
+
"eval_runtime": 71.414,
|
| 159 |
+
"eval_samples_per_second": 134.624,
|
| 160 |
+
"eval_steps_per_second": 8.416,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.6642011834319526,
|
| 165 |
+
"grad_norm": 17.50662612915039,
|
| 166 |
+
"learning_rate": 1.6642011834319525e-06,
|
| 167 |
+
"loss": 0.5189,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.6642011834319526,
|
| 172 |
+
"eval_accuracy": 0.7335136259621385,
|
| 173 |
+
"eval_f1": 0.7180897887323944,
|
| 174 |
+
"eval_loss": 0.4555279016494751,
|
| 175 |
+
"eval_precision": 0.7813697318007663,
|
| 176 |
+
"eval_recall": 0.6642915309446255,
|
| 177 |
+
"eval_runtime": 71.347,
|
| 178 |
+
"eval_samples_per_second": 134.75,
|
| 179 |
+
"eval_steps_per_second": 8.424,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.849112426035503,
|
| 184 |
+
"grad_norm": 11.771262168884277,
|
| 185 |
+
"learning_rate": 1.849112426035503e-06,
|
| 186 |
+
"loss": 0.4782,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.849112426035503,
|
| 191 |
+
"eval_accuracy": 0.7384023299355107,
|
| 192 |
+
"eval_f1": 0.7066371165286364,
|
| 193 |
+
"eval_loss": 0.43298760056495667,
|
| 194 |
+
"eval_precision": 0.827369571155422,
|
| 195 |
+
"eval_recall": 0.6166530944625407,
|
| 196 |
+
"eval_runtime": 71.4997,
|
| 197 |
+
"eval_samples_per_second": 134.462,
|
| 198 |
+
"eval_steps_per_second": 8.406,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.0340236686390534,
|
| 203 |
+
"grad_norm": 11.091800689697266,
|
| 204 |
+
"learning_rate": 1.9962195923734386e-06,
|
| 205 |
+
"loss": 0.4474,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.0340236686390534,
|
| 210 |
+
"eval_accuracy": 0.7443311836904514,
|
| 211 |
+
"eval_f1": 0.754739572939533,
|
| 212 |
+
"eval_loss": 0.41377708315849304,
|
| 213 |
+
"eval_precision": 0.7401174168297456,
|
| 214 |
+
"eval_recall": 0.7699511400651465,
|
| 215 |
+
"eval_runtime": 71.4016,
|
| 216 |
+
"eval_samples_per_second": 134.647,
|
| 217 |
+
"eval_steps_per_second": 8.417,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.2189349112426036,
|
| 222 |
+
"grad_norm": 31.02802276611328,
|
| 223 |
+
"learning_rate": 1.975673898750822e-06,
|
| 224 |
+
"loss": 0.4275,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.2189349112426036,
|
| 229 |
+
"eval_accuracy": 0.7448512585812357,
|
| 230 |
+
"eval_f1": 0.769822651778174,
|
| 231 |
+
"eval_loss": 0.40316781401634216,
|
| 232 |
+
"eval_precision": 0.7140121845082681,
|
| 233 |
+
"eval_recall": 0.8350977198697068,
|
| 234 |
+
"eval_runtime": 71.3228,
|
| 235 |
+
"eval_samples_per_second": 134.796,
|
| 236 |
+
"eval_steps_per_second": 8.426,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.4038461538461537,
|
| 241 |
+
"grad_norm": 30.21622085571289,
|
| 242 |
+
"learning_rate": 1.955128205128205e-06,
|
| 243 |
+
"loss": 0.425,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.4038461538461537,
|
| 248 |
+
"eval_accuracy": 0.7466195132099023,
|
| 249 |
+
"eval_f1": 0.792504258943782,
|
| 250 |
+
"eval_loss": 0.40604618191719055,
|
| 251 |
+
"eval_precision": 0.6813122437024018,
|
| 252 |
+
"eval_recall": 0.9470684039087948,
|
| 253 |
+
"eval_runtime": 71.2177,
|
| 254 |
+
"eval_samples_per_second": 134.995,
|
| 255 |
+
"eval_steps_per_second": 8.439,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.5887573964497044,
|
| 260 |
+
"grad_norm": 7.608345031738281,
|
| 261 |
+
"learning_rate": 1.9345825115055883e-06,
|
| 262 |
+
"loss": 0.4093,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.5887573964497044,
|
| 267 |
+
"eval_accuracy": 0.7550447264406075,
|
| 268 |
+
"eval_f1": 0.7994208329784516,
|
| 269 |
+
"eval_loss": 0.38763341307640076,
|
| 270 |
+
"eval_precision": 0.6872162834968517,
|
| 271 |
+
"eval_recall": 0.9554153094462541,
|
| 272 |
+
"eval_runtime": 71.3556,
|
| 273 |
+
"eval_samples_per_second": 134.734,
|
| 274 |
+
"eval_steps_per_second": 8.423,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.7736686390532546,
|
| 279 |
+
"grad_norm": 18.13289451599121,
|
| 280 |
+
"learning_rate": 1.9140368178829715e-06,
|
| 281 |
+
"loss": 0.4136,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.7736686390532546,
|
| 286 |
+
"eval_accuracy": 0.7645100894528812,
|
| 287 |
+
"eval_f1": 0.7836391437308868,
|
| 288 |
+
"eval_loss": 0.3780820667743683,
|
| 289 |
+
"eval_precision": 0.7384726224783862,
|
| 290 |
+
"eval_recall": 0.8346905537459284,
|
| 291 |
+
"eval_runtime": 71.3682,
|
| 292 |
+
"eval_samples_per_second": 134.71,
|
| 293 |
+
"eval_steps_per_second": 8.421,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.9585798816568047,
|
| 298 |
+
"grad_norm": 18.237754821777344,
|
| 299 |
+
"learning_rate": 1.8934911242603548e-06,
|
| 300 |
+
"loss": 0.4026,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.9585798816568047,
|
| 305 |
+
"eval_accuracy": 0.7601414603702933,
|
| 306 |
+
"eval_f1": 0.8055649241146712,
|
| 307 |
+
"eval_loss": 0.3755676746368408,
|
| 308 |
+
"eval_precision": 0.6875359815774323,
|
| 309 |
+
"eval_recall": 0.9725162866449512,
|
| 310 |
+
"eval_runtime": 71.4592,
|
| 311 |
+
"eval_samples_per_second": 134.538,
|
| 312 |
+
"eval_steps_per_second": 8.41,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.143491124260355,
|
| 317 |
+
"grad_norm": 7.552541255950928,
|
| 318 |
+
"learning_rate": 1.8729454306377385e-06,
|
| 319 |
+
"loss": 0.3895,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.143491124260355,
|
| 324 |
+
"eval_accuracy": 0.7738714374869982,
|
| 325 |
+
"eval_f1": 0.7812877263581489,
|
| 326 |
+
"eval_loss": 0.3771662712097168,
|
| 327 |
+
"eval_precision": 0.7722752585521082,
|
| 328 |
+
"eval_recall": 0.7905130293159609,
|
| 329 |
+
"eval_runtime": 71.6042,
|
| 330 |
+
"eval_samples_per_second": 134.266,
|
| 331 |
+
"eval_steps_per_second": 8.393,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.328402366863905,
|
| 336 |
+
"grad_norm": 22.454090118408203,
|
| 337 |
+
"learning_rate": 1.8523997370151217e-06,
|
| 338 |
+
