Initial load
Browse filesInitial upload
- config.json +26 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1546 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "projecte-aina/roberta-base-ca-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 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": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"transformers_version": "4.6.1",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50262
|
| 26 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84366f600d418cbc05b709434546a0ded5861910f34f0d11532da7f2094c5afd
|
| 3 |
+
size 992555871
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70825645ccf10f620e1b8b5cf5d5670b7d4cc75b17ff5c49fae631e2f80d4ee5
|
| 3 |
+
size 496304837
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9aa0ff6be5834c1cfe23be4c968f33505d7a462b3503dfa80df0f74095ee07f
|
| 3 |
+
size 15677
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50afd229a139bd4d6648d01d0a37b84090d72db522edcc2d0c958c1c0a0c2dbd
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "projecte-aina/roberta-base-ca-v2"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1546 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 89.26259594116004,
|
| 3 |
+
"best_model_checkpoint": "/home/shared/dt01/temutauro/ccasimiro/berta/src/qa/roberta-base-ca-v2-qa/SQAC-ca_catalanqa/checkpoint-2458",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 12290,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.979658258746949e-05,
|
| 13 |
+
"loss": 5.2373,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 4.959316517493898e-05,
|
| 19 |
+
"loss": 3.9809,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 4.938974776240847e-05,
|
| 25 |
+
"loss": 3.5244,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 4.918633034987795e-05,
|
| 31 |
+
"loss": 3.1797,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2,
|
| 36 |
+
"learning_rate": 4.898291293734744e-05,
|
| 37 |
+
"loss": 2.9253,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24,
|
| 42 |
+
"learning_rate": 4.877949552481693e-05,
|
| 43 |
+
"loss": 2.585,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.28,
|
| 48 |
+
"learning_rate": 4.857607811228642e-05,
|
| 49 |
+
"loss": 2.3783,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.33,
|
| 54 |
+
"learning_rate": 4.83726606997559e-05,
|
| 55 |
+
"loss": 2.1168,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.37,
|
| 60 |
+
"learning_rate": 4.816924328722539e-05,
|
| 61 |
+
"loss": 1.918,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.41,
|
| 66 |
+
"learning_rate": 4.796582587469488e-05,
|
| 67 |
+
"loss": 1.7789,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.45,
|
| 72 |
+
"learning_rate": 4.776240846216437e-05,
|
| 73 |
+
"loss": 1.683,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.49,
|
| 78 |
+
"learning_rate": 4.755899104963385e-05,
|
| 79 |
+
"loss": 1.5405,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.53,
|
| 84 |
+
"learning_rate": 4.7355573637103337e-05,
|
| 85 |
+
"loss": 1.5408,
|
| 86 |
+
"step": 650
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.57,
|
| 90 |
+
"learning_rate": 4.715215622457283e-05,
|
| 91 |
+
"loss": 1.5068,
|
| 92 |
+
"step": 700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.61,
|
| 96 |
+
"learning_rate": 4.694873881204231e-05,
|
| 97 |
+
"loss": 1.3649,
|
| 98 |
+
"step": 750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.65,
|
| 102 |
+
"learning_rate": 4.6745321399511796e-05,
|
| 103 |
+
"loss": 1.3839,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.69,
|
| 108 |
+
"learning_rate": 4.6541903986981287e-05,
|
| 109 |
+
"loss": 1.2455,
|
| 110 |
+
"step": 850
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.73,
|
| 114 |
+
"learning_rate": 4.633848657445077e-05,
|
| 115 |
+
"loss": 1.3101,
|
| 116 |
+
"step": 900
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.77,
|
| 120 |
+
"learning_rate": 4.613506916192026e-05,
|
| 121 |
+
"loss": 1.2689,
|
| 122 |
+
"step": 950
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.81,
|
| 126 |
+
"learning_rate": 4.5931651749389746e-05,
|
| 127 |
+
"loss": 1.1822,
|
| 128 |
+
"step": 1000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.85,
|
| 132 |
+
"learning_rate": 4.5728234336859237e-05,
|
| 133 |
+
"loss": 1.183,
|
| 134 |
+
"step": 1050
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.9,
|
| 138 |
+
"learning_rate": 4.552481692432872e-05,
|
| 139 |
+
"loss": 1.1435,
|
| 140 |
+
"step": 1100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.94,
|
| 144 |
+
"learning_rate": 4.532139951179821e-05,
|
| 145 |
+
"loss": 1.2057,
|
| 146 |
+
"step": 1150
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.98,
|
| 150 |
+
"learning_rate": 4.5117982099267696e-05,
|
| 151 |
+
"loss": 1.1225,
|
| 152 |
+
"step": 1200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.0,
|
| 156 |
+
"eval_exact_match": 74.34094903339192,
|
| 157 |
+
"eval_f1": 88.58853878556948,
|
| 158 |
+
"step": 1229
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.02,
|
| 162 |
+
"learning_rate": 4.4914564686737187e-05,
|
| 163 |
+
"loss": 0.9737,
|
| 164 |
+
"step": 1250
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.06,
|
| 168 |
+
"learning_rate": 4.471114727420667e-05,
|
| 169 |
+
"loss": 0.8994,
|
| 170 |
+
"step": 1300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.1,
|
| 174 |
+
"learning_rate": 4.450772986167616e-05,
|
| 175 |
+
"loss": 0.8886,
