Training in progress, step 1913, checkpoint
Browse files- checkpoint-1913/1_Pooling/config.json +10 -0
- checkpoint-1913/README.md +0 -0
- checkpoint-1913/added_tokens.json +3 -0
- checkpoint-1913/config.json +35 -0
- checkpoint-1913/config_sentence_transformers.json +10 -0
- checkpoint-1913/modules.json +14 -0
- checkpoint-1913/optimizer.pt +3 -0
- checkpoint-1913/pytorch_model.bin +3 -0
- checkpoint-1913/rng_state.pth +3 -0
- checkpoint-1913/scheduler.pt +3 -0
- checkpoint-1913/sentence_bert_config.json +4 -0
- checkpoint-1913/special_tokens_map.json +15 -0
- checkpoint-1913/spm.model +3 -0
- checkpoint-1913/tokenizer.json +0 -0
- checkpoint-1913/tokenizer_config.json +58 -0
- checkpoint-1913/trainer_state.json +744 -0
- checkpoint-1913/training_args.bin +3 -0
checkpoint-1913/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
checkpoint-1913/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1913/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-1913/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2Model"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 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": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 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": "4.41.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
checkpoint-1913/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.41.2",
|
| 5 |
+
"pytorch": "2.3.0+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-1913/modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
checkpoint-1913/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af61e56dfe04a0b682f5218d5610c2aefbe608c2aa8c1c61874a43d93fb10568
|
| 3 |
+
size 1130520122
|
checkpoint-1913/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e749b0cc1993f82ac5974119c4495a72497de6c71917001ec3d8948dec31cc0a
|
| 3 |
+
size 565251810
|
checkpoint-1913/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1595af74edb88bd9e6f393028ffc4c8f5a74f90b430555bda01bd8a81c6b40a
|
| 3 |
+
size 14244
|
checkpoint-1913/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c3bf38f933025263e028bd3f13836c4c84f0a7b698b2ea25617a1e1671e274c
|
| 3 |
+
size 1064
|
checkpoint-1913/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-1913/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-1913/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-1913/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1913/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
checkpoint-1913/trainer_state.json
ADDED
|
@@ -0,0 +1,744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.30003136762860727,
|
| 5 |
+
"eval_steps": 479,
|
| 6 |
+
"global_step": 1913,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0075282308657465494,
|
| 13 |
+
"grad_norm": 87.12931823730469,
|
| 14 |
+
"learning_rate": 3.147218736930155e-07,
|
| 15 |
+
"loss": 12.3074,
|
| 16 |
+
"step": 48
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.015056461731493099,
|
| 20 |
+
"grad_norm": 64.15751647949219,
|
| 21 |
+
"learning_rate": 6.660393140945211e-07,
|
| 22 |
+
"loss": 15.7221,
|
| 23 |
+
"step": 96
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02258469259723965,
|
| 27 |
+
"grad_norm": 81.39651489257812,
|
| 28 |
+
"learning_rate": 1.0173567544960265e-06,
|
| 29 |
+
"loss": 10.8027,
|
| 30 |
+
"step": 144
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.030112923462986198,
|
| 34 |
+
"grad_norm": 22.048904418945312,
|
| 35 |
+
"learning_rate": 1.3686741948975323e-06,
|
| 36 |
+
"loss": 8.9559,
|
| 37 |
+
"step": 192
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.037641154328732745,
|
| 41 |
+
"grad_norm": 11.542724609375,
|
| 42 |
+
"learning_rate": 1.7126725219573398e-06,
|
| 43 |
+
"loss": 8.8511,
|
| 44 |
+
"step": 240
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0451693851944793,
