Training in progress, step 716, checkpoint
Browse files- checkpoint-716/1_Pooling/config.json +10 -0
- checkpoint-716/added_tokens.json +3 -0
- checkpoint-716/config.json +35 -0
- checkpoint-716/config_sentence_transformers.json +10 -0
- checkpoint-716/modules.json +14 -0
- checkpoint-716/optimizer.pt +3 -0
- checkpoint-716/pytorch_model.bin +3 -0
- checkpoint-716/rng_state.pth +3 -0
- checkpoint-716/scheduler.pt +3 -0
- checkpoint-716/sentence_bert_config.json +4 -0
- checkpoint-716/special_tokens_map.json +51 -0
- checkpoint-716/spm.model +3 -0
- checkpoint-716/tokenizer.json +0 -0
- checkpoint-716/tokenizer_config.json +65 -0
- checkpoint-716/trainer_state.json +858 -0
- checkpoint-716/training_args.bin +3 -0
checkpoint-716/1_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-716/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-716/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bobox/DeBERTa-ST-AllLayers-v3-checkpoints-tmp",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2Model"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.41.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
checkpoint-716/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.41.2",
|
| 5 |
+
"pytorch": "2.3.0+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-716/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-716/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41596b0669a785028a6375835bf7dd69c5416745370e8e0c88cef703219a8abf
|
| 3 |
+
size 1130520122
|
checkpoint-716/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:321e5203f313bcf7d364114ca08e3b34977f8816dc017487429467dd10658bc3
|
| 3 |
+
size 565251810
|
checkpoint-716/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea2550c7aaa22352b073afcd46bcc4207f5b341a2aef20a2620daa43b62f853
|
| 3 |
+
size 14244
|
checkpoint-716/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59aaab6983107b79b258f60a9fd2e0784eebfa8d3263a57407c94cd5178be0d7
|
| 3 |
+
size 1064
|
checkpoint-716/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-716/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-716/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-716/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-716/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": 1000000000000000019884624838656,
|
| 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-716/trainer_state.json
ADDED
|
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2,
|
| 5 |
+
"eval_steps": 179,
|
| 6 |
+
"global_step": 716,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005027932960893855,
|
| 13 |
+
"grad_norm": 28.300092697143555,
|
| 14 |
+
"learning_rate": 6.331471135940411e-07,
|
| 15 |
+
"loss": 1.0198,
|
| 16 |
+
"step": 18
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01005586592178771,
|
| 20 |
+
"grad_norm": 1.059788465499878,
|
| 21 |
+
"learning_rate": 1.303538175046555e-06,
|
| 22 |
+
"loss": 0.8564,
|
| 23 |
+
"step": 36
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.015083798882681564,
|
| 27 |
+
"grad_norm": 9.368417739868164,
|
| 28 |
+
"learning_rate": 1.9739292364990693e-06,
|
| 29 |
+
"loss": 0.685,
|
| 30 |
+
"step": 54
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02011173184357542,
|
| 34 |
+
"grad_norm": 3.4458816051483154,
|
| 35 |
+
"learning_rate": 2.644320297951583e-06,
|
| 36 |
+
"loss": 0.7667,
|
| 37 |
+
"step": 72
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.025139664804469275,
|
| 41 |
+
"grad_norm": 4.497154712677002,
|
| 42 |
+
"learning_rate": 3.314711359404097e-06,
|
| 43 |
+
"loss": 0.7907,
|
| 44 |
+
"step": 90
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.030167597765363128,
|
| 48 |
+
"grad_norm": 4.394736289978027,
|
| 49 |
+
"learning_rate": 3.985102420856611e-06,
|
| 50 |
+
"loss": 0.9719,
|
| 51 |
+
"step": 108
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03519553072625698,
|
| 55 |
+
"grad_norm": 10.305765151977539,
|
| 56 |
+
"learning_rate": 4.655493482309125e-06,
|
| 57 |
+
"loss": 1.1097,
|
| 58 |
+
"step": 126
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04022346368715084,
|
| 62 |
+
"grad_norm": 5.402688980102539,
|
| 63 |
+
"learning_rate": 5.325884543761639e-06,
|
| 64 |
+
"loss": 1.0463,
|
| 65 |
+
"step": 144
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.045251396648044694,
