Upload 12 files
Browse files- added_tokens.json +3 -0
- config.json +35 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +1159 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForMultipleChoice"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 1024,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.33.1",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f3a9520e6ea139162eaac1cfb3aabcc1cbd12aba9c9f6225cb361006c83863c
|
| 3 |
+
size 617320389
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:883b4689a2a1b1f3a1b0456d1362de82eb814c802004fa164275cf3565e1672b
|
| 3 |
+
size 1740387701
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00b0e5ba20b05bd7d2250c478388b604d376884dd33fc0a9241635a5db65c8ff
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16f603b3addff29dbecae32d0ae6971e16dd9bf0828145ba9e4f197635c7d613
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9083333333333333,
|
| 3 |
+
"best_model_checkpoint": "deverta_60k_fillna_val100/checkpoint-7600",
|
| 4 |
+
"epoch": 1.9984551415846303,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 7600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1.717791411042945e-06,
|
| 14 |
+
"loss": 1.615,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"eval_loss": 1.6094433069229126,
|
| 20 |
+
"eval_map@3": 0.36999999999999994,
|
| 21 |
+
"eval_runtime": 3.9269,
|
| 22 |
+
"eval_samples_per_second": 25.465,
|
| 23 |
+
"eval_steps_per_second": 25.465,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"learning_rate": 3.470639789658195e-06,
|
| 29 |
+
"loss": 1.615,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"eval_loss": 1.6090234518051147,
|
| 35 |
+
"eval_map@3": 0.5433333333333333,
|
| 36 |
+
"eval_runtime": 3.9569,
|
| 37 |
+
"eval_samples_per_second": 25.272,
|
| 38 |
+
"eval_steps_per_second": 25.272,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 5.2234881682734454e-06,
|
| 44 |
+
"loss": 1.6106,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"eval_loss": 1.6112011671066284,
|
| 50 |
+
"eval_map@3": 0.6250000000000001,
|
| 51 |
+
"eval_runtime": 4.2374,
|
| 52 |
+
"eval_samples_per_second": 23.6,
|
| 53 |
+
"eval_steps_per_second": 23.6,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.11,
|
| 58 |
+
"learning_rate": 6.976336546888695e-06,
|
| 59 |
+
"loss": 1.4954,
|
| 60 |
+
"step": 400
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.11,
|
| 64 |
+
"eval_loss": 1.2830108404159546,
|
| 65 |
+
"eval_map@3": 0.755,
|
| 66 |
+
"eval_runtime": 4.1043,
|
| 67 |
+
"eval_samples_per_second": 24.364,
|
| 68 |
+
"eval_steps_per_second": 24.364,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 8.729184925503945e-06,
|
| 74 |
+
"loss": 1.0519,
|
| 75 |
+
"step": 500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.13,
|
| 79 |
+
"eval_loss": 0.8515128493309021,
|
| 80 |
+
"eval_map@3": 0.8183333333333335,
|
| 81 |
+
"eval_runtime": 4.0929,
|
| 82 |
+
"eval_samples_per_second": 24.432,
|
| 83 |
+
"eval_steps_per_second": 24.432,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.16,
|
| 88 |
+
"learning_rate": 1.0482033304119195e-05,
|
| 89 |
+
"loss": 0.8846,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.16,
|
| 94 |
+
"eval_loss": 0.7408291101455688,
|
| 95 |
+
"eval_map@3": 0.8366666666666667,
|
| 96 |
+
"eval_runtime": 4.1086,
|
| 97 |
+
"eval_samples_per_second": 24.339,
|
| 98 |
+
"eval_steps_per_second": 24.339,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"learning_rate": 1.2234881682734446e-05,
|
| 104 |
+
"loss": 0.8651,
|
| 105 |
+
"step": 700
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.18,
|
| 109 |
+
"eval_loss": 0.7649513483047485,
|
| 110 |
+
"eval_map@3": 0.8633333333333334,
|
| 111 |
+
"eval_runtime": 4.0899,
|
| 112 |
+
"eval_samples_per_second": 24.45,
|
| 113 |
+
"eval_steps_per_second": 24.45,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21,
|
| 118 |
+
"learning_rate": 1.3987730061349694e-05,
|
| 119 |
+
"loss": 0.8166,
|
| 120 |
+
"step": 800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.21,
|
| 124 |
+
"eval_loss": 0.7141894698143005,
|
| 125 |
+
"eval_map@3": 0.8583333333333334,
|
| 126 |
+
"eval_runtime": 4.1369,
|
| 127 |
+
"eval_samples_per_second": 24.173,
|
| 128 |
+
"eval_steps_per_second": 24.173,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24,