|
| 176 |
+
"step": 1350
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.14,
|
| 180 |
+
"learning_rate": 4.4304312449145646e-05,
|
| 181 |
+
"loss": 0.8679,
|
| 182 |
+
"step": 1400
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.18,
|
| 186 |
+
"learning_rate": 4.4100895036615137e-05,
|
| 187 |
+
"loss": 0.899,
|
| 188 |
+
"step": 1450
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.22,
|
| 192 |
+
"learning_rate": 4.389747762408463e-05,
|
| 193 |
+
"loss": 0.8763,
|
| 194 |
+
"step": 1500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.26,
|
| 198 |
+
"learning_rate": 4.369406021155411e-05,
|
| 199 |
+
"loss": 0.8041,
|
| 200 |
+
"step": 1550
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.3,
|
| 204 |
+
"learning_rate": 4.34906427990236e-05,
|
| 205 |
+
"loss": 0.828,
|
| 206 |
+
"step": 1600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.34,
|
| 210 |
+
"learning_rate": 4.3287225386493087e-05,
|
| 211 |
+
"loss": 0.8691,
|
| 212 |
+
"step": 1650
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.38,
|
| 216 |
+
"learning_rate": 4.308380797396258e-05,
|
| 217 |
+
"loss": 0.8637,
|
| 218 |
+
"step": 1700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.42,
|
| 222 |
+
"learning_rate": 4.288039056143206e-05,
|
| 223 |
+
"loss": 0.8469,
|
| 224 |
+
"step": 1750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.46,
|
| 228 |
+
"learning_rate": 4.267697314890155e-05,
|
| 229 |
+
"loss": 0.8547,
|
| 230 |
+
"step": 1800
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.51,
|
| 234 |
+
"learning_rate": 4.2473555736371037e-05,
|
| 235 |
+
"loss": 0.8116,
|
| 236 |
+
"step": 1850
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.55,
|
| 240 |
+
"learning_rate": 4.227013832384053e-05,
|
| 241 |
+
"loss": 0.8748,
|
| 242 |
+
"step": 1900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.59,
|
| 246 |
+
"learning_rate": 4.206672091131001e-05,
|
| 247 |
+
"loss": 0.8508,
|
| 248 |
+
"step": 1950
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.63,
|
| 252 |
+
"learning_rate": 4.18633034987795e-05,
|
| 253 |
+
"loss": 0.8338,
|
| 254 |
+
"step": 2000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.67,
|
| 258 |
+
"learning_rate": 4.1659886086248987e-05,
|
| 259 |
+
"loss": 0.8547,
|
| 260 |
+
"step": 2050
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.71,
|
| 264 |
+
"learning_rate": 4.145646867371847e-05,
|
| 265 |
+
"loss": 0.8266,
|
| 266 |
+
"step": 2100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.75,
|
| 270 |
+
"learning_rate": 4.125305126118796e-05,
|
| 271 |
+
"loss": 0.8162,
|
| 272 |
+
"step": 2150
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.79,
|
| 276 |
+
"learning_rate": 4.1049633848657446e-05,
|
| 277 |
+
"loss": 0.8152,
|
| 278 |
+
"step": 2200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.83,
|
| 282 |
+
"learning_rate": 4.084621643612693e-05,
|
| 283 |
+
"loss": 0.8674,
|
| 284 |
+
"step": 2250
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.87,
|
| 288 |
+
"learning_rate": 4.064279902359642e-05,
|
| 289 |
+
"loss": 0.868,
|
| 290 |
+
"step": 2300
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.91,
|
| 294 |
+
"learning_rate": 4.0439381611065905e-05,
|
| 295 |
+
"loss": 0.7845,
|
| 296 |
+
"step": 2350
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.95,
|
| 300 |
+
"learning_rate": 4.0235964198535396e-05,
|
| 301 |
+
"loss": 0.8029,
|
| 302 |
+
"step": 2400
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.99,
|
| 306 |
+
"learning_rate": 4.003254678600488e-05,
|
| 307 |
+
"loss": 0.7942,
|
| 308 |
+
"step": 2450
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.0,
|
| 312 |
+
"eval_exact_match": 75.52724077328647,
|
| 313 |
+
"eval_f1": 89.26259594116004,
|
| 314 |
+
"step": 2458
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.03,
|
| 318 |
+
"learning_rate": 3.982912937347437e-05,
|
| 319 |
+
"loss": 0.6307,
|
| 320 |
+
"step": 2500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.07,
|
| 324 |
+
"learning_rate": 3.9625711960943855e-05,
|
| 325 |
+
"loss": 0.5914,
|
| 326 |
+
"step": 2550
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.12,
|
| 330 |
+
"learning_rate": 3.9422294548413346e-05,
|
| 331 |
+
"loss": 0.5965,
|
| 332 |
+
"step": 2600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.16,
|
| 336 |
+
"learning_rate": 3.921887713588283e-05,
|
| 337 |
+
"loss": 0.5843,
|
| 338 |
+
"step": 2650
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.2,
|
| 342 |
+
"learning_rate": 3.901545972335232e-05,
|
| 343 |
+
"loss": 0.6001,
|
| 344 |
+
"step": 2700
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.24,
|
| 348 |
+
"learning_rate": 3.8812042310821805e-05,
|
| 349 |
+
"loss": 0.5671,
|
| 350 |
+
"step": 2750
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.28,
|
| 354 |
+
"learning_rate": 3.8608624898291296e-05,
|
| 355 |
+
"loss": 0.5726,
|
| 356 |
+
"step": 2800
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.32,
|
| 360 |
+
"learning_rate": 3.840520748576078e-05,
|
| 361 |
+
"loss": 0.5599,
|
| 362 |
+
"step": 2850
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.36,
|
| 366 |
+
"learning_rate": 3.820179007323027e-05,
|
| 367 |
+
"loss": 0.582,
|
| 368 |
+
"step": 2900
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.4,
|
| 372 |
+
"learning_rate": 3.799837266069976e-05,
|
| 373 |
+
"loss": 0.5981,
|
| 374 |
+
"step": 2950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.44,
