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 +1097 -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 sha256:4d9faf24c87d094660f4613da1f474e63ab28b21d8c00f0dd8abc75c78efe6e1
|
| 3 |
+
size 3114003416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f41ffe6505613aaa073412d4848db1511f4de89c58725d2f5a604338c0999895
|
| 3 |
+
size 6228131858
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc3350e09e33243d3adef6227e03425b69ee6073021fab84a5e1a825863f9273
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6537f366327295128a7a0b9d2d2eae80aa1755e0729fd0c3748d6aecfb1933fb
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1097 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8164585392148055,
|
| 3 |
+
"best_model_checkpoint": "./XLM-V-multi-outputs/checkpoint-40000",
|
| 4 |
+
"epoch": 19.82300884955752,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 56000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.35398230088495575,
|
| 13 |
+
"grad_norm": 1.4846587181091309,
|
| 14 |
+
"learning_rate": 3.5398230088495575e-07,
|
| 15 |
+
"loss": 0.6947,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.35398230088495575,
|
| 20 |
+
"eval_accuracy": 0.5090112516180424,
|
| 21 |
+
"eval_f1": 0.6746288353678654,
|
| 22 |
+
"eval_loss": 0.6931052207946777,
|
| 23 |
+
"eval_precision": 0.5090112516180424,
|
| 24 |
+
"eval_recall": 1.0,
|
| 25 |
+
"eval_runtime": 53.8213,
|
| 26 |
+
"eval_samples_per_second": 186.599,
|
| 27 |
+
"eval_steps_per_second": 5.834,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.7079646017699115,
|
| 32 |
+
"grad_norm": 3.2122230529785156,
|
| 33 |
+
"learning_rate": 7.079646017699115e-07,
|
| 34 |
+
"loss": 0.6924,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.7079646017699115,
|
| 39 |
+
"eval_accuracy": 0.5752265259384646,
|
| 40 |
+
"eval_f1": 0.698601102161933,
|
| 41 |
+
"eval_loss": 0.681232213973999,
|
| 42 |
+
"eval_precision": 0.5467816854678168,
|
| 43 |
+
"eval_recall": 0.9671361502347418,
|
| 44 |
+
"eval_runtime": 53.8929,
|
| 45 |
+
"eval_samples_per_second": 186.351,
|
| 46 |
+
"eval_steps_per_second": 5.826,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.0619469026548674,
|
| 51 |
+
"grad_norm": 4.78421688079834,
|
| 52 |
+
"learning_rate": 1.0619469026548673e-06,
|
| 53 |
+
"loss": 0.6783,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.0619469026548674,
|
| 58 |
+
"eval_accuracy": 0.6099770984765508,
|
| 59 |
+
"eval_f1": 0.7189092213850018,
|
| 60 |
+
"eval_loss": 0.6526923179626465,
|
| 61 |
+
"eval_precision": 0.5677207299104613,
|
| 62 |
+
"eval_recall": 0.9798513302034428,
|
| 63 |
+
"eval_runtime": 53.7592,
|
| 64 |
+
"eval_samples_per_second": 186.814,
|
| 65 |
+
"eval_steps_per_second": 5.841,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.415929203539823,
|
| 70 |
+
"grad_norm": 49.178401947021484,
|
| 71 |
+
"learning_rate": 1.415929203539823e-06,
|
| 72 |
+
"loss": 0.6613,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.415929203539823,
|
| 77 |
+
"eval_accuracy": 0.6256098775266354,
|
| 78 |
+
"eval_f1": 0.7167821633021995,
|
| 79 |
+
"eval_loss": 0.633762538433075,
|
| 80 |
+
"eval_precision": 0.5828025477707006,
|
| 81 |
+
"eval_recall": 0.9307511737089202,
|
| 82 |
+
"eval_runtime": 53.5833,
|
| 83 |
+
"eval_samples_per_second": 187.428,
|
| 84 |
+
"eval_steps_per_second": 5.86,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.7699115044247788,
|
| 89 |
+
"grad_norm": 11.674603462219238,
|
| 90 |
+
"learning_rate": 1.7699115044247788e-06,
|
| 91 |
+
"loss": 0.6551,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.7699115044247788,
|
| 96 |
+
"eval_accuracy": 0.6342726277008862,
|
| 97 |
+
"eval_f1": 0.7293493478741434,
|
| 98 |
+
"eval_loss": 0.6212999820709229,
|
| 99 |
+
"eval_precision": 0.5850573353824329,
|
| 100 |
+
"eval_recall": 0.968114241001565,
|
| 101 |
+
"eval_runtime": 53.825,
|
| 102 |
+
"eval_samples_per_second": 186.586,
|
| 103 |
+
"eval_steps_per_second": 5.834,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.1238938053097347,
|
| 108 |
+
"grad_norm": 5.5286545753479,
|
| 109 |
+
"learning_rate": 1.986234021632252e-06,
|
| 110 |
+
"loss": 0.6481,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.1238938053097347,
|
| 115 |
+
"eval_accuracy": 0.656078860898138,
|
| 116 |
+
"eval_f1": 0.740222623345367,
|
| 117 |
+
"eval_loss": 0.6046485900878906,
|
| 118 |
+
"eval_precision": 0.6012952101661779,
|
| 119 |
+
"eval_recall": 0.9626369327073553,
|
| 120 |
+
"eval_runtime": 53.8663,
|
| 121 |
+
"eval_samples_per_second": 186.443,
|
| 122 |
+
"eval_steps_per_second": 5.829,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.47787610619469,
|
| 127 |
+
"grad_norm": 47.20358657836914,
|
| 128 |
+
"learning_rate": 1.9469026548672563e-06,
|
| 129 |
+
"loss": 0.639,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.47787610619469,
|
