Upload folder using huggingface_hub
Browse files- config.json +29 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1682 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.38.0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250002
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2c4235e0122df8053e5b145ce022717e48f8b11f7ae6b8747405efa073ab860
|
| 3 |
+
size 2239618672
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5fe5a3a9c7de4dff2e4a0a958fda8ad34f65f134b8eb103f3940d2af4ef5b11
|
| 3 |
+
size 4479472721
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb3ca69ddef97a508052d0fb90faf53edae00a390ad05f5f5e1d42c9e09606d9
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:261690907322abaddd2cd63061922e342503711f5208de9f0dbbbb4535b0bbd4
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1682 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.20471014082431793,
|
| 3 |
+
"best_model_checkpoint": "./results_all/checkpoint-2000",
|
| 4 |
+
"epoch": 9.945750452079565,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 11000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 5.776618480682373,
|
| 14 |
+
"learning_rate": 9.954792043399639e-06,
|
| 15 |
+
"loss": 0.4562,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09,
|
| 20 |
+
"grad_norm": 4.7439141273498535,
|
| 21 |
+
"learning_rate": 9.909584086799278e-06,
|
| 22 |
+
"loss": 0.2825,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14,
|
| 27 |
+
"grad_norm": 8.098787307739258,
|
| 28 |
+
"learning_rate": 9.864376130198916e-06,
|
| 29 |
+
"loss": 0.248,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18,
|
| 34 |
+
"grad_norm": 4.512809753417969,
|
| 35 |
+
"learning_rate": 9.819168173598554e-06,
|
| 36 |
+
"loss": 0.2309,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.23,
|
| 41 |
+
"grad_norm": 4.11778450012207,
|
| 42 |
+
"learning_rate": 9.773960216998193e-06,
|
| 43 |
+
"loss": 0.2357,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"grad_norm": 2.7208287715911865,
|
| 49 |
+
"learning_rate": 9.728752260397831e-06,
|
| 50 |
+
"loss": 0.2285,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.32,
|
| 55 |
+
"grad_norm": 5.254836082458496,
|
| 56 |
+
"learning_rate": 9.68354430379747e-06,
|
| 57 |
+
"loss": 0.2189,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.36,
|
| 62 |
+
"grad_norm": 6.350110054016113,
|
| 63 |
+
"learning_rate": 9.638336347197107e-06,
|
| 64 |
+
"loss": 0.2197,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.41,
|
| 69 |
+
"grad_norm": 3.0524585247039795,
|
| 70 |
+
"learning_rate": 9.593128390596746e-06,
|
| 71 |
+
"loss": 0.2108,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.45,
|
| 76 |
+
"grad_norm": 3.113680362701416,
|
| 77 |
+
"learning_rate": 9.547920433996384e-06,
|
| 78 |
+
"loss": 0.206,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5,
|
| 83 |
+
"grad_norm": 3.020354986190796,
|
| 84 |
+
"learning_rate": 9.502712477396022e-06,
|
| 85 |
+
"loss": 0.2123,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.54,
|
| 90 |
+
"grad_norm": 3.340101480484009,
|
| 91 |
+
"learning_rate": 9.457504520795661e-06,
|
| 92 |
+
"loss": 0.2137,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.59,
|
| 97 |
+
"grad_norm": 4.386758804321289,
|
| 98 |
+
"learning_rate": 9.412296564195299e-06,
|
| 99 |
+
"loss": 0.2071,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.63,
|
| 104 |
+
"grad_norm": 4.073632717132568,
|
| 105 |
+
"learning_rate": 9.367088607594937e-06,
|
| 106 |
+
"loss": 0.2063,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.68,
|
| 111 |
+
"grad_norm": 2.6999106407165527,
|
| 112 |
+
"learning_rate": 9.321880650994576e-06,
|
| 113 |
+
"loss": 0.2089,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.72,
|
| 118 |
+
"grad_norm": 2.527625322341919,
|
| 119 |
+
"learning_rate": 9.276672694394214e-06,
|
| 120 |
+
"loss": 0.2025,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.77,
|
| 125 |
+
"grad_norm": 3.8473989963531494,
|
| 126 |
+
"learning_rate": 9.231464737793852e-06,
|
| 127 |
+
"loss": 0.2059,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.81,
|
| 132 |
+
"grad_norm": 2.255798816680908,
|
| 133 |
+
"learning_rate": 9.186256781193491e-06,
|
| 134 |
+
"loss": 0.2018,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.86,
|
| 139 |
+
"grad_norm": 3.915482521057129,
|
| 140 |
+
"learning_rate": 9.14104882459313e-06,
|
| 141 |
+
"loss": 0.1985,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9,
|
| 146 |
+
"grad_norm": 2.375387191772461,
|
| 147 |
+
"learning_rate": 9.095840867992769e-06,
|
| 148 |
+
"loss": 0.2014,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9,
|
| 153 |
+
"eval_accuracy": 0.9132575757575757,
|
| 154 |
+
"eval_auc": 0.9716989722609015,
|
| 155 |
+
"eval_f1": 0.875638101444553,
|
| 156 |
+
"eval_loss": 0.20884743332862854,
|
| 157 |
+
"eval_runtime": 53.4002,
|
| 158 |
+
"eval_samples_per_second": 247.19,
|
| 159 |
+
"eval_steps_per_second": 3.876,
|
| 160 |
+
"step": 1000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.95,
|
| 164 |
+
"grad_norm": 3.186845302581787,
|
| 165 |
+
"learning_rate": 9.050632911392407e-06,
|
| 166 |
+
"loss": 0.1916,
|
| 167 |
+
"step": 1050
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.99,
|
| 171 |
+
"grad_norm": 3.6988000869750977,
|
| 172 |
+
"learning_rate": 9.005424954792044e-06,
|
| 173 |
+
"loss": 0.1913,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.04,
|
| 178 |
+
"grad_norm": 3.2452192306518555,
|
| 179 |
+
"learning_rate": 8.960216998191682e-06,
|
| 180 |
+
"loss": 0.1836,
|
| 181 |
+
"step": 1150
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.08,
|
| 185 |
+
"grad_norm": 3.898977041244507,
|
| 186 |
+
"learning_rate": 8.91500904159132e-06,
|
| 187 |
+
"loss": 0.1848,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.13,
|
| 192 |
+
"grad_norm": 1.8791488409042358,
|
| 193 |
+
"learning_rate": 8.86980108499096e-06,
|
| 194 |
+
"loss": 0.1812,
|
| 195 |
+
"step": 1250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.18,
|
| 199 |
+
"grad_norm": 3.3532564640045166,
|
| 200 |
+
"learning_rate": 8.824593128390597e-06,
|
| 201 |
+
"loss": 0.1785,
|
| 202 |
+
"step": 1300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.22,
|
| 206 |
+
"grad_norm": 3.177605390548706,
|
| 207 |
+
"learning_rate": 8.779385171790235e-06,
|
| 208 |
+
"loss": 0.1888,
|
| 209 |
+
"step": 1350