|
| 133 |
+
"learning_rate": 1.5740578439964945e-05,
|
| 134 |
+
"loss": 0.8283,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24,
|
| 139 |
+
"eval_loss": 0.6661826968193054,
|
| 140 |
+
"eval_map@3": 0.845,
|
| 141 |
+
"eval_runtime": 4.1543,
|
| 142 |
+
"eval_samples_per_second": 24.071,
|
| 143 |
+
"eval_steps_per_second": 24.071,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.26,
|
| 148 |
+
"learning_rate": 1.7493426818580194e-05,
|
| 149 |
+
"loss": 0.7593,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26,
|
| 154 |
+
"eval_loss": 0.6564372181892395,
|
| 155 |
+
"eval_map@3": 0.8483333333333334,
|
| 156 |
+
"eval_runtime": 4.076,
|
| 157 |
+
"eval_samples_per_second": 24.534,
|
| 158 |
+
"eval_steps_per_second": 24.534,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.29,
|
| 163 |
+
"learning_rate": 1.9246275197195444e-05,
|
| 164 |
+
"loss": 0.7401,
|
| 165 |
+
"step": 1100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.29,
|
| 169 |
+
"eval_loss": 0.6686395406723022,
|
| 170 |
+
"eval_map@3": 0.85,
|
| 171 |
+
"eval_runtime": 4.0963,
|
| 172 |
+
"eval_samples_per_second": 24.412,
|
| 173 |
+
"eval_steps_per_second": 24.412,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.32,
|
| 178 |
+
"learning_rate": 1.9998531353530498e-05,
|
| 179 |
+
"loss": 0.7791,
|
| 180 |
+
"step": 1200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.32,
|
| 184 |
+
"eval_loss": 0.608403742313385,
|
| 185 |
+
"eval_map@3": 0.875,
|
| 186 |
+
"eval_runtime": 4.1272,
|
| 187 |
+
"eval_samples_per_second": 24.229,
|
| 188 |
+
"eval_steps_per_second": 24.229,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.34,
|
| 193 |
+
"learning_rate": 1.998860488949288e-05,
|
| 194 |
+
"loss": 0.7868,
|
| 195 |
+
"step": 1300
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.34,
|
| 199 |
+
"eval_loss": 0.6702239513397217,
|
| 200 |
+
"eval_map@3": 0.87,
|
| 201 |
+
"eval_runtime": 4.0746,
|
| 202 |
+
"eval_samples_per_second": 24.542,
|
| 203 |
+
"eval_steps_per_second": 24.542,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.37,
|
| 208 |
+
"learning_rate": 1.9969323231985812e-05,
|
| 209 |
+
"loss": 0.7567,
|
| 210 |
+
"step": 1400
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.37,
|
| 214 |
+
"eval_loss": 0.6087381839752197,
|
| 215 |
+
"eval_map@3": 0.8683333333333334,
|
| 216 |
+
"eval_runtime": 3.8341,
|
| 217 |
+
"eval_samples_per_second": 26.081,
|
| 218 |
+
"eval_steps_per_second": 26.081,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.39,
|
| 223 |
+
"learning_rate": 1.994070443995129e-05,
|
| 224 |
+
"loss": 0.7488,
|
| 225 |
+
"step": 1500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.39,
|
| 229 |
+
"eval_loss": 0.6629943251609802,
|
| 230 |
+
"eval_map@3": 0.8616666666666667,
|
| 231 |
+
"eval_runtime": 4.0681,
|
| 232 |
+
"eval_samples_per_second": 24.581,
|
| 233 |
+
"eval_steps_per_second": 24.581,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.42,
|
| 238 |
+
"learning_rate": 1.990277531736638e-05,
|
| 239 |
+
"loss": 0.7833,
|
| 240 |
+
"step": 1600
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.42,
|
| 244 |
+
"eval_loss": 0.592115581035614,
|
| 245 |
+
"eval_map@3": 0.8566666666666667,
|
| 246 |
+
"eval_runtime": 4.0797,
|
| 247 |
+
"eval_samples_per_second": 24.512,
|
| 248 |
+
"eval_steps_per_second": 24.512,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.45,
|
| 253 |
+
"learning_rate": 1.9855571388138954e-05,
|
| 254 |
+
"loss": 0.7706,
|
| 255 |
+
"step": 1700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"eval_loss": 0.6199390888214111,
|
| 260 |
+
"eval_map@3": 0.8733333333333333,
|
| 261 |
+
"eval_runtime": 3.9265,
|
| 262 |
+
"eval_samples_per_second": 25.468,
|
| 263 |
+
"eval_steps_per_second": 25.468,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.47,
|
| 268 |
+
"learning_rate": 1.979913686283649e-05,
|
| 269 |
+
"loss": 0.7422,
|
| 270 |
+
"step": 1800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.47,
|
| 274 |
+
"eval_loss": 0.6019750237464905,
|
| 275 |
+
"eval_map@3": 0.8833333333333334,
|
| 276 |
+
"eval_runtime": 3.9986,
|
| 277 |
+
"eval_samples_per_second": 25.009,
|
| 278 |
+
"eval_steps_per_second": 25.009,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.5,