"loss": 0.3916,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.328402366863905,
|
| 343 |
+
"eval_accuracy": 0.7645100894528812,
|
| 344 |
+
"eval_f1": 0.7874178403755868,
|
| 345 |
+
"eval_loss": 0.3725959360599518,
|
| 346 |
+
"eval_precision": 0.7307424189613105,
|
| 347 |
+
"eval_recall": 0.8536237785016286,
|
| 348 |
+
"eval_runtime": 71.5401,
|
| 349 |
+
"eval_samples_per_second": 134.386,
|
| 350 |
+
"eval_steps_per_second": 8.401,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.5133136094674557,
|
| 355 |
+
"grad_norm": 8.693994522094727,
|
| 356 |
+
"learning_rate": 1.831854043392505e-06,
|
| 357 |
+
"loss": 0.3882,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.5133136094674557,
|
| 362 |
+
"eval_accuracy": 0.7733513625962138,
|
| 363 |
+
"eval_f1": 0.8056026407351236,
|
| 364 |
+
"eval_loss": 0.3690403401851654,
|
| 365 |
+
"eval_precision": 0.717008099094807,
|
| 366 |
+
"eval_recall": 0.9191775244299675,
|
| 367 |
+
"eval_runtime": 71.609,
|
| 368 |
+
"eval_samples_per_second": 134.257,
|
| 369 |
+
"eval_steps_per_second": 8.393,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.698224852071006,
|
| 374 |
+
"grad_norm": 5.8600358963012695,
|
| 375 |
+
"learning_rate": 1.8113083497698882e-06,
|
| 376 |
+
"loss": 0.3901,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.698224852071006,
|
| 381 |
+
"eval_accuracy": 0.783960890368213,
|
| 382 |
+
"eval_f1": 0.780188379722722,
|
| 383 |
+
"eval_loss": 0.3576684594154358,
|
| 384 |
+
"eval_precision": 0.8124311218867093,
|
| 385 |
+
"eval_recall": 0.7504071661237784,
|
| 386 |
+
"eval_runtime": 71.3088,
|
| 387 |
+
"eval_samples_per_second": 134.822,
|
| 388 |
+
"eval_steps_per_second": 8.428,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.883136094674556,
|
| 393 |
+
"grad_norm": 19.961711883544922,
|
| 394 |
+
"learning_rate": 1.7907626561472714e-06,
|
| 395 |
+
"loss": 0.3776,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.883136094674556,
|
| 400 |
+
"eval_accuracy": 0.7951945080091534,
|
| 401 |
+
"eval_f1": 0.8153081324453616,
|
| 402 |
+
"eval_loss": 0.3502472937107086,
|
| 403 |
+
"eval_precision": 0.7559575578361454,
|
| 404 |
+
"eval_recall": 0.884771986970684,
|
| 405 |
+
"eval_runtime": 71.2812,
|
| 406 |
+
"eval_samples_per_second": 134.874,
|
| 407 |
+
"eval_steps_per_second": 8.431,
|
| 408 |
+
"step": 21000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.068047337278107,
|
| 412 |
+
"grad_norm": 5.484897136688232,
|
| 413 |
+
"learning_rate": 1.7702169625246549e-06,
|
| 414 |
+
"loss": 0.3687,
|
| 415 |
+
"step": 22000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.068047337278107,
|
| 419 |
+
"eval_accuracy": 0.7998751820262118,
|
| 420 |
+
"eval_f1": 0.8182848507744617,
|
| 421 |
+
"eval_loss": 0.34667038917541504,
|
| 422 |
+
"eval_precision": 0.7632135306553911,
|
| 423 |
+
"eval_recall": 0.8819218241042345,
|
| 424 |
+
"eval_runtime": 71.5944,
|
| 425 |
+
"eval_samples_per_second": 134.284,
|
| 426 |
+
"eval_steps_per_second": 8.395,
|
| 427 |
+
"step": 22000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.252958579881657,
|
| 431 |
+
"grad_norm": 14.385085105895996,
|
| 432 |
+
"learning_rate": 1.7496712689020381e-06,
|
| 433 |
+
"loss": 0.354,
|
| 434 |
+
"step": 23000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.252958579881657,
|
| 438 |
+
"eval_accuracy": 0.8051799459122113,
|
| 439 |
+
"eval_f1": 0.8130178696216432,
|
| 440 |
+
"eval_loss": 0.3367505669593811,
|
| 441 |
+
"eval_precision": 0.7976493633692459,
|
| 442 |
+
"eval_recall": 0.8289902280130294,
|
| 443 |
+
"eval_runtime": 71.182,
|
| 444 |
+
"eval_samples_per_second": 135.062,
|
| 445 |
+
"eval_steps_per_second": 8.443,
|
| 446 |
+
"step": 23000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.437869822485207,
|
| 450 |
+
"grad_norm": 7.935754776000977,
|
| 451 |
+
"learning_rate": 1.7291255752794214e-06,
|
| 452 |
+
"loss": 0.3498,
|
| 453 |
+
"step": 24000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.437869822485207,
|
| 457 |
+
"eval_accuracy": 0.8109007697108384,
|
| 458 |
+
"eval_f1": 0.8206039076376554,
|
| 459 |
+
"eval_loss": 0.33399322628974915,
|
| 460 |
+
"eval_precision": 0.7962466487935657,
|
| 461 |
+
"eval_recall": 0.8464983713355049,
|
| 462 |
+
"eval_runtime": 71.7203,
|
| 463 |
+
"eval_samples_per_second": 134.048,
|
| 464 |
+
"eval_steps_per_second": 8.38,
|
| 465 |
+
"step": 24000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.622781065088757,
|
| 469 |
+
"grad_norm": 5.013232707977295,
|
| 470 |
+
"learning_rate": 1.7085798816568046e-06,
|
| 471 |
+
"loss": 0.349,
|
| 472 |
+
"step": 25000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 4.622781065088757,
|
| 476 |
+
"eval_accuracy": 0.8079883503224464,
|
| 477 |
+
"eval_f1": 0.8264058679706602,
|
| 478 |
+
"eval_loss": 0.3555152416229248,
|
| 479 |
+
"eval_precision": 0.7679133170220203,
|
| 480 |
+
"eval_recall": 0.8945439739413681,
|
| 481 |
+
"eval_runtime": 71.3751,
|
| 482 |
+
"eval_samples_per_second": 134.697,
|
| 483 |
+
"eval_steps_per_second": 8.42,
|
| 484 |
+
"step": 25000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 4.8076923076923075,
|
| 488 |
+
"grad_norm": 15.721752166748047,
|
| 489 |
+
"learning_rate": 1.688034188034188e-06,
|
| 490 |
+
"loss": 0.3341,
|
| 491 |
+
"step": 26000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.8076923076923075,
|
| 495 |
+
"eval_accuracy": 0.8115248595797795,
|
| 496 |
+
"eval_f1": 0.8270662340141248,
|
| 497 |
+
"eval_loss": 0.3554248809814453,
|
| 498 |
+
"eval_precision": 0.7784764642472153,
|
| 499 |
+
"eval_recall": 0.8821254071661238,
|
| 500 |
+
"eval_runtime": 71.5461,
|
| 501 |
+
"eval_samples_per_second": 134.375,
|
| 502 |
+
"eval_steps_per_second": 8.4,
|
| 503 |
+
"step": 26000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.992603550295858,
|
| 507 |
+
"grad_norm": 21.64997100830078,
|
| 508 |
+
"learning_rate": 1.6674884944115713e-06,
|
| 509 |
+
"loss": 0.3348,
|
| 510 |
+