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.27,
|
| 213 |
+
"grad_norm": 4.205639362335205,
|
| 214 |
+
"learning_rate": 8.734177215189874e-06,
|
| 215 |
+
"loss": 0.1807,
|
| 216 |
+
"step": 1400
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.31,
|
| 220 |
+
"grad_norm": 2.800039052963257,
|
| 221 |
+
"learning_rate": 8.688969258589512e-06,
|
| 222 |
+
"loss": 0.1851,
|
| 223 |
+
"step": 1450
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.36,
|
| 227 |
+
"grad_norm": 3.714484930038452,
|
| 228 |
+
"learning_rate": 8.64376130198915e-06,
|
| 229 |
+
"loss": 0.1854,
|
| 230 |
+
"step": 1500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4,
|
| 234 |
+
"grad_norm": 3.9688687324523926,
|
| 235 |
+
"learning_rate": 8.59855334538879e-06,
|
| 236 |
+
"loss": 0.1781,
|
| 237 |
+
"step": 1550
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.45,
|
| 241 |
+
"grad_norm": 3.0902647972106934,
|
| 242 |
+
"learning_rate": 8.553345388788427e-06,
|
| 243 |
+
"loss": 0.1789,
|
| 244 |
+
"step": 1600
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.49,
|
| 248 |
+
"grad_norm": 2.457174301147461,
|
| 249 |
+
"learning_rate": 8.508137432188067e-06,
|
| 250 |
+
"loss": 0.1743,
|
| 251 |
+
"step": 1650
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.54,
|
| 255 |
+
"grad_norm": 2.403961420059204,
|
| 256 |
+
"learning_rate": 8.462929475587705e-06,
|
| 257 |
+
"loss": 0.1854,
|
| 258 |
+
"step": 1700
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.58,
|
| 262 |
+
"grad_norm": 4.13264274597168,
|
| 263 |
+
"learning_rate": 8.417721518987342e-06,
|
| 264 |
+
"loss": 0.1833,
|
| 265 |
+
"step": 1750
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.63,
|
| 269 |
+
"grad_norm": 3.0983669757843018,
|
| 270 |
+
"learning_rate": 8.372513562386982e-06,
|
| 271 |
+
"loss": 0.1796,
|
| 272 |
+
"step": 1800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.67,
|
| 276 |
+
"grad_norm": 2.797614812850952,
|
| 277 |
+
"learning_rate": 8.327305605786618e-06,
|
| 278 |
+
"loss": 0.1745,
|
| 279 |
+
"step": 1850
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.72,
|
| 283 |
+
"grad_norm": 2.1761841773986816,
|
| 284 |
+
"learning_rate": 8.282097649186258e-06,
|
| 285 |
+
"loss": 0.1738,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.76,
|
| 290 |
+
"grad_norm": 2.973947286605835,
|
| 291 |
+
"learning_rate": 8.236889692585895e-06,
|
| 292 |
+
"loss": 0.1756,
|
| 293 |
+
"step": 1950
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.81,
|
| 297 |
+
"grad_norm": 3.152864694595337,
|
| 298 |
+
"learning_rate": 8.191681735985533e-06,
|
| 299 |
+
"loss": 0.1755,
|
| 300 |
+
"step": 2000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.81,
|
| 304 |
+
"eval_accuracy": 0.9200757575757575,
|
| 305 |
+
"eval_auc": 0.974728335511236,
|
| 306 |
+
"eval_f1": 0.8865225341508013,
|
| 307 |
+
"eval_loss": 0.20471014082431793,
|
| 308 |
+
"eval_runtime": 53.1495,
|
| 309 |
+
"eval_samples_per_second": 248.356,
|
| 310 |
+
"eval_steps_per_second": 3.895,
|
| 311 |
+
"step": 2000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.85,
|
| 315 |
+
"grad_norm": 2.979734420776367,
|
| 316 |
+
"learning_rate": 8.146473779385173e-06,
|
| 317 |
+
"loss": 0.1762,
|
| 318 |
+
"step": 2050
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.9,
|
| 322 |
+
"grad_norm": 2.802384853363037,
|
| 323 |
+
"learning_rate": 8.10126582278481e-06,
|
| 324 |
+
"loss": 0.1764,
|
| 325 |
+
"step": 2100
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.94,
|
| 329 |
+
"grad_norm": 4.056249618530273,
|
| 330 |
+
"learning_rate": 8.056057866184448e-06,
|
| 331 |
+
"loss": 0.1786,
|
| 332 |
+
"step": 2150
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.99,
|
| 336 |
+
"grad_norm": 3.7627487182617188,
|
| 337 |
+
"learning_rate": 8.010849909584088e-06,
|
| 338 |
+
"loss": 0.1755,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.03,
|
| 343 |
+
"grad_norm": 2.634819984436035,
|
| 344 |
+
"learning_rate": 7.965641952983726e-06,
|
| 345 |
+
"loss": 0.1642,
|
| 346 |
+
"step": 2250
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.08,
|
| 350 |
+
"grad_norm": 3.3615341186523438,
|
| 351 |
+
"learning_rate": 7.920433996383365e-06,
|
| 352 |
+
"loss": 0.1581,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.12,
|
| 357 |
+
"grad_norm": 3.702347993850708,
|
| 358 |
+
"learning_rate": 7.875226039783003e-06,
|
| 359 |
+
"loss": 0.1597,
|
| 360 |
+
"step": 2350
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.17,
|
| 364 |
+
"grad_norm": 11.943075180053711,
|
| 365 |
+
"learning_rate": 7.83001808318264e-06,
|
| 366 |
+
"loss": 0.1565,
|
| 367 |
+
"step": 2400
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.22,
|
| 371 |
+
"grad_norm": 4.544873237609863,
|
| 372 |
+
"learning_rate": 7.78481012658228e-06,
|
| 373 |
+
"loss": 0.1607,
|
| 374 |
+
"step": 2450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.26,
|
| 378 |
+
"grad_norm": 3.886201858520508,
|
| 379 |
+
"learning_rate": 7.739602169981918e-06,
|
| 380 |
+
"loss": 0.155,
|
| 381 |
+
"step": 2500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.31,
|
| 385 |
+
"grad_norm": 2.688396692276001,
|
| 386 |
+
"learning_rate": 7.694394213381556e-06,
|
| 387 |
+
"loss": 0.1637,
|
| 388 |
+
"step": 2550
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.35,
|
| 392 |
+
"grad_norm": 4.257401466369629,
|
| 393 |
+
"learning_rate": 7.649186256781194e-06,
|
| 394 |
+
"loss": 0.1518,
|
| 395 |
+
"step": 2600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.4,
|
| 399 |
+
"grad_norm": 3.5023510456085205,
|
| 400 |
+
"learning_rate": 7.603978300180832e-06,
|
| 401 |
+
"loss": 0.1545,
|
| 402 |
+
"step": 2650
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.44,
|
| 406 |
+
"grad_norm": 3.3911523818969727,
|
| 407 |
+
"learning_rate": 7.558770343580471e-06,
|
| 408 |
+
"loss": 0.1587,
|
| 409 |
+
"step": 2700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.49,
|
| 413 |
+
"grad_norm": 3.0427675247192383,
|
| 414 |
+
"learning_rate": 7.513562386980109e-06,
|
| 415 |
+
"loss": 0.1592,
|
| 416 |
+
"step": 2750
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.53,
|
| 420 |
+
"grad_norm": 3.7051773071289062,
|
| 421 |
+
"learning_rate": 7.468354430379747e-06,
|
| 422 |
+
"loss": 0.1643,
|
| 423 |
+
"step": 2800
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.58,
|
| 427 |
+
"grad_norm": 3.8492684364318848,
