adds checkpoint files
Browse files- .gitattributes +1 -0
- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
- trainer_state.json +1089 -0
- training_args.bin +3 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.46.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 250002
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee5883c1057f621c91800a5bc690324bc0c08f09bedfd536bce34ece8588ab9
|
| 3 |
+
size 1113205088
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929e56bc25a1c8e4009fb8446da422a4ea133e11209338a74bfeb90c1ab5a101
|
| 3 |
+
size 2226529989
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5903fb1f635e8e626a9891ed34ac9098f51a92e7475d80635a1fe68c6872addb
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f501d5e1260553195a353332eba22c973f062dfae3f61cb0ab81af200e3a5a52
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
| 3 |
+
size 17082999
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 53 |
+
"unk_token": "<unk>"
|
| 54 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1089 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3431232091690544,
|
| 5 |
+
"eval_steps": 2500,
|
| 6 |
+
"global_step": 60000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01119269340974212,
|
| 13 |
+
"grad_norm": 2.299727201461792,
|
| 14 |
+
"learning_rate": 4.981345510983763e-05,
|
| 15 |
+
"loss": 1.8848,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02238538681948424,
|
| 20 |
+
"grad_norm": 1.9952893257141113,
|
| 21 |
+
"learning_rate": 4.962691021967526e-05,
|
| 22 |
+
"loss": 1.7595,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03357808022922636,
|
| 27 |
+
"grad_norm": 2.1056811809539795,
|
| 28 |
+
"learning_rate": 4.944036532951289e-05,
|
| 29 |
+
"loss": 1.6994,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04477077363896848,
|
| 34 |
+
"grad_norm": 2.0474352836608887,
|
| 35 |
+
"learning_rate": 4.925382043935053e-05,
|
| 36 |
+
"loss": 1.6629,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0559634670487106,
|
| 41 |
+
"grad_norm": 1.9989269971847534,
|
| 42 |
+
"learning_rate": 4.906727554918816e-05,
|
| 43 |
+
"loss": 1.6236,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0559634670487106,
|
| 48 |
+
"eval_accuracy": 0.5569847646608951,
|
| 49 |
+
"eval_loss": 2.425182342529297,
|
| 50 |
+
"eval_runtime": 707.8445,
|
| 51 |
+
"eval_samples_per_second": 91.796,
|
| 52 |
+
"eval_steps_per_second": 3.826,
|
| 53 |
+
"step": 2500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.06715616045845273,
|
| 57 |
+
"grad_norm": 1.879557490348816,
|
| 58 |
+
"learning_rate": 4.888073065902579e-05,
|
| 59 |
+
"loss": 1.5991,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.07834885386819485,
|
| 64 |
+
"grad_norm": 1.9889895915985107,
|
| 65 |
+
"learning_rate": 4.869418576886342e-05,
|
| 66 |
+
"loss": 1.5751,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.08954154727793696,
|
| 71 |
+
"grad_norm": 1.910925269126892,
|
| 72 |
+
"learning_rate": 4.8507640878701055e-05,
|
| 73 |
+
"loss": 1.5587,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.10073424068767908,
|
| 78 |
+
"grad_norm": 1.9268312454223633,
|
| 79 |
+
"learning_rate": 4.8321095988538685e-05,
|
| 80 |
+
"loss": 1.546,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.1119269340974212,
|
| 85 |
+
"grad_norm": 1.8074718713760376,
|
| 86 |
+
"learning_rate": 4.8134551098376315e-05,
|
| 87 |
+
