Training in progress, step 321, checkpoint
Browse files- checkpoint-321/1_Pooling/config.json +10 -0
- checkpoint-321/README.md +0 -0
- checkpoint-321/added_tokens.json +3 -0
- checkpoint-321/config.json +35 -0
- checkpoint-321/config_sentence_transformers.json +10 -0
- checkpoint-321/modules.json +14 -0
- checkpoint-321/optimizer.pt +3 -0
- checkpoint-321/pytorch_model.bin +3 -0
- checkpoint-321/rng_state.pth +3 -0
- checkpoint-321/scheduler.pt +3 -0
- checkpoint-321/sentence_bert_config.json +4 -0
- checkpoint-321/special_tokens_map.json +15 -0
- checkpoint-321/spm.model +3 -0
- checkpoint-321/tokenizer.json +0 -0
- checkpoint-321/tokenizer_config.json +58 -0
- checkpoint-321/trainer_state.json +2399 -0
- checkpoint-321/training_args.bin +3 -0
checkpoint-321/1_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-321/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-321/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-321/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": "4.42.3",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
checkpoint-321/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.42.3",
|
| 5 |
+
"pytorch": "2.1.2"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-321/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-321/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3aa9921491405358bb24e497194a4ce68ce44490d81ffefd9b40620fb2eb212
|
| 3 |
+
size 1130520122
|
checkpoint-321/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b02c753a9983a3ba15ab09631fa32eddf314ac35a09d8d740eb4b78aec702dee
|
| 3 |
+
size 565251810
|
checkpoint-321/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c9ee4ccd8311f99eb705f558600271dcd514089e6251f010818e0278cc931f2
|
| 3 |
+
size 14244
|
checkpoint-321/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:074088b6be78b4ba4014e0c7d353a939a19f00f8494cb69e974d33e535fd8e46
|
| 3 |
+
size 1064
|
checkpoint-321/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-321/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-321/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-321/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-321/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-321/trainer_state.json
ADDED
|
@@ -0,0 +1,2399 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8122794636556105,
|
| 5 |
+
"eval_steps": 27,
|
| 6 |
+
"global_step": 321,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016937191249117856,
|
| 13 |
+
"grad_norm": 34.22002029418945,
|
| 14 |
+
"learning_rate": 6.818181818181818e-07,
|
| 15 |
+
"loss": 7.2372,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03387438249823571,
|
| 20 |
+
"grad_norm": 21.76839828491211,
|
| 21 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 22 |
+
"loss": 6.855,
|
| 23 |
+
"step": 6
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05081157374735357,
|
| 27 |
+
"grad_norm": 21.260774612426758,
|
| 28 |
+
"learning_rate": 2.0454545454545457e-06,
|
| 29 |
+
"loss": 7.4707,
|
| 30 |
+
"step": 9
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06774876499647142,
|
| 34 |
+
"grad_norm": 16.885921478271484,
|
| 35 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 36 |
+
"loss": 7.0187,
|
| 37 |
+
"step": 12
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08468595624558928,
|
| 41 |
+
"grad_norm": 19.509899139404297,
|
| 42 |
+
"learning_rate": 3.409090909090909e-06,
|
| 43 |
+
"loss": 6.6756,
|
| 44 |
+
"step": 15
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10162314749470713,
|
| 48 |
+
"grad_norm": 7.9427289962768555,
|
| 49 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 50 |
+
"loss": 6.0155,
|
| 51 |
+
"step": 18
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11856033874382499,
|
| 55 |
+
"grad_norm": 7.325345039367676,
|
| 56 |
+
"learning_rate": 4.772727272727273e-06,
|
| 57 |
+
"loss": 6.1644,
|
| 58 |
+
"step": 21
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13549752999294284,
|
| 62 |
+
"grad_norm": 7.544689655303955,
|
| 63 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 64 |
+
"loss": 6.2158,
|
| 65 |
+
"step": 24
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1524347212420607,
|
| 69 |
+
"grad_norm": 5.141758918762207,
|
| 70 |
+
"learning_rate": 6.136363636363637e-06,
|
| 71 |
+
"loss": 6.1369,
|
| 72 |
+
"step": 27
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1524347212420607,
|
| 76 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 77 |
+
"eval_NLI-v2_dot_accuracy": 0.109375,
|
| 78 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 79 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 80 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 81 |
+
"eval_VitaminC_cosine_accuracy": 0.5546875,
|
| 82 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.9544724822044373,
|
| 83 |
+
"eval_VitaminC_cosine_ap": 0.5356492030729136,
|
| 84 |
+
"eval_VitaminC_cosine_f1": 0.6542553191489362,
|
| 85 |
+
"eval_VitaminC_cosine_f1_threshold": 0.7148199081420898,
|
| 86 |
+
"eval_VitaminC_cosine_precision": 0.48616600790513836,
|
| 87 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 88 |
+
"eval_VitaminC_dot_accuracy": 0.55078125,
|
| 89 |
+
"eval_VitaminC_dot_accuracy_threshold": 414.4264831542969,
|
| 90 |
+
"eval_VitaminC_dot_ap": 0.5108219546857565,
|
| 91 |
+
"eval_VitaminC_dot_f1": 0.6507936507936508,
|
| 92 |
+
"eval_VitaminC_dot_f1_threshold": 271.6522521972656,
|
| 93 |
+
"eval_VitaminC_dot_precision": 0.4823529411764706,
|
| 94 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 95 |
+
"eval_VitaminC_euclidean_accuracy": 0.55078125,
|
| 96 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 6.519885063171387,
|
| 97 |
+
"eval_VitaminC_euclidean_ap": 0.5226419655984281,
|
| 98 |
+
"eval_VitaminC_euclidean_f1": 0.6505376344086021,
|
| 99 |
+
"eval_VitaminC_euclidean_f1_threshold": 15.194067001342773,
|
| 100 |
+
"eval_VitaminC_euclidean_precision": 0.4859437751004016,
|
| 101 |
+
"eval_VitaminC_euclidean_recall": 0.983739837398374,
|
| 102 |
+
"eval_VitaminC_manhattan_accuracy": 0.546875,
|
| 103 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 149.20114135742188,
|
| 104 |
+
"eval_VitaminC_manhattan_ap": 0.5237451656134715,
|
| 105 |
+
"eval_VitaminC_manhattan_f1": 0.6542553191489362,
|
| 106 |
+
"eval_VitaminC_manhattan_f1_threshold": 259.007080078125,
|
| 107 |
+
"eval_VitaminC_manhattan_precision": 0.48616600790513836,
|
| 108 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 109 |
+
"eval_VitaminC_max_accuracy": 0.5546875,
|
| 110 |
+
"eval_VitaminC_max_accuracy_threshold": 414.4264831542969,
|
| 111 |
+
"eval_VitaminC_max_ap": 0.5356492030729136,
|
| 112 |
+
"eval_VitaminC_max_f1": 0.6542553191489362,
|
| 113 |
+
"eval_VitaminC_max_f1_threshold": 271.6522521972656,
|
| 114 |
+
"eval_VitaminC_max_precision": 0.48616600790513836,
|
| 115 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 116 |
+
"eval_sequential_score": 0.5356492030729136,
|
| 117 |
+
"eval_sts-test_pearson_cosine": 0.056062031998983373,
|
| 118 |
+
"eval_sts-test_pearson_dot": 0.2979259445723872,
|
| 119 |
+
"eval_sts-test_pearson_euclidean": 0.0498319208592713,
|
| 120 |
+
"eval_sts-test_pearson_manhattan": 0.07381429239121526,
|
| 121 |
+
"eval_sts-test_pearson_max": 0.2979259445723872,
|
| 122 |
+
"eval_sts-test_spearman_cosine": 0.1066788491614481,
|
| 123 |
+
"eval_sts-test_spearman_dot": 0.315952670306405,
|
| 124 |
+
"eval_sts-test_spearman_euclidean": 0.07303394554435191,
|
| 125 |
+
"eval_sts-test_spearman_manhattan": 0.09039525717692232,
|
| 126 |
+
"eval_sts-test_spearman_max": 0.315952670306405,
|
| 127 |
+
"eval_vitaminc-pairs_loss": 2.698580741882324,
|
| 128 |
+
"eval_vitaminc-pairs_runtime": 1.4747,
|
| 129 |
+
"eval_vitaminc-pairs_samples_per_second": 73.236,
|
| 130 |
+
"eval_vitaminc-pairs_steps_per_second": 1.356,
|
| 131 |
+
"step": 27
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.1524347212420607,
|
| 135 |
+
"eval_negation-triplets_loss": 5.142906665802002,
|
| 136 |
+
"eval_negation-triplets_runtime": 0.2993,
|
| 137 |
+
"eval_negation-triplets_samples_per_second": 213.865,
|
| 138 |
+
"eval_negation-triplets_steps_per_second": 3.342,
|
| 139 |
+
"step": 27
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.1524347212420607,
|
| 143 |
+
"eval_scitail-pairs-pos_loss": 1.9216958284378052,
|
| 144 |
+
"eval_scitail-pairs-pos_runtime": 0.3834,
|
| 145 |
+
"eval_scitail-pairs-pos_samples_per_second": 140.842,
|
| 146 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.608,
|
| 147 |
+
"step": 27
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1524347212420607,
|
| 151 |
+
"eval_xsum-pairs_loss": 6.073049545288086,
|
| 152 |
+
"eval_xsum-pairs_runtime": 3.1587,
|
| 153 |
+
"eval_xsum-pairs_samples_per_second": 40.523,
|
| 154 |
+
"eval_xsum-pairs_steps_per_second": 0.633,
|
| 155 |
+
"step": 27
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.1524347212420607,
|
| 159 |
+
"eval_sciq_pairs_loss": 0.3449864387512207,
|
| 160 |
+
"eval_sciq_pairs_runtime": 3.3747,
|
| 161 |
+
"eval_sciq_pairs_samples_per_second": 37.93,
|
| 162 |
+
"eval_sciq_pairs_steps_per_second": 0.593,
|
| 163 |
+
"step": 27
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1524347212420607,
|
| 167 |
+
"eval_qasc_pairs_loss": 3.2267842292785645,
|
| 168 |
+
"eval_qasc_pairs_runtime": 0.6576,
|
| 169 |
+
"eval_qasc_pairs_samples_per_second": 194.646,
|
| 170 |
+
"eval_qasc_pairs_steps_per_second": 3.041,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1524347212420607,
|
| 175 |
+
"eval_openbookqa_pairs_loss": 4.405983924865723,
|
| 176 |
+
"eval_openbookqa_pairs_runtime": 0.6107,
|
| 177 |
+
"eval_openbookqa_pairs_samples_per_second": 209.594,
|
| 178 |
+
"eval_openbookqa_pairs_steps_per_second": 3.275,
|
| 179 |
+
"step": 27
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.1524347212420607,
|
| 183 |
+
"eval_msmarco_pairs_loss": 6.937691688537598,
|
| 184 |
+
"eval_msmarco_pairs_runtime": 1.3091,
|
| 185 |
+
"eval_msmarco_pairs_samples_per_second": 97.779,
|
| 186 |
+
"eval_msmarco_pairs_steps_per_second": 1.528,
|
| 187 |
+
"step": 27
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.1524347212420607,
|
| 191 |
+
"eval_nq_pairs_loss": 6.794108867645264,
|
| 192 |
+
"eval_nq_pairs_runtime": 2.3968,
|
| 193 |
+
"eval_nq_pairs_samples_per_second": 53.404,
|
| 194 |
+
"eval_nq_pairs_steps_per_second": 0.834,
|
| 195 |
+
"step": 27
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1524347212420607,
|
| 199 |
+
"eval_trivia_pairs_loss": 6.3355631828308105,
|
| 200 |
+
"eval_trivia_pairs_runtime": 4.4974,
|
| 201 |
+
"eval_trivia_pairs_samples_per_second": 28.461,
|
| 202 |
+
"eval_trivia_pairs_steps_per_second": 0.445,
|
| 203 |
+
"step": 27
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.1524347212420607,
|
| 207 |
+
"eval_gooaq_pairs_loss": 6.405998706817627,
|
| 208 |
+
"eval_gooaq_pairs_runtime": 0.8745,
|
| 209 |
+
"eval_gooaq_pairs_samples_per_second": 146.37,
|
| 210 |
+
"eval_gooaq_pairs_steps_per_second": 2.287,
|
| 211 |
+
"step": 27
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.1524347212420607,
|
| 215 |
+
"eval_paws-pos_loss": 2.2308223247528076,
|
| 216 |
+
"eval_paws-pos_runtime": 0.6998,
|
| 217 |
+
"eval_paws-pos_samples_per_second": 182.908,
|
| 218 |
+
"eval_paws-pos_steps_per_second": 2.858,
|
| 219 |
+
"step": 27
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16937191249117856,
|
| 223 |
+
"grad_norm": 5.885251522064209,
|
| 224 |
+
"learning_rate": 6.818181818181818e-06,
|
| 225 |
+
"loss": 5.7653,
|
| 226 |
+
"step": 30
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1863091037402964,
|
| 230 |
+
"grad_norm": 7.357480049133301,
|
| 231 |
+
"learning_rate": 7.500000000000001e-06,
|
| 232 |
+
"loss": 6.1259,
|
| 233 |
+
"step": 33
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.20324629498941427,
|
| 237 |
+
"grad_norm": 7.321795463562012,
|
| 238 |
+
"learning_rate": 8.181818181818183e-06,
|
| 239 |
+
"loss": 5.7539,
|
| 240 |
+
"step": 36
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.22018348623853212,
|
| 244 |
+
"grad_norm": 4.239792346954346,
|
| 245 |
+
"learning_rate": 8.863636363636365e-06,
|
| 246 |
+
"loss": 6.0131,
|
| 247 |
+
"step": 39
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23712067748764998,
|
| 251 |
+
"grad_norm": 3.9554407596588135,
|
| 252 |
+
"learning_rate": 9.545454545454547e-06,
|
| 253 |
+
"loss": 6.0074,
|
| 254 |
+
"step": 42
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.25405786873676783,
|
| 258 |
+
"grad_norm": 4.406026840209961,
|
| 259 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 260 |
+
"loss": 5.7125,
|
| 261 |
+
"step": 45
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2709950599858857,
|
| 265 |
+
"grad_norm": 7.235893249511719,
|
| 266 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 267 |
+
"loss": 5.5634,
|
| 268 |
+
"step": 48
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.28793225123500354,
|
| 272 |
+
"grad_norm": 5.330288410186768,
|
| 273 |
+
"learning_rate": 1.1590909090909093e-05,
|
| 274 |
+
"loss": 5.2924,
|
| 275 |
+
"step": 51
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3048694424841214,
