Upload 10 files
Browse files- .gitattributes +1 -0
- config.json +33 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +57 -0
- trainer_state.json +734 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4096,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-05,
|
| 21 |
+
"max_position_embeddings": 8194,
|
| 22 |
+
"model_type": "xlm-roberta",
|
| 23 |
+
"num_attention_heads": 16,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.54.0",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 250002
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40576216be508b60a07f78be41168b70e5fa9b2b3468a1e5e0b2678b07632f7c
|
| 3 |
+
size 2271071852
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6635b999b9b2d9d9174e91167e1e81c4a1aaf5d072405c9af8fa4f093715373
|
| 3 |
+
size 4542376393
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d786454ce1e7e7869f5655206348d395d5a6eb0fd681a671734ab85f58b0569d
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a95b7af946de7e74370f93554fb888fdac796ea31906357beeb4ab42a9f2cc4
|
| 3 |
+
size 1000
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 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": "</s>",
|
| 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": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bf8afbfd11306bd872018c53bfdf2e160a56f8edbcf49933324404791c148d3
|
| 3 |
+
size 17082900
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 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": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 8192,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"return_tensors": false,
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,734 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1359452956130453,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0013594529561304532,
|
| 14 |
+
"grad_norm": 2.6843507289886475,
|
| 15 |
+
"learning_rate": 2.9959624247202926e-05,
|
| 16 |
+
"loss": 0.791,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0027189059122609063,
|
| 21 |
+
"grad_norm": 7.921170711517334,
|
| 22 |
+
"learning_rate": 2.9918840658519014e-05,
|
| 23 |
+
"loss": 0.7116,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0040783588683913595,
|
| 28 |
+
"grad_norm": 1.703231692314148,
|
| 29 |
+
"learning_rate": 2.98780570698351e-05,
|
| 30 |
+
"loss": 0.7025,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.005437811824521813,
|
| 35 |
+
"grad_norm": 1.4689126014709473,
|
| 36 |
+
"learning_rate": 2.9837273481151187e-05,
|
| 37 |
+
"loss": 0.7026,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.006797264780652266,
|
| 42 |
+
"grad_norm": 6.632850646972656,
|
| 43 |
+
"learning_rate": 2.979648989246727e-05,
|
| 44 |
+
"loss": 0.7006,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.008156717736782719,
|
| 49 |
+
"grad_norm": 1.7937493324279785,
|
| 50 |
+
"learning_rate": 2.975570630378336e-05,
|
| 51 |
+
"loss": 0.6996,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.009516170692913172,
|
| 56 |
+
"grad_norm": 1.545050024986267,
|
| 57 |
+
"learning_rate": 2.9714922715099447e-05,
|
| 58 |
+
"loss": 0.6988,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.010875623649043625,
|
| 63 |
+
"grad_norm": 6.718420505523682,
|
| 64 |
+
"learning_rate": 2.967413912641553e-05,
|
| 65 |
+
"loss": 0.6934,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.012235076605174078,
|
| 70 |
+
"grad_norm": 2.417815923690796,
|
| 71 |
+
"learning_rate": 2.9633355537731616e-05,
|
| 72 |
+
"loss": 0.7031,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.013594529561304532,
|
| 77 |
+
"grad_norm": 3.016540765762329,
|
| 78 |
+
"learning_rate": 2.9592571949047704e-05,
|
| 79 |
+
"loss": 0.7003,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.014953982517434985,
|
| 84 |
+
"grad_norm": 1.3102728128433228,
|
| 85 |
+
"learning_rate": 2.9551788360363792e-05,
|
| 86 |
+