|
| 48 |
+
"grad_norm": 10.625059127807617,
|
| 49 |
+
"learning_rate": 2.063989962358846e-06,
|
| 50 |
+
"loss": 9.3478,
|
| 51 |
+
"step": 288
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05269761606022585,
|
| 55 |
+
"grad_norm": 14.21434211730957,
|
| 56 |
+
"learning_rate": 2.415307402760351e-06,
|
| 57 |
+
"loss": 8.8892,
|
| 58 |
+
"step": 336
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.060225846925972396,
|
| 62 |
+
"grad_norm": 13.216053009033203,
|
| 63 |
+
"learning_rate": 2.7666248431618565e-06,
|
| 64 |
+
"loss": 8.3008,
|
| 65 |
+
"step": 384
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06775407779171895,
|
| 69 |
+
"grad_norm": 22.503334045410156,
|
| 70 |
+
"learning_rate": 3.117942283563362e-06,
|
| 71 |
+
"loss": 7.3455,
|
| 72 |
+
"step": 432
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07512547051442911,
|
| 76 |
+
"eval_nli-pairs_loss": 6.591032028198242,
|
| 77 |
+
"eval_nli-pairs_runtime": 4.3469,
|
| 78 |
+
"eval_nli-pairs_samples_per_second": 46.01,
|
| 79 |
+
"eval_nli-pairs_steps_per_second": 1.15,
|
| 80 |
+
"eval_sts-test_pearson_cosine": 0.39488461174644296,
|
| 81 |
+
"eval_sts-test_pearson_dot": 0.15593446481859455,
|
| 82 |
+
"eval_sts-test_pearson_euclidean": 0.39975070029693277,
|
| 83 |
+
"eval_sts-test_pearson_manhattan": 0.4314268556737928,
|
| 84 |
+
"eval_sts-test_pearson_max": 0.4314268556737928,
|
| 85 |
+
"eval_sts-test_spearman_cosine": 0.3997824055251076,
|
| 86 |
+
"eval_sts-test_spearman_dot": 0.14324216739430146,
|
| 87 |
+
"eval_sts-test_spearman_euclidean": 0.40262274612650517,
|
| 88 |
+
"eval_sts-test_spearman_manhattan": 0.42925492969387746,
|
| 89 |
+
"eval_sts-test_spearman_max": 0.42925492969387746,
|
| 90 |
+
"step": 479
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.07512547051442911,
|
| 94 |
+
"eval_vitaminc-pairs_loss": 6.247874736785889,
|
| 95 |
+
"eval_vitaminc-pairs_runtime": 1.4382,
|
| 96 |
+
"eval_vitaminc-pairs_samples_per_second": 115.426,
|
| 97 |
+
"eval_vitaminc-pairs_steps_per_second": 2.781,
|
| 98 |
+
"step": 479
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.07512547051442911,
|
| 102 |
+
"eval_sts-label_loss": 3.371708869934082,
|
| 103 |
+
"eval_sts-label_runtime": 0.3925,
|
| 104 |
+
"eval_sts-label_samples_per_second": 509.603,
|
| 105 |
+
"eval_sts-label_steps_per_second": 12.74,
|
| 106 |
+
"step": 479
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07512547051442911,
|
| 110 |
+
"eval_qnli-contrastive_loss": 3.5311310291290283,
|
| 111 |
+
"eval_qnli-contrastive_runtime": 0.2814,
|
| 112 |
+
"eval_qnli-contrastive_samples_per_second": 710.798,
|
| 113 |
+
"eval_qnli-contrastive_steps_per_second": 17.77,
|
| 114 |
+
"step": 479
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07512547051442911,
|
| 118 |
+
"eval_scitail-pairs-qa_loss": 5.4017333984375,
|
| 119 |
+
"eval_scitail-pairs-qa_runtime": 1.1087,
|
| 120 |
+
"eval_scitail-pairs-qa_samples_per_second": 180.387,
|
| 121 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.51,
|
| 122 |
+
"step": 479
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07512547051442911,
|
| 126 |
+
"eval_scitail-pairs-pos_loss": 4.29502534866333,
|
| 127 |
+
"eval_scitail-pairs-pos_runtime": 2.4269,
|
| 128 |
+
"eval_scitail-pairs-pos_samples_per_second": 82.41,
|
| 129 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.06,
|
| 130 |
+
"step": 479
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.07512547051442911,
|
| 134 |
+
"eval_xsum-pairs_loss": 3.540722370147705,
|
| 135 |
+
"eval_xsum-pairs_runtime": 1.0447,
|
| 136 |
+
"eval_xsum-pairs_samples_per_second": 191.444,
|
| 137 |
+
"eval_xsum-pairs_steps_per_second": 4.786,
|
| 138 |
+
"step": 479
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.07512547051442911,
|
| 142 |
+