|
| 279 |
+
"grad_norm": 7.216403961181641,
|
| 280 |
+
"learning_rate": 1.2272727272727274e-05,
|
| 281 |
+
"loss": 5.2286,
|
| 282 |
+
"step": 54
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3048694424841214,
|
| 286 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 287 |
+
"eval_NLI-v2_dot_accuracy": 0.046875,
|
| 288 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 289 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 290 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 291 |
+
"eval_VitaminC_cosine_accuracy": 0.54296875,
|
| 292 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.9328227043151855,
|
| 293 |
+
"eval_VitaminC_cosine_ap": 0.5212059026196154,
|
| 294 |
+
"eval_VitaminC_cosine_f1": 0.6576819407008085,
|
| 295 |
+
"eval_VitaminC_cosine_f1_threshold": 0.7373804450035095,
|
| 296 |
+
"eval_VitaminC_cosine_precision": 0.49193548387096775,
|
| 297 |
+
"eval_VitaminC_cosine_recall": 0.991869918699187,
|
| 298 |
+
"eval_VitaminC_dot_accuracy": 0.55078125,
|
| 299 |
+
"eval_VitaminC_dot_accuracy_threshold": 418.2774658203125,
|
| 300 |
+
"eval_VitaminC_dot_ap": 0.5160594099493883,
|
| 301 |
+
"eval_VitaminC_dot_f1": 0.6521739130434782,
|
| 302 |
+
"eval_VitaminC_dot_f1_threshold": 291.5081481933594,
|
| 303 |
+
"eval_VitaminC_dot_precision": 0.4897959183673469,
|
| 304 |
+
"eval_VitaminC_dot_recall": 0.975609756097561,
|
| 305 |
+
"eval_VitaminC_euclidean_accuracy": 0.5390625,
|
| 306 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 8.120429039001465,
|
| 307 |
+
"eval_VitaminC_euclidean_ap": 0.5224837623095228,
|
| 308 |
+
"eval_VitaminC_euclidean_f1": 0.6576819407008085,
|
| 309 |
+
"eval_VitaminC_euclidean_f1_threshold": 14.879999160766602,
|
| 310 |
+
"eval_VitaminC_euclidean_precision": 0.49193548387096775,
|
| 311 |
+
"eval_VitaminC_euclidean_recall": 0.991869918699187,
|
| 312 |
+
"eval_VitaminC_manhattan_accuracy": 0.53515625,
|
| 313 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 137.40658569335938,
|
| 314 |
+
"eval_VitaminC_manhattan_ap": 0.5186382518671783,
|
| 315 |
+
"eval_VitaminC_manhattan_f1": 0.6576086956521738,
|
| 316 |
+
"eval_VitaminC_manhattan_f1_threshold": 263.32452392578125,
|
| 317 |
+
"eval_VitaminC_manhattan_precision": 0.49387755102040815,
|
| 318 |
+
"eval_VitaminC_manhattan_recall": 0.983739837398374,
|
| 319 |
+
"eval_VitaminC_max_accuracy": 0.55078125,
|
| 320 |
+
"eval_VitaminC_max_accuracy_threshold": 418.2774658203125,
|
| 321 |
+
"eval_VitaminC_max_ap": 0.5224837623095228,
|
| 322 |
+
"eval_VitaminC_max_f1": 0.6576819407008085,
|
| 323 |
+
"eval_VitaminC_max_f1_threshold": 291.5081481933594,
|
| 324 |
+
"eval_VitaminC_max_precision": 0.49387755102040815,
|
| 325 |
+
"eval_VitaminC_max_recall": 0.991869918699187,
|
| 326 |
+
"eval_sequential_score": 0.5224837623095228,
|
| 327 |
+
"eval_sts-test_pearson_cosine": 0.14377091128453176,
|
| 328 |
+
"eval_sts-test_pearson_dot": 0.24728387094758872,
|
| 329 |
+
"eval_sts-test_pearson_euclidean": 0.14604155960515372,
|
| 330 |
+
"eval_sts-test_pearson_manhattan": 0.1446467532231986,
|
| 331 |
+
"eval_sts-test_pearson_max": 0.24728387094758872,
|
| 332 |
+
"eval_sts-test_spearman_cosine": 0.1968510434344728,
|
| 333 |
+
"eval_sts-test_spearman_dot": 0.29467218283745694,
|
| 334 |
+
"eval_sts-test_spearman_euclidean": 0.17218164683969664,
|
| 335 |
+
"eval_sts-test_spearman_manhattan": 0.17741843340856742,
|
| 336 |
+
"eval_sts-test_spearman_max": 0.29467218283745694,
|
| 337 |
+
"eval_vitaminc-pairs_loss": 2.664700746536255,
|
| 338 |
+
"eval_vitaminc-pairs_runtime": 1.4487,
|
| 339 |
+
"eval_vitaminc-pairs_samples_per_second": 74.551,
|
| 340 |
+
"eval_vitaminc-pairs_steps_per_second": 1.381,
|
| 341 |
+
"step": 54
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.3048694424841214,
|
| 345 |
+
"eval_negation-triplets_loss": 4.6218037605285645,
|
| 346 |
+
"eval_negation-triplets_runtime": 0.2971,
|
| 347 |
+
"eval_negation-triplets_samples_per_second": 215.438,
|
| 348 |
+
"eval_negation-triplets_steps_per_second": 3.366,
|
| 349 |
+
"step": 54
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.3048694424841214,
|
| 353 |
+
"eval_scitail-pairs-pos_loss": 1.2413936853408813,
|
| 354 |
+
"eval_scitail-pairs-pos_runtime": 0.372,
|
| 355 |
+
"eval_scitail-pairs-pos_samples_per_second": 145.175,
|
| 356 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.688,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.3048694424841214,
|
| 361 |
+
"eval_xsum-pairs_loss": 5.249766826629639,
|
| 362 |
+
"eval_xsum-pairs_runtime": 3.1506,
|
| 363 |
+
"eval_xsum-pairs_samples_per_second": 40.627,
|
| 364 |
+
"eval_xsum-pairs_steps_per_second": 0.635,
|
| 365 |
+
"step": 54
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.3048694424841214,
|
| 369 |
+
"eval_sciq_pairs_loss": 0.2961578667163849,
|
| 370 |
+
"eval_sciq_pairs_runtime": 3.2909,
|
| 371 |
+
"eval_sciq_pairs_samples_per_second": 38.895,
|
| 372 |
+
"eval_sciq_pairs_steps_per_second": 0.608,
|
| 373 |
+
"step": 54
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3048694424841214,
|
| 377 |
+
"eval_qasc_pairs_loss": 2.530872344970703,
|
| 378 |
+
"eval_qasc_pairs_runtime": 0.6255,
|
| 379 |
+
"eval_qasc_pairs_samples_per_second": 204.63,
|
| 380 |
+
"eval_qasc_pairs_steps_per_second": 3.197,
|
| 381 |
+
"step": 54
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3048694424841214,
|
| 385 |
+
"eval_openbookqa_pairs_loss": 3.8855104446411133,
|
| 386 |
+
"eval_openbookqa_pairs_runtime": 0.5742,
|
| 387 |
+
"eval_openbookqa_pairs_samples_per_second": 222.914,
|
| 388 |
+
"eval_openbookqa_pairs_steps_per_second": 3.483,
|
| 389 |
+
"step": 54
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3048694424841214,
|
| 393 |
+
"eval_msmarco_pairs_loss": 5.246406555175781,
|
| 394 |
+
"eval_msmarco_pairs_runtime": 1.2872,
|
| 395 |
+
"eval_msmarco_pairs_samples_per_second": 99.442,
|
| 396 |
+
"eval_msmarco_pairs_steps_per_second": 1.554,
|
| 397 |
+
"step": 54
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.3048694424841214,
|
| 401 |
+
"eval_nq_pairs_loss": 5.332630157470703,
|
| 402 |
+
"eval_nq_pairs_runtime": 2.3739,
|
| 403 |
+
"eval_nq_pairs_samples_per_second": 53.92,
|
| 404 |
+
"eval_nq_pairs_steps_per_second": 0.843,
|
| 405 |
+
"step": 54
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.3048694424841214,
|
| 409 |
+
"eval_trivia_pairs_loss": 5.647429943084717,
|
| 410 |
+
"eval_trivia_pairs_runtime": 4.4729,
|
| 411 |
+
"eval_trivia_pairs_samples_per_second": 28.617,
|
| 412 |
+
"eval_trivia_pairs_steps_per_second": 0.447,
|
| 413 |
+
"step": 54
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.3048694424841214,
|
| 417 |
+
"eval_gooaq_pairs_loss": 5.225871562957764,
|
| 418 |
+
"eval_gooaq_pairs_runtime": 0.8715,
|
| 419 |
+
"eval_gooaq_pairs_samples_per_second": 146.868,
|
| 420 |
+
"eval_gooaq_pairs_steps_per_second": 2.295,
|
| 421 |
+
"step": 54
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.3048694424841214,
|
| 425 |
+
"eval_paws-pos_loss": 0.8335962891578674,
|
| 426 |
+
"eval_paws-pos_runtime": 0.6844,
|
| 427 |
+
"eval_paws-pos_samples_per_second": 187.036,
|
| 428 |
+
"eval_paws-pos_steps_per_second": 2.922,
|
| 429 |
+
"step": 54
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32180663373323926,
|
| 433 |
+
"grad_norm": 6.847682952880859,
|
| 434 |
+
"learning_rate": 1.2954545454545455e-05,
|
| 435 |
+
"loss": 4.4811,
|
| 436 |
+
"step": 57
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3387438249823571,
|
| 440 |
+
"grad_norm": 8.383002281188965,
|
| 441 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 442 |
+
"loss": 4.4239,
|
| 443 |
+
"step": 60
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.35568101623147497,
|
| 447 |
+
"grad_norm": 7.014843463897705,
|
| 448 |
+
"learning_rate": 1.431818181818182e-05,
|
| 449 |
+
"loss": 4.0273,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3726182074805928,
|
| 454 |
+
"grad_norm": 5.9739885330200195,
|
| 455 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 456 |
+
"loss": 3.4508,
|
| 457 |
+
"step": 66
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3895553987297107,
|
| 461 |
+
"grad_norm": 11.202752113342285,
|
| 462 |
+
"learning_rate": 1.5681818181818182e-05,
|
| 463 |
+
"loss": 3.9702,
|
| 464 |
+
"step": 69
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.40649258997882853,
|
| 468 |
+
"grad_norm": 7.064818859100342,
|
| 469 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 470 |
+
"loss": 3.5295,
|
| 471 |
+
"step": 72
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4234297812279464,
|
| 475 |
+
"grad_norm": 5.912719249725342,
|
| 476 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 477 |
+
"loss": 3.6395,
|
| 478 |
+
"step": 75
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.44036697247706424,
|
| 482 |
+
"grad_norm": 5.033207893371582,
|
| 483 |
+
"learning_rate": 1.772727272727273e-05,
|
| 484 |
+
"loss": 3.2398,
|
| 485 |
+
"step": 78
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.4573041637261821,
|
| 489 |
+
"grad_norm": 5.218384265899658,
|
| 490 |
+
"learning_rate": 1.840909090909091e-05,
|
| 491 |
+
"loss": 3.116,
|
| 492 |
+
"step": 81
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.4573041637261821,
|
| 496 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 497 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 498 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 499 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 500 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 501 |
+
"eval_VitaminC_cosine_accuracy": 0.5546875,
|
| 502 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.9041332006454468,
|
| 503 |
+
"eval_VitaminC_cosine_ap": 0.5292859731465609,
|
| 504 |
+
"eval_VitaminC_cosine_f1": 0.6542553191489362,
|
| 505 |
+
"eval_VitaminC_cosine_f1_threshold": 0.452939510345459,
|
| 506 |
+
"eval_VitaminC_cosine_precision": 0.48616600790513836,
|
| 507 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 508 |
+
"eval_VitaminC_dot_accuracy": 0.5546875,
|
| 509 |
+
"eval_VitaminC_dot_accuracy_threshold": 414.42559814453125,
|
| 510 |
+
"eval_VitaminC_dot_ap": 0.5222732504955002,
|
| 511 |
+
"eval_VitaminC_dot_f1": 0.6542553191489362,
|
| 512 |
+
"eval_VitaminC_dot_f1_threshold": 212.6934814453125,
|
| 513 |
+
"eval_VitaminC_dot_precision": 0.48616600790513836,
|
| 514 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 515 |
+
"eval_VitaminC_euclidean_accuracy": 0.5546875,
|
| 516 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 9.18377685546875,
|
| 517 |
+
"eval_VitaminC_euclidean_ap": 0.5291787221346742,
|
| 518 |
+
"eval_VitaminC_euclidean_f1": 0.6542553191489362,
|
| 519 |
+
"eval_VitaminC_euclidean_f1_threshold": 22.683509826660156,
|
| 520 |
+
"eval_VitaminC_euclidean_precision": 0.48616600790513836,
|
| 521 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 522 |
+
"eval_VitaminC_manhattan_accuracy": 0.55859375,
|
| 523 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 173.8212127685547,
|
| 524 |
+
"eval_VitaminC_manhattan_ap": 0.5305698453165033,
|
| 525 |
+
"eval_VitaminC_manhattan_f1": 0.6542553191489362,
|
| 526 |
+
"eval_VitaminC_manhattan_f1_threshold": 415.5366516113281,
|
| 527 |
+
"eval_VitaminC_manhattan_precision": 0.48616600790513836,
|
| 528 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 529 |
+
"eval_VitaminC_max_accuracy": 0.55859375,
|
| 530 |
+
"eval_VitaminC_max_accuracy_threshold": 414.42559814453125,
|
| 531 |
+
"eval_VitaminC_max_ap": 0.5305698453165033,
|
| 532 |
+
"eval_VitaminC_max_f1": 0.6542553191489362,
|
| 533 |
+
"eval_VitaminC_max_f1_threshold": 415.5366516113281,
|
| 534 |
+
"eval_VitaminC_max_precision": 0.48616600790513836,
|
| 535 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 536 |
+
"eval_sequential_score": 0.5305698453165033,
|
| 537 |
+
"eval_sts-test_pearson_cosine": 0.45494716382349193,
|
| 538 |
+
"eval_sts-test_pearson_dot": 0.44837123659858896,
|
| 539 |
+
"eval_sts-test_pearson_euclidean": 0.4480861256491879,
|
| 540 |
+
"eval_sts-test_pearson_manhattan": 0.4417008219313264,
|
| 541 |
+
"eval_sts-test_pearson_max": 0.45494716382349193,
|
| 542 |
+
"eval_sts-test_spearman_cosine": 0.48921418507251446,
|
| 543 |
+
"eval_sts-test_spearman_dot": 0.46707725062744593,
|
| 544 |
+
"eval_sts-test_spearman_euclidean": 0.4610824798409968,
|
| 545 |
+
"eval_sts-test_spearman_manhattan": 0.46068648052845956,
|
| 546 |
+
"eval_sts-test_spearman_max": 0.48921418507251446,
|
| 547 |
+
"eval_vitaminc-pairs_loss": 2.5043575763702393,
|
| 548 |
+
"eval_vitaminc-pairs_runtime": 1.4778,
|
| 549 |
+
"eval_vitaminc-pairs_samples_per_second": 73.079,
|
| 550 |
+
"eval_vitaminc-pairs_steps_per_second": 1.353,
|
| 551 |
+
"step": 81
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.4573041637261821,
|
| 555 |
+
"eval_negation-triplets_loss": 3.4229447841644287,
|
| 556 |
+
"eval_negation-triplets_runtime": 0.2991,
|
| 557 |
+
"eval_negation-triplets_samples_per_second": 213.954,
|
| 558 |
+
"eval_negation-triplets_steps_per_second": 3.343,
|
| 559 |
+
"step": 81
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.4573041637261821,
|
| 563 |