| 134 |
+
"eval_accuracy": 0.6773872348899731,
|
| 135 |
+
"eval_f1": 0.7519142419601837,
|
| 136 |
+
"eval_loss": 0.5804159045219421,
|
| 137 |
+
"eval_precision": 0.6177654755913438,
|
| 138 |
+
"eval_recall": 0.9604851330203443,
|
| 139 |
+
"eval_runtime": 53.8098,
|
| 140 |
+
"eval_samples_per_second": 186.639,
|
| 141 |
+
"eval_steps_per_second": 5.835,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.831858407079646,
|
| 146 |
+
"grad_norm": 20.222881317138672,
|
| 147 |
+
"learning_rate": 1.9075712881022612e-06,
|
| 148 |
+
"loss": 0.63,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.831858407079646,
|
| 153 |
+
"eval_accuracy": 0.6816688240565568,
|
| 154 |
+
"eval_f1": 0.6923299008757579,
|
| 155 |
+
"eval_loss": 0.584140419960022,
|
| 156 |
+
"eval_precision": 0.6813790490623224,
|
| 157 |
+
"eval_recall": 0.7036384976525821,
|
| 158 |
+
"eval_runtime": 53.9333,
|
| 159 |
+
"eval_samples_per_second": 186.211,
|
| 160 |
+
"eval_steps_per_second": 5.822,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.185840707964602,
|
| 165 |
+
"grad_norm": 8.778471946716309,
|
| 166 |
+
"learning_rate": 1.8682399213372663e-06,
|
| 167 |
+
"loss": 0.6087,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.185840707964602,
|
| 172 |
+
"eval_accuracy": 0.7025789106840585,
|
| 173 |
+
"eval_f1": 0.747271342753194,
|
| 174 |
+
"eval_loss": 0.5566529035568237,
|
| 175 |
+
"eval_precision": 0.6584165796928582,
|
| 176 |
+
"eval_recall": 0.863849765258216,
|
| 177 |
+
"eval_runtime": 53.826,
|
| 178 |
+
"eval_samples_per_second": 186.583,
|
| 179 |
+
"eval_steps_per_second": 5.834,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.5398230088495577,
|
| 184 |
+
"grad_norm": 16.00111198425293,
|
| 185 |
+
"learning_rate": 1.8289085545722714e-06,
|
| 186 |
+
"loss": 0.5851,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.5398230088495577,
|
| 191 |
+
"eval_accuracy": 0.708553221149059,
|
| 192 |
+
"eval_f1": 0.7571155920670484,
|
| 193 |
+
"eval_loss": 0.5440040826797485,
|
| 194 |
+
"eval_precision": 0.6574434356535523,
|
| 195 |
+
"eval_recall": 0.8924100156494522,
|
| 196 |
+
"eval_runtime": 53.8534,
|
| 197 |
+
"eval_samples_per_second": 186.488,
|
| 198 |
+
"eval_steps_per_second": 5.831,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.893805309734513,
|
| 203 |
+
"grad_norm": 4.33933162689209,
|
| 204 |
+
"learning_rate": 1.7895771878072763e-06,
|
| 205 |
+
"loss": 0.5516,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.893805309734513,
|
| 210 |
+
"eval_accuracy": 0.7223937070596436,
|
| 211 |
+
"eval_f1": 0.7767456758488148,
|
| 212 |
+
"eval_loss": 0.4870859384536743,
|
| 213 |
+
"eval_precision": 0.6575379609544468,
|
| 214 |
+
"eval_recall": 0.9487480438184663,
|
| 215 |
+
"eval_runtime": 53.9228,
|
| 216 |
+
"eval_samples_per_second": 186.248,
|
| 217 |
+
"eval_steps_per_second": 5.823,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.247787610619469,
|
| 222 |
+
"grad_norm": 13.392922401428223,
|
| 223 |
+
"learning_rate": 1.7502458210422812e-06,
|
| 224 |
+
"loss": 0.495,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.247787610619469,
|
| 229 |
+
"eval_accuracy": 0.7339440406253112,
|
| 230 |
+
"eval_f1": 0.7293903180068868,
|
| 231 |
+
"eval_loss": 0.43779730796813965,
|
| 232 |
+
"eval_precision": 0.7561948761024779,
|
| 233 |
+
"eval_recall": 0.7044209702660407,
|
| 234 |
+
"eval_runtime": 53.9151,
|
| 235 |
+
"eval_samples_per_second": 186.274,
|
| 236 |
+
"eval_steps_per_second": 5.824,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.601769911504425,
|
| 241 |
+
"grad_norm": 6.77086067199707,
|
| 242 |
+
"learning_rate": 1.7109144542772859e-06,
|
| 243 |
+
"loss": 0.4655,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.601769911504425,
|
| 248 |
+
"eval_accuracy": 0.7499751070397291,
|
| 249 |
+
"eval_f1": 0.7768991559306975,
|
| 250 |
+
"eval_loss": 0.41514188051223755,
|
| 251 |
+
"eval_precision": 0.7117043789679309,
|
| 252 |
+
"eval_recall": 0.8552425665101722,
|
| 253 |
+
"eval_runtime": 53.8935,
|
| 254 |
+
"eval_samples_per_second": 186.349,
|
| 255 |
+
"eval_steps_per_second": 5.826,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.95575221238938,
|
| 260 |
+
"grad_norm": 6.903416156768799,
|
| 261 |
+
"learning_rate": 1.671583087512291e-06,
|
| 262 |
+
"loss": 0.4451,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.95575221238938,
|
| 267 |
+
"eval_accuracy": 0.7510703972916459,
|
| 268 |
+
"eval_f1": 0.7728511720879521,
|
| 269 |
+
"eval_loss": 0.4052245318889618,
|
| 270 |
+
"eval_precision": 0.7215812690872073,
|
| 271 |
+
"eval_recall": 0.831964006259781,
|
| 272 |
+
"eval_runtime": 53.8879,
|
| 273 |
+
"eval_samples_per_second": 186.368,
|
| 274 |
+
"eval_steps_per_second": 5.827,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.3097345132743365,
|
| 279 |
+
"grad_norm": 24.238162994384766,