"eval_compression-pairs_loss": 2.8060033321380615,
|
| 143 |
+
"eval_compression-pairs_runtime": 0.2399,
|
| 144 |
+
"eval_compression-pairs_samples_per_second": 833.621,
|
| 145 |
+
"eval_compression-pairs_steps_per_second": 20.841,
|
| 146 |
+
"step": 479
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.07512547051442911,
|
| 150 |
+
"eval_sciq_pairs_loss": 10.621454238891602,
|
| 151 |
+
"eval_sciq_pairs_runtime": 9.0638,
|
| 152 |
+
"eval_sciq_pairs_samples_per_second": 22.066,
|
| 153 |
+
"eval_sciq_pairs_steps_per_second": 0.552,
|
| 154 |
+
"step": 479
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.07512547051442911,
|
| 158 |
+
"eval_qasc_pairs_loss": 7.7197771072387695,
|
| 159 |
+
"eval_qasc_pairs_runtime": 1.2078,
|
| 160 |
+
"eval_qasc_pairs_samples_per_second": 165.595,
|
| 161 |
+
"eval_qasc_pairs_steps_per_second": 4.14,
|
| 162 |
+
"step": 479
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.07512547051442911,
|
| 166 |
+
"eval_openbookqa_pairs_loss": 7.620975494384766,
|
| 167 |
+
"eval_openbookqa_pairs_runtime": 1.053,
|
| 168 |
+
"eval_openbookqa_pairs_samples_per_second": 189.941,
|
| 169 |
+
"eval_openbookqa_pairs_steps_per_second": 4.749,
|
| 170 |
+
"step": 479
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.07512547051442911,
|
| 174 |
+
"eval_msmarco_pairs_loss": 8.353594779968262,
|
| 175 |
+
"eval_msmarco_pairs_runtime": 2.5338,
|
| 176 |
+
"eval_msmarco_pairs_samples_per_second": 78.932,
|
| 177 |
+
"eval_msmarco_pairs_steps_per_second": 1.973,
|
| 178 |
+
"step": 479
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07512547051442911,
|
| 182 |
+
"eval_nq_pairs_loss": 7.995354652404785,
|
| 183 |
+
"eval_nq_pairs_runtime": 5.7107,
|
| 184 |
+
"eval_nq_pairs_samples_per_second": 35.022,
|
| 185 |
+
"eval_nq_pairs_steps_per_second": 0.876,
|
| 186 |
+
"step": 479
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.07512547051442911,
|
| 190 |
+
"eval_trivia_pairs_loss": 8.177907943725586,
|
| 191 |
+
"eval_trivia_pairs_runtime": 9.1824,
|
| 192 |
+
"eval_trivia_pairs_samples_per_second": 21.781,
|
| 193 |
+
"eval_trivia_pairs_steps_per_second": 0.545,
|
| 194 |
+
"step": 479
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.07512547051442911,
|
| 198 |
+
"eval_quora_pairs_loss": 1.1983369588851929,
|
| 199 |
+
"eval_quora_pairs_runtime": 0.659,
|
| 200 |
+
"eval_quora_pairs_samples_per_second": 303.48,
|
| 201 |
+
"eval_quora_pairs_steps_per_second": 7.587,
|
| 202 |
+
"step": 479
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.07512547051442911,
|
| 206 |
+
"eval_gooaq_pairs_loss": 7.4573974609375,
|
| 207 |
+
"eval_gooaq_pairs_runtime": 1.5917,
|
| 208 |
+
"eval_gooaq_pairs_samples_per_second": 125.65,
|
| 209 |
+
"eval_gooaq_pairs_steps_per_second": 3.141,
|
| 210 |
+
"step": 479
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.07512547051442911,
|
| 214 |
+
"eval_mrpc_pairs_loss": 2.1152825355529785,
|
| 215 |
+
"eval_mrpc_pairs_runtime": 0.241,
|
| 216 |
+
"eval_mrpc_pairs_samples_per_second": 829.751,
|
| 217 |
+
"eval_mrpc_pairs_steps_per_second": 20.744,
|
| 218 |
+
"step": 479
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.07528230865746549,
|
| 222 |
+
"grad_norm": 17.753456115722656,
|
| 223 |
+
"learning_rate": 3.469259723964868e-06,
|
| 224 |
+
"loss": 8.0369,
|
| 225 |
+
"step": 480
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.08281053952321205,
|
| 229 |
+
"grad_norm": 12.012594223022461,
|
| 230 |
+
"learning_rate": 3.820577164366374e-06,
|
| 231 |
+
"loss": 6.2732,
|
| 232 |
+
"step": 528
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.0903387703889586,
|
| 236 |
+
"grad_norm": 34.92698287963867,
|
| 237 |
+
"learning_rate": 4.1718946047678796e-06,
|
| 238 |
+
"loss": 7.8529,
|
| 239 |
+
"step": 576
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.09786700125470514,