+
"eval_scitail-pairs-pos_loss": 0.2784869372844696,
|
| 564 |
+
"eval_scitail-pairs-pos_runtime": 0.3633,
|
| 565 |
+
"eval_scitail-pairs-pos_samples_per_second": 148.649,
|
| 566 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.753,
|
| 567 |
+
"step": 81
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.4573041637261821,
|
| 571 |
+
"eval_xsum-pairs_loss": 2.428964614868164,
|
| 572 |
+
"eval_xsum-pairs_runtime": 3.1548,
|
| 573 |
+
"eval_xsum-pairs_samples_per_second": 40.573,
|
| 574 |
+
"eval_xsum-pairs_steps_per_second": 0.634,
|
| 575 |
+
"step": 81
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.4573041637261821,
|
| 579 |
+
"eval_sciq_pairs_loss": 0.15256048738956451,
|
| 580 |
+
"eval_sciq_pairs_runtime": 3.2432,
|
| 581 |
+
"eval_sciq_pairs_samples_per_second": 39.467,
|
| 582 |
+
"eval_sciq_pairs_steps_per_second": 0.617,
|
| 583 |
+
"step": 81
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4573041637261821,
|
| 587 |
+
"eval_qasc_pairs_loss": 1.2902077436447144,
|
| 588 |
+
"eval_qasc_pairs_runtime": 0.6211,
|
| 589 |
+
"eval_qasc_pairs_samples_per_second": 206.085,
|
| 590 |
+
"eval_qasc_pairs_steps_per_second": 3.22,
|
| 591 |
+
"step": 81
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.4573041637261821,
|
| 595 |
+
"eval_openbookqa_pairs_loss": 2.4784862995147705,
|
| 596 |
+
"eval_openbookqa_pairs_runtime": 0.5758,
|
| 597 |
+
"eval_openbookqa_pairs_samples_per_second": 222.308,
|
| 598 |
+
"eval_openbookqa_pairs_steps_per_second": 3.474,
|
| 599 |
+
"step": 81
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.4573041637261821,
|
| 603 |
+
"eval_msmarco_pairs_loss": 2.967724084854126,
|
| 604 |
+
"eval_msmarco_pairs_runtime": 1.2944,
|
| 605 |
+
"eval_msmarco_pairs_samples_per_second": 98.885,
|
| 606 |
+
"eval_msmarco_pairs_steps_per_second": 1.545,
|
| 607 |
+
"step": 81
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.4573041637261821,
|
| 611 |
+
"eval_nq_pairs_loss": 3.358661413192749,
|
| 612 |
+
"eval_nq_pairs_runtime": 2.3827,
|
| 613 |
+
"eval_nq_pairs_samples_per_second": 53.722,
|
| 614 |
+
"eval_nq_pairs_steps_per_second": 0.839,
|
| 615 |
+
"step": 81
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.4573041637261821,
|
| 619 |
+
"eval_trivia_pairs_loss": 3.1391680240631104,
|
| 620 |
+
"eval_trivia_pairs_runtime": 4.4155,
|
| 621 |
+
"eval_trivia_pairs_samples_per_second": 28.989,
|
| 622 |
+
"eval_trivia_pairs_steps_per_second": 0.453,
|
| 623 |
+
"step": 81
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.4573041637261821,
|
| 627 |
+
"eval_gooaq_pairs_loss": 2.8774912357330322,
|
| 628 |
+
"eval_gooaq_pairs_runtime": 0.8746,
|
| 629 |
+
"eval_gooaq_pairs_samples_per_second": 146.346,
|
| 630 |
+
"eval_gooaq_pairs_steps_per_second": 2.287,
|
| 631 |
+
"step": 81
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.4573041637261821,
|
| 635 |
+
"eval_paws-pos_loss": 0.19754411280155182,
|
| 636 |
+
"eval_paws-pos_runtime": 0.684,
|
| 637 |
+
"eval_paws-pos_samples_per_second": 187.141,
|
| 638 |
+
"eval_paws-pos_steps_per_second": 2.924,
|
| 639 |
+
"step": 81
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.47424135497529996,
|
| 643 |
+
"grad_norm": 5.149569988250732,
|
| 644 |
+
"learning_rate": 1.9090909090909094e-05,
|
| 645 |
+
"loss": 2.6049,
|
| 646 |
+
"step": 84
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4911785462244178,
|
| 650 |
+
"grad_norm": 5.012928009033203,
|
| 651 |
+
"learning_rate": 1.9772727272727274e-05,
|
| 652 |
+
"loss": 2.7738,
|
| 653 |
+
"step": 87
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5081157374735357,
|
| 657 |
+
"grad_norm": 4.880725383758545,
|
| 658 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 659 |
+
"loss": 2.5416,
|
| 660 |
+
"step": 90
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5250529287226535,
|
| 664 |
+
"grad_norm": 5.618528366088867,
|
| 665 |
+
"learning_rate": 2.113636363636364e-05,
|
| 666 |
+
"loss": 2.3913,
|
| 667 |
+
"step": 93
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5419901199717714,
|
| 671 |
+
"grad_norm": 5.020515441894531,
|
| 672 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 673 |
+
"loss": 2.3144,
|
| 674 |
+
"step": 96
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5589273112208892,
|
| 678 |
+
"grad_norm": 4.818451404571533,
|
| 679 |
+
"learning_rate": 2.25e-05,
|
| 680 |
+
"loss": 2.1857,
|
| 681 |
+
"step": 99
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5758645024700071,
|
| 685 |
+
"grad_norm": 5.094771385192871,
|
| 686 |
+
"learning_rate": 2.3181818181818185e-05,
|
| 687 |
+
"loss": 1.8881,
|
| 688 |
+
"step": 102
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.592801693719125,
|
| 692 |
+
"grad_norm": 3.795962333679199,
|
| 693 |
+
"learning_rate": 2.3863636363636365e-05,
|
| 694 |
+
"loss": 2.2699,
|
| 695 |
+
"step": 105
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6097388849682428,
|
| 699 |
+
"grad_norm": 4.46245813369751,
|
| 700 |
+
"learning_rate": 2.454545454545455e-05,
|
| 701 |
+
"loss": 2.1425,
|
| 702 |
+
"step": 108
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6097388849682428,
|
| 706 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 707 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 708 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 709 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 710 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 711 |
+
"eval_VitaminC_cosine_accuracy": 0.5546875,
|
| 712 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.8830112218856812,
|
| 713 |
+
"eval_VitaminC_cosine_ap": 0.5302172957740995,
|
| 714 |
+
"eval_VitaminC_cosine_f1": 0.6558265582655827,
|
| 715 |
+
"eval_VitaminC_cosine_f1_threshold": 0.5253933668136597,
|
| 716 |
+
"eval_VitaminC_cosine_precision": 0.491869918699187,
|
| 717 |
+
"eval_VitaminC_cosine_recall": 0.983739837398374,
|
| 718 |
+
"eval_VitaminC_dot_accuracy": 0.5390625,
|
| 719 |
+
"eval_VitaminC_dot_accuracy_threshold": 427.5576171875,
|
| 720 |
+
"eval_VitaminC_dot_ap": 0.517120157327104,
|
| 721 |
+
"eval_VitaminC_dot_f1": 0.6542553191489362,
|
| 722 |
+
"eval_VitaminC_dot_f1_threshold": 175.80963134765625,
|
| 723 |
+
"eval_VitaminC_dot_precision": 0.48616600790513836,
|
| 724 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 725 |
+
"eval_VitaminC_euclidean_accuracy": 0.5625,
|
| 726 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 10.817148208618164,
|
| 727 |
+
"eval_VitaminC_euclidean_ap": 0.532255112376416,
|
| 728 |
+
"eval_VitaminC_euclidean_f1": 0.6558265582655827,
|
| 729 |
+
"eval_VitaminC_euclidean_f1_threshold": 21.10729217529297,
|
| 730 |
+
"eval_VitaminC_euclidean_precision": 0.491869918699187,
|
| 731 |
+
"eval_VitaminC_euclidean_recall": 0.983739837398374,
|
| 732 |
+
"eval_VitaminC_manhattan_accuracy": 0.5546875,
|
| 733 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 224.70416259765625,
|
| 734 |
+
"eval_VitaminC_manhattan_ap": 0.5298930718604624,
|
| 735 |
+
"eval_VitaminC_manhattan_f1": 0.6558265582655827,
|
| 736 |
+
"eval_VitaminC_manhattan_f1_threshold": 415.3311767578125,
|
| 737 |
+
"eval_VitaminC_manhattan_precision": 0.491869918699187,
|
| 738 |
+
"eval_VitaminC_manhattan_recall": 0.983739837398374,
|
| 739 |
+
"eval_VitaminC_max_accuracy": 0.5625,
|
| 740 |
+
"eval_VitaminC_max_accuracy_threshold": 427.5576171875,
|
| 741 |
+
"eval_VitaminC_max_ap": 0.532255112376416,
|
| 742 |
+
"eval_VitaminC_max_f1": 0.6558265582655827,
|
| 743 |
+
"eval_VitaminC_max_f1_threshold": 415.3311767578125,
|
| 744 |
+
"eval_VitaminC_max_precision": 0.491869918699187,
|
| 745 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 746 |
+
"eval_sequential_score": 0.532255112376416,
|
| 747 |
+
"eval_sts-test_pearson_cosine": 0.755963151531783,
|
| 748 |
+
"eval_sts-test_pearson_dot": 0.7384823091540473,
|
| 749 |
+
"eval_sts-test_pearson_euclidean": 0.764089555623164,
|
| 750 |
+
"eval_sts-test_pearson_manhattan": 0.7670467479701304,
|
| 751 |
+
"eval_sts-test_pearson_max": 0.7670467479701304,
|
| 752 |
+
"eval_sts-test_spearman_cosine": 0.7806331583677342,
|
| 753 |
+
"eval_sts-test_spearman_dot": 0.7442842883778696,
|
| 754 |
+
"eval_sts-test_spearman_euclidean": 0.7674205303105437,
|
| 755 |
+
"eval_sts-test_spearman_manhattan": 0.7664974867050092,
|
| 756 |
+
"eval_sts-test_spearman_max": 0.7806331583677342,
|
| 757 |
+
"eval_vitaminc-pairs_loss": 2.721674919128418,
|
| 758 |
+
"eval_vitaminc-pairs_runtime": 1.4468,
|
| 759 |
+
"eval_vitaminc-pairs_samples_per_second": 74.65,
|
| 760 |
+
"eval_vitaminc-pairs_steps_per_second": 1.382,
|
| 761 |
+
"step": 108
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.6097388849682428,
|
| 765 |
+
"eval_negation-triplets_loss": 2.338909387588501,
|
| 766 |
+
"eval_negation-triplets_runtime": 0.3017,
|
| 767 |
+
"eval_negation-triplets_samples_per_second": 212.101,
|
| 768 |
+
"eval_negation-triplets_steps_per_second": 3.314,
|
| 769 |
+
"step": 108
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.6097388849682428,
|
| 773 |
+
"eval_scitail-pairs-pos_loss": 0.23291125893592834,
|
| 774 |
+
"eval_scitail-pairs-pos_runtime": 0.3664,
|
| 775 |
+
"eval_scitail-pairs-pos_samples_per_second": 147.385,
|
| 776 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.729,
|
| 777 |
+
"step": 108
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6097388849682428,
|
| 781 |
+
"eval_xsum-pairs_loss": 1.2065516710281372,
|
| 782 |
+
"eval_xsum-pairs_runtime": 3.1488,
|
| 783 |
+
"eval_xsum-pairs_samples_per_second": 40.65,
|
| 784 |
+
"eval_xsum-pairs_steps_per_second": 0.635,
|
| 785 |
+
"step": 108
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.6097388849682428,
|
| 789 |
+
"eval_sciq_pairs_loss": 0.09487833082675934,
|
| 790 |
+
"eval_sciq_pairs_runtime": 3.2618,
|
| 791 |
+
"eval_sciq_pairs_samples_per_second": 39.242,
|
| 792 |
+
"eval_sciq_pairs_steps_per_second": 0.613,
|
| 793 |
+
"step": 108
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6097388849682428,
|
| 797 |
+
"eval_qasc_pairs_loss": 0.8461999297142029,
|
| 798 |
+
"eval_qasc_pairs_runtime": 0.6246,
|
| 799 |
+
"eval_qasc_pairs_samples_per_second": 204.93,
|
| 800 |
+
"eval_qasc_pairs_steps_per_second": 3.202,
|
| 801 |
+
"step": 108
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6097388849682428,
|
| 805 |
+
"eval_openbookqa_pairs_loss": 1.5739191770553589,
|
| 806 |
+
"eval_openbookqa_pairs_runtime": 0.5751,
|
| 807 |
+
"eval_openbookqa_pairs_samples_per_second": 222.568,
|
| 808 |
+
"eval_openbookqa_pairs_steps_per_second": 3.478,
|
| 809 |
+
"step": 108
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.6097388849682428,
|
| 813 |
+
"eval_msmarco_pairs_loss": 1.6446179151535034,
|
| 814 |
+
"eval_msmarco_pairs_runtime": 1.2828,
|
| 815 |
+
"eval_msmarco_pairs_samples_per_second": 99.784,
|
| 816 |
+
"eval_msmarco_pairs_steps_per_second": 1.559,
|
| 817 |
+
"step": 108
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.6097388849682428,
|
| 821 |
+
"eval_nq_pairs_loss": 2.364896535873413,
|
| 822 |
+
"eval_nq_pairs_runtime": 2.3802,
|
| 823 |
+
"eval_nq_pairs_samples_per_second": 53.777,
|
| 824 |
+
"eval_nq_pairs_steps_per_second": 0.84,
|
| 825 |
+
"step": 108
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.6097388849682428,
|
| 829 |
+
"eval_trivia_pairs_loss": 1.7080069780349731,
|
| 830 |
+
"eval_trivia_pairs_runtime": 4.4372,
|
| 831 |
+
"eval_trivia_pairs_samples_per_second": 28.847,
|
| 832 |
+
"eval_trivia_pairs_steps_per_second": 0.451,
|
| 833 |
+
"step": 108
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.6097388849682428,
|
| 837 |
+
"eval_gooaq_pairs_loss": 1.7924479246139526,
|
| 838 |
+
"eval_gooaq_pairs_runtime": 0.8761,
|
| 839 |
+
"eval_gooaq_pairs_samples_per_second": 146.094,
|
| 840 |
+
"eval_gooaq_pairs_steps_per_second": 2.283,
|
| 841 |
+
"step": 108
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.6097388849682428,
|
| 845 |
+
"eval_paws-pos_loss": 0.08000019192695618,
|
| 846 |
+
"eval_paws-pos_runtime": 0.6839,
|
| 847 |
+
"eval_paws-pos_samples_per_second": 187.168,
|
| 848 |
+
"eval_paws-pos_steps_per_second": 2.924,
|
| 849 |
+
"step": 108
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6266760762173607,
|
| 853 |
+
"grad_norm": 4.418070316314697,
|
| 854 |
+
"learning_rate": 2.5227272727272732e-05,
|
| 855 |
+
"loss": 2.1276,
|
| 856 |
+
"step": 111
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6436132674664785,
|
| 860 |
+
"grad_norm": 4.3495259284973145,
|
| 861 |
+
"learning_rate": 2.590909090909091e-05,
|
| 862 |
+
"loss": 1.7531,
|
| 863 |
+
"step": 114
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6605504587155964,
|
| 867 |
+
"grad_norm": 4.294332027435303,
|
| 868 |
+
"learning_rate": 2.6590909090909093e-05,
|
| 869 |
+
"loss": 2.0179,
|
| 870 |
+
"step": 117
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6774876499647142,
|
| 874 |
+
"grad_norm": 3.4215610027313232,
|
| 875 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 876 |
+
"loss": 1.5305,
|
| 877 |
+
"step": 120
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6944248412138321,
|
| 881 |
+
"grad_norm": 4.37844181060791,
|
| 882 |
+