|
| 69 |
+
"grad_norm": 0.2811428904533386,
|
| 70 |
+
"learning_rate": 5.996275605214154e-06,
|
| 71 |
+
"loss": 0.8796,
|
| 72 |
+
"step": 162
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05,
|
| 76 |
+
"eval_nli-pairs_loss": 0.9358150959014893,
|
| 77 |
+
"eval_nli-pairs_runtime": 3.7163,
|
| 78 |
+
"eval_nli-pairs_samples_per_second": 40.363,
|
| 79 |
+
"eval_nli-pairs_steps_per_second": 0.538,
|
| 80 |
+
"eval_sts-test_pearson_cosine": 0.7920907827756308,
|
| 81 |
+
"eval_sts-test_pearson_dot": 0.553905804338793,
|
| 82 |
+
"eval_sts-test_pearson_euclidean": 0.7477067417028286,
|
| 83 |
+
"eval_sts-test_pearson_manhattan": 0.7454637009944656,
|
| 84 |
+
"eval_sts-test_pearson_max": 0.7920907827756308,
|
| 85 |
+
"eval_sts-test_spearman_cosine": 0.8050902340286232,
|
| 86 |
+
"eval_sts-test_spearman_dot": 0.5325926730168974,
|
| 87 |
+
"eval_sts-test_spearman_euclidean": 0.73705041377373,
|
| 88 |
+
"eval_sts-test_spearman_manhattan": 0.7373939486807765,
|
| 89 |
+
"eval_sts-test_spearman_max": 0.8050902340286232,
|
| 90 |
+
"step": 179
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05,
|
| 94 |
+
"eval_vitaminc-pairs_loss": 4.57532262802124,
|
| 95 |
+
"eval_vitaminc-pairs_runtime": 0.8386,
|
| 96 |
+
"eval_vitaminc-pairs_samples_per_second": 149.066,
|
| 97 |
+
"eval_vitaminc-pairs_steps_per_second": 2.385,
|
| 98 |
+
"step": 179
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.05,
|
| 102 |
+
"eval_qnli-contrastive_loss": 0.260235071182251,
|
| 103 |
+
"eval_qnli-contrastive_runtime": 0.1227,
|
| 104 |
+
"eval_qnli-contrastive_samples_per_second": 1222.824,
|
| 105 |
+
"eval_qnli-contrastive_steps_per_second": 16.304,
|
| 106 |
+
"step": 179
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.05,
|
| 110 |
+
"eval_scitail-pairs-qa_loss": 0.06116430461406708,
|
| 111 |
+
"eval_scitail-pairs-qa_runtime": 0.6972,
|
| 112 |
+
"eval_scitail-pairs-qa_samples_per_second": 215.142,
|
| 113 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.869,
|
| 114 |
+
"step": 179
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05,
|
| 118 |
+
"eval_scitail-pairs-pos_loss": 0.3001463711261749,
|
| 119 |
+
"eval_scitail-pairs-pos_runtime": 1.8226,
|
| 120 |
+
"eval_scitail-pairs-pos_samples_per_second": 82.299,
|
| 121 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.097,
|
| 122 |
+
"step": 179
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05,
|
| 126 |
+
"eval_xsum-pairs_loss": 0.43996042013168335,
|
| 127 |
+
"eval_xsum-pairs_runtime": 0.1548,
|
| 128 |
+
"eval_xsum-pairs_samples_per_second": 529.555,
|
| 129 |
+
"eval_xsum-pairs_steps_per_second": 6.458,
|
| 130 |
+
"step": 179
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05,
|
| 134 |
+
"eval_compression-pairs_loss": 0.10088926553726196,
|
| 135 |
+
"eval_compression-pairs_runtime": 0.1051,
|
| 136 |
+
"eval_compression-pairs_samples_per_second": 1427.213,
|
| 137 |
+
"eval_compression-pairs_steps_per_second": 19.03,
|
| 138 |
+
"step": 179
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.05,
|
| 142 |
+
"eval_sciq_pairs_loss": 0.15509434044361115,
|
| 143 |
+
"eval_sciq_pairs_runtime": 4.9415,
|
| 144 |
+
"eval_sciq_pairs_samples_per_second": 30.355,
|
| 145 |
+
"eval_sciq_pairs_steps_per_second": 0.405,
|
| 146 |
+
"step": 179
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.05,
|
| 150 |
+
"eval_qasc_pairs_loss": 0.24072103202342987,
|
| 151 |
+
"eval_qasc_pairs_runtime": 0.6453,
|
| 152 |
+
"eval_qasc_pairs_samples_per_second": 232.455,
|
| 153 |
+
"eval_qasc_pairs_steps_per_second": 3.099,
|
| 154 |
+
"step": 179
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.05,
|
| 158 |
+
"eval_openbookqa_pairs_loss": 1.5241280794143677,
|
| 159 |
+
"eval_openbookqa_pairs_runtime": 0.7059,
|
| 160 |
+
"eval_openbookqa_pairs_samples_per_second": 212.48,
|
| 161 |
+
"eval_openbookqa_pairs_steps_per_second": 2.833,
|
| 162 |
+
"step": 179
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.05,
|
| 166 |
+
"eval_msmarco_pairs_loss": 0.6149919629096985,
|
| 167 |
+
"eval_msmarco_pairs_runtime": 1.2013,
|
| 168 |
+
"eval_msmarco_pairs_samples_per_second": 124.863,
|
| 169 |
+
"eval_msmarco_pairs_steps_per_second": 1.665,
|
| 170 |
+
"step": 179
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.05,