"loss": 1.5301,
|
| 88 |
+
"step": 5000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.1119269340974212,
|
| 92 |
+
"eval_accuracy": 0.566450867740456,
|
| 93 |
+
"eval_loss": 2.3531110286712646,
|
| 94 |
+
"eval_runtime": 716.3757,
|
| 95 |
+
"eval_samples_per_second": 90.702,
|
| 96 |
+
"eval_steps_per_second": 3.78,
|
| 97 |
+
"step": 5000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.12311962750716332,
|
| 101 |
+
"grad_norm": 1.8723756074905396,
|
| 102 |
+
"learning_rate": 4.7948006208213945e-05,
|
| 103 |
+
"loss": 1.5153,
|
| 104 |
+
"step": 5500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.13431232091690545,
|
| 108 |
+
"grad_norm": 1.8938133716583252,
|
| 109 |
+
"learning_rate": 4.7761461318051575e-05,
|
| 110 |
+
"loss": 1.5051,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.14550501432664756,
|
| 115 |
+
"grad_norm": 1.8093421459197998,
|
| 116 |
+
"learning_rate": 4.757491642788921e-05,
|
| 117 |
+
"loss": 1.4922,
|
| 118 |
+
"step": 6500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.1566977077363897,
|
| 122 |
+
"grad_norm": 1.8811379671096802,
|
| 123 |
+
"learning_rate": 4.738837153772684e-05,
|
| 124 |
+
"loss": 1.4841,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.1678904011461318,
|
| 129 |
+
"grad_norm": 1.8162873983383179,
|
| 130 |
+
"learning_rate": 4.720182664756447e-05,
|
| 131 |
+
"loss": 1.4664,
|
| 132 |
+
"step": 7500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.1678904011461318,
|
| 136 |
+
"eval_accuracy": 0.5726688422748262,
|
| 137 |
+
"eval_loss": 2.2988929748535156,
|
| 138 |
+
"eval_runtime": 706.3059,
|
| 139 |
+
"eval_samples_per_second": 91.996,
|
| 140 |
+
"eval_steps_per_second": 3.834,
|
| 141 |
+
"step": 7500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.17908309455587393,
|
| 145 |
+
"grad_norm": 1.861790418624878,
|
| 146 |
+
"learning_rate": 4.70152817574021e-05,
|
| 147 |
+
"loss": 1.4613,
|
| 148 |
+
"step": 8000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.19027578796561603,
|
| 152 |
+
"grad_norm": 1.7351659536361694,
|
| 153 |
+
"learning_rate": 4.682873686723974e-05,
|
| 154 |
+
"loss": 1.4554,
|
| 155 |
+
"step": 8500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.20146848137535817,
|
| 159 |
+
"grad_norm": 1.796727180480957,
|
| 160 |
+
"learning_rate": 4.664219197707737e-05,
|
| 161 |
+
"loss": 1.4469,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.2126611747851003,
|
| 166 |
+
"grad_norm": 1.751111388206482,
|
| 167 |
+
"learning_rate": 4.6455647086915e-05,
|
| 168 |
+
"loss": 1.4405,
|
| 169 |
+
"step": 9500
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.2238538681948424,
|
| 173 |
+
"grad_norm": 1.793644905090332,
|
| 174 |
+
"learning_rate": 4.626910219675263e-05,
|
| 175 |
+
"loss": 1.4314,
|
| 176 |
+
"step": 10000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2238538681948424,
|
| 180 |
+
"eval_accuracy": 0.5781162212828304,
|
| 181 |
+
"eval_loss": 2.257195472717285,
|
| 182 |
+
"eval_runtime": 709.7465,
|
| 183 |
+
"eval_samples_per_second": 91.55,
|
| 184 |
+
"eval_steps_per_second": 3.815,
|
| 185 |
+
"step": 10000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.23504656160458454,
|
| 189 |
+
"grad_norm": 1.7030937671661377,
|
| 190 |
+
"learning_rate": 4.6082557306590264e-05,
|
| 191 |
+
"loss": 1.425,
|
| 192 |
+
"step": 10500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.24623925501432664,
