Training in progress, step 89, checkpoint
Browse files- checkpoint-89/1_Pooling/config.json +10 -0
- checkpoint-89/README.md +0 -0
- checkpoint-89/added_tokens.json +3 -0
- checkpoint-89/config.json +35 -0
- checkpoint-89/config_sentence_transformers.json +10 -0
- checkpoint-89/modules.json +14 -0
- checkpoint-89/optimizer.pt +3 -0
- checkpoint-89/pytorch_model.bin +3 -0
- checkpoint-89/rng_state.pth +3 -0
- checkpoint-89/scheduler.pt +3 -0
- checkpoint-89/sentence_bert_config.json +4 -0
- checkpoint-89/special_tokens_map.json +51 -0
- checkpoint-89/spm.model +3 -0
- checkpoint-89/tokenizer.json +0 -0
- checkpoint-89/tokenizer_config.json +65 -0
- checkpoint-89/trainer_state.json +806 -0
- checkpoint-89/training_args.bin +3 -0
checkpoint-89/1_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-89/README.md
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-89/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-89/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bobox/DeBERTa-small-ST-v1-test-step2",
|
| 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": "4.44.0",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
checkpoint-89/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.44.0",
|
| 5 |
+
"pytorch": "2.4.0"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-89/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-89/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1233bad028a85700329e62b20ef95f03dcc46444def49eb126dfcdc9323daaec
|
| 3 |
+
size 1130520122
|
checkpoint-89/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e6a36c2280f5123ebee6c3081af0096f34b0c56396ae39ebba00f1bded29ff7
|
| 3 |
+
size 565251810
|
checkpoint-89/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b815252ed3fe78e2bb3e4313682bbf9fa37afbfa479a3aa25022eea0d6f9e95
|
| 3 |
+
size 14244
|
checkpoint-89/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b566d04a4709d8df6bcfe9d5c77f703f7c11abc36e0f795ff805417b27b87f4b
|
| 3 |
+
size 1064
|
checkpoint-89/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-89/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-89/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-89/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-89/tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "[SEP]",
|
| 57 |
+
"sp_model_kwargs": {},
|
| 58 |
+
"split_by_punct": false,
|
| 59 |
+
"stride": 0,
|
| 60 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
+
"unk_token": "[UNK]",
|
| 64 |
+
"vocab_type": "spm"
|
| 65 |
+
}
|
checkpoint-89/trainer_state.json
ADDED
|
@@ -0,0 +1,806 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2,
|
| 5 |
+
"eval_steps": 45,
|
| 6 |
+
"global_step": 89,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0022471910112359553,
|
| 13 |
+
"grad_norm": 3.9492883682250977,
|
| 14 |
+
"learning_rate": 1.9662921348314604e-07,
|
| 15 |
+
"loss": 0.8103,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0044943820224719105,
|
| 20 |
+
"grad_norm": 4.117438793182373,
|
| 21 |
+
"learning_rate": 3.932584269662921e-07,
|
| 22 |
+
"loss": 0.8803,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.006741573033707865,
|
| 27 |
+
"grad_norm": 3.809002161026001,
|
| 28 |
+
"learning_rate": 5.898876404494381e-07,
|
| 29 |
+
"loss": 0.8219,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008988764044943821,
|
| 34 |
+
"grad_norm": 0.7417504787445068,
|
| 35 |
+
"learning_rate": 7.865168539325842e-07,
|
| 36 |
+
"loss": 0.0574,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.011235955056179775,
|
| 41 |
+
"grad_norm": 2.707460403442383,
|
| 42 |
+
"learning_rate": 9.831460674157302e-07,
|
| 43 |
+