|
| 428 |
+
"learning_rate": 7.423146473779386e-06,
|
| 429 |
+
"loss": 0.1554,
|
| 430 |
+
"step": 2850
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.62,
|
| 434 |
+
"grad_norm": 2.938525676727295,
|
| 435 |
+
"learning_rate": 7.377938517179024e-06,
|
| 436 |
+
"loss": 0.1612,
|
| 437 |
+
"step": 2900
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.67,
|
| 441 |
+
"grad_norm": 2.807177782058716,
|
| 442 |
+
"learning_rate": 7.3327305605786624e-06,
|
| 443 |
+
"loss": 0.1559,
|
| 444 |
+
"step": 2950
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.71,
|
| 448 |
+
"grad_norm": 2.838815212249756,
|
| 449 |
+
"learning_rate": 7.287522603978301e-06,
|
| 450 |
+
"loss": 0.1586,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.71,
|
| 455 |
+
"eval_accuracy": 0.9209848484848485,
|
| 456 |
+
"eval_auc": 0.9746563484736904,
|
| 457 |
+
"eval_f1": 0.885447556287754,
|
| 458 |
+
"eval_loss": 0.2061145007610321,
|
| 459 |
+
"eval_runtime": 53.3625,
|
| 460 |
+
"eval_samples_per_second": 247.365,
|
| 461 |
+
"eval_steps_per_second": 3.879,
|
| 462 |
+
"step": 3000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.76,
|
| 466 |
+
"grad_norm": 3.3024938106536865,
|
| 467 |
+
"learning_rate": 7.24231464737794e-06,
|
| 468 |
+
"loss": 0.1613,
|
| 469 |
+
"step": 3050
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.8,
|
| 473 |
+
"grad_norm": 3.188176393508911,
|
| 474 |
+
"learning_rate": 7.1971066907775775e-06,
|
| 475 |
+
"loss": 0.1613,
|
| 476 |
+
"step": 3100
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.85,
|
| 480 |
+
"grad_norm": 2.8831701278686523,
|
| 481 |
+
"learning_rate": 7.151898734177216e-06,
|
| 482 |
+
"loss": 0.152,
|
| 483 |
+
"step": 3150
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.89,
|
| 487 |
+
"grad_norm": 3.3415660858154297,
|
| 488 |
+
"learning_rate": 7.106690777576855e-06,
|
| 489 |
+
"loss": 0.1606,
|
| 490 |
+
"step": 3200
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.94,
|
| 494 |
+
"grad_norm": 3.208709478378296,
|
| 495 |
+
"learning_rate": 7.061482820976493e-06,
|
| 496 |
+
"loss": 0.1569,
|
| 497 |
+
"step": 3250
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.98,
|
| 501 |
+
"grad_norm": 3.284241199493408,
|
| 502 |
+
"learning_rate": 7.01627486437613e-06,
|
| 503 |
+
"loss": 0.1586,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.03,
|
| 508 |
+
"grad_norm": 4.061830520629883,
|
| 509 |
+
"learning_rate": 6.971066907775769e-06,
|
| 510 |
+
"loss": 0.1494,
|
| 511 |
+
"step": 3350
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.07,
|
| 515 |
+
"grad_norm": 4.065818786621094,
|
| 516 |
+
"learning_rate": 6.925858951175407e-06,
|
| 517 |
+
"loss": 0.142,
|
| 518 |
+
"step": 3400
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.12,
|
| 522 |
+
"grad_norm": 4.541987895965576,
|
| 523 |
+
"learning_rate": 6.8806509945750455e-06,
|
| 524 |
+
"loss": 0.1436,
|
| 525 |
+
"step": 3450
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.16,
|
| 529 |
+
"grad_norm": 3.972423791885376,
|
| 530 |
+
"learning_rate": 6.835443037974684e-06,
|
| 531 |
+
"loss": 0.1323,
|
| 532 |
+
"step": 3500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.21,
|
| 536 |
+
"grad_norm": 6.7635579109191895,
|
| 537 |
+
"learning_rate": 6.790235081374322e-06,
|
| 538 |
+
"loss": 0.1398,
|
| 539 |
+
"step": 3550
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.25,
|
| 543 |
+
"grad_norm": 3.5160984992980957,
|
| 544 |
+
"learning_rate": 6.745027124773961e-06,
|
| 545 |
+
"loss": 0.1418,
|
| 546 |
+
"step": 3600
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.3,
|
| 550 |
+
"grad_norm": 2.7026939392089844,
|
| 551 |
+
"learning_rate": 6.699819168173599e-06,
|
| 552 |
+
"loss": 0.1352,
|
| 553 |
+
"step": 3650
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.35,
|
| 557 |
+
"grad_norm": 3.9507486820220947,
|
| 558 |
+
"learning_rate": 6.654611211573238e-06,
|
| 559 |
+
"loss": 0.1406,
|
| 560 |
+
"step": 3700
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.39,
|
| 564 |
+
"grad_norm": 3.7145042419433594,
|
| 565 |
+
"learning_rate": 6.609403254972876e-06,
|
| 566 |
+
"loss": 0.1355,
|
| 567 |
+
"step": 3750
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.44,
|
| 571 |
+
"grad_norm": 3.2809576988220215,
|
| 572 |
+
"learning_rate": 6.564195298372514e-06,
|
| 573 |
+
"loss": 0.1406,
|
| 574 |
+
"step": 3800
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 3.48,
|
| 578 |
+
"grad_norm": 3.0519375801086426,
|
| 579 |
+
"learning_rate": 6.518987341772153e-06,
|
| 580 |
+
"loss": 0.1352,
|
| 581 |
+
"step": 3850
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 3.53,
|
| 585 |
+
"grad_norm": 3.6294689178466797,
|
| 586 |
+
"learning_rate": 6.473779385171791e-06,
|
| 587 |
+
"loss": 0.1396,
|
| 588 |
+
"step": 3900
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.57,
|
| 592 |
+
"grad_norm": 3.4787845611572266,
|
| 593 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 594 |
+
"loss": 0.1409,
|
| 595 |
+
"step": 3950
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 3.62,
|
| 599 |
+
"grad_norm": 3.510904550552368,
|
| 600 |
+
"learning_rate": 6.383363471971068e-06,
|
| 601 |
+
"loss": 0.141,
|
| 602 |
+
"step": 4000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.62,
|
| 606 |
+
"eval_accuracy": 0.9195454545454546,
|
| 607 |
+
"eval_auc": 0.9743002838306037,
|
| 608 |
+
"eval_f1": 0.8847406121120035,
|
| 609 |
+
"eval_loss": 0.22910813987255096,
|
| 610 |
+
"eval_runtime": 53.2967,
|
| 611 |
+
"eval_samples_per_second": 247.67,
|
| 612 |
+
"eval_steps_per_second": 3.884,
|
| 613 |
+
"step": 4000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 3.66,
|
| 617 |
+
"grad_norm": 3.591719150543213,
|
| 618 |
+
"learning_rate": 6.338155515370705e-06,
|
| 619 |
+
"loss": 0.1368,
|
| 620 |
+
"step": 4050
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.71,
|
| 624 |
+
"grad_norm": 4.009765625,
|
| 625 |
+
"learning_rate": 6.292947558770344e-06,
|
| 626 |
+
"loss": 0.1344,
|
| 627 |
+
"step": 4100
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.75,
|
| 631 |
+
"grad_norm": 3.1466119289398193,
|
| 632 |
+
"learning_rate": 6.247739602169982e-06,
|
| 633 |
+
"loss": 0.1424,
|
| 634 |
+
"step": 4150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.8,
|
| 638 |
+
"grad_norm": 3.8974554538726807,
|
| 639 |
+
"learning_rate": 6.20253164556962e-06,
|