|
| 196 |
+
"grad_norm": 1.7245328426361084,
|
| 197 |
+
"learning_rate": 4.5896012416427894e-05,
|
| 198 |
+
"loss": 1.4206,
|
| 199 |
+
"step": 11000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.25743194842406875,
|
| 203 |
+
"grad_norm": 1.7355397939682007,
|
| 204 |
+
"learning_rate": 4.570946752626552e-05,
|
| 205 |
+
"loss": 1.409,
|
| 206 |
+
"step": 11500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2686246418338109,
|
| 210 |
+
"grad_norm": 1.7283306121826172,
|
| 211 |
+
"learning_rate": 4.5522922636103154e-05,
|
| 212 |
+
"loss": 1.4086,
|
| 213 |
+
"step": 12000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.279817335243553,
|
| 217 |
+
"grad_norm": 1.7133527994155884,
|
| 218 |
+
"learning_rate": 4.5336377745940784e-05,
|
| 219 |
+
"loss": 1.4042,
|
| 220 |
+
"step": 12500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.279817335243553,
|
| 224 |
+
"eval_accuracy": 0.5822483255357088,
|
| 225 |
+
"eval_loss": 2.2244207859039307,
|
| 226 |
+
"eval_runtime": 708.1859,
|
| 227 |
+
"eval_samples_per_second": 91.751,
|
| 228 |
+
"eval_steps_per_second": 3.824,
|
| 229 |
+
"step": 12500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.2910100286532951,
|
| 233 |
+
"grad_norm": 1.688602328300476,
|
| 234 |
+
"learning_rate": 4.514983285577842e-05,
|
| 235 |
+
"loss": 1.3952,
|
| 236 |
+
"step": 13000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.3022027220630373,
|
| 240 |
+
"grad_norm": 1.6839321851730347,
|
| 241 |
+
"learning_rate": 4.4963287965616043e-05,
|
| 242 |
+
"loss": 1.3932,
|
| 243 |
+
"step": 13500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3133954154727794,
|
| 247 |
+
"grad_norm": 1.7225844860076904,
|
| 248 |
+
"learning_rate": 4.477674307545368e-05,
|
| 249 |
+
"loss": 1.3839,
|
| 250 |
+
"step": 14000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3245881088825215,
|
| 254 |
+
"grad_norm": 1.6329905986785889,
|
| 255 |
+
"learning_rate": 4.459019818529131e-05,
|
| 256 |
+
"loss": 1.3856,
|
| 257 |
+
"step": 14500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.3357808022922636,
|
| 261 |
+
"grad_norm": 1.7012953758239746,
|
| 262 |
+
"learning_rate": 4.440365329512895e-05,
|
| 263 |
+
"loss": 1.3771,
|
| 264 |
+
"step": 15000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.3357808022922636,
|
| 268 |
+
"eval_accuracy": 0.586269614225024,
|
| 269 |
+
"eval_loss": 2.1954798698425293,
|
| 270 |
+
"eval_runtime": 718.0126,
|
| 271 |
+
"eval_samples_per_second": 90.496,
|
| 272 |
+
"eval_steps_per_second": 3.772,
|
| 273 |
+
"step": 15000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.34697349570200575,
|
| 277 |
+
"grad_norm": 1.6593496799468994,
|
| 278 |
+
"learning_rate": 4.421710840496657e-05,
|
| 279 |
+
"loss": 1.376,
|
| 280 |
+
"step": 15500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.35816618911174786,
|
| 284 |
+
"grad_norm": 1.6412550210952759,
|
| 285 |
+
"learning_rate": 4.4030563514804206e-05,
|
| 286 |
+
"loss": 1.3712,
|
| 287 |
+
"step": 16000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.36935888252148996,
|
| 291 |
+
"grad_norm": 1.6455302238464355,
|
| 292 |
+
"learning_rate": 4.3844018624641836e-05,
|
| 293 |
+
"loss": 1.3699,
|
| 294 |
+
"step": 16500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.38055157593123207,
|
| 298 |
+
"grad_norm": 1.6210881471633911,
|
| 299 |
+