"loss": 0.3044,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01348314606741573,
|
| 48 |
+
"grad_norm": 3.082705497741699,
|
| 49 |
+
"learning_rate": 1.1797752808988763e-06,
|
| 50 |
+
"loss": 0.3306,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.015730337078651686,
|
| 55 |
+
"grad_norm": 3.102416753768921,
|
| 56 |
+
"learning_rate": 1.3764044943820223e-06,
|
| 57 |
+
"loss": 0.759,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.017977528089887642,
|
| 62 |
+
"grad_norm": 0.6271047592163086,
|
| 63 |
+
"learning_rate": 1.5730337078651683e-06,
|
| 64 |
+
"loss": 0.0472,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.020224719101123594,
|
| 69 |
+
"grad_norm": 3.1362593173980713,
|
| 70 |
+
"learning_rate": 1.7696629213483144e-06,
|
| 71 |
+
"loss": 0.7782,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02247191011235955,
|
| 76 |
+
"grad_norm": 1.124997615814209,
|
| 77 |
+
"learning_rate": 1.9662921348314604e-06,
|
| 78 |
+
"loss": 0.0757,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.024719101123595506,
|
| 83 |
+
"grad_norm": 3.194413185119629,
|
| 84 |
+
"learning_rate": 2.1629213483146067e-06,
|
| 85 |
+
"loss": 0.7778,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02696629213483146,
|
| 90 |
+
"grad_norm": 3.966202974319458,
|
| 91 |
+
"learning_rate": 2.3595505617977525e-06,
|
| 92 |
+
"loss": 0.7111,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.029213483146067417,
|
| 97 |
+
"grad_norm": 3.63393235206604,
|
| 98 |
+
"learning_rate": 2.5561797752808988e-06,
|
| 99 |
+
"loss": 0.6598,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03146067415730337,
|
| 104 |
+
"grad_norm": 4.087065696716309,
|
| 105 |
+
"learning_rate": 2.7528089887640446e-06,
|
| 106 |
+
"loss": 0.8901,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.033707865168539325,
|
| 111 |
+
"grad_norm": 2.769573211669922,
|
| 112 |
+
"learning_rate": 2.949438202247191e-06,
|
| 113 |
+
"loss": 0.3206,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.035955056179775284,
|
| 118 |
+
"grad_norm": 2.630620002746582,
|
| 119 |
+
"learning_rate": 3.1460674157303367e-06,
|
| 120 |
+
"loss": 0.3408,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.038202247191011236,
|
| 125 |
+
"grad_norm": 2.9570937156677246,
|
| 126 |
+
"learning_rate": 3.342696629213483e-06,
|
| 127 |
+
"loss": 0.5623,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.04044943820224719,
|
| 132 |
+
"grad_norm": 1.0999970436096191,
|
| 133 |
+
"learning_rate": 3.5393258426966288e-06,
|
| 134 |
+
"loss": 0.0758,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04269662921348315,
|
| 139 |
+
"grad_norm": 5.516472816467285,
|
| 140 |
+
"learning_rate": 3.735955056179775e-06,
|
| 141 |
+
"loss": 0.994,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.0449438202247191,
|
| 146 |
+
"grad_norm": 6.245299816131592,
|
| 147 |
+
"learning_rate": 3.932584269662921e-06,
|
| 148 |
+
"loss": 2.4196,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.04719101123595506,
|
| 153 |
+
"grad_norm": 0.546605110168457,
|
| 154 |
+
"learning_rate": 4.129213483146067e-06,
|
| 155 |
+
"loss": 0.0561,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04943820224719101,
|
| 160 |
+
"grad_norm": 0.7049635648727417,
|
| 161 |
+
"learning_rate": 4.325842696629213e-06,
|
| 162 |
+
"loss": 0.0827,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.051685393258426963,
|
| 167 |
+
"grad_norm": 3.1022439002990723,
|
| 168 |
+
"learning_rate": 4.522471910112359e-06,
|
| 169 |
+
"loss": 0.7405,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.05393258426966292,
|
| 174 |
+
"grad_norm": 4.534759044647217,