"step": 27000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 4.992603550295858,
|
| 514 |
+
"eval_accuracy": 0.819742042854171,
|
| 515 |
+
"eval_f1": 0.8303807379857101,
|
| 516 |
+
"eval_loss": 0.3212674856185913,
|
| 517 |
+
"eval_precision": 0.7996229971724788,
|
| 518 |
+
"eval_recall": 0.863599348534202,
|
| 519 |
+
"eval_runtime": 71.2415,
|
| 520 |
+
"eval_samples_per_second": 134.949,
|
| 521 |
+
"eval_steps_per_second": 8.436,
|
| 522 |
+
"step": 27000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 5.177514792899408,
|
| 526 |
+
"grad_norm": 15.086274147033691,
|
| 527 |
+
"learning_rate": 1.6469428007889545e-06,
|
| 528 |
+
"loss": 0.3122,
|
| 529 |
+
"step": 28000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 5.177514792899408,
|
| 533 |
+
"eval_accuracy": 0.8222384023299355,
|
| 534 |
+
"eval_f1": 0.8343510710477852,
|
| 535 |
+
"eval_loss": 0.3286217749118805,
|
| 536 |
+
"eval_precision": 0.7962997224791859,
|
| 537 |
+
"eval_recall": 0.8762214983713354,
|
| 538 |
+
"eval_runtime": 71.5509,
|
| 539 |
+
"eval_samples_per_second": 134.366,
|
| 540 |
+
"eval_steps_per_second": 8.4,
|
| 541 |
+
"step": 28000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.362426035502959,
|
| 545 |
+
"grad_norm": 8.424311637878418,
|
| 546 |
+
"learning_rate": 1.6263971071663378e-06,
|
| 547 |
+
"loss": 0.3024,
|
| 548 |
+
"step": 29000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.362426035502959,
|
| 552 |
+
"eval_accuracy": 0.8286873309756605,
|
| 553 |
+
"eval_f1": 0.835019533206451,
|
| 554 |
+
"eval_loss": 0.32026207447052,
|
| 555 |
+
"eval_precision": 0.8219286136856636,
|
| 556 |
+
"eval_recall": 0.8485342019543974,
|
| 557 |
+
"eval_runtime": 71.2045,
|
| 558 |
+
"eval_samples_per_second": 135.02,
|
| 559 |
+
"eval_steps_per_second": 8.44,
|
| 560 |
+
"step": 29000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 5.547337278106509,
|
| 564 |
+
"grad_norm": 31.459623336791992,
|
| 565 |
+
"learning_rate": 1.605851413543721e-06,
|
| 566 |
+
"loss": 0.3023,
|
| 567 |
+
"step": 30000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 5.547337278106509,
|
| 571 |
+
"eval_accuracy": 0.829831495735386,
|
| 572 |
+
"eval_f1": 0.8446638815039879,
|
| 573 |
+
"eval_loss": 0.32447922229766846,
|
| 574 |
+
"eval_precision": 0.7914590747330961,
|
| 575 |
+
"eval_recall": 0.9055374592833876,
|
| 576 |
+
"eval_runtime": 71.4681,
|
| 577 |
+
"eval_samples_per_second": 134.522,
|
| 578 |
+
"eval_steps_per_second": 8.409,
|
| 579 |
+
"step": 30000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 5.732248520710059,
|
| 583 |
+
"grad_norm": 6.890359878540039,
|
| 584 |
+
"learning_rate": 1.5853057199211045e-06,
|
| 585 |
+
"loss": 0.3049,
|
| 586 |
+
"step": 31000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 5.732248520710059,
|
| 590 |
+
"eval_accuracy": 0.832639900145621,
|
| 591 |
+
"eval_f1": 0.8481072406306052,
|
| 592 |
+
"eval_loss": 0.31333744525909424,
|
| 593 |
+
"eval_precision": 0.7907058616440767,
|
| 594 |
+
"eval_recall": 0.9144951140065146,
|
| 595 |
+
"eval_runtime": 71.3131,
|
| 596 |
+
"eval_samples_per_second": 134.814,
|
| 597 |
+
"eval_steps_per_second": 8.428,
|
| 598 |
+
"step": 31000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 5.9171597633136095,
|
| 602 |
+
"grad_norm": 23.060514450073242,
|
| 603 |
+
"learning_rate": 1.5647600262984877e-06,
|
| 604 |
+
"loss": 0.3039,
|
| 605 |
+
"step": 32000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.9171597633136095,
|
| 609 |
+
"eval_accuracy": 0.8346161847306012,
|
| 610 |
+
"eval_f1": 0.8510957108072673,
|
| 611 |
+
"eval_loss": 0.29815933108329773,
|
| 612 |
+
"eval_precision": 0.78806798473812,
|
| 613 |
+
"eval_recall": 0.9250814332247557,
|
| 614 |
+
"eval_runtime": 71.51,
|
| 615 |
+
"eval_samples_per_second": 134.443,
|
| 616 |
+
"eval_steps_per_second": 8.404,
|
| 617 |
+
"step": 32000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 6.10207100591716,
|
| 621 |
+
"grad_norm": 13.75260066986084,
|
| 622 |
+
"learning_rate": 1.544214332675871e-06,
|
| 623 |
+
"loss": 0.2884,
|
| 624 |
+
"step": 33000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 6.10207100591716,
|
| 628 |
+
"eval_accuracy": 0.8325358851674641,
|
| 629 |
+
"eval_f1": 0.8447743925954493,
|
| 630 |
+
"eval_loss": 0.3285083770751953,
|
| 631 |
+
"eval_precision": 0.8023809523809524,
|
| 632 |
+
"eval_recall": 0.8918973941368078,
|
| 633 |
+
"eval_runtime": 71.4708,
|
| 634 |
+
"eval_samples_per_second": 134.516,
|
| 635 |
+
"eval_steps_per_second": 8.409,
|
| 636 |
+
"step": 33000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 6.28698224852071,
|
| 640 |
+
"grad_norm": 9.07077407836914,
|
| 641 |
+
"learning_rate": 1.5236686390532542e-06,
|
| 642 |
+
"loss": 0.2803,
|
| 643 |
+
"step": 34000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 6.28698224852071,
|
| 647 |
+
"eval_accuracy": 0.8398169336384439,
|
| 648 |
+
"eval_f1": 0.849078792630341,
|
| 649 |
+
"eval_loss": 0.30692258477211,
|
| 650 |
+
"eval_precision": 0.81859410430839,
|
| 651 |
+
"eval_recall": 0.8819218241042345,
|
| 652 |
+
"eval_runtime": 71.54,
|
| 653 |
+
"eval_samples_per_second": 134.386,
|
| 654 |
+
"eval_steps_per_second": 8.401,
|
| 655 |
+
"step": 34000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 6.47189349112426,
|
| 659 |
+
"grad_norm": 31.427412033081055,
|
| 660 |
+
"learning_rate": 1.5031229454306379e-06,
|
| 661 |
+
"loss": 0.2731,
|
| 662 |
+
"step": 35000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.47189349112426,
|
| 666 |
+
"eval_accuracy": 0.8372165591845225,
|
| 667 |
+
"eval_f1": 0.8451261751608115,
|
| 668 |
+
"eval_loss": 0.3197310268878937,
|
| 669 |
+
"eval_precision": 0.822260735605623,
|
| 670 |
+
"eval_recall": 0.869299674267101,
|
| 671 |
+
"eval_runtime": 71.1627,
|
| 672 |
+
"eval_samples_per_second": 135.099,
|
| 673 |
+
"eval_steps_per_second": 8.445,
|
| 674 |
+
"step": 35000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.65680473372781,
|