|
| 174 |
+
"eval_nq_pairs_loss": 0.591522216796875,
|
| 175 |
+
"eval_nq_pairs_runtime": 2.2917,
|
| 176 |
+
"eval_nq_pairs_samples_per_second": 65.455,
|
| 177 |
+
"eval_nq_pairs_steps_per_second": 0.873,
|
| 178 |
+
"step": 179
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.05,
|
| 182 |
+
"eval_trivia_pairs_loss": 1.0899044275283813,
|
| 183 |
+
"eval_trivia_pairs_runtime": 3.1583,
|
| 184 |
+
"eval_trivia_pairs_samples_per_second": 47.494,
|
| 185 |
+
"eval_trivia_pairs_steps_per_second": 0.633,
|
| 186 |
+
"step": 179
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.05,
|
| 190 |
+
"eval_quora_pairs_loss": 0.21252885460853577,
|
| 191 |
+
"eval_quora_pairs_runtime": 0.3861,
|
| 192 |
+
"eval_quora_pairs_samples_per_second": 388.452,
|
| 193 |
+
"eval_quora_pairs_steps_per_second": 5.179,
|
| 194 |
+
"step": 179
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.05,
|
| 198 |
+
"eval_gooaq_pairs_loss": 0.5593109130859375,
|
| 199 |
+
"eval_gooaq_pairs_runtime": 0.7918,
|
| 200 |
+
"eval_gooaq_pairs_samples_per_second": 189.449,
|
| 201 |
+
"eval_gooaq_pairs_steps_per_second": 2.526,
|
| 202 |
+
"step": 179
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.05,
|
| 206 |
+
"eval_mrpc_pairs_loss": 0.055620357394218445,
|
| 207 |
+
"eval_mrpc_pairs_runtime": 0.1048,
|
| 208 |
+
"eval_mrpc_pairs_samples_per_second": 1431.291,
|
| 209 |
+
"eval_mrpc_pairs_steps_per_second": 19.084,
|
| 210 |
+
"step": 179
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.05027932960893855,
|
| 214 |
+
"grad_norm": 9.769979476928711,
|
| 215 |
+
"learning_rate": 6.666666666666667e-06,
|
| 216 |
+
"loss": 0.7777,
|
| 217 |
+
"step": 180
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.0553072625698324,
|
| 221 |
+
"grad_norm": 9.294490814208984,
|
| 222 |
+
"learning_rate": 7.337057728119181e-06,
|
| 223 |
+
"loss": 0.9075,
|
| 224 |
+
"step": 198
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.060335195530726256,
|
| 228 |
+
"grad_norm": 0.6179952621459961,
|
| 229 |
+
"learning_rate": 8.007448789571696e-06,
|
| 230 |
+
"loss": 0.8239,
|
| 231 |
+
"step": 216
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.06536312849162011,
|
| 235 |
+
"grad_norm": 6.369142532348633,
|
| 236 |
+
"learning_rate": 8.677839851024209e-06,
|
| 237 |
+
"loss": 0.949,
|
| 238 |
+
"step": 234
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.07039106145251396,
|
| 242 |
+
"grad_norm": 1.7066636085510254,
|
| 243 |
+
"learning_rate": 9.348230912476724e-06,
|
| 244 |
+
"loss": 1.2046,
|
| 245 |
+
"step": 252
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.07541899441340782,
|
| 249 |
+
"grad_norm": 0.33892622590065,
|
| 250 |
+
"learning_rate": 1.0018621973929237e-05,
|
| 251 |
+
"loss": 0.8526,
|
| 252 |
+
"step": 270
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.08044692737430167,
|
| 256 |
+
"grad_norm": 24.46626091003418,
|
| 257 |
+
"learning_rate": 1.0689013035381753e-05,
|
| 258 |
+
"loss": 0.8629,
|
| 259 |
+
"step": 288
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.08547486033519552,
|
| 263 |
+
"grad_norm": 9.228001594543457,
|
| 264 |
+
"learning_rate": 1.1359404096834266e-05,
|
| 265 |
+
"loss": 1.1474,
|
| 266 |
+
"step": 306
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.09050279329608939,
|
| 270 |
+
"grad_norm": 3.441566228866577,
|
| 271 |
+
"learning_rate": 1.2029795158286779e-05,
|
| 272 |
+
"loss": 0.9141,
|
| 273 |
+
"step": 324
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.09553072625698324,
|
| 277 |
+
"grad_norm": 0.3621586859226227,
|
| 278 |
+
"learning_rate": 1.2700186219739294e-05,
|
| 279 |
+
"loss": 0.9756,
|
| 280 |
+
"step": 342
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.1,
|
| 284 |
+
"eval_nli-pairs_loss": 0.9455356001853943,
|
| 285 |
+
"eval_nli-pairs_runtime": 3.6115,
|
| 286 |
+
"eval_nli-pairs_samples_per_second": 41.533,
|
| 287 |
+
"eval_nli-pairs_steps_per_second": 0.554,
|
| 288 |
+
"eval_sts-test_pearson_cosine": 0.7944563743777492,
|
| 289 |
+
"eval_sts-test_pearson_dot": 0.554185693724103,
|
| 290 |
+
"eval_sts-test_pearson_euclidean": 0.7483225064388481,
|
| 291 |
+
"eval_sts-test_pearson_manhattan": 0.7454936340776467,
|
| 292 |
+
"eval_sts-test_pearson_max": 0.7944563743777492,
|
| 293 |
+