"loss": 0.6939,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.016313435473565438,
|
| 91 |
+
"grad_norm": 3.511146306991577,
|
| 92 |
+
"learning_rate": 2.9511004771679877e-05,
|
| 93 |
+
"loss": 0.7018,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.01767288842969589,
|
| 98 |
+
"grad_norm": 2.3049850463867188,
|
| 99 |
+
"learning_rate": 2.9470221182995965e-05,
|
| 100 |
+
"loss": 0.7093,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.019032341385826344,
|
| 105 |
+
"grad_norm": 1.0154485702514648,
|
| 106 |
+
"learning_rate": 2.942943759431205e-05,
|
| 107 |
+
"loss": 0.7035,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.020391794341956797,
|
| 112 |
+
"grad_norm": 2.085158348083496,
|
| 113 |
+
"learning_rate": 2.9388654005628134e-05,
|
| 114 |
+
"loss": 0.7015,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.02175124729808725,
|
| 119 |
+
"grad_norm": 3.9277114868164062,
|
| 120 |
+
"learning_rate": 2.9347870416944225e-05,
|
| 121 |
+
"loss": 0.6994,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.023110700254217704,
|
| 126 |
+
"grad_norm": 1.8050942420959473,
|
| 127 |
+
"learning_rate": 2.930708682826031e-05,
|
| 128 |
+
"loss": 0.7027,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.024470153210348157,
|
| 133 |
+
"grad_norm": 1.5299062728881836,
|
| 134 |
+
"learning_rate": 2.9266303239576394e-05,
|
| 135 |
+
"loss": 0.6989,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.02582960616647861,
|
| 140 |
+
"grad_norm": 3.9614956378936768,
|
| 141 |
+
"learning_rate": 2.9225519650892482e-05,
|
| 142 |
+
"loss": 0.6968,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.027189059122609063,
|
| 147 |
+
"grad_norm": 1.5142548084259033,
|
| 148 |
+
"learning_rate": 2.9184736062208567e-05,
|
| 149 |
+
"loss": 0.6996,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.028548512078739516,
|
| 154 |
+
"grad_norm": 2.0255579948425293,
|
| 155 |
+
"learning_rate": 2.9143952473524655e-05,
|
| 156 |
+
"loss": 0.6992,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.02990796503486997,
|
| 161 |
+
"grad_norm": 3.3495869636535645,
|
| 162 |
+
"learning_rate": 2.9103168884840743e-05,
|
| 163 |
+
"loss": 0.6986,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.03126741799100042,
|
| 168 |
+
"grad_norm": 4.41119909286499,
|
| 169 |
+
"learning_rate": 2.9062385296156827e-05,
|
| 170 |
+
"loss": 0.6963,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.032626870947130876,
|
| 175 |
+
"grad_norm": 2.923621416091919,
|
| 176 |
+
"learning_rate": 2.902160170747291e-05,
|
| 177 |
+
"loss": 0.6935,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.033986323903261326,
|
| 182 |
+
"grad_norm": 6.4013285636901855,
|
| 183 |
+
"learning_rate": 2.8980818118789e-05,
|
| 184 |
+
"loss": 0.6984,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.03534577685939178,
|
| 189 |
+
"grad_norm": 2.191399097442627,
|
| 190 |
+
"learning_rate": 2.8940034530105088e-05,
|
| 191 |
+
"loss": 0.6955,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.03670522981552223,
|
| 196 |
+
"grad_norm": 1.6993489265441895,
|
| 197 |
+
"learning_rate": 2.8899250941421172e-05,
|
| 198 |
+
"loss": 0.7002,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.03806468277165269,
|
| 203 |
+
"grad_norm": 3.364286184310913,
|
| 204 |
+
"learning_rate": 2.885846735273726e-05,
|
| 205 |
+
"loss": 0.6964,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03942413572778314,
|
| 210 |
+
"grad_norm": 1.9982099533081055,
|
| 211 |
+
"learning_rate": 2.8817683764053345e-05,
|
| 212 |
+
"loss": 0.7069,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.040783588683913595,
|
| 217 |
+
"grad_norm": 1.524899959564209,
|
| 218 |
+
"learning_rate": 2.877690017536943e-05,
|
| 219 |
+
"loss": 0.6961,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.042143041640044045,
|
| 224 |
+
"grad_norm": 2.2762181758880615,
|
| 225 |
+