"learning_rate": 4.3657473734479466e-05,
|
| 300 |
+
"loss": 1.3618,
|
| 301 |
+
"step": 17000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.3917442693409742,
|
| 305 |
+
"grad_norm": 1.6821410655975342,
|
| 306 |
+
"learning_rate": 4.3470928844317096e-05,
|
| 307 |
+
"loss": 1.3563,
|
| 308 |
+
"step": 17500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3917442693409742,
|
| 312 |
+
"eval_accuracy": 0.589598096204646,
|
| 313 |
+
"eval_loss": 2.168947219848633,
|
| 314 |
+
"eval_runtime": 707.8628,
|
| 315 |
+
"eval_samples_per_second": 91.793,
|
| 316 |
+
"eval_steps_per_second": 3.826,
|
| 317 |
+
"step": 17500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.40293696275071633,
|
| 321 |
+
"grad_norm": 1.719738245010376,
|
| 322 |
+
"learning_rate": 4.3284383954154726e-05,
|
| 323 |
+
"loss": 1.3585,
|
| 324 |
+
"step": 18000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.41412965616045844,
|
| 328 |
+
"grad_norm": 1.660507321357727,
|
| 329 |
+
"learning_rate": 4.309783906399236e-05,
|
| 330 |
+
"loss": 1.3502,
|
| 331 |
+
"step": 18500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4253223495702006,
|
| 335 |
+
"grad_norm": 1.7758148908615112,
|
| 336 |
+
"learning_rate": 4.291129417382999e-05,
|
| 337 |
+
"loss": 1.3459,
|
| 338 |
+
"step": 19000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4365150429799427,
|
| 342 |
+
"grad_norm": 1.6665699481964111,
|
| 343 |
+
"learning_rate": 4.272474928366762e-05,
|
| 344 |
+
"loss": 1.3435,
|
| 345 |
+
"step": 19500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4477077363896848,
|
| 349 |
+
"grad_norm": 1.6364027261734009,
|
| 350 |
+
"learning_rate": 4.253820439350525e-05,
|
| 351 |
+
"loss": 1.3401,
|
| 352 |
+
"step": 20000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4477077363896848,
|
| 356 |
+
"eval_accuracy": 0.5922608205511055,
|
| 357 |
+
"eval_loss": 2.1485562324523926,
|
| 358 |
+
"eval_runtime": 704.3891,
|
| 359 |
+
"eval_samples_per_second": 92.246,
|
| 360 |
+
"eval_steps_per_second": 3.844,
|
| 361 |
+
"step": 20000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.4589004297994269,
|
| 365 |
+
"grad_norm": 9.470758438110352,
|
| 366 |
+
"learning_rate": 4.426374462750716e-05,
|
| 367 |
+
"loss": 8.0235,
|
| 368 |
+
"step": 20500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.4700931232091691,
|
| 372 |
+
"grad_norm": 9.91232967376709,
|
| 373 |
+
"learning_rate": 4.412383595988539e-05,
|
| 374 |
+
"loss": 7.9603,
|
| 375 |
+
"step": 21000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.4812858166189112,
|
| 379 |
+
"grad_norm": 9.734143257141113,
|
| 380 |
+
"learning_rate": 4.398392729226361e-05,
|
| 381 |
+
"loss": 7.9793,
|
| 382 |
+
"step": 21500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.4924785100286533,
|
| 386 |
+
"grad_norm": 9.574400901794434,
|
| 387 |
+
"learning_rate": 4.3844018624641836e-05,
|
| 388 |
+
"loss": 7.9731,
|
| 389 |
+
"step": 22000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.5036712034383954,
|
| 393 |
+
"grad_norm": 10.017444610595703,
|
| 394 |
+
"learning_rate": 4.370410995702006e-05,
|
| 395 |
+
"loss": 7.9335,
|
| 396 |
+
"step": 22500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.5036712034383954,
|
| 400 |
+
"eval_accuracy": 0.5952892349509148,
|
| 401 |
+
"eval_loss": 2.1270551681518555,
|
| 402 |
+
"eval_runtime": 525.2336,
|
| 403 |
+