"learning_rate": 2.7954545454545457e-05,
|
| 883 |
+
"loss": 1.6925,
|
| 884 |
+
"step": 123
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.7113620324629499,
|
| 888 |
+
"grad_norm": 4.019878387451172,
|
| 889 |
+
"learning_rate": 2.863636363636364e-05,
|
| 890 |
+
"loss": 1.5248,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7282992237120678,
|
| 895 |
+
"grad_norm": 4.662445068359375,
|
| 896 |
+
"learning_rate": 2.931818181818182e-05,
|
| 897 |
+
"loss": 1.523,
|
| 898 |
+
"step": 129
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7452364149611856,
|
| 902 |
+
"grad_norm": 4.6323161125183105,
|
| 903 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 904 |
+
"loss": 1.5474,
|
| 905 |
+
"step": 132
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.7621736062103035,
|
| 909 |
+
"grad_norm": 4.586575984954834,
|
| 910 |
+
"learning_rate": 3.068181818181819e-05,
|
| 911 |
+
"loss": 1.7221,
|
| 912 |
+
"step": 135
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.7621736062103035,
|
| 916 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 917 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 918 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 919 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 920 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 921 |
+
"eval_VitaminC_cosine_accuracy": 0.56640625,
|
| 922 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.8478574156761169,
|
| 923 |
+
"eval_VitaminC_cosine_ap": 0.5325579595957614,
|
| 924 |
+
"eval_VitaminC_cosine_f1": 0.6559999999999999,
|
| 925 |
+
"eval_VitaminC_cosine_f1_threshold": 0.35839784145355225,
|
| 926 |
+
"eval_VitaminC_cosine_precision": 0.4880952380952381,
|
| 927 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 928 |
+
"eval_VitaminC_dot_accuracy": 0.5625,
|
| 929 |
+
"eval_VitaminC_dot_accuracy_threshold": 366.9839172363281,
|
| 930 |
+
"eval_VitaminC_dot_ap": 0.5326813797607027,
|
| 931 |
+
"eval_VitaminC_dot_f1": 0.6559999999999999,
|
| 932 |
+
"eval_VitaminC_dot_f1_threshold": 157.35829162597656,
|
| 933 |
+
"eval_VitaminC_dot_precision": 0.4880952380952381,
|
| 934 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 935 |
+
"eval_VitaminC_euclidean_accuracy": 0.5625,
|
| 936 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 12.044445037841797,
|
| 937 |
+
"eval_VitaminC_euclidean_ap": 0.5304103559932005,
|
| 938 |
+
"eval_VitaminC_euclidean_f1": 0.6542553191489362,
|
| 939 |
+
"eval_VitaminC_euclidean_f1_threshold": 24.461441040039062,
|
| 940 |
+
"eval_VitaminC_euclidean_precision": 0.48616600790513836,
|
| 941 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 942 |
+
"eval_VitaminC_manhattan_accuracy": 0.5625,
|
| 943 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 239.24815368652344,
|
| 944 |
+
"eval_VitaminC_manhattan_ap": 0.5314780667834758,
|
| 945 |
+
"eval_VitaminC_manhattan_f1": 0.6575342465753424,
|
| 946 |
+
"eval_VitaminC_manhattan_f1_threshold": 400.6834716796875,
|
| 947 |
+
"eval_VitaminC_manhattan_precision": 0.49586776859504134,
|
| 948 |
+
"eval_VitaminC_manhattan_recall": 0.975609756097561,
|
| 949 |
+
"eval_VitaminC_max_accuracy": 0.56640625,
|
| 950 |
+
"eval_VitaminC_max_accuracy_threshold": 366.9839172363281,
|
| 951 |
+
"eval_VitaminC_max_ap": 0.5326813797607027,
|
| 952 |
+
"eval_VitaminC_max_f1": 0.6575342465753424,
|
| 953 |
+
"eval_VitaminC_max_f1_threshold": 400.6834716796875,
|
| 954 |
+
"eval_VitaminC_max_precision": 0.49586776859504134,
|
| 955 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 956 |
+
"eval_sequential_score": 0.5326813797607027,
|
| 957 |
+
"eval_sts-test_pearson_cosine": 0.7919597804368175,
|
| 958 |
+
"eval_sts-test_pearson_dot": 0.7994867531185785,
|
| 959 |
+
"eval_sts-test_pearson_euclidean": 0.8117960113303863,
|
| 960 |
+
"eval_sts-test_pearson_manhattan": 0.8144714466358016,
|
| 961 |
+
"eval_sts-test_pearson_max": 0.8144714466358016,
|
| 962 |
+
"eval_sts-test_spearman_cosine": 0.831478610786181,
|
| 963 |
+
"eval_sts-test_spearman_dot": 0.8192534746855707,
|
| 964 |
+
"eval_sts-test_spearman_euclidean": 0.8185577905406703,
|
| 965 |
+
"eval_sts-test_spearman_manhattan": 0.8154771593606782,
|
| 966 |
+
"eval_sts-test_spearman_max": 0.831478610786181,
|
| 967 |
+
"eval_vitaminc-pairs_loss": 2.852091073989868,
|
| 968 |
+
"eval_vitaminc-pairs_runtime": 1.4427,
|
| 969 |
+
"eval_vitaminc-pairs_samples_per_second": 74.858,
|
| 970 |
+
"eval_vitaminc-pairs_steps_per_second": 1.386,
|
| 971 |
+
"step": 135
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.7621736062103035,
|
| 975 |
+
"eval_negation-triplets_loss": 2.074247121810913,
|
| 976 |
+
"eval_negation-triplets_runtime": 0.3,
|
| 977 |
+
"eval_negation-triplets_samples_per_second": 213.353,
|
| 978 |
+
"eval_negation-triplets_steps_per_second": 3.334,
|
| 979 |
+
"step": 135
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.7621736062103035,
|
| 983 |
+
"eval_scitail-pairs-pos_loss": 0.2149849385023117,
|
| 984 |
+
"eval_scitail-pairs-pos_runtime": 0.3744,
|
| 985 |
+
"eval_scitail-pairs-pos_samples_per_second": 144.219,
|
| 986 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.671,
|
| 987 |
+
"step": 135
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.7621736062103035,
|
| 991 |
+
"eval_xsum-pairs_loss": 0.7706837058067322,
|
| 992 |
+
"eval_xsum-pairs_runtime": 3.1609,
|
| 993 |
+
"eval_xsum-pairs_samples_per_second": 40.495,
|
| 994 |
+
"eval_xsum-pairs_steps_per_second": 0.633,
|
| 995 |
+
"step": 135
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.7621736062103035,
|
| 999 |
+
"eval_sciq_pairs_loss": 0.07513368874788284,
|
| 1000 |
+
"eval_sciq_pairs_runtime": 3.2949,
|
| 1001 |
+
"eval_sciq_pairs_samples_per_second": 38.848,
|
| 1002 |
+
"eval_sciq_pairs_steps_per_second": 0.607,
|
| 1003 |
+
"step": 135
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7621736062103035,
|
| 1007 |
+
"eval_qasc_pairs_loss": 0.6355602741241455,
|
| 1008 |
+
"eval_qasc_pairs_runtime": 0.6392,
|
| 1009 |
+
"eval_qasc_pairs_samples_per_second": 200.246,
|
| 1010 |
+
"eval_qasc_pairs_steps_per_second": 3.129,
|
| 1011 |
+
"step": 135
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.7621736062103035,
|
| 1015 |
+
"eval_openbookqa_pairs_loss": 1.4014525413513184,
|
| 1016 |
+
"eval_openbookqa_pairs_runtime": 0.622,
|
| 1017 |
+
"eval_openbookqa_pairs_samples_per_second": 205.786,
|
| 1018 |
+
"eval_openbookqa_pairs_steps_per_second": 3.215,
|
| 1019 |
+
"step": 135
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.7621736062103035,
|
| 1023 |
+
"eval_msmarco_pairs_loss": 1.1524099111557007,
|
| 1024 |
+
"eval_msmarco_pairs_runtime": 1.31,
|
| 1025 |
+
"eval_msmarco_pairs_samples_per_second": 97.709,
|
| 1026 |
+
"eval_msmarco_pairs_steps_per_second": 1.527,
|
| 1027 |
+
"step": 135
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.7621736062103035,
|
| 1031 |
+
"eval_nq_pairs_loss": 1.7768574953079224,
|
| 1032 |
+
"eval_nq_pairs_runtime": 2.3979,
|
| 1033 |
+
"eval_nq_pairs_samples_per_second": 53.379,
|
| 1034 |
+
"eval_nq_pairs_steps_per_second": 0.834,
|
| 1035 |
+
"step": 135
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.7621736062103035,
|
| 1039 |
+
"eval_trivia_pairs_loss": 1.4495295286178589,
|
| 1040 |
+
"eval_trivia_pairs_runtime": 4.4194,
|
| 1041 |
+
"eval_trivia_pairs_samples_per_second": 28.964,
|
| 1042 |
+
"eval_trivia_pairs_steps_per_second": 0.453,
|
| 1043 |
+
"step": 135
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.7621736062103035,
|
| 1047 |
+
"eval_gooaq_pairs_loss": 1.3955378532409668,
|
| 1048 |
+
"eval_gooaq_pairs_runtime": 0.8788,
|
| 1049 |
+
"eval_gooaq_pairs_samples_per_second": 145.649,
|
| 1050 |
+
"eval_gooaq_pairs_steps_per_second": 2.276,
|
| 1051 |
+
"step": 135
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.7621736062103035,
|
| 1055 |
+
"eval_paws-pos_loss": 0.06006813049316406,
|
| 1056 |
+
"eval_paws-pos_runtime": 0.6896,
|
| 1057 |
+
"eval_paws-pos_samples_per_second": 185.603,
|
| 1058 |
+
"eval_paws-pos_steps_per_second": 2.9,
|
| 1059 |
+
"step": 135
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7791107974594214,
|
| 1063 |
+
"grad_norm": 3.864208936691284,
|
| 1064 |
+
"learning_rate": 3.1363636363636365e-05,
|
| 1065 |
+
"loss": 1.5366,
|
| 1066 |
+
"step": 138
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7960479887085392,
|
| 1070 |
+
"grad_norm": 3.837550640106201,
|
| 1071 |
+
"learning_rate": 3.204545454545455e-05,
|
| 1072 |
+
"loss": 1.3045,
|
| 1073 |
+
"step": 141
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8129851799576571,
|
| 1077 |
+
"grad_norm": 3.5258102416992188,
|
| 1078 |
+
"learning_rate": 3.272727272727273e-05,
|
| 1079 |
+
"loss": 1.1999,
|
| 1080 |
+
"step": 144
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8299223712067749,
|
| 1084 |
+
"grad_norm": 3.4431183338165283,
|
| 1085 |
+
"learning_rate": 3.340909090909091e-05,
|
| 1086 |
+
"loss": 1.3483,
|
| 1087 |
+
"step": 147
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8468595624558928,
|
| 1091 |
+
"grad_norm": 3.6455864906311035,
|
| 1092 |
+
"learning_rate": 3.409090909090909e-05,
|
| 1093 |
+
"loss": 1.2009,
|
| 1094 |
+
"step": 150
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8637967537050106,
|
| 1098 |
+
"grad_norm": 4.508525371551514,
|
| 1099 |
+
"learning_rate": 3.4772727272727276e-05,
|
| 1100 |
+
"loss": 1.4495,
|
| 1101 |
+
"step": 153
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8807339449541285,
|
| 1105 |
+
"grad_norm": 3.0432400703430176,
|
| 1106 |
+
"learning_rate": 3.545454545454546e-05,
|
| 1107 |
+
"loss": 1.2329,
|
| 1108 |
+
"step": 156
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8976711362032463,
|
| 1112 |
+
"grad_norm": 3.0190365314483643,
|
| 1113 |
+
"learning_rate": 3.613636363636364e-05,
|
| 1114 |
+
"loss": 1.1905,
|
| 1115 |
+
"step": 159
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.9146083274523642,
|
| 1119 |
+
"grad_norm": 3.74668288230896,
|
| 1120 |
+
"learning_rate": 3.681818181818182e-05,
|
| 1121 |
+
"loss": 1.277,
|
| 1122 |
+
"step": 162
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.9146083274523642,
|
| 1126 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 1127 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 1128 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 1129 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 1130 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 1131 |
+
"eval_VitaminC_cosine_accuracy": 0.57421875,
|
| 1132 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.8101799488067627,
|
| 1133 |
+
"eval_VitaminC_cosine_ap": 0.5298515171639175,
|
| 1134 |
+
"eval_VitaminC_cosine_f1": 0.6542553191489362,
|
| 1135 |
+
"eval_VitaminC_cosine_f1_threshold": 0.345889687538147,
|
| 1136 |
+
"eval_VitaminC_cosine_precision": 0.48616600790513836,
|
| 1137 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 1138 |
+
"eval_VitaminC_dot_accuracy": 0.55078125,
|
| 1139 |
+
"eval_VitaminC_dot_accuracy_threshold": 373.5804443359375,
|
| 1140 |
+
"eval_VitaminC_dot_ap": 0.5310954683437364,
|
| 1141 |
+
"eval_VitaminC_dot_f1": 0.6542553191489362,
|
| 1142 |
+
"eval_VitaminC_dot_f1_threshold": 155.41326904296875,
|
| 1143 |
+
"eval_VitaminC_dot_precision": 0.48616600790513836,
|
| 1144 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 1145 |
+
"eval_VitaminC_euclidean_accuracy": 0.57421875,
|
| 1146 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 13.60124683380127,
|
| 1147 |
+
"eval_VitaminC_euclidean_ap": 0.5286057955992807,
|
| 1148 |
+
"eval_VitaminC_euclidean_f1": 0.6577540106951871,
|
| 1149 |
+
"eval_VitaminC_euclidean_f1_threshold": 22.904512405395508,
|
| 1150 |
+
"eval_VitaminC_euclidean_precision": 0.4900398406374502,
|
| 1151 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 1152 |
+
"eval_VitaminC_manhattan_accuracy": 0.57421875,
|
| 1153 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 262.37322998046875,
|
| 1154 |
+
"eval_VitaminC_manhattan_ap": 0.5253560845853567,
|
| 1155 |
+
"eval_VitaminC_manhattan_f1": 0.6559999999999999,
|
| 1156 |
+
"eval_VitaminC_manhattan_f1_threshold": 465.94549560546875,
|
| 1157 |
+
"eval_VitaminC_manhattan_precision": 0.4880952380952381,
|
| 1158 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 1159 |
+
"eval_VitaminC_max_accuracy": 0.57421875,
|
| 1160 |
+
"eval_VitaminC_max_accuracy_threshold": 373.5804443359375,
|
| 1161 |
+
"eval_VitaminC_max_ap": 0.5310954683437364,
|
| 1162 |
+
"eval_VitaminC_max_f1": 0.6577540106951871,
|
| 1163 |
+
"eval_VitaminC_max_f1_threshold": 465.94549560546875,
|
| 1164 |
+
"eval_VitaminC_max_precision": 0.4900398406374502,
|
| 1165 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 1166 |
+
"eval_sequential_score": 0.5310954683437364,
|
| 1167 |
+
"eval_sts-test_pearson_cosine": 0.8067612938723231,
|
| 1168 |
+
"eval_sts-test_pearson_dot": 0.8217874837658639,
|
| 1169 |
+
"eval_sts-test_pearson_euclidean": 0.827948115812785,
|
| 1170 |
+
"eval_sts-test_pearson_manhattan": 0.8261527694953693,
|
| 1171 |
+
"eval_sts-test_pearson_max": 0.827948115812785,
|
| 1172 |
+
"eval_sts-test_spearman_cosine": 0.8547777638284432,
|
| 1173 |
+