|
| 280 |
+
"learning_rate": 1.6322517207472959e-06,
|
| 281 |
+
"loss": 0.4275,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.3097345132743365,
|
| 286 |
+
"eval_accuracy": 0.7568455640744798,
|
| 287 |
+
"eval_f1": 0.7681792291627112,
|
| 288 |
+
"eval_loss": 0.3967246115207672,
|
| 289 |
+
"eval_precision": 0.7462191073404648,
|
| 290 |
+
"eval_recall": 0.7914710485133021,
|
| 291 |
+
"eval_runtime": 53.89,
|
| 292 |
+
"eval_samples_per_second": 186.361,
|
| 293 |
+
"eval_steps_per_second": 5.827,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.663716814159292,
|
| 298 |
+
"grad_norm": 22.419418334960938,
|
| 299 |
+
"learning_rate": 1.5929203539823008e-06,
|
| 300 |
+
"loss": 0.4085,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.663716814159292,
|
| 305 |
+
"eval_accuracy": 0.7561485611868963,
|
| 306 |
+
"eval_f1": 0.7775456444727041,
|
| 307 |
+
"eval_loss": 0.39186546206474304,
|
| 308 |
+
"eval_precision": 0.7257927759877904,
|
| 309 |
+
"eval_recall": 0.837245696400626,
|
| 310 |
+
"eval_runtime": 54.0231,
|
| 311 |
+
"eval_samples_per_second": 185.902,
|
| 312 |
+
"eval_steps_per_second": 5.812,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 6.017699115044247,
|
| 317 |
+
"grad_norm": 25.710134506225586,
|
| 318 |
+
"learning_rate": 1.5535889872173059e-06,
|
| 319 |
+
"loss": 0.4088,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.017699115044247,
|
| 324 |
+
"eval_accuracy": 0.7595340037837299,
|
| 325 |
+
"eval_f1": 0.7705027083531313,
|
| 326 |
+
"eval_loss": 0.3929796516895294,
|
| 327 |
+
"eval_precision": 0.7492145629273702,
|
| 328 |
+
"eval_recall": 0.793035993740219,
|
| 329 |
+
"eval_runtime": 53.8892,
|
| 330 |
+
"eval_samples_per_second": 186.364,
|
| 331 |
+
"eval_steps_per_second": 5.827,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.371681415929204,
|
| 336 |
+
"grad_norm": 12.00070571899414,
|
| 337 |
+
"learning_rate": 1.5142576204523108e-06,
|
| 338 |
+
"loss": 0.3982,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.371681415929204,
|
| 343 |
+
"eval_accuracy": 0.756347704869063,
|
| 344 |
+
"eval_f1": 0.7932753231393089,
|
| 345 |
+
"eval_loss": 0.38643109798431396,
|
| 346 |
+
"eval_precision": 0.6981412639405205,
|
| 347 |
+
"eval_recall": 0.9184272300469484,
|
| 348 |
+
"eval_runtime": 53.924,
|
| 349 |
+
"eval_samples_per_second": 186.243,
|
| 350 |
+
"eval_steps_per_second": 5.823,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.725663716814159,
|
| 355 |
+
"grad_norm": 8.227592468261719,
|
| 356 |
+
"learning_rate": 1.4749262536873155e-06,
|
| 357 |
+
"loss": 0.3952,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.725663716814159,
|
| 362 |
+
"eval_accuracy": 0.7651100268843971,
|
| 363 |
+
"eval_f1": 0.776673293571902,
|
| 364 |
+
"eval_loss": 0.3926367461681366,
|
| 365 |
+
"eval_precision": 0.7525224729407448,
|
| 366 |
+
"eval_recall": 0.8024256651017214,
|
| 367 |
+
"eval_runtime": 53.9659,
|
| 368 |
+
"eval_samples_per_second": 186.099,
|
| 369 |
+
"eval_steps_per_second": 5.818,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 7.079646017699115,
|
| 374 |
+
"grad_norm": 5.537351131439209,
|
| 375 |
+
"learning_rate": 1.4355948869223204e-06,
|
| 376 |
+
"loss": 0.3876,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.079646017699115,
|
| 381 |
+
"eval_accuracy": 0.763915164791397,
|
| 382 |
+
"eval_f1": 0.792472647702407,
|
| 383 |
+
"eval_loss": 0.38483595848083496,
|
| 384 |
+
"eval_precision": 0.7170917155076826,
|
| 385 |
+
"eval_recall": 0.8855633802816901,
|
| 386 |
+
"eval_runtime": 53.9366,
|
| 387 |
+
"eval_samples_per_second": 186.2,
|
| 388 |
+
"eval_steps_per_second": 5.822,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.433628318584071,
|
| 393 |
+
"grad_norm": 4.749475002288818,
|
| 394 |
+
"learning_rate": 1.3962635201573255e-06,
|
| 395 |
+
"loss": 0.3832,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 7.433628318584071,
|
| 400 |
+
"eval_accuracy": 0.7616250124464802,
|
| 401 |
+
"eval_f1": 0.7432432432432432,
|
| 402 |
+
"eval_loss": 0.38059765100479126,
|
| 403 |
+
"eval_precision": 0.8226495726495726,
|
| 404 |
+
"eval_recall": 0.6778169014084507,
|
| 405 |
+
"eval_runtime": 53.9079,
|
| 406 |
+
"eval_samples_per_second": 186.299,
|
| 407 |
+
"eval_steps_per_second": 5.825,
|
| 408 |
+
"step": 21000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 7.787610619469026,
|
| 412 |
+
"grad_norm": 9.643062591552734,
|
| 413 |
+
"learning_rate": 1.3569321533923304e-06,
|
| 414 |
+
"loss": 0.3778,
|
| 415 |
+
"step": 22000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 7.787610619469026,
|
| 419 |
+
"eval_accuracy": 0.7705864781439808,
|
| 420 |
+
"eval_f1": 0.7876889052709178,
|
| 421 |
+
"eval_loss": 0.37772777676582336,
|
| 422 |
+
"eval_precision": 0.7445993031358885,
|
| 423 |
+
"eval_recall": 0.8360719874804382,
|
| 424 |
+
