Upload folder using huggingface_hub
Browse files- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1876 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/xlm-v-base",
|
| 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": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.41.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 901629
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:247422dd87c06f290bb2131535523b8157cf87e58c4b95bd452f9d5b3c64925f
|
| 3 |
+
size 3114003416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1feb31fef8adba0bb5582f4478b9a1117c7c5e03f42a9354e84b416d3bb24a5f
|
| 3 |
+
size 6228131858
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f969521184d7cbac17b1aded02ba29c6e5ea4fd70cd328e059dd32e3e99dcb7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37076a3401646abb80639d5c59a874fc8aa79aca62b266c7d6910f5014cab9b4
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1876 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8473693995166388,
|
| 3 |
+
"best_model_checkpoint": "./XLM-V_16-multi-outputs/checkpoint-97000",
|
| 4 |
+
"epoch": 17.171180739953975,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 97000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17702248185519562,
|
| 13 |
+
"grad_norm": 0.6527151465415955,
|
| 14 |
+
"learning_rate": 1.770224818551956e-07,
|
| 15 |
+
"loss": 0.6947,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.17702248185519562,
|
| 20 |
+
"eval_accuracy": 0.5090112516180424,
|
| 21 |
+
"eval_f1": 0.6746288353678654,
|
| 22 |
+
"eval_loss": 0.6933906078338623,
|
| 23 |
+
"eval_precision": 0.5090112516180424,
|
| 24 |
+
"eval_recall": 1.0,
|
| 25 |
+
"eval_runtime": 48.5534,
|
| 26 |
+
"eval_samples_per_second": 206.844,
|
| 27 |
+
"eval_steps_per_second": 12.934,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.35404496371039124,
|
| 32 |
+
"grad_norm": 0.5621433258056641,
|
| 33 |
+
"learning_rate": 3.540449637103912e-07,
|
| 34 |
+
"loss": 0.695,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.35404496371039124,
|
| 39 |
+
"eval_accuracy": 0.5090112516180424,
|
| 40 |
+
"eval_f1": 0.6746288353678654,
|
| 41 |
+
"eval_loss": 0.6930156946182251,
|
| 42 |
+
"eval_precision": 0.5090112516180424,
|
| 43 |
+
"eval_recall": 1.0,
|
| 44 |
+
"eval_runtime": 48.572,
|
| 45 |
+
"eval_samples_per_second": 206.765,
|
| 46 |
+
"eval_steps_per_second": 12.929,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.5310674455655868,
|
| 51 |
+
"grad_norm": 3.589186906814575,
|
| 52 |
+
"learning_rate": 5.310674455655868e-07,
|
| 53 |
+
"loss": 0.6932,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.5310674455655868,
|
| 58 |
+
"eval_accuracy": 0.5623817584387135,
|
| 59 |
+
"eval_f1": 0.6990344449770595,
|
| 60 |
+
"eval_loss": 0.686276376247406,
|
| 61 |
+
"eval_precision": 0.537772626698978,
|
| 62 |
+
"eval_recall": 0.9984350547730829,
|
| 63 |
+
"eval_runtime": 48.4146,
|
| 64 |
+
"eval_samples_per_second": 207.437,
|
| 65 |
+
"eval_steps_per_second": 12.971,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.7080899274207825,
|
| 70 |
+
"grad_norm": 6.542071342468262,
|
| 71 |
+
"learning_rate": 7.080899274207824e-07,
|
| 72 |
+
"loss": 0.6861,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7080899274207825,
|
| 77 |
+
"eval_accuracy": 0.5879717215971323,
|
| 78 |
+
"eval_f1": 0.7084272829763247,
|
| 79 |
+
"eval_loss": 0.6729876399040222,
|
| 80 |
+
"eval_precision": 0.5536343612334802,
|
| 81 |
+
"eval_recall": 0.9833724569640062,
|
| 82 |
+
"eval_runtime": 48.5835,
|
| 83 |
+
"eval_samples_per_second": 206.716,
|
| 84 |
+
"eval_steps_per_second": 12.926,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.885112409275978,
|
| 89 |
+
"grad_norm": 7.369508266448975,
|
| 90 |
+
"learning_rate": 8.85112409275978e-07,
|
| 91 |
+
"loss": 0.6765,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.885112409275978,
|
| 96 |
+
"eval_accuracy": 0.6080852334959673,
|
| 97 |
+
"eval_f1": 0.7152365793662278,
|
| 98 |
+
"eval_loss": 0.6543276309967041,
|
| 99 |
+
"eval_precision": 0.5675086107921928,
|
| 100 |
+
"eval_recall": 0.9669405320813772,
|
| 101 |
+
"eval_runtime": 48.5351,
|
| 102 |
+
"eval_samples_per_second": 206.923,
|
| 103 |
+
"eval_steps_per_second": 12.939,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0621348911311737,
|
| 108 |
+
"grad_norm": 17.797739028930664,
|
| 109 |
+
"learning_rate": 1.0621348911311736e-06,
|
| 110 |
+
"loss": 0.6685,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.0621348911311737,
|
| 115 |
+
"eval_accuracy": 0.6179428457632181,
|
| 116 |
+
"eval_f1": 0.7082794799665476,
|
| 117 |
+
"eval_loss": 0.6436656713485718,
|
| 118 |
+
"eval_precision": 0.5792811839323467,
|
| 119 |
+
"eval_recall": 0.911189358372457,
|
| 120 |
+
"eval_runtime": 48.6552,
|
| 121 |
+
"eval_samples_per_second": 206.412,
|
| 122 |
+
"eval_steps_per_second": 12.907,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2391573729863692,
|
| 127 |
+
"grad_norm": 9.185620307922363,
|
| 128 |
+
"learning_rate": 1.2391573729863691e-06,
|
| 129 |
+
"loss": 0.6598,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.2391573729863692,
|
| 134 |
+
"eval_accuracy": 0.630986756945136,
|
| 135 |
+
"eval_f1": 0.7220638968051597,
|
| 136 |
+
"eval_loss": 0.6283608675003052,
|
| 137 |
+
"eval_precision": 0.5855023108732669,
|
| 138 |
+
"eval_recall": 0.9417057902973396,
|
| 139 |
+
"eval_runtime": 48.3633,
|
| 140 |
+
"eval_samples_per_second": 207.657,
|
| 141 |
+
"eval_steps_per_second": 12.985,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.416179854841565,
|
| 146 |
+
"grad_norm": 4.287769794464111,
|
| 147 |
+
"learning_rate": 1.4161798548415648e-06,
|
| 148 |
+
"loss": 0.6587,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.416179854841565,
|
| 153 |
+
"eval_accuracy": 0.6417405157821369,
|
| 154 |
+
"eval_f1": 0.7242489270386266,
|
| 155 |
+
"eval_loss": 0.6228181719779968,
|
| 156 |
+
"eval_precision": 0.5953881048387096,
|
| 157 |
+
"eval_recall": 0.9242957746478874,
|
| 158 |
+
"eval_runtime": 48.577,
|
| 159 |
+
"eval_samples_per_second": 206.744,
|
| 160 |
+
"eval_steps_per_second": 12.928,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.5932023366967605,
|
| 165 |
+
"grad_norm": 6.105784893035889,
|
| 166 |
+
"learning_rate": 1.5932023366967605e-06,
|
| 167 |
+
"loss": 0.6522,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.5932023366967605,
|
| 172 |
+
"eval_accuracy": 0.6528925619834711,
|
| 173 |
+
"eval_f1": 0.736228813559322,
|
| 174 |
+
"eval_loss": 0.6043413877487183,
|
| 175 |
+
"eval_precision": 0.6003208292201382,
|
| 176 |
+
"eval_recall": 0.9516823161189358,
|
| 177 |
+
"eval_runtime": 48.4503,
|
| 178 |
+
"eval_samples_per_second": 207.284,
|
| 179 |
+
"eval_steps_per_second": 12.962,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.7702248185519562,
|
| 184 |
+
"grad_norm": 2.1733198165893555,
|
| 185 |
+
"learning_rate": 1.770224818551956e-06,
|
| 186 |
+
"loss": 0.6593,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.7702248185519562,
|
| 191 |
+
"eval_accuracy": 0.6620531713631385,
|
| 192 |
+
"eval_f1": 0.646531972505728,
|
| 193 |
+
"eval_loss": 0.6066622734069824,
|
| 194 |
+
"eval_precision": 0.6913140311804009,
|
| 195 |
+
"eval_recall": 0.6071987480438185,
|
| 196 |
+
"eval_runtime": 48.6257,
|
| 197 |
+
"eval_samples_per_second": 206.537,
|
| 198 |
+
"eval_steps_per_second": 12.915,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.9472473004071515,
|
| 203 |
+
"grad_norm": 11.66081714630127,
|
| 204 |
+
"learning_rate": 1.9472473004071516e-06,
|
| 205 |
+
"loss": 0.6324,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.9472473004071515,
|
| 210 |
+
"eval_accuracy": 0.667430050781639,
|
| 211 |
+
"eval_f1": 0.6654647435897436,
|
| 212 |
+
"eval_loss": 0.5872398018836975,
|
| 213 |
+
"eval_precision": 0.6818555008210181,
|
| 214 |
+
"eval_recall": 0.6498435054773083,
|
| 215 |
+
"eval_runtime": 48.3877,
|
| 216 |
+
"eval_samples_per_second": 207.553,
|
| 217 |
+
"eval_steps_per_second": 12.979,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.1242697822623473,
|
| 222 |
+
"grad_norm": 22.538427352905273,
|
| 223 |
+
"learning_rate": 1.9861922464152945e-06,
|
| 224 |
+
"loss": 0.6223,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.1242697822623473,
|
| 229 |
+
"eval_accuracy": 0.6970028875833915,
|
| 230 |
+
"eval_f1": 0.7325305440801617,
|
| 231 |
+
"eval_loss": 0.5736498236656189,
|
| 232 |
+
"eval_precision": 0.6651237031125299,