|
| 378 |
+
"learning_rate": 3.7794955248169246e-05,
|
| 379 |
+
"loss": 0.572,
|
| 380 |
+
"step": 3000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.48,
|
| 384 |
+
"learning_rate": 3.759153783563874e-05,
|
| 385 |
+
"loss": 0.5506,
|
| 386 |
+
"step": 3050
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.52,
|
| 390 |
+
"learning_rate": 3.738812042310822e-05,
|
| 391 |
+
"loss": 0.5822,
|
| 392 |
+
"step": 3100
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.56,
|
| 396 |
+
"learning_rate": 3.718470301057771e-05,
|
| 397 |
+
"loss": 0.5504,
|
| 398 |
+
"step": 3150
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.6,
|
| 402 |
+
"learning_rate": 3.6981285598047196e-05,
|
| 403 |
+
"loss": 0.6113,
|
| 404 |
+
"step": 3200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.64,
|
| 408 |
+
"learning_rate": 3.677786818551669e-05,
|
| 409 |
+
"loss": 0.5381,
|
| 410 |
+
"step": 3250
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.69,
|
| 414 |
+
"learning_rate": 3.657445077298617e-05,
|
| 415 |
+
"loss": 0.624,
|
| 416 |
+
"step": 3300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.73,
|
| 420 |
+
"learning_rate": 3.637103336045566e-05,
|
| 421 |
+
"loss": 0.5775,
|
| 422 |
+
"step": 3350
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.77,
|
| 426 |
+
"learning_rate": 3.6167615947925146e-05,
|
| 427 |
+
"loss": 0.5344,
|
| 428 |
+
"step": 3400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.81,
|
| 432 |
+
"learning_rate": 3.596419853539463e-05,
|
| 433 |
+
"loss": 0.5982,
|
| 434 |
+
"step": 3450
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.85,
|
| 438 |
+
"learning_rate": 3.576078112286412e-05,
|
| 439 |
+
"loss": 0.6115,
|
| 440 |
+
"step": 3500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.89,
|
| 444 |
+
"learning_rate": 3.5557363710333605e-05,
|
| 445 |
+
"loss": 0.5735,
|
| 446 |
+
"step": 3550
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.93,
|
| 450 |
+
"learning_rate": 3.535394629780309e-05,
|
| 451 |
+
"loss": 0.5682,
|
| 452 |
+
"step": 3600
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.97,
|
| 456 |
+
"learning_rate": 3.515052888527258e-05,
|
| 457 |
+
"loss": 0.5968,
|
| 458 |
+
"step": 3650
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.0,
|
| 462 |
+
"eval_exact_match": 75.96660808435853,
|
| 463 |
+
"eval_f1": 88.9904800819017,
|
| 464 |
+
"step": 3687
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.01,
|
| 468 |
+
"learning_rate": 3.4947111472742064e-05,
|
| 469 |
+
"loss": 0.5059,
|
| 470 |
+
"step": 3700
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.05,
|
| 474 |
+
"learning_rate": 3.4743694060211555e-05,
|
| 475 |
+
"loss": 0.4033,
|
| 476 |
+
"step": 3750
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.09,
|
| 480 |
+
"learning_rate": 3.454027664768104e-05,
|
| 481 |
+
"loss": 0.4208,
|
| 482 |
+
"step": 3800
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.13,
|
| 486 |
+
"learning_rate": 3.433685923515053e-05,
|
| 487 |
+
"loss": 0.4397,
|
| 488 |
+
"step": 3850
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.17,
|
| 492 |
+
"learning_rate": 3.4133441822620014e-05,
|
| 493 |
+
"loss": 0.4268,
|
| 494 |
+
"step": 3900
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.21,
|
| 498 |
+
"learning_rate": 3.3930024410089505e-05,
|
| 499 |
+
"loss": 0.4098,
|
| 500 |
+
"step": 3950
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.25,
|
| 504 |
+
"learning_rate": 3.372660699755899e-05,
|
| 505 |
+
"loss": 0.4226,
|
| 506 |
+
"step": 4000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.3,
|
| 510 |
+
"learning_rate": 3.352318958502848e-05,
|
| 511 |
+
"loss": 0.4164,
|
| 512 |
+
"step": 4050
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.34,
|
| 516 |
+
"learning_rate": 3.3319772172497964e-05,
|
| 517 |
+
"loss": 0.3775,
|
| 518 |
+
"step": 4100
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.38,
|
| 522 |
+
"learning_rate": 3.3116354759967455e-05,
|
| 523 |
+
"loss": 0.4004,
|
| 524 |
+
"step": 4150
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.42,
|
| 528 |
+
"learning_rate": 3.291293734743694e-05,
|
| 529 |
+
"loss": 0.4427,
|
| 530 |
+
"step": 4200
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.46,
|
| 534 |
+
"learning_rate": 3.270951993490643e-05,
|
| 535 |
+
"loss": 0.4358,
|
| 536 |
+
"step": 4250
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.5,
|
| 540 |
+
"learning_rate": 3.250610252237592e-05,
|
| 541 |
+
"loss": 0.3924,
|
| 542 |
+
"step": 4300
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.54,
|
| 546 |
+
"learning_rate": 3.2302685109845405e-05,
|
| 547 |
+
"loss": 0.4541,
|
| 548 |
+
"step": 4350
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.58,
|
| 552 |
+
"learning_rate": 3.2099267697314896e-05,
|
| 553 |
+
"loss": 0.4247,
|
| 554 |
+
"step": 4400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.62,
|
| 558 |
+
"learning_rate": 3.189585028478438e-05,
|
| 559 |
+
"loss": 0.4114,
|
| 560 |
+
"step": 4450
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.66,
|
| 564 |
+
"learning_rate": 3.169243287225387e-05,
|
| 565 |
+
"loss": 0.4264,
|
| 566 |
+
"step": 4500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.7,
|
| 570 |
+
"learning_rate": 3.1489015459723355e-05,
|
| 571 |
+
"loss": 0.4246,
|
| 572 |
+
"step": 4550
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.74,
|
| 576 |
+
"learning_rate": 3.1285598047192846e-05,