"eval_runtime": 53.9925,
|
| 425 |
+
"eval_samples_per_second": 186.007,
|
| 426 |
+
"eval_steps_per_second": 5.816,
|
| 427 |
+
"step": 22000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 8.141592920353983,
|
| 431 |
+
"grad_norm": 5.115036487579346,
|
| 432 |
+
"learning_rate": 1.3176007866273352e-06,
|
| 433 |
+
"loss": 0.3832,
|
| 434 |
+
"step": 23000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.141592920353983,
|
| 438 |
+
"eval_accuracy": 0.7656078860898138,
|
| 439 |
+
"eval_f1": 0.7999320074791773,
|
| 440 |
+
"eval_loss": 0.3883359134197235,
|
| 441 |
+
"eval_precision": 0.7072437631499849,
|
| 442 |
+
"eval_recall": 0.9205790297339593,
|
| 443 |
+
"eval_runtime": 53.8543,
|
| 444 |
+
"eval_samples_per_second": 186.485,
|
| 445 |
+
"eval_steps_per_second": 5.831,
|
| 446 |
+
"step": 23000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.495575221238939,
|
| 450 |
+
"grad_norm": 3.359361410140991,
|
| 451 |
+
"learning_rate": 1.2782694198623401e-06,
|
| 452 |
+
"loss": 0.3723,
|
| 453 |
+
"step": 24000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 8.495575221238939,
|
| 457 |
+
"eval_accuracy": 0.7721796276013143,
|
| 458 |
+
"eval_f1": 0.7823853909073616,
|
| 459 |
+
"eval_loss": 0.3792983293533325,
|
| 460 |
+
"eval_precision": 0.7613846723435764,
|
| 461 |
+
"eval_recall": 0.8045774647887324,
|
| 462 |
+
"eval_runtime": 53.9123,
|
| 463 |
+
"eval_samples_per_second": 186.284,
|
| 464 |
+
"eval_steps_per_second": 5.824,
|
| 465 |
+
"step": 24000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 8.849557522123893,
|
| 469 |
+
"grad_norm": 4.47456169128418,
|
| 470 |
+
"learning_rate": 1.238938053097345e-06,
|
| 471 |
+
"loss": 0.369,
|
| 472 |
+
"step": 25000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 8.849557522123893,
|
| 476 |
+
"eval_accuracy": 0.7759633575624814,
|
| 477 |
+
"eval_f1": 0.7839446898405992,
|
| 478 |
+
"eval_loss": 0.37068039178848267,
|
| 479 |
+
"eval_precision": 0.7698981516408903,
|
| 480 |
+
"eval_recall": 0.7985133020344288,
|
| 481 |
+
"eval_runtime": 53.9248,
|
| 482 |
+
"eval_samples_per_second": 186.241,
|
| 483 |
+
"eval_steps_per_second": 5.823,
|
| 484 |
+
"step": 25000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 9.20353982300885,
|
| 488 |
+
"grad_norm": 8.337353706359863,
|
| 489 |
+
"learning_rate": 1.19960668633235e-06,
|
| 490 |
+
"loss": 0.3683,
|
| 491 |
+
"step": 26000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.20353982300885,
|
| 495 |
+
"eval_accuracy": 0.7734740615353978,
|
| 496 |
+
"eval_f1": 0.7609540821687507,
|
| 497 |
+
"eval_loss": 0.3703781068325043,
|
| 498 |
+
"eval_precision": 0.8220204313280364,
|
| 499 |
+
"eval_recall": 0.7083333333333334,
|
| 500 |
+
"eval_runtime": 53.895,
|
| 501 |
+
"eval_samples_per_second": 186.344,
|
| 502 |
+
"eval_steps_per_second": 5.826,
|
| 503 |
+
"step": 26000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.557522123893806,
|
| 507 |
+
"grad_norm": 8.439238548278809,
|
| 508 |
+
"learning_rate": 1.1602753195673548e-06,
|
| 509 |
+
"loss": 0.362,
|
| 510 |
+
"step": 27000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 9.557522123893806,
|
| 514 |
+
"eval_accuracy": 0.7749676391516479,
|
| 515 |
+
"eval_f1": 0.793644996347699,
|
| 516 |
+
"eval_loss": 0.3685624301433563,
|
| 517 |
+
"eval_precision": 0.7441780821917808,
|
| 518 |
+
"eval_recall": 0.8501564945226917,
|
| 519 |
+
"eval_runtime": 53.8072,
|
| 520 |
+
"eval_samples_per_second": 186.648,
|
| 521 |
+
"eval_steps_per_second": 5.836,
|
| 522 |
+
"step": 27000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 9.91150442477876,
|
| 526 |
+
"grad_norm": 9.439690589904785,
|
| 527 |
+
"learning_rate": 1.12094395280236e-06,
|
| 528 |
+
"loss": 0.3566,
|
| 529 |
+
"step": 28000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 9.91150442477876,
|
| 533 |
+
"eval_accuracy": 0.7782535099073982,
|
| 534 |
+
"eval_f1": 0.7853080111828786,
|
| 535 |
+
"eval_loss": 0.3649461269378662,
|
| 536 |
+
"eval_precision": 0.7741874168409048,
|
| 537 |
+
"eval_recall": 0.7967527386541471,
|
| 538 |
+
"eval_runtime": 53.8844,
|
| 539 |
+
"eval_samples_per_second": 186.38,
|
| 540 |
+
"eval_steps_per_second": 5.827,
|
| 541 |
+
"step": 28000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 10.265486725663717,
|
| 545 |
+
"grad_norm": 9.049650192260742,
|
| 546 |
+
"learning_rate": 1.0816125860373648e-06,
|
| 547 |
+
"loss": 0.3554,
|
| 548 |
+
"step": 29000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 10.265486725663717,
|
| 552 |
+
"eval_accuracy": 0.7810415214577318,
|
| 553 |
+
"eval_f1": 0.7799899949974988,
|
| 554 |
+
"eval_loss": 0.3608804941177368,
|
| 555 |
+
"eval_precision": 0.7982797460577514,
|
| 556 |
+
"eval_recall": 0.7625195618153364,
|
| 557 |
+
"eval_runtime": 53.8179,
|
| 558 |
+
"eval_samples_per_second": 186.611,
|
| 559 |
+
"eval_steps_per_second": 5.834,