|
| 233 |
+
"eval_recall": 0.8151408450704225,
|
| 234 |
+
"eval_runtime": 48.7219,
|
| 235 |
+
"eval_samples_per_second": 206.129,
|
| 236 |
+
"eval_steps_per_second": 12.889,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.301292264117543,
|
| 241 |
+
"grad_norm": 34.23973846435547,
|
| 242 |
+
"learning_rate": 1.9665230817647173e-06,
|
| 243 |
+
"loss": 0.6164,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.301292264117543,
|
| 248 |
+
"eval_accuracy": 0.6979986059942248,
|
| 249 |
+
"eval_f1": 0.7626946248337376,
|
| 250 |
+
"eval_loss": 0.562938392162323,
|
| 251 |
+
"eval_precision": 0.635545703481549,
|
| 252 |
+
"eval_recall": 0.9534428794992176,
|
| 253 |
+
"eval_runtime": 48.4533,
|
| 254 |
+
"eval_samples_per_second": 207.272,
|
| 255 |
+
"eval_steps_per_second": 12.961,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.4783147459727384,
|
| 260 |
+
"grad_norm": 12.478341102600098,
|
| 261 |
+
"learning_rate": 1.94685391711414e-06,
|
| 262 |
+
"loss": 0.5989,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.4783147459727384,
|
| 267 |
+
"eval_accuracy": 0.6986956088818083,
|
| 268 |
+
"eval_f1": 0.7548209366391184,
|
| 269 |
+
"eval_loss": 0.5621292591094971,
|
| 270 |
+
"eval_precision": 0.6442600276625173,
|
| 271 |
+
"eval_recall": 0.911189358372457,
|
| 272 |
+
"eval_runtime": 48.6389,
|
| 273 |
+
"eval_samples_per_second": 206.481,
|
| 274 |
+
"eval_steps_per_second": 12.911,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.655337227827934,
|
| 279 |
+
"grad_norm": 12.369190216064453,
|
| 280 |
+
"learning_rate": 1.9271847524635626e-06,
|
| 281 |
+
"loss": 0.5746,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.655337227827934,
|
| 286 |
+
"eval_accuracy": 0.7115403763815593,
|
| 287 |
+
"eval_f1": 0.7359402059976301,
|
| 288 |
+
"eval_loss": 0.5231748819351196,
|
| 289 |
+
"eval_precision": 0.6890254309609148,
|
| 290 |
+
"eval_recall": 0.7897104851330203,
|
| 291 |
+
"eval_runtime": 48.3574,
|
| 292 |
+
"eval_samples_per_second": 207.683,
|
| 293 |
+
"eval_steps_per_second": 12.987,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.83235970968313,
|
| 298 |
+
"grad_norm": 20.652965545654297,
|
| 299 |
+
"learning_rate": 1.9075155878129855e-06,
|
| 300 |
+
"loss": 0.5257,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.83235970968313,
|
| 305 |
+
"eval_accuracy": 0.7224932789007269,
|
| 306 |
+
"eval_f1": 0.7712386111795124,
|
| 307 |
+
"eval_loss": 0.4791330397129059,
|
| 308 |
+
"eval_precision": 0.6644039032668646,
|
| 309 |
+
"eval_recall": 0.9190140845070423,
|
| 310 |
+
"eval_runtime": 48.5117,
|
| 311 |
+
"eval_samples_per_second": 207.022,
|
| 312 |
+
"eval_steps_per_second": 12.945,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.009382191538325,
|
| 317 |
+
"grad_norm": 12.337203025817871,
|
| 318 |
+
"learning_rate": 1.8878464231624083e-06,
|
| 319 |
+
"loss": 0.4955,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.009382191538325,
|
| 324 |
+
"eval_accuracy": 0.7429055063228119,
|
| 325 |
+
"eval_f1": 0.7466143277723258,
|
| 326 |
+
"eval_loss": 0.4369197189807892,
|
| 327 |
+
"eval_precision": 0.7491138243402915,
|
| 328 |
+
"eval_recall": 0.744131455399061,
|
| 329 |
+
"eval_runtime": 48.4884,
|
| 330 |
+
"eval_samples_per_second": 207.122,
|
| 331 |
+
"eval_steps_per_second": 12.952,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.186404673393521,
|
| 336 |
+
"grad_norm": 78.35604858398438,
|
| 337 |
+
"learning_rate": 1.868177258511831e-06,
|
| 338 |
+
"loss": 0.4701,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.186404673393521,
|
| 343 |
+
"eval_accuracy": 0.7424076471173952,
|
| 344 |
+
"eval_f1": 0.7794731906913307,
|
| 345 |
+
"eval_loss": 0.4281806945800781,
|
| 346 |
+
"eval_precision": 0.6907387822933978,
|
| 347 |
+
"eval_recall": 0.8943661971830986,
|
| 348 |
+
"eval_runtime": 48.4785,
|
| 349 |
+
"eval_samples_per_second": 207.164,
|
| 350 |
+
"eval_steps_per_second": 12.954,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.3634271552487167,
|
| 355 |
+
"grad_norm": 12.168407440185547,
|
| 356 |
+
"learning_rate": 1.8485080938612536e-06,
|
| 357 |
+
"loss": 0.4503,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.3634271552487167,
|
| 362 |
+
"eval_accuracy": 0.7501742507218958,
|
| 363 |
+
"eval_f1": 0.73006993006993,
|
| 364 |
+
"eval_loss": 0.4149376451969147,
|
| 365 |
+
"eval_precision": 0.8111403299067654,
|
| 366 |
+
"eval_recall": 0.6637323943661971,
|
| 367 |
+
"eval_runtime": 48.505,
|
| 368 |
+
"eval_samples_per_second": 207.051,
|
| 369 |
+
"eval_steps_per_second": 12.947,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.5404496371039125,
|
| 374 |
+
"grad_norm": 22.702987670898438,
|
| 375 |
+
"learning_rate": 1.8288389292106762e-06,
|
| 376 |
+
"loss": 0.4408,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.5404496371039125,
|
| 381 |
+
"eval_accuracy": 0.7519665438613959,
|
| 382 |
+
"eval_f1": 0.7831084022638224,
|
| 383 |
+
"eval_loss": 0.4072709083557129,
|
| 384 |
+
"eval_precision": 0.7056331398085673,
|
| 385 |
+
"eval_recall": 0.8796948356807511,
|
| 386 |
+
"eval_runtime": 48.5087,
|
| 387 |
+
"eval_samples_per_second": 207.035,
|
| 388 |
+
"eval_steps_per_second": 12.946,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.717472118959108,
|
| 393 |
+
"grad_norm": 11.862476348876953,
|
| 394 |
+
"learning_rate": 1.809169764560099e-06,
|
| 395 |
+
"loss": 0.4318,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.717472118959108,
|
| 400 |
+
"eval_accuracy": 0.7565468485512297,
|
| 401 |
+
"eval_f1": 0.7653325655053268,
|
| 402 |
+
"eval_loss": 0.398566335439682,
|
| 403 |
+
"eval_precision": 0.751271905031091,
|
| 404 |
+
"eval_recall": 0.7799295774647887,
|
| 405 |
+
"eval_runtime": 48.5139,
|
| 406 |
+
"eval_samples_per_second": 207.013,
|
| 407 |
+
"eval_steps_per_second": 12.945,
|
| 408 |
+
"step": 21000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.8944946008143035,
|
| 412 |
+
"grad_norm": 5.476343631744385,
|
| 413 |
+
"learning_rate": 1.7895005999095219e-06,
|
| 414 |
+
"loss": 0.4275,
|
| 415 |
+
"step": 22000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 3.8944946008143035,
|
| 419 |
+
"eval_accuracy": 0.7611271532410634,
|
| 420 |
+
"eval_f1": 0.7729294841457643,
|
| 421 |
+
"eval_loss": 0.3958267569541931,
|
| 422 |
+
"eval_precision": 0.7487621492756281,
|
| 423 |
+
"eval_recall": 0.7987089201877934,
|
| 424 |
+
"eval_runtime": 48.4857,
|
| 425 |
+
"eval_samples_per_second": 207.133,
|
| 426 |
+
"eval_steps_per_second": 12.952,
|
| 427 |
+
"step": 22000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.071517082669499,
|
| 431 |
+
"grad_norm": 4.330970764160156,
|
| 432 |
+
"learning_rate": 1.7698314352589445e-06,
|
| 433 |
+
"loss": 0.4162,
|
| 434 |
+
"step": 23000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.071517082669499,
|
| 438 |
+
"eval_accuracy": 0.7533605496365627,
|
| 439 |
+
"eval_f1": 0.7667827888146126,
|
| 440 |
+
"eval_loss": 0.3944496214389801,
|
| 441 |
+
"eval_precision": 0.7391541114539844,
|
| 442 |
+
"eval_recall": 0.7965571205007824,
|
| 443 |
+
"eval_runtime": 48.5603,
|
| 444 |
+
"eval_samples_per_second": 206.815,
|
| 445 |
+
"eval_steps_per_second": 12.932,
|
| 446 |
+
"step": 23000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.248539564524695,
|
| 450 |
+
"grad_norm": 4.463377475738525,
|
| 451 |
+
"learning_rate": 1.7501622706083671e-06,
|
| 452 |
+
"loss": 0.4158,
|
| 453 |
+
"step": 24000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.248539564524695,
|
| 457 |
+
"eval_accuracy": 0.7555511301403963,
|
| 458 |
+
"eval_f1": 0.7441908929873919,
|
| 459 |
+
"eval_loss": 0.3938951790332794,
|
| 460 |
+
"eval_precision": 0.7962095875139353,
|
| 461 |
+
"eval_recall": 0.6985524256651017,
|
| 462 |
+
"eval_runtime": 48.4747,
|
| 463 |
+
"eval_samples_per_second": 207.18,
|
| 464 |
+
"eval_steps_per_second": 12.955,
|
| 465 |
+
"step": 24000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.42556204637989,
|
| 469 |
+
"grad_norm": 102.01718139648438,
|
| 470 |
+
"learning_rate": 1.7304931059577898e-06,
|
| 471 |
+
"loss": 0.412,
|
| 472 |
+
"step": 25000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 4.42556204637989,
|
| 476 |
+
"eval_accuracy": 0.7532609777954794,
|
| 477 |
+
"eval_f1": 0.79493545183714,
|
| 478 |
+
"eval_loss": 0.404395192861557,
|
| 479 |
+
"eval_precision": 0.6888984509466437,
|
| 480 |
+
"eval_recall": 0.9395539906103286,
|
| 481 |
+
"eval_runtime": 48.4966,
|
| 482 |
+