"eval_sts-test_spearman_cosine": 0.8064910811776218,
|
| 294 |
+
"eval_sts-test_spearman_dot": 0.5333761592947532,
|
| 295 |
+
"eval_sts-test_spearman_euclidean": 0.7382698586949932,
|
| 296 |
+
"eval_sts-test_spearman_manhattan": 0.7378149008082869,
|
| 297 |
+
"eval_sts-test_spearman_max": 0.8064910811776218,
|
| 298 |
+
"step": 358
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1,
|
| 302 |
+
"eval_vitaminc-pairs_loss": 4.517832279205322,
|
| 303 |
+
"eval_vitaminc-pairs_runtime": 0.8908,
|
| 304 |
+
"eval_vitaminc-pairs_samples_per_second": 140.33,
|
| 305 |
+
"eval_vitaminc-pairs_steps_per_second": 2.245,
|
| 306 |
+
"step": 358
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.1,
|
| 310 |
+
"eval_qnli-contrastive_loss": 0.2627922296524048,
|
| 311 |
+
"eval_qnli-contrastive_runtime": 0.1229,
|
| 312 |
+
"eval_qnli-contrastive_samples_per_second": 1220.886,
|
| 313 |
+
"eval_qnli-contrastive_steps_per_second": 16.278,
|
| 314 |
+
"step": 358
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.1,
|
| 318 |
+
"eval_scitail-pairs-qa_loss": 0.06381849944591522,
|
| 319 |
+
"eval_scitail-pairs-qa_runtime": 0.7125,
|
| 320 |
+
"eval_scitail-pairs-qa_samples_per_second": 210.516,
|
| 321 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.807,
|
| 322 |
+
"step": 358
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.1,
|
| 326 |
+
"eval_scitail-pairs-pos_loss": 0.30350035429000854,
|
| 327 |
+
"eval_scitail-pairs-pos_runtime": 1.877,
|
| 328 |
+
"eval_scitail-pairs-pos_samples_per_second": 79.916,
|
| 329 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.066,
|
| 330 |
+
"step": 358
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.1,
|
| 334 |
+
"eval_xsum-pairs_loss": 0.44631534814834595,
|
| 335 |
+
"eval_xsum-pairs_runtime": 0.1512,
|
| 336 |
+
"eval_xsum-pairs_samples_per_second": 542.377,
|
| 337 |
+
"eval_xsum-pairs_steps_per_second": 6.614,
|
| 338 |
+
"step": 358
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.1,
|
| 342 |
+
"eval_compression-pairs_loss": 0.10376789420843124,
|
| 343 |
+
"eval_compression-pairs_runtime": 0.1034,
|
| 344 |
+
"eval_compression-pairs_samples_per_second": 1450.105,
|
| 345 |
+
"eval_compression-pairs_steps_per_second": 19.335,
|
| 346 |
+
"step": 358
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.1,
|
| 350 |
+
"eval_sciq_pairs_loss": 0.15615364909172058,
|
| 351 |
+
"eval_sciq_pairs_runtime": 5.1236,
|
| 352 |
+
"eval_sciq_pairs_samples_per_second": 29.276,
|
| 353 |
+
"eval_sciq_pairs_steps_per_second": 0.39,
|
| 354 |
+
"step": 358
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.1,
|
| 358 |
+
"eval_qasc_pairs_loss": 0.24106402695178986,
|
| 359 |
+
"eval_qasc_pairs_runtime": 0.6663,
|
| 360 |
+
"eval_qasc_pairs_samples_per_second": 225.133,
|
| 361 |
+
"eval_qasc_pairs_steps_per_second": 3.002,
|
| 362 |
+
"step": 358
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.1,
|
| 366 |
+
"eval_openbookqa_pairs_loss": 1.5405189990997314,
|
| 367 |
+
"eval_openbookqa_pairs_runtime": 0.7365,
|
| 368 |
+
"eval_openbookqa_pairs_samples_per_second": 203.658,
|
| 369 |
+
"eval_openbookqa_pairs_steps_per_second": 2.715,
|
| 370 |
+
"step": 358
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.1,
|
| 374 |
+
"eval_msmarco_pairs_loss": 0.6067730188369751,
|
| 375 |
+
"eval_msmarco_pairs_runtime": 1.2272,
|
| 376 |
+
"eval_msmarco_pairs_samples_per_second": 122.233,
|
| 377 |
+
"eval_msmarco_pairs_steps_per_second": 1.63,
|
| 378 |
+
"step": 358
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.1,
|
| 382 |
+
"eval_nq_pairs_loss": 0.5683658123016357,
|
| 383 |
+
"eval_nq_pairs_runtime": 2.3358,
|
| 384 |
+
"eval_nq_pairs_samples_per_second": 64.219,
|
| 385 |
+
"eval_nq_pairs_steps_per_second": 0.856,
|
| 386 |
+
"step": 358
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.1,
|
| 390 |
+
"eval_trivia_pairs_loss": 1.1103042364120483,
|
| 391 |
+
"eval_trivia_pairs_runtime": 3.2191,
|
| 392 |
+
"eval_trivia_pairs_samples_per_second": 46.596,
|
| 393 |
+
"eval_trivia_pairs_steps_per_second": 0.621,
|
| 394 |
+
"step": 358
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1,
|
| 398 |
+
"eval_quora_pairs_loss": 0.2291153520345688,
|
| 399 |
+
"eval_quora_pairs_runtime": 0.39,
|
| 400 |
+
"eval_quora_pairs_samples_per_second": 384.605,