| 678 |
+
"grad_norm": 18.06778335571289,
|
| 679 |
+
"learning_rate": 1.4825772518080211e-06,
|
| 680 |
+
"loss": 0.2717,
|
| 681 |
+
"step": 36000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.65680473372781,
|
| 685 |
+
"eval_accuracy": 0.8398169336384439,
|
| 686 |
+
"eval_f1": 0.8547717842323651,
|
| 687 |
+
"eval_loss": 0.29738789796829224,
|
| 688 |
+
"eval_precision": 0.7962052002810963,
|
| 689 |
+
"eval_recall": 0.9226384364820847,
|
| 690 |
+
"eval_runtime": 71.4155,
|
| 691 |
+
"eval_samples_per_second": 134.621,
|
| 692 |
+
"eval_steps_per_second": 8.416,
|
| 693 |
+
"step": 36000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.841715976331361,
|
| 697 |
+
"grad_norm": 10.752886772155762,
|
| 698 |
+
"learning_rate": 1.4620315581854044e-06,
|
| 699 |
+
"loss": 0.2764,
|
| 700 |
+
"step": 37000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 6.841715976331361,
|
| 704 |
+
"eval_accuracy": 0.8452257125026004,
|
| 705 |
+
"eval_f1": 0.8565644881434356,
|
| 706 |
+
"eval_loss": 0.2894780933856964,
|
| 707 |
+
"eval_precision": 0.8134383009886489,
|
| 708 |
+
"eval_recall": 0.9045195439739414,
|
| 709 |
+
"eval_runtime": 71.1003,
|
| 710 |
+
"eval_samples_per_second": 135.218,
|
| 711 |
+
"eval_steps_per_second": 8.453,
|
| 712 |
+
"step": 37000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 7.0266272189349115,
|
| 716 |
+
"grad_norm": 9.670276641845703,
|
| 717 |
+
"learning_rate": 1.4414858645627876e-06,
|
| 718 |
+
"loss": 0.2689,
|
| 719 |
+
"step": 38000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 7.0266272189349115,
|
| 723 |
+
"eval_accuracy": 0.8449136675681298,
|
| 724 |
+
"eval_f1": 0.8576882695428081,
|
| 725 |
+
"eval_loss": 0.30610039830207825,
|
| 726 |
+
"eval_precision": 0.8073674752920036,
|
| 727 |
+
"eval_recall": 0.9146986970684039,
|
| 728 |
+
"eval_runtime": 71.4568,
|
| 729 |
+
"eval_samples_per_second": 134.543,
|
| 730 |
+
"eval_steps_per_second": 8.411,
|
| 731 |
+
"step": 38000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 7.211538461538462,
|
| 735 |
+
"grad_norm": 24.961204528808594,
|
| 736 |
+
"learning_rate": 1.4209401709401708e-06,
|
| 737 |
+
"loss": 0.256,
|
| 738 |
+
"step": 39000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 7.211538461538462,
|
| 742 |
+
"eval_accuracy": 0.8429373829831496,
|
| 743 |
+
"eval_f1": 0.8588785046728972,
|
| 744 |
+
"eval_loss": 0.3088281452655792,
|
| 745 |
+
"eval_precision": 0.7938838977194195,
|
| 746 |
+
"eval_recall": 0.9354641693811075,
|
| 747 |
+
"eval_runtime": 71.3164,
|
| 748 |
+
"eval_samples_per_second": 134.808,
|
| 749 |
+
"eval_steps_per_second": 8.427,
|
| 750 |
+
"step": 39000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 7.396449704142012,
|
| 754 |
+
"grad_norm": 11.780752182006836,
|
| 755 |
+
"learning_rate": 1.4003944773175543e-06,
|
| 756 |
+
"loss": 0.2584,
|
| 757 |
+
"step": 40000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 7.396449704142012,
|
| 761 |
+
"eval_accuracy": 0.8485541918036197,
|
| 762 |
+
"eval_f1": 0.858448376433988,
|
| 763 |
+
"eval_loss": 0.28954440355300903,
|
| 764 |
+
"eval_precision": 0.8215481950130257,
|
| 765 |
+
"eval_recall": 0.8988192182410424,
|
| 766 |
+
"eval_runtime": 72.3859,
|
| 767 |
+
"eval_samples_per_second": 132.816,
|
| 768 |
+
"eval_steps_per_second": 8.303,
|
| 769 |
+
"step": 40000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 7.581360946745562,
|
| 773 |
+
"grad_norm": 5.480474472045898,
|
| 774 |
+
"learning_rate": 1.3798487836949375e-06,
|
| 775 |
+
"loss": 0.2559,
|
| 776 |
+
"step": 41000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 7.581360946745562,
|
| 780 |
+
"eval_accuracy": 0.8439775327647181,
|
| 781 |
+
"eval_f1": 0.8532002348796242,
|
| 782 |
+
"eval_loss": 0.3007795214653015,
|
| 783 |
+
"eval_precision": 0.8215228043724085,
|
| 784 |
+
"eval_recall": 0.8874185667752443,
|
| 785 |
+
"eval_runtime": 71.4351,
|
| 786 |
+
"eval_samples_per_second": 134.584,
|
| 787 |
+
"eval_steps_per_second": 8.413,
|
| 788 |
+
"step": 41000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 7.766272189349112,
|
| 792 |
+
"grad_norm": 35.79705047607422,
|
| 793 |
+
"learning_rate": 1.3593030900723208e-06,
|
| 794 |
+
"loss": 0.2583,
|
| 795 |
+
"step": 42000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 7.766272189349112,
|
| 799 |
+
"eval_accuracy": 0.8460578323278553,
|
| 800 |
+
"eval_f1": 0.8545597484276729,
|
| 801 |
+
"eval_loss": 0.30222100019454956,
|
| 802 |
+
"eval_precision": 0.8259878419452887,
|
| 803 |
+
"eval_recall": 0.8851791530944625,
|
| 804 |
+
"eval_runtime": 71.1634,
|
| 805 |
+
"eval_samples_per_second": 135.098,
|
| 806 |
+
"eval_steps_per_second": 8.445,
|
| 807 |
+
"step": 42000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 7.951183431952662,
|
| 811 |
+
"grad_norm": 7.736880779266357,
|
| 812 |
+
"learning_rate": 1.338757396449704e-06,
|
| 813 |
+
"loss": 0.2572,
|
| 814 |
+
"step": 43000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 7.951183431952662,
|
| 818 |
+
"eval_accuracy": 0.8488662367380903,
|
| 819 |
+
"eval_f1": 0.8615003336192927,
|
| 820 |
+
"eval_loss": 0.29688963294029236,
|
| 821 |
+
"eval_precision": 0.8100017924359204,
|
| 822 |
+
"eval_recall": 0.9199918566775245,
|
| 823 |
+
"eval_runtime": 71.4477,
|
| 824 |
+
"eval_samples_per_second": 134.56,
|
| 825 |
+
"eval_steps_per_second": 8.412,
|
| 826 |
+
"step": 43000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 8.136094674556213,
|
| 830 |
+
"grad_norm": 31.98334503173828,
|
| 831 |
+
"learning_rate": 1.3182117028270875e-06,
|
| 832 |
+
"loss": 0.25,
|
| 833 |
+
"step": 44000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 8.136094674556213,
|
| 837 |
+
"eval_accuracy": 0.8475140420220512,
|
| 838 |
+
"eval_f1": 0.8559072144682524,
|
| 839 |
+
"eval_loss": 0.2971686124801636,
|
| 840 |
+
"eval_precision": 0.8274420372481947,
|
| 841 |
+
"eval_recall": 0.886400651465798,
|
| 842 |
+
"eval_runtime": 71.3134,
|
| 843 |