| 640 |
+
"loss": 0.1374,
|
| 641 |
+
"step": 4200
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.84,
|
| 645 |
+
"grad_norm": 3.8210461139678955,
|
| 646 |
+
"learning_rate": 6.157323688969259e-06,
|
| 647 |
+
"loss": 0.1365,
|
| 648 |
+
"step": 4250
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.89,
|
| 652 |
+
"grad_norm": 3.865953207015991,
|
| 653 |
+
"learning_rate": 6.1121157323688975e-06,
|
| 654 |
+
"loss": 0.1416,
|
| 655 |
+
"step": 4300
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.93,
|
| 659 |
+
"grad_norm": 3.4419188499450684,
|
| 660 |
+
"learning_rate": 6.066907775768536e-06,
|
| 661 |
+
"loss": 0.1394,
|
| 662 |
+
"step": 4350
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.98,
|
| 666 |
+
"grad_norm": 3.2424869537353516,
|
| 667 |
+
"learning_rate": 6.021699819168174e-06,
|
| 668 |
+
"loss": 0.1379,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.02,
|
| 673 |
+
"grad_norm": 4.413413047790527,
|
| 674 |
+
"learning_rate": 5.9764918625678126e-06,
|
| 675 |
+
"loss": 0.1305,
|
| 676 |
+
"step": 4450
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.07,
|
| 680 |
+
"grad_norm": 5.382500648498535,
|
| 681 |
+
"learning_rate": 5.931283905967451e-06,
|
| 682 |
+
"loss": 0.1246,
|
| 683 |
+
"step": 4500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.11,
|
| 687 |
+
"grad_norm": 3.337273120880127,
|
| 688 |
+
"learning_rate": 5.886075949367089e-06,
|
| 689 |
+
"loss": 0.121,
|
| 690 |
+
"step": 4550
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 4.16,
|
| 694 |
+
"grad_norm": 4.4842705726623535,
|
| 695 |
+
"learning_rate": 5.840867992766728e-06,
|
| 696 |
+
"loss": 0.12,
|
| 697 |
+
"step": 4600
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.2,
|
| 701 |
+
"grad_norm": 3.6167163848876953,
|
| 702 |
+
"learning_rate": 5.795660036166366e-06,
|
| 703 |
+
"loss": 0.1223,
|
| 704 |
+
"step": 4650
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.25,
|
| 708 |
+
"grad_norm": 3.679234027862549,
|
| 709 |
+
"learning_rate": 5.750452079566005e-06,
|
| 710 |
+
"loss": 0.123,
|
| 711 |
+
"step": 4700
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.29,
|
| 715 |
+
"grad_norm": 4.960000991821289,
|
| 716 |
+
"learning_rate": 5.705244122965642e-06,
|
| 717 |
+
"loss": 0.1175,
|
| 718 |
+
"step": 4750
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.34,
|
| 722 |
+
"grad_norm": 5.214667320251465,
|
| 723 |
+
"learning_rate": 5.6600361663652806e-06,
|
| 724 |
+
"loss": 0.1237,
|
| 725 |
+
"step": 4800
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.39,
|
| 729 |
+
"grad_norm": 3.636551856994629,
|
| 730 |
+
"learning_rate": 5.614828209764918e-06,
|
| 731 |
+
"loss": 0.121,
|
| 732 |
+
"step": 4850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.43,
|
| 736 |
+
"grad_norm": 4.095456123352051,
|
| 737 |
+
"learning_rate": 5.569620253164557e-06,
|
| 738 |
+
"loss": 0.118,
|
| 739 |
+
"step": 4900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.48,
|
| 743 |
+
"grad_norm": 3.4457345008850098,
|
| 744 |
+
"learning_rate": 5.524412296564196e-06,
|
| 745 |
+
"loss": 0.1226,
|
| 746 |
+
"step": 4950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 4.52,
|
| 750 |
+
"grad_norm": 4.705195903778076,
|
| 751 |
+
"learning_rate": 5.479204339963834e-06,
|
| 752 |
+
"loss": 0.1232,
|
| 753 |
+
"step": 5000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.52,
|
| 757 |
+
"eval_accuracy": 0.9215909090909091,
|
| 758 |
+
"eval_auc": 0.9733304450242736,
|
| 759 |
+
"eval_f1": 0.8873653281096964,
|
| 760 |
+
"eval_loss": 0.26092976331710815,
|
| 761 |
+
"eval_runtime": 52.7152,
|
| 762 |
+
"eval_samples_per_second": 250.402,
|
| 763 |
+
"eval_steps_per_second": 3.927,
|
| 764 |
+
"step": 5000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 4.57,
|
| 768 |
+
"grad_norm": 5.460992336273193,
|
| 769 |
+
"learning_rate": 5.433996383363472e-06,
|
| 770 |
+
"loss": 0.1191,
|
| 771 |
+
"step": 5050
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 4.61,
|
| 775 |
+
"grad_norm": 4.26489782333374,
|
| 776 |
+
"learning_rate": 5.388788426763111e-06,
|
| 777 |
+
"loss": 0.1206,
|
| 778 |
+
"step": 5100
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.66,
|
| 782 |
+
"grad_norm": 5.637485027313232,
|
| 783 |
+
"learning_rate": 5.343580470162749e-06,
|
| 784 |
+
"loss": 0.1237,
|
| 785 |
+
"step": 5150
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 4.7,
|
| 789 |
+
"grad_norm": 3.848707675933838,
|
| 790 |
+
"learning_rate": 5.298372513562387e-06,
|
| 791 |
+
"loss": 0.1204,
|
| 792 |
+
"step": 5200
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 4.75,
|
| 796 |
+
"grad_norm": 3.9218106269836426,
|
| 797 |
+
"learning_rate": 5.253164556962026e-06,
|
| 798 |
+
"loss": 0.1226,
|
| 799 |
+
"step": 5250
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 4.79,
|
| 803 |
+
"grad_norm": 6.16193151473999,
|
| 804 |
+
"learning_rate": 5.2079566003616645e-06,
|
| 805 |
+
"loss": 0.1267,
|
| 806 |
+
"step": 5300
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.84,
|
| 810 |
+
"grad_norm": 3.432070016860962,
|
| 811 |
+
"learning_rate": 5.162748643761303e-06,
|
| 812 |
+
"loss": 0.1232,
|
| 813 |
+
"step": 5350
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.88,
|
| 817 |
+
"grad_norm": 4.200852394104004,
|
| 818 |
+
"learning_rate": 5.117540687160941e-06,
|
| 819 |
+
"loss": 0.1219,
|
| 820 |
+
"step": 5400
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.93,
|
| 824 |
+
"grad_norm": 5.724985599517822,
|
| 825 |
+
"learning_rate": 5.07233273056058e-06,
|
| 826 |
+
"loss": 0.1215,
|
| 827 |
+
"step": 5450
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 4.97,
|
| 831 |
+
"grad_norm": 5.0651445388793945,
|
| 832 |
+
"learning_rate": 5.0271247739602165e-06,
|
| 833 |
+
"loss": 0.1236,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 5.02,
|
| 838 |
+
"grad_norm": 4.59727144241333,
|
| 839 |
+
"learning_rate": 4.981916817359856e-06,
|
| 840 |
+
"loss": 0.1177,
|
| 841 |
+
"step": 5550
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 5.06,
|
| 845 |
+
"grad_norm": 4.37638521194458,
|
| 846 |
+
"learning_rate": 4.936708860759495e-06,
|
| 847 |
+
"loss": 0.1035,
|
| 848 |
+
"step": 5600
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 5.11,
|
| 852 |
+
"grad_norm": 4.5621337890625,
|
| 853 |
+
"learning_rate": 4.8915009041591325e-06,
|
| 854 |
+
"loss": 0.108,
|
| 855 |