|
| 243 |
+
"grad_norm": 23.564632415771484,
|
| 244 |
+
"learning_rate": 4.523212045169385e-06,
|
| 245 |
+
"loss": 5.8643,
|
| 246 |
+
"step": 624
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.1053952321204517,
|
| 250 |
+
"grad_norm": 22.126293182373047,
|
| 251 |
+
"learning_rate": 4.874529485570891e-06,
|
| 252 |
+
"loss": 6.3179,
|
| 253 |
+
"step": 672
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.11292346298619825,
|
| 257 |
+
"grad_norm": 25.067686080932617,
|
| 258 |
+
"learning_rate": 5.225846925972396e-06,
|
| 259 |
+
"loss": 6.1175,
|
| 260 |
+
"step": 720
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.12045169385194479,
|
| 264 |
+
"grad_norm": 29.170730590820312,
|
| 265 |
+
"learning_rate": 5.577164366373902e-06,
|
| 266 |
+
"loss": 5.2392,
|
| 267 |
+
"step": 768
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12797992471769135,
|
| 271 |
+
"grad_norm": 29.377540588378906,
|
| 272 |
+
"learning_rate": 5.928481806775407e-06,
|
| 273 |
+
"loss": 5.8324,
|
| 274 |
+
"step": 816
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.1355081555834379,
|
| 278 |
+
"grad_norm": 33.512088775634766,
|
| 279 |
+
"learning_rate": 6.279799247176913e-06,
|
| 280 |
+
"loss": 5.1523,
|
| 281 |
+
"step": 864
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.14303638644918445,
|
| 285 |
+
"grad_norm": 32.54931640625,
|
| 286 |
+
"learning_rate": 6.6311166875784185e-06,
|
| 287 |
+
"loss": 6.0303,
|
| 288 |
+
"step": 912
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.15025094102885822,
|
| 292 |
+
"eval_nli-pairs_loss": 4.317643165588379,
|
| 293 |
+
"eval_nli-pairs_runtime": 4.0158,
|
| 294 |
+
"eval_nli-pairs_samples_per_second": 49.803,
|
| 295 |
+
"eval_nli-pairs_steps_per_second": 1.245,
|
| 296 |
+
"eval_sts-test_pearson_cosine": 0.6751726661173544,
|
| 297 |
+
"eval_sts-test_pearson_dot": 0.5308173325280101,
|
| 298 |
+
"eval_sts-test_pearson_euclidean": 0.6660519042507951,
|
| 299 |
+
"eval_sts-test_pearson_manhattan": 0.6723411683739887,
|
| 300 |
+
"eval_sts-test_pearson_max": 0.6751726661173544,
|
| 301 |
+
"eval_sts-test_spearman_cosine": 0.6458966208807124,
|
| 302 |
+
"eval_sts-test_spearman_dot": 0.5040208096497271,
|
| 303 |
+
"eval_sts-test_spearman_euclidean": 0.6447205374312966,
|
| 304 |
+
"eval_sts-test_spearman_manhattan": 0.6498560301461127,
|
| 305 |
+
"eval_sts-test_spearman_max": 0.6498560301461127,
|
| 306 |
+
"step": 958
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.15025094102885822,
|
| 310 |
+
"eval_vitaminc-pairs_loss": 6.306981563568115,
|
| 311 |
+
"eval_vitaminc-pairs_runtime": 1.4737,
|
| 312 |
+
"eval_vitaminc-pairs_samples_per_second": 112.643,
|
| 313 |
+
"eval_vitaminc-pairs_steps_per_second": 2.714,
|
| 314 |
+
"step": 958
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.15025094102885822,
|
| 318 |
+
"eval_sts-label_loss": 3.7677345275878906,
|
| 319 |
+
"eval_sts-label_runtime": 0.4136,
|
| 320 |
+
"eval_sts-label_samples_per_second": 483.59,
|
| 321 |
+
"eval_sts-label_steps_per_second": 12.09,
|
| 322 |
+
"step": 958
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.15025094102885822,
|
| 326 |
+
"eval_qnli-contrastive_loss": 2.8633975982666016,
|
| 327 |
+
"eval_qnli-contrastive_runtime": 0.2816,
|
| 328 |
+
"eval_qnli-contrastive_samples_per_second": 710.123,
|
| 329 |
+
"eval_qnli-contrastive_steps_per_second": 17.753,
|
| 330 |
+
"step": 958
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.15025094102885822,
|
| 334 |
+
"eval_scitail-pairs-qa_loss": 1.4301409721374512,
|
| 335 |
+
"eval_scitail-pairs-qa_runtime": 1.0526,
|
| 336 |
+
"eval_scitail-pairs-qa_samples_per_second": 190.003,
|
| 337 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.75,
|
| 338 |
+
"step": 958
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15025094102885822,