|
| 577 |
+
"loss": 0.4324,
|
| 578 |
+
"step": 4600
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.78,
|
| 582 |
+
"learning_rate": 3.108218063466233e-05,
|
| 583 |
+
"loss": 0.4018,
|
| 584 |
+
"step": 4650
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.82,
|
| 588 |
+
"learning_rate": 3.087876322213182e-05,
|
| 589 |
+
"loss": 0.4354,
|
| 590 |
+
"step": 4700
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.86,
|
| 594 |
+
"learning_rate": 3.0675345809601305e-05,
|
| 595 |
+
"loss": 0.4279,
|
| 596 |
+
"step": 4750
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.91,
|
| 600 |
+
"learning_rate": 3.0471928397070792e-05,
|
| 601 |
+
"loss": 0.4264,
|
| 602 |
+
"step": 4800
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.95,
|
| 606 |
+
"learning_rate": 3.0268510984540277e-05,
|
| 607 |
+
"loss": 0.4211,
|
| 608 |
+
"step": 4850
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.99,
|
| 612 |
+
"learning_rate": 3.0065093572009767e-05,
|
| 613 |
+
"loss": 0.5077,
|
| 614 |
+
"step": 4900
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.0,
|
| 618 |
+
"eval_exact_match": 75.61511423550088,
|
| 619 |
+
"eval_f1": 88.81911407320312,
|
| 620 |
+
"step": 4916
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.03,
|
| 624 |
+
"learning_rate": 2.986167615947925e-05,
|
| 625 |
+
"loss": 0.302,
|
| 626 |
+
"step": 4950
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.07,
|
| 630 |
+
"learning_rate": 2.9658258746948742e-05,
|
| 631 |
+
"loss": 0.3048,
|
| 632 |
+
"step": 5000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.11,
|
| 636 |
+
"learning_rate": 2.9454841334418227e-05,
|
| 637 |
+
"loss": 0.3303,
|
| 638 |
+
"step": 5050
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.15,
|
| 642 |
+
"learning_rate": 2.9251423921887717e-05,
|
| 643 |
+
"loss": 0.2985,
|
| 644 |
+
"step": 5100
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.19,
|
| 648 |
+
"learning_rate": 2.90480065093572e-05,
|
| 649 |
+
"loss": 0.3188,
|
| 650 |
+
"step": 5150
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 4.23,
|
| 654 |
+
"learning_rate": 2.884458909682669e-05,
|
| 655 |
+
"loss": 0.3033,
|
| 656 |
+
"step": 5200
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.27,
|
| 660 |
+
"learning_rate": 2.8641171684296177e-05,
|
| 661 |
+
"loss": 0.2714,
|
| 662 |
+
"step": 5250
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 4.31,
|
| 666 |
+
"learning_rate": 2.8437754271765664e-05,
|
| 667 |
+
"loss": 0.3447,
|
| 668 |
+
"step": 5300
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.35,
|
| 672 |
+
"learning_rate": 2.8234336859235148e-05,
|
| 673 |
+
"loss": 0.3115,
|
| 674 |
+
"step": 5350
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.39,
|
| 678 |
+
"learning_rate": 2.803091944670464e-05,
|
| 679 |
+
"loss": 0.3237,
|
| 680 |
+
"step": 5400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.43,
|
| 684 |
+
"learning_rate": 2.7827502034174123e-05,
|
| 685 |
+
"loss": 0.3097,
|
| 686 |
+
"step": 5450
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 4.48,
|
| 690 |
+
"learning_rate": 2.7624084621643614e-05,
|
| 691 |
+
"loss": 0.3016,
|
| 692 |
+
"step": 5500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 4.52,
|
| 696 |
+
"learning_rate": 2.7420667209113098e-05,
|
| 697 |
+
"loss": 0.3256,
|
| 698 |
+
"step": 5550
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.56,
|
| 702 |
+
"learning_rate": 2.721724979658259e-05,
|
| 703 |
+
"loss": 0.3051,
|
| 704 |
+
"step": 5600
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.6,
|
| 708 |
+
"learning_rate": 2.7013832384052073e-05,
|
| 709 |
+
"loss": 0.3188,
|
| 710 |
+
"step": 5650
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.64,
|
| 714 |
+
"learning_rate": 2.6810414971521564e-05,
|
| 715 |
+
"loss": 0.3153,
|
| 716 |
+
"step": 5700
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.68,
|
| 720 |
+
"learning_rate": 2.6606997558991055e-05,
|
| 721 |
+
"loss": 0.2839,
|
| 722 |
+
"step": 5750
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.72,
|
| 726 |
+
"learning_rate": 2.640358014646054e-05,
|
| 727 |
+
"loss": 0.3019,
|
| 728 |
+
"step": 5800
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 4.76,
|
| 732 |
+
"learning_rate": 2.6200162733930027e-05,
|
| 733 |
+
"loss": 0.3057,
|
| 734 |
+
"step": 5850
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 4.8,
|
| 738 |
+
"learning_rate": 2.5996745321399514e-05,
|
| 739 |
+
"loss": 0.3041,
|
| 740 |
+
"step": 5900
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.84,
|
| 744 |
+
"learning_rate": 2.5793327908869e-05,
|
| 745 |
+
"loss": 0.2825,
|
| 746 |
+
"step": 5950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 4.88,
|
| 750 |
+
"learning_rate": 2.5589910496338486e-05,
|
| 751 |
+
"loss": 0.3363,
|
| 752 |
+
"step": 6000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 4.92,
|
| 756 |
+
"learning_rate": 2.5386493083807977e-05,
|
| 757 |
+
"loss": 0.3117,
|
| 758 |
+
"step": 6050
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.96,
|
| 762 |
+
"learning_rate": 2.518307567127746e-05,
|
| 763 |
+
"loss": 0.3155,
|
| 764 |
+
"step": 6100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 5.0,
|
| 768 |
+
"eval_exact_match": 75.35149384885764,
|
| 769 |
+
"eval_f1": 88.92853845000909,
|
| 770 |
+
"step": 6145
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 5.0,
|
| 774 |
+
"learning_rate": 2.4979658258746948e-05,
|
| 775 |