|
| 175 |
+
"learning_rate": 4.719101123595505e-06,
|
| 176 |
+
"loss": 0.9656,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.056179775280898875,
|
| 181 |
+
"grad_norm": 3.0486032962799072,
|
| 182 |
+
"learning_rate": 4.915730337078652e-06,
|
| 183 |
+
"loss": 0.7855,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.058426966292134834,
|
| 188 |
+
"grad_norm": 3.7457478046417236,
|
| 189 |
+
"learning_rate": 5.1123595505617975e-06,
|
| 190 |
+
"loss": 0.6349,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.060674157303370786,
|
| 195 |
+
"grad_norm": 3.2051479816436768,
|
| 196 |
+
"learning_rate": 5.308988764044943e-06,
|
| 197 |
+
"loss": 0.8087,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.06292134831460675,
|
| 202 |
+
"grad_norm": 4.389094829559326,
|
| 203 |
+
"learning_rate": 5.505617977528089e-06,
|
| 204 |
+
"loss": 0.9282,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0651685393258427,
|
| 209 |
+
"grad_norm": 2.920410394668579,
|
| 210 |
+
"learning_rate": 5.702247191011236e-06,
|
| 211 |
+
"loss": 0.3377,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06741573033707865,
|
| 216 |
+
"grad_norm": 2.7193148136138916,
|
| 217 |
+
"learning_rate": 5.898876404494382e-06,
|
| 218 |
+
"loss": 0.3289,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0696629213483146,
|
| 223 |
+
"grad_norm": 4.0008225440979,
|
| 224 |
+
"learning_rate": 6.0955056179775275e-06,
|
| 225 |
+
"loss": 0.6314,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.07191011235955057,
|
| 230 |
+
"grad_norm": 0.5842159390449524,
|
| 231 |
+
"learning_rate": 6.292134831460673e-06,
|
| 232 |
+
"loss": 0.0611,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.07415730337078652,
|
| 237 |
+
"grad_norm": 3.1256043910980225,
|
| 238 |
+
"learning_rate": 6.48876404494382e-06,
|
| 239 |
+
"loss": 0.8942,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.07640449438202247,
|
| 244 |
+
"grad_norm": 0.9526051878929138,
|
| 245 |
+
"learning_rate": 6.685393258426966e-06,
|
| 246 |
+
"loss": 0.0701,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07865168539325842,
|
| 251 |
+
"grad_norm": 4.061926364898682,
|
| 252 |
+
"learning_rate": 6.882022471910112e-06,
|
| 253 |
+
"loss": 0.8506,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.08089887640449438,
|
| 258 |
+
"grad_norm": 2.8898491859436035,
|
| 259 |
+
"learning_rate": 7.0786516853932575e-06,
|
| 260 |
+
"loss": 0.3386,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.08314606741573034,
|
| 265 |
+
"grad_norm": 0.9806709289550781,
|
| 266 |
+
"learning_rate": 7.275280898876404e-06,
|
| 267 |
+
"loss": 0.0701,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0853932584269663,
|
| 272 |
+
"grad_norm": 3.8004391193389893,
|
| 273 |
+
"learning_rate": 7.47191011235955e-06,
|
| 274 |
+
"loss": 0.8042,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.08764044943820225,
|
| 279 |
+
"grad_norm": 4.089083194732666,
|
| 280 |
+
"learning_rate": 7.668539325842697e-06,
|
| 281 |
+
"loss": 0.8744,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.0898876404494382,
|
| 286 |
+
"grad_norm": 3.419440984725952,
|
| 287 |
+
"learning_rate": 7.865168539325842e-06,
|
| 288 |
+
"loss": 0.8644,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.09213483146067415,
|
| 293 |
+
"grad_norm": 4.094921588897705,
|
| 294 |
+
"learning_rate": 8.061797752808988e-06,
|
| 295 |
+
"loss": 0.8647,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.09438202247191012,
|
| 300 |
+
"grad_norm": 3.9199764728546143,
|
| 301 |
+
"learning_rate": 8.258426966292133e-06,
|
| 302 |
+