|
| 560 |
+
"step": 29000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.619469026548673,
|
| 564 |
+
"grad_norm": 5.94489860534668,
|
| 565 |
+
"learning_rate": 1.0422812192723695e-06,
|
| 566 |
+
"loss": 0.3486,
|
| 567 |
+
"step": 30000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 10.619469026548673,
|
| 571 |
+
"eval_accuracy": 0.7845265358956487,
|
| 572 |
+
"eval_f1": 0.7943747624477385,
|
| 573 |
+
"eval_loss": 0.3635348081588745,
|
| 574 |
+
"eval_precision": 0.7723577235772358,
|
| 575 |
+
"eval_recall": 0.8176838810641628,
|
| 576 |
+
"eval_runtime": 53.7295,
|
| 577 |
+
"eval_samples_per_second": 186.918,
|
| 578 |
+
"eval_steps_per_second": 5.844,
|
| 579 |
+
"step": 30000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 10.973451327433628,
|
| 583 |
+
"grad_norm": 22.234378814697266,
|
| 584 |
+
"learning_rate": 1.0029498525073746e-06,
|
| 585 |
+
"loss": 0.3506,
|
| 586 |
+
"step": 31000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 10.973451327433628,
|
| 590 |
+
"eval_accuracy": 0.7844269640545654,
|
| 591 |
+
"eval_f1": 0.7878075075958052,
|
| 592 |
+
"eval_loss": 0.3596493601799011,
|
| 593 |
+
"eval_precision": 0.7894323315655077,
|
| 594 |
+
"eval_recall": 0.786189358372457,
|
| 595 |
+
"eval_runtime": 53.8293,
|
| 596 |
+
"eval_samples_per_second": 186.571,
|
| 597 |
+
"eval_steps_per_second": 5.833,
|
| 598 |
+
"step": 31000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 11.327433628318584,
|
| 602 |
+
"grad_norm": 12.47771167755127,
|
| 603 |
+
"learning_rate": 9.636184857423795e-07,
|
| 604 |
+
"loss": 0.3441,
|
| 605 |
+
"step": 32000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 11.327433628318584,
|
| 609 |
+
"eval_accuracy": 0.7883102658568157,
|
| 610 |
+
"eval_f1": 0.785901309164149,
|
| 611 |
+
"eval_loss": 0.35861310362815857,
|
| 612 |
+
"eval_precision": 0.8098796180987962,
|
| 613 |
+
"eval_recall": 0.763302034428795,
|
| 614 |
+
"eval_runtime": 53.7987,
|
| 615 |
+
"eval_samples_per_second": 186.677,
|
| 616 |
+
"eval_steps_per_second": 5.837,
|
| 617 |
+
"step": 32000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 11.68141592920354,
|
| 621 |
+
"grad_norm": 13.281210899353027,
|
| 622 |
+
"learning_rate": 9.242871189773844e-07,
|
| 623 |
+
"loss": 0.3416,
|
| 624 |
+
"step": 33000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 11.68141592920354,
|
| 628 |
+
"eval_accuracy": 0.7906004182017325,
|
| 629 |
+
"eval_f1": 0.7919263876521223,
|
| 630 |
+
"eval_loss": 0.3558104336261749,
|
| 631 |
+
"eval_precision": 0.8012012012012012,
|
| 632 |
+
"eval_recall": 0.7828638497652582,
|
| 633 |
+
"eval_runtime": 53.8593,
|
| 634 |
+
"eval_samples_per_second": 186.467,
|
| 635 |
+
"eval_steps_per_second": 5.83,
|
| 636 |
+
"step": 33000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 12.035398230088495,
|
| 640 |
+
"grad_norm": 13.627979278564453,
|
| 641 |
+
"learning_rate": 8.849557522123894e-07,
|
| 642 |
+
"loss": 0.3419,
|
| 643 |
+
"step": 34000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 12.035398230088495,
|
| 647 |
+
"eval_accuracy": 0.7892064124265658,
|
| 648 |
+
"eval_f1": 0.8029781293624941,
|
| 649 |
+
"eval_loss": 0.35980644822120667,
|
| 650 |
+
"eval_precision": 0.7658441327889224,
|
| 651 |
+
"eval_recall": 0.8438967136150235,
|
| 652 |
+
"eval_runtime": 53.8953,
|
| 653 |
+
"eval_samples_per_second": 186.343,
|
| 654 |
+
"eval_steps_per_second": 5.826,
|
| 655 |
+
"step": 34000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 12.389380530973451,
|
| 659 |
+
"grad_norm": 23.55402374267578,
|
| 660 |
+
"learning_rate": 8.456243854473943e-07,
|
| 661 |
+
"loss": 0.3306,
|
| 662 |
+
"step": 35000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 12.389380530973451,
|
| 666 |
+
"eval_accuracy": 0.7884098376978991,
|
| 667 |
+
"eval_f1": 0.7980997624703088,
|
| 668 |
+
"eval_loss": 0.353899210691452,
|
| 669 |
+
"eval_precision": 0.775909846665435,
|
| 670 |
+
"eval_recall": 0.8215962441314554,
|
| 671 |
+
"eval_runtime": 53.8141,
|
| 672 |
+
"eval_samples_per_second": 186.624,
|
| 673 |
+
"eval_steps_per_second": 5.835,
|
| 674 |
+
"step": 35000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 12.743362831858407,
|
| 678 |
+
"grad_norm": 18.79817771911621,
|
| 679 |
+
"learning_rate": 8.062930186823992e-07,
|
| 680 |
+
"loss": 0.335,
|
| 681 |
+
"step": 36000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 12.743362831858407,
|
| 685 |
+
"eval_accuracy": 0.7951807228915663,
|
| 686 |
+
"eval_f1": 0.7915695612524065,
|
| 687 |
+
"eval_loss": 0.35350722074508667,
|
| 688 |
+
"eval_precision": 0.8211057389110784,
|
| 689 |
+
"eval_recall": 0.7640845070422535,
|
| 690 |
+
"eval_runtime": 53.8902,
|
| 691 |
+
"eval_samples_per_second": 186.36,
|
| 692 |
+
"eval_steps_per_second": 5.827,
|
| 693 |
+
"step": 36000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 13.097345132743364,