"eval_samples_per_second": 123.711,
|
| 404 |
+
"eval_steps_per_second": 2.578,
|
| 405 |
+
"step": 22500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.5148638968481375,
|
| 409 |
+
"grad_norm": 9.66054916381836,
|
| 410 |
+
"learning_rate": 4.356420128939828e-05,
|
| 411 |
+
"loss": 7.9224,
|
| 412 |
+
"step": 23000
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.5260565902578797,
|
| 416 |
+
"grad_norm": 9.483991622924805,
|
| 417 |
+
"learning_rate": 4.342429262177651e-05,
|
| 418 |
+
"loss": 7.9197,
|
| 419 |
+
"step": 23500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.5372492836676218,
|
| 423 |
+
"grad_norm": 9.803547859191895,
|
| 424 |
+
"learning_rate": 4.3284383954154726e-05,
|
| 425 |
+
"loss": 7.8932,
|
| 426 |
+
"step": 24000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5484419770773639,
|
| 430 |
+
"grad_norm": 9.597293853759766,
|
| 431 |
+
"learning_rate": 4.3144475286532955e-05,
|
| 432 |
+
"loss": 7.8622,
|
| 433 |
+
"step": 24500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.559634670487106,
|
| 437 |
+
"grad_norm": 9.679096221923828,
|
| 438 |
+
"learning_rate": 4.300456661891118e-05,
|
| 439 |
+
"loss": 7.8644,
|
| 440 |
+
"step": 25000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.559634670487106,
|
| 444 |
+
"eval_accuracy": 0.5979848217689566,
|
| 445 |
+
"eval_loss": 2.106226682662964,
|
| 446 |
+
"eval_runtime": 528.4389,
|
| 447 |
+
"eval_samples_per_second": 122.96,
|
| 448 |
+
"eval_steps_per_second": 2.562,
|
| 449 |
+
"step": 25000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.5708273638968482,
|
| 453 |
+
"grad_norm": 9.878997802734375,
|
| 454 |
+
"learning_rate": 4.28646579512894e-05,
|
| 455 |
+
"loss": 7.8388,
|
| 456 |
+
"step": 25500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.5820200573065902,
|
| 460 |
+
"grad_norm": 9.320840835571289,
|
| 461 |
+
"learning_rate": 4.272474928366762e-05,
|
| 462 |
+
"loss": 7.8199,
|
| 463 |
+
"step": 26000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5932127507163324,
|
| 467 |
+
"grad_norm": 9.581457138061523,
|
| 468 |
+
"learning_rate": 4.2584840616045845e-05,
|
| 469 |
+
"loss": 7.8194,
|
| 470 |
+
"step": 26500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.6044054441260746,
|
| 474 |
+
"grad_norm": 9.690735816955566,
|
| 475 |
+
"learning_rate": 4.2444931948424074e-05,
|
| 476 |
+
"loss": 7.8147,
|
| 477 |
+
"step": 27000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.6155981375358166,
|
| 481 |
+
"grad_norm": 9.55455207824707,
|
| 482 |
+
"learning_rate": 4.230502328080229e-05,
|
| 483 |
+
"loss": 7.7927,
|
| 484 |
+
"step": 27500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.6155981375358166,
|
| 488 |
+
"eval_accuracy": 0.599545230267029,
|
| 489 |
+
"eval_loss": 2.09478497505188,
|
| 490 |
+
"eval_runtime": 531.729,
|
| 491 |
+
"eval_samples_per_second": 122.199,
|
| 492 |
+
"eval_steps_per_second": 2.546,
|
| 493 |
+
"step": 27500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6267908309455588,
|
| 497 |
+
"grad_norm": 9.352036476135254,
|
| 498 |
+
"learning_rate": 4.216511461318052e-05,
|
| 499 |
+
"loss": 7.7711,
|
| 500 |
+
"step": 28000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6379835243553008,
|
| 504 |
+
"grad_norm": 9.413168907165527,
|
| 505 |
+
"learning_rate": 4.202520594555874e-05,
|
| 506 |
+
"loss": 7.7733,
|
| 507 |
+