+
"loss": 0.3373,
|
| 776 |
+
"step": 6150
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 5.04,
|
| 780 |
+
"learning_rate": 2.4776240846216436e-05,
|
| 781 |
+
"loss": 0.2384,
|
| 782 |
+
"step": 6200
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 5.09,
|
| 786 |
+
"learning_rate": 2.4572823433685923e-05,
|
| 787 |
+
"loss": 0.2404,
|
| 788 |
+
"step": 6250
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 5.13,
|
| 792 |
+
"learning_rate": 2.436940602115541e-05,
|
| 793 |
+
"loss": 0.2242,
|
| 794 |
+
"step": 6300
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 5.17,
|
| 798 |
+
"learning_rate": 2.4165988608624898e-05,
|
| 799 |
+
"loss": 0.213,
|
| 800 |
+
"step": 6350
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 5.21,
|
| 804 |
+
"learning_rate": 2.3962571196094386e-05,
|
| 805 |
+
"loss": 0.229,
|
| 806 |
+
"step": 6400
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 5.25,
|
| 810 |
+
"learning_rate": 2.3759153783563877e-05,
|
| 811 |
+
"loss": 0.2324,
|
| 812 |
+
"step": 6450
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 5.29,
|
| 816 |
+
"learning_rate": 2.3555736371033364e-05,
|
| 817 |
+
"loss": 0.2143,
|
| 818 |
+
"step": 6500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 5.33,
|
| 822 |
+
"learning_rate": 2.335231895850285e-05,
|
| 823 |
+
"loss": 0.1819,
|
| 824 |
+
"step": 6550
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 5.37,
|
| 828 |
+
"learning_rate": 2.3148901545972336e-05,
|
| 829 |
+
"loss": 0.2446,
|
| 830 |
+
"step": 6600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 5.41,
|
| 834 |
+
"learning_rate": 2.2945484133441823e-05,
|
| 835 |
+
"loss": 0.2254,
|
| 836 |
+
"step": 6650
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 5.45,
|
| 840 |
+
"learning_rate": 2.274206672091131e-05,
|
| 841 |
+
"loss": 0.2415,
|
| 842 |
+
"step": 6700
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 5.49,
|
| 846 |
+
"learning_rate": 2.2538649308380798e-05,
|
| 847 |
+
"loss": 0.2914,
|
| 848 |
+
"step": 6750
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 5.53,
|
| 852 |
+
"learning_rate": 2.2335231895850286e-05,
|
| 853 |
+
"loss": 0.2204,
|
| 854 |
+
"step": 6800
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 5.57,
|
| 858 |
+
"learning_rate": 2.2131814483319773e-05,
|
| 859 |
+
"loss": 0.2447,
|
| 860 |
+
"step": 6850
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 5.61,
|
| 864 |
+
"learning_rate": 2.192839707078926e-05,
|
| 865 |
+
"loss": 0.2629,
|
| 866 |
+
"step": 6900
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 5.66,
|
| 870 |
+
"learning_rate": 2.1724979658258748e-05,
|
| 871 |
+
"loss": 0.2668,
|
| 872 |
+
"step": 6950
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 5.7,
|
| 876 |
+
"learning_rate": 2.1521562245728236e-05,
|
| 877 |
+
"loss": 0.224,
|
| 878 |
+
"step": 7000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 5.74,
|
| 882 |
+
"learning_rate": 2.1318144833197723e-05,
|
| 883 |
+
"loss": 0.2601,
|
| 884 |
+
"step": 7050
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.78,
|
| 888 |
+
"learning_rate": 2.111472742066721e-05,
|
| 889 |
+
"loss": 0.2408,
|
| 890 |
+
"step": 7100
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 5.82,
|
| 894 |
+
"learning_rate": 2.0911310008136698e-05,
|
| 895 |
+
"loss": 0.2212,
|
| 896 |
+
"step": 7150
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 5.86,
|
| 900 |
+
"learning_rate": 2.0707892595606186e-05,
|
| 901 |
+
"loss": 0.2445,
|
| 902 |
+
"step": 7200
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 5.9,
|
| 906 |
+
"learning_rate": 2.0504475183075673e-05,
|
| 907 |
+
"loss": 0.2413,
|
| 908 |
+
"step": 7250
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 5.94,
|
| 912 |
+
"learning_rate": 2.030105777054516e-05,
|
| 913 |
+
"loss": 0.2178,
|
| 914 |
+
"step": 7300
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 5.98,
|
| 918 |
+
"learning_rate": 2.009764035801465e-05,
|
| 919 |
+
"loss": 0.2166,
|
| 920 |
+
"step": 7350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 6.0,
|
| 924 |
+
"eval_exact_match": 75.04393673110721,
|
| 925 |
+
"eval_f1": 88.49211373882532,
|
| 926 |
+
"step": 7374
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 6.02,
|
| 930 |
+
"learning_rate": 1.9894222945484132e-05,
|
| 931 |
+
"loss": 0.2315,
|
| 932 |
+
"step": 7400
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 6.06,
|
| 936 |
+
"learning_rate": 1.969080553295362e-05,
|
| 937 |
+
"loss": 0.1622,
|
| 938 |
+
"step": 7450
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 6.1,
|
| 942 |
+
"learning_rate": 1.9487388120423107e-05,
|
| 943 |
+
"loss": 0.1563,
|
| 944 |
+
"step": 7500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 6.14,
|
| 948 |
+
"learning_rate": 1.9283970707892595e-05,
|
| 949 |
+
"loss": 0.1794,
|
| 950 |
+
"step": 7550
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 6.18,
|
| 954 |
+
"learning_rate": 1.9080553295362082e-05,
|
| 955 |
+
"loss": 0.1874,
|
| 956 |
+
"step": 7600
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 6.22,
|
| 960 |
+
"learning_rate": 1.887713588283157e-05,
|
| 961 |
+
"loss": 0.1561,
|
| 962 |
+
"step": 7650
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 6.27,
|
| 966 |
+
"learning_rate": 1.8673718470301057e-05,
|
| 967 |
+
"loss": 0.1966,
|
| 968 |
+
"step": 7700
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 6.31,
|
| 972 |
+
"learning_rate": 1.8470301057770545e-05,