|
| 401 |
+
"eval_quora_pairs_steps_per_second": 5.128,
|
| 402 |
+
"step": 358
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.1,
|
| 406 |
+
"eval_gooaq_pairs_loss": 0.5594914555549622,
|
| 407 |
+
"eval_gooaq_pairs_runtime": 0.814,
|
| 408 |
+
"eval_gooaq_pairs_samples_per_second": 184.276,
|
| 409 |
+
"eval_gooaq_pairs_steps_per_second": 2.457,
|
| 410 |
+
"step": 358
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.1,
|
| 414 |
+
"eval_mrpc_pairs_loss": 0.056830935180187225,
|
| 415 |
+
"eval_mrpc_pairs_runtime": 0.1099,
|
| 416 |
+
"eval_mrpc_pairs_samples_per_second": 1364.673,
|
| 417 |
+
"eval_mrpc_pairs_steps_per_second": 18.196,
|
| 418 |
+
"step": 358
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1005586592178771,
|
| 422 |
+
"grad_norm": 0.40709275007247925,
|
| 423 |
+
"learning_rate": 1.3370577281191808e-05,
|
| 424 |
+
"loss": 0.7904,
|
| 425 |
+
"step": 360
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.10558659217877095,
|
| 429 |
+
"grad_norm": 8.056321144104004,
|
| 430 |
+
"learning_rate": 1.4040968342644321e-05,
|
| 431 |
+
"loss": 1.2543,
|
| 432 |
+
"step": 378
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.1106145251396648,
|
| 436 |
+
"grad_norm": 6.643378257751465,
|
| 437 |
+
"learning_rate": 1.4711359404096834e-05,
|
| 438 |
+
"loss": 0.854,
|
| 439 |
+
"step": 396
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.11564245810055866,
|
| 443 |
+
"grad_norm": 7.473087310791016,
|
| 444 |
+
"learning_rate": 1.538175046554935e-05,
|
| 445 |
+
"loss": 0.4719,
|
| 446 |
+
"step": 414
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.12067039106145251,
|
| 450 |
+
"grad_norm": 8.68940258026123,
|
| 451 |
+
"learning_rate": 1.6052141527001864e-05,
|
| 452 |
+
"loss": 1.4229,
|
| 453 |
+
"step": 432
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.12569832402234637,
|
| 457 |
+
"grad_norm": 8.564693450927734,
|
| 458 |
+
"learning_rate": 1.6722532588454377e-05,
|
| 459 |
+
"loss": 0.7646,
|
| 460 |
+
"step": 450
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.13072625698324022,
|
| 464 |
+
"grad_norm": 0.39765194058418274,
|
| 465 |
+
"learning_rate": 1.7392923649906893e-05,
|
| 466 |
+
"loss": 0.8512,
|
| 467 |
+
"step": 468
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.13575418994413407,
|
| 471 |
+
"grad_norm": 7.3941192626953125,
|
| 472 |
+
"learning_rate": 1.8063314711359406e-05,
|
| 473 |
+
"loss": 1.1333,
|
| 474 |
+
"step": 486
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.14078212290502792,
|
| 478 |
+
"grad_norm": 3.183729410171509,
|
| 479 |
+
"learning_rate": 1.873370577281192e-05,
|
| 480 |
+
"loss": 0.4451,
|
| 481 |
+
"step": 504
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.1458100558659218,
|
| 485 |
+
"grad_norm": 1.2496144771575928,
|
| 486 |
+
"learning_rate": 1.9404096834264436e-05,
|
| 487 |
+
"loss": 0.8859,
|
| 488 |
+
"step": 522
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.15,
|
| 492 |
+
"eval_nli-pairs_loss": 0.9459429979324341,
|
| 493 |
+
"eval_nli-pairs_runtime": 3.418,
|
| 494 |
+
"eval_nli-pairs_samples_per_second": 43.886,
|
| 495 |
+
"eval_nli-pairs_steps_per_second": 0.585,
|
| 496 |
+
"eval_sts-test_pearson_cosine": 0.7949855875446147,
|
| 497 |
+
"eval_sts-test_pearson_dot": 0.5640384325880634,
|
| 498 |
+
"eval_sts-test_pearson_euclidean": 0.751389277231376,
|
| 499 |
+
"eval_sts-test_pearson_manhattan": 0.7487497192657817,
|
| 500 |
+
"eval_sts-test_pearson_max": 0.7949855875446147,
|
| 501 |
+
"eval_sts-test_spearman_cosine": 0.8064088099185094,
|
| 502 |
+
"eval_sts-test_spearman_dot": 0.5419498621910633,
|
| 503 |
+
"eval_sts-test_spearman_euclidean": 0.7411803691316964,
|
| 504 |
+
"eval_sts-test_spearman_manhattan": 0.7408925147897409,
|
| 505 |
+
"eval_sts-test_spearman_max": 0.8064088099185094,
|
| 506 |
+
"step": 537
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.15,
|
| 510 |
+
"eval_vitaminc-pairs_loss": 4.557371139526367,
|
| 511 |
+
"eval_vitaminc-pairs_runtime": 0.8813,
|
| 512 |
+
"eval_vitaminc-pairs_samples_per_second": 141.843,
|
| 513 |
+
"eval_vitaminc-pairs_steps_per_second": 2.269,
|
| 514 |
+
"step": 537
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.15,
|
| 518 |
+
"eval_qnli-contrastive_loss": 0.2963089942932129,
|
| 519 |
+