+
"step": 5650
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 5.15,
|
| 859 |
+
"grad_norm": 3.9966683387756348,
|
| 860 |
+
"learning_rate": 4.84629294755877e-06,
|
| 861 |
+
"loss": 0.1057,
|
| 862 |
+
"step": 5700
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 5.2,
|
| 866 |
+
"grad_norm": 3.630200147628784,
|
| 867 |
+
"learning_rate": 4.801084990958409e-06,
|
| 868 |
+
"loss": 0.1043,
|
| 869 |
+
"step": 5750
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 5.24,
|
| 873 |
+
"grad_norm": 4.338815689086914,
|
| 874 |
+
"learning_rate": 4.755877034358048e-06,
|
| 875 |
+
"loss": 0.1066,
|
| 876 |
+
"step": 5800
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.29,
|
| 880 |
+
"grad_norm": 2.695749282836914,
|
| 881 |
+
"learning_rate": 4.710669077757685e-06,
|
| 882 |
+
"loss": 0.1059,
|
| 883 |
+
"step": 5850
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 5.33,
|
| 887 |
+
"grad_norm": 7.642387866973877,
|
| 888 |
+
"learning_rate": 4.665461121157324e-06,
|
| 889 |
+
"loss": 0.1073,
|
| 890 |
+
"step": 5900
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 5.38,
|
| 894 |
+
"grad_norm": 6.227341651916504,
|
| 895 |
+
"learning_rate": 4.620253164556963e-06,
|
| 896 |
+
"loss": 0.1115,
|
| 897 |
+
"step": 5950
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 5.42,
|
| 901 |
+
"grad_norm": 5.479009628295898,
|
| 902 |
+
"learning_rate": 4.575045207956601e-06,
|
| 903 |
+
"loss": 0.1058,
|
| 904 |
+
"step": 6000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 5.42,
|
| 908 |
+
"eval_accuracy": 0.913409090909091,
|
| 909 |
+
"eval_auc": 0.9717929602890524,
|
| 910 |
+
"eval_f1": 0.8788553259141495,
|
| 911 |
+
"eval_loss": 0.2780343294143677,
|
| 912 |
+
"eval_runtime": 53.9647,
|
| 913 |
+
"eval_samples_per_second": 244.604,
|
| 914 |
+
"eval_steps_per_second": 3.836,
|
| 915 |
+
"step": 6000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 5.47,
|
| 919 |
+
"grad_norm": 4.2524871826171875,
|
| 920 |
+
"learning_rate": 4.529837251356239e-06,
|
| 921 |
+
"loss": 0.1053,
|
| 922 |
+
"step": 6050
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 5.52,
|
| 926 |
+
"grad_norm": 3.475076675415039,
|
| 927 |
+
"learning_rate": 4.484629294755877e-06,
|
| 928 |
+
"loss": 0.1068,
|
| 929 |
+
"step": 6100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 5.56,
|
| 933 |
+
"grad_norm": 4.190853118896484,
|
| 934 |
+
"learning_rate": 4.439421338155516e-06,
|
| 935 |
+
"loss": 0.1067,
|
| 936 |
+
"step": 6150
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.61,
|
| 940 |
+
"grad_norm": 4.308005332946777,
|
| 941 |
+
"learning_rate": 4.394213381555154e-06,
|
| 942 |
+
"loss": 0.104,
|
| 943 |
+
"step": 6200
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 5.65,
|
| 947 |
+
"grad_norm": 3.767345666885376,
|
| 948 |
+
"learning_rate": 4.349005424954793e-06,
|
| 949 |
+
"loss": 0.1056,
|
| 950 |
+
"step": 6250
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 5.7,
|
| 954 |
+
"grad_norm": 3.9116408824920654,
|
| 955 |
+
"learning_rate": 4.303797468354431e-06,
|
| 956 |
+
"loss": 0.1123,
|
| 957 |
+
"step": 6300
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 5.74,
|
| 961 |
+
"grad_norm": 5.004114151000977,
|
| 962 |
+
"learning_rate": 4.258589511754069e-06,
|
| 963 |
+
"loss": 0.1099,
|
| 964 |
+
"step": 6350
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 5.79,
|
| 968 |
+
"grad_norm": 4.2018208503723145,
|
| 969 |
+
"learning_rate": 4.213381555153707e-06,
|
| 970 |
+
"loss": 0.11,
|
| 971 |
+
"step": 6400
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 5.83,
|
| 975 |
+
"grad_norm": 3.213355779647827,
|
| 976 |
+
"learning_rate": 4.168173598553346e-06,
|
| 977 |
+
"loss": 0.1067,
|
| 978 |
+
"step": 6450
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 5.88,
|
| 982 |
+
"grad_norm": 6.60046911239624,
|
| 983 |
+
"learning_rate": 4.122965641952984e-06,
|
| 984 |
+
"loss": 0.1056,
|
| 985 |
+
"step": 6500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.92,
|
| 989 |
+
"grad_norm": 3.6781232357025146,
|
| 990 |
+
"learning_rate": 4.077757685352622e-06,
|
| 991 |
+
"loss": 0.1053,
|
| 992 |
+
"step": 6550
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 5.97,
|
| 996 |
+
"grad_norm": 3.4061131477355957,
|
| 997 |
+
"learning_rate": 4.032549728752261e-06,
|
| 998 |
+
"loss": 0.1084,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 6.01,
|
| 1003 |
+
"grad_norm": 5.02764892578125,
|
| 1004 |
+
"learning_rate": 3.9873417721518995e-06,
|
| 1005 |
+
"loss": 0.1054,
|
| 1006 |
+
"step": 6650
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 6.06,
|
| 1010 |
+
"grad_norm": 4.55075740814209,
|
| 1011 |
+
"learning_rate": 3.942133815551537e-06,
|
| 1012 |
+
"loss": 0.0913,
|
| 1013 |
+
"step": 6700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 6.1,
|
| 1017 |
+
"grad_norm": 4.121731758117676,
|
| 1018 |
+
"learning_rate": 3.896925858951175e-06,
|
| 1019 |
+
"loss": 0.0928,
|
| 1020 |
+
"step": 6750
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 6.15,
|
| 1024 |
+
"grad_norm": 4.887127876281738,
|
| 1025 |
+
"learning_rate": 3.851717902350814e-06,
|
| 1026 |
+
"loss": 0.092,
|
| 1027 |
+
"step": 6800
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 6.19,
|
| 1031 |
+
"grad_norm": 6.114282131195068,
|
| 1032 |
+
"learning_rate": 3.8065099457504524e-06,
|
| 1033 |
+
"loss": 0.091,
|
| 1034 |
+
"step": 6850
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 6.24,
|
| 1038 |
+
"grad_norm": 3.952768564224243,
|
| 1039 |
+
"learning_rate": 3.7613019891500906e-06,
|
| 1040 |
+
"loss": 0.093,
|
| 1041 |
+
"step": 6900
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 6.28,
|
| 1045 |
+
"grad_norm": 4.0614800453186035,
|
| 1046 |
+
"learning_rate": 3.7160940325497293e-06,
|
| 1047 |
+
"loss": 0.0871,
|
| 1048 |
+
"step": 6950
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 6.33,
|
| 1052 |
+
"grad_norm": 5.143472671508789,
|
| 1053 |
+
"learning_rate": 3.6708860759493675e-06,
|
| 1054 |
+
"loss": 0.093,
|
| 1055 |
+
"step": 7000
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 6.33,
|
| 1059 |
+
"eval_accuracy": 0.9113636363636364,
|
| 1060 |
+
"eval_auc": 0.9692261016594985,
|
| 1061 |
+
"eval_f1": 0.8748127541194094,
|
| 1062 |
+
"eval_loss": 0.2975885272026062,
|
| 1063 |
+
"eval_runtime": 53.1958,
|
| 1064 |
+
"eval_samples_per_second": 248.14,
|
| 1065 |
+