"eval_samples_per_second": 207.087,
|
| 483 |
+
"eval_steps_per_second": 12.949,
|
| 484 |
+
"step": 25000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 4.602584528235086,
|
| 488 |
+
"grad_norm": 4.4260969161987305,
|
| 489 |
+
"learning_rate": 1.7108239413072126e-06,
|
| 490 |
+
"loss": 0.406,
|
| 491 |
+
"step": 26000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.602584528235086,
|
| 495 |
+
"eval_accuracy": 0.7578412824853131,
|
| 496 |
+
"eval_f1": 0.7183229094278434,
|
| 497 |
+
"eval_loss": 0.3970828354358673,
|
| 498 |
+
"eval_precision": 0.880465644520159,
|
| 499 |
+
"eval_recall": 0.6066118935837246,
|
| 500 |
+
"eval_runtime": 48.4882,
|
| 501 |
+
"eval_samples_per_second": 207.122,
|
| 502 |
+
"eval_steps_per_second": 12.952,
|
| 503 |
+
"step": 26000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.779607010090281,
|
| 507 |
+
"grad_norm": 9.056214332580566,
|
| 508 |
+
"learning_rate": 1.6911547766566355e-06,
|
| 509 |
+
"loss": 0.4044,
|
| 510 |
+
"step": 27000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 4.779607010090281,
|
| 514 |
+
"eval_accuracy": 0.7609280095588967,
|
| 515 |
+
"eval_f1": 0.7647231749142577,
|
| 516 |
+
"eval_loss": 0.3946742117404938,
|
| 517 |
+
"eval_precision": 0.7661496171215394,
|
| 518 |
+
"eval_recall": 0.763302034428795,
|
| 519 |
+
"eval_runtime": 48.479,
|
| 520 |
+
"eval_samples_per_second": 207.162,
|
| 521 |
+
"eval_steps_per_second": 12.954,
|
| 522 |
+
"step": 27000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.956629491945477,
|
| 526 |
+
"grad_norm": 70.51245880126953,
|
| 527 |
+
"learning_rate": 1.671485612006058e-06,
|
| 528 |
+
"loss": 0.407,
|
| 529 |
+
"step": 28000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 4.956629491945477,
|
| 533 |
+
"eval_accuracy": 0.7619237279697302,
|
| 534 |
+
"eval_f1": 0.7924659317767555,
|
| 535 |
+
"eval_loss": 0.3901920020580292,
|
| 536 |
+
"eval_precision": 0.7122796068029333,
|
| 537 |
+
"eval_recall": 0.8929968701095462,
|
| 538 |
+
"eval_runtime": 48.4988,
|
| 539 |
+
"eval_samples_per_second": 207.077,
|
| 540 |
+
"eval_steps_per_second": 12.949,
|
| 541 |
+
"step": 28000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.1336519738006725,
|
| 545 |
+
"grad_norm": 1.7648775577545166,
|
| 546 |
+
"learning_rate": 1.6518164473554807e-06,
|
| 547 |
+
"loss": 0.3916,
|
| 548 |
+
"step": 29000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.1336519738006725,
|
| 552 |
+
"eval_accuracy": 0.7610275813999801,
|
| 553 |
+
"eval_f1": 0.7391304347826086,
|
| 554 |
+
"eval_loss": 0.38304734230041504,
|
| 555 |
+
"eval_precision": 0.8317025440313112,
|
| 556 |
+
"eval_recall": 0.6651017214397497,
|
| 557 |
+
"eval_runtime": 48.5026,
|
| 558 |
+
"eval_samples_per_second": 207.061,
|
| 559 |
+
"eval_steps_per_second": 12.948,
|
| 560 |
+
"step": 29000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 5.310674455655868,
|
| 564 |
+
"grad_norm": 5.286086559295654,
|
| 565 |
+
"learning_rate": 1.6321472827049034e-06,
|
| 566 |
+
"loss": 0.4001,
|
| 567 |
+
"step": 30000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 5.310674455655868,
|
| 571 |
+
"eval_accuracy": 0.764512595837897,
|
| 572 |
+
"eval_f1": 0.7388183324130315,
|
| 573 |
+
"eval_loss": 0.3838052451610565,
|
| 574 |
+
"eval_precision": 0.8483388283033223,
|
| 575 |
+
"eval_recall": 0.6543427230046949,
|
| 576 |
+
"eval_runtime": 48.8022,
|
| 577 |
+
"eval_samples_per_second": 205.79,
|
| 578 |
+
"eval_steps_per_second": 12.868,
|
| 579 |
+
"step": 30000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 5.487696937511064,
|
| 583 |
+
"grad_norm": 22.618858337402344,
|
| 584 |
+
"learning_rate": 1.612478118054326e-06,
|
| 585 |
+
"loss": 0.3886,
|
| 586 |
+
"step": 31000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 5.487696937511064,
|
| 590 |
+
"eval_accuracy": 0.7602310066713134,
|
| 591 |
+
"eval_f1": 0.8046088932164882,
|
| 592 |
+
"eval_loss": 0.3872602581977844,
|
| 593 |
+
"eval_precision": 0.687465335551858,
|
| 594 |
+
"eval_recall": 0.9698748043818466,
|
| 595 |
+
"eval_runtime": 48.4944,
|
| 596 |
+
"eval_samples_per_second": 207.096,
|
| 597 |
+
"eval_steps_per_second": 12.95,
|
| 598 |
+
"step": 31000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 5.66471941936626,
|
| 602 |
+
"grad_norm": 11.363678932189941,
|
| 603 |
+
"learning_rate": 1.5928089534037488e-06,
|
| 604 |
+
"loss": 0.3802,
|
| 605 |
+
"step": 32000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.66471941936626,
|
| 609 |
+
"eval_accuracy": 0.7706860499850642,
|
| 610 |
+
"eval_f1": 0.800138852729324,
|
| 611 |
+
"eval_loss": 0.37955331802368164,
|
| 612 |
+
"eval_precision": 0.7190765871158945,
|
| 613 |
+
"eval_recall": 0.9017996870109546,
|
| 614 |
+
"eval_runtime": 48.4665,
|
| 615 |
+
"eval_samples_per_second": 207.215,
|
| 616 |
+
"eval_steps_per_second": 12.957,
|
| 617 |
+
"step": 32000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.8417419012214555,
|
| 621 |
+
"grad_norm": 18.808916091918945,
|
| 622 |
+
"learning_rate": 1.5731397887531717e-06,
|
| 623 |
+
"loss": 0.383,
|
| 624 |
+
"step": 33000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.8417419012214555,
|
| 628 |
+
"eval_accuracy": 0.7748680673105646,
|
| 629 |
+
"eval_f1": 0.8042932571626418,
|
| 630 |
+
"eval_loss": 0.3785202205181122,
|
| 631 |
+
"eval_precision": 0.7213165657506598,
|
| 632 |
+
"eval_recall": 0.9088419405320813,
|
| 633 |
+
"eval_runtime": 48.5221,
|
| 634 |
+
"eval_samples_per_second": 206.978,
|
| 635 |
+
"eval_steps_per_second": 12.943,
|
| 636 |
+
"step": 33000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 6.01876438307665,
|
| 640 |
+
"grad_norm": 3.9943904876708984,
|
| 641 |
+
"learning_rate": 1.5534706241025943e-06,
|
| 642 |
+
"loss": 0.3833,
|
| 643 |
+
"step": 34000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 6.01876438307665,
|
| 647 |
+
"eval_accuracy": 0.7772577914965648,
|
| 648 |
+
"eval_f1": 0.787296757630503,
|
| 649 |
+
"eval_loss": 0.3748994767665863,
|
| 650 |
+
"eval_precision": 0.7659574468085106,
|
| 651 |
+
"eval_recall": 0.8098591549295775,
|
| 652 |
+
"eval_runtime": 48.5676,
|
| 653 |
+
"eval_samples_per_second": 206.784,
|
| 654 |
+
"eval_steps_per_second": 12.93,
|
| 655 |
+
"step": 34000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 6.195786864931846,
|
| 659 |
+
"grad_norm": 5.812683582305908,
|
| 660 |
+
"learning_rate": 1.533801459452017e-06,
|
| 661 |
+
"loss": 0.3695,
|
| 662 |
+
"step": 35000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.195786864931846,
|
| 666 |
+
"eval_accuracy": 0.776759932291148,
|
| 667 |
+
"eval_f1": 0.8093537414965987,
|
| 668 |
+
"eval_loss": 0.38256847858428955,
|
| 669 |
+
"eval_precision": 0.7158543922984356,
|
| 670 |
+
"eval_recall": 0.9309467918622848,
|
| 671 |
+
"eval_runtime": 48.4235,
|
| 672 |
+
"eval_samples_per_second": 207.399,
|
| 673 |
+
"eval_steps_per_second": 12.969,
|
| 674 |
+
"step": 35000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.372809346787042,
|
| 678 |
+
"grad_norm": 3.7167677879333496,
|
| 679 |
+
"learning_rate": 1.5141322948014396e-06,
|
| 680 |
+
"loss": 0.3732,
|
| 681 |
+
"step": 36000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.372809346787042,
|
| 685 |
+
"eval_accuracy": 0.7745693517873146,
|
| 686 |
+
"eval_f1": 0.8088806348134391,
|
| 687 |
+
"eval_loss": 0.3752972483634949,
|
| 688 |
+
"eval_precision": 0.7114642114642115,
|
| 689 |
+
"eval_recall": 0.937206572769953,
|
| 690 |
+
"eval_runtime": 48.483,
|
| 691 |
+
"eval_samples_per_second": 207.145,
|
| 692 |
+
"eval_steps_per_second": 12.953,
|
| 693 |
+
"step": 36000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.549831828642238,
|
| 697 |
+
"grad_norm": 16.73068618774414,
|
| 698 |
+
"learning_rate": 1.4944631301508624e-06,
|
| 699 |
+
"loss": 0.3675,
|
| 700 |
+
"step": 37000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 6.549831828642238,
|
| 704 |
+
"eval_accuracy": 0.7851239669421488,
|
| 705 |
+
"eval_f1": 0.7800652262535671,
|
| 706 |
+
"eval_loss": 0.3612446188926697,
|
| 707 |
+
"eval_precision": 0.8142553191489361,
|
| 708 |
+
"eval_recall": 0.7486306729264476,
|
| 709 |
+
"eval_runtime": 48.4403,
|
| 710 |
+
"eval_samples_per_second": 207.327,
|
| 711 |
+
"eval_steps_per_second": 12.964,
|
| 712 |
+
"step": 37000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 6.726854310497433,
|
| 716 |
+
"grad_norm": 11.350728988647461,
|
| 717 |
+
"learning_rate": 1.4747939655002853e-06,
|
| 718 |
+