|
| 283 |
+
"learning_rate": 1.9733524597279037e-05,
|
| 284 |
+
"loss": 0.7129,
|
| 285 |
+
"step": 1900
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.5,
|
| 289 |
+
"eval_loss": 0.5683853626251221,
|
| 290 |
+
"eval_map@3": 0.8766666666666666,
|
| 291 |
+
"eval_runtime": 4.0628,
|
| 292 |
+
"eval_samples_per_second": 24.613,
|
| 293 |
+
"eval_steps_per_second": 24.613,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.53,
|
| 298 |
+
"learning_rate": 1.965879604303516e-05,
|
| 299 |
+
"loss": 0.753,
|
| 300 |
+
"step": 2000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.53,
|
| 304 |
+
"eval_loss": 0.536411464214325,
|
| 305 |
+
"eval_map@3": 0.8733333333333333,
|
| 306 |
+
"eval_runtime": 3.989,
|
| 307 |
+
"eval_samples_per_second": 25.069,
|
| 308 |
+
"eval_steps_per_second": 25.069,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.55,
|
| 313 |
+
"learning_rate": 1.957502118986723e-05,
|
| 314 |
+
"loss": 0.7057,
|
| 315 |
+
"step": 2100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.55,
|
| 319 |
+
"eval_loss": 0.5491364002227783,
|
| 320 |
+
"eval_map@3": 0.8583333333333333,
|
| 321 |
+
"eval_runtime": 3.9154,
|
| 322 |
+
"eval_samples_per_second": 25.54,
|
| 323 |
+
"eval_steps_per_second": 25.54,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.58,
|
| 328 |
+
"learning_rate": 1.9482278500179953e-05,
|
| 329 |
+
"loss": 0.73,
|
| 330 |
+
"step": 2200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.58,
|
| 334 |
+
"eval_loss": 0.5584819316864014,
|
| 335 |
+
"eval_map@3": 0.8766666666666667,
|
| 336 |
+
"eval_runtime": 3.9164,
|
| 337 |
+
"eval_samples_per_second": 25.534,
|
| 338 |
+
"eval_steps_per_second": 25.534,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6,
|
| 343 |
+
"learning_rate": 1.9380654835533523e-05,
|
| 344 |
+
"loss": 0.6898,
|
| 345 |
+
"step": 2300
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6,
|
| 349 |
+
"eval_loss": 0.5588586330413818,
|
| 350 |
+
"eval_map@3": 0.88,
|
| 351 |
+
"eval_runtime": 3.8846,
|
| 352 |
+
"eval_samples_per_second": 25.743,
|
| 353 |
+
"eval_steps_per_second": 25.743,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.63,
|
| 358 |
+
"learning_rate": 1.9270245375290263e-05,
|
| 359 |
+
"loss": 0.6842,
|
| 360 |
+
"step": 2400
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.63,
|
| 364 |
+
"eval_loss": 0.573777437210083,
|
| 365 |
+
"eval_map@3": 0.8683333333333334,
|
| 366 |
+
"eval_runtime": 4.0374,
|
| 367 |
+
"eval_samples_per_second": 24.768,
|
| 368 |
+
"eval_steps_per_second": 24.768,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.66,
|
| 373 |
+
"learning_rate": 1.9151153527470895e-05,
|
| 374 |
+
"loss": 0.728,
|
| 375 |
+
"step": 2500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.66,
|
| 379 |
+
"eval_loss": 0.5937029123306274,
|
| 380 |
+
"eval_map@3": 0.8866666666666666,
|
| 381 |
+
"eval_runtime": 3.9109,
|
| 382 |
+
"eval_samples_per_second": 25.57,
|
| 383 |
+
"eval_steps_per_second": 25.57,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.68,
|
| 388 |
+
"learning_rate": 1.902349083190399e-05,
|
| 389 |
+
"loss": 0.7047,
|
| 390 |
+
"step": 2600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.68,
|
| 394 |
+
"eval_loss": 0.5620361566543579,
|
| 395 |
+
"eval_map@3": 0.885,
|
| 396 |
+
"eval_runtime": 3.9171,
|
| 397 |
+
"eval_samples_per_second": 25.529,
|
| 398 |
+
"eval_steps_per_second": 25.529,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.71,
|
| 403 |
+
"learning_rate": 1.888737685575924e-05,
|
| 404 |
+
"loss": 0.7554,
|
| 405 |
+
"step": 2700
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.71,
|
| 409 |
+
"eval_loss": 0.5551219582557678,
|
| 410 |
+
"eval_map@3": 0.8883333333333333,
|
| 411 |
+
"eval_runtime": 3.9451,
|
| 412 |
+
"eval_samples_per_second": 25.348,
|
| 413 |
+
"eval_steps_per_second": 25.348,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.74,
|
| 418 |
+
"learning_rate": 1.874293908156247e-05,
|
| 419 |
+
"loss": 0.7252,
|
| 420 |
+
"step": 2800
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.74,
|
| 424 |
+
"eval_loss": 0.5565034747123718,
|
| 425 |
+
"eval_map@3": 0.8983333333333331,
|
| 426 |
+
"eval_runtime": 4.1016,
|
| 427 |
+
"eval_samples_per_second": 24.381,
|
| 428 |
+