"learning_rate": 2.873611658668552e-05,
|
| 226 |
+
"loss": 0.6991,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0435024945961745,
|
| 231 |
+
"grad_norm": 2.0052831172943115,
|
| 232 |
+
"learning_rate": 2.8695332998001605e-05,
|
| 233 |
+
"loss": 0.6987,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.04486194755230495,
|
| 238 |
+
"grad_norm": 1.6109389066696167,
|
| 239 |
+
"learning_rate": 2.865454940931769e-05,
|
| 240 |
+
"loss": 0.6974,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.04622140050843541,
|
| 245 |
+
"grad_norm": 1.7458642721176147,
|
| 246 |
+
"learning_rate": 2.8613765820633778e-05,
|
| 247 |
+
"loss": 0.6984,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.04758085346456586,
|
| 252 |
+
"grad_norm": 5.7916083335876465,
|
| 253 |
+
"learning_rate": 2.8572982231949862e-05,
|
| 254 |
+
"loss": 0.6986,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.048940306420696314,
|
| 259 |
+
"grad_norm": 2.8352317810058594,
|
| 260 |
+
"learning_rate": 2.8532198643265954e-05,
|
| 261 |
+
"loss": 0.7004,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.050299759376826764,
|
| 266 |
+
"grad_norm": 6.102287769317627,
|
| 267 |
+
"learning_rate": 2.8491415054582038e-05,
|
| 268 |
+
"loss": 0.6975,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.05165921233295722,
|
| 273 |
+
"grad_norm": 2.8221065998077393,
|
| 274 |
+
"learning_rate": 2.8450631465898123e-05,
|
| 275 |
+
"loss": 0.7092,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.05301866528908767,
|
| 280 |
+
"grad_norm": 2.0802714824676514,
|
| 281 |
+
"learning_rate": 2.840984787721421e-05,
|
| 282 |
+
"loss": 0.7097,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.05437811824521813,
|
| 287 |
+
"grad_norm": 4.515227794647217,
|
| 288 |
+
"learning_rate": 2.8369064288530295e-05,
|
| 289 |
+
"loss": 0.6991,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.055737571201348576,
|
| 294 |
+
"grad_norm": 4.737243175506592,
|
| 295 |
+
"learning_rate": 2.8328280699846383e-05,
|
| 296 |
+
"loss": 0.7042,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.05709702415747903,
|
| 301 |
+
"grad_norm": 5.016382694244385,
|
| 302 |
+
"learning_rate": 2.828749711116247e-05,
|
| 303 |
+
"loss": 0.7008,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.05845647711360948,
|
| 308 |
+
"grad_norm": 2.7722420692443848,
|
| 309 |
+
"learning_rate": 2.8246713522478556e-05,
|
| 310 |
+
"loss": 0.7038,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05981593006973994,
|
| 315 |
+
"grad_norm": 3.596283435821533,
|
| 316 |
+
"learning_rate": 2.820592993379464e-05,
|
| 317 |
+
"loss": 0.7008,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.06117538302587039,
|
| 322 |
+
"grad_norm": 3.8389534950256348,
|
| 323 |
+
"learning_rate": 2.8165146345110728e-05,
|
| 324 |
+
"loss": 0.6986,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.06253483598200084,
|
| 329 |
+
"grad_norm": 2.992204189300537,
|
| 330 |
+
"learning_rate": 2.8124362756426816e-05,
|
| 331 |
+
"loss": 0.7027,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.0638942889381313,
|
| 336 |
+
"grad_norm": 1.4091521501541138,
|
| 337 |
+
"learning_rate": 2.80835791677429e-05,
|
| 338 |
+
"loss": 0.7032,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.06525374189426175,
|
| 343 |
+
"grad_norm": 1.7205729484558105,
|
| 344 |
+
"learning_rate": 2.804279557905899e-05,
|
| 345 |
+
"loss": 0.7061,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0666131948503922,
|
| 350 |
+
"grad_norm": 2.666346549987793,
|
| 351 |
+
"learning_rate": 2.8002011990375073e-05,
|
| 352 |
+
"loss": 0.7016,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.06797264780652265,
|
| 357 |
+
"grad_norm": 2.0234336853027344,
|
| 358 |
+
"learning_rate": 2.7961228401691158e-05,
|
| 359 |
+
"loss": 0.6986,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.06933210076265311,
|
| 364 |
+