"eval_qnli-contrastive_runtime": 0.1173,
|
| 520 |
+
"eval_qnli-contrastive_samples_per_second": 1279.24,
|
| 521 |
+
"eval_qnli-contrastive_steps_per_second": 17.057,
|
| 522 |
+
"step": 537
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.15,
|
| 526 |
+
"eval_scitail-pairs-qa_loss": 0.06569412350654602,
|
| 527 |
+
"eval_scitail-pairs-qa_runtime": 0.6754,
|
| 528 |
+
"eval_scitail-pairs-qa_samples_per_second": 222.091,
|
| 529 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.961,
|
| 530 |
+
"step": 537
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.15,
|
| 534 |
+
"eval_scitail-pairs-pos_loss": 0.3104495108127594,
|
| 535 |
+
"eval_scitail-pairs-pos_runtime": 1.7852,
|
| 536 |
+
"eval_scitail-pairs-pos_samples_per_second": 84.022,
|
| 537 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.12,
|
| 538 |
+
"step": 537
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.15,
|
| 542 |
+
"eval_xsum-pairs_loss": 0.44305890798568726,
|
| 543 |
+
"eval_xsum-pairs_runtime": 0.1668,
|
| 544 |
+
"eval_xsum-pairs_samples_per_second": 491.658,
|
| 545 |
+
"eval_xsum-pairs_steps_per_second": 5.996,
|
| 546 |
+
"step": 537
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.15,
|
| 550 |
+
"eval_compression-pairs_loss": 0.10611961036920547,
|
| 551 |
+
"eval_compression-pairs_runtime": 0.1033,
|
| 552 |
+
"eval_compression-pairs_samples_per_second": 1451.474,
|
| 553 |
+
"eval_compression-pairs_steps_per_second": 19.353,
|
| 554 |
+
"step": 537
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.15,
|
| 558 |
+
"eval_sciq_pairs_loss": 0.15942400693893433,
|
| 559 |
+
"eval_sciq_pairs_runtime": 4.8457,
|
| 560 |
+
"eval_sciq_pairs_samples_per_second": 30.955,
|
| 561 |
+
"eval_sciq_pairs_steps_per_second": 0.413,
|
| 562 |
+
"step": 537
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.15,
|
| 566 |
+
"eval_qasc_pairs_loss": 0.2380143702030182,
|
| 567 |
+
"eval_qasc_pairs_runtime": 0.6528,
|
| 568 |
+
"eval_qasc_pairs_samples_per_second": 229.78,
|
| 569 |
+
"eval_qasc_pairs_steps_per_second": 3.064,
|
| 570 |
+
"step": 537
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.15,
|
| 574 |
+
"eval_openbookqa_pairs_loss": 1.556572437286377,
|
| 575 |
+
"eval_openbookqa_pairs_runtime": 0.6905,
|
| 576 |
+
"eval_openbookqa_pairs_samples_per_second": 217.246,
|
| 577 |
+
"eval_openbookqa_pairs_steps_per_second": 2.897,
|
| 578 |
+
"step": 537
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.15,
|
| 582 |
+
"eval_msmarco_pairs_loss": 0.5950079560279846,
|
| 583 |
+
"eval_msmarco_pairs_runtime": 1.1541,
|
| 584 |
+
"eval_msmarco_pairs_samples_per_second": 129.968,
|
| 585 |
+
"eval_msmarco_pairs_steps_per_second": 1.733,
|
| 586 |
+
"step": 537
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.15,
|
| 590 |
+
"eval_nq_pairs_loss": 0.5976797938346863,
|
| 591 |
+
"eval_nq_pairs_runtime": 2.2683,
|
| 592 |
+
"eval_nq_pairs_samples_per_second": 66.128,
|
| 593 |
+
"eval_nq_pairs_steps_per_second": 0.882,
|
| 594 |
+
"step": 537
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.15,
|
| 598 |
+
"eval_trivia_pairs_loss": 1.1377041339874268,
|
| 599 |
+
"eval_trivia_pairs_runtime": 3.1791,
|
| 600 |
+
"eval_trivia_pairs_samples_per_second": 47.183,
|
| 601 |
+
"eval_trivia_pairs_steps_per_second": 0.629,
|
| 602 |
+
"step": 537
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.15,
|
| 606 |
+
"eval_quora_pairs_loss": 0.20836791396141052,
|
| 607 |
+
"eval_quora_pairs_runtime": 0.374,
|
| 608 |
+
"eval_quora_pairs_samples_per_second": 401.115,
|
| 609 |
+
"eval_quora_pairs_steps_per_second": 5.348,
|
| 610 |
+
"step": 537
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.15,
|
| 614 |
+
"eval_gooaq_pairs_loss": 0.5545207262039185,
|
| 615 |
+
"eval_gooaq_pairs_runtime": 0.7667,
|
| 616 |
+
"eval_gooaq_pairs_samples_per_second": 195.642,
|
| 617 |
+
"eval_gooaq_pairs_steps_per_second": 2.609,
|
| 618 |
+
"step": 537
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.15,
|
| 622 |
+
"eval_mrpc_pairs_loss": 0.060290463268756866,
|
| 623 |
+
"eval_mrpc_pairs_runtime": 0.1026,
|
| 624 |
+
"eval_mrpc_pairs_samples_per_second": 1462.106,
|
| 625 |
+
"eval_mrpc_pairs_steps_per_second": 19.495,
|
| 626 |
+
"step": 537
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.15083798882681565,