"loss": 0.3631,
|
| 719 |
+
"step": 38000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 6.726854310497433,
|
| 723 |
+
"eval_accuracy": 0.7871154037638156,
|
| 724 |
+
"eval_f1": 0.7887769215570045,
|
| 725 |
+
"eval_loss": 0.3669988214969635,
|
| 726 |
+
"eval_precision": 0.7968063872255489,
|
| 727 |
+
"eval_recall": 0.7809076682316118,
|
| 728 |
+
"eval_runtime": 48.6242,
|
| 729 |
+
"eval_samples_per_second": 206.543,
|
| 730 |
+
"eval_steps_per_second": 12.915,
|
| 731 |
+
"step": 38000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 6.903876792352628,
|
| 735 |
+
"grad_norm": 19.71718406677246,
|
| 736 |
+
"learning_rate": 1.455124800849708e-06,
|
| 737 |
+
"loss": 0.3619,
|
| 738 |
+
"step": 39000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 6.903876792352628,
|
| 742 |
+
"eval_accuracy": 0.7860201135118988,
|
| 743 |
+
"eval_f1": 0.8045475216007276,
|
| 744 |
+
"eval_loss": 0.3651063144207001,
|
| 745 |
+
"eval_precision": 0.7518272989971103,
|
| 746 |
+
"eval_recall": 0.8652190923317684,
|
| 747 |
+
"eval_runtime": 48.6286,
|
| 748 |
+
"eval_samples_per_second": 206.524,
|
| 749 |
+
"eval_steps_per_second": 12.914,
|
| 750 |
+
"step": 39000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 7.080899274207824,
|
| 754 |
+
"grad_norm": 25.673242568969727,
|
| 755 |
+
"learning_rate": 1.4354556361991305e-06,
|
| 756 |
+
"loss": 0.3587,
|
| 757 |
+
"step": 40000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 7.080899274207824,
|
| 761 |
+
"eval_accuracy": 0.795977297620233,
|
| 762 |
+
"eval_f1": 0.7845652402481338,
|
| 763 |
+
"eval_loss": 0.35970279574394226,
|
| 764 |
+
"eval_precision": 0.8481473062059559,
|
| 765 |
+
"eval_recall": 0.7298513302034428,
|
| 766 |
+
"eval_runtime": 48.507,
|
| 767 |
+
"eval_samples_per_second": 207.042,
|
| 768 |
+
"eval_steps_per_second": 12.947,
|
| 769 |
+
"step": 40000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 7.25792175606302,
|
| 773 |
+
"grad_norm": 19.93338966369629,
|
| 774 |
+
"learning_rate": 1.4157864715485532e-06,
|
| 775 |
+
"loss": 0.349,
|
| 776 |
+
"step": 41000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 7.25792175606302,
|
| 780 |
+
"eval_accuracy": 0.7883102658568157,
|
| 781 |
+
"eval_f1": 0.7995096190116937,
|
| 782 |
+
"eval_loss": 0.3596351444721222,
|
| 783 |
+
"eval_precision": 0.7718499635833941,
|
| 784 |
+
"eval_recall": 0.829225352112676,
|
| 785 |
+
"eval_runtime": 48.3456,
|
| 786 |
+
"eval_samples_per_second": 207.734,
|
| 787 |
+
"eval_steps_per_second": 12.99,
|
| 788 |
+
"step": 41000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 7.434944237918216,
|
| 792 |
+
"grad_norm": 7.293708801269531,
|
| 793 |
+
"learning_rate": 1.396117306897976e-06,
|
| 794 |
+
"loss": 0.3402,
|
| 795 |
+
"step": 42000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 7.434944237918216,
|
| 799 |
+
"eval_accuracy": 0.7938862889574828,
|
| 800 |
+
"eval_f1": 0.7982849347105827,
|
| 801 |
+
"eval_loss": 0.3619771897792816,
|
| 802 |
+
"eval_precision": 0.7953398058252428,
|
| 803 |
+
"eval_recall": 0.8012519561815337,
|
| 804 |
+
"eval_runtime": 48.7896,
|
| 805 |
+
"eval_samples_per_second": 205.843,
|
| 806 |
+
"eval_steps_per_second": 12.872,
|
| 807 |
+
"step": 42000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 7.611966719773411,
|
| 811 |
+
"grad_norm": 82.438720703125,
|
| 812 |
+
"learning_rate": 1.3764481422473986e-06,
|
| 813 |
+
"loss": 0.3448,
|
| 814 |
+
"step": 43000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 7.611966719773411,
|
| 818 |
+
"eval_accuracy": 0.7969730160310664,
|
| 819 |
+
"eval_f1": 0.8135345221764975,
|
| 820 |
+
"eval_loss": 0.3580198884010315,
|
| 821 |
+
"eval_precision": 0.7638674222909153,
|
| 822 |
+
"eval_recall": 0.8701095461658842,
|
| 823 |
+
"eval_runtime": 48.395,
|
| 824 |
+
"eval_samples_per_second": 207.522,
|
| 825 |
+
"eval_steps_per_second": 12.977,
|
| 826 |
+
"step": 43000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 7.788989201628607,
|
| 830 |
+
"grad_norm": 13.257980346679688,
|
| 831 |
+
"learning_rate": 1.3567789775968215e-06,
|
| 832 |
+
"loss": 0.336,
|
| 833 |
+
"step": 44000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 7.788989201628607,
|
| 837 |
+
"eval_accuracy": 0.7987653091705665,
|
| 838 |
+
"eval_f1": 0.7967005331455588,
|
| 839 |
+
"eval_loss": 0.3453768789768219,
|
| 840 |
+
"eval_precision": 0.8200455580865603,
|
| 841 |
+
"eval_recall": 0.7746478873239436,
|
| 842 |
+
"eval_runtime": 48.664,
|
| 843 |
+
"eval_samples_per_second": 206.374,
|
| 844 |
+
"eval_steps_per_second": 12.905,
|
| 845 |
+
"step": 44000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 7.966011683483803,
|
| 849 |
+
"grad_norm": 11.088878631591797,
|
| 850 |
+
"learning_rate": 1.3371098129462441e-06,
|
| 851 |
+
"loss": 0.336,
|
| 852 |
+
"step": 45000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 7.966011683483803,
|
| 856 |
+
"eval_accuracy": 0.8018520362441501,
|
| 857 |
+
"eval_f1": 0.8217484772482981,
|
| 858 |
+
"eval_loss": 0.3519151210784912,
|
| 859 |
+
"eval_precision": 0.7579312623925974,
|
| 860 |
+
"eval_recall": 0.8973004694835681,
|
| 861 |
+
"eval_runtime": 48.4613,
|
| 862 |
+
"eval_samples_per_second": 207.237,
|
| 863 |
+
"eval_steps_per_second": 12.959,
|
| 864 |
+
"step": 45000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 8.143034165338998,
|
| 868 |
+
"grad_norm": 10.603625297546387,
|
| 869 |
+
"learning_rate": 1.3174406482956667e-06,
|
| 870 |
+
"loss": 0.3307,
|
| 871 |
+
"step": 46000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 8.143034165338998,
|
| 875 |
+
"eval_accuracy": 0.8025490391317336,
|
| 876 |
+
"eval_f1": 0.8225185715564307,
|
| 877 |
+
"eval_loss": 0.3641522526741028,
|
| 878 |
+
"eval_precision": 0.7581257218280811,
|
| 879 |
+
"eval_recall": 0.8988654147104851,
|
| 880 |
+
"eval_runtime": 48.5668,
|
| 881 |
+
"eval_samples_per_second": 206.788,
|
| 882 |
+
"eval_steps_per_second": 12.931,
|
| 883 |
+
"step": 46000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 8.320056647194194,
|
| 887 |
+
"grad_norm": 45.665870666503906,
|
| 888 |
+
"learning_rate": 1.2977714836450896e-06,
|
| 889 |
+
"loss": 0.3192,
|
| 890 |
+
"step": 47000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 8.320056647194194,
|
| 894 |
+
"eval_accuracy": 0.8047396196355671,
|
| 895 |
+
"eval_f1": 0.8228705627314605,
|
| 896 |
+
"eval_loss": 0.3606601357460022,
|
| 897 |
+
"eval_precision": 0.764389998321866,
|
| 898 |
+
"eval_recall": 0.8910406885758998,
|
| 899 |
+
"eval_runtime": 48.3992,
|
| 900 |
+
"eval_samples_per_second": 207.504,
|
| 901 |
+
"eval_steps_per_second": 12.975,
|
| 902 |
+
"step": 47000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 8.49707912904939,
|
| 906 |
+
"grad_norm": 45.48286819458008,
|
| 907 |
+
"learning_rate": 1.2781023189945122e-06,
|
| 908 |
+
"loss": 0.325,
|
| 909 |
+
"step": 48000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 8.49707912904939,
|
| 913 |
+
"eval_accuracy": 0.8093199243254008,
|
| 914 |
+
"eval_f1": 0.802963267825908,
|
| 915 |
+
"eval_loss": 0.34560200572013855,
|
| 916 |
+
"eval_precision": 0.846971999131756,
|
| 917 |
+
"eval_recall": 0.763302034428795,
|
| 918 |
+
"eval_runtime": 48.6156,
|
| 919 |
+
"eval_samples_per_second": 206.58,
|
| 920 |
+
"eval_steps_per_second": 12.918,
|
| 921 |
+
"step": 48000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.674101610904584,
|
| 925 |
+
"grad_norm": 12.470772743225098,
|
| 926 |
+
"learning_rate": 1.258433154343935e-06,
|
| 927 |
+
"loss": 0.32,
|
| 928 |
+
"step": 49000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 8.674101610904584,
|
| 932 |
+
"eval_accuracy": 0.8102160708951508,
|
| 933 |
+
"eval_f1": 0.8108751736455646,
|
| 934 |
+
"eval_loss": 0.3369452655315399,
|
| 935 |
+
"eval_precision": 0.8227950060410794,
|
| 936 |
+
"eval_recall": 0.7992957746478874,
|
| 937 |
+
"eval_runtime": 48.3828,
|
| 938 |
+
"eval_samples_per_second": 207.574,
|
| 939 |
+
"eval_steps_per_second": 12.98,
|
| 940 |
+
"step": 49000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 8.85112409275978,
|
| 944 |
+
"grad_norm": 9.075933456420898,
|
| 945 |
+
"learning_rate": 1.2387639896933577e-06,
|
| 946 |
+
"loss": 0.316,
|
| 947 |
+
"step": 50000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 8.85112409275978,
|
| 951 |
+
"eval_accuracy": 0.8132032261276511,
|
| 952 |
+
"eval_f1": 0.8101214574898785,
|
| 953 |
+
"eval_loss": 0.34877920150756836,
|
| 954 |
+
"eval_precision": 0.8393456375838926,