"grad_norm": 1.3103491067886353,
|
| 365 |
+
"learning_rate": 2.792044481300725e-05,
|
| 366 |
+
"loss": 0.6995,
|
| 367 |
+
"step": 5100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.07069155371878356,
|
| 371 |
+
"grad_norm": 3.3153600692749023,
|
| 372 |
+
"learning_rate": 2.7879661224323334e-05,
|
| 373 |
+
"loss": 0.6968,
|
| 374 |
+
"step": 5200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.07205100667491401,
|
| 378 |
+
"grad_norm": 3.262269973754883,
|
| 379 |
+
"learning_rate": 2.7838877635639418e-05,
|
| 380 |
+
"loss": 0.7041,
|
| 381 |
+
"step": 5300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.07341045963104446,
|
| 385 |
+
"grad_norm": 5.839659214019775,
|
| 386 |
+
"learning_rate": 2.7798094046955506e-05,
|
| 387 |
+
"loss": 0.692,
|
| 388 |
+
"step": 5400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.07476991258717493,
|
| 392 |
+
"grad_norm": 6.034287929534912,
|
| 393 |
+
"learning_rate": 2.775731045827159e-05,
|
| 394 |
+
"loss": 0.7034,
|
| 395 |
+
"step": 5500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.07612936554330538,
|
| 399 |
+
"grad_norm": 3.7333922386169434,
|
| 400 |
+
"learning_rate": 2.771652686958768e-05,
|
| 401 |
+
"loss": 0.6986,
|
| 402 |
+
"step": 5600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.07748881849943583,
|
| 406 |
+
"grad_norm": 2.81872820854187,
|
| 407 |
+
"learning_rate": 2.7675743280903767e-05,
|
| 408 |
+
"loss": 0.7021,
|
| 409 |
+
"step": 5700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.07884827145556628,
|
| 413 |
+
"grad_norm": 2.6562986373901367,
|
| 414 |
+
"learning_rate": 2.763495969221985e-05,
|
| 415 |
+
"loss": 0.6999,
|
| 416 |
+
"step": 5800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.08020772441169673,
|
| 420 |
+
"grad_norm": 4.191847801208496,
|
| 421 |
+
"learning_rate": 2.7594176103535936e-05,
|
| 422 |
+
"loss": 0.704,
|
| 423 |
+
"step": 5900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.08156717736782719,
|
| 427 |
+
"grad_norm": 1.9238234758377075,
|
| 428 |
+
"learning_rate": 2.7553392514852024e-05,
|
| 429 |
+
"loss": 0.6996,
|
| 430 |
+
"step": 6000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.08292663032395764,
|
| 434 |
+
"grad_norm": 1.6448299884796143,
|
| 435 |
+
"learning_rate": 2.751260892616811e-05,
|
| 436 |
+
"loss": 0.7033,
|
| 437 |
+
"step": 6100
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.08428608328008809,
|
| 441 |
+
"grad_norm": 2.8520469665527344,
|
| 442 |
+
"learning_rate": 2.7471825337484196e-05,
|
| 443 |
+
"loss": 0.707,
|
| 444 |
+
"step": 6200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.08564553623621854,
|
| 448 |
+
"grad_norm": 4.698349952697754,
|
| 449 |
+
"learning_rate": 2.7431041748800284e-05,
|
| 450 |
+
"loss": 0.6995,
|
| 451 |
+
"step": 6300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.087004989192349,
|
| 455 |
+
"grad_norm": 3.2636826038360596,
|
| 456 |
+
"learning_rate": 2.739025816011637e-05,
|
| 457 |
+
"loss": 0.697,
|
| 458 |
+
"step": 6400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.08836444214847945,
|
| 462 |
+
"grad_norm": 5.062309741973877,
|
| 463 |
+
"learning_rate": 2.7349474571432457e-05,
|
| 464 |
+
"loss": 0.7068,
|
| 465 |
+
"step": 6500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.0897238951046099,
|
| 469 |
+
"grad_norm": 1.9477702379226685,
|
| 470 |
+
"learning_rate": 2.7308690982748545e-05,
|
| 471 |
+
"loss": 0.6946,
|
| 472 |
+
"step": 6600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.09108334806074035,
|
| 476 |
+
"grad_norm": 6.437952518463135,
|
| 477 |
+
"learning_rate": 2.726790739406463e-05,
|
| 478 |
+
"loss": 0.6968,
|
| 479 |
+
"step": 6700
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.09244280101687082,
|
| 483 |
+
"grad_norm": 1.488918423652649,
|
| 484 |
+
"learning_rate": 2.7227123805380717e-05,
|
| 485 |
+
"loss": 0.6964,
|
| 486 |
+