"eval_steps_per_second": 24.381,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.76,
|
| 433 |
+
"learning_rate": 1.8590312787797196e-05,
|
| 434 |
+
"loss": 0.7245,
|
| 435 |
+
"step": 2900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.76,
|
| 439 |
+
"eval_loss": 0.5758660435676575,
|
| 440 |
+
"eval_map@3": 0.8816666666666667,
|
| 441 |
+
"eval_runtime": 3.9367,
|
| 442 |
+
"eval_samples_per_second": 25.402,
|
| 443 |
+
"eval_steps_per_second": 25.402,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.79,
|
| 448 |
+
"learning_rate": 1.8429640922204614e-05,
|
| 449 |
+
"loss": 0.725,
|
| 450 |
+
"step": 3000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.79,
|
| 454 |
+
"eval_loss": 0.5699021816253662,
|
| 455 |
+
"eval_map@3": 0.8883333333333333,
|
| 456 |
+
"eval_runtime": 3.8274,
|
| 457 |
+
"eval_samples_per_second": 26.128,
|
| 458 |
+
"eval_steps_per_second": 26.128,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.82,
|
| 463 |
+
"learning_rate": 1.8261073967900676e-05,
|
| 464 |
+
"loss": 0.6983,
|
| 465 |
+
"step": 3100
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.82,
|
| 469 |
+
"eval_loss": 0.5696993470191956,
|
| 470 |
+
"eval_map@3": 0.8883333333333333,
|
| 471 |
+
"eval_runtime": 3.8632,
|
| 472 |
+
"eval_samples_per_second": 25.885,
|
| 473 |
+
"eval_steps_per_second": 25.885,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.84,
|
| 478 |
+
"learning_rate": 1.80847698024356e-05,
|
| 479 |
+
"loss": 0.7055,
|
| 480 |
+
"step": 3200
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.84,
|
| 484 |
+
"eval_loss": 0.5589382648468018,
|
| 485 |
+
"eval_map@3": 0.8933333333333333,
|
| 486 |
+
"eval_runtime": 4.205,
|
| 487 |
+
"eval_samples_per_second": 23.781,
|
| 488 |
+
"eval_steps_per_second": 23.781,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.87,
|
| 493 |
+
"learning_rate": 1.790089354992788e-05,
|
| 494 |
+
"loss": 0.7091,
|
| 495 |
+
"step": 3300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.87,
|
| 499 |
+
"eval_loss": 0.5517598986625671,
|
| 500 |
+
"eval_map@3": 0.8883333333333333,
|
| 501 |
+
"eval_runtime": 4.2776,
|
| 502 |
+
"eval_samples_per_second": 23.378,
|
| 503 |
+
"eval_steps_per_second": 23.378,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.89,
|
| 508 |
+
"learning_rate": 1.7711566234443824e-05,
|
| 509 |
+
"loss": 0.7128,
|
| 510 |
+
"step": 3400
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.89,
|
| 514 |
+
"eval_loss": 0.5628377795219421,
|
| 515 |
+
"eval_map@3": 0.8866666666666667,
|
| 516 |
+
"eval_runtime": 4.1647,
|
| 517 |
+
"eval_samples_per_second": 24.011,
|
| 518 |
+
"eval_steps_per_second": 24.011,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.92,
|
| 523 |
+
"learning_rate": 1.751314068469163e-05,
|
| 524 |
+
"loss": 0.7465,
|
| 525 |
+
"step": 3500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.92,
|
| 529 |
+
"eval_loss": 0.5919340252876282,
|
| 530 |
+
"eval_map@3": 0.8833333333333333,
|
| 531 |
+
"eval_runtime": 4.0418,
|
| 532 |
+
"eval_samples_per_second": 24.742,
|
| 533 |
+
"eval_steps_per_second": 24.742,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.95,
|
| 538 |
+
"learning_rate": 1.730767842806733e-05,
|
| 539 |
+
"loss": 0.708,
|
| 540 |
+
"step": 3600
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.95,
|
| 544 |
+
"eval_loss": 0.554470419883728,
|
| 545 |
+
"eval_map@3": 0.895,
|
| 546 |
+
"eval_runtime": 4.0703,
|
| 547 |
+
"eval_samples_per_second": 24.568,
|
| 548 |
+
"eval_steps_per_second": 24.568,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.97,
|
| 553 |
+
"learning_rate": 1.709537189776684e-05,
|
| 554 |
+
"loss": 0.7017,
|
| 555 |
+
"step": 3700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.97,
|
| 559 |
+
"eval_loss": 0.5175462365150452,
|
| 560 |
+
"eval_map@3": 0.895,
|
| 561 |
+
"eval_runtime": 4.1999,
|
| 562 |
+
"eval_samples_per_second": 23.81,
|
| 563 |
+
"eval_steps_per_second": 23.81,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.0,
|
| 568 |
+
"learning_rate": 1.6876419937241033e-05,
|
| 569 |
+
"loss": 0.7,
|
| 570 |
+
"step": 3800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0,
|
| 574 |
+
"eval_loss": 0.5037916302680969,
|
| 575 |
+
"eval_map@3": 0.8916666666666667,
|
| 576 |
+
"eval_runtime": 4.1774,
|
| 577 |
+