"eval_sts-test_spearman_dot": 0.8498786150097738,
|
| 1174 |
+
"eval_sts-test_spearman_euclidean": 0.8373845860667446,
|
| 1175 |
+
"eval_sts-test_spearman_manhattan": 0.8324507067477893,
|
| 1176 |
+
"eval_sts-test_spearman_max": 0.8547777638284432,
|
| 1177 |
+
"eval_vitaminc-pairs_loss": 2.776399612426758,
|
| 1178 |
+
"eval_vitaminc-pairs_runtime": 1.4503,
|
| 1179 |
+
"eval_vitaminc-pairs_samples_per_second": 74.467,
|
| 1180 |
+
"eval_vitaminc-pairs_steps_per_second": 1.379,
|
| 1181 |
+
"step": 162
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.9146083274523642,
|
| 1185 |
+
"eval_negation-triplets_loss": 2.005451202392578,
|
| 1186 |
+
"eval_negation-triplets_runtime": 0.2981,
|
| 1187 |
+
"eval_negation-triplets_samples_per_second": 214.709,
|
| 1188 |
+
"eval_negation-triplets_steps_per_second": 3.355,
|
| 1189 |
+
"step": 162
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.9146083274523642,
|
| 1193 |
+
"eval_scitail-pairs-pos_loss": 0.19877880811691284,
|
| 1194 |
+
"eval_scitail-pairs-pos_runtime": 0.3623,
|
| 1195 |
+
"eval_scitail-pairs-pos_samples_per_second": 149.043,
|
| 1196 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.76,
|
| 1197 |
+
"step": 162
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.9146083274523642,
|
| 1201 |
+
"eval_xsum-pairs_loss": 0.5586928725242615,
|
| 1202 |
+
"eval_xsum-pairs_runtime": 3.1466,
|
| 1203 |
+
"eval_xsum-pairs_samples_per_second": 40.679,
|
| 1204 |
+
"eval_xsum-pairs_steps_per_second": 0.636,
|
| 1205 |
+
"step": 162
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.9146083274523642,
|
| 1209 |
+
"eval_sciq_pairs_loss": 0.06038254499435425,
|
| 1210 |
+
"eval_sciq_pairs_runtime": 3.4092,
|
| 1211 |
+
"eval_sciq_pairs_samples_per_second": 37.545,
|
| 1212 |
+
"eval_sciq_pairs_steps_per_second": 0.587,
|
| 1213 |
+
"step": 162
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9146083274523642,
|
| 1217 |
+
"eval_qasc_pairs_loss": 0.49434012174606323,
|
| 1218 |
+
"eval_qasc_pairs_runtime": 0.6342,
|
| 1219 |
+
"eval_qasc_pairs_samples_per_second": 201.832,
|
| 1220 |
+
"eval_qasc_pairs_steps_per_second": 3.154,
|
| 1221 |
+
"step": 162
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.9146083274523642,
|
| 1225 |
+
"eval_openbookqa_pairs_loss": 1.1903400421142578,
|
| 1226 |
+
"eval_openbookqa_pairs_runtime": 0.5754,
|
| 1227 |
+
"eval_openbookqa_pairs_samples_per_second": 222.449,
|
| 1228 |
+
"eval_openbookqa_pairs_steps_per_second": 3.476,
|
| 1229 |
+
"step": 162
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.9146083274523642,
|
| 1233 |
+
"eval_msmarco_pairs_loss": 0.8656420707702637,
|
| 1234 |
+
"eval_msmarco_pairs_runtime": 1.2858,
|
| 1235 |
+
"eval_msmarco_pairs_samples_per_second": 99.547,
|
| 1236 |
+
"eval_msmarco_pairs_steps_per_second": 1.555,
|
| 1237 |
+
"step": 162
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.9146083274523642,
|
| 1241 |
+
"eval_nq_pairs_loss": 1.1553651094436646,
|
| 1242 |
+
"eval_nq_pairs_runtime": 2.3754,
|
| 1243 |
+
"eval_nq_pairs_samples_per_second": 53.885,
|
| 1244 |
+
"eval_nq_pairs_steps_per_second": 0.842,
|
| 1245 |
+
"step": 162
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.9146083274523642,
|
| 1249 |
+
"eval_trivia_pairs_loss": 1.2928619384765625,
|
| 1250 |
+
"eval_trivia_pairs_runtime": 4.4084,
|
| 1251 |
+
"eval_trivia_pairs_samples_per_second": 29.035,
|
| 1252 |
+
"eval_trivia_pairs_steps_per_second": 0.454,
|
| 1253 |
+
"step": 162
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.9146083274523642,
|
| 1257 |
+
"eval_gooaq_pairs_loss": 1.1580811738967896,
|
| 1258 |
+
"eval_gooaq_pairs_runtime": 0.8731,
|
| 1259 |
+
"eval_gooaq_pairs_samples_per_second": 146.607,
|
| 1260 |
+
"eval_gooaq_pairs_steps_per_second": 2.291,
|
| 1261 |
+
"step": 162
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.9146083274523642,
|
| 1265 |
+
"eval_paws-pos_loss": 0.052534349262714386,
|
| 1266 |
+
"eval_paws-pos_runtime": 0.6835,
|
| 1267 |
+
"eval_paws-pos_samples_per_second": 187.258,
|
| 1268 |
+
"eval_paws-pos_steps_per_second": 2.926,
|
| 1269 |
+
"step": 162
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.9315455187014821,
|
| 1273 |
+
"grad_norm": 4.7817864418029785,
|
| 1274 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1275 |
+
"loss": 1.339,
|
| 1276 |
+
"step": 165
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9484827099505999,
|
| 1280 |
+
"grad_norm": 4.000570774078369,
|
| 1281 |
+
"learning_rate": 3.818181818181819e-05,
|
| 1282 |
+
"loss": 1.1535,
|
| 1283 |
+
"step": 168
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9654199011997178,
|
| 1287 |
+
"grad_norm": 3.5971670150756836,
|
| 1288 |
+
"learning_rate": 3.8863636363636364e-05,
|
| 1289 |
+
"loss": 1.1643,
|
| 1290 |
+
"step": 171
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.9823570924488356,
|
| 1294 |
+
"grad_norm": 3.6582131385803223,
|
| 1295 |
+
"learning_rate": 3.954545454545455e-05,
|
| 1296 |
+
"loss": 1.2221,
|
| 1297 |
+
"step": 174
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.9992942836979535,
|
| 1301 |
+
"grad_norm": 4.0953898429870605,
|
| 1302 |
+
"learning_rate": 3.9999477905707075e-05,
|
| 1303 |
+
"loss": 1.0974,
|
| 1304 |
+
"step": 177
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.0162314749470713,
|
| 1308 |
+
"grad_norm": 4.092026233673096,
|
| 1309 |
+
"learning_rate": 3.999164730903481e-05,
|
| 1310 |
+
"loss": 1.0984,
|
| 1311 |
+
"step": 180
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.0331686661961892,
|
| 1315 |
+
"grad_norm": 3.6480906009674072,
|
| 1316 |
+
"learning_rate": 3.997442539262898e-05,
|
| 1317 |
+
"loss": 1.0543,
|
| 1318 |
+
"step": 183
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.050105857445307,
|
| 1322 |
+
"grad_norm": 3.433056592941284,
|
| 1323 |
+
"learning_rate": 3.99478242943326e-05,
|
| 1324 |
+
"loss": 1.0994,
|
| 1325 |
+
"step": 186
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.067043048694425,
|
| 1329 |
+
"grad_norm": 3.507981777191162,
|
| 1330 |
+
"learning_rate": 3.991186276234698e-05,
|
| 1331 |
+
"loss": 1.0621,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.067043048694425,
|
| 1336 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 1337 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 1338 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 1339 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 1340 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 1341 |
+
"eval_VitaminC_cosine_accuracy": 0.578125,
|
| 1342 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.7840081453323364,
|
| 1343 |
+
"eval_VitaminC_cosine_ap": 0.5400770399437144,
|
| 1344 |
+
"eval_VitaminC_cosine_f1": 0.6577540106951871,
|
| 1345 |
+
"eval_VitaminC_cosine_f1_threshold": 0.39448243379592896,
|
| 1346 |
+
"eval_VitaminC_cosine_precision": 0.4900398406374502,
|
| 1347 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 1348 |
+
"eval_VitaminC_dot_accuracy": 0.5625,
|
| 1349 |
+
"eval_VitaminC_dot_accuracy_threshold": 323.20281982421875,
|
| 1350 |
+
"eval_VitaminC_dot_ap": 0.5420016101916201,
|
| 1351 |
+
"eval_VitaminC_dot_f1": 0.6575342465753424,
|
| 1352 |
+
"eval_VitaminC_dot_f1_threshold": 198.04354858398438,
|
| 1353 |
+
"eval_VitaminC_dot_precision": 0.49586776859504134,
|
| 1354 |
+
"eval_VitaminC_dot_recall": 0.975609756097561,
|
| 1355 |
+
"eval_VitaminC_euclidean_accuracy": 0.5859375,
|
| 1356 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 13.84214973449707,
|
| 1357 |
+
"eval_VitaminC_euclidean_ap": 0.5392157650683609,
|
| 1358 |
+
"eval_VitaminC_euclidean_f1": 0.6577540106951871,
|
| 1359 |
+
"eval_VitaminC_euclidean_f1_threshold": 22.595678329467773,
|
| 1360 |
+
"eval_VitaminC_euclidean_precision": 0.4900398406374502,
|
| 1361 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 1362 |
+
"eval_VitaminC_manhattan_accuracy": 0.5703125,
|
| 1363 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 275.1253356933594,
|
| 1364 |
+
"eval_VitaminC_manhattan_ap": 0.5341380380767263,
|
| 1365 |
+
"eval_VitaminC_manhattan_f1": 0.6576819407008085,
|
| 1366 |
+
"eval_VitaminC_manhattan_f1_threshold": 457.04986572265625,
|
| 1367 |
+
"eval_VitaminC_manhattan_precision": 0.49193548387096775,
|
| 1368 |
+
"eval_VitaminC_manhattan_recall": 0.991869918699187,
|
| 1369 |
+
"eval_VitaminC_max_accuracy": 0.5859375,
|
| 1370 |
+
"eval_VitaminC_max_accuracy_threshold": 323.20281982421875,
|
| 1371 |
+
"eval_VitaminC_max_ap": 0.5420016101916201,
|
| 1372 |
+
"eval_VitaminC_max_f1": 0.6577540106951871,
|
| 1373 |
+
"eval_VitaminC_max_f1_threshold": 457.04986572265625,
|
| 1374 |
+
"eval_VitaminC_max_precision": 0.49586776859504134,
|
| 1375 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 1376 |
+
"eval_sequential_score": 0.5420016101916201,
|
| 1377 |
+
"eval_sts-test_pearson_cosine": 0.8193410747427454,
|
| 1378 |
+
"eval_sts-test_pearson_dot": 0.8275444476338831,
|
| 1379 |
+
"eval_sts-test_pearson_euclidean": 0.8464528142983967,
|
| 1380 |
+
"eval_sts-test_pearson_manhattan": 0.8440476980962159,
|
| 1381 |
+
"eval_sts-test_pearson_max": 0.8464528142983967,
|
| 1382 |
+
"eval_sts-test_spearman_cosine": 0.8680272706642878,
|
| 1383 |
+
"eval_sts-test_spearman_dot": 0.8555529342729671,
|
| 1384 |
+
"eval_sts-test_spearman_euclidean": 0.8542457068859202,
|
| 1385 |
+
"eval_sts-test_spearman_manhattan": 0.8510265117511795,
|
| 1386 |
+
"eval_sts-test_spearman_max": 0.8680272706642878,
|
| 1387 |
+
"eval_vitaminc-pairs_loss": 2.6755428314208984,
|
| 1388 |
+
"eval_vitaminc-pairs_runtime": 1.4509,
|
| 1389 |
+
"eval_vitaminc-pairs_samples_per_second": 74.437,
|
| 1390 |
+
"eval_vitaminc-pairs_steps_per_second": 1.378,
|
| 1391 |
+
"step": 189
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.067043048694425,
|
| 1395 |
+
"eval_negation-triplets_loss": 1.9071491956710815,
|
| 1396 |
+
"eval_negation-triplets_runtime": 0.3051,
|
| 1397 |
+
"eval_negation-triplets_samples_per_second": 209.756,
|
| 1398 |
+
"eval_negation-triplets_steps_per_second": 3.277,
|
| 1399 |
+
"step": 189
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.067043048694425,
|
| 1403 |
+
"eval_scitail-pairs-pos_loss": 0.18539850413799286,
|
| 1404 |
+
"eval_scitail-pairs-pos_runtime": 0.4199,
|
| 1405 |
+
"eval_scitail-pairs-pos_samples_per_second": 128.604,
|
| 1406 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.382,
|
| 1407 |
+
"step": 189
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.067043048694425,
|
| 1411 |
+
"eval_xsum-pairs_loss": 0.38365328311920166,
|
| 1412 |
+
"eval_xsum-pairs_runtime": 3.1907,
|
| 1413 |
+
"eval_xsum-pairs_samples_per_second": 40.116,
|
| 1414 |
+
"eval_xsum-pairs_steps_per_second": 0.627,
|
| 1415 |
+
"step": 189
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.067043048694425,
|
| 1419 |
+
"eval_sciq_pairs_loss": 0.05558515340089798,
|
| 1420 |
+
"eval_sciq_pairs_runtime": 3.2891,
|
| 1421 |
+
"eval_sciq_pairs_samples_per_second": 38.917,
|
| 1422 |
+
"eval_sciq_pairs_steps_per_second": 0.608,
|
| 1423 |
+
"step": 189
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.067043048694425,
|
| 1427 |
+
"eval_qasc_pairs_loss": 0.40469691157341003,
|
| 1428 |
+
"eval_qasc_pairs_runtime": 0.6267,
|
| 1429 |
+
"eval_qasc_pairs_samples_per_second": 204.245,
|
| 1430 |
+
"eval_qasc_pairs_steps_per_second": 3.191,
|
| 1431 |
+
"step": 189
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.067043048694425,
|
| 1435 |
+
"eval_openbookqa_pairs_loss": 1.0837312936782837,
|
| 1436 |
+
"eval_openbookqa_pairs_runtime": 0.5765,
|
| 1437 |
+
"eval_openbookqa_pairs_samples_per_second": 222.02,
|
| 1438 |
+
"eval_openbookqa_pairs_steps_per_second": 3.469,
|
| 1439 |
+
"step": 189
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.067043048694425,
|
| 1443 |
+
"eval_msmarco_pairs_loss": 0.6897398233413696,
|
| 1444 |
+
"eval_msmarco_pairs_runtime": 1.2918,
|
| 1445 |
+
"eval_msmarco_pairs_samples_per_second": 99.089,
|
| 1446 |
+
"eval_msmarco_pairs_steps_per_second": 1.548,
|
| 1447 |
+
"step": 189
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 1.067043048694425,
|
| 1451 |
+
"eval_nq_pairs_loss": 0.9603796601295471,
|
| 1452 |
+
"eval_nq_pairs_runtime": 2.3975,
|
| 1453 |
+
"eval_nq_pairs_samples_per_second": 53.39,
|
| 1454 |
+
"eval_nq_pairs_steps_per_second": 0.834,
|
| 1455 |
+
"step": 189
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.067043048694425,
|
| 1459 |
+
"eval_trivia_pairs_loss": 1.200446605682373,
|
| 1460 |
+
"eval_trivia_pairs_runtime": 4.4582,
|
| 1461 |
+
"eval_trivia_pairs_samples_per_second": 28.711,
|
| 1462 |
+
"eval_trivia_pairs_steps_per_second": 0.449,
|
| 1463 |
+
"step": 189
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.067043048694425,
|
| 1467 |
+
"eval_gooaq_pairs_loss": 1.0353316068649292,
|
| 1468 |
+
"eval_gooaq_pairs_runtime": 0.8765,
|
| 1469 |
+
"eval_gooaq_pairs_samples_per_second": 146.042,
|
| 1470 |
+
"eval_gooaq_pairs_steps_per_second": 2.282,
|
| 1471 |
+
"step": 189
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.067043048694425,
|
| 1475 |
+
"eval_paws-pos_loss": 0.042069558054208755,
|
| 1476 |
+
"eval_paws-pos_runtime": 0.6909,
|