"eval_steps_per_second": 3.891,
|
| 1066 |
+
"step": 7000
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 6.37,
|
| 1070 |
+
"grad_norm": 3.874722957611084,
|
| 1071 |
+
"learning_rate": 3.6256781193490057e-06,
|
| 1072 |
+
"loss": 0.0949,
|
| 1073 |
+
"step": 7050
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 6.42,
|
| 1077 |
+
"grad_norm": 3.9388911724090576,
|
| 1078 |
+
"learning_rate": 3.580470162748644e-06,
|
| 1079 |
+
"loss": 0.0963,
|
| 1080 |
+
"step": 7100
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 6.46,
|
| 1084 |
+
"grad_norm": 3.774689197540283,
|
| 1085 |
+
"learning_rate": 3.535262206148282e-06,
|
| 1086 |
+
"loss": 0.0915,
|
| 1087 |
+
"step": 7150
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 6.51,
|
| 1091 |
+
"grad_norm": 5.495402812957764,
|
| 1092 |
+
"learning_rate": 3.4900542495479204e-06,
|
| 1093 |
+
"loss": 0.0935,
|
| 1094 |
+
"step": 7200
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 6.56,
|
| 1098 |
+
"grad_norm": 5.229218006134033,
|
| 1099 |
+
"learning_rate": 3.444846292947559e-06,
|
| 1100 |
+
"loss": 0.0955,
|
| 1101 |
+
"step": 7250
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 6.6,
|
| 1105 |
+
"grad_norm": 8.326276779174805,
|
| 1106 |
+
"learning_rate": 3.3996383363471973e-06,
|
| 1107 |
+
"loss": 0.0905,
|
| 1108 |
+
"step": 7300
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 6.65,
|
| 1112 |
+
"grad_norm": 3.566875457763672,
|
| 1113 |
+
"learning_rate": 3.354430379746836e-06,
|
| 1114 |
+
"loss": 0.0988,
|
| 1115 |
+
"step": 7350
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 6.69,
|
| 1119 |
+
"grad_norm": 4.5591559410095215,
|
| 1120 |
+
"learning_rate": 3.309222423146474e-06,
|
| 1121 |
+
"loss": 0.0902,
|
| 1122 |
+
"step": 7400
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 6.74,
|
| 1126 |
+
"grad_norm": 4.157392978668213,
|
| 1127 |
+
"learning_rate": 3.264014466546113e-06,
|
| 1128 |
+
"loss": 0.0937,
|
| 1129 |
+
"step": 7450
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 6.78,
|
| 1133 |
+
"grad_norm": 3.770798444747925,
|
| 1134 |
+
"learning_rate": 3.2188065099457506e-06,
|
| 1135 |
+
"loss": 0.0928,
|
| 1136 |
+
"step": 7500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 6.83,
|
| 1140 |
+
"grad_norm": 4.334375858306885,
|
| 1141 |
+
"learning_rate": 3.173598553345389e-06,
|
| 1142 |
+
"loss": 0.0929,
|
| 1143 |
+
"step": 7550
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 6.87,
|
| 1147 |
+
"grad_norm": 4.411478519439697,
|
| 1148 |
+
"learning_rate": 3.1283905967450275e-06,
|
| 1149 |
+
"loss": 0.0921,
|
| 1150 |
+
"step": 7600
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 6.92,
|
| 1154 |
+
"grad_norm": 3.9217774868011475,
|
| 1155 |
+
"learning_rate": 3.0831826401446657e-06,
|
| 1156 |
+
"loss": 0.0907,
|
| 1157 |
+
"step": 7650
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 6.96,
|
| 1161 |
+
"grad_norm": 4.253012657165527,
|
| 1162 |
+
"learning_rate": 3.037974683544304e-06,
|
| 1163 |
+
"loss": 0.0965,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 7.01,
|
| 1168 |
+
"grad_norm": 4.301031112670898,
|
| 1169 |
+
"learning_rate": 2.9927667269439426e-06,
|
| 1170 |
+
"loss": 0.0916,
|
| 1171 |
+
"step": 7750
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 7.05,
|
| 1175 |
+
"grad_norm": 4.984923362731934,
|
| 1176 |
+
"learning_rate": 2.947558770343581e-06,
|
| 1177 |
+
"loss": 0.079,
|
| 1178 |
+
"step": 7800
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.1,
|
| 1182 |
+
"grad_norm": 6.965585231781006,
|
| 1183 |
+
"learning_rate": 2.9023508137432186e-06,
|
| 1184 |
+
"loss": 0.0856,
|
| 1185 |
+
"step": 7850
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 7.14,
|
| 1189 |
+
"grad_norm": 5.262626647949219,
|
| 1190 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 1191 |
+
"loss": 0.0814,
|
| 1192 |
+
"step": 7900
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 7.19,
|
| 1196 |
+
"grad_norm": 6.5270771980285645,
|
| 1197 |
+
"learning_rate": 2.8119349005424955e-06,
|
| 1198 |
+
"loss": 0.084,
|
| 1199 |
+
"step": 7950
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 7.23,
|
| 1203 |
+
"grad_norm": 4.8120808601379395,
|
| 1204 |
+
"learning_rate": 2.766726943942134e-06,
|
| 1205 |
+
"loss": 0.0811,
|
| 1206 |
+
"step": 8000
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 7.23,
|
| 1210 |
+
"eval_accuracy": 0.915530303030303,
|
| 1211 |
+
"eval_auc": 0.969414026787581,
|
| 1212 |
+
"eval_f1": 0.8789753609030717,
|
| 1213 |
+
"eval_loss": 0.3245289623737335,
|
| 1214 |
+
"eval_runtime": 52.4229,
|
| 1215 |
+
"eval_samples_per_second": 251.799,
|
| 1216 |
+
"eval_steps_per_second": 3.949,
|
| 1217 |
+
"step": 8000
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 7.28,
|
| 1221 |
+
"grad_norm": 6.172023773193359,
|
| 1222 |
+
"learning_rate": 2.7215189873417724e-06,
|
| 1223 |
+
"loss": 0.0845,
|
| 1224 |
+
"step": 8050
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 7.32,
|
| 1228 |
+
"grad_norm": 4.027543544769287,
|
| 1229 |
+
"learning_rate": 2.676311030741411e-06,
|
| 1230 |
+
"loss": 0.081,
|
| 1231 |
+
"step": 8100
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 7.37,
|
| 1235 |
+
"grad_norm": 4.544090747833252,
|
| 1236 |
+
"learning_rate": 2.6311030741410492e-06,
|
| 1237 |
+
"loss": 0.0885,
|
| 1238 |
+
"step": 8150
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 7.41,
|
| 1242 |
+
"grad_norm": 5.340161323547363,
|
| 1243 |
+
"learning_rate": 2.585895117540687e-06,
|
| 1244 |
+
"loss": 0.0856,
|
| 1245 |
+
"step": 8200
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 7.46,
|
| 1249 |
+
"grad_norm": 7.733421325683594,
|
| 1250 |
+
"learning_rate": 2.5406871609403257e-06,
|
| 1251 |
+
"loss": 0.0815,
|
| 1252 |
+
"step": 8250
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 7.5,
|
| 1256 |
+
"grad_norm": 5.390356063842773,
|
| 1257 |
+
"learning_rate": 2.495479204339964e-06,
|
| 1258 |
+
"loss": 0.0812,
|
| 1259 |
+
"step": 8300
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 7.55,
|
| 1263 |
+
"grad_norm": 4.908448696136475,
|
| 1264 |
+
"learning_rate": 2.4502712477396025e-06,
|
| 1265 |
+
"loss": 0.0814,
|
| 1266 |
+
"step": 8350
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 7.59,
|
| 1270 |
+
"grad_norm": 7.446599960327148,
|
| 1271 |
+
"learning_rate": 2.4050632911392408e-06,
|
| 1272 |
+
"loss": 0.0833,
|
| 1273 |