|
| 630 |
+
"grad_norm": 1.3315377235412598,
|
| 631 |
+
"learning_rate": 1.9999898748390674e-05,
|
| 632 |
+
"loss": 0.9245,
|
| 633 |
+
"step": 540
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.1558659217877095,
|
| 637 |
+
"grad_norm": 8.015869140625,
|
| 638 |
+
"learning_rate": 1.9989876718445097e-05,
|
| 639 |
+
"loss": 1.0384,
|
| 640 |
+
"step": 558
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.16089385474860335,
|
| 644 |
+
"grad_norm": 1.3641886711120605,
|
| 645 |
+
"learning_rate": 1.9963472835306562e-05,
|
| 646 |
+
"loss": 0.8826,
|
| 647 |
+
"step": 576
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.1659217877094972,
|
| 651 |
+
"grad_norm": 7.676197528839111,
|
| 652 |
+
"learning_rate": 1.9920735213598995e-05,
|
| 653 |
+
"loss": 0.6693,
|
| 654 |
+
"step": 594
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.17094972067039105,
|
| 658 |
+
"grad_norm": 8.144271850585938,
|
| 659 |
+
"learning_rate": 1.9861741732192866e-05,
|
| 660 |
+
"loss": 0.8437,
|
| 661 |
+
"step": 612
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.17597765363128492,
|
| 665 |
+
"grad_norm": 11.723029136657715,
|
| 666 |
+
"learning_rate": 1.9786599892290035e-05,
|
| 667 |
+
"loss": 1.2241,
|
| 668 |
+
"step": 630
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.18100558659217877,
|
| 672 |
+
"grad_norm": 12.107389450073242,
|
| 673 |
+
"learning_rate": 1.9695446621529053e-05,
|
| 674 |
+
"loss": 0.7169,
|
| 675 |
+
"step": 648
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.18603351955307262,
|
| 679 |
+
"grad_norm": 0.671999454498291,
|
| 680 |
+
"learning_rate": 1.9588448024468015e-05,
|
| 681 |
+
"loss": 0.7937,
|
| 682 |
+
"step": 666
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.19106145251396647,
|
| 686 |
+
"grad_norm": 2.9247829914093018,
|
| 687 |
+
"learning_rate": 1.9465799079899608e-05,
|
| 688 |
+
"loss": 0.8666,
|
| 689 |
+
"step": 684
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.19608938547486032,
|
| 693 |
+
"grad_norm": 9.634854316711426,
|
| 694 |
+
"learning_rate": 1.932772328554989e-05,
|
| 695 |
+
"loss": 0.8002,
|
| 696 |
+
"step": 702
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.2,
|
| 700 |
+
"eval_nli-pairs_loss": 0.9524073004722595,
|
| 701 |
+
"eval_nli-pairs_runtime": 3.3652,
|
| 702 |
+
"eval_nli-pairs_samples_per_second": 44.573,
|
| 703 |
+
"eval_nli-pairs_steps_per_second": 0.594,
|
| 704 |
+
"eval_sts-test_pearson_cosine": 0.7960974627777679,
|
| 705 |
+
"eval_sts-test_pearson_dot": 0.5653927619143873,
|
| 706 |
+
"eval_sts-test_pearson_euclidean": 0.7510324476182012,
|
| 707 |
+
"eval_sts-test_pearson_manhattan": 0.7478581635465753,
|
| 708 |
+
"eval_sts-test_pearson_max": 0.7960974627777679,
|
| 709 |
+
"eval_sts-test_spearman_cosine": 0.8076217698074869,
|
| 710 |
+
"eval_sts-test_spearman_dot": 0.5437275169754562,
|
| 711 |
+
"eval_sts-test_spearman_euclidean": 0.7394612354069316,
|
| 712 |
+
"eval_sts-test_spearman_manhattan": 0.7383580125266631,
|
| 713 |
+
"eval_sts-test_spearman_max": 0.8076217698074869,
|
| 714 |
+
"step": 716
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.2,
|
| 718 |
+
"eval_vitaminc-pairs_loss": 4.544824600219727,
|
| 719 |
+
"eval_vitaminc-pairs_runtime": 0.8209,
|
| 720 |
+
"eval_vitaminc-pairs_samples_per_second": 152.27,
|
| 721 |
+
"eval_vitaminc-pairs_steps_per_second": 2.436,
|
| 722 |
+
"step": 716
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.2,
|
| 726 |
+
"eval_qnli-contrastive_loss": 0.2854141891002655,
|
| 727 |
+
"eval_qnli-contrastive_runtime": 0.116,
|
| 728 |
+
"eval_qnli-contrastive_samples_per_second": 1293.335,
|
| 729 |
+
"eval_qnli-contrastive_steps_per_second": 17.244,
|
| 730 |
+
"step": 716
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2,
|
| 734 |
+
"eval_scitail-pairs-qa_loss": 0.06479831039905548,
|
| 735 |
+
"eval_scitail-pairs-qa_runtime": 0.6668,
|
| 736 |
+
"eval_scitail-pairs-qa_samples_per_second": 224.963,
|
| 737 |
+
"eval_scitail-pairs-qa_steps_per_second": 3.0,
|
| 738 |
+
"step": 716
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.2,
|
| 742 |
+
"eval_scitail-pairs-pos_loss": 0.30356064438819885,
|
| 743 |
+
"eval_scitail-pairs-pos_runtime": 1.7895,
|
| 744 |
+
"eval_scitail-pairs-pos_samples_per_second": 83.823,
|