+
"eval_samples_per_second": 134.813,
|
| 844 |
+
"eval_steps_per_second": 8.428,
|
| 845 |
+
"step": 44000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 8.321005917159763,
|
| 849 |
+
"grad_norm": 15.46840763092041,
|
| 850 |
+
"learning_rate": 1.2976660092044707e-06,
|
| 851 |
+
"loss": 0.2384,
|
| 852 |
+
"step": 45000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 8.321005917159763,
|
| 856 |
+
"eval_accuracy": 0.8495943415851883,
|
| 857 |
+
"eval_f1": 0.8559760956175299,
|
| 858 |
+
"eval_loss": 0.29278796911239624,
|
| 859 |
+
"eval_precision": 0.8379485179407177,
|
| 860 |
+
"eval_recall": 0.8747964169381107,
|
| 861 |
+
"eval_runtime": 71.4398,
|
| 862 |
+
"eval_samples_per_second": 134.575,
|
| 863 |
+
"eval_steps_per_second": 8.413,
|
| 864 |
+
"step": 45000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 8.505917159763314,
|
| 868 |
+
"grad_norm": 9.12899112701416,
|
| 869 |
+
"learning_rate": 1.277120315581854e-06,
|
| 870 |
+
"loss": 0.2408,
|
| 871 |
+
"step": 46000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 8.505917159763314,
|
| 875 |
+
"eval_accuracy": 0.8494903266070314,
|
| 876 |
+
"eval_f1": 0.8632454399395142,
|
| 877 |
+
"eval_loss": 0.3010319471359253,
|
| 878 |
+
"eval_precision": 0.8056094549303228,
|
| 879 |
+
"eval_recall": 0.9297638436482085,
|
| 880 |
+
"eval_runtime": 71.1731,
|
| 881 |
+
"eval_samples_per_second": 135.079,
|
| 882 |
+
"eval_steps_per_second": 8.444,
|
| 883 |
+
"step": 46000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 8.690828402366863,
|
| 887 |
+
"grad_norm": 6.4189934730529785,
|
| 888 |
+
"learning_rate": 1.2565746219592372e-06,
|
| 889 |
+
"loss": 0.251,
|
| 890 |
+
"step": 47000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 8.690828402366863,
|
| 894 |
+
"eval_accuracy": 0.853338880798835,
|
| 895 |
+
"eval_f1": 0.8613569321533924,
|
| 896 |
+
"eval_loss": 0.2985897958278656,
|
| 897 |
+
"eval_precision": 0.8330163560289083,
|
| 898 |
+
"eval_recall": 0.8916938110749185,
|
| 899 |
+
"eval_runtime": 71.3021,
|
| 900 |
+
"eval_samples_per_second": 134.835,
|
| 901 |
+
"eval_steps_per_second": 8.429,
|
| 902 |
+
"step": 47000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 8.875739644970414,
|
| 906 |
+
"grad_norm": 28.648107528686523,
|
| 907 |
+
"learning_rate": 1.2360289283366204e-06,
|
| 908 |
+
"loss": 0.2436,
|
| 909 |
+
"step": 48000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 8.875739644970414,
|
| 913 |
+
"eval_accuracy": 0.8517786561264822,
|
| 914 |
+
"eval_f1": 0.8599783826274934,
|
| 915 |
+
"eval_loss": 0.29831263422966003,
|
| 916 |
+
"eval_precision": 0.8311490978157645,
|
| 917 |
+
"eval_recall": 0.8908794788273615,
|
| 918 |
+
"eval_runtime": 71.1941,
|
| 919 |
+
"eval_samples_per_second": 135.039,
|
| 920 |
+
"eval_steps_per_second": 8.442,
|
| 921 |
+
"step": 48000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 9.060650887573965,
|
| 925 |
+
"grad_norm": 15.021607398986816,
|
| 926 |
+
"learning_rate": 1.2154832347140039e-06,
|
| 927 |
+
"loss": 0.2386,
|
| 928 |
+
"step": 49000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 9.060650887573965,
|
| 932 |
+
"eval_accuracy": 0.8550031204493447,
|
| 933 |
+
"eval_f1": 0.864870104691741,
|
| 934 |
+
"eval_loss": 0.30714085698127747,
|
| 935 |
+
"eval_precision": 0.825499629903775,
|
| 936 |
+
"eval_recall": 0.9081840390879479,
|
| 937 |
+
"eval_runtime": 71.3285,
|
| 938 |
+
"eval_samples_per_second": 134.785,
|
| 939 |
+
"eval_steps_per_second": 8.426,
|
| 940 |
+
"step": 49000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 9.245562130177515,
|
| 944 |
+
"grad_norm": 16.410472869873047,
|
| 945 |
+
"learning_rate": 1.1949375410913871e-06,
|
| 946 |
+
"loss": 0.2245,
|
| 947 |
+
"step": 50000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 9.245562130177515,
|
| 951 |
+
"eval_accuracy": 0.8564593301435407,
|
| 952 |
+
"eval_f1": 0.8665893271461717,
|
| 953 |
+
"eval_loss": 0.2869988977909088,
|
| 954 |
+
"eval_precision": 0.8251104565537555,
|
| 955 |
+
"eval_recall": 0.9124592833876222,
|
| 956 |
+
"eval_runtime": 71.7556,
|
| 957 |
+
"eval_samples_per_second": 133.983,
|
| 958 |
+
"eval_steps_per_second": 8.376,
|
| 959 |
+
"step": 50000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 9.430473372781066,
|
| 963 |
+
"grad_norm": 3.089381694793701,
|
| 964 |
+
"learning_rate": 1.1743918474687704e-06,
|
| 965 |
+
"loss": 0.2318,
|
| 966 |
+
"step": 51000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 9.430473372781066,
|
| 970 |
+
"eval_accuracy": 0.8566673600998543,
|
| 971 |
+
"eval_f1": 0.8679570716749713,
|
| 972 |
+
"eval_loss": 0.2949957549571991,
|
| 973 |
+
"eval_precision": 0.8198769007965243,
|
| 974 |
+
"eval_recall": 0.9220276872964169,
|
| 975 |
+
"eval_runtime": 71.3514,
|
| 976 |
+
"eval_samples_per_second": 134.742,
|
| 977 |
+
"eval_steps_per_second": 8.423,
|
| 978 |
+
"step": 51000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.615384615384615,
|
| 982 |
+
"grad_norm": 19.565244674682617,
|
| 983 |
+
"learning_rate": 1.1538461538461536e-06,
|
| 984 |
+
"loss": 0.2348,
|
| 985 |
+
"step": 52000
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.615384615384615,
|
| 989 |
+
"eval_accuracy": 0.8584356147285209,
|
| 990 |
+
"eval_f1": 0.8695485478769289,
|
| 991 |
+
"eval_loss": 0.30221354961395264,
|
| 992 |
+
"eval_precision": 0.8215902916138381,
|
| 993 |
+
"eval_recall": 0.9234527687296417,
|
| 994 |
+
"eval_runtime": 71.2576,
|
| 995 |
+
"eval_samples_per_second": 134.919,
|
| 996 |
+
"eval_steps_per_second": 8.434,
|
| 997 |
+
"step": 52000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 9.800295857988166,
|
| 1001 |
+
"grad_norm": 6.412939548492432,
|
| 1002 |
+
"learning_rate": 1.1333004602235373e-06,
|
| 1003 |
+
"loss": 0.2356,
|
| 1004 |
+
"step": 53000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 9.800295857988166,
|
| 1008 |
+
"eval_accuracy": 0.8553151653838152,
|
| 1009 |
+
"eval_f1": 0.8600744391912283,