"step": 6800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.09380225397300126,
|
| 490 |
+
"grad_norm": 1.5171183347702026,
|
| 491 |
+
"learning_rate": 2.7186340216696802e-05,
|
| 492 |
+
"loss": 0.6948,
|
| 493 |
+
"step": 6900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.09516170692913171,
|
| 497 |
+
"grad_norm": 5.248293876647949,
|
| 498 |
+
"learning_rate": 2.7145556628012886e-05,
|
| 499 |
+
"loss": 0.6914,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.09652115988526216,
|
| 504 |
+
"grad_norm": 3.5038247108459473,
|
| 505 |
+
"learning_rate": 2.7104773039328978e-05,
|
| 506 |
+
"loss": 0.7016,
|
| 507 |
+
"step": 7100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.09788061284139263,
|
| 511 |
+
"grad_norm": 2.2439801692962646,
|
| 512 |
+
"learning_rate": 2.7063989450645062e-05,
|
| 513 |
+
"loss": 0.6976,
|
| 514 |
+
"step": 7200
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.09924006579752308,
|
| 518 |
+
"grad_norm": 5.262351036071777,
|
| 519 |
+
"learning_rate": 2.7023205861961147e-05,
|
| 520 |
+
"loss": 0.7015,
|
| 521 |
+
"step": 7300
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.10059951875365353,
|
| 525 |
+
"grad_norm": 2.734067916870117,
|
| 526 |
+
"learning_rate": 2.6982422273277235e-05,
|
| 527 |
+
"loss": 0.7012,
|
| 528 |
+
"step": 7400
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.10195897170978398,
|
| 532 |
+
"grad_norm": 7.341092586517334,
|
| 533 |
+
"learning_rate": 2.694163868459332e-05,
|
| 534 |
+
"loss": 0.6977,
|
| 535 |
+
"step": 7500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.10331842466591444,
|
| 539 |
+
"grad_norm": 2.047778367996216,
|
| 540 |
+
"learning_rate": 2.6900855095909407e-05,
|
| 541 |
+
"loss": 0.6934,
|
| 542 |
+
"step": 7600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.10467787762204489,
|
| 546 |
+
"grad_norm": 5.612318515777588,
|
| 547 |
+
"learning_rate": 2.6860071507225495e-05,
|
| 548 |
+
"loss": 0.696,
|
| 549 |
+
"step": 7700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.10603733057817534,
|
| 553 |
+
"grad_norm": 3.8864567279815674,
|
| 554 |
+
"learning_rate": 2.681928791854158e-05,
|
| 555 |
+
"loss": 0.6958,
|
| 556 |
+
"step": 7800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.10739678353430579,
|
| 560 |
+
"grad_norm": 2.456672191619873,
|
| 561 |
+
"learning_rate": 2.6778504329857664e-05,
|
| 562 |
+
"loss": 0.7014,
|
| 563 |
+
"step": 7900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.10875623649043625,
|
| 567 |
+
"grad_norm": 1.5562827587127686,
|
| 568 |
+
"learning_rate": 2.6737720741173752e-05,
|
| 569 |
+
"loss": 0.7,
|
| 570 |
+
"step": 8000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.1101156894465667,
|
| 574 |
+
"grad_norm": 1.646262764930725,
|
| 575 |
+
"learning_rate": 2.669693715248984e-05,
|
| 576 |
+
"loss": 0.7028,
|
| 577 |
+
"step": 8100
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.11147514240269715,
|
| 581 |
+
"grad_norm": 2.5881056785583496,
|
| 582 |
+
"learning_rate": 2.6656153563805925e-05,
|
| 583 |
+
"loss": 0.697,
|
| 584 |
+
"step": 8200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.1128345953588276,
|
| 588 |
+
"grad_norm": 3.108797788619995,
|
| 589 |
+
"learning_rate": 2.6615369975122013e-05,
|
| 590 |
+
"loss": 0.7,
|
| 591 |
+
"step": 8300
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.11419404831495807,
|
| 595 |
+
"grad_norm": 1.5215388536453247,
|
| 596 |
+
"learning_rate": 2.6574586386438097e-05,
|
| 597 |
+
"loss": 0.6956,
|
| 598 |
+
"step": 8400
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.11555350127108852,
|
| 602 |
+
"grad_norm": 1.2557023763656616,
|
| 603 |
+
"learning_rate": 2.6533802797754182e-05,
|
| 604 |
+
"loss": 0.7032,
|
| 605 |
+
"step": 8500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.11691295422721897,
|
| 609 |
+
"grad_norm": 3.6592652797698975,
|
| 610 |
+