| 745 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.118,
|
| 746 |
+
"step": 716
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.2,
|
| 750 |
+
"eval_xsum-pairs_loss": 0.4510384202003479,
|
| 751 |
+
"eval_xsum-pairs_runtime": 0.1513,
|
| 752 |
+
"eval_xsum-pairs_samples_per_second": 541.869,
|
| 753 |
+
"eval_xsum-pairs_steps_per_second": 6.608,
|
| 754 |
+
"step": 716
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.2,
|
| 758 |
+
"eval_compression-pairs_loss": 0.10218393057584763,
|
| 759 |
+
"eval_compression-pairs_runtime": 0.1063,
|
| 760 |
+
"eval_compression-pairs_samples_per_second": 1410.495,
|
| 761 |
+
"eval_compression-pairs_steps_per_second": 18.807,
|
| 762 |
+
"step": 716
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2,
|
| 766 |
+
"eval_sciq_pairs_loss": 0.16117030382156372,
|
| 767 |
+
"eval_sciq_pairs_runtime": 4.8842,
|
| 768 |
+
"eval_sciq_pairs_samples_per_second": 30.711,
|
| 769 |
+
"eval_sciq_pairs_steps_per_second": 0.409,
|
| 770 |
+
"step": 716
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.2,
|
| 774 |
+
"eval_qasc_pairs_loss": 0.25312450528144836,
|
| 775 |
+
"eval_qasc_pairs_runtime": 0.626,
|
| 776 |
+
"eval_qasc_pairs_samples_per_second": 239.619,
|
| 777 |
+
"eval_qasc_pairs_steps_per_second": 3.195,
|
| 778 |
+
"step": 716
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.2,
|
| 782 |
+
"eval_openbookqa_pairs_loss": 1.560429573059082,
|
| 783 |
+
"eval_openbookqa_pairs_runtime": 0.6856,
|
| 784 |
+
"eval_openbookqa_pairs_samples_per_second": 218.787,
|
| 785 |
+
"eval_openbookqa_pairs_steps_per_second": 2.917,
|
| 786 |
+
"step": 716
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2,
|
| 790 |
+
"eval_msmarco_pairs_loss": 0.6264744997024536,
|
| 791 |
+
"eval_msmarco_pairs_runtime": 1.1496,
|
| 792 |
+
"eval_msmarco_pairs_samples_per_second": 130.479,
|
| 793 |
+
"eval_msmarco_pairs_steps_per_second": 1.74,
|
| 794 |
+
"step": 716
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2,
|
| 798 |
+
"eval_nq_pairs_loss": 0.602968692779541,
|
| 799 |
+
"eval_nq_pairs_runtime": 2.2714,
|
| 800 |
+
"eval_nq_pairs_samples_per_second": 66.038,
|
| 801 |
+
"eval_nq_pairs_steps_per_second": 0.881,
|
| 802 |
+
"step": 716
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.2,
|
| 806 |
+
"eval_trivia_pairs_loss": 1.1763343811035156,
|
| 807 |
+
"eval_trivia_pairs_runtime": 3.1779,
|
| 808 |
+
"eval_trivia_pairs_samples_per_second": 47.201,
|
| 809 |
+
"eval_trivia_pairs_steps_per_second": 0.629,
|
| 810 |
+
"step": 716
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.2,
|
| 814 |
+
"eval_quora_pairs_loss": 0.25559327006340027,
|
| 815 |
+
"eval_quora_pairs_runtime": 0.3926,
|
| 816 |
+
"eval_quora_pairs_samples_per_second": 382.056,
|
| 817 |
+
"eval_quora_pairs_steps_per_second": 5.094,
|
| 818 |
+
"step": 716
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.2,
|
| 822 |
+
"eval_gooaq_pairs_loss": 0.5762031078338623,
|
| 823 |
+
"eval_gooaq_pairs_runtime": 0.7962,
|
| 824 |
+
"eval_gooaq_pairs_samples_per_second": 188.399,
|
| 825 |
+
"eval_gooaq_pairs_steps_per_second": 2.512,
|
| 826 |
+
"step": 716
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.2,
|
| 830 |
+
"eval_mrpc_pairs_loss": 0.05901935696601868,
|
| 831 |
+
"eval_mrpc_pairs_runtime": 0.1022,
|
| 832 |
+
"eval_mrpc_pairs_samples_per_second": 1467.265,
|
| 833 |
+
"eval_mrpc_pairs_steps_per_second": 19.564,
|
| 834 |
+
"step": 716
|
| 835 |
+
}
|
| 836 |
+
],
|
| 837 |
+
"logging_steps": 18,
|
| 838 |
+
"max_steps": 7160,
|
| 839 |
+
"num_input_tokens_seen": 0,
|
| 840 |
+
"num_train_epochs": 2,
|
| 841 |
+
"save_steps": 716,
|
| 842 |
+
"stateful_callbacks": {
|
| 843 |
+
"TrainerControl": {
|
| 844 |
+
"args": {
|
| 845 |
+
"should_epoch_stop": false,
|
| 846 |
+
"should_evaluate": false,
|
| 847 |
+
"should_log": false,
|
| 848 |
+
"should_save": true,
|
| 849 |
+
"should_training_stop": false
|
| 850 |
+
},
|
| 851 |
+
"attributes": {}
|
| 852 |
+
}
|
| 853 |
+
},
|
| 854 |
+
"total_flos": 0.0,
|
| 855 |
+
"train_batch_size": 82,
|
| 856 |
+
"trial_name": null,
|
| 857 |
+
"trial_params": null
|
| 858 |
+
}
|
checkpoint-716/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5ad0ebae5d54ccad20b596d9ef597aaa6d8c8f398f1064eecf9dd488a2646a3
|
| 3 |
+
size 5688
|