|
| 973 |
+
"loss": 0.1621,
|
| 974 |
+
"step": 7750
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 6.35,
|
| 978 |
+
"learning_rate": 1.8266883645240032e-05,
|
| 979 |
+
"loss": 0.1468,
|
| 980 |
+
"step": 7800
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 6.39,
|
| 984 |
+
"learning_rate": 1.806346623270952e-05,
|
| 985 |
+
"loss": 0.1831,
|
| 986 |
+
"step": 7850
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 6.43,
|
| 990 |
+
"learning_rate": 1.786004882017901e-05,
|
| 991 |
+
"loss": 0.177,
|
| 992 |
+
"step": 7900
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 6.47,
|
| 996 |
+
"learning_rate": 1.76566314076485e-05,
|
| 997 |
+
"loss": 0.1498,
|
| 998 |
+
"step": 7950
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 6.51,
|
| 1002 |
+
"learning_rate": 1.7453213995117982e-05,
|
| 1003 |
+
"loss": 0.1556,
|
| 1004 |
+
"step": 8000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 6.55,
|
| 1008 |
+
"learning_rate": 1.724979658258747e-05,
|
| 1009 |
+
"loss": 0.1928,
|
| 1010 |
+
"step": 8050
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 6.59,
|
| 1014 |
+
"learning_rate": 1.7046379170056957e-05,
|
| 1015 |
+
"loss": 0.1776,
|
| 1016 |
+
"step": 8100
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 6.63,
|
| 1020 |
+
"learning_rate": 1.6842961757526445e-05,
|
| 1021 |
+
"loss": 0.1697,
|
| 1022 |
+
"step": 8150
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 6.67,
|
| 1026 |
+
"learning_rate": 1.6639544344995932e-05,
|
| 1027 |
+
"loss": 0.1782,
|
| 1028 |
+
"step": 8200
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 6.71,
|
| 1032 |
+
"learning_rate": 1.643612693246542e-05,
|
| 1033 |
+
"loss": 0.1658,
|
| 1034 |
+
"step": 8250
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 6.75,
|
| 1038 |
+
"learning_rate": 1.6232709519934907e-05,
|
| 1039 |
+
"loss": 0.1605,
|
| 1040 |
+
"step": 8300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 6.79,
|
| 1044 |
+
"learning_rate": 1.6029292107404395e-05,
|
| 1045 |
+
"loss": 0.1512,
|
| 1046 |
+
"step": 8350
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 6.83,
|
| 1050 |
+
"learning_rate": 1.5825874694873882e-05,
|
| 1051 |
+
"loss": 0.1689,
|
| 1052 |
+
"step": 8400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 6.88,
|
| 1056 |
+
"learning_rate": 1.562245728234337e-05,
|
| 1057 |
+
"loss": 0.1774,
|
| 1058 |
+
"step": 8450
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 6.92,
|
| 1062 |
+
"learning_rate": 1.5419039869812857e-05,
|
| 1063 |
+
"loss": 0.1884,
|
| 1064 |
+
"step": 8500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 6.96,
|
| 1068 |
+
"learning_rate": 1.5215622457282345e-05,
|
| 1069 |
+
"loss": 0.1559,
|
| 1070 |
+
"step": 8550
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 7.0,
|
| 1074 |
+
"learning_rate": 1.501220504475183e-05,
|
| 1075 |
+
"loss": 0.18,
|
| 1076 |
+
"step": 8600
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 7.0,
|
| 1080 |
+
"eval_exact_match": 73.72583479789104,
|
| 1081 |
+
"eval_f1": 87.84725743086018,
|
| 1082 |
+
"step": 8603
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 7.04,
|
| 1086 |
+
"learning_rate": 1.4808787632221318e-05,
|
| 1087 |
+
"loss": 0.1476,
|
| 1088 |
+
"step": 8650
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 7.08,
|
| 1092 |
+
"learning_rate": 1.4605370219690806e-05,
|
| 1093 |
+
"loss": 0.1096,
|
| 1094 |
+
"step": 8700
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.12,
|
| 1098 |
+
"learning_rate": 1.4401952807160293e-05,
|
| 1099 |
+
"loss": 0.1364,
|
| 1100 |
+
"step": 8750
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 7.16,
|
| 1104 |
+
"learning_rate": 1.419853539462978e-05,
|
| 1105 |
+
"loss": 0.1248,
|
| 1106 |
+
"step": 8800
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 7.2,
|
| 1110 |
+
"learning_rate": 1.3995117982099268e-05,
|
| 1111 |
+
"loss": 0.1468,
|
| 1112 |
+
"step": 8850
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 7.24,
|
| 1116 |
+
"learning_rate": 1.3791700569568756e-05,
|
| 1117 |
+
"loss": 0.1217,
|
| 1118 |
+
"step": 8900
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 7.28,
|
| 1122 |
+
"learning_rate": 1.3588283157038242e-05,
|
| 1123 |
+
"loss": 0.113,
|
| 1124 |
+
"step": 8950
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 7.32,
|
| 1128 |
+
"learning_rate": 1.3384865744507729e-05,
|
| 1129 |
+
"loss": 0.1347,
|
| 1130 |
+
"step": 9000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 7.36,
|
| 1134 |
+
"learning_rate": 1.3181448331977217e-05,
|
| 1135 |
+
"loss": 0.1284,
|
| 1136 |
+
"step": 9050
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.4,
|
| 1140 |
+
"learning_rate": 1.2978030919446704e-05,
|
| 1141 |
+
"loss": 0.1326,
|
| 1142 |
+
"step": 9100
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 7.45,
|
| 1146 |
+
"learning_rate": 1.2774613506916192e-05,
|
| 1147 |
+
"loss": 0.12,
|
| 1148 |
+
"step": 9150
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 7.49,
|
| 1152 |
+
"learning_rate": 1.2571196094385679e-05,
|
| 1153 |
+
"loss": 0.1201,
|
| 1154 |
+
"step": 9200
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 7.53,
|
| 1158 |
+
"learning_rate": 1.2367778681855167e-05,
|
| 1159 |
+
"loss": 0.1273,
|
| 1160 |
+
"step": 9250
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 7.57,
|
| 1164 |
+
"learning_rate": 1.2164361269324654e-05,
|
| 1165 |
+
"loss": 0.1191,
|
| 1166 |
+
"step": 9300