"eval_samples_per_second": 23.938,
|
| 578 |
+
"eval_steps_per_second": 23.938,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.03,
|
| 583 |
+
"learning_rate": 1.665102761396169e-05,
|
| 584 |
+
"loss": 0.5923,
|
| 585 |
+
"step": 3900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.03,
|
| 589 |
+
"eval_loss": 0.48426902294158936,
|
| 590 |
+
"eval_map@3": 0.8916666666666667,
|
| 591 |
+
"eval_runtime": 4.139,
|
| 592 |
+
"eval_samples_per_second": 24.16,
|
| 593 |
+
"eval_steps_per_second": 24.16,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.05,
|
| 598 |
+
"learning_rate": 1.641940602735802e-05,
|
| 599 |
+
"loss": 0.594,
|
| 600 |
+
"step": 4000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.05,
|
| 604 |
+
"eval_loss": 0.48445701599121094,
|
| 605 |
+
"eval_map@3": 0.895,
|
| 606 |
+
"eval_runtime": 4.2445,
|
| 607 |
+
"eval_samples_per_second": 23.56,
|
| 608 |
+
"eval_steps_per_second": 23.56,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.08,
|
| 613 |
+
"learning_rate": 1.6181772111103775e-05,
|
| 614 |
+
"loss": 0.6075,
|
| 615 |
+
"step": 4100
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.08,
|
| 619 |
+
"eval_loss": 0.5103535652160645,
|
| 620 |
+
"eval_map@3": 0.8899999999999999,
|
| 621 |
+
"eval_runtime": 4.059,
|
| 622 |
+
"eval_samples_per_second": 24.636,
|
| 623 |
+
"eval_steps_per_second": 24.636,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.1,
|
| 628 |
+
"learning_rate": 1.5938348429940095e-05,
|
| 629 |
+
"loss": 0.5226,
|
| 630 |
+
"step": 4200
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.1,
|
| 634 |
+
"eval_loss": 0.5009714961051941,
|
| 635 |
+
"eval_map@3": 0.8883333333333333,
|
| 636 |
+
"eval_runtime": 4.0879,
|
| 637 |
+
"eval_samples_per_second": 24.463,
|
| 638 |
+
"eval_steps_per_second": 24.463,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.13,
|
| 643 |
+
"learning_rate": 1.568936297122432e-05,
|
| 644 |
+
"loss": 0.5886,
|
| 645 |
+
"step": 4300
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.13,
|
| 649 |
+
"eval_loss": 0.49200114607810974,
|
| 650 |
+
"eval_map@3": 0.9033333333333333,
|
| 651 |
+
"eval_runtime": 4.1867,
|
| 652 |
+
"eval_samples_per_second": 23.885,
|
| 653 |
+
"eval_steps_per_second": 23.885,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.16,
|
| 658 |
+
"learning_rate": 1.543504893140011e-05,
|
| 659 |
+
"loss": 0.5619,
|
| 660 |
+
"step": 4400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.16,
|
| 664 |
+
"eval_loss": 0.49913597106933594,
|
| 665 |
+
"eval_map@3": 0.89,
|
| 666 |
+
"eval_runtime": 4.0492,
|
| 667 |
+
"eval_samples_per_second": 24.696,
|
| 668 |
+
"eval_steps_per_second": 24.696,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.18,
|
| 673 |
+
"learning_rate": 1.517564449758878e-05,
|
| 674 |
+
"loss": 0.6017,
|
| 675 |
+
"step": 4500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.18,
|
| 679 |
+
"eval_loss": 0.4905971586704254,
|
| 680 |
+
"eval_map@3": 0.9033333333333333,
|
| 681 |
+
"eval_runtime": 4.0275,
|
| 682 |
+
"eval_samples_per_second": 24.83,
|
| 683 |
+
"eval_steps_per_second": 24.83,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.21,
|
| 688 |
+
"learning_rate": 1.4911392624506427e-05,
|
| 689 |
+
"loss": 0.534,
|
| 690 |
+
"step": 4600
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.21,
|
| 694 |
+
"eval_loss": 0.4901256263256073,
|
| 695 |
+
"eval_map@3": 0.89,
|
| 696 |
+
"eval_runtime": 5.205,
|
| 697 |
+
"eval_samples_per_second": 19.212,
|
| 698 |
+
"eval_steps_per_second": 19.212,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.24,
|
| 703 |
+
"learning_rate": 1.4642540806915802e-05,
|
| 704 |
+
"loss": 0.5914,
|
| 705 |
+
"step": 4700
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.24,
|
| 709 |
+
"eval_loss": 0.4857093095779419,
|
| 710 |
+
"eval_map@3": 0.8916666666666666,
|
| 711 |
+
"eval_runtime": 4.357,
|
| 712 |
+
"eval_samples_per_second": 22.952,
|
| 713 |
+
"eval_steps_per_second": 22.952,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.26,
|
| 718 |
+
"learning_rate": 1.4369340847826037e-05,
|
| 719 |
+
"loss": 0.6155,
|
| 720 |
+
"step": 4800
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.26,
|
| 724 |
+
"eval_loss": 0.49262702465057373,
|
| 725 |
+
"eval_map@3": 0.8849999999999999,
|