"step": 28500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.649176217765043,
|
| 511 |
+
"grad_norm": 9.420402526855469,
|
| 512 |
+
"learning_rate": 4.1885297277936964e-05,
|
| 513 |
+
"loss": 7.74,
|
| 514 |
+
"step": 29000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6603689111747851,
|
| 518 |
+
"grad_norm": 9.579030990600586,
|
| 519 |
+
"learning_rate": 4.1745388610315186e-05,
|
| 520 |
+
"loss": 7.7237,
|
| 521 |
+
"step": 29500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6715616045845272,
|
| 525 |
+
"grad_norm": 12.816407203674316,
|
| 526 |
+
"learning_rate": 4.160547994269341e-05,
|
| 527 |
+
"loss": 7.7401,
|
| 528 |
+
"step": 30000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6715616045845272,
|
| 532 |
+
"eval_accuracy": 0.6018761556694041,
|
| 533 |
+
"eval_loss": 2.079362630844116,
|
| 534 |
+
"eval_runtime": 531.1941,
|
| 535 |
+
"eval_samples_per_second": 122.323,
|
| 536 |
+
"eval_steps_per_second": 2.549,
|
| 537 |
+
"step": 30000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6827542979942693,
|
| 541 |
+
"grad_norm": 9.477621078491211,
|
| 542 |
+
"learning_rate": 4.146557127507164e-05,
|
| 543 |
+
"loss": 7.717,
|
| 544 |
+
"step": 30500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6939469914040115,
|
| 548 |
+
"grad_norm": 9.8326416015625,
|
| 549 |
+
"learning_rate": 4.132566260744986e-05,
|
| 550 |
+
"loss": 7.7148,
|
| 551 |
+
"step": 31000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.7051396848137536,
|
| 555 |
+
"grad_norm": 9.668205261230469,
|
| 556 |
+
"learning_rate": 4.118575393982808e-05,
|
| 557 |
+
"loss": 7.6845,
|
| 558 |
+
"step": 31500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.7163323782234957,
|
| 562 |
+
"grad_norm": 9.344961166381836,
|
| 563 |
+
"learning_rate": 4.1045845272206305e-05,
|
| 564 |
+
"loss": 7.673,
|
| 565 |
+
"step": 32000
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.7275250716332379,
|
| 569 |
+
"grad_norm": 12.754666328430176,
|
| 570 |
+
"learning_rate": 4.090593660458453e-05,
|
| 571 |
+
"loss": 7.646,
|
| 572 |
+
"step": 32500
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.7275250716332379,
|
| 576 |
+
"eval_accuracy": 0.6036969981017439,
|
| 577 |
+
"eval_loss": 2.0638949871063232,
|
| 578 |
+
"eval_runtime": 534.6839,
|
| 579 |
+
"eval_samples_per_second": 121.524,
|
| 580 |
+
"eval_steps_per_second": 2.532,
|
| 581 |
+
"step": 32500
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.7387177650429799,
|
| 585 |
+
"grad_norm": 9.269234657287598,
|
| 586 |
+
"learning_rate": 4.076602793696275e-05,
|
| 587 |
+
"loss": 7.6452,
|
| 588 |
+
"step": 33000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.7499104584527221,
|
| 592 |
+
"grad_norm": 9.59334659576416,
|
| 593 |
+
"learning_rate": 4.062611926934098e-05,
|
| 594 |
+
"loss": 7.6369,
|
| 595 |
+
"step": 33500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.7611031518624641,
|
| 599 |
+
"grad_norm": 9.979016304016113,
|
| 600 |
+
"learning_rate": 4.04862106017192e-05,
|
| 601 |
+
"loss": 7.6306,
|
| 602 |
+
"step": 34000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.7722958452722063,
|
| 606 |
+
"grad_norm": 9.395634651184082,
|
| 607 |
+
"learning_rate": 4.0346301934097424e-05,
|
| 608 |
+
"loss": 7.6083,
|
| 609 |
+
"step": 34500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.7834885386819485,
|
| 613 |
+
"grad_norm": 9.377208709716797,
|