|
| 342 |
+
"eval_scitail-pairs-pos_loss": 2.468087673187256,
|
| 343 |
+
"eval_scitail-pairs-pos_runtime": 2.3275,
|
| 344 |
+
"eval_scitail-pairs-pos_samples_per_second": 85.928,
|
| 345 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.148,
|
| 346 |
+
"step": 958
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.15025094102885822,
|
| 350 |
+
"eval_xsum-pairs_loss": 2.153658151626587,
|
| 351 |
+
"eval_xsum-pairs_runtime": 1.0409,
|
| 352 |
+
"eval_xsum-pairs_samples_per_second": 192.151,
|
| 353 |
+
"eval_xsum-pairs_steps_per_second": 4.804,
|
| 354 |
+
"step": 958
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.15025094102885822,
|
| 358 |
+
"eval_compression-pairs_loss": 1.6288033723831177,
|
| 359 |
+
"eval_compression-pairs_runtime": 0.2383,
|
| 360 |
+
"eval_compression-pairs_samples_per_second": 839.253,
|
| 361 |
+
"eval_compression-pairs_steps_per_second": 20.981,
|
| 362 |
+
"step": 958
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.15025094102885822,
|
| 366 |
+
"eval_sciq_pairs_loss": 9.78779411315918,
|
| 367 |
+
"eval_sciq_pairs_runtime": 9.0233,
|
| 368 |
+
"eval_sciq_pairs_samples_per_second": 22.165,
|
| 369 |
+
"eval_sciq_pairs_steps_per_second": 0.554,
|
| 370 |
+
"step": 958
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.15025094102885822,
|
| 374 |
+
"eval_qasc_pairs_loss": 3.7814972400665283,
|
| 375 |
+
"eval_qasc_pairs_runtime": 1.2108,
|
| 376 |
+
"eval_qasc_pairs_samples_per_second": 165.179,
|
| 377 |
+
"eval_qasc_pairs_steps_per_second": 4.129,
|
| 378 |
+
"step": 958
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.15025094102885822,
|
| 382 |
+
"eval_openbookqa_pairs_loss": 5.005772590637207,
|
| 383 |
+
"eval_openbookqa_pairs_runtime": 1.0415,
|
| 384 |
+
"eval_openbookqa_pairs_samples_per_second": 192.037,
|
| 385 |
+
"eval_openbookqa_pairs_steps_per_second": 4.801,
|
| 386 |
+
"step": 958
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.15025094102885822,
|
| 390 |
+
"eval_msmarco_pairs_loss": 4.574879169464111,
|
| 391 |
+
"eval_msmarco_pairs_runtime": 2.527,
|
| 392 |
+
"eval_msmarco_pairs_samples_per_second": 79.146,
|
| 393 |
+
"eval_msmarco_pairs_steps_per_second": 1.979,
|
| 394 |
+
"step": 958
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.15025094102885822,
|
| 398 |
+
"eval_nq_pairs_loss": 5.281248569488525,
|
| 399 |
+
"eval_nq_pairs_runtime": 5.6503,
|
| 400 |
+
"eval_nq_pairs_samples_per_second": 35.397,
|
| 401 |
+
"eval_nq_pairs_steps_per_second": 0.885,
|
| 402 |
+
"step": 958
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.15025094102885822,
|
| 406 |
+
"eval_trivia_pairs_loss": 4.913428783416748,
|
| 407 |
+
"eval_trivia_pairs_runtime": 9.0564,
|
| 408 |
+
"eval_trivia_pairs_samples_per_second": 22.084,
|
| 409 |
+
"eval_trivia_pairs_steps_per_second": 0.552,
|
| 410 |
+
"step": 958
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.15025094102885822,
|
| 414 |
+
"eval_quora_pairs_loss": 0.9212128520011902,
|
| 415 |
+
"eval_quora_pairs_runtime": 0.6293,
|
| 416 |
+
"eval_quora_pairs_samples_per_second": 317.839,
|
| 417 |
+
"eval_quora_pairs_steps_per_second": 7.946,
|
| 418 |
+
"step": 958
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.15025094102885822,
|
| 422 |
+
"eval_gooaq_pairs_loss": 3.932173490524292,
|
| 423 |
+
"eval_gooaq_pairs_runtime": 1.6066,
|
| 424 |
+
"eval_gooaq_pairs_samples_per_second": 124.483,
|
| 425 |
+
"eval_gooaq_pairs_steps_per_second": 3.112,
|
| 426 |
+
"step": 958
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.15025094102885822,
|
| 430 |
+
"eval_mrpc_pairs_loss": 1.0853501558303833,
|
| 431 |
+
"eval_mrpc_pairs_runtime": 0.2402,
|
| 432 |
+
"eval_mrpc_pairs_samples_per_second": 832.56,
|
| 433 |
+
"eval_mrpc_pairs_steps_per_second": 20.814,
|
| 434 |
+
"step": 958