| 726 |
+
"eval_runtime": 4.3241,
|
| 727 |
+
"eval_samples_per_second": 23.126,
|
| 728 |
+
"eval_steps_per_second": 23.126,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.29,
|
| 733 |
+
"learning_rate": 1.4092048622657309e-05,
|
| 734 |
+
"loss": 0.5779,
|
| 735 |
+
"step": 4900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.29,
|
| 739 |
+
"eval_loss": 0.4796687960624695,
|
| 740 |
+
"eval_map@3": 0.8849999999999999,
|
| 741 |
+
"eval_runtime": 4.3677,
|
| 742 |
+
"eval_samples_per_second": 22.895,
|
| 743 |
+
"eval_steps_per_second": 22.895,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.31,
|
| 748 |
+
"learning_rate": 1.3810923839591368e-05,
|
| 749 |
+
"loss": 0.6144,
|
| 750 |
+
"step": 5000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.31,
|
| 754 |
+
"eval_loss": 0.4864266514778137,
|
| 755 |
+
"eval_map@3": 0.8916666666666666,
|
| 756 |
+
"eval_runtime": 4.1788,
|
| 757 |
+
"eval_samples_per_second": 23.93,
|
| 758 |
+
"eval_steps_per_second": 23.93,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.34,
|
| 763 |
+
"learning_rate": 1.3526229796332322e-05,
|
| 764 |
+
"loss": 0.5532,
|
| 765 |
+
"step": 5100
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.34,
|
| 769 |
+
"eval_loss": 0.5059311389923096,
|
| 770 |
+
"eval_map@3": 0.9033333333333334,
|
| 771 |
+
"eval_runtime": 4.1314,
|
| 772 |
+
"eval_samples_per_second": 24.205,
|
| 773 |
+
"eval_steps_per_second": 24.205,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.37,
|
| 778 |
+
"learning_rate": 1.3238233133505538e-05,
|
| 779 |
+
"loss": 0.5238,
|
| 780 |
+
"step": 5200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.37,
|
| 784 |
+
"eval_loss": 0.5035010576248169,
|
| 785 |
+
"eval_map@3": 0.8933333333333334,
|
| 786 |
+
"eval_runtime": 4.0704,
|
| 787 |
+
"eval_samples_per_second": 24.568,
|
| 788 |
+
"eval_steps_per_second": 24.568,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.39,
|
| 793 |
+
"learning_rate": 1.2947203584925607e-05,
|
| 794 |
+
"loss": 0.5993,
|
| 795 |
+
"step": 5300
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.39,
|
| 799 |
+
"eval_loss": 0.5209221839904785,
|
| 800 |
+
"eval_map@3": 0.8983333333333334,
|
| 801 |
+
"eval_runtime": 4.0192,
|
| 802 |
+
"eval_samples_per_second": 24.881,
|
| 803 |
+
"eval_steps_per_second": 24.881,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.42,
|
| 808 |
+
"learning_rate": 1.2653413724967272e-05,
|
| 809 |
+
"loss": 0.5443,
|
| 810 |
+
"step": 5400
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.42,
|
| 814 |
+
"eval_loss": 0.5166578888893127,
|
| 815 |
+
"eval_map@3": 0.8883333333333334,
|
| 816 |
+
"eval_runtime": 4.0162,
|
| 817 |
+
"eval_samples_per_second": 24.899,
|
| 818 |
+
"eval_steps_per_second": 24.899,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.45,
|
| 823 |
+
"learning_rate": 1.2357138713275916e-05,
|
| 824 |
+
"loss": 0.5564,
|
| 825 |
+
"step": 5500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.45,
|
| 829 |
+
"eval_loss": 0.50209641456604,
|
| 830 |
+
"eval_map@3": 0.8883333333333334,
|
| 831 |
+
"eval_runtime": 4.0769,
|
| 832 |
+
"eval_samples_per_second": 24.529,
|
| 833 |
+
"eval_steps_per_second": 24.529,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.47,
|
| 838 |
+
"learning_rate": 1.2058656037056733e-05,
|
| 839 |
+
"loss": 0.5962,
|
| 840 |
+
"step": 5600
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.47,
|
| 844 |
+
"eval_loss": 0.5111860632896423,
|
| 845 |
+
"eval_map@3": 0.8933333333333334,
|
| 846 |
+
"eval_runtime": 4.1245,
|
| 847 |
+
"eval_samples_per_second": 24.245,
|
| 848 |
+
"eval_steps_per_second": 24.245,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.5,
|
| 853 |
+
"learning_rate": 1.1758245251183917e-05,
|
| 854 |
+
"loss": 0.5824,
|
| 855 |
+
"step": 5700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.5,
|
| 859 |
+
"eval_loss": 0.5007131695747375,
|
| 860 |
+
"eval_map@3": 0.8966666666666666,
|
| 861 |
+
"eval_runtime": 4.0577,
|
| 862 |
+
"eval_samples_per_second": 24.644,
|
| 863 |
+
"eval_steps_per_second": 24.644,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.53,
|
| 868 |
+
"learning_rate": 1.1456187716373334e-05,
|
| 869 |
+
"loss": 0.5327,
|
| 870 |
+
"step": 5800
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.53,