| 614 |
+
"learning_rate": 4.0206393266475646e-05,
|
| 615 |
+
"loss": 7.6113,
|
| 616 |
+
"step": 35000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.7834885386819485,
|
| 620 |
+
"eval_accuracy": 0.6060486530458662,
|
| 621 |
+
"eval_loss": 2.046678066253662,
|
| 622 |
+
"eval_runtime": 527.2553,
|
| 623 |
+
"eval_samples_per_second": 123.236,
|
| 624 |
+
"eval_steps_per_second": 2.568,
|
| 625 |
+
"step": 35000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7946812320916905,
|
| 629 |
+
"grad_norm": 9.33324146270752,
|
| 630 |
+
"learning_rate": 4.006648459885387e-05,
|
| 631 |
+
"loss": 7.596,
|
| 632 |
+
"step": 35500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8058739255014327,
|
| 636 |
+
"grad_norm": 10.012749671936035,
|
| 637 |
+
"learning_rate": 3.992657593123209e-05,
|
| 638 |
+
"loss": 7.5944,
|
| 639 |
+
"step": 36000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8170666189111748,
|
| 643 |
+
"grad_norm": 9.17791748046875,
|
| 644 |
+
"learning_rate": 3.9786667263610314e-05,
|
| 645 |
+
"loss": 7.5724,
|
| 646 |
+
"step": 36500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8282593123209169,
|
| 650 |
+
"grad_norm": 9.714068412780762,
|
| 651 |
+
"learning_rate": 3.964675859598854e-05,
|
| 652 |
+
"loss": 7.5716,
|
| 653 |
+
"step": 37000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.839452005730659,
|
| 657 |
+
"grad_norm": 9.122146606445312,
|
| 658 |
+
"learning_rate": 3.9506849928366765e-05,
|
| 659 |
+
"loss": 7.5428,
|
| 660 |
+
"step": 37500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.839452005730659,
|
| 664 |
+
"eval_accuracy": 0.6080310471813272,
|
| 665 |
+
"eval_loss": 2.0341005325317383,
|
| 666 |
+
"eval_runtime": 534.9624,
|
| 667 |
+
"eval_samples_per_second": 121.461,
|
| 668 |
+
"eval_steps_per_second": 2.531,
|
| 669 |
+
"step": 37500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.8506446991404012,
|
| 673 |
+
"grad_norm": 8.890284538269043,
|
| 674 |
+
"learning_rate": 3.936694126074499e-05,
|
| 675 |
+
"loss": 7.5108,
|
| 676 |
+
"step": 38000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.8618373925501432,
|
| 680 |
+
"grad_norm": 9.258638381958008,
|
| 681 |
+
"learning_rate": 3.922703259312321e-05,
|
| 682 |
+
"loss": 7.5283,
|
| 683 |
+
"step": 38500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.8730300859598854,
|
| 687 |
+
"grad_norm": 9.524474143981934,
|
| 688 |
+
"learning_rate": 3.908712392550143e-05,
|
| 689 |
+
"loss": 7.5168,
|
| 690 |
+
"step": 39000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.8842227793696275,
|
| 694 |
+
"grad_norm": 9.608149528503418,
|
| 695 |
+
"learning_rate": 3.894721525787966e-05,
|
| 696 |
+
"loss": 7.5206,
|
| 697 |
+
"step": 39500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8954154727793696,
|
| 701 |
+
"grad_norm": 9.405288696289062,
|
| 702 |
+
"learning_rate": 3.880730659025788e-05,
|
| 703 |
+
"loss": 7.5039,
|
| 704 |
+
"step": 40000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.8954154727793696,
|
| 708 |
+
"eval_accuracy": 0.6094788673634718,
|
| 709 |
+
"eval_loss": 2.0253567695617676,
|
| 710 |
+
"eval_runtime": 535.0948,
|
| 711 |
+
"eval_samples_per_second": 121.431,
|
| 712 |
+
"eval_steps_per_second": 2.53,
|
| 713 |
+
"step": 40000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.9066081661891118,
|
| 717 |
+
"grad_norm": 8.706295013427734,
|
| 718 |