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.15056461731493098,
|
| 438 |
+
"grad_norm": 28.37123680114746,
|
| 439 |
+
"learning_rate": 6.982434127979924e-06,
|
| 440 |
+
"loss": 5.7748,
|
| 441 |
+
"step": 960
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.15809284818067754,
|
| 445 |
+
"grad_norm": 26.708221435546875,
|
| 446 |
+
"learning_rate": 7.33375156838143e-06,
|
| 447 |
+
"loss": 4.8728,
|
| 448 |
+
"step": 1008
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.1656210790464241,
|
| 452 |
+
"grad_norm": 26.786447525024414,
|
| 453 |
+
"learning_rate": 7.685069008782934e-06,
|
| 454 |
+
"loss": 4.7375,
|
| 455 |
+
"step": 1056
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.17314930991217065,
|
| 459 |
+
"grad_norm": 26.215879440307617,
|
| 460 |
+
"learning_rate": 8.03638644918444e-06,
|
| 461 |
+
"loss": 4.6766,
|
| 462 |
+
"step": 1104
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.1806775407779172,
|
| 466 |
+
"grad_norm": 35.618831634521484,
|
| 467 |
+
"learning_rate": 8.387703889585947e-06,
|
| 468 |
+
"loss": 4.3209,
|
| 469 |
+
"step": 1152
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.18820577164366373,
|
| 473 |
+
"grad_norm": 37.166072845458984,
|
| 474 |
+
"learning_rate": 8.739021329987453e-06,
|
| 475 |
+
"loss": 3.7761,
|
| 476 |
+
"step": 1200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.19573400250941028,
|
| 480 |
+
"grad_norm": 35.78367233276367,
|
| 481 |
+
"learning_rate": 9.090338770388957e-06,
|
| 482 |
+
"loss": 4.2161,
|
| 483 |
+
"step": 1248
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.20326223337515684,
|
| 487 |
+
"grad_norm": 36.299678802490234,
|
| 488 |
+
"learning_rate": 9.441656210790464e-06,
|
| 489 |
+
"loss": 4.9089,
|
| 490 |
+
"step": 1296
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.2107904642409034,
|
| 494 |
+
"grad_norm": 18.610933303833008,
|
| 495 |
+
"learning_rate": 9.792973651191968e-06,
|
| 496 |
+
"loss": 4.3406,
|
| 497 |
+
"step": 1344
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.21831869510664995,
|
| 501 |
+
"grad_norm": 9.592538833618164,
|
| 502 |
+
"learning_rate": 1.0144291091593475e-05,
|
| 503 |
+
"loss": 3.5664,
|
| 504 |
+
"step": 1392
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.22537641154328733,
|
| 508 |
+
"eval_nli-pairs_loss": 3.2245519161224365,
|
| 509 |
+
"eval_nli-pairs_runtime": 4.0436,
|
| 510 |
+
"eval_nli-pairs_samples_per_second": 49.461,
|
| 511 |
+
"eval_nli-pairs_steps_per_second": 1.237,
|
| 512 |
+
"eval_sts-test_pearson_cosine": 0.7002978854888552,
|
| 513 |
+
"eval_sts-test_pearson_dot": 0.5685392445320393,
|
| 514 |
+
"eval_sts-test_pearson_euclidean": 0.6963744527231541,
|
| 515 |
+
"eval_sts-test_pearson_manhattan": 0.7050517306003169,
|
| 516 |
+
"eval_sts-test_pearson_max": 0.7050517306003169,
|
| 517 |
+
"eval_sts-test_spearman_cosine": 0.6718756239728468,
|
| 518 |
+
"eval_sts-test_spearman_dot": 0.5416448961602434,
|
| 519 |
+
"eval_sts-test_spearman_euclidean": 0.6742379556154348,
|
| 520 |
+
"eval_sts-test_spearman_manhattan": 0.6824201536078427,
|
| 521 |
+
"eval_sts-test_spearman_max": 0.6824201536078427,
|
| 522 |
+
"step": 1437
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.22537641154328733,
|
| 526 |
+
"eval_vitaminc-pairs_loss": 6.715206623077393,
|
| 527 |
+
"eval_vitaminc-pairs_runtime": 1.4251,
|
| 528 |
+
"eval_vitaminc-pairs_samples_per_second": 116.481,
|
| 529 |
+
"eval_vitaminc-pairs_steps_per_second": 2.807,
|
| 530 |
+
"step": 1437
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.22537641154328733,
|
| 534 |
+
"eval_sts-label_loss": 4.016364097595215,
|
| 535 |
+
"eval_sts-label_runtime": 0.4049,
|
| 536 |
+
"eval_sts-label_samples_per_second": 493.95,
|
| 537 |
+
"eval_sts-label_steps_per_second": 12.349,
|
| 538 |
+
"step": 1437