"loss": 0.7916,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.09662921348314607,
|
| 307 |
+
"grad_norm": 4.082360744476318,
|
| 308 |
+
"learning_rate": 8.45505617977528e-06,
|
| 309 |
+
"loss": 0.8599,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.09887640449438202,
|
| 314 |
+
"grad_norm": 0.6443855166435242,
|
| 315 |
+
"learning_rate": 8.651685393258427e-06,
|
| 316 |
+
"loss": 0.0523,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.10112359550561797,
|
| 321 |
+
"grad_norm": 4.051048278808594,
|
| 322 |
+
"learning_rate": 8.848314606741572e-06,
|
| 323 |
+
"loss": 0.6968,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.10112359550561797,
|
| 328 |
+
"eval_VitaminC_cosine_accuracy": 0.55859375,
|
| 329 |
+
"eval_VitaminC_cosine_accuracy_threshold": 0.8300318121910095,
|
| 330 |
+
"eval_VitaminC_cosine_ap": 0.5514483751609435,
|
| 331 |
+
"eval_VitaminC_cosine_f1": 0.6657718120805369,
|
| 332 |
+
"eval_VitaminC_cosine_f1_threshold": 0.37456807494163513,
|
| 333 |
+
"eval_VitaminC_cosine_precision": 0.5020242914979757,
|
| 334 |
+
"eval_VitaminC_cosine_recall": 0.9880478087649402,
|
| 335 |
+
"eval_VitaminC_dot_accuracy": 0.5546875,
|
| 336 |
+
"eval_VitaminC_dot_accuracy_threshold": 311.380615234375,
|
| 337 |
+
"eval_VitaminC_dot_ap": 0.5333497363350208,
|
| 338 |
+
"eval_VitaminC_dot_f1": 0.6684709066305818,
|
| 339 |
+
"eval_VitaminC_dot_f1_threshold": 144.8927001953125,
|
| 340 |
+
"eval_VitaminC_dot_precision": 0.5061475409836066,
|
| 341 |
+
"eval_VitaminC_dot_recall": 0.9840637450199203,
|
| 342 |
+
"eval_VitaminC_euclidean_accuracy": 0.556640625,
|
| 343 |
+
"eval_VitaminC_euclidean_accuracy_threshold": 11.028482437133789,
|
| 344 |
+
"eval_VitaminC_euclidean_ap": 0.5544340410314673,
|
| 345 |
+
"eval_VitaminC_euclidean_f1": 0.6649006622516557,
|
| 346 |
+
"eval_VitaminC_euclidean_f1_threshold": 23.38451385498047,
|
| 347 |
+
"eval_VitaminC_euclidean_precision": 0.498015873015873,
|
| 348 |
+
"eval_VitaminC_euclidean_recall": 1.0,
|
| 349 |
+
"eval_VitaminC_manhattan_accuracy": 0.556640625,
|
| 350 |
+
"eval_VitaminC_manhattan_accuracy_threshold": 232.38790893554688,
|
| 351 |
+
"eval_VitaminC_manhattan_ap": 0.5515569514532939,
|
| 352 |
+
"eval_VitaminC_manhattan_f1": 0.6649006622516557,
|
| 353 |
+
"eval_VitaminC_manhattan_f1_threshold": 498.126220703125,
|
| 354 |
+
"eval_VitaminC_manhattan_precision": 0.498015873015873,
|
| 355 |
+
"eval_VitaminC_manhattan_recall": 1.0,
|
| 356 |
+
"eval_VitaminC_max_accuracy": 0.55859375,
|
| 357 |
+
"eval_VitaminC_max_accuracy_threshold": 311.380615234375,
|
| 358 |
+
"eval_VitaminC_max_ap": 0.5544340410314673,
|
| 359 |
+
"eval_VitaminC_max_f1": 0.6684709066305818,
|
| 360 |
+
"eval_VitaminC_max_f1_threshold": 498.126220703125,
|
| 361 |
+
"eval_VitaminC_max_precision": 0.5061475409836066,
|
| 362 |
+
"eval_VitaminC_max_recall": 1.0,
|
| 363 |
+
"eval_sequential_score": 0.5544340410314673,
|
| 364 |
+
"eval_sts-test_pearson_cosine": 0.8803067271464453,
|
| 365 |
+
"eval_sts-test_pearson_dot": 0.8698285291814508,
|
| 366 |
+
"eval_sts-test_pearson_euclidean": 0.9023937835918766,
|
| 367 |
+
"eval_sts-test_pearson_manhattan": 0.9020751259156048,
|
| 368 |
+
"eval_sts-test_pearson_max": 0.9023937835918766,
|
| 369 |
+
"eval_sts-test_spearman_cosine": 0.9038005474254912,
|
| 370 |
+
"eval_sts-test_spearman_dot": 0.8707897794601254,
|
| 371 |
+
"eval_sts-test_spearman_euclidean": 0.8989733631129851,
|
| 372 |
+
"eval_sts-test_spearman_manhattan": 0.8980189529612906,
|
| 373 |
+
"eval_sts-test_spearman_max": 0.9038005474254912,
|
| 374 |
+
"eval_vitaminc-pairs_loss": 1.7273772954940796,
|
| 375 |
+
"eval_vitaminc-pairs_runtime": 1.8924,