|
| 697 |
+
"grad_norm": 5.215780735015869,
|
| 698 |
+
"learning_rate": 7.669616519174042e-07,
|
| 699 |
+
"loss": 0.3286,
|
| 700 |
+
"step": 37000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 13.097345132743364,
|
| 704 |
+
"eval_accuracy": 0.7942845763218161,
|
| 705 |
+
"eval_f1": 0.8051678611844587,
|
| 706 |
+
"eval_loss": 0.35424739122390747,
|
| 707 |
+
"eval_precision": 0.7773124544792426,
|
| 708 |
+
"eval_recall": 0.835093896713615,
|
| 709 |
+
"eval_runtime": 53.8955,
|
| 710 |
+
"eval_samples_per_second": 186.342,
|
| 711 |
+
"eval_steps_per_second": 5.826,
|
| 712 |
+
"step": 37000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 13.451327433628318,
|
| 716 |
+
"grad_norm": 15.066843032836914,
|
| 717 |
+
"learning_rate": 7.27630285152409e-07,
|
| 718 |
+
"loss": 0.3239,
|
| 719 |
+
"step": 38000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 13.451327433628318,
|
| 723 |
+
"eval_accuracy": 0.7946828636861496,
|
| 724 |
+
"eval_f1": 0.8016544824932667,
|
| 725 |
+
"eval_loss": 0.3558191955089569,
|
| 726 |
+
"eval_precision": 0.7886071158213475,
|
| 727 |
+
"eval_recall": 0.8151408450704225,
|
| 728 |
+
"eval_runtime": 53.8826,
|
| 729 |
+
"eval_samples_per_second": 186.387,
|
| 730 |
+
"eval_steps_per_second": 5.827,
|
| 731 |
+
"step": 38000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 13.805309734513274,
|
| 735 |
+
"grad_norm": 17.407468795776367,
|
| 736 |
+
"learning_rate": 6.88298918387414e-07,
|
| 737 |
+
"loss": 0.3231,
|
| 738 |
+
"step": 39000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 13.805309734513274,
|
| 742 |
+
"eval_accuracy": 0.7991635965348999,
|
| 743 |
+
"eval_f1": 0.7988431235663708,
|
| 744 |
+
"eval_loss": 0.351671427488327,
|
| 745 |
+
"eval_precision": 0.814852492370295,
|
| 746 |
+
"eval_recall": 0.7834507042253521,
|
| 747 |
+
"eval_runtime": 53.9126,
|
| 748 |
+
"eval_samples_per_second": 186.283,
|
| 749 |
+
"eval_steps_per_second": 5.824,
|
| 750 |
+
"step": 39000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 14.15929203539823,
|
| 754 |
+
"grad_norm": 9.669415473937988,
|
| 755 |
+
"learning_rate": 6.489675516224188e-07,
|
| 756 |
+
"loss": 0.323,
|
| 757 |
+
"step": 40000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 14.15929203539823,
|
| 761 |
+
"eval_accuracy": 0.7965747286667331,
|
| 762 |
+
"eval_f1": 0.8164585392148055,
|
| 763 |
+
"eval_loss": 0.34596434235572815,
|
| 764 |
+
"eval_precision": 0.7549426815085563,
|
| 765 |
+
"eval_recall": 0.8888888888888888,
|
| 766 |
+
"eval_runtime": 53.8184,
|
| 767 |
+
"eval_samples_per_second": 186.609,
|
| 768 |
+
"eval_steps_per_second": 5.834,
|
| 769 |
+
"step": 40000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 14.513274336283185,
|
| 773 |
+
"grad_norm": 12.53975772857666,
|
| 774 |
+
"learning_rate": 6.096361848574237e-07,
|
| 775 |
+
"loss": 0.3158,
|
| 776 |
+
"step": 41000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 14.513274336283185,
|
| 780 |
+
"eval_accuracy": 0.7998605994224833,
|
| 781 |
+
"eval_f1": 0.8066192033865692,
|
| 782 |
+
"eval_loss": 0.35504859685897827,
|
| 783 |
+
"eval_precision": 0.7936387731919727,
|
| 784 |
+
"eval_recall": 0.8200312989045383,
|
| 785 |
+
"eval_runtime": 53.7599,
|
| 786 |
+
"eval_samples_per_second": 186.812,
|
| 787 |
+
"eval_steps_per_second": 5.841,
|
| 788 |
+
"step": 41000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 14.867256637168142,
|
| 792 |
+
"grad_norm": 20.021963119506836,
|
| 793 |
+
"learning_rate": 5.703048180924287e-07,
|
| 794 |
+
"loss": 0.3126,
|
| 795 |
+
"step": 42000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 14.867256637168142,
|
| 799 |
+
"eval_accuracy": 0.8029473264960669,
|
| 800 |
+
"eval_f1": 0.7949435291679618,
|
| 801 |
+
"eval_loss": 0.34774094820022583,
|
| 802 |
+
"eval_precision": 0.8451200705001102,
|
| 803 |
+
"eval_recall": 0.7503912363067292,
|
| 804 |
+
"eval_runtime": 53.9679,
|
| 805 |
+
"eval_samples_per_second": 186.092,
|
| 806 |
+
"eval_steps_per_second": 5.818,
|
| 807 |
+
"step": 42000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 15.221238938053098,
|
| 811 |
+
"grad_norm": 27.91417694091797,
|
| 812 |
+
"learning_rate": 5.309734513274336e-07,
|
| 813 |
+
"loss": 0.3135,
|
| 814 |
+
"step": 43000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 15.221238938053098,
|
| 818 |
+
"eval_accuracy": 0.8033456138604003,
|
| 819 |
+
"eval_f1": 0.8052076141631325,
|
| 820 |
+
"eval_loss": 0.346435546875,
|
| 821 |
+
"eval_precision": 0.8120151183608514,
|
| 822 |
+
"eval_recall": 0.7985133020344288,
|
| 823 |
+
"eval_runtime": 53.8793,
|
| 824 |
+
"eval_samples_per_second": 186.398,
|
| 825 |
+
"eval_steps_per_second": 5.828,
|
| 826 |
+
"step": 43000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 15.575221238938052,
|
| 830 |
+
"grad_norm": 9.588032722473145,