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 7.61,
|
| 1170 |
+
"learning_rate": 1.1960943856794142e-05,
|
| 1171 |
+
"loss": 0.114,
|
| 1172 |
+
"step": 9350
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 7.65,
|
| 1176 |
+
"learning_rate": 1.1757526444263629e-05,
|
| 1177 |
+
"loss": 0.1596,
|
| 1178 |
+
"step": 9400
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.69,
|
| 1182 |
+
"learning_rate": 1.1554109031733117e-05,
|
| 1183 |
+
"loss": 0.1388,
|
| 1184 |
+
"step": 9450
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 7.73,
|
| 1188 |
+
"learning_rate": 1.1350691619202604e-05,
|
| 1189 |
+
"loss": 0.1238,
|
| 1190 |
+
"step": 9500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 7.77,
|
| 1194 |
+
"learning_rate": 1.1147274206672092e-05,
|
| 1195 |
+
"loss": 0.0968,
|
| 1196 |
+
"step": 9550
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 7.81,
|
| 1200 |
+
"learning_rate": 1.0943856794141579e-05,
|
| 1201 |
+
"loss": 0.1267,
|
| 1202 |
+
"step": 9600
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 7.85,
|
| 1206 |
+
"learning_rate": 1.0740439381611067e-05,
|
| 1207 |
+
"loss": 0.1168,
|
| 1208 |
+
"step": 9650
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 7.89,
|
| 1212 |
+
"learning_rate": 1.0537021969080554e-05,
|
| 1213 |
+
"loss": 0.1243,
|
| 1214 |
+
"step": 9700
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 7.93,
|
| 1218 |
+
"learning_rate": 1.0333604556550042e-05,
|
| 1219 |
+
"loss": 0.1277,
|
| 1220 |
+
"step": 9750
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 7.97,
|
| 1224 |
+
"learning_rate": 1.013018714401953e-05,
|
| 1225 |
+
"loss": 0.1074,
|
| 1226 |
+
"step": 9800
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 8.0,
|
| 1230 |
+
"eval_exact_match": 74.56063268892794,
|
| 1231 |
+
"eval_f1": 88.45070096881145,
|
| 1232 |
+
"step": 9832
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 8.01,
|
| 1236 |
+
"learning_rate": 9.926769731489017e-06,
|
| 1237 |
+
"loss": 0.1002,
|
| 1238 |
+
"step": 9850
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 8.06,
|
| 1242 |
+
"learning_rate": 9.723352318958504e-06,
|
| 1243 |
+
"loss": 0.0957,
|
| 1244 |
+
"step": 9900
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 8.1,
|
| 1248 |
+
"learning_rate": 9.51993490642799e-06,
|
| 1249 |
+
"loss": 0.0851,
|
| 1250 |
+
"step": 9950
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 8.14,
|
| 1254 |
+
"learning_rate": 9.316517493897477e-06,
|
| 1255 |
+
"loss": 0.0911,
|
| 1256 |
+
"step": 10000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 8.18,
|
| 1260 |
+
"learning_rate": 9.113100081366965e-06,
|
| 1261 |
+
"loss": 0.1098,
|
| 1262 |
+
"step": 10050
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 8.22,
|
| 1266 |
+
"learning_rate": 8.909682668836452e-06,
|
| 1267 |
+
"loss": 0.0731,
|
| 1268 |
+
"step": 10100
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 8.26,
|
| 1272 |
+
"learning_rate": 8.70626525630594e-06,
|
| 1273 |
+
"loss": 0.1131,
|
| 1274 |
+
"step": 10150
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 8.3,
|
| 1278 |
+
"learning_rate": 8.502847843775427e-06,
|
| 1279 |
+
"loss": 0.1102,
|
| 1280 |
+
"step": 10200
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 8.34,
|
| 1284 |
+
"learning_rate": 8.299430431244915e-06,
|
| 1285 |
+
"loss": 0.0748,
|
| 1286 |
+
"step": 10250
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 8.38,
|
| 1290 |
+
"learning_rate": 8.096013018714402e-06,
|
| 1291 |
+
"loss": 0.0686,
|
| 1292 |
+
"step": 10300
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 8.42,
|
| 1296 |
+
"learning_rate": 7.892595606183888e-06,
|
| 1297 |
+
"loss": 0.0966,
|
| 1298 |
+
"step": 10350
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 8.46,
|
| 1302 |
+
"learning_rate": 7.689178193653377e-06,
|
| 1303 |
+
"loss": 0.1004,
|
| 1304 |
+
"step": 10400
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 8.5,
|
| 1308 |
+
"learning_rate": 7.485760781122865e-06,
|
| 1309 |
+
"loss": 0.084,
|
| 1310 |
+
"step": 10450
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 8.54,
|
| 1314 |
+
"learning_rate": 7.2823433685923525e-06,
|
| 1315 |
+
"loss": 0.0836,
|
| 1316 |
+
"step": 10500
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 8.58,
|
| 1320 |
+
"learning_rate": 7.078925956061839e-06,
|
| 1321 |
+
"loss": 0.0896,
|
| 1322 |
+
"step": 10550
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 8.62,
|
| 1326 |
+
"learning_rate": 6.875508543531327e-06,
|
| 1327 |
+
"loss": 0.0939,
|
| 1328 |
+
"step": 10600
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 8.67,
|
| 1332 |
+
"learning_rate": 6.672091131000814e-06,
|
| 1333 |
+
"loss": 0.0965,
|
| 1334 |
+
"step": 10650
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 8.71,
|
| 1338 |
+
"learning_rate": 6.468673718470302e-06,
|
| 1339 |
+
"loss": 0.1025,
|
| 1340 |
+
"step": 10700
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 8.75,
|
| 1344 |
+
"learning_rate": 6.265256305939788e-06,
|
| 1345 |
+
"loss": 0.1208,
|
| 1346 |
+
"step": 10750
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 8.79,
|
| 1350 |
+
"learning_rate": 6.061838893409276e-06,
|
| 1351 |
+
"loss": 0.1072,
|
| 1352 |
+
"step": 10800
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 8.83,
|
| 1356 |
+
"learning_rate": 5.858421480878763e-06,
|
| 1357 |
+
"loss": 0.102,
|
| 1358 |
+
"step": 10850
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 8.87,