|
| 376 |
+
"eval_vitaminc-pairs_samples_per_second": 57.071,
|
| 377 |
+
"eval_vitaminc-pairs_steps_per_second": 1.057,
|
| 378 |
+
"step": 45
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.10112359550561797,
|
| 382 |
+
"eval_negation-triplets_loss": 0.9174526929855347,
|
| 383 |
+
"eval_negation-triplets_runtime": 0.2972,
|
| 384 |
+
"eval_negation-triplets_samples_per_second": 215.314,
|
| 385 |
+
"eval_negation-triplets_steps_per_second": 3.364,
|
| 386 |
+
"step": 45
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.10112359550561797,
|
| 390 |
+
"eval_scitail-pairs-pos_loss": 0.07368183881044388,
|
| 391 |
+
"eval_scitail-pairs-pos_runtime": 0.379,
|
| 392 |
+
"eval_scitail-pairs-pos_samples_per_second": 142.492,
|
| 393 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.639,
|
| 394 |
+
"step": 45
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.10112359550561797,
|
| 398 |
+
"eval_scitail-pairs-qa_loss": 0.001584450714290142,
|
| 399 |
+
"eval_scitail-pairs-qa_runtime": 0.5178,
|
| 400 |
+
"eval_scitail-pairs-qa_samples_per_second": 247.198,
|
| 401 |
+
"eval_scitail-pairs-qa_steps_per_second": 3.862,
|
| 402 |
+
"step": 45
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.10112359550561797,
|
| 406 |
+
"eval_xsum-pairs_loss": 0.038235221058130264,
|
| 407 |
+
"eval_xsum-pairs_runtime": 2.7268,
|
| 408 |
+
"eval_xsum-pairs_samples_per_second": 46.941,
|
| 409 |
+
"eval_xsum-pairs_steps_per_second": 0.733,
|
| 410 |
+
"step": 45
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.10112359550561797,
|
| 414 |
+
"eval_sciq_pairs_loss": 0.01538097020238638,
|
| 415 |
+
"eval_sciq_pairs_runtime": 2.7808,
|
| 416 |
+
"eval_sciq_pairs_samples_per_second": 46.029,
|
| 417 |
+
"eval_sciq_pairs_steps_per_second": 0.719,
|
| 418 |
+
"step": 45
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.10112359550561797,
|
| 422 |
+
"eval_qasc_pairs_loss": 0.09078988432884216,
|
| 423 |
+
"eval_qasc_pairs_runtime": 0.6473,
|
| 424 |
+
"eval_qasc_pairs_samples_per_second": 197.758,
|
| 425 |
+
"eval_qasc_pairs_steps_per_second": 3.09,
|
| 426 |
+
"step": 45
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.10112359550561797,
|
| 430 |
+
"eval_openbookqa_pairs_loss": 0.6754768490791321,
|
| 431 |
+
"eval_openbookqa_pairs_runtime": 0.573,
|
| 432 |
+
"eval_openbookqa_pairs_samples_per_second": 223.397,
|
| 433 |
+
"eval_openbookqa_pairs_steps_per_second": 3.491,
|
| 434 |
+
"step": 45
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.10112359550561797,
|
| 438 |
+
"eval_msmarco_pairs_loss": 0.15991328656673431,
|
| 439 |
+
"eval_msmarco_pairs_runtime": 1.487,
|
| 440 |
+
"eval_msmarco_pairs_samples_per_second": 86.078,
|
| 441 |
+
"eval_msmarco_pairs_steps_per_second": 1.345,
|
| 442 |
+
"step": 45
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.10112359550561797,
|
| 446 |
+
"eval_nq_pairs_loss": 0.09591890126466751,
|
| 447 |
+
"eval_nq_pairs_runtime": 2.3943,
|
| 448 |
+
"eval_nq_pairs_samples_per_second": 53.459,
|
| 449 |
+
"eval_nq_pairs_steps_per_second": 0.835,
|
| 450 |
+
"step": 45
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.10112359550561797,
|
| 454 |
+
"eval_trivia_pairs_loss": 0.5305934548377991,
|
| 455 |
+
"eval_trivia_pairs_runtime": 3.5752,
|
| 456 |
+
"eval_trivia_pairs_samples_per_second": 35.802,
|
| 457 |
+
"eval_trivia_pairs_steps_per_second": 0.559,
|
| 458 |
+
"step": 45
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.10112359550561797,
|
| 462 |
+
"eval_gooaq_pairs_loss": 0.29681000113487244,
|
| 463 |
+
"eval_gooaq_pairs_runtime": 0.9087,
|
| 464 |
+
"eval_gooaq_pairs_samples_per_second": 140.861,