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.22537641154328733,
|
| 542 |
+
"eval_qnli-contrastive_loss": 1.999517560005188,
|
| 543 |
+
"eval_qnli-contrastive_runtime": 0.2804,
|
| 544 |
+
"eval_qnli-contrastive_samples_per_second": 713.282,
|
| 545 |
+
"eval_qnli-contrastive_steps_per_second": 17.832,
|
| 546 |
+
"step": 1437
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.22537641154328733,
|
| 550 |
+
"eval_scitail-pairs-qa_loss": 1.0403239727020264,
|
| 551 |
+
"eval_scitail-pairs-qa_runtime": 1.0483,
|
| 552 |
+
"eval_scitail-pairs-qa_samples_per_second": 190.793,
|
| 553 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.77,
|
| 554 |
+
"step": 1437
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.22537641154328733,
|
| 558 |
+
"eval_scitail-pairs-pos_loss": 1.9232473373413086,
|
| 559 |
+
"eval_scitail-pairs-pos_runtime": 2.3447,
|
| 560 |
+
"eval_scitail-pairs-pos_samples_per_second": 85.298,
|
| 561 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.132,
|
| 562 |
+
"step": 1437
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.22537641154328733,
|
| 566 |
+
"eval_xsum-pairs_loss": 1.6821197271347046,
|
| 567 |
+
"eval_xsum-pairs_runtime": 1.0422,
|
| 568 |
+
"eval_xsum-pairs_samples_per_second": 191.901,
|
| 569 |
+
"eval_xsum-pairs_steps_per_second": 4.798,
|
| 570 |
+
"step": 1437
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.22537641154328733,
|
| 574 |
+
"eval_compression-pairs_loss": 1.1713249683380127,
|
| 575 |
+
"eval_compression-pairs_runtime": 0.2392,
|
| 576 |
+
"eval_compression-pairs_samples_per_second": 836.05,
|
| 577 |
+
"eval_compression-pairs_steps_per_second": 20.901,
|
| 578 |
+
"step": 1437
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.22537641154328733,
|
| 582 |
+
"eval_sciq_pairs_loss": 9.443825721740723,
|
| 583 |
+
"eval_sciq_pairs_runtime": 8.9916,
|
| 584 |
+
"eval_sciq_pairs_samples_per_second": 22.243,
|
| 585 |
+
"eval_sciq_pairs_steps_per_second": 0.556,
|
| 586 |
+
"step": 1437
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.22537641154328733,
|
| 590 |
+
"eval_qasc_pairs_loss": 2.9044029712677,
|
| 591 |
+
"eval_qasc_pairs_runtime": 1.2182,
|
| 592 |
+
"eval_qasc_pairs_samples_per_second": 164.182,
|
| 593 |
+
"eval_qasc_pairs_steps_per_second": 4.105,
|
| 594 |
+
"step": 1437
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.22537641154328733,
|
| 598 |
+
"eval_openbookqa_pairs_loss": 4.360418796539307,
|
| 599 |
+
"eval_openbookqa_pairs_runtime": 1.0522,
|
| 600 |
+
"eval_openbookqa_pairs_samples_per_second": 190.077,
|
| 601 |
+
"eval_openbookqa_pairs_steps_per_second": 4.752,
|
| 602 |
+
"step": 1437
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.22537641154328733,
|
| 606 |
+
"eval_msmarco_pairs_loss": 3.516049861907959,
|
| 607 |
+
"eval_msmarco_pairs_runtime": 2.5595,
|
| 608 |
+
"eval_msmarco_pairs_samples_per_second": 78.139,
|
| 609 |
+
"eval_msmarco_pairs_steps_per_second": 1.953,
|
| 610 |
+
"step": 1437
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.22537641154328733,
|
| 614 |
+
"eval_nq_pairs_loss": 4.016308784484863,
|
| 615 |
+
"eval_nq_pairs_runtime": 5.6561,
|
| 616 |
+
"eval_nq_pairs_samples_per_second": 35.36,
|
| 617 |
+
"eval_nq_pairs_steps_per_second": 0.884,
|
| 618 |
+
"step": 1437
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.22537641154328733,
|
| 622 |
+
"eval_trivia_pairs_loss": 3.781872272491455,
|
| 623 |
+
"eval_trivia_pairs_runtime": 9.0801,
|
| 624 |
+
"eval_trivia_pairs_samples_per_second": 22.026,
|
| 625 |
+
"eval_trivia_pairs_steps_per_second": 0.551,
|
| 626 |
+
"step": 1437
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.22537641154328733,
|
| 630 |
+
"eval_quora_pairs_loss": 0.8747495412826538,
|
| 631 |
+
"eval_quora_pairs_runtime": 0.6229,
|
| 632 |
+
"eval_quora_pairs_samples_per_second": 321.076,