| 1477 |
+
"eval_paws-pos_samples_per_second": 185.263,
|
| 1478 |
+
"eval_paws-pos_steps_per_second": 2.895,
|
| 1479 |
+
"step": 189
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.0839802399435428,
|
| 1483 |
+
"grad_norm": 2.979419469833374,
|
| 1484 |
+
"learning_rate": 3.986656614201813e-05,
|
| 1485 |
+
"loss": 0.8724,
|
| 1486 |
+
"step": 192
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.1009174311926606,
|
| 1490 |
+
"grad_norm": 2.835219144821167,
|
| 1491 |
+
"learning_rate": 3.981196635797361e-05,
|
| 1492 |
+
"loss": 0.9381,
|
| 1493 |
+
"step": 195
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.1178546224417785,
|
| 1497 |
+
"grad_norm": 3.6650869846343994,
|
| 1498 |
+
"learning_rate": 3.974810189162238e-05,
|
| 1499 |
+
"loss": 0.9617,
|
| 1500 |
+
"step": 198
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.1347918136908963,
|
| 1504 |
+
"grad_norm": 4.188896656036377,
|
| 1505 |
+
"learning_rate": 3.967501775403343e-05,
|
| 1506 |
+
"loss": 1.0139,
|
| 1507 |
+
"step": 201
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.1517290049400142,
|
| 1511 |
+
"grad_norm": 3.1624915599823,
|
| 1512 |
+
"learning_rate": 3.959276545421244e-05,
|
| 1513 |
+
"loss": 1.1073,
|
| 1514 |
+
"step": 204
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.168666196189132,
|
| 1518 |
+
"grad_norm": 3.245002508163452,
|
| 1519 |
+
"learning_rate": 3.950140296279871e-05,
|
| 1520 |
+
"loss": 0.8365,
|
| 1521 |
+
"step": 207
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.18560338743825,
|
| 1525 |
+
"grad_norm": 4.376185894012451,
|
| 1526 |
+
"learning_rate": 3.9400994671208e-05,
|
| 1527 |
+
"loss": 1.1012,
|
| 1528 |
+
"step": 210
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2025405786873677,
|
| 1532 |
+
"grad_norm": 3.236583948135376,
|
| 1533 |
+
"learning_rate": 3.9291611346250066e-05,
|
| 1534 |
+
"loss": 1.0016,
|
| 1535 |
+
"step": 213
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2194777699364856,
|
| 1539 |
+
"grad_norm": 3.7601733207702637,
|
| 1540 |
+
"learning_rate": 3.9173330080252904e-05,
|
| 1541 |
+
"loss": 1.0957,
|
| 1542 |
+
"step": 216
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2194777699364856,
|
| 1546 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 1547 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 1548 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 1549 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 1550 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 1551 |
+
"eval_VitaminC_cosine_accuracy": 0.57421875,
|
| 1552 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.7863086462020874,
|
| 1553 |
+
"eval_VitaminC_cosine_ap": 0.538511783260847,
|
| 1554 |
+
"eval_VitaminC_cosine_f1": 0.6577540106951871,
|
| 1555 |
+
"eval_VitaminC_cosine_f1_threshold": 0.4006580412387848,
|
| 1556 |
+
"eval_VitaminC_cosine_precision": 0.4900398406374502,
|
| 1557 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 1558 |
+
"eval_VitaminC_dot_accuracy": 0.57421875,
|
| 1559 |
+
"eval_VitaminC_dot_accuracy_threshold": 323.53277587890625,
|
| 1560 |
+
"eval_VitaminC_dot_ap": 0.5304994537787167,
|
| 1561 |
+
"eval_VitaminC_dot_f1": 0.6577540106951871,
|
| 1562 |
+
"eval_VitaminC_dot_f1_threshold": 166.45921325683594,
|
| 1563 |
+
"eval_VitaminC_dot_precision": 0.4900398406374502,
|
| 1564 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 1565 |
+
"eval_VitaminC_euclidean_accuracy": 0.578125,
|
| 1566 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 13.631423950195312,
|
| 1567 |
+
"eval_VitaminC_euclidean_ap": 0.5363284984763951,
|
| 1568 |
+
"eval_VitaminC_euclidean_f1": 0.6542553191489362,
|
| 1569 |
+
"eval_VitaminC_euclidean_f1_threshold": 25.392715454101562,
|
| 1570 |
+
"eval_VitaminC_euclidean_precision": 0.48616600790513836,
|
| 1571 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 1572 |
+
"eval_VitaminC_manhattan_accuracy": 0.57421875,
|
| 1573 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 283.5897216796875,
|
| 1574 |
+
"eval_VitaminC_manhattan_ap": 0.5327191155331534,
|
| 1575 |
+
"eval_VitaminC_manhattan_f1": 0.6559999999999999,
|
| 1576 |
+
"eval_VitaminC_manhattan_f1_threshold": 491.0370178222656,
|
| 1577 |
+
"eval_VitaminC_manhattan_precision": 0.4880952380952381,
|
| 1578 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 1579 |
+
"eval_VitaminC_max_accuracy": 0.578125,
|
| 1580 |
+
"eval_VitaminC_max_accuracy_threshold": 323.53277587890625,
|
| 1581 |
+
"eval_VitaminC_max_ap": 0.538511783260847,
|
| 1582 |
+
"eval_VitaminC_max_f1": 0.6577540106951871,
|
| 1583 |
+
"eval_VitaminC_max_f1_threshold": 491.0370178222656,
|
| 1584 |
+
"eval_VitaminC_max_precision": 0.4900398406374502,
|
| 1585 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 1586 |
+
"eval_sequential_score": 0.538511783260847,
|
| 1587 |
+
"eval_sts-test_pearson_cosine": 0.8156684919084325,
|
| 1588 |
+
"eval_sts-test_pearson_dot": 0.8230786053133633,
|
| 1589 |
+
"eval_sts-test_pearson_euclidean": 0.845348828865422,
|
| 1590 |
+
"eval_sts-test_pearson_manhattan": 0.8432655375716184,
|
| 1591 |
+
"eval_sts-test_pearson_max": 0.845348828865422,
|
| 1592 |
+
"eval_sts-test_spearman_cosine": 0.8655524539841267,
|
| 1593 |
+
"eval_sts-test_spearman_dot": 0.8507196659909223,
|
| 1594 |
+
"eval_sts-test_spearman_euclidean": 0.8547050804103192,
|
| 1595 |
+
"eval_sts-test_spearman_manhattan": 0.8508668230591436,
|
| 1596 |
+
"eval_sts-test_spearman_max": 0.8655524539841267,
|
| 1597 |
+
"eval_vitaminc-pairs_loss": 2.5465524196624756,
|
| 1598 |
+
"eval_vitaminc-pairs_runtime": 1.4425,
|
| 1599 |
+
"eval_vitaminc-pairs_samples_per_second": 74.869,
|
| 1600 |
+
"eval_vitaminc-pairs_steps_per_second": 1.386,
|
| 1601 |
+
"step": 216
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 1.2194777699364856,
|
| 1605 |
+
"eval_negation-triplets_loss": 1.9161474704742432,
|
| 1606 |
+
"eval_negation-triplets_runtime": 0.2994,
|
| 1607 |
+
"eval_negation-triplets_samples_per_second": 213.785,
|
| 1608 |
+
"eval_negation-triplets_steps_per_second": 3.34,
|
| 1609 |
+
"step": 216
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 1.2194777699364856,
|
| 1613 |
+
"eval_scitail-pairs-pos_loss": 0.19009728729724884,
|
| 1614 |
+
"eval_scitail-pairs-pos_runtime": 0.3745,
|
| 1615 |
+
"eval_scitail-pairs-pos_samples_per_second": 144.203,
|
| 1616 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.67,
|
| 1617 |
+
"step": 216
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.2194777699364856,
|
| 1621 |
+
"eval_xsum-pairs_loss": 0.35912859439849854,
|
| 1622 |
+
"eval_xsum-pairs_runtime": 3.1543,
|
| 1623 |
+
"eval_xsum-pairs_samples_per_second": 40.58,
|
| 1624 |
+
"eval_xsum-pairs_steps_per_second": 0.634,
|
| 1625 |
+
"step": 216
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.2194777699364856,
|
| 1629 |
+
"eval_sciq_pairs_loss": 0.05168920382857323,
|
| 1630 |
+
"eval_sciq_pairs_runtime": 3.2561,
|
| 1631 |
+
"eval_sciq_pairs_samples_per_second": 39.31,
|
| 1632 |
+
"eval_sciq_pairs_steps_per_second": 0.614,
|
| 1633 |
+
"step": 216
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.2194777699364856,
|
| 1637 |
+
"eval_qasc_pairs_loss": 0.30753791332244873,
|
| 1638 |
+
"eval_qasc_pairs_runtime": 0.6201,
|
| 1639 |
+
"eval_qasc_pairs_samples_per_second": 206.418,
|
| 1640 |
+
"eval_qasc_pairs_steps_per_second": 3.225,
|
| 1641 |
+
"step": 216
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.2194777699364856,
|
| 1645 |
+
"eval_openbookqa_pairs_loss": 0.9365726113319397,
|
| 1646 |
+
"eval_openbookqa_pairs_runtime": 0.5832,
|
| 1647 |
+
"eval_openbookqa_pairs_samples_per_second": 219.496,
|
| 1648 |
+
"eval_openbookqa_pairs_steps_per_second": 3.43,
|
| 1649 |
+
"step": 216
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.2194777699364856,
|
| 1653 |
+
"eval_msmarco_pairs_loss": 0.5819053053855896,
|
| 1654 |
+
"eval_msmarco_pairs_runtime": 1.2858,
|
| 1655 |
+
"eval_msmarco_pairs_samples_per_second": 99.551,
|
| 1656 |
+
"eval_msmarco_pairs_steps_per_second": 1.555,
|
| 1657 |
+
"step": 216
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.2194777699364856,
|
| 1661 |
+
"eval_nq_pairs_loss": 0.8172401785850525,
|
| 1662 |
+
"eval_nq_pairs_runtime": 2.3809,
|
| 1663 |
+
"eval_nq_pairs_samples_per_second": 53.761,
|
| 1664 |
+
"eval_nq_pairs_steps_per_second": 0.84,
|
| 1665 |
+
"step": 216
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.2194777699364856,
|
| 1669 |
+
"eval_trivia_pairs_loss": 1.1411677598953247,
|
| 1670 |
+
"eval_trivia_pairs_runtime": 4.4162,
|
| 1671 |
+
"eval_trivia_pairs_samples_per_second": 28.984,
|
| 1672 |
+
"eval_trivia_pairs_steps_per_second": 0.453,
|
| 1673 |
+
"step": 216
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.2194777699364856,
|
| 1677 |
+
"eval_gooaq_pairs_loss": 0.9686058759689331,
|
| 1678 |
+
"eval_gooaq_pairs_runtime": 0.8788,
|
| 1679 |
+
"eval_gooaq_pairs_samples_per_second": 145.645,
|
| 1680 |
+
"eval_gooaq_pairs_steps_per_second": 2.276,
|
| 1681 |
+
"step": 216
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.2194777699364856,
|
| 1685 |
+
"eval_paws-pos_loss": 0.03953952714800835,
|
| 1686 |
+
"eval_paws-pos_runtime": 0.708,
|
| 1687 |
+
"eval_paws-pos_samples_per_second": 180.782,
|
| 1688 |
+
"eval_paws-pos_steps_per_second": 2.825,
|
| 1689 |
+
"step": 216
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.2364149611856035,
|
| 1693 |
+
"grad_norm": 3.566471576690674,
|
| 1694 |
+
"learning_rate": 3.904623423672881e-05,
|
| 1695 |
+
"loss": 1.1273,
|
| 1696 |
+
"step": 219
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.2533521524347213,
|
| 1700 |
+
"grad_norm": 4.086460590362549,
|
| 1701 |
+
"learning_rate": 3.891041339162053e-05,
|
| 1702 |
+
"loss": 1.2568,
|
| 1703 |
+
"step": 222
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.2702893436838392,
|
| 1707 |
+
"grad_norm": 3.2877376079559326,
|
| 1708 |
+
"learning_rate": 3.876596327016904e-05,
|
| 1709 |
+
"loss": 0.873,
|
| 1710 |
+
"step": 225
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.287226534932957,
|
| 1714 |
+
"grad_norm": 3.383211851119995,
|
| 1715 |
+
"learning_rate": 3.861298567944728e-05,
|
| 1716 |
+
"loss": 1.0003,
|
| 1717 |
+
"step": 228
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.3041637261820749,
|
| 1721 |
+
"grad_norm": 3.8474605083465576,
|
| 1722 |
+
"learning_rate": 3.8451588436607487e-05,
|
| 1723 |
+
"loss": 1.142,
|
| 1724 |
+
"step": 231
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.3211009174311927,
|
| 1728 |
+
"grad_norm": 3.027008533477783,
|
| 1729 |
+
"learning_rate": 3.8281885292892706e-05,
|
| 1730 |
+
"loss": 0.807,
|
| 1731 |
+
"step": 234
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.3380381086803106,
|
| 1735 |
+
"grad_norm": 2.9607250690460205,
|
| 1736 |
+
"learning_rate": 3.810399585346599e-05,
|
| 1737 |
+
"loss": 1.0231,
|
| 1738 |
+
"step": 237
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.3549752999294284,
|
| 1742 |
+
"grad_norm": 2.511488676071167,
|
| 1743 |
+
"learning_rate": 3.791804549311382e-05,
|
| 1744 |
+
"loss": 0.797,
|
| 1745 |
+
"step": 240
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.3719124911785463,
|
| 1749 |
+
"grad_norm": 2.603672504425049,
|
| 1750 |
+
"learning_rate": 3.7724165267883146e-05,
|
| 1751 |
+
"loss": 0.8473,
|
| 1752 |
+
"step": 243
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.3719124911785463,
|
| 1756 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 1757 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 1758 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 1759 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 1760 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 1761 |
+
"eval_VitaminC_cosine_accuracy": 0.578125,
|
| 1762 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.7651997804641724,
|
| 1763 |
+
"eval_VitaminC_cosine_ap": 0.5427753322056709,
|
| 1764 |
+
"eval_VitaminC_cosine_f1": 0.6595174262734584,
|
| 1765 |
+
"eval_VitaminC_cosine_f1_threshold": 0.38563254475593567,
|
| 1766 |
+
"eval_VitaminC_cosine_precision": 0.492,
|
| 1767 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 1768 |
+
"eval_VitaminC_dot_accuracy": 0.5703125,
|
| 1769 |
+
"eval_VitaminC_dot_accuracy_threshold": 330.23577880859375,
|
| 1770 |
+
"eval_VitaminC_dot_ap": 0.5507967714924796,
|
| 1771 |
+
"eval_VitaminC_dot_f1": 0.6595174262734584,
|
| 1772 |
+
"eval_VitaminC_dot_f1_threshold": 160.55694580078125,
|
| 1773 |
+
"eval_VitaminC_dot_precision": 0.492,
|
| 1774 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 1775 |
+
"eval_VitaminC_euclidean_accuracy": 0.578125,
|
| 1776 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 13.033781051635742,
|
| 1777 |
+
"eval_VitaminC_euclidean_ap": 0.5406935655135654,
|
| 1778 |
+
"eval_VitaminC_euclidean_f1": 0.6576819407008085,
|
| 1779 |
+
"eval_VitaminC_euclidean_f1_threshold": 22.224994659423828,
|
| 1780 |
+
"eval_VitaminC_euclidean_precision": 0.49193548387096775,
|
| 1781 |
+
"eval_VitaminC_euclidean_recall": 0.991869918699187,
|
| 1782 |
+
"eval_VitaminC_manhattan_accuracy": 0.57421875,
|