|
| 465 |
+
"eval_gooaq_pairs_steps_per_second": 2.201,
|
| 466 |
+
"step": 45
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.10112359550561797,
|
| 470 |
+
"eval_paws-pos_loss": 0.024501051753759384,
|
| 471 |
+
"eval_paws-pos_runtime": 0.6773,
|
| 472 |
+
"eval_paws-pos_samples_per_second": 188.996,
|
| 473 |
+
"eval_paws-pos_steps_per_second": 2.953,
|
| 474 |
+
"step": 45
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.10337078651685393,
|
| 478 |
+
"grad_norm": 2.9021923542022705,
|
| 479 |
+
"learning_rate": 9.044943820224718e-06,
|
| 480 |
+
"loss": 0.3376,
|
| 481 |
+
"step": 46
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.10561797752808989,
|
| 485 |
+
"grad_norm": 3.179288625717163,
|
| 486 |
+
"learning_rate": 9.241573033707863e-06,
|
| 487 |
+
"loss": 0.5174,
|
| 488 |
+
"step": 47
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.10786516853932585,
|
| 492 |
+
"grad_norm": 3.1919493675231934,
|
| 493 |
+
"learning_rate": 9.43820224719101e-06,
|
| 494 |
+
"loss": 0.8162,
|
| 495 |
+
"step": 48
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.1101123595505618,
|
| 499 |
+
"grad_norm": 2.8602521419525146,
|
| 500 |
+
"learning_rate": 9.634831460674157e-06,
|
| 501 |
+
"loss": 0.3545,
|
| 502 |
+
"step": 49
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.11235955056179775,
|
| 506 |
+
"grad_norm": 2.7570478916168213,
|
| 507 |
+
"learning_rate": 9.831460674157303e-06,
|
| 508 |
+
"loss": 0.315,
|
| 509 |
+
"step": 50
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.1146067415730337,
|
| 513 |
+
"grad_norm": 0.8641514778137207,
|
| 514 |
+
"learning_rate": 1.0028089887640448e-05,
|
| 515 |
+
"loss": 0.0627,
|
| 516 |
+
"step": 51
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.11685393258426967,
|
| 520 |
+
"grad_norm": 3.9437484741210938,
|
| 521 |
+
"learning_rate": 1.0224719101123595e-05,
|
| 522 |
+
"loss": 0.8851,
|
| 523 |
+
"step": 52
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.11910112359550562,
|
| 527 |
+
"grad_norm": 4.144773006439209,
|
| 528 |
+
"learning_rate": 1.042134831460674e-05,
|
| 529 |
+
"loss": 0.8382,
|
| 530 |
+
"step": 53
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.12134831460674157,
|
| 534 |
+
"grad_norm": 4.277736186981201,
|
| 535 |
+
"learning_rate": 1.0617977528089887e-05,
|
| 536 |
+
"loss": 0.733,
|
| 537 |
+
"step": 54
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.12359550561797752,
|
| 541 |
+
"grad_norm": 4.025904178619385,
|
| 542 |
+
"learning_rate": 1.0814606741573032e-05,
|
| 543 |
+
"loss": 0.7173,
|
| 544 |
+
"step": 55
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.1258426966292135,
|
| 548 |
+
"grad_norm": 3.923046827316284,
|
| 549 |
+
"learning_rate": 1.1011235955056178e-05,
|
| 550 |
+
"loss": 0.7659,
|
| 551 |
+
"step": 56
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.12808988764044943,
|
| 555 |
+
"grad_norm": 3.2707138061523438,
|
| 556 |
+
"learning_rate": 1.1207865168539325e-05,
|
| 557 |
+
"loss": 0.793,
|
| 558 |
+
"step": 57
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.1303370786516854,
|
| 562 |
+
"grad_norm": 3.1660959720611572,
|
| 563 |
+
"learning_rate": 1.1404494382022472e-05,
|
| 564 |
+
"loss": 0.5426,
|
| 565 |
+
"step": 58
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.13258426966292136,
|
| 569 |
+
"grad_norm": 4.5236663818359375,
|
| 570 |
+
"learning_rate": 1.1601123595505617e-05,
|
| 571 |
+
"loss": 0.7641,
|
| 572 |
+
"step": 59
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.1348314606741573,
|
| 576 |
+
"grad_norm": 0.5771021246910095,
|
| 577 |
+
"learning_rate": 1.1797752808988763e-05,