|
| 1010 |
+
"eval_loss": 0.2939301133155823,
|
| 1011 |
+
"eval_precision": 0.8500695963412209,
|
| 1012 |
+
"eval_recall": 0.8703175895765473,
|
| 1013 |
+
"eval_runtime": 71.2887,
|
| 1014 |
+
"eval_samples_per_second": 134.86,
|
| 1015 |
+
"eval_steps_per_second": 8.431,
|
| 1016 |
+
"step": 53000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 9.985207100591715,
|
| 1020 |
+
"grad_norm": 24.278528213500977,
|
| 1021 |
+
"learning_rate": 1.1127547666009205e-06,
|
| 1022 |
+
"loss": 0.2274,
|
| 1023 |
+
"step": 54000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 9.985207100591715,
|
| 1027 |
+
"eval_accuracy": 0.8551071354275016,
|
| 1028 |
+
"eval_f1": 0.8684732319894249,
|
| 1029 |
+
"eval_loss": 0.31603407859802246,
|
| 1030 |
+
"eval_precision": 0.8098256735340729,
|
| 1031 |
+
"eval_recall": 0.9362785016286646,
|
| 1032 |
+
"eval_runtime": 71.2443,
|
| 1033 |
+
"eval_samples_per_second": 134.944,
|
| 1034 |
+
"eval_steps_per_second": 8.436,
|
| 1035 |
+
"step": 54000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 10.170118343195266,
|
| 1039 |
+
"grad_norm": 7.386682987213135,
|
| 1040 |
+
"learning_rate": 1.0922090729783038e-06,
|
| 1041 |
+
"loss": 0.2226,
|
| 1042 |
+
"step": 55000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 10.170118343195266,
|
| 1046 |
+
"eval_accuracy": 0.8546910755148741,
|
| 1047 |
+
"eval_f1": 0.8655567317871234,
|
| 1048 |
+
"eval_loss": 0.3250740170478821,
|
| 1049 |
+
"eval_precision": 0.8207702135426173,
|
| 1050 |
+
"eval_recall": 0.9155130293159609,
|
| 1051 |
+
"eval_runtime": 71.3288,
|
| 1052 |
+
"eval_samples_per_second": 134.784,
|
| 1053 |
+
"eval_steps_per_second": 8.426,
|
| 1054 |
+
"step": 55000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 10.355029585798816,
|
| 1058 |
+
"grad_norm": 26.67705535888672,
|
| 1059 |
+
"learning_rate": 1.071663379355687e-06,
|
| 1060 |
+
"loss": 0.225,
|
| 1061 |
+
"step": 56000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 10.355029585798816,
|
| 1065 |
+
"eval_accuracy": 0.8517786561264822,
|
| 1066 |
+
"eval_f1": 0.8643503093764874,
|
| 1067 |
+
"eval_loss": 0.3132619559764862,
|
| 1068 |
+
"eval_precision": 0.8117289468979081,
|
| 1069 |
+
"eval_recall": 0.9242671009771987,
|
| 1070 |
+
"eval_runtime": 71.3488,
|
| 1071 |
+
"eval_samples_per_second": 134.746,
|
| 1072 |
+
"eval_steps_per_second": 8.423,
|
| 1073 |
+
"step": 56000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 10.539940828402367,
|
| 1077 |
+
"grad_norm": 6.816524028778076,
|
| 1078 |
+
"learning_rate": 1.0511176857330705e-06,
|
| 1079 |
+
"loss": 0.2257,
|
| 1080 |
+
"step": 57000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 10.539940828402367,
|
| 1084 |
+
"eval_accuracy": 0.8545870605367173,
|
| 1085 |
+
"eval_f1": 0.8601720344068814,
|
| 1086 |
+
"eval_loss": 0.30009618401527405,
|
| 1087 |
+
"eval_precision": 0.8454581203303185,
|
| 1088 |
+
"eval_recall": 0.8754071661237784,
|
| 1089 |
+
"eval_runtime": 71.2356,
|
| 1090 |
+
"eval_samples_per_second": 134.961,
|
| 1091 |
+
"eval_steps_per_second": 8.437,
|
| 1092 |
+
"step": 57000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 10.724852071005918,
|
| 1096 |
+
"grad_norm": 20.463912963867188,
|
| 1097 |
+
"learning_rate": 1.0305719921104537e-06,
|
| 1098 |
+
"loss": 0.2199,
|
| 1099 |
+
"step": 58000
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 10.724852071005918,
|
| 1103 |
+
"eval_accuracy": 0.8569794050343249,
|
| 1104 |
+
"eval_f1": 0.8605900841528946,
|
| 1105 |
+
"eval_loss": 0.3028598725795746,
|
| 1106 |
+
"eval_precision": 0.8572005655423147,
|
| 1107 |
+
"eval_recall": 0.8640065146579805,
|
| 1108 |
+
"eval_runtime": 71.2275,
|
| 1109 |
+
"eval_samples_per_second": 134.976,
|
| 1110 |
+
"eval_steps_per_second": 8.438,
|
| 1111 |
+
"step": 58000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 10.909763313609467,
|
| 1115 |
+
"grad_norm": 2.745788335800171,
|
| 1116 |
+
"learning_rate": 1.010026298487837e-06,
|
| 1117 |
+
"loss": 0.2235,
|
| 1118 |
+
"step": 59000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 10.909763313609467,
|
| 1122 |
+
"eval_accuracy": 0.8582275847722072,
|
| 1123 |
+
"eval_f1": 0.8604484488584008,
|
| 1124 |
+
"eval_loss": 0.3084582984447479,
|
| 1125 |
+
"eval_precision": 0.8654994850669413,
|
| 1126 |
+
"eval_recall": 0.8554560260586319,
|
| 1127 |
+
"eval_runtime": 71.3104,
|
| 1128 |
+
"eval_samples_per_second": 134.819,
|
| 1129 |
+
"eval_steps_per_second": 8.428,
|
| 1130 |
+
"step": 59000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 11.094674556213018,
|
| 1134 |
+
"grad_norm": 34.805477142333984,
|
| 1135 |
+
"learning_rate": 9.894806048652202e-07,
|
| 1136 |
+
"loss": 0.2149,
|
| 1137 |
+
"step": 60000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 11.094674556213018,
|
| 1141 |
+
"eval_accuracy": 0.856251300187227,
|
| 1142 |
+
"eval_f1": 0.8660073686251697,
|
| 1143 |
+
"eval_loss": 0.3204440772533417,
|
| 1144 |
+
"eval_precision": 0.8267308404294705,
|
| 1145 |
+
"eval_recall": 0.9092019543973942,
|
| 1146 |
+
"eval_runtime": 71.3919,
|
| 1147 |
+
"eval_samples_per_second": 134.665,
|
| 1148 |
+
"eval_steps_per_second": 8.418,
|
| 1149 |
+
"step": 60000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 11.279585798816568,
|
| 1153 |
+
"grad_norm": 0.9099503755569458,
|
| 1154 |
+
"learning_rate": 9.689349112426034e-07,
|
| 1155 |
+
"loss": 0.2105,
|
| 1156 |
+
"step": 61000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 11.279585798816568,
|
| 1160 |
+
"eval_accuracy": 0.8560432702309132,
|
| 1161 |
+
"eval_f1": 0.8661249758173728,
|
| 1162 |
+
"eval_loss": 0.3223714828491211,
|
| 1163 |
+
"eval_precision": 0.8251013638039071,
|
| 1164 |
+
"eval_recall": 0.9114413680781759,
|
| 1165 |
+
"eval_runtime": 71.3086,
|
| 1166 |
+
"eval_samples_per_second": 134.822,
|
| 1167 |
+
"eval_steps_per_second": 8.428,
|
| 1168 |
+
"step": 61000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 11.464497041420119,
|