| 1783 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 274.7045593261719,
|
| 1784 |
+
"eval_VitaminC_manhattan_ap": 0.5366045405118165,
|
| 1785 |
+
"eval_VitaminC_manhattan_f1": 0.6577540106951871,
|
| 1786 |
+
"eval_VitaminC_manhattan_f1_threshold": 475.4096374511719,
|
| 1787 |
+
"eval_VitaminC_manhattan_precision": 0.4900398406374502,
|
| 1788 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 1789 |
+
"eval_VitaminC_max_accuracy": 0.578125,
|
| 1790 |
+
"eval_VitaminC_max_accuracy_threshold": 330.23577880859375,
|
| 1791 |
+
"eval_VitaminC_max_ap": 0.5507967714924796,
|
| 1792 |
+
"eval_VitaminC_max_f1": 0.6595174262734584,
|
| 1793 |
+
"eval_VitaminC_max_f1_threshold": 475.4096374511719,
|
| 1794 |
+
"eval_VitaminC_max_precision": 0.492,
|
| 1795 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 1796 |
+
"eval_sequential_score": 0.5507967714924796,
|
| 1797 |
+
"eval_sts-test_pearson_cosine": 0.8204982036322743,
|
| 1798 |
+
"eval_sts-test_pearson_dot": 0.8243481169631539,
|
| 1799 |
+
"eval_sts-test_pearson_euclidean": 0.8495098083065487,
|
| 1800 |
+
"eval_sts-test_pearson_manhattan": 0.8491539225772841,
|
| 1801 |
+
"eval_sts-test_pearson_max": 0.8495098083065487,
|
| 1802 |
+
"eval_sts-test_spearman_cosine": 0.8687444375928703,
|
| 1803 |
+
"eval_sts-test_spearman_dot": 0.8509044179305871,
|
| 1804 |
+
"eval_sts-test_spearman_euclidean": 0.8563313271350431,
|
| 1805 |
+
"eval_sts-test_spearman_manhattan": 0.8563900467437737,
|
| 1806 |
+
"eval_sts-test_spearman_max": 0.8687444375928703,
|
| 1807 |
+
"eval_vitaminc-pairs_loss": 2.5139691829681396,
|
| 1808 |
+
"eval_vitaminc-pairs_runtime": 1.449,
|
| 1809 |
+
"eval_vitaminc-pairs_samples_per_second": 74.533,
|
| 1810 |
+
"eval_vitaminc-pairs_steps_per_second": 1.38,
|
| 1811 |
+
"step": 243
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.3719124911785463,
|
| 1815 |
+
"eval_negation-triplets_loss": 1.8629425764083862,
|
| 1816 |
+
"eval_negation-triplets_runtime": 0.3014,
|
| 1817 |
+
"eval_negation-triplets_samples_per_second": 212.31,
|
| 1818 |
+
"eval_negation-triplets_steps_per_second": 3.317,
|
| 1819 |
+
"step": 243
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 1.3719124911785463,
|
| 1823 |
+
"eval_scitail-pairs-pos_loss": 0.17502877116203308,
|
| 1824 |
+
"eval_scitail-pairs-pos_runtime": 0.3707,
|
| 1825 |
+
"eval_scitail-pairs-pos_samples_per_second": 145.673,
|
| 1826 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.698,
|
| 1827 |
+
"step": 243
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.3719124911785463,
|
| 1831 |
+
"eval_xsum-pairs_loss": 0.2802315950393677,
|
| 1832 |
+
"eval_xsum-pairs_runtime": 3.1565,
|
| 1833 |
+
"eval_xsum-pairs_samples_per_second": 40.551,
|
| 1834 |
+
"eval_xsum-pairs_steps_per_second": 0.634,
|
| 1835 |
+
"step": 243
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.3719124911785463,
|
| 1839 |
+
"eval_sciq_pairs_loss": 0.046695925295352936,
|
| 1840 |
+
"eval_sciq_pairs_runtime": 3.2866,
|
| 1841 |
+
"eval_sciq_pairs_samples_per_second": 38.946,
|
| 1842 |
+
"eval_sciq_pairs_steps_per_second": 0.609,
|
| 1843 |
+
"step": 243
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.3719124911785463,
|
| 1847 |
+
"eval_qasc_pairs_loss": 0.2354799211025238,
|
| 1848 |
+
"eval_qasc_pairs_runtime": 0.6228,
|
| 1849 |
+
"eval_qasc_pairs_samples_per_second": 205.533,
|
| 1850 |
+
"eval_qasc_pairs_steps_per_second": 3.211,
|
| 1851 |
+
"step": 243
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.3719124911785463,
|
| 1855 |
+
"eval_openbookqa_pairs_loss": 0.8562020659446716,
|
| 1856 |
+
"eval_openbookqa_pairs_runtime": 0.5764,
|
| 1857 |
+
"eval_openbookqa_pairs_samples_per_second": 222.058,
|
| 1858 |
+
"eval_openbookqa_pairs_steps_per_second": 3.47,
|
| 1859 |
+
"step": 243
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.3719124911785463,
|
| 1863 |
+
"eval_msmarco_pairs_loss": 0.5559017658233643,
|
| 1864 |
+
"eval_msmarco_pairs_runtime": 1.2826,
|
| 1865 |
+
"eval_msmarco_pairs_samples_per_second": 99.801,
|
| 1866 |
+
"eval_msmarco_pairs_steps_per_second": 1.559,
|
| 1867 |
+
"step": 243
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 1.3719124911785463,
|
| 1871 |
+
"eval_nq_pairs_loss": 0.743526041507721,
|
| 1872 |
+
"eval_nq_pairs_runtime": 2.3784,
|
| 1873 |
+
"eval_nq_pairs_samples_per_second": 53.817,
|
| 1874 |
+
"eval_nq_pairs_steps_per_second": 0.841,
|
| 1875 |
+
"step": 243
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 1.3719124911785463,
|
| 1879 |
+
"eval_trivia_pairs_loss": 1.106662392616272,
|
| 1880 |
+
"eval_trivia_pairs_runtime": 4.4193,
|
| 1881 |
+
"eval_trivia_pairs_samples_per_second": 28.964,
|
| 1882 |
+
"eval_trivia_pairs_steps_per_second": 0.453,
|
| 1883 |
+
"step": 243
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 1.3719124911785463,
|
| 1887 |
+
"eval_gooaq_pairs_loss": 0.8928955793380737,
|
| 1888 |
+
"eval_gooaq_pairs_runtime": 0.8831,
|
| 1889 |
+
"eval_gooaq_pairs_samples_per_second": 144.944,
|
| 1890 |
+
"eval_gooaq_pairs_steps_per_second": 2.265,
|
| 1891 |
+
"step": 243
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.3719124911785463,
|
| 1895 |
+
"eval_paws-pos_loss": 0.03428014740347862,
|
| 1896 |
+
"eval_paws-pos_runtime": 0.6872,
|
| 1897 |
+
"eval_paws-pos_samples_per_second": 186.261,
|
| 1898 |
+
"eval_paws-pos_steps_per_second": 2.91,
|
| 1899 |
+
"step": 243
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.3888496824276642,
|
| 1903 |
+
"grad_norm": 4.478828430175781,
|
| 1904 |
+
"learning_rate": 3.752249182271433e-05,
|
| 1905 |
+
"loss": 0.9531,
|
| 1906 |
+
"step": 246
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.405786873676782,
|
| 1910 |
+
"grad_norm": 3.3206863403320312,
|
| 1911 |
+
"learning_rate": 3.731316729513507e-05,
|
| 1912 |
+
"loss": 0.9023,
|
| 1913 |
+
"step": 249
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.4227240649258999,
|
| 1917 |
+
"grad_norm": 3.4713878631591797,
|
| 1918 |
+
"learning_rate": 3.7096339215083274e-05,
|
| 1919 |
+
"loss": 0.8922,
|
| 1920 |
+
"step": 252
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.4396612561750177,
|
| 1924 |
+
"grad_norm": 3.4212491512298584,
|
| 1925 |
+
"learning_rate": 3.687216040092931e-05,
|
| 1926 |
+
"loss": 0.9874,
|
| 1927 |
+
"step": 255
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.4565984474241356,
|
| 1931 |
+
"grad_norm": 3.398963689804077,
|
| 1932 |
+
"learning_rate": 3.6640788851771084e-05,
|
| 1933 |
+
"loss": 0.8508,
|
| 1934 |
+
"step": 258
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.4735356386732534,
|
| 1938 |
+
"grad_norm": 3.350128650665283,
|
| 1939 |
+
"learning_rate": 3.64023876360778e-05,
|
| 1940 |
+
"loss": 0.7149,
|
| 1941 |
+
"step": 261
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.4904728299223713,
|
| 1945 |
+
"grad_norm": 3.438978433609009,
|
| 1946 |
+
"learning_rate": 3.615712477676081e-05,
|
| 1947 |
+
"loss": 0.894,
|
| 1948 |
+
"step": 264
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.5074100211714891,
|
| 1952 |
+
"grad_norm": 3.1700806617736816,
|
| 1953 |
+
"learning_rate": 3.5905173132752725e-05,
|
| 1954 |
+
"loss": 0.867,
|
| 1955 |
+
"step": 267
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.524347212420607,
|
| 1959 |
+
"grad_norm": 3.1567916870117188,
|
| 1960 |
+
"learning_rate": 3.5646710277178006e-05,
|
| 1961 |
+
"loss": 0.7493,
|
| 1962 |
+
"step": 270
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.524347212420607,
|
| 1966 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 1967 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 1968 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 1969 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 1970 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 1971 |
+
"eval_VitaminC_cosine_accuracy": 0.58203125,
|
| 1972 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.7990785241127014,
|
| 1973 |
+
"eval_VitaminC_cosine_ap": 0.5489113961762149,
|
| 1974 |
+
"eval_VitaminC_cosine_f1": 0.6595174262734584,
|
| 1975 |
+
"eval_VitaminC_cosine_f1_threshold": 0.3687684237957001,
|
| 1976 |
+
"eval_VitaminC_cosine_precision": 0.492,
|
| 1977 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 1978 |
+
"eval_VitaminC_dot_accuracy": 0.57421875,
|
| 1979 |
+
"eval_VitaminC_dot_accuracy_threshold": 328.30560302734375,
|
| 1980 |
+
"eval_VitaminC_dot_ap": 0.5498735151014204,
|
| 1981 |
+
"eval_VitaminC_dot_f1": 0.6595174262734584,
|
| 1982 |
+
"eval_VitaminC_dot_f1_threshold": 153.01849365234375,
|
| 1983 |
+
"eval_VitaminC_dot_precision": 0.492,
|
| 1984 |
+
"eval_VitaminC_dot_recall": 1.0,
|
| 1985 |
+
"eval_VitaminC_euclidean_accuracy": 0.578125,
|
| 1986 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 12.773557662963867,
|
| 1987 |
+
"eval_VitaminC_euclidean_ap": 0.5426159894851803,
|
| 1988 |
+
"eval_VitaminC_euclidean_f1": 0.6559999999999999,
|
| 1989 |
+
"eval_VitaminC_euclidean_f1_threshold": 23.71053123474121,
|
| 1990 |
+
"eval_VitaminC_euclidean_precision": 0.4880952380952381,
|
| 1991 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 1992 |
+
"eval_VitaminC_manhattan_accuracy": 0.58203125,
|
| 1993 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 272.04931640625,
|
| 1994 |
+
"eval_VitaminC_manhattan_ap": 0.5396432749419082,
|
| 1995 |
+
"eval_VitaminC_manhattan_f1": 0.6577540106951871,
|
| 1996 |
+
"eval_VitaminC_manhattan_f1_threshold": 494.33001708984375,
|
| 1997 |
+
"eval_VitaminC_manhattan_precision": 0.4900398406374502,
|
| 1998 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 1999 |
+
"eval_VitaminC_max_accuracy": 0.58203125,
|
| 2000 |
+
"eval_VitaminC_max_accuracy_threshold": 328.30560302734375,
|
| 2001 |
+
"eval_VitaminC_max_ap": 0.5498735151014204,
|
| 2002 |
+
"eval_VitaminC_max_f1": 0.6595174262734584,
|
| 2003 |
+
"eval_VitaminC_max_f1_threshold": 494.33001708984375,
|
| 2004 |
+
"eval_VitaminC_max_precision": 0.492,
|
| 2005 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 2006 |
+
"eval_sequential_score": 0.5498735151014204,
|
| 2007 |
+
"eval_sts-test_pearson_cosine": 0.8213785723785002,
|
| 2008 |
+
"eval_sts-test_pearson_dot": 0.8169840312248031,
|
| 2009 |
+
"eval_sts-test_pearson_euclidean": 0.8549065829936804,
|
| 2010 |
+
"eval_sts-test_pearson_manhattan": 0.8559014033008101,
|
| 2011 |
+
"eval_sts-test_pearson_max": 0.8559014033008101,
|
| 2012 |
+
"eval_sts-test_spearman_cosine": 0.871560114440785,
|
| 2013 |
+
"eval_sts-test_spearman_dot": 0.8412461164335756,
|
| 2014 |
+
"eval_sts-test_spearman_euclidean": 0.8616554770242205,
|
| 2015 |
+
"eval_sts-test_spearman_manhattan": 0.86344749922969,
|
| 2016 |
+
"eval_sts-test_spearman_max": 0.871560114440785,
|
| 2017 |
+
"eval_vitaminc-pairs_loss": 2.5574047565460205,
|
| 2018 |
+
"eval_vitaminc-pairs_runtime": 1.4466,
|
| 2019 |
+
"eval_vitaminc-pairs_samples_per_second": 74.658,
|
| 2020 |
+
"eval_vitaminc-pairs_steps_per_second": 1.383,
|
| 2021 |
+
"step": 270
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 1.524347212420607,
|
| 2025 |
+
"eval_negation-triplets_loss": 1.853515386581421,
|
| 2026 |
+
"eval_negation-triplets_runtime": 0.2992,
|
| 2027 |
+
"eval_negation-triplets_samples_per_second": 213.896,
|
| 2028 |
+
"eval_negation-triplets_steps_per_second": 3.342,
|
| 2029 |
+
"step": 270
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 1.524347212420607,
|
| 2033 |
+
"eval_scitail-pairs-pos_loss": 0.1692524254322052,
|
| 2034 |
+
"eval_scitail-pairs-pos_runtime": 0.3739,
|
| 2035 |
+
"eval_scitail-pairs-pos_samples_per_second": 144.426,
|
| 2036 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.675,
|
| 2037 |
+
"step": 270
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.524347212420607,
|
| 2041 |
+
"eval_xsum-pairs_loss": 0.22170975804328918,
|
| 2042 |
+
"eval_xsum-pairs_runtime": 3.1517,
|
| 2043 |
+
"eval_xsum-pairs_samples_per_second": 40.613,
|
| 2044 |
+
"eval_xsum-pairs_steps_per_second": 0.635,
|
| 2045 |
+
"step": 270
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.524347212420607,
|
| 2049 |
+
"eval_sciq_pairs_loss": 0.04346679896116257,
|
| 2050 |
+
"eval_sciq_pairs_runtime": 3.2686,
|
| 2051 |
+
"eval_sciq_pairs_samples_per_second": 39.16,
|
| 2052 |
+
"eval_sciq_pairs_steps_per_second": 0.612,
|
| 2053 |
+
"step": 270
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.524347212420607,
|
| 2057 |
+
"eval_qasc_pairs_loss": 0.24427936971187592,
|
| 2058 |
+
"eval_qasc_pairs_runtime": 0.6217,
|
| 2059 |
+
"eval_qasc_pairs_samples_per_second": 205.897,
|
| 2060 |
+
"eval_qasc_pairs_steps_per_second": 3.217,
|
| 2061 |
+
"step": 270
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.524347212420607,
|
| 2065 |
+
"eval_openbookqa_pairs_loss": 0.7998915910720825,
|
| 2066 |
+
"eval_openbookqa_pairs_runtime": 0.576,
|
| 2067 |
+
"eval_openbookqa_pairs_samples_per_second": 222.206,
|
| 2068 |
+
"eval_openbookqa_pairs_steps_per_second": 3.472,
|
| 2069 |
+
"step": 270
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.524347212420607,
|
| 2073 |
+
"eval_msmarco_pairs_loss": 0.5027381777763367,
|
| 2074 |
+
"eval_msmarco_pairs_runtime": 1.2901,
|
| 2075 |
+
"eval_msmarco_pairs_samples_per_second": 99.216,
|