|
| 955 |
+
"eval_recall": 0.7828638497652582,
|
| 956 |
+
"eval_runtime": 48.5199,
|
| 957 |
+
"eval_samples_per_second": 206.987,
|
| 958 |
+
"eval_steps_per_second": 12.943,
|
| 959 |
+
"step": 50000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 9.028146574614976,
|
| 963 |
+
"grad_norm": 19.899991989135742,
|
| 964 |
+
"learning_rate": 1.2190948250427803e-06,
|
| 965 |
+
"loss": 0.3202,
|
| 966 |
+
"step": 51000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 9.028146574614976,
|
| 970 |
+
"eval_accuracy": 0.8114109329881509,
|
| 971 |
+
"eval_f1": 0.8094567404426559,
|
| 972 |
+
"eval_loss": 0.339097797870636,
|
| 973 |
+
"eval_precision": 0.8332642916321458,
|
| 974 |
+
"eval_recall": 0.7869718309859155,
|
| 975 |
+
"eval_runtime": 48.4752,
|
| 976 |
+
"eval_samples_per_second": 207.178,
|
| 977 |
+
"eval_steps_per_second": 12.955,
|
| 978 |
+
"step": 51000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.205169056470172,
|
| 982 |
+
"grad_norm": 12.141376495361328,
|
| 983 |
+
"learning_rate": 1.199425660392203e-06,
|
| 984 |
+
"loss": 0.3081,
|
| 985 |
+
"step": 52000
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.205169056470172,
|
| 989 |
+
"eval_accuracy": 0.8111122174649009,
|
| 990 |
+
"eval_f1": 0.8052561338671594,
|
| 991 |
+
"eval_loss": 0.32928845286369324,
|
| 992 |
+
"eval_precision": 0.8472672283430547,
|
| 993 |
+
"eval_recall": 0.7672143974960877,
|
| 994 |
+
"eval_runtime": 48.4715,
|
| 995 |
+
"eval_samples_per_second": 207.194,
|
| 996 |
+
"eval_steps_per_second": 12.956,
|
| 997 |
+
"step": 52000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 9.382191538325367,
|
| 1001 |
+
"grad_norm": 10.343143463134766,
|
| 1002 |
+
"learning_rate": 1.1797564957416258e-06,
|
| 1003 |
+
"loss": 0.3036,
|
| 1004 |
+
"step": 53000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 9.382191538325367,
|
| 1008 |
+
"eval_accuracy": 0.8130040824454844,
|
| 1009 |
+
"eval_f1": 0.8091463414634147,
|
| 1010 |
+
"eval_loss": 0.3455412685871124,
|
| 1011 |
+
"eval_precision": 0.8420050761421319,
|
| 1012 |
+
"eval_recall": 0.778755868544601,
|
| 1013 |
+
"eval_runtime": 48.4453,
|
| 1014 |
+
"eval_samples_per_second": 207.306,
|
| 1015 |
+
"eval_steps_per_second": 12.963,
|
| 1016 |
+
"step": 53000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 9.559214020180562,
|
| 1020 |
+
"grad_norm": 15.281163215637207,
|
| 1021 |
+
"learning_rate": 1.1600873310910486e-06,
|
| 1022 |
+
"loss": 0.3025,
|
| 1023 |
+
"step": 54000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 9.559214020180562,
|
| 1027 |
+
"eval_accuracy": 0.8187792492283182,
|
| 1028 |
+
"eval_f1": 0.828883038736367,
|
| 1029 |
+
"eval_loss": 0.3434953987598419,
|
| 1030 |
+
"eval_precision": 0.7979724837074583,
|
| 1031 |
+
"eval_recall": 0.8622848200312989,
|
| 1032 |
+
"eval_runtime": 48.4882,
|
| 1033 |
+
"eval_samples_per_second": 207.123,
|
| 1034 |
+
"eval_steps_per_second": 12.952,
|
| 1035 |
+
"step": 54000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 9.736236502035759,
|
| 1039 |
+
"grad_norm": 10.584362983703613,
|
| 1040 |
+
"learning_rate": 1.1404181664404713e-06,
|
| 1041 |
+
"loss": 0.2983,
|
| 1042 |
+
"step": 55000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 9.736236502035759,
|
| 1046 |
+
"eval_accuracy": 0.8190779647515682,
|
| 1047 |
+
"eval_f1": 0.8283419933868682,
|
| 1048 |
+
"eval_loss": 0.3416574001312256,
|
| 1049 |
+
"eval_precision": 0.8010232048236798,
|
| 1050 |
+
"eval_recall": 0.8575899843505478,
|
| 1051 |
+
"eval_runtime": 48.4574,
|
| 1052 |
+
"eval_samples_per_second": 207.254,
|
| 1053 |
+
"eval_steps_per_second": 12.96,
|
| 1054 |
+
"step": 55000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 9.913258983890954,
|
| 1058 |
+
"grad_norm": 18.094242095947266,
|
| 1059 |
+
"learning_rate": 1.120749001789894e-06,
|
| 1060 |
+
"loss": 0.2959,
|
| 1061 |
+
"step": 56000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 9.913258983890954,
|
| 1065 |
+
"eval_accuracy": 0.8174848152942348,
|
| 1066 |
+
"eval_f1": 0.8205228630177225,
|
| 1067 |
+
"eval_loss": 0.3372325301170349,
|
| 1068 |
+
"eval_precision": 0.8214075671436973,
|
| 1069 |
+
"eval_recall": 0.8196400625978091,
|
| 1070 |
+
"eval_runtime": 48.5309,
|
| 1071 |
+
"eval_samples_per_second": 206.94,
|
| 1072 |
+
"eval_steps_per_second": 12.94,
|
| 1073 |
+
"step": 56000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 10.09028146574615,
|
| 1077 |
+
"grad_norm": 7.2225422859191895,
|
| 1078 |
+
"learning_rate": 1.1010798371393165e-06,
|
| 1079 |
+
"loss": 0.2917,
|
| 1080 |
+
"step": 57000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 10.09028146574615,
|
| 1084 |
+
"eval_accuracy": 0.8219655481429852,
|
| 1085 |
+
"eval_f1": 0.8156320890905341,
|
| 1086 |
+
"eval_loss": 0.3421269953250885,
|
| 1087 |
+
"eval_precision": 0.8624073266463149,
|
| 1088 |
+
"eval_recall": 0.7736697965571205,
|
| 1089 |
+
"eval_runtime": 48.4733,
|
| 1090 |
+
"eval_samples_per_second": 207.186,
|
| 1091 |
+
"eval_steps_per_second": 12.956,
|
| 1092 |
+
"step": 57000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 10.267303947601345,
|
| 1096 |
+
"grad_norm": 21.429712295532227,
|
| 1097 |
+
"learning_rate": 1.0814106724887394e-06,
|
| 1098 |
+
"loss": 0.2856,
|
| 1099 |
+
"step": 58000
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 10.267303947601345,
|
| 1103 |
+
"eval_accuracy": 0.8219655481429852,
|
| 1104 |
+
"eval_f1": 0.8340141106572596,
|
| 1105 |
+
"eval_loss": 0.3443463146686554,
|
| 1106 |
+
"eval_precision": 0.7936395759717314,
|
| 1107 |
+
"eval_recall": 0.878716744913928,
|
| 1108 |
+
"eval_runtime": 48.4616,
|
| 1109 |
+
"eval_samples_per_second": 207.236,
|
| 1110 |
+
"eval_steps_per_second": 12.959,
|
| 1111 |
+
"step": 58000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 10.444326429456542,
|
| 1115 |
+
"grad_norm": 89.16828918457031,
|
| 1116 |
+
"learning_rate": 1.061741507838162e-06,
|
| 1117 |
+
"loss": 0.2855,
|
| 1118 |
+
"step": 59000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 10.444326429456542,
|
| 1122 |
+
"eval_accuracy": 0.8195758239569849,
|
| 1123 |
+
"eval_f1": 0.8235981308411215,
|
| 1124 |
+
"eval_loss": 0.3458768427371979,
|
| 1125 |
+
"eval_precision": 0.8197674418604651,
|
| 1126 |
+
"eval_recall": 0.8274647887323944,
|
| 1127 |
+
"eval_runtime": 48.4454,
|
| 1128 |
+
"eval_samples_per_second": 207.305,
|
| 1129 |
+
"eval_steps_per_second": 12.963,
|
| 1130 |
+
"step": 59000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 10.621348911311737,
|
| 1134 |
+
"grad_norm": 6.35772705078125,
|
| 1135 |
+
"learning_rate": 1.0420723431875849e-06,
|
| 1136 |
+
"loss": 0.2869,
|
| 1137 |
+
"step": 60000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 10.621348911311737,
|
| 1141 |
+
"eval_accuracy": 0.8268445683560689,
|
| 1142 |
+
"eval_f1": 0.8420957050758194,
|
| 1143 |
+
"eval_loss": 0.3441038131713867,
|
| 1144 |
+
"eval_precision": 0.7857990171157431,
|
| 1145 |
+
"eval_recall": 0.9070813771517997,
|
| 1146 |
+
"eval_runtime": 48.5327,
|
| 1147 |
+
"eval_samples_per_second": 206.932,
|
| 1148 |
+
"eval_steps_per_second": 12.94,
|
| 1149 |
+
"step": 60000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 10.798371393166931,
|
| 1153 |
+
"grad_norm": 13.831587791442871,
|
| 1154 |
+
"learning_rate": 1.0224031785370075e-06,
|
| 1155 |
+
"loss": 0.2902,
|
| 1156 |
+
"step": 61000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 10.798371393166931,
|
| 1160 |
+
"eval_accuracy": 0.8228616947127353,
|
| 1161 |
+
"eval_f1": 0.8143200083498591,
|
| 1162 |
+
"eval_loss": 0.3371775150299072,
|
| 1163 |
+
"eval_precision": 0.8729022152606847,
|
| 1164 |
+
"eval_recall": 0.7631064162754304,
|
| 1165 |
+
"eval_runtime": 48.4429,
|
| 1166 |
+
"eval_samples_per_second": 207.316,
|
| 1167 |
+
"eval_steps_per_second": 12.964,
|
| 1168 |
+
"step": 61000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 10.975393875022128,
|
| 1172 |
+
"grad_norm": 47.082096099853516,
|
| 1173 |
+
"learning_rate": 1.0027340138864301e-06,
|
| 1174 |
+
"loss": 0.2886,
|
| 1175 |
+
"step": 62000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 10.975393875022128,
|
| 1179 |
+
"eval_accuracy": 0.8266454246739022,
|
| 1180 |
+
"eval_f1": 0.8348980559506876,
|
| 1181 |
+
"eval_loss": 0.32535311579704285,
|
| 1182 |
+
"eval_precision": 0.8102337566721884,
|
| 1183 |
+
"eval_recall": 0.8611111111111112,
|
| 1184 |
+
"eval_runtime": 48.5202,
|
| 1185 |
+