|
| 831 |
+
"learning_rate": 4.916420845624385e-07,
|
| 832 |
+
"loss": 0.3095,
|
| 833 |
+
"step": 44000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 15.575221238938052,
|
| 837 |
+
"eval_accuracy": 0.8035447575425669,
|
| 838 |
+
"eval_f1": 0.8067391517288667,
|
| 839 |
+
"eval_loss": 0.34088295698165894,
|
| 840 |
+
"eval_precision": 0.807926231116343,
|
| 841 |
+
"eval_recall": 0.8055555555555556,
|
| 842 |
+
"eval_runtime": 53.8032,
|
| 843 |
+
"eval_samples_per_second": 186.662,
|
| 844 |
+
"eval_steps_per_second": 5.836,
|
| 845 |
+
"step": 44000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 15.929203539823009,
|
| 849 |
+
"grad_norm": 10.44812297821045,
|
| 850 |
+
"learning_rate": 4.5231071779744347e-07,
|
| 851 |
+
"loss": 0.3099,
|
| 852 |
+
"step": 45000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 15.929203539823009,
|
| 856 |
+
"eval_accuracy": 0.80065717415115,
|
| 857 |
+
"eval_f1": 0.8102729340409401,
|
| 858 |
+
"eval_loss": 0.3472129702568054,
|
| 859 |
+
"eval_precision": 0.7858455882352942,
|
| 860 |
+
"eval_recall": 0.8362676056338029,
|
| 861 |
+
"eval_runtime": 53.8919,
|
| 862 |
+
"eval_samples_per_second": 186.355,
|
| 863 |
+
"eval_steps_per_second": 5.826,
|
| 864 |
+
"step": 45000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 16.283185840707965,
|
| 868 |
+
"grad_norm": 10.668062210083008,
|
| 869 |
+
"learning_rate": 4.1297935103244836e-07,
|
| 870 |
+
"loss": 0.3056,
|
| 871 |
+
"step": 46000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 16.283185840707965,
|
| 875 |
+
"eval_accuracy": 0.8055361943642338,
|
| 876 |
+
"eval_f1": 0.7982229569170369,
|
| 877 |
+
"eval_loss": 0.3375505208969116,
|
| 878 |
+
"eval_precision": 0.8458506678344646,
|
| 879 |
+
"eval_recall": 0.7556729264475743,
|
| 880 |
+
"eval_runtime": 54.0333,
|
| 881 |
+
"eval_samples_per_second": 185.867,
|
| 882 |
+
"eval_steps_per_second": 5.811,
|
| 883 |
+
"step": 46000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 16.63716814159292,
|
| 887 |
+
"grad_norm": 62.42535400390625,
|
| 888 |
+
"learning_rate": 3.7364798426745325e-07,
|
| 889 |
+
"loss": 0.2983,
|
| 890 |
+
"step": 47000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 16.63716814159292,
|
| 894 |
+
"eval_accuracy": 0.8077267748680673,
|
| 895 |
+
"eval_f1": 0.8059491508391117,
|
| 896 |
+
"eval_loss": 0.34593281149864197,
|
| 897 |
+
"eval_precision": 0.8286836123165944,
|
| 898 |
+
"eval_recall": 0.7844287949921753,
|
| 899 |
+
"eval_runtime": 53.7142,
|
| 900 |
+
"eval_samples_per_second": 186.971,
|
| 901 |
+
"eval_steps_per_second": 5.846,
|
| 902 |
+
"step": 47000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 16.991150442477878,
|
| 906 |
+
"grad_norm": 20.520849227905273,
|
| 907 |
+
"learning_rate": 3.343166175024582e-07,
|
| 908 |
+
"loss": 0.2974,
|
| 909 |
+
"step": 48000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 16.991150442477878,
|
| 913 |
+
"eval_accuracy": 0.8077267748680673,
|
| 914 |
+
"eval_f1": 0.810295706847431,
|
| 915 |
+
"eval_loss": 0.34830448031425476,
|
| 916 |
+
"eval_precision": 0.8138938227748175,
|
| 917 |
+
"eval_recall": 0.8067292644757433,
|
| 918 |
+
"eval_runtime": 53.7486,
|
| 919 |
+
"eval_samples_per_second": 186.851,
|
| 920 |
+
"eval_steps_per_second": 5.842,
|
| 921 |
+
"step": 48000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 17.345132743362832,
|
| 925 |
+
"grad_norm": 10.991024017333984,
|
| 926 |
+
"learning_rate": 2.949852507374631e-07,
|
| 927 |
+
"loss": 0.2966,
|
| 928 |
+
"step": 49000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 17.345132743362832,
|
| 932 |
+
"eval_accuracy": 0.8075276311859007,
|
| 933 |
+
"eval_f1": 0.8143666570632863,
|
| 934 |
+
"eval_loss": 0.35505732893943787,
|
| 935 |
+
"eval_precision": 0.7998490850782871,
|
| 936 |
+
"eval_recall": 0.8294209702660407,
|
| 937 |
+
"eval_runtime": 53.9387,
|
| 938 |
+
"eval_samples_per_second": 186.193,
|
| 939 |
+
"eval_steps_per_second": 5.821,
|
| 940 |
+
"step": 49000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 17.699115044247787,
|
| 944 |
+
"grad_norm": 16.205684661865234,
|
| 945 |
+
"learning_rate": 2.55653883972468e-07,
|
| 946 |
+
"loss": 0.2974,
|
| 947 |
+
"step": 50000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 17.699115044247787,
|
| 951 |
+
"eval_accuracy": 0.8090212088021508,
|
| 952 |
+
"eval_f1": 0.8085446196845678,
|
| 953 |
+
"eval_loss": 0.3468624949455261,
|
| 954 |
+
"eval_precision": 0.8255197717081125,
|
| 955 |
+
"eval_recall": 0.7922535211267606,
|
| 956 |
+
"eval_runtime": 53.9814,
|
| 957 |
+
"eval_samples_per_second": 186.045,
|
| 958 |
+
"eval_steps_per_second": 5.817,
|
| 959 |
+
"step": 50000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 18.053097345132745,
|
| 963 |
+
"grad_norm": 11.926201820373535,
|
| 964 |
+
"learning_rate": 2.1632251720747293e-07,
|