+
"step": 8400
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 7.64,
|
| 1277 |
+
"grad_norm": 4.445633888244629,
|
| 1278 |
+
"learning_rate": 2.359855334538879e-06,
|
| 1279 |
+
"loss": 0.0804,
|
| 1280 |
+
"step": 8450
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 7.69,
|
| 1284 |
+
"grad_norm": 3.859055757522583,
|
| 1285 |
+
"learning_rate": 2.3146473779385172e-06,
|
| 1286 |
+
"loss": 0.0813,
|
| 1287 |
+
"step": 8500
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 7.73,
|
| 1291 |
+
"grad_norm": 8.008405685424805,
|
| 1292 |
+
"learning_rate": 2.269439421338156e-06,
|
| 1293 |
+
"loss": 0.0835,
|
| 1294 |
+
"step": 8550
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 7.78,
|
| 1298 |
+
"grad_norm": 4.7624711990356445,
|
| 1299 |
+
"learning_rate": 2.224231464737794e-06,
|
| 1300 |
+
"loss": 0.0827,
|
| 1301 |
+
"step": 8600
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 7.82,
|
| 1305 |
+
"grad_norm": 4.379971504211426,
|
| 1306 |
+
"learning_rate": 2.1790235081374323e-06,
|
| 1307 |
+
"loss": 0.079,
|
| 1308 |
+
"step": 8650
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 7.87,
|
| 1312 |
+
"grad_norm": 5.949471473693848,
|
| 1313 |
+
"learning_rate": 2.1338155515370705e-06,
|
| 1314 |
+
"loss": 0.0789,
|
| 1315 |
+
"step": 8700
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 7.91,
|
| 1319 |
+
"grad_norm": 5.32230281829834,
|
| 1320 |
+
"learning_rate": 2.088607594936709e-06,
|
| 1321 |
+
"loss": 0.0799,
|
| 1322 |
+
"step": 8750
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 7.96,
|
| 1326 |
+
"grad_norm": 8.27724552154541,
|
| 1327 |
+
"learning_rate": 2.0433996383363474e-06,
|
| 1328 |
+
"loss": 0.0842,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 8.0,
|
| 1333 |
+
"grad_norm": 6.394008159637451,
|
| 1334 |
+
"learning_rate": 1.9981916817359856e-06,
|
| 1335 |
+
"loss": 0.0808,
|
| 1336 |
+
"step": 8850
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 8.05,
|
| 1340 |
+
"grad_norm": 4.033376693725586,
|
| 1341 |
+
"learning_rate": 1.952983725135624e-06,
|
| 1342 |
+
"loss": 0.0687,
|
| 1343 |
+
"step": 8900
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 8.09,
|
| 1347 |
+
"grad_norm": 5.514036178588867,
|
| 1348 |
+
"learning_rate": 1.9077757685352625e-06,
|
| 1349 |
+
"loss": 0.0757,
|
| 1350 |
+
"step": 8950
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 8.14,
|
| 1354 |
+
"grad_norm": 3.8214776515960693,
|
| 1355 |
+
"learning_rate": 1.8625678119349007e-06,
|
| 1356 |
+
"loss": 0.0721,
|
| 1357 |
+
"step": 9000
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 8.14,
|
| 1361 |
+
"eval_accuracy": 0.9152272727272728,
|
| 1362 |
+
"eval_auc": 0.9681984211284476,
|
| 1363 |
+
"eval_f1": 0.8782239634345413,
|
| 1364 |
+
"eval_loss": 0.34035009145736694,
|
| 1365 |
+
"eval_runtime": 52.8174,
|
| 1366 |
+
"eval_samples_per_second": 249.918,
|
| 1367 |
+
"eval_steps_per_second": 3.919,
|
| 1368 |
+
"step": 9000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 8.18,
|
| 1372 |
+
"grad_norm": 5.467037200927734,
|
| 1373 |
+
"learning_rate": 1.817359855334539e-06,
|
| 1374 |
+
"loss": 0.0761,
|
| 1375 |
+
"step": 9050
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 8.23,
|
| 1379 |
+
"grad_norm": 5.79172945022583,
|
| 1380 |
+
"learning_rate": 1.7721518987341774e-06,
|
| 1381 |
+
"loss": 0.074,
|
| 1382 |
+
"step": 9100
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 8.27,
|
| 1386 |
+
"grad_norm": 3.8891448974609375,
|
| 1387 |
+
"learning_rate": 1.7269439421338158e-06,
|
| 1388 |
+
"loss": 0.0767,
|
| 1389 |
+
"step": 9150
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 8.32,
|
| 1393 |
+
"grad_norm": 4.498980522155762,
|
| 1394 |
+
"learning_rate": 1.6817359855334538e-06,
|
| 1395 |
+
"loss": 0.074,
|
| 1396 |
+
"step": 9200
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 8.36,
|
| 1400 |
+
"grad_norm": 5.459845542907715,
|
| 1401 |
+
"learning_rate": 1.6365280289330923e-06,
|
| 1402 |
+
"loss": 0.075,
|
| 1403 |
+
"step": 9250
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 8.41,
|
| 1407 |
+
"grad_norm": 6.381141662597656,
|
| 1408 |
+
"learning_rate": 1.5913200723327307e-06,
|
| 1409 |
+
"loss": 0.0767,
|
| 1410 |
+
"step": 9300
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 8.45,
|
| 1414 |
+
"grad_norm": 5.742413520812988,
|
| 1415 |
+
"learning_rate": 1.5461121157323692e-06,
|
| 1416 |
+
"loss": 0.0763,
|
| 1417 |
+
"step": 9350
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 8.5,
|
| 1421 |
+
"grad_norm": 5.142722129821777,
|
| 1422 |
+
"learning_rate": 1.5009041591320072e-06,
|
| 1423 |
+
"loss": 0.0747,
|
| 1424 |
+
"step": 9400
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 8.54,
|
| 1428 |
+
"grad_norm": 5.048556804656982,
|
| 1429 |
+
"learning_rate": 1.4556962025316456e-06,
|
| 1430 |
+
"loss": 0.0748,
|
| 1431 |
+
"step": 9450
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 8.59,
|
| 1435 |
+
"grad_norm": 5.201704502105713,
|
| 1436 |
+
"learning_rate": 1.410488245931284e-06,
|
| 1437 |
+
"loss": 0.0748,
|
| 1438 |
+
"step": 9500
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 8.63,
|
| 1442 |
+
"grad_norm": 5.143392086029053,
|
| 1443 |
+
"learning_rate": 1.3652802893309225e-06,
|
| 1444 |
+
"loss": 0.076,
|
| 1445 |
+
"step": 9550
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 8.68,
|
| 1449 |
+
"grad_norm": 5.493886470794678,
|
| 1450 |
+
"learning_rate": 1.3200723327305607e-06,
|
| 1451 |
+
"loss": 0.0718,
|
| 1452 |
+
"step": 9600
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 8.73,
|
| 1456 |
+
"grad_norm": 3.705559492111206,
|
| 1457 |
+
"learning_rate": 1.274864376130199e-06,
|
| 1458 |
+
"loss": 0.0712,
|
| 1459 |
+
"step": 9650
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 8.77,
|
| 1463 |
+
"grad_norm": 5.664219856262207,
|
| 1464 |
+
"learning_rate": 1.2296564195298374e-06,
|
| 1465 |
+
"loss": 0.0729,
|
| 1466 |
+
"step": 9700
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 8.82,
|
| 1470 |
+
"grad_norm": 5.6803812980651855,
|
| 1471 |
+
"learning_rate": 1.1844484629294758e-06,
|
| 1472 |
+
"loss": 0.0719,
|
| 1473 |
+
"step": 9750
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 8.86,
|
| 1477 |
+
"grad_norm": 4.449408054351807,
|
| 1478 |
+
"learning_rate": 1.139240506329114e-06,
|
| 1479 |
+
"loss": 0.0732,
|
| 1480 |
+
"step": 9800