"eval_samples_per_second": 206.986,
|
| 1186 |
+
"eval_steps_per_second": 12.943,
|
| 1187 |
+
"step": 62000
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 11.152416356877323,
|
| 1191 |
+
"grad_norm": 14.556977272033691,
|
| 1192 |
+
"learning_rate": 9.83064849235853e-07,
|
| 1193 |
+
"loss": 0.2788,
|
| 1194 |
+
"step": 63000
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 11.152416356877323,
|
| 1198 |
+
"eval_accuracy": 0.8296325799064025,
|
| 1199 |
+
"eval_f1": 0.8395987625386707,
|
| 1200 |
+
"eval_loss": 0.3404853045940399,
|
| 1201 |
+
"eval_precision": 0.8061206120612061,
|
| 1202 |
+
"eval_recall": 0.8759780907668232,
|
| 1203 |
+
"eval_runtime": 48.4849,
|
| 1204 |
+
"eval_samples_per_second": 207.137,
|
| 1205 |
+
"eval_steps_per_second": 12.952,
|
| 1206 |
+
"step": 63000
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 11.32943883873252,
|
| 1210 |
+
"grad_norm": 49.14487075805664,
|
| 1211 |
+
"learning_rate": 9.633956845852756e-07,
|
| 1212 |
+
"loss": 0.2722,
|
| 1213 |
+
"step": 64000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 11.32943883873252,
|
| 1217 |
+
"eval_accuracy": 0.8275415712436522,
|
| 1218 |
+
"eval_f1": 0.8202573682025737,
|
| 1219 |
+
"eval_loss": 0.3554268181324005,
|
| 1220 |
+
"eval_precision": 0.8735632183908046,
|
| 1221 |
+
"eval_recall": 0.7730829420970265,
|
| 1222 |
+
"eval_runtime": 48.5073,
|
| 1223 |
+
"eval_samples_per_second": 207.041,
|
| 1224 |
+
"eval_steps_per_second": 12.947,
|
| 1225 |
+
"step": 64000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 11.506461320587714,
|
| 1229 |
+
"grad_norm": 75.99839782714844,
|
| 1230 |
+
"learning_rate": 9.437265199346983e-07,
|
| 1231 |
+
"loss": 0.2727,
|
| 1232 |
+
"step": 65000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 11.506461320587714,
|
| 1236 |
+
"eval_accuracy": 0.8255501344219854,
|
| 1237 |
+
"eval_f1": 0.8319263238679969,
|
| 1238 |
+
"eval_loss": 0.3575954735279083,
|
| 1239 |
+
"eval_precision": 0.8162650602409639,
|
| 1240 |
+
"eval_recall": 0.8482003129890454,
|
| 1241 |
+
"eval_runtime": 48.4953,
|
| 1242 |
+
"eval_samples_per_second": 207.092,
|
| 1243 |
+
"eval_steps_per_second": 12.95,
|
| 1244 |
+
"step": 65000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 11.683483802442911,
|
| 1248 |
+
"grad_norm": 10.247947692871094,
|
| 1249 |
+
"learning_rate": 9.24057355284121e-07,
|
| 1250 |
+
"loss": 0.2797,
|
| 1251 |
+
"step": 66000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 11.683483802442911,
|
| 1255 |
+
"eval_accuracy": 0.8265458528328189,
|
| 1256 |
+
"eval_f1": 0.8270796108794918,
|
| 1257 |
+
"eval_loss": 0.32501116394996643,
|
| 1258 |
+
"eval_precision": 0.8395808141878275,
|
| 1259 |
+
"eval_recall": 0.814945226917058,
|
| 1260 |
+
"eval_runtime": 48.5218,
|
| 1261 |
+
"eval_samples_per_second": 206.979,
|
| 1262 |
+
"eval_steps_per_second": 12.943,
|
| 1263 |
+
"step": 66000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 11.860506284298106,
|
| 1267 |
+
"grad_norm": 14.356186866760254,
|
| 1268 |
+
"learning_rate": 9.043881906335438e-07,
|
| 1269 |
+
"loss": 0.2775,
|
| 1270 |
+
"step": 67000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 11.860506284298106,
|
| 1274 |
+
"eval_accuracy": 0.8279398586079857,
|
| 1275 |
+
"eval_f1": 0.8267148014440433,
|
| 1276 |
+
"eval_loss": 0.34262222051620483,
|
| 1277 |
+
"eval_precision": 0.8481481481481481,
|
| 1278 |
+
"eval_recall": 0.8063380281690141,
|
| 1279 |
+
"eval_runtime": 48.4239,
|
| 1280 |
+
"eval_samples_per_second": 207.397,
|
| 1281 |
+
"eval_steps_per_second": 12.969,
|
| 1282 |
+
"step": 67000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 12.0375287661533,
|
| 1286 |
+
"grad_norm": 55.23761749267578,
|
| 1287 |
+
"learning_rate": 8.847190259829664e-07,
|
| 1288 |
+
"loss": 0.2753,
|
| 1289 |
+
"step": 68000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 12.0375287661533,
|
| 1293 |
+
"eval_accuracy": 0.8288360051777357,
|
| 1294 |
+
"eval_f1": 0.8412302576891105,
|
| 1295 |
+
"eval_loss": 0.3272722363471985,
|
| 1296 |
+
"eval_precision": 0.7968503937007874,
|
| 1297 |
+
"eval_recall": 0.8908450704225352,
|
| 1298 |
+
"eval_runtime": 48.5309,
|
| 1299 |
+
"eval_samples_per_second": 206.94,
|
| 1300 |
+
"eval_steps_per_second": 12.94,
|
| 1301 |
+
"step": 68000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 12.214551248008497,
|
| 1305 |
+
"grad_norm": 8.974770545959473,
|
| 1306 |
+
"learning_rate": 8.650498613323892e-07,
|
| 1307 |
+
"loss": 0.2625,
|
| 1308 |
+
"step": 69000
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 12.214551248008497,
|
| 1312 |
+
"eval_accuracy": 0.8281390022901524,
|
| 1313 |
+
"eval_f1": 0.8395910780669145,
|
| 1314 |
+
"eval_loss": 0.33536896109580994,
|
| 1315 |
+
"eval_precision": 0.7997521246458924,
|
| 1316 |
+
"eval_recall": 0.8836071987480438,
|
| 1317 |
+
"eval_runtime": 48.4526,
|
| 1318 |
+
"eval_samples_per_second": 207.275,
|
| 1319 |
+
"eval_steps_per_second": 12.961,
|
| 1320 |
+
"step": 69000
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 12.391573729863692,
|
| 1324 |
+
"grad_norm": 6.9588446617126465,
|
| 1325 |
+
"learning_rate": 8.453806966818119e-07,
|
| 1326 |
+
"loss": 0.2593,
|
| 1327 |
+
"step": 70000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 12.391573729863692,
|
| 1331 |
+
"eval_accuracy": 0.8278402867669024,
|
| 1332 |
+
"eval_f1": 0.8303071940327804,
|
| 1333 |
+
"eval_loss": 0.33842170238494873,
|
| 1334 |
+
"eval_precision": 0.8331691944061453,
|
| 1335 |
+
"eval_recall": 0.8274647887323944,
|
| 1336 |
+
"eval_runtime": 48.5216,
|
| 1337 |
+
"eval_samples_per_second": 206.98,
|
| 1338 |
+
"eval_steps_per_second": 12.943,
|
| 1339 |
+
"step": 70000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 12.568596211718889,
|
| 1343 |
+
"grad_norm": 2.9586853981018066,
|
| 1344 |
+
"learning_rate": 8.257115320312346e-07,
|
| 1345 |
+
"loss": 0.2716,
|
| 1346 |
+
"step": 71000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 12.568596211718889,
|
| 1350 |
+
"eval_accuracy": 0.8300308672707358,
|
| 1351 |
+
"eval_f1": 0.8259051504334524,
|
| 1352 |
+
"eval_loss": 0.3227674663066864,
|
| 1353 |
+
"eval_precision": 0.8627743447688047,
|
| 1354 |
+
"eval_recall": 0.792057902973396,
|
| 1355 |
+
"eval_runtime": 48.4717,
|
| 1356 |
+
"eval_samples_per_second": 207.193,
|
| 1357 |
+
"eval_steps_per_second": 12.956,
|
| 1358 |
+
"step": 71000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 12.745618693574084,
|
| 1362 |
+
"grad_norm": 41.94707489013672,
|
| 1363 |
+
"learning_rate": 8.060423673806573e-07,
|
| 1364 |
+
"loss": 0.2673,
|
| 1365 |
+
"step": 72000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 12.745618693574084,
|
| 1369 |
+
"eval_accuracy": 0.8310265856815693,
|
| 1370 |
+
"eval_f1": 0.8221733207586712,
|
| 1371 |
+
"eval_loss": 0.3358391225337982,
|
| 1372 |
+
"eval_precision": 0.8853531934100655,
|
| 1373 |
+
"eval_recall": 0.7674100156494522,
|
| 1374 |
+
"eval_runtime": 48.4704,
|
| 1375 |
+
"eval_samples_per_second": 207.199,
|
| 1376 |
+
"eval_steps_per_second": 12.956,
|
| 1377 |
+
"step": 72000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 12.922641175429279,
|
| 1381 |
+
"grad_norm": 29.572885513305664,
|
| 1382 |
+
"learning_rate": 7.8637320273008e-07,
|
| 1383 |
+
"loss": 0.2656,
|
| 1384 |
+
"step": 73000
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 12.922641175429279,
|
| 1388 |
+
"eval_accuracy": 0.8303295827939858,
|
| 1389 |
+
"eval_f1": 0.8300757877941763,
|
| 1390 |
+
"eval_loss": 0.33422765135765076,
|
| 1391 |
+
"eval_precision": 0.8466232709519935,
|
| 1392 |
+
"eval_recall": 0.8141627543035994,
|
| 1393 |
+
"eval_runtime": 48.4871,
|
| 1394 |
+
"eval_samples_per_second": 207.127,
|
| 1395 |
+
"eval_steps_per_second": 12.952,
|
| 1396 |
+
"step": 73000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 13.099663657284475,
|
| 1400 |
+
"grad_norm": 23.2849178314209,
|
| 1401 |
+
"learning_rate": 7.667040380795027e-07,
|
| 1402 |
+
"loss": 0.2536,
|
| 1403 |
+
"step": 74000
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 13.099663657284475,
|
| 1407 |
+
"eval_accuracy": 0.8306282983172358,
|
| 1408 |
+
"eval_f1": 0.8436149673623242,
|
| 1409 |
+
"eval_loss": 0.3436105251312256,
|
| 1410 |
+
"eval_precision": 0.795836947094536,
|
| 1411 |
+
"eval_recall": 0.8974960876369327,
|
| 1412 |
+
"eval_runtime": 48.5424,
|
| 1413 |
+
"eval_samples_per_second": 206.891,
|
| 1414 |
+
"eval_steps_per_second": 12.937,
|
| 1415 |
+