| 1172 |
+
"grad_norm": 44.76268005371094,
|
| 1173 |
+
"learning_rate": 9.483892176199868e-07,
|
| 1174 |
+
"loss": 0.2196,
|
| 1175 |
+
"step": 62000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 11.464497041420119,
|
| 1179 |
+
"eval_accuracy": 0.853338880798835,
|
| 1180 |
+
"eval_f1": 0.8583199356913184,
|
| 1181 |
+
"eval_loss": 0.3199668824672699,
|
| 1182 |
+
"eval_precision": 0.8474206349206349,
|
| 1183 |
+
"eval_recall": 0.8695032573289903,
|
| 1184 |
+
"eval_runtime": 71.2065,
|
| 1185 |
+
"eval_samples_per_second": 135.016,
|
| 1186 |
+
"eval_steps_per_second": 8.44,
|
| 1187 |
+
"step": 62000
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 11.649408284023668,
|
| 1191 |
+
"grad_norm": 5.310791969299316,
|
| 1192 |
+
"learning_rate": 9.278435239973701e-07,
|
| 1193 |
+
"loss": 0.2112,
|
| 1194 |
+
"step": 63000
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 11.649408284023668,
|
| 1198 |
+
"eval_accuracy": 0.8580195548158935,
|
| 1199 |
+
"eval_f1": 0.8656363815336156,
|
| 1200 |
+
"eval_loss": 0.3171244263648987,
|
| 1201 |
+
"eval_precision": 0.8380026681913474,
|
| 1202 |
+
"eval_recall": 0.8951547231270358,
|
| 1203 |
+
"eval_runtime": 71.347,
|
| 1204 |
+
"eval_samples_per_second": 134.75,
|
| 1205 |
+
"eval_steps_per_second": 8.424,
|
| 1206 |
+
"step": 63000
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 11.834319526627219,
|
| 1210 |
+
"grad_norm": 23.944461822509766,
|
| 1211 |
+
"learning_rate": 9.072978303747534e-07,
|
| 1212 |
+
"loss": 0.2157,
|
| 1213 |
+
"step": 64000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 11.834319526627219,
|
| 1217 |
+
"eval_accuracy": 0.857707509881423,
|
| 1218 |
+
"eval_f1": 0.8635275339185954,
|
| 1219 |
+
"eval_loss": 0.3211972117424011,
|
| 1220 |
+
"eval_precision": 0.8466353677621283,
|
| 1221 |
+
"eval_recall": 0.8811074918566775,
|
| 1222 |
+
"eval_runtime": 71.2358,
|
| 1223 |
+
"eval_samples_per_second": 134.96,
|
| 1224 |
+
"eval_steps_per_second": 8.437,
|
| 1225 |
+
"step": 64000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 12.01923076923077,
|
| 1229 |
+
"grad_norm": 10.31908893585205,
|
| 1230 |
+
"learning_rate": 8.867521367521367e-07,
|
| 1231 |
+
"loss": 0.2221,
|
| 1232 |
+
"step": 65000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 12.01923076923077,
|
| 1236 |
+
"eval_accuracy": 0.8616600790513834,
|
| 1237 |
+
"eval_f1": 0.8634777253130774,
|
| 1238 |
+
"eval_loss": 0.3090285360813141,
|
| 1239 |
+
"eval_precision": 0.8708074534161491,
|
| 1240 |
+
"eval_recall": 0.8562703583061889,
|
| 1241 |
+
"eval_runtime": 71.285,
|
| 1242 |
+
"eval_samples_per_second": 134.867,
|
| 1243 |
+
"eval_steps_per_second": 8.431,
|
| 1244 |
+
"step": 65000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 12.20414201183432,
|
| 1248 |
+
"grad_norm": 10.808996200561523,
|
| 1249 |
+
"learning_rate": 8.6620644312952e-07,
|
| 1250 |
+
"loss": 0.2122,
|
| 1251 |
+
"step": 66000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 12.20414201183432,
|
| 1255 |
+
"eval_accuracy": 0.8554191803619722,
|
| 1256 |
+
"eval_f1": 0.8607214428857716,
|
| 1257 |
+
"eval_loss": 0.32709065079689026,
|
| 1258 |
+
"eval_precision": 0.8474743488555643,
|
| 1259 |
+
"eval_recall": 0.8743892508143323,
|
| 1260 |
+
"eval_runtime": 71.3543,
|
| 1261 |
+
"eval_samples_per_second": 134.736,
|
| 1262 |
+
"eval_steps_per_second": 8.423,
|
| 1263 |
+
"step": 66000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 12.38905325443787,
|
| 1267 |
+
"grad_norm": 36.5963020324707,
|
| 1268 |
+
"learning_rate": 8.456607495069034e-07,
|
| 1269 |
+
"loss": 0.2087,
|
| 1270 |
+
"step": 67000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 12.38905325443787,
|
| 1274 |
+
"eval_accuracy": 0.8594757645100894,
|
| 1275 |
+
"eval_f1": 0.8617619973396091,
|
| 1276 |
+
"eval_loss": 0.31520143151283264,
|
| 1277 |
+
"eval_precision": 0.8662826578893232,
|
| 1278 |
+
"eval_recall": 0.8572882736156352,
|
| 1279 |
+
"eval_runtime": 71.4929,
|
| 1280 |
+
"eval_samples_per_second": 134.475,
|
| 1281 |
+
"eval_steps_per_second": 8.406,
|
| 1282 |
+
"step": 67000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 12.57396449704142,
|
| 1286 |
+
"grad_norm": 69.17304229736328,
|
| 1287 |
+
"learning_rate": 8.251150558842866e-07,
|
| 1288 |
+
"loss": 0.2053,
|
| 1289 |
+
"step": 68000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 12.57396449704142,
|
| 1293 |
+
"eval_accuracy": 0.857603494903266,
|
| 1294 |
+
"eval_f1": 0.8651630060080764,
|
| 1295 |
+
"eval_loss": 0.32987838983535767,
|
| 1296 |
+
"eval_precision": 0.8380080137378363,
|
| 1297 |
+
"eval_recall": 0.8941368078175895,
|
| 1298 |
+
"eval_runtime": 71.5274,
|
| 1299 |
+
"eval_samples_per_second": 134.41,
|
| 1300 |
+
"eval_steps_per_second": 8.402,
|
| 1301 |
+
"step": 68000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 12.75887573964497,
|
| 1305 |
+
"grad_norm": 22.708887100219727,
|
| 1306 |
+
"learning_rate": 8.045693622616699e-07,
|
| 1307 |
+
"loss": 0.2124,
|
| 1308 |
+
"step": 69000
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 12.75887573964497,
|
| 1312 |
+
"eval_accuracy": 0.8570834200124818,
|
| 1313 |
+
"eval_f1": 0.8667054714784633,
|
| 1314 |
+
"eval_loss": 0.33354252576828003,
|
| 1315 |
+
"eval_precision": 0.8278354336545589,
|
| 1316 |
+
"eval_recall": 0.9094055374592834,
|
| 1317 |
+
"eval_runtime": 71.3908,
|
| 1318 |
+
"eval_samples_per_second": 134.667,
|
| 1319 |
+
"eval_steps_per_second": 8.418,
|
| 1320 |
+
"step": 69000
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 12.94378698224852,
|
| 1324 |
+
"grad_norm": 20.74620246887207,
|
| 1325 |
+
"learning_rate": 7.840236686390532e-07,
|
| 1326 |
+
"loss": 0.2086,
|
| 1327 |
+
"step": 70000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 12.94378698224852,
|
| 1331 |
+
"eval_accuracy": 0.8591637195756189,
|
| 1332 |
+
"eval_f1": 0.8646,
|
| 1333 |
+
"eval_loss": 0.32121601700782776,
|
| 1334 |
+
"eval_precision": 0.8496462264150944,