|
| 874 |
+
"eval_loss": 0.5062887072563171,
|
| 875 |
+
"eval_map@3": 0.8883333333333334,
|
| 876 |
+
"eval_runtime": 3.9467,
|
| 877 |
+
"eval_samples_per_second": 25.337,
|
| 878 |
+
"eval_steps_per_second": 25.337,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.55,
|
| 883 |
+
"learning_rate": 1.1152766335663825e-05,
|
| 884 |
+
"loss": 0.5649,
|
| 885 |
+
"step": 5900
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.55,
|
| 889 |
+
"eval_loss": 0.5016913414001465,
|
| 890 |
+
"eval_map@3": 0.8883333333333334,
|
| 891 |
+
"eval_runtime": 4.1523,
|
| 892 |
+
"eval_samples_per_second": 24.083,
|
| 893 |
+
"eval_steps_per_second": 24.083,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.58,
|
| 898 |
+
"learning_rate": 1.0848265289454028e-05,
|
| 899 |
+
"loss": 0.5717,
|
| 900 |
+
"step": 6000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.58,
|
| 904 |
+
"eval_loss": 0.4974103271961212,
|
| 905 |
+
"eval_map@3": 0.9033333333333334,
|
| 906 |
+
"eval_runtime": 4.0909,
|
| 907 |
+
"eval_samples_per_second": 24.444,
|
| 908 |
+
"eval_steps_per_second": 24.444,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.6,
|
| 913 |
+
"learning_rate": 1.054296976934281e-05,
|
| 914 |
+
"loss": 0.5737,
|
| 915 |
+
"step": 6100
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.6,
|
| 919 |
+
"eval_loss": 0.49186939001083374,
|
| 920 |
+
"eval_map@3": 0.8933333333333334,
|
| 921 |
+
"eval_runtime": 4.2135,
|
| 922 |
+
"eval_samples_per_second": 23.733,
|
| 923 |
+
"eval_steps_per_second": 23.733,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.63,
|
| 928 |
+
"learning_rate": 1.0237165711022661e-05,
|
| 929 |
+
"loss": 0.5351,
|
| 930 |
+
"step": 6200
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.63,
|
| 934 |
+
"eval_loss": 0.4999094009399414,
|
| 935 |
+
"eval_map@3": 0.895,
|
| 936 |
+
"eval_runtime": 3.9962,
|
| 937 |
+
"eval_samples_per_second": 25.024,
|
| 938 |
+
"eval_steps_per_second": 25.024,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.66,
|
| 943 |
+
"learning_rate": 9.934199946768965e-06,
|
| 944 |
+
"loss": 0.5341,
|
| 945 |
+
"step": 6300
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.66,
|
| 949 |
+
"eval_loss": 0.4991361200809479,
|
| 950 |
+
"eval_map@3": 0.9016666666666667,
|
| 951 |
+
"eval_runtime": 4.1686,
|
| 952 |
+
"eval_samples_per_second": 23.989,
|
| 953 |
+
"eval_steps_per_second": 23.989,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.68,
|
| 958 |
+
"learning_rate": 9.628236192287725e-06,
|
| 959 |
+
"loss": 0.5501,
|
| 960 |
+
"step": 6400
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.68,
|
| 964 |
+
"eval_loss": 0.5340888500213623,
|
| 965 |
+
"eval_map@3": 0.8866666666666667,
|
| 966 |
+
"eval_runtime": 4.1621,
|
| 967 |
+
"eval_samples_per_second": 24.027,
|
| 968 |
+
"eval_steps_per_second": 24.027,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.71,
|
| 973 |
+
"learning_rate": 9.32262062680631e-06,
|
| 974 |
+
"loss": 0.5552,
|
| 975 |
+
"step": 6500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.71,
|
| 979 |
+
"eval_loss": 0.4900314211845398,
|
| 980 |
+
"eval_map@3": 0.9016666666666667,
|
| 981 |
+
"eval_runtime": 4.0101,
|
| 982 |
+
"eval_samples_per_second": 24.937,
|
| 983 |
+
"eval_steps_per_second": 24.937,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.74,
|
| 988 |
+
"learning_rate": 9.017639485767398e-06,
|
| 989 |
+
"loss": 0.5362,
|
| 990 |
+
"step": 6600
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.74,
|
| 994 |
+
"eval_loss": 0.5052759647369385,
|
| 995 |
+
"eval_map@3": 0.905,
|
| 996 |
+
"eval_runtime": 4.083,
|
| 997 |
+
"eval_samples_per_second": 24.492,
|
| 998 |
+
"eval_steps_per_second": 24.492,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.76,
|
| 1003 |
+
"learning_rate": 8.713578410420254e-06,
|
| 1004 |
+
"loss": 0.5474,
|
| 1005 |
+
"step": 6700
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.76,
|
| 1009 |
+
"eval_loss": 0.5121599435806274,
|
| 1010 |
+
"eval_map@3": 0.905,
|
| 1011 |
+
"eval_runtime": 3.9444,
|
| 1012 |
+
"eval_samples_per_second": 25.352,
|
| 1013 |
+
"eval_steps_per_second": 25.352,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.79,
|
| 1018 |
+
"learning_rate": 8.41072218029293e-06,
|
| 1019 |
+
"loss": 0.5134,
|