"step": 74000
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 13.27668613913967,
|
| 1419 |
+
"grad_norm": 8.842978477478027,
|
| 1420 |
+
"learning_rate": 7.470348734289255e-07,
|
| 1421 |
+
"loss": 0.2591,
|
| 1422 |
+
"step": 75000
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 13.27668613913967,
|
| 1426 |
+
"eval_accuracy": 0.823956984964652,
|
| 1427 |
+
"eval_f1": 0.8267006469319741,
|
| 1428 |
+
"eval_loss": 0.34493395686149597,
|
| 1429 |
+
"eval_precision": 0.8284872298624755,
|
| 1430 |
+
"eval_recall": 0.8249217527386542,
|
| 1431 |
+
"eval_runtime": 48.4584,
|
| 1432 |
+
"eval_samples_per_second": 207.25,
|
| 1433 |
+
"eval_steps_per_second": 12.96,
|
| 1434 |
+
"step": 75000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 13.453708620994867,
|
| 1438 |
+
"grad_norm": 52.21194839477539,
|
| 1439 |
+
"learning_rate": 7.273657087783481e-07,
|
| 1440 |
+
"loss": 0.2558,
|
| 1441 |
+
"step": 76000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 13.453708620994867,
|
| 1445 |
+
"eval_accuracy": 0.8287364333366524,
|
| 1446 |
+
"eval_f1": 0.833106928003105,
|
| 1447 |
+
"eval_loss": 0.35551726818084717,
|
| 1448 |
+
"eval_precision": 0.826530612244898,
|
| 1449 |
+
"eval_recall": 0.8397887323943662,
|
| 1450 |
+
"eval_runtime": 48.5138,
|
| 1451 |
+
"eval_samples_per_second": 207.013,
|
| 1452 |
+
"eval_steps_per_second": 12.945,
|
| 1453 |
+
"step": 76000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 13.630731102850062,
|
| 1457 |
+
"grad_norm": 8.401360511779785,
|
| 1458 |
+
"learning_rate": 7.076965441277709e-07,
|
| 1459 |
+
"loss": 0.2534,
|
| 1460 |
+
"step": 77000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 13.630731102850062,
|
| 1464 |
+
"eval_accuracy": 0.8238574131235686,
|
| 1465 |
+
"eval_f1": 0.8269249584189414,
|
| 1466 |
+
"eval_loss": 0.3419524133205414,
|
| 1467 |
+
"eval_precision": 0.8271677431982776,
|
| 1468 |
+
"eval_recall": 0.8266823161189358,
|
| 1469 |
+
"eval_runtime": 48.4633,
|
| 1470 |
+
"eval_samples_per_second": 207.229,
|
| 1471 |
+
"eval_steps_per_second": 12.958,
|
| 1472 |
+
"step": 77000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 13.807753584705258,
|
| 1476 |
+
"grad_norm": 19.153236389160156,
|
| 1477 |
+
"learning_rate": 6.880273794771936e-07,
|
| 1478 |
+
"loss": 0.2574,
|
| 1479 |
+
"step": 78000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 13.807753584705258,
|
| 1483 |
+
"eval_accuracy": 0.8307278701583193,
|
| 1484 |
+
"eval_f1": 0.8393194706994329,
|
| 1485 |
+
"eval_loss": 0.3600776791572571,
|
| 1486 |
+
"eval_precision": 0.8119970738844184,
|
| 1487 |
+
"eval_recall": 0.8685446009389671,
|
| 1488 |
+
"eval_runtime": 48.5086,
|
| 1489 |
+
"eval_samples_per_second": 207.035,
|
| 1490 |
+
"eval_steps_per_second": 12.946,
|
| 1491 |
+
"step": 78000
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 13.984776066560453,
|
| 1495 |
+
"grad_norm": 5.686819553375244,
|
| 1496 |
+
"learning_rate": 6.683582148266162e-07,
|
| 1497 |
+
"loss": 0.2605,
|
| 1498 |
+
"step": 79000
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 13.984776066560453,
|
| 1502 |
+
"eval_accuracy": 0.8274419994025689,
|
| 1503 |
+
"eval_f1": 0.8354382299876555,
|
| 1504 |
+
"eval_loss": 0.34466180205345154,
|
| 1505 |
+
"eval_precision": 0.8117733899243403,
|
| 1506 |
+
"eval_recall": 0.8605242566510172,
|
| 1507 |
+
"eval_runtime": 48.4951,
|
| 1508 |
+
"eval_samples_per_second": 207.093,
|
| 1509 |
+
"eval_steps_per_second": 12.95,
|
| 1510 |
+
"step": 79000
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 14.161798548415648,
|
| 1514 |
+
"grad_norm": 28.316547393798828,
|
| 1515 |
+
"learning_rate": 6.486890501760391e-07,
|
| 1516 |
+
"loss": 0.253,
|
| 1517 |
+
"step": 80000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 14.161798548415648,
|
| 1521 |
+
"eval_accuracy": 0.8313253012048193,
|
| 1522 |
+
"eval_f1": 0.8302605210420841,
|
| 1523 |
+
"eval_loss": 0.3548405170440674,
|
| 1524 |
+
"eval_precision": 0.8510682004930156,
|
| 1525 |
+
"eval_recall": 0.8104460093896714,
|
| 1526 |
+
"eval_runtime": 48.5444,
|
| 1527 |
+
"eval_samples_per_second": 206.883,
|
| 1528 |
+
"eval_steps_per_second": 12.937,
|
| 1529 |
+
"step": 80000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 14.338821030270845,
|
| 1533 |
+
"grad_norm": 16.459693908691406,
|
| 1534 |
+
"learning_rate": 6.290198855254617e-07,
|
| 1535 |
+
"loss": 0.2522,
|
| 1536 |
+
"step": 81000
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 14.338821030270845,
|
| 1540 |
+
"eval_accuracy": 0.8271432838793189,
|
| 1541 |
+
"eval_f1": 0.8302698474775128,
|
| 1542 |
+
"eval_loss": 0.3594595193862915,
|
| 1543 |
+
"eval_precision": 0.8299452697419859,
|
| 1544 |
+
"eval_recall": 0.8305946791862285,
|
| 1545 |
+
"eval_runtime": 48.5687,
|
| 1546 |
+
"eval_samples_per_second": 206.779,
|
| 1547 |
+
"eval_steps_per_second": 12.93,
|
| 1548 |
+
"step": 81000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 14.51584351212604,
|
| 1552 |
+
"grad_norm": 54.176578521728516,
|
| 1553 |
+
"learning_rate": 6.093507208748843e-07,
|
| 1554 |
+
"loss": 0.2418,
|
| 1555 |
+
"step": 82000
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 14.51584351212604,
|
| 1559 |
+
"eval_accuracy": 0.8300308672707358,
|
| 1560 |
+
"eval_f1": 0.8312407315867524,
|
| 1561 |
+
"eval_loss": 0.3571302890777588,
|
| 1562 |
+
"eval_precision": 0.8402958225064961,
|
| 1563 |
+
"eval_recall": 0.8223787167449139,
|
| 1564 |
+
"eval_runtime": 48.4796,
|
| 1565 |
+
"eval_samples_per_second": 207.159,
|
| 1566 |
+
"eval_steps_per_second": 12.954,
|
| 1567 |
+
"step": 82000
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 14.692865993981236,
|
| 1571 |
+
"grad_norm": 18.803722381591797,
|
| 1572 |
+
"learning_rate": 5.896815562243072e-07,
|
| 1573 |
+
"loss": 0.2543,
|
| 1574 |
+
"step": 83000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 14.692865993981236,
|
| 1578 |
+
"eval_accuracy": 0.8324205914567361,
|
| 1579 |
+
"eval_f1": 0.8432523051131601,
|
| 1580 |
+
"eval_loss": 0.36417821049690247,
|
| 1581 |
+
"eval_precision": 0.8048,
|
| 1582 |
+
"eval_recall": 0.8855633802816901,
|
| 1583 |
+
"eval_runtime": 48.459,
|
| 1584 |
+
"eval_samples_per_second": 207.247,
|
| 1585 |
+
"eval_steps_per_second": 12.959,
|
| 1586 |
+
"step": 83000
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 14.869888475836431,
|
| 1590 |
+
"grad_norm": 6.331387996673584,
|
| 1591 |
+
"learning_rate": 5.700123915737298e-07,
|
| 1592 |
+
"loss": 0.2483,
|
| 1593 |
+
"step": 84000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 14.869888475836431,
|
| 1597 |
+
"eval_accuracy": 0.828636861495569,
|
| 1598 |
+
"eval_f1": 0.83049345021176,
|
| 1599 |
+
"eval_loss": 0.3517729938030243,
|
| 1600 |
+
"eval_precision": 0.8363419956357866,
|
| 1601 |
+
"eval_recall": 0.8247261345852895,
|
| 1602 |
+
"eval_runtime": 48.6656,
|
| 1603 |
+
"eval_samples_per_second": 206.368,
|
| 1604 |
+
"eval_steps_per_second": 12.904,
|
| 1605 |
+
"step": 84000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 15.046910957691626,
|
| 1609 |
+
"grad_norm": 63.694122314453125,
|
| 1610 |
+
"learning_rate": 5.503432269231526e-07,
|
| 1611 |
+
"loss": 0.2489,
|
| 1612 |
+
"step": 85000
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 15.046910957691626,
|
| 1616 |
+
"eval_accuracy": 0.8317235885691526,
|
| 1617 |
+
"eval_f1": 0.8441247002398081,
|
| 1618 |
+
"eval_loss": 0.35860148072242737,
|
| 1619 |
+
"eval_precision": 0.7986038394415358,
|
| 1620 |
+
"eval_recall": 0.8951486697965572,
|
| 1621 |
+
"eval_runtime": 48.5388,
|
| 1622 |
+
"eval_samples_per_second": 206.907,
|
| 1623 |
+
"eval_steps_per_second": 12.938,
|
| 1624 |
+
"step": 85000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 15.223933439546823,
|
| 1628 |
+
"grad_norm": 18.07522201538086,
|
| 1629 |
+
"learning_rate": 5.306740622725753e-07,
|
| 1630 |
+
"loss": 0.2439,
|
| 1631 |
+
"step": 86000
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 15.223933439546823,
|
| 1635 |
+
"eval_accuracy": 0.8292342925420692,
|
| 1636 |
+
"eval_f1": 0.8383143207315924,
|
| 1637 |
+
"eval_loss": 0.3605121970176697,
|
| 1638 |
+
"eval_precision": 0.8090991810737034,
|
| 1639 |
+
"eval_recall": 0.8697183098591549,
|
| 1640 |
+
"eval_runtime": 48.5578,
|
| 1641 |
+
"eval_samples_per_second": 206.826,
|
| 1642 |
+
"eval_steps_per_second": 12.933,
|
| 1643 |
+
"step": 86000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 15.400955921402018,
|
| 1647 |
+