| 965 |
+
"loss": 0.2937,
|
| 966 |
+
"step": 51000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 18.053097345132745,
|
| 970 |
+
"eval_accuracy": 0.807925918550234,
|
| 971 |
+
"eval_f1": 0.8064224786753638,
|
| 972 |
+
"eval_loss": 0.3447153568267822,
|
| 973 |
+
"eval_precision": 0.8279414794972182,
|
| 974 |
+
"eval_recall": 0.7859937402190923,
|
| 975 |
+
"eval_runtime": 53.9266,
|
| 976 |
+
"eval_samples_per_second": 186.235,
|
| 977 |
+
"eval_steps_per_second": 5.823,
|
| 978 |
+
"step": 51000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 18.4070796460177,
|
| 982 |
+
"grad_norm": 8.203916549682617,
|
| 983 |
+
"learning_rate": 1.7699115044247788e-07,
|
| 984 |
+
"loss": 0.2902,
|
| 985 |
+
"step": 52000
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 18.4070796460177,
|
| 989 |
+
"eval_accuracy": 0.808224634073484,
|
| 990 |
+
"eval_f1": 0.8113983548766157,
|
| 991 |
+
"eval_loss": 0.34868165850639343,
|
| 992 |
+
"eval_precision": 0.8123529411764706,
|
| 993 |
+
"eval_recall": 0.8104460093896714,
|
| 994 |
+
"eval_runtime": 53.9322,
|
| 995 |
+
"eval_samples_per_second": 186.215,
|
| 996 |
+
"eval_steps_per_second": 5.822,
|
| 997 |
+
"step": 52000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 18.761061946902654,
|
| 1001 |
+
"grad_norm": 15.017583847045898,
|
| 1002 |
+
"learning_rate": 1.376597836774828e-07,
|
| 1003 |
+
"loss": 0.2969,
|
| 1004 |
+
"step": 53000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 18.761061946902654,
|
| 1008 |
+
"eval_accuracy": 0.8092203524843175,
|
| 1009 |
+
"eval_f1": 0.8131825273010921,
|
| 1010 |
+
"eval_loss": 0.343014657497406,
|
| 1011 |
+
"eval_precision": 0.8106531881804043,
|
| 1012 |
+
"eval_recall": 0.8157276995305164,
|
| 1013 |
+
"eval_runtime": 53.6911,
|
| 1014 |
+
"eval_samples_per_second": 187.051,
|
| 1015 |
+
"eval_steps_per_second": 5.848,
|
| 1016 |
+
"step": 53000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 19.115044247787612,
|
| 1020 |
+
"grad_norm": 17.386789321899414,
|
| 1021 |
+
"learning_rate": 9.83284169124877e-08,
|
| 1022 |
+
"loss": 0.2913,
|
| 1023 |
+
"step": 54000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 19.115044247787612,
|
| 1027 |
+
"eval_accuracy": 0.8131036542865677,
|
| 1028 |
+
"eval_f1": 0.8098855464397853,
|
| 1029 |
+
"eval_loss": 0.33793944120407104,
|
| 1030 |
+
"eval_precision": 0.8397395505145978,
|
| 1031 |
+
"eval_recall": 0.7820813771517997,
|
| 1032 |
+
"eval_runtime": 53.8514,
|
| 1033 |
+
"eval_samples_per_second": 186.495,
|
| 1034 |
+
"eval_steps_per_second": 5.831,
|
| 1035 |
+
"step": 54000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 19.469026548672566,
|
| 1039 |
+
"grad_norm": 10.149681091308594,
|
| 1040 |
+
"learning_rate": 5.899705014749262e-08,
|
| 1041 |
+
"loss": 0.2928,
|
| 1042 |
+
"step": 55000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 19.469026548672566,
|
| 1046 |
+
"eval_accuracy": 0.8094194961664841,
|
| 1047 |
+
"eval_f1": 0.8097415506958251,
|
| 1048 |
+
"eval_loss": 0.3402244746685028,
|
| 1049 |
+
"eval_precision": 0.8231608730800324,
|
| 1050 |
+
"eval_recall": 0.7967527386541471,
|
| 1051 |
+
"eval_runtime": 53.8454,
|
| 1052 |
+
"eval_samples_per_second": 186.516,
|
| 1053 |
+
"eval_steps_per_second": 5.832,
|
| 1054 |
+
"step": 55000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 19.82300884955752,
|
| 1058 |
+
"grad_norm": 12.412276268005371,
|
| 1059 |
+
"learning_rate": 1.966568338249754e-08,
|
| 1060 |
+
"loss": 0.2894,
|
| 1061 |
+
"step": 56000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 19.82300884955752,
|
| 1065 |
+
"eval_accuracy": 0.8115105048292343,
|
| 1066 |
+
"eval_f1": 0.8119972191876055,
|
| 1067 |
+
"eval_loss": 0.3394980728626251,
|
| 1068 |
+
"eval_precision": 0.8246923542465201,
|
| 1069 |
+
"eval_recall": 0.7996870109546166,
|
| 1070 |
+
"eval_runtime": 53.757,
|
| 1071 |
+
"eval_samples_per_second": 186.822,
|
| 1072 |
+
"eval_steps_per_second": 5.841,
|
| 1073 |
+
"step": 56000
|
| 1074 |
+
}
|
| 1075 |
+
],
|
| 1076 |
+
"logging_steps": 1000,
|
| 1077 |
+
"max_steps": 56500,
|
| 1078 |
+
"num_input_tokens_seen": 0,
|
| 1079 |
+
"num_train_epochs": 20,
|
| 1080 |
+
"save_steps": 1000,
|
| 1081 |
+
"stateful_callbacks": {
|
| 1082 |
+
"TrainerControl": {
|
| 1083 |
+
"args": {
|
| 1084 |
+
"should_epoch_stop": false,
|
| 1085 |
+
"should_evaluate": false,
|
| 1086 |
+
"should_log": false,
|
| 1087 |
+
"should_save": true,
|
| 1088 |
+
"should_training_stop": false
|
| 1089 |
+
},
|
| 1090 |
+
"attributes": {}
|
| 1091 |
+
}
|
| 1092 |
+
},
|
| 1093 |
+
"total_flos": 3.8793058646730336e+17,
|
| 1094 |
+
"train_batch_size": 32,
|
| 1095 |
+
"trial_name": null,
|
| 1096 |
+
"trial_params": null
|
| 1097 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1118a3f5eefb0734722b29e7f9910877857d7604b50ca720e9a5fd4e1f88591
|
| 3 |
+
size 5048
|