"learning_rate": 2.6493019209070273e-05,
|
| 611 |
+
"loss": 0.6957,
|
| 612 |
+
"step": 8600
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.11827240718334942,
|
| 616 |
+
"grad_norm": 1.6143642663955688,
|
| 617 |
+
"learning_rate": 2.6452235620386358e-05,
|
| 618 |
+
"loss": 0.6961,
|
| 619 |
+
"step": 8700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.11963186013947988,
|
| 623 |
+
"grad_norm": 1.7212355136871338,
|
| 624 |
+
"learning_rate": 2.6411452031702442e-05,
|
| 625 |
+
"loss": 0.7041,
|
| 626 |
+
"step": 8800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.12099131309561033,
|
| 630 |
+
"grad_norm": 1.2407207489013672,
|
| 631 |
+
"learning_rate": 2.637066844301853e-05,
|
| 632 |
+
"loss": 0.6938,
|
| 633 |
+
"step": 8900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.12235076605174078,
|
| 637 |
+
"grad_norm": 4.306702613830566,
|
| 638 |
+
"learning_rate": 2.6329884854334615e-05,
|
| 639 |
+
"loss": 0.704,
|
| 640 |
+
"step": 9000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.12371021900787123,
|
| 644 |
+
"grad_norm": 4.0667219161987305,
|
| 645 |
+
"learning_rate": 2.6289101265650703e-05,
|
| 646 |
+
"loss": 0.6966,
|
| 647 |
+
"step": 9100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.12506967196400168,
|
| 651 |
+
"grad_norm": 2.244699478149414,
|
| 652 |
+
"learning_rate": 2.624831767696679e-05,
|
| 653 |
+
"loss": 0.6976,
|
| 654 |
+
"step": 9200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.12642912492013214,
|
| 658 |
+
"grad_norm": 4.839937210083008,
|
| 659 |
+
"learning_rate": 2.6207534088282875e-05,
|
| 660 |
+
"loss": 0.6972,
|
| 661 |
+
"step": 9300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.1277885778762626,
|
| 665 |
+
"grad_norm": 5.436954021453857,
|
| 666 |
+
"learning_rate": 2.6166750499598963e-05,
|
| 667 |
+
"loss": 0.698,
|
| 668 |
+
"step": 9400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.12914803083239304,
|
| 672 |
+
"grad_norm": 5.324636459350586,
|
| 673 |
+
"learning_rate": 2.6125966910915048e-05,
|
| 674 |
+
"loss": 0.699,
|
| 675 |
+
"step": 9500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.1305074837885235,
|
| 679 |
+
"grad_norm": 2.4143927097320557,
|
| 680 |
+
"learning_rate": 2.6085183322231136e-05,
|
| 681 |
+
"loss": 0.7033,
|
| 682 |
+
"step": 9600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.13186693674465394,
|
| 686 |
+
"grad_norm": 3.336245059967041,
|
| 687 |
+
"learning_rate": 2.6044399733547224e-05,
|
| 688 |
+
"loss": 0.6993,
|
| 689 |
+
"step": 9700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.1332263897007844,
|
| 693 |
+
"grad_norm": 1.2645655870437622,
|
| 694 |
+
"learning_rate": 2.600361614486331e-05,
|
| 695 |
+
"loss": 0.6977,
|
| 696 |
+
"step": 9800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.13458584265691487,
|
| 700 |
+
"grad_norm": 3.2803938388824463,
|
| 701 |
+
"learning_rate": 2.5962832556179393e-05,
|
| 702 |
+
"loss": 0.6993,
|
| 703 |
+
"step": 9900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.1359452956130453,
|
| 707 |
+
"grad_norm": 2.2295751571655273,
|
| 708 |
+
"learning_rate": 2.592204896749548e-05,
|
| 709 |
+
"loss": 0.6923,
|
| 710 |
+
"step": 10000
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"logging_steps": 100,
|
| 714 |
+
"max_steps": 73559,
|
| 715 |
+
"num_input_tokens_seen": 0,
|
| 716 |
+
"num_train_epochs": 1,
|
| 717 |
+
"save_steps": 10000,
|
| 718 |
+
"stateful_callbacks": {
|
| 719 |
+
"TrainerControl": {
|
| 720 |
+
"args": {
|
| 721 |
+
"should_epoch_stop": false,
|
| 722 |
+
"should_evaluate": false,
|
| 723 |
+
"should_log": false,
|
| 724 |
+
"should_save": true,
|
| 725 |
+
"should_training_stop": false
|
| 726 |
+
},
|
| 727 |
+
"attributes": {}
|
| 728 |
+
}
|
| 729 |
+
},
|
| 730 |
+
"total_flos": 0.0,
|
| 731 |
+
"train_batch_size": 8,
|
| 732 |
+
"trial_name": null,
|
| 733 |
+
"trial_params": null
|
| 734 |
+
}
|