"grad_norm": 6.01281213760376,
|
| 1648 |
+
"learning_rate": 5.110048976219979e-07,
|
| 1649 |
+
"loss": 0.2463,
|
| 1650 |
+
"step": 87000
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 15.400955921402018,
|
| 1654 |
+
"eval_accuracy": 0.8317235885691526,
|
| 1655 |
+
"eval_f1": 0.8435764531654942,
|
| 1656 |
+
"eval_loss": 0.3613792955875397,
|
| 1657 |
+
"eval_precision": 0.800597329585383,
|
| 1658 |
+
"eval_recall": 0.8914319248826291,
|
| 1659 |
+
"eval_runtime": 48.4585,
|
| 1660 |
+
"eval_samples_per_second": 207.25,
|
| 1661 |
+
"eval_steps_per_second": 12.96,
|
| 1662 |
+
"step": 87000
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 15.577978403257214,
|
| 1666 |
+
"grad_norm": 4.72086763381958,
|
| 1667 |
+
"learning_rate": 4.913357329714207e-07,
|
| 1668 |
+
"loss": 0.2421,
|
| 1669 |
+
"step": 88000
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 15.577978403257214,
|
| 1673 |
+
"eval_accuracy": 0.8301304391118192,
|
| 1674 |
+
"eval_f1": 0.8313896026882783,
|
| 1675 |
+
"eval_loss": 0.3474978506565094,
|
| 1676 |
+
"eval_precision": 0.8401917698761486,
|
| 1677 |
+
"eval_recall": 0.8227699530516432,
|
| 1678 |
+
"eval_runtime": 48.4981,
|
| 1679 |
+
"eval_samples_per_second": 207.08,
|
| 1680 |
+
"eval_steps_per_second": 12.949,
|
| 1681 |
+
"step": 88000
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 15.755000885112409,
|
| 1685 |
+
"grad_norm": 7.4664530754089355,
|
| 1686 |
+
"learning_rate": 4.716665683208434e-07,
|
| 1687 |
+
"loss": 0.2449,
|
| 1688 |
+
"step": 89000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 15.755000885112409,
|
| 1692 |
+
"eval_accuracy": 0.8310265856815693,
|
| 1693 |
+
"eval_f1": 0.8286723876829883,
|
| 1694 |
+
"eval_loss": 0.35074958205223083,
|
| 1695 |
+
"eval_precision": 0.856248696015022,
|
| 1696 |
+
"eval_recall": 0.8028169014084507,
|
| 1697 |
+
"eval_runtime": 48.4074,
|
| 1698 |
+
"eval_samples_per_second": 207.468,
|
| 1699 |
+
"eval_steps_per_second": 12.973,
|
| 1700 |
+
"step": 89000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 15.932023366967606,
|
| 1704 |
+
"grad_norm": 18.542203903198242,
|
| 1705 |
+
"learning_rate": 4.5199740367026614e-07,
|
| 1706 |
+
"loss": 0.242,
|
| 1707 |
+
"step": 90000
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 15.932023366967606,
|
| 1711 |
+
"eval_accuracy": 0.8300308672707358,
|
| 1712 |
+
"eval_f1": 0.8335121427874769,
|
| 1713 |
+
"eval_loss": 0.34495285153388977,
|
| 1714 |
+
"eval_precision": 0.831161252674577,
|
| 1715 |
+
"eval_recall": 0.8358763693270735,
|
| 1716 |
+
"eval_runtime": 48.5317,
|
| 1717 |
+
"eval_samples_per_second": 206.937,
|
| 1718 |
+
"eval_steps_per_second": 12.94,
|
| 1719 |
+
"step": 90000
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 16.1090458488228,
|
| 1723 |
+
"grad_norm": 53.64085006713867,
|
| 1724 |
+
"learning_rate": 4.323282390196888e-07,
|
| 1725 |
+
"loss": 0.2477,
|
| 1726 |
+
"step": 91000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 16.1090458488228,
|
| 1730 |
+
"eval_accuracy": 0.8307278701583193,
|
| 1731 |
+
"eval_f1": 0.8348552554886342,
|
| 1732 |
+
"eval_loss": 0.3650229275226593,
|
| 1733 |
+
"eval_precision": 0.8292165187186414,
|
| 1734 |
+
"eval_recall": 0.8405712050078247,
|
| 1735 |
+
"eval_runtime": 48.4566,
|
| 1736 |
+
"eval_samples_per_second": 207.257,
|
| 1737 |
+
"eval_steps_per_second": 12.96,
|
| 1738 |
+
"step": 91000
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 16.286068330677995,
|
| 1742 |
+
"grad_norm": 10.626422882080078,
|
| 1743 |
+
"learning_rate": 4.126590743691115e-07,
|
| 1744 |
+
"loss": 0.2388,
|
| 1745 |
+
"step": 92000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 16.286068330677995,
|
| 1749 |
+
"eval_accuracy": 0.8311261575226526,
|
| 1750 |
+
"eval_f1": 0.8387526145655068,
|
| 1751 |
+
"eval_loss": 0.35832735896110535,
|
| 1752 |
+
"eval_precision": 0.8159452460229375,
|
| 1753 |
+
"eval_recall": 0.8628716744913928,
|
| 1754 |
+
"eval_runtime": 48.551,
|
| 1755 |
+
"eval_samples_per_second": 206.855,
|
| 1756 |
+
"eval_steps_per_second": 12.935,
|
| 1757 |
+
"step": 92000
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 16.463090812533192,
|
| 1761 |
+
"grad_norm": 23.993255615234375,
|
| 1762 |
+
"learning_rate": 3.9298990971853425e-07,
|
| 1763 |
+
"loss": 0.2469,
|
| 1764 |
+
"step": 93000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 16.463090812533192,
|
| 1768 |
+
"eval_accuracy": 0.8298317235885692,
|
| 1769 |
+
"eval_f1": 0.8339648304673078,
|
| 1770 |
+
"eval_loss": 0.3484230637550354,
|
| 1771 |
+
"eval_precision": 0.8284115035707392,
|
| 1772 |
+
"eval_recall": 0.8395931142410016,
|
| 1773 |
+
"eval_runtime": 48.4135,
|
| 1774 |
+
"eval_samples_per_second": 207.442,
|
| 1775 |
+
"eval_steps_per_second": 12.972,
|
| 1776 |
+
"step": 93000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 16.64011329438839,
|
| 1780 |
+
"grad_norm": 3.7660863399505615,
|
| 1781 |
+
"learning_rate": 3.73320745067957e-07,
|
| 1782 |
+
"loss": 0.235,
|
| 1783 |
+
"step": 94000
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 16.64011329438839,
|
| 1787 |
+
"eval_accuracy": 0.8298317235885692,
|
| 1788 |
+
"eval_f1": 0.8365375418460067,
|
| 1789 |
+
"eval_loss": 0.3643123507499695,
|
| 1790 |
+
"eval_precision": 0.8184540520306943,
|
| 1791 |
+
"eval_recall": 0.8554381846635368,
|
| 1792 |
+
"eval_runtime": 48.5272,
|
| 1793 |
+
"eval_samples_per_second": 206.956,
|
| 1794 |
+
"eval_steps_per_second": 12.941,
|
| 1795 |
+
"step": 94000
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 16.817135776243582,
|
| 1799 |
+
"grad_norm": 17.013097763061523,
|
| 1800 |
+
"learning_rate": 3.536515804173796e-07,
|
| 1801 |
+
"loss": 0.2336,
|
| 1802 |
+
"step": 95000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 16.817135776243582,
|
| 1806 |
+
"eval_accuracy": 0.827740714925819,
|
| 1807 |
+
"eval_f1": 0.8336858296481446,
|
| 1808 |
+
"eval_loss": 0.34748417139053345,
|
| 1809 |
+
"eval_precision": 0.8196597353497165,
|
| 1810 |
+
"eval_recall": 0.8482003129890454,
|
| 1811 |
+
"eval_runtime": 48.3887,
|
| 1812 |
+
"eval_samples_per_second": 207.548,
|
| 1813 |
+
"eval_steps_per_second": 12.978,
|
| 1814 |
+
"step": 95000
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 16.99415825809878,
|
| 1818 |
+
"grad_norm": 17.022958755493164,
|
| 1819 |
+
"learning_rate": 3.3398241576680236e-07,
|
| 1820 |
+
"loss": 0.2455,
|
| 1821 |
+
"step": 96000
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 16.99415825809878,
|
| 1825 |
+
"eval_accuracy": 0.8288360051777357,
|
| 1826 |
+
"eval_f1": 0.8308903098868667,
|
| 1827 |
+
"eval_loss": 0.348213791847229,
|
| 1828 |
+
"eval_precision": 0.8357411438749258,
|
| 1829 |
+
"eval_recall": 0.826095461658842,
|
| 1830 |
+
"eval_runtime": 48.5355,
|
| 1831 |
+
"eval_samples_per_second": 206.921,
|
| 1832 |
+
"eval_steps_per_second": 12.939,
|
| 1833 |
+
"step": 96000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 17.171180739953975,
|
| 1837 |
+
"grad_norm": 6.458636283874512,
|
| 1838 |
+
"learning_rate": 3.143132511162251e-07,
|
| 1839 |
+
"loss": 0.2372,
|
| 1840 |
+
"step": 97000
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 17.171180739953975,
|
| 1844 |
+
"eval_accuracy": 0.836503036941153,
|
| 1845 |
+
"eval_f1": 0.8473693995166388,
|
| 1846 |
+
"eval_loss": 0.35692235827445984,
|
| 1847 |
+
"eval_precision": 0.8072972015586256,
|
| 1848 |
+
"eval_recall": 0.8916275430359938,
|
| 1849 |
+
"eval_runtime": 48.4702,
|
| 1850 |
+
"eval_samples_per_second": 207.2,
|
| 1851 |
+
"eval_steps_per_second": 12.956,
|
| 1852 |
+
"step": 97000
|
| 1853 |
+
}
|
| 1854 |
+
],
|
| 1855 |
+
"logging_steps": 1000,
|
| 1856 |
+
"max_steps": 112980,
|
| 1857 |
+
"num_input_tokens_seen": 0,
|
| 1858 |
+
"num_train_epochs": 20,
|
| 1859 |
+
"save_steps": 1000,
|
| 1860 |
+
"stateful_callbacks": {
|
| 1861 |
+
"TrainerControl": {
|
| 1862 |
+
"args": {
|
| 1863 |
+
"should_epoch_stop": false,
|
| 1864 |
+
"should_evaluate": false,
|
| 1865 |
+
"should_log": false,
|
| 1866 |
+
"should_save": true,
|
| 1867 |
+
"should_training_stop": false
|
| 1868 |
+
},
|
| 1869 |
+
"attributes": {}
|
| 1870 |
+
}
|
| 1871 |
+
},
|
| 1872 |
+
"total_flos": 2.9198903946321024e+17,
|
| 1873 |
+
"train_batch_size": 16,
|
| 1874 |
+
"trial_name": null,
|
| 1875 |
+
"trial_params": null
|
| 1876 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf2b49e3228c475421d9f49d1e7ed6127d54e8d7b757a9b4f7f63e1106e08a22
|
| 3 |
+
size 5048
|