|
| 578 |
+
"loss": 0.0657,
|
| 579 |
+
"step": 60
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.13707865168539327,
|
| 583 |
+
"grad_norm": 3.8541343212127686,
|
| 584 |
+
"learning_rate": 1.1994382022471908e-05,
|
| 585 |
+
"loss": 0.7836,
|
| 586 |
+
"step": 61
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.1393258426966292,
|
| 590 |
+
"grad_norm": 4.284148693084717,
|
| 591 |
+
"learning_rate": 1.2191011235955055e-05,
|
| 592 |
+
"loss": 0.9306,
|
| 593 |
+
"step": 62
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.14157303370786517,
|
| 597 |
+
"grad_norm": 4.175032615661621,
|
| 598 |
+
"learning_rate": 1.23876404494382e-05,
|
| 599 |
+
"loss": 0.8673,
|
| 600 |
+
"step": 63
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.14382022471910114,
|
| 604 |
+
"grad_norm": 5.025452136993408,
|
| 605 |
+
"learning_rate": 1.2584269662921347e-05,
|
| 606 |
+
"loss": 0.9296,
|
| 607 |
+
"step": 64
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.14606741573033707,
|
| 611 |
+
"grad_norm": 3.970745086669922,
|
| 612 |
+
"learning_rate": 1.2780898876404493e-05,
|
| 613 |
+
"loss": 0.8211,
|
| 614 |
+
"step": 65
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.14831460674157304,
|
| 618 |
+
"grad_norm": 3.150197744369507,
|
| 619 |
+
"learning_rate": 1.297752808988764e-05,
|
| 620 |
+
"loss": 0.7685,
|
| 621 |
+
"step": 66
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.15056179775280898,
|
| 625 |
+
"grad_norm": 4.280994415283203,
|
| 626 |
+
"learning_rate": 1.3174157303370785e-05,
|
| 627 |
+
"loss": 0.7139,
|
| 628 |
+
"step": 67
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.15280898876404495,
|
| 632 |
+
"grad_norm": 4.288730621337891,
|
| 633 |
+
"learning_rate": 1.3370786516853932e-05,
|
| 634 |
+
"loss": 0.8241,
|
| 635 |
+
"step": 68
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.1550561797752809,
|
| 639 |
+
"grad_norm": 3.7402424812316895,
|
| 640 |
+
"learning_rate": 1.3567415730337077e-05,
|
| 641 |
+
"loss": 0.6256,
|
| 642 |
+
"step": 69
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.15730337078651685,
|
| 646 |
+
"grad_norm": 4.478890895843506,
|
| 647 |
+
"learning_rate": 1.3764044943820223e-05,
|
| 648 |
+
"loss": 0.8842,
|
| 649 |
+
"step": 70
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.15955056179775282,
|
| 653 |
+
"grad_norm": 3.8147876262664795,
|
| 654 |
+
"learning_rate": 1.3960674157303368e-05,
|
| 655 |
+
"loss": 0.804,
|
| 656 |
+
"step": 71
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.16179775280898875,
|
| 660 |
+
"grad_norm": 0.7314035296440125,
|
| 661 |
+
"learning_rate": 1.4157303370786515e-05,
|
| 662 |
+
"loss": 0.0989,
|
| 663 |
+
"step": 72
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.16404494382022472,
|
| 667 |
+
"grad_norm": 3.074303150177002,
|
| 668 |
+
"learning_rate": 1.4353932584269662e-05,
|
| 669 |
+
"loss": 0.332,
|
| 670 |
+
"step": 73
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.1662921348314607,
|
| 674 |
+
"grad_norm": 3.414987325668335,
|
| 675 |
+
"learning_rate": 1.4550561797752808e-05,
|
| 676 |
+
"loss": 0.5736,
|
| 677 |
+
"step": 74
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.16853932584269662,
|
| 681 |
+
"grad_norm": 3.7946674823760986,
|
| 682 |
+
"learning_rate": 1.4747191011235953e-05,
|
| 683 |
+
"loss": 0.8285,
|
| 684 |
+
"step": 75
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.1707865168539326,
|
| 688 |
+
"grad_norm": 4.310474395751953,
|
| 689 |
+
"learning_rate": 1.49438202247191e-05,
|
| 690 |
+
"loss": 0.9561,
|
| 691 |
+
"step": 76
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.17303370786516853,