| 2076 |
+
"eval_msmarco_pairs_steps_per_second": 1.55,
|
| 2077 |
+
"step": 270
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 1.524347212420607,
|
| 2081 |
+
"eval_nq_pairs_loss": 0.6529555916786194,
|
| 2082 |
+
"eval_nq_pairs_runtime": 2.3842,
|
| 2083 |
+
"eval_nq_pairs_samples_per_second": 53.687,
|
| 2084 |
+
"eval_nq_pairs_steps_per_second": 0.839,
|
| 2085 |
+
"step": 270
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 1.524347212420607,
|
| 2089 |
+
"eval_trivia_pairs_loss": 1.0634211301803589,
|
| 2090 |
+
"eval_trivia_pairs_runtime": 4.4089,
|
| 2091 |
+
"eval_trivia_pairs_samples_per_second": 29.032,
|
| 2092 |
+
"eval_trivia_pairs_steps_per_second": 0.454,
|
| 2093 |
+
"step": 270
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 1.524347212420607,
|
| 2097 |
+
"eval_gooaq_pairs_loss": 0.800453245639801,
|
| 2098 |
+
"eval_gooaq_pairs_runtime": 0.8705,
|
| 2099 |
+
"eval_gooaq_pairs_samples_per_second": 147.034,
|
| 2100 |
+
"eval_gooaq_pairs_steps_per_second": 2.297,
|
| 2101 |
+
"step": 270
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.524347212420607,
|
| 2105 |
+
"eval_paws-pos_loss": 0.031901415437459946,
|
| 2106 |
+
"eval_paws-pos_runtime": 0.6828,
|
| 2107 |
+
"eval_paws-pos_samples_per_second": 187.456,
|
| 2108 |
+
"eval_paws-pos_steps_per_second": 2.929,
|
| 2109 |
+
"step": 270
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.5412844036697249,
|
| 2113 |
+
"grad_norm": 3.258525848388672,
|
| 2114 |
+
"learning_rate": 3.5381918372201175e-05,
|
| 2115 |
+
"loss": 0.7974,
|
| 2116 |
+
"step": 273
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.5582215949188427,
|
| 2120 |
+
"grad_norm": 2.9689552783966064,
|
| 2121 |
+
"learning_rate": 3.5110984040640627e-05,
|
| 2122 |
+
"loss": 0.797,
|
| 2123 |
+
"step": 276
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.5751587861679606,
|
| 2127 |
+
"grad_norm": 3.50411057472229,
|
| 2128 |
+
"learning_rate": 3.483409823443864e-05,
|
| 2129 |
+
"loss": 0.6749,
|
| 2130 |
+
"step": 279
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.5920959774170784,
|
| 2134 |
+
"grad_norm": 2.840614080429077,
|
| 2135 |
+
"learning_rate": 3.4551456100080266e-05,
|
| 2136 |
+
"loss": 0.9325,
|
| 2137 |
+
"step": 282
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.6090331686661963,
|
| 2141 |
+
"grad_norm": 2.934267044067383,
|
| 2142 |
+
"learning_rate": 3.426325684105594e-05,
|
| 2143 |
+
"loss": 0.8418,
|
| 2144 |
+
"step": 285
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.6259703599153141,
|
| 2148 |
+
"grad_norm": 3.5037455558776855,
|
| 2149 |
+
"learning_rate": 3.396970357746474e-05,
|
| 2150 |
+
"loss": 1.0135,
|
| 2151 |
+
"step": 288
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.642907551164432,
|
| 2155 |
+
"grad_norm": 3.349975109100342,
|
| 2156 |
+
"learning_rate": 3.3671003202857315e-05,
|
| 2157 |
+
"loss": 0.6961,
|
| 2158 |
+
"step": 291
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.6598447424135498,
|
| 2162 |
+
"grad_norm": 3.207557439804077,
|
| 2163 |
+
"learning_rate": 3.336736623841924e-05,
|
| 2164 |
+
"loss": 0.9361,
|
| 2165 |
+
"step": 294
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.6767819336626677,
|
| 2169 |
+
"grad_norm": 2.0259296894073486,
|
| 2170 |
+
"learning_rate": 3.305900668459766e-05,
|
| 2171 |
+
"loss": 0.6747,
|
| 2172 |
+
"step": 297
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.6767819336626677,
|
| 2176 |
+
"eval_NLI-v2_cosine_accuracy": 1.0,
|
| 2177 |
+
"eval_NLI-v2_dot_accuracy": 0.0,
|
| 2178 |
+
"eval_NLI-v2_euclidean_accuracy": 1.0,
|
| 2179 |
+
"eval_NLI-v2_manhattan_accuracy": 1.0,
|
| 2180 |
+
"eval_NLI-v2_max_accuracy": 1.0,
|
| 2181 |
+
"eval_VitaminC_cosine_accuracy": 0.57421875,
|
| 2182 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.7887165546417236,
|
| 2183 |
+
"eval_VitaminC_cosine_ap": 0.5443802154749287,
|
| 2184 |
+
"eval_VitaminC_cosine_f1": 0.6595174262734584,
|
| 2185 |
+
"eval_VitaminC_cosine_f1_threshold": 0.35189926624298096,
|
| 2186 |
+
"eval_VitaminC_cosine_precision": 0.492,
|
| 2187 |
+
"eval_VitaminC_cosine_recall": 1.0,
|
| 2188 |
+
"eval_VitaminC_dot_accuracy": 0.5625,
|
| 2189 |
+
"eval_VitaminC_dot_accuracy_threshold": 335.016357421875,
|
| 2190 |
+
"eval_VitaminC_dot_ap": 0.5460930199557891,
|
| 2191 |
+
"eval_VitaminC_dot_f1": 0.6594594594594595,
|
| 2192 |
+
"eval_VitaminC_dot_f1_threshold": 158.6214599609375,
|
| 2193 |
+
"eval_VitaminC_dot_precision": 0.4939271255060729,
|
| 2194 |
+
"eval_VitaminC_dot_recall": 0.991869918699187,
|
| 2195 |
+
"eval_VitaminC_euclidean_accuracy": 0.57421875,
|
| 2196 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 13.359209060668945,
|
| 2197 |
+
"eval_VitaminC_euclidean_ap": 0.5420558119789205,
|
| 2198 |
+
"eval_VitaminC_euclidean_f1": 0.6577540106951871,
|
| 2199 |
+
"eval_VitaminC_euclidean_f1_threshold": 23.44475746154785,
|
| 2200 |
+
"eval_VitaminC_euclidean_precision": 0.4900398406374502,
|
| 2201 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 2202 |
+
"eval_VitaminC_manhattan_accuracy": 0.578125,
|
| 2203 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 309.7850646972656,
|
| 2204 |
+
"eval_VitaminC_manhattan_ap": 0.5398712022586767,
|
| 2205 |
+
"eval_VitaminC_manhattan_f1": 0.6595174262734584,
|
| 2206 |
+
"eval_VitaminC_manhattan_f1_threshold": 486.6765441894531,
|
| 2207 |
+
"eval_VitaminC_manhattan_precision": 0.492,
|
| 2208 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 2209 |
+
"eval_VitaminC_max_accuracy": 0.578125,
|
| 2210 |
+
"eval_VitaminC_max_accuracy_threshold": 335.016357421875,
|
| 2211 |
+
"eval_VitaminC_max_ap": 0.5460930199557891,
|
| 2212 |
+
"eval_VitaminC_max_f1": 0.6595174262734584,
|
| 2213 |
+
"eval_VitaminC_max_f1_threshold": 486.6765441894531,
|
| 2214 |
+
"eval_VitaminC_max_precision": 0.4939271255060729,
|
| 2215 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 2216 |
+
"eval_sequential_score": 0.5460930199557891,
|
| 2217 |
+
"eval_sts-test_pearson_cosine": 0.8332392980969607,
|
| 2218 |
+
"eval_sts-test_pearson_dot": 0.8346600863241642,
|
| 2219 |
+
"eval_sts-test_pearson_euclidean": 0.8653211336269704,
|
| 2220 |
+
"eval_sts-test_pearson_manhattan": 0.8653335270474869,
|
| 2221 |
+
"eval_sts-test_pearson_max": 0.8653335270474869,
|
| 2222 |
+
"eval_sts-test_spearman_cosine": 0.8786841635561152,
|
| 2223 |
+
"eval_sts-test_spearman_dot": 0.8596876540389535,
|
| 2224 |
+
"eval_sts-test_spearman_euclidean": 0.8687344122938186,
|
| 2225 |
+
"eval_sts-test_spearman_manhattan": 0.8687734393508408,
|
| 2226 |
+
"eval_sts-test_spearman_max": 0.8786841635561152,
|
| 2227 |
+
"eval_vitaminc-pairs_loss": 2.4870808124542236,
|
| 2228 |
+
"eval_vitaminc-pairs_runtime": 1.4506,
|
| 2229 |
+
"eval_vitaminc-pairs_samples_per_second": 74.451,
|
| 2230 |
+
"eval_vitaminc-pairs_steps_per_second": 1.379,
|
| 2231 |
+
"step": 297
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 1.6767819336626677,
|
| 2235 |
+
"eval_negation-triplets_loss": 1.7349412441253662,
|
| 2236 |
+
"eval_negation-triplets_runtime": 0.2993,
|
| 2237 |
+
"eval_negation-triplets_samples_per_second": 213.838,
|
| 2238 |
+
"eval_negation-triplets_steps_per_second": 3.341,
|
| 2239 |
+
"step": 297
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 1.6767819336626677,
|
| 2243 |
+
"eval_scitail-pairs-pos_loss": 0.15961770713329315,
|
| 2244 |
+
"eval_scitail-pairs-pos_runtime": 0.3704,
|
| 2245 |
+
"eval_scitail-pairs-pos_samples_per_second": 145.808,
|
| 2246 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.7,
|
| 2247 |
+
"step": 297
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 1.6767819336626677,
|
| 2251 |
+
"eval_xsum-pairs_loss": 0.22417353093624115,
|
| 2252 |
+
"eval_xsum-pairs_runtime": 3.1629,
|
| 2253 |
+
"eval_xsum-pairs_samples_per_second": 40.469,
|
| 2254 |
+
"eval_xsum-pairs_steps_per_second": 0.632,
|
| 2255 |
+
"step": 297
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 1.6767819336626677,
|
| 2259 |
+
"eval_sciq_pairs_loss": 0.03957323729991913,
|
| 2260 |
+
"eval_sciq_pairs_runtime": 3.2788,
|
| 2261 |
+
"eval_sciq_pairs_samples_per_second": 39.039,
|
| 2262 |
+
"eval_sciq_pairs_steps_per_second": 0.61,
|
| 2263 |
+
"step": 297
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.6767819336626677,
|
| 2267 |
+
"eval_qasc_pairs_loss": 0.19627788662910461,
|
| 2268 |
+
"eval_qasc_pairs_runtime": 0.6246,
|
| 2269 |
+
"eval_qasc_pairs_samples_per_second": 204.945,
|
| 2270 |
+
"eval_qasc_pairs_steps_per_second": 3.202,
|
| 2271 |
+
"step": 297
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.6767819336626677,
|
| 2275 |
+
"eval_openbookqa_pairs_loss": 0.7668256163597107,
|
| 2276 |
+
"eval_openbookqa_pairs_runtime": 0.5769,
|
| 2277 |
+
"eval_openbookqa_pairs_samples_per_second": 221.888,
|
| 2278 |
+
"eval_openbookqa_pairs_steps_per_second": 3.467,
|
| 2279 |
+
"step": 297
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 1.6767819336626677,
|
| 2283 |
+
"eval_msmarco_pairs_loss": 0.5024800300598145,
|
| 2284 |
+
"eval_msmarco_pairs_runtime": 1.287,
|
| 2285 |
+
"eval_msmarco_pairs_samples_per_second": 99.457,
|
| 2286 |
+
"eval_msmarco_pairs_steps_per_second": 1.554,
|
| 2287 |
+
"step": 297
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 1.6767819336626677,
|
| 2291 |
+
"eval_nq_pairs_loss": 0.6426529288291931,
|
| 2292 |
+
"eval_nq_pairs_runtime": 2.3694,
|
| 2293 |
+
"eval_nq_pairs_samples_per_second": 54.023,
|
| 2294 |
+
"eval_nq_pairs_steps_per_second": 0.844,
|
| 2295 |
+
"step": 297
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 1.6767819336626677,
|
| 2299 |
+
"eval_trivia_pairs_loss": 0.9762344360351562,
|
| 2300 |
+
"eval_trivia_pairs_runtime": 4.4202,
|
| 2301 |
+
"eval_trivia_pairs_samples_per_second": 28.958,
|
| 2302 |
+
"eval_trivia_pairs_steps_per_second": 0.452,
|
| 2303 |
+
"step": 297
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 1.6767819336626677,
|
| 2307 |
+
"eval_gooaq_pairs_loss": 0.7546207904815674,
|
| 2308 |
+
"eval_gooaq_pairs_runtime": 0.8779,
|
| 2309 |
+
"eval_gooaq_pairs_samples_per_second": 145.803,
|
| 2310 |
+
"eval_gooaq_pairs_steps_per_second": 2.278,
|
| 2311 |
+
"step": 297
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 1.6767819336626677,
|
| 2315 |
+
"eval_paws-pos_loss": 0.029145879670977592,
|
| 2316 |
+
"eval_paws-pos_runtime": 0.6938,
|
| 2317 |
+
"eval_paws-pos_samples_per_second": 184.484,
|
| 2318 |
+
"eval_paws-pos_steps_per_second": 2.883,
|
| 2319 |
+
"step": 297
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.6937191249117856,
|
| 2323 |
+
"grad_norm": 2.766063928604126,
|
| 2324 |
+
"learning_rate": 3.274614187027587e-05,
|
| 2325 |
+
"loss": 0.7786,
|
| 2326 |
+
"step": 300
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.7106563161609034,
|
| 2330 |
+
"grad_norm": 3.1933176517486572,
|
| 2331 |
+
"learning_rate": 3.2428992299601946e-05,
|
| 2332 |
+
"loss": 0.7171,
|
| 2333 |
+
"step": 303
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.7275935074100213,
|
| 2337 |
+
"grad_norm": 3.0088443756103516,
|
| 2338 |
+
"learning_rate": 3.2107781496579536e-05,
|
| 2339 |
+
"loss": 0.6627,
|
| 2340 |
+
"step": 306
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.7445306986591391,
|
| 2344 |
+
"grad_norm": 3.13895845413208,
|
| 2345 |
+
"learning_rate": 3.178273584753023e-05,
|
| 2346 |
+
"loss": 0.6711,
|
| 2347 |
+
"step": 309
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.761467889908257,
|
| 2351 |
+
"grad_norm": 3.34114933013916,
|
| 2352 |
+
"learning_rate": 3.145408444153868e-05,
|
| 2353 |
+
"loss": 0.9076,
|
| 2354 |
+
"step": 312
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.7784050811573748,
|
| 2358 |
+
"grad_norm": 2.5035502910614014,
|
| 2359 |
+
"learning_rate": 3.1122058908992746e-05,
|
| 2360 |
+
"loss": 0.7414,
|
| 2361 |
+
"step": 315
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.7953422724064927,
|
| 2365 |
+
"grad_norm": 2.284698247909546,
|
| 2366 |
+
"learning_rate": 3.078689325833264e-05,
|
| 2367 |
+
"loss": 0.582,
|
| 2368 |
+
"step": 318
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.8122794636556105,
|
| 2372 |
+
"grad_norm": 2.643444538116455,
|
| 2373 |
+
"learning_rate": 3.044882371112396e-05,
|
| 2374 |
+
"loss": 0.6068,
|
| 2375 |
+
"step": 321
|
| 2376 |
+
}
|
| 2377 |
+
],
|
| 2378 |
+
"logging_steps": 3,
|
| 2379 |
+
"max_steps": 531,
|
| 2380 |
+
"num_input_tokens_seen": 0,
|
| 2381 |
+
"num_train_epochs": 3,
|
| 2382 |
+
"save_steps": 107,
|
| 2383 |
+
"stateful_callbacks": {
|
| 2384 |
+
"TrainerControl": {
|
| 2385 |
+
"args": {
|
| 2386 |
+
"should_epoch_stop": false,
|
| 2387 |
+
"should_evaluate": false,
|
| 2388 |
+
"should_log": false,
|
| 2389 |
+
"should_save": true,
|
| 2390 |
+
"should_training_stop": false
|
| 2391 |
+
},
|
| 2392 |
+
"attributes": {}
|
| 2393 |
+
}
|
| 2394 |
+
},
|
| 2395 |
+
"total_flos": 0.0,
|
| 2396 |
+
"train_batch_size": 160,
|
| 2397 |
+
"trial_name": null,
|
| 2398 |
+
"trial_params": null
|
| 2399 |
+
}
|
checkpoint-321/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:526057a01875662c89243f2f1101012515e0f154fca67a38aba3fb44dcb2d6d0
|
| 3 |
+
size 5688
|