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 8.91,
|
| 1484 |
+
"grad_norm": 6.274992942810059,
|
| 1485 |
+
"learning_rate": 1.0940325497287525e-06,
|
| 1486 |
+
"loss": 0.0764,
|
| 1487 |
+
"step": 9850
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 8.95,
|
| 1491 |
+
"grad_norm": 6.5285797119140625,
|
| 1492 |
+
"learning_rate": 1.0488245931283907e-06,
|
| 1493 |
+
"loss": 0.072,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 9.0,
|
| 1498 |
+
"grad_norm": 10.324697494506836,
|
| 1499 |
+
"learning_rate": 1.0036166365280291e-06,
|
| 1500 |
+
"loss": 0.073,
|
| 1501 |
+
"step": 9950
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 9.04,
|
| 1505 |
+
"grad_norm": 12.908041954040527,
|
| 1506 |
+
"learning_rate": 9.584086799276674e-07,
|
| 1507 |
+
"loss": 0.0689,
|
| 1508 |
+
"step": 10000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 9.04,
|
| 1512 |
+
"eval_accuracy": 0.915530303030303,
|
| 1513 |
+
"eval_auc": 0.9687716182332089,
|
| 1514 |
+
"eval_f1": 0.8797843665768194,
|
| 1515 |
+
"eval_loss": 0.3541575074195862,
|
| 1516 |
+
"eval_runtime": 52.8789,
|
| 1517 |
+
"eval_samples_per_second": 249.627,
|
| 1518 |
+
"eval_steps_per_second": 3.915,
|
| 1519 |
+
"step": 10000
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 9.09,
|
| 1523 |
+
"grad_norm": 4.13251256942749,
|
| 1524 |
+
"learning_rate": 9.132007233273058e-07,
|
| 1525 |
+
"loss": 0.0687,
|
| 1526 |
+
"step": 10050
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 9.13,
|
| 1530 |
+
"grad_norm": 6.25527286529541,
|
| 1531 |
+
"learning_rate": 8.67992766726944e-07,
|
| 1532 |
+
"loss": 0.0731,
|
| 1533 |
+
"step": 10100
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 9.18,
|
| 1537 |
+
"grad_norm": 5.105614185333252,
|
| 1538 |
+
"learning_rate": 8.227848101265823e-07,
|
| 1539 |
+
"loss": 0.0715,
|
| 1540 |
+
"step": 10150
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 9.22,
|
| 1544 |
+
"grad_norm": 4.943532943725586,
|
| 1545 |
+
"learning_rate": 7.775768535262207e-07,
|
| 1546 |
+
"loss": 0.0653,
|
| 1547 |
+
"step": 10200
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 9.27,
|
| 1551 |
+
"grad_norm": 5.668446063995361,
|
| 1552 |
+
"learning_rate": 7.32368896925859e-07,
|
| 1553 |
+
"loss": 0.0694,
|
| 1554 |
+
"step": 10250
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 9.31,
|
| 1558 |
+
"grad_norm": 5.078279972076416,
|
| 1559 |
+
"learning_rate": 6.871609403254973e-07,
|
| 1560 |
+
"loss": 0.0659,
|
| 1561 |
+
"step": 10300
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 9.36,
|
| 1565 |
+
"grad_norm": 4.663586616516113,
|
| 1566 |
+
"learning_rate": 6.419529837251357e-07,
|
| 1567 |
+
"loss": 0.0661,
|
| 1568 |
+
"step": 10350
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 9.4,
|
| 1572 |
+
"grad_norm": 4.528202533721924,
|
| 1573 |
+
"learning_rate": 5.96745027124774e-07,
|
| 1574 |
+
"loss": 0.0701,
|
| 1575 |
+
"step": 10400
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 9.45,
|
| 1579 |
+
"grad_norm": 5.685123920440674,
|
| 1580 |
+
"learning_rate": 5.515370705244123e-07,
|
| 1581 |
+
"loss": 0.069,
|
| 1582 |
+
"step": 10450
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 9.49,
|
| 1586 |
+
"grad_norm": 5.798079967498779,
|
| 1587 |
+
"learning_rate": 5.063291139240507e-07,
|
| 1588 |
+
"loss": 0.0628,
|
| 1589 |
+
"step": 10500
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 9.54,
|
| 1593 |
+
"grad_norm": 4.510618686676025,
|
| 1594 |
+
"learning_rate": 4.61121157323689e-07,
|
| 1595 |
+
"loss": 0.0677,
|
| 1596 |
+
"step": 10550
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 9.58,
|
| 1600 |
+
"grad_norm": 5.0236382484436035,
|
| 1601 |
+
"learning_rate": 4.1591320072332737e-07,
|
| 1602 |
+
"loss": 0.0685,
|
| 1603 |
+
"step": 10600
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 9.63,
|
| 1607 |
+
"grad_norm": 5.243931770324707,
|
| 1608 |
+
"learning_rate": 3.707052441229657e-07,
|
| 1609 |
+
"loss": 0.0687,
|
| 1610 |
+
"step": 10650
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 9.67,
|
| 1614 |
+
"grad_norm": 4.094812870025635,
|
| 1615 |
+
"learning_rate": 3.2549728752260403e-07,
|
| 1616 |
+
"loss": 0.0663,
|
| 1617 |
+
"step": 10700
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 9.72,
|
| 1621 |
+
"grad_norm": 4.533218860626221,
|
| 1622 |
+
"learning_rate": 2.802893309222423e-07,
|
| 1623 |
+
"loss": 0.0685,
|
| 1624 |
+
"step": 10750
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 9.76,
|
| 1628 |
+
"grad_norm": 6.6322021484375,
|
| 1629 |
+
"learning_rate": 2.3508137432188067e-07,
|
| 1630 |
+
"loss": 0.0664,
|
| 1631 |
+
"step": 10800
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 9.81,
|
| 1635 |
+
"grad_norm": 6.374199390411377,
|
| 1636 |
+
"learning_rate": 1.89873417721519e-07,
|
| 1637 |
+
"loss": 0.0688,
|
| 1638 |
+
"step": 10850
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 9.86,
|
| 1642 |
+
"grad_norm": 5.66272497177124,
|
| 1643 |
+
"learning_rate": 1.4466546112115733e-07,
|
| 1644 |
+
"loss": 0.0696,
|
| 1645 |
+
"step": 10900
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 9.9,
|
| 1649 |
+
"grad_norm": 7.157235622406006,
|
| 1650 |
+
"learning_rate": 9.945750452079567e-08,
|
| 1651 |
+
"loss": 0.0654,
|
| 1652 |
+
"step": 10950
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 9.95,
|
| 1656 |
+
"grad_norm": 6.200794696807861,
|
| 1657 |
+
"learning_rate": 5.4249547920434e-08,
|
| 1658 |
+
"loss": 0.0712,
|
| 1659 |
+
"step": 11000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 9.95,
|
| 1663 |
+
"eval_accuracy": 0.9162121212121213,
|
| 1664 |
+
"eval_auc": 0.9685840496026594,
|
| 1665 |
+
"eval_f1": 0.8797826086956522,
|
| 1666 |
+
"eval_loss": 0.35418105125427246,
|
| 1667 |
+
"eval_runtime": 52.517,
|
| 1668 |
+
"eval_samples_per_second": 251.347,
|
| 1669 |
+
"eval_steps_per_second": 3.942,
|
| 1670 |
+
"step": 11000
|
| 1671 |
+
}
|
| 1672 |
+
],
|
| 1673 |
+
"logging_steps": 50,
|
| 1674 |
+
"max_steps": 11060,
|
| 1675 |
+
"num_input_tokens_seen": 0,
|
| 1676 |
+
"num_train_epochs": 10,
|
| 1677 |
+
"save_steps": 1000,
|
| 1678 |
+
"total_flos": 1.3113541708679086e+18,
|
| 1679 |
+
"train_batch_size": 512,
|
| 1680 |
+
"trial_name": null,
|
| 1681 |
+
"trial_params": null
|
| 1682 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01b338da7d13b5aaf587413f60c59186112df880ca73bd369438d7398966e3a0
|
| 3 |
+
size 4920
|