|
| 695 |
+
"grad_norm": 0.9791378974914551,
|
| 696 |
+
"learning_rate": 1.5140449438202245e-05,
|
| 697 |
+
"loss": 0.0633,
|
| 698 |
+
"step": 77
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.1752808988764045,
|
| 702 |
+
"grad_norm": 0.6351795196533203,
|
| 703 |
+
"learning_rate": 1.5337078651685393e-05,
|
| 704 |
+
"loss": 0.0848,
|
| 705 |
+
"step": 78
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.17752808988764046,
|
| 709 |
+
"grad_norm": 3.4832303524017334,
|
| 710 |
+
"learning_rate": 1.553370786516854e-05,
|
| 711 |
+
"loss": 0.8325,
|
| 712 |
+
"step": 79
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.1797752808988764,
|
| 716 |
+
"grad_norm": 5.115800380706787,
|
| 717 |
+
"learning_rate": 1.5730337078651683e-05,
|
| 718 |
+
"loss": 1.0011,
|
| 719 |
+
"step": 80
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.18202247191011237,
|
| 723 |
+
"grad_norm": 3.552396297454834,
|
| 724 |
+
"learning_rate": 1.592696629213483e-05,
|
| 725 |
+
"loss": 0.8697,
|
| 726 |
+
"step": 81
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.1842696629213483,
|
| 730 |
+
"grad_norm": 4.491541862487793,
|
| 731 |
+
"learning_rate": 1.6123595505617977e-05,
|
| 732 |
+
"loss": 0.8344,
|
| 733 |
+
"step": 82
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.18651685393258427,
|
| 737 |
+
"grad_norm": 4.73278284072876,
|
| 738 |
+
"learning_rate": 1.6320224719101122e-05,
|
| 739 |
+
"loss": 0.9967,
|
| 740 |
+
"step": 83
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.18876404494382024,
|
| 744 |
+
"grad_norm": 2.994192123413086,
|
| 745 |
+
"learning_rate": 1.6516853932584267e-05,
|
| 746 |
+
"loss": 0.4638,
|
| 747 |
+
"step": 84
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.19101123595505617,
|
| 751 |
+
"grad_norm": 4.142394542694092,
|
| 752 |
+
"learning_rate": 1.6713483146067415e-05,
|
| 753 |
+
"loss": 0.8994,
|
| 754 |
+
"step": 85
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.19325842696629214,
|
| 758 |
+
"grad_norm": 4.149839401245117,
|
| 759 |
+
"learning_rate": 1.691011235955056e-05,
|
| 760 |
+
"loss": 0.7789,
|
| 761 |
+
"step": 86
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.19550561797752808,
|
| 765 |
+
"grad_norm": 0.45795938372612,
|
| 766 |
+
"learning_rate": 1.7106741573033705e-05,
|
| 767 |
+
"loss": 0.0555,
|
| 768 |
+
"step": 87
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.19775280898876405,
|
| 772 |
+
"grad_norm": 3.4293618202209473,
|
| 773 |
+
"learning_rate": 1.7303370786516853e-05,
|
| 774 |
+
"loss": 0.3778,
|
| 775 |
+
"step": 88
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.2,
|
| 779 |
+
"grad_norm": 4.041529655456543,
|
| 780 |
+
"learning_rate": 1.75e-05,
|
| 781 |
+
"loss": 0.708,
|
| 782 |
+
"step": 89
|
| 783 |
+
}
|
| 784 |
+
],
|
| 785 |
+
"logging_steps": 1,
|
| 786 |
+
"max_steps": 890,
|
| 787 |
+
"num_input_tokens_seen": 0,
|
| 788 |
+
"num_train_epochs": 2,
|
| 789 |
+
"save_steps": 89,
|
| 790 |
+
"stateful_callbacks": {
|
| 791 |
+
"TrainerControl": {
|
| 792 |
+
"args": {
|
| 793 |
+
"should_epoch_stop": false,
|
| 794 |
+
"should_evaluate": false,
|
| 795 |
+
"should_log": false,
|
| 796 |
+
"should_save": true,
|
| 797 |
+
"should_training_stop": false
|
| 798 |
+
},
|
| 799 |
+
"attributes": {}
|
| 800 |
+
}
|
| 801 |
+
},
|
| 802 |
+
"total_flos": 0.0,
|
| 803 |
+
"train_batch_size": 640,
|
| 804 |
+
"trial_name": null,
|
| 805 |
+
"trial_params": null
|
| 806 |
+
}
|
checkpoint-89/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db14a166daba939b5d6d6e272be7e74379c2defcff24dc5638ec137086aaf24
|
| 3 |
+
size 5752
|