|
| 633 |
+
"eval_quora_pairs_steps_per_second": 8.027,
|
| 634 |
+
"step": 1437
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.22537641154328733,
|
| 638 |
+
"eval_gooaq_pairs_loss": 3.0769765377044678,
|
| 639 |
+
"eval_gooaq_pairs_runtime": 1.552,
|
| 640 |
+
"eval_gooaq_pairs_samples_per_second": 128.863,
|
| 641 |
+
"eval_gooaq_pairs_steps_per_second": 3.222,
|
| 642 |
+
"step": 1437
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.22537641154328733,
|
| 646 |
+
"eval_mrpc_pairs_loss": 0.7370794415473938,
|
| 647 |
+
"eval_mrpc_pairs_runtime": 0.2401,
|
| 648 |
+
"eval_mrpc_pairs_samples_per_second": 832.867,
|
| 649 |
+
"eval_mrpc_pairs_steps_per_second": 20.822,
|
| 650 |
+
"step": 1437
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.2258469259723965,
|
| 654 |
+
"grad_norm": 29.73522186279297,
|
| 655 |
+
"learning_rate": 1.049560853199498e-05,
|
| 656 |
+
"loss": 4.7194,
|
| 657 |
+
"step": 1440
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.23337515683814303,
|
| 661 |
+
"grad_norm": 30.467117309570312,
|
| 662 |
+
"learning_rate": 1.0846925972396486e-05,
|
| 663 |
+
"loss": 3.6345,
|
| 664 |
+
"step": 1488
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.24090338770388958,
|
| 668 |
+
"grad_norm": 24.454021453857422,
|
| 669 |
+
"learning_rate": 1.1198243412797992e-05,
|
| 670 |
+
"loss": 3.5947,
|
| 671 |
+
"step": 1536
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.24843161856963614,
|
| 675 |
+
"grad_norm": 20.165475845336914,
|
| 676 |
+
"learning_rate": 1.1549560853199497e-05,
|
| 677 |
+
"loss": 4.0526,
|
| 678 |
+
"step": 1584
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.2559598494353827,
|
| 682 |
+
"grad_norm": 34.79319381713867,
|
| 683 |
+
"learning_rate": 1.1900878293601003e-05,
|
| 684 |
+
"loss": 3.7962,
|
| 685 |
+
"step": 1632
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.26348808030112925,
|
| 689 |
+
"grad_norm": 127.97925567626953,
|
| 690 |
+
"learning_rate": 1.2252195734002508e-05,
|
| 691 |
+
"loss": 4.1927,
|
| 692 |
+
"step": 1680
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.2710163111668758,
|
| 696 |
+
"grad_norm": 27.80243682861328,
|
| 697 |
+
"learning_rate": 1.2603513174404014e-05,
|
| 698 |
+
"loss": 3.6351,
|
| 699 |
+
"step": 1728
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.27854454203262236,
|
| 703 |
+
"grad_norm": 31.81105613708496,
|
| 704 |
+
"learning_rate": 1.295483061480552e-05,
|
| 705 |
+
"loss": 3.4256,
|
| 706 |
+
"step": 1776
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.2860727728983689,
|
| 710 |
+
"grad_norm": 32.932865142822266,
|
| 711 |
+
"learning_rate": 1.3306148055207025e-05,
|
| 712 |
+
"loss": 3.3175,
|
| 713 |
+
"step": 1824
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.2936010037641154,
|
| 717 |
+
"grad_norm": 31.197385787963867,
|
| 718 |
+
"learning_rate": 1.365746549560853e-05,
|
| 719 |
+
"loss": 3.4984,
|
| 720 |
+
"step": 1872
|
| 721 |
+
}
|
| 722 |
+
],
|
| 723 |
+
"logging_steps": 48,
|
| 724 |
+
"max_steps": 19128,
|
| 725 |
+
"num_input_tokens_seen": 0,
|
| 726 |
+
"num_train_epochs": 3,
|
| 727 |
+
"save_steps": 1913,
|
| 728 |
+
"stateful_callbacks": {
|
| 729 |
+
"TrainerControl": {
|
| 730 |
+
"args": {
|
| 731 |
+
"should_epoch_stop": false,
|
| 732 |
+
"should_evaluate": false,
|
| 733 |
+
"should_log": false,
|
| 734 |
+
"should_save": true,
|
| 735 |
+
"should_training_stop": false
|
| 736 |
+
},
|
| 737 |
+
"attributes": {}
|
| 738 |
+
}
|
| 739 |
+
},
|
| 740 |
+
"total_flos": 0.0,
|
| 741 |
+
"train_batch_size": 42,
|
| 742 |
+
"trial_name": null,
|
| 743 |
+
"trial_params": null
|
| 744 |
+
}
|
checkpoint-1913/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f0d30e9d834ad3faa1c6260f078cc6b8b6620d2f13869b6672c84d4621cb729
|
| 3 |
+
size 5624
|