| 1020 |
+
"step": 6800
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.79,
|
| 1024 |
+
"eval_loss": 0.510312020778656,
|
| 1025 |
+
"eval_map@3": 0.8983333333333334,
|
| 1026 |
+
"eval_runtime": 4.0574,
|
| 1027 |
+
"eval_samples_per_second": 24.647,
|
| 1028 |
+
"eval_steps_per_second": 24.647,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.81,
|
| 1033 |
+
"learning_rate": 8.1093544464716e-06,
|
| 1034 |
+
"loss": 0.5454,
|
| 1035 |
+
"step": 6900
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.81,
|
| 1039 |
+
"eval_loss": 0.5062999725341797,
|
| 1040 |
+
"eval_map@3": 0.9,
|
| 1041 |
+
"eval_runtime": 4.0245,
|
| 1042 |
+
"eval_samples_per_second": 24.848,
|
| 1043 |
+
"eval_steps_per_second": 24.848,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.84,
|
| 1048 |
+
"learning_rate": 7.809757465936754e-06,
|
| 1049 |
+
"loss": 0.5726,
|
| 1050 |
+
"step": 7000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.84,
|
| 1054 |
+
"eval_loss": 0.5135546326637268,
|
| 1055 |
+
"eval_map@3": 0.905,
|
| 1056 |
+
"eval_runtime": 4.053,
|
| 1057 |
+
"eval_samples_per_second": 24.673,
|
| 1058 |
+
"eval_steps_per_second": 24.673,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.87,
|
| 1063 |
+
"learning_rate": 7.512211837205075e-06,
|
| 1064 |
+
"loss": 0.5173,
|
| 1065 |
+
"step": 7100
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.87,
|
| 1069 |
+
"eval_loss": 0.49537014961242676,
|
| 1070 |
+
"eval_map@3": 0.9,
|
| 1071 |
+
"eval_runtime": 4.1604,
|
| 1072 |
+
"eval_samples_per_second": 24.036,
|
| 1073 |
+
"eval_steps_per_second": 24.036,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.89,
|
| 1078 |
+
"learning_rate": 7.216996237524646e-06,
|
| 1079 |
+
"loss": 0.5118,
|
| 1080 |
+
"step": 7200
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.89,
|
| 1084 |
+
"eval_loss": 0.5108374357223511,
|
| 1085 |
+
"eval_map@3": 0.9066666666666667,
|
| 1086 |
+
"eval_runtime": 4.0629,
|
| 1087 |
+
"eval_samples_per_second": 24.613,
|
| 1088 |
+
"eval_steps_per_second": 24.613,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.92,
|
| 1093 |
+
"learning_rate": 6.924387161869565e-06,
|
| 1094 |
+
"loss": 0.5372,
|
| 1095 |
+
"step": 7300
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.92,
|
| 1099 |
+
"eval_loss": 0.5062543749809265,
|
| 1100 |
+
"eval_map@3": 0.8866666666666666,
|
| 1101 |
+
"eval_runtime": 3.9525,
|
| 1102 |
+
"eval_samples_per_second": 25.3,
|
| 1103 |
+
"eval_steps_per_second": 25.3,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.95,
|
| 1108 |
+
"learning_rate": 6.634658663978463e-06,
|
| 1109 |
+
"loss": 0.4689,
|
| 1110 |
+
"step": 7400
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.95,
|
| 1114 |
+
"eval_loss": 0.5014258623123169,
|
| 1115 |
+
"eval_map@3": 0.8933333333333333,
|
| 1116 |
+
"eval_runtime": 4.084,
|
| 1117 |
+
"eval_samples_per_second": 24.486,
|
| 1118 |
+
"eval_steps_per_second": 24.486,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.97,
|
| 1123 |
+
"learning_rate": 6.348082099679445e-06,
|
| 1124 |
+
"loss": 0.5096,
|
| 1125 |
+
"step": 7500
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.97,
|
| 1129 |
+
"eval_loss": 0.5079813003540039,
|
| 1130 |
+
"eval_map@3": 0.905,
|
| 1131 |
+
"eval_runtime": 4.207,
|
| 1132 |
+
"eval_samples_per_second": 23.77,
|
| 1133 |
+
"eval_steps_per_second": 23.77,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.0,
|
| 1138 |
+
"learning_rate": 6.0649258727418535e-06,
|
| 1139 |
+
"loss": 0.5272,
|
| 1140 |
+
"step": 7600
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.0,
|
| 1144 |
+
"eval_loss": 0.4955463409423828,
|
| 1145 |
+
"eval_map@3": 0.9083333333333333,
|
| 1146 |
+
"eval_runtime": 4.0938,
|
| 1147 |
+
"eval_samples_per_second": 24.427,
|
| 1148 |
+
"eval_steps_per_second": 24.427,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
}
|
| 1151 |
+
],
|
| 1152 |
+
"logging_steps": 100,
|
| 1153 |
+
"max_steps": 11406,
|
| 1154 |
+
"num_train_epochs": 3,
|
| 1155 |
+
"save_steps": 100,
|
| 1156 |
+
"total_flos": 3.996618693693601e+17,
|
| 1157 |
+
"trial_name": null,
|
| 1158 |
+
"trial_params": null
|
| 1159 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73a678ce749c60f5e44929d4d02123f240667b09ccba261e1c5f64b07ae9cbe9
|
| 3 |
+
size 4027
|