|
| 1362 |
+
"learning_rate": 5.655004068348251e-06,
|
| 1363 |
+
"loss": 0.0979,
|
| 1364 |
+
"step": 10900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 8.91,
|
| 1368 |
+
"learning_rate": 5.451586655817738e-06,
|
| 1369 |
+
"loss": 0.1203,
|
| 1370 |
+
"step": 10950
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 8.95,
|
| 1374 |
+
"learning_rate": 5.248169243287226e-06,
|
| 1375 |
+
"loss": 0.0906,
|
| 1376 |
+
"step": 11000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 8.99,
|
| 1380 |
+
"learning_rate": 5.044751830756713e-06,
|
| 1381 |
+
"loss": 0.1009,
|
| 1382 |
+
"step": 11050
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 9.0,
|
| 1386 |
+
"eval_exact_match": 74.78031634446397,
|
| 1387 |
+
"eval_f1": 88.33201226117784,
|
| 1388 |
+
"step": 11061
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 9.03,
|
| 1392 |
+
"learning_rate": 4.8413344182262e-06,
|
| 1393 |
+
"loss": 0.094,
|
| 1394 |
+
"step": 11100
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 9.07,
|
| 1398 |
+
"learning_rate": 4.6379170056956875e-06,
|
| 1399 |
+
"loss": 0.0629,
|
| 1400 |
+
"step": 11150
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 9.11,
|
| 1404 |
+
"learning_rate": 4.434499593165175e-06,
|
| 1405 |
+
"loss": 0.081,
|
| 1406 |
+
"step": 11200
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 9.15,
|
| 1410 |
+
"learning_rate": 4.2310821806346625e-06,
|
| 1411 |
+
"loss": 0.0693,
|
| 1412 |
+
"step": 11250
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 9.19,
|
| 1416 |
+
"learning_rate": 4.02766476810415e-06,
|
| 1417 |
+
"loss": 0.0731,
|
| 1418 |
+
"step": 11300
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 9.24,
|
| 1422 |
+
"learning_rate": 3.8242473555736375e-06,
|
| 1423 |
+
"loss": 0.0884,
|
| 1424 |
+
"step": 11350
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 9.28,
|
| 1428 |
+
"learning_rate": 3.6208299430431246e-06,
|
| 1429 |
+
"loss": 0.0618,
|
| 1430 |
+
"step": 11400
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 9.32,
|
| 1434 |
+
"learning_rate": 3.417412530512612e-06,
|
| 1435 |
+
"loss": 0.0915,
|
| 1436 |
+
"step": 11450
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 9.36,
|
| 1440 |
+
"learning_rate": 3.213995117982099e-06,
|
| 1441 |
+
"loss": 0.0928,
|
| 1442 |
+
"step": 11500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 9.4,
|
| 1446 |
+
"learning_rate": 3.010577705451587e-06,
|
| 1447 |
+
"loss": 0.0846,
|
| 1448 |
+
"step": 11550
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 9.44,
|
| 1452 |
+
"learning_rate": 2.807160292921074e-06,
|
| 1453 |
+
"loss": 0.0602,
|
| 1454 |
+
"step": 11600
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 9.48,
|
| 1458 |
+
"learning_rate": 2.6037428803905617e-06,
|
| 1459 |
+
"loss": 0.0671,
|
| 1460 |
+
"step": 11650
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 9.52,
|
| 1464 |
+
"learning_rate": 2.4003254678600487e-06,
|
| 1465 |
+
"loss": 0.0714,
|
| 1466 |
+
"step": 11700
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 9.56,
|
| 1470 |
+
"learning_rate": 2.1969080553295362e-06,
|
| 1471 |
+
"loss": 0.081,
|
| 1472 |
+
"step": 11750
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 9.6,
|
| 1476 |
+
"learning_rate": 1.9934906427990237e-06,
|
| 1477 |
+
"loss": 0.0798,
|
| 1478 |
+
"step": 11800
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 9.64,
|
| 1482 |
+
"learning_rate": 1.790073230268511e-06,
|
| 1483 |
+
"loss": 0.0834,
|
| 1484 |
+
"step": 11850
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 9.68,
|
| 1488 |
+
"learning_rate": 1.5866558177379985e-06,
|
| 1489 |
+
"loss": 0.0907,
|
| 1490 |
+
"step": 11900
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 9.72,
|
| 1494 |
+
"learning_rate": 1.3832384052074858e-06,
|
| 1495 |
+
"loss": 0.0705,
|
| 1496 |
+
"step": 11950
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 9.76,
|
| 1500 |
+
"learning_rate": 1.1798209926769731e-06,
|
| 1501 |
+
"loss": 0.0923,
|
| 1502 |
+
"step": 12000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 9.8,
|
| 1506 |
+
"learning_rate": 9.764035801464606e-07,
|
| 1507 |
+
"loss": 0.0656,
|
| 1508 |
+
"step": 12050
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 9.85,
|
| 1512 |
+
"learning_rate": 7.729861676159479e-07,
|
| 1513 |
+
"loss": 0.0633,
|
| 1514 |
+
"step": 12100
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 9.89,
|
| 1518 |
+
"learning_rate": 5.695687550854353e-07,
|
| 1519 |
+
"loss": 0.0727,
|
| 1520 |
+
"step": 12150
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 9.93,
|
| 1524 |
+
"learning_rate": 3.661513425549227e-07,
|
| 1525 |
+
"loss": 0.0921,
|
| 1526 |
+
"step": 12200
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 9.97,
|
| 1530 |
+
"learning_rate": 1.627339300244101e-07,
|
| 1531 |
+
"loss": 0.0661,
|
| 1532 |
+
"step": 12250
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 10.0,
|
| 1536 |
+
"eval_exact_match": 74.47275922671353,
|
| 1537 |
+
"eval_f1": 88.1676160670247,
|
| 1538 |
+
"step": 12290
|
| 1539 |
+
}
|
| 1540 |
+
],
|
| 1541 |
+
"max_steps": 12290,
|
| 1542 |
+
"num_train_epochs": 10,
|
| 1543 |
+
"total_flos": 1.4981977109796864e+16,
|
| 1544 |
+
"trial_name": null,
|
| 1545 |
+
"trial_params": null
|
| 1546 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feaef5ded1b075687fd58ab68e24c1a08110481dd168a9ececaa50cdc6420080
|
| 3 |
+
size 2607
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|