|
| 1335 |
+
"eval_recall": 0.8800895765472313,
|
| 1336 |
+
"eval_runtime": 71.264,
|
| 1337 |
+
"eval_samples_per_second": 134.907,
|
| 1338 |
+
"eval_steps_per_second": 8.433,
|
| 1339 |
+
"step": 70000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 13.128698224852071,
|
| 1343 |
+
"grad_norm": 191.69613647460938,
|
| 1344 |
+
"learning_rate": 7.634779750164365e-07,
|
| 1345 |
+
"loss": 0.2016,
|
| 1346 |
+
"step": 71000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 13.128698224852071,
|
| 1350 |
+
"eval_accuracy": 0.8614520490950697,
|
| 1351 |
+
"eval_f1": 0.8714781937475878,
|
| 1352 |
+
"eval_loss": 0.32725852727890015,
|
| 1353 |
+
"eval_precision": 0.8283198826118855,
|
| 1354 |
+
"eval_recall": 0.9193811074918566,
|
| 1355 |
+
"eval_runtime": 71.3109,
|
| 1356 |
+
"eval_samples_per_second": 134.818,
|
| 1357 |
+
"eval_steps_per_second": 8.428,
|
| 1358 |
+
"step": 71000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 13.31360946745562,
|
| 1362 |
+
"grad_norm": 9.116983413696289,
|
| 1363 |
+
"learning_rate": 7.429322813938198e-07,
|
| 1364 |
+
"loss": 0.2026,
|
| 1365 |
+
"step": 72000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 13.31360946745562,
|
| 1369 |
+
"eval_accuracy": 0.8582275847722072,
|
| 1370 |
+
"eval_f1": 0.8682455292411793,
|
| 1371 |
+
"eval_loss": 0.3508372902870178,
|
| 1372 |
+
"eval_precision": 0.8266151297625621,
|
| 1373 |
+
"eval_recall": 0.9142915309446255,
|
| 1374 |
+
"eval_runtime": 71.2132,
|
| 1375 |
+
"eval_samples_per_second": 135.003,
|
| 1376 |
+
"eval_steps_per_second": 8.439,
|
| 1377 |
+
"step": 72000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 13.498520710059172,
|
| 1381 |
+
"grad_norm": 4.702348232269287,
|
| 1382 |
+
"learning_rate": 7.223865877712031e-07,
|
| 1383 |
+
"loss": 0.2006,
|
| 1384 |
+
"step": 73000
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 13.498520710059172,
|
| 1388 |
+
"eval_accuracy": 0.8582275847722072,
|
| 1389 |
+
"eval_f1": 0.8654624420096733,
|
| 1390 |
+
"eval_loss": 0.34033337235450745,
|
| 1391 |
+
"eval_precision": 0.8400076643035064,
|
| 1392 |
+
"eval_recall": 0.8925081433224755,
|
| 1393 |
+
"eval_runtime": 71.1462,
|
| 1394 |
+
"eval_samples_per_second": 135.13,
|
| 1395 |
+
"eval_steps_per_second": 8.447,
|
| 1396 |
+
"step": 73000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 13.683431952662723,
|
| 1400 |
+
"grad_norm": 29.501680374145508,
|
| 1401 |
+
"learning_rate": 7.018408941485864e-07,
|
| 1402 |
+
"loss": 0.2064,
|
| 1403 |
+
"step": 74000
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 13.683431952662723,
|
| 1407 |
+
"eval_accuracy": 0.8606199292698149,
|
| 1408 |
+
"eval_f1": 0.863876472978464,
|
| 1409 |
+
"eval_loss": 0.3424365222454071,
|
| 1410 |
+
"eval_precision": 0.862124898621249,
|
| 1411 |
+
"eval_recall": 0.8656351791530945,
|
| 1412 |
+
"eval_runtime": 71.1345,
|
| 1413 |
+
"eval_samples_per_second": 135.152,
|
| 1414 |
+
"eval_steps_per_second": 8.449,
|
| 1415 |
+
"step": 74000
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 13.868343195266272,
|
| 1419 |
+
"grad_norm": 2.9182920455932617,
|
| 1420 |
+
"learning_rate": 6.812952005259697e-07,
|
| 1421 |
+
"loss": 0.2071,
|
| 1422 |
+
"step": 75000
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 13.868343195266272,
|
| 1426 |
+
"eval_accuracy": 0.8584356147285209,
|
| 1427 |
+
"eval_f1": 0.8673101296675441,
|
| 1428 |
+
"eval_loss": 0.33476874232292175,
|
| 1429 |
+
"eval_precision": 0.832179607109448,
|
| 1430 |
+
"eval_recall": 0.9055374592833876,
|
| 1431 |
+
"eval_runtime": 71.1759,
|
| 1432 |
+
"eval_samples_per_second": 135.074,
|
| 1433 |
+
"eval_steps_per_second": 8.444,
|
| 1434 |
+
"step": 75000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 14.053254437869823,
|
| 1438 |
+
"grad_norm": 27.45977020263672,
|
| 1439 |
+
"learning_rate": 6.607495069033531e-07,
|
| 1440 |
+
"loss": 0.1996,
|
| 1441 |
+
"step": 76000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 14.053254437869823,
|
| 1445 |
+
"eval_accuracy": 0.8590597045974621,
|
| 1446 |
+
"eval_f1": 0.86776617546599,
|
| 1447 |
+
"eval_loss": 0.32783225178718567,
|
| 1448 |
+
"eval_precision": 0.8333645735707591,
|
| 1449 |
+
"eval_recall": 0.9051302931596091,
|
| 1450 |
+
"eval_runtime": 71.2136,
|
| 1451 |
+
"eval_samples_per_second": 135.002,
|
| 1452 |
+
"eval_steps_per_second": 8.439,
|
| 1453 |
+
"step": 76000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 14.238165680473372,
|
| 1457 |
+
"grad_norm": 28.44346046447754,
|
| 1458 |
+
"learning_rate": 6.402038132807364e-07,
|
| 1459 |
+
"loss": 0.1946,
|
| 1460 |
+
"step": 77000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 14.238165680473372,
|
| 1464 |
+
"eval_accuracy": 0.8610359891824423,
|
| 1465 |
+
"eval_f1": 0.8730279414559969,
|
| 1466 |
+
"eval_loss": 0.33918145298957825,
|
| 1467 |
+
"eval_precision": 0.818716577540107,
|
| 1468 |
+
"eval_recall": 0.935057003257329,
|
| 1469 |
+
"eval_runtime": 71.1883,
|
| 1470 |
+
"eval_samples_per_second": 135.05,
|
| 1471 |
+
"eval_steps_per_second": 8.442,
|
| 1472 |
+
"step": 77000
|
| 1473 |
+
}
|
| 1474 |
+
],
|
| 1475 |
+
"logging_steps": 1000,
|
| 1476 |
+
"max_steps": 108160,
|
| 1477 |
+
"num_input_tokens_seen": 0,
|
| 1478 |
+
"num_train_epochs": 20,
|
| 1479 |
+
"save_steps": 1000,
|
| 1480 |
+
"stateful_callbacks": {
|
| 1481 |
+
"TrainerControl": {
|
| 1482 |
+
"args": {
|
| 1483 |
+
"should_epoch_stop": false,
|
| 1484 |
+
"should_evaluate": false,
|
| 1485 |
+
"should_log": false,
|
| 1486 |
+
"should_save": true,
|
| 1487 |
+
"should_training_stop": false
|
| 1488 |
+
},
|
| 1489 |
+
"attributes": {}
|
| 1490 |
+
}
|
| 1491 |
+
},
|
| 1492 |
+
"total_flos": 2.5466830173511814e+17,
|
| 1493 |
+
"train_batch_size": 16,
|
| 1494 |
+
"trial_name": null,
|
| 1495 |
+
"trial_params": null
|
| 1496 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed1901b34b5dfb74ebd34caece50722799a47da6dd5246206bd9248b34cfaba
|
| 3 |
+
size 5048
|