+
"learning_rate": 3.8667397922636107e-05,
|
| 719 |
+
"loss": 7.4819,
|
| 720 |
+
"step": 40500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.9178008595988538,
|
| 724 |
+
"grad_norm": 9.542219161987305,
|
| 725 |
+
"learning_rate": 3.852748925501433e-05,
|
| 726 |
+
"loss": 7.4888,
|
| 727 |
+
"step": 41000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.928993553008596,
|
| 731 |
+
"grad_norm": 9.111319541931152,
|
| 732 |
+
"learning_rate": 3.838758058739255e-05,
|
| 733 |
+
"loss": 7.4749,
|
| 734 |
+
"step": 41500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.9401862464183381,
|
| 738 |
+
"grad_norm": 9.335123062133789,
|
| 739 |
+
"learning_rate": 3.824767191977078e-05,
|
| 740 |
+
"loss": 7.4591,
|
| 741 |
+
"step": 42000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.9513789398280802,
|
| 745 |
+
"grad_norm": 9.537328720092773,
|
| 746 |
+
"learning_rate": 3.8107763252148996e-05,
|
| 747 |
+
"loss": 7.4533,
|
| 748 |
+
"step": 42500
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.9513789398280802,
|
| 752 |
+
"eval_accuracy": 0.6107361281876699,
|
| 753 |
+
"eval_loss": 2.0133583545684814,
|
| 754 |
+
"eval_runtime": 530.2968,
|
| 755 |
+
"eval_samples_per_second": 122.529,
|
| 756 |
+
"eval_steps_per_second": 2.553,
|
| 757 |
+
"step": 42500
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.9625716332378224,
|
| 761 |
+
"grad_norm": 9.227987289428711,
|
| 762 |
+
"learning_rate": 3.7967854584527225e-05,
|
| 763 |
+
"loss": 7.4506,
|
| 764 |
+
"step": 43000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.9737643266475645,
|
| 768 |
+
"grad_norm": 9.076460838317871,
|
| 769 |
+
"learning_rate": 3.782794591690544e-05,
|
| 770 |
+
"loss": 7.4557,
|
| 771 |
+
"step": 43500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.9849570200573066,
|
| 775 |
+
"grad_norm": 9.841446876525879,
|
| 776 |
+
"learning_rate": 3.768803724928367e-05,
|
| 777 |
+
"loss": 7.4319,
|
| 778 |
+
"step": 44000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.9961497134670487,
|
| 782 |
+
"grad_norm": 9.169388771057129,
|
| 783 |
+
"learning_rate": 3.754812858166189e-05,
|
| 784 |
+
"loss": 7.4453,
|
| 785 |
+
"step": 44500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.0073424068767909,
|
| 789 |
+
"grad_norm": 9.200368881225586,
|
| 790 |
+
"learning_rate": 3.7408219914040115e-05,
|
| 791 |
+
"loss": 7.4149,
|
| 792 |
+
"step": 45000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.0073424068767909,
|
| 796 |
+
"eval_accuracy": 0.6120696404224526,
|
| 797 |
+
"eval_loss": 2.0035457611083984,
|
| 798 |
+
"eval_runtime": 532.3092,
|
| 799 |
+
"eval_samples_per_second": 122.066,
|
| 800 |
+
"eval_steps_per_second": 2.544,
|
| 801 |
+
"step": 45000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.018535100286533,
|
| 805 |
+
"grad_norm": 9.189336776733398,
|
| 806 |
+
"learning_rate": 3.7268311246418344e-05,
|
| 807 |
+
"loss": 7.3981,
|
| 808 |
+
"step": 45500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.029727793696275,
|
| 812 |
+
"grad_norm": 9.504659652709961,
|
| 813 |
+
"learning_rate": 3.712840257879656e-05,
|
| 814 |
+
"loss": 7.4031,
|
| 815 |
+
"step": 46000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.0409204871060171,
|
| 819 |
+
"grad_norm": 9.516868591308594,
|
| 820 |
+
"learning_rate": 3.698849391117479e-05,
|
| 821 |
+
"loss": 7.3822,
|
| 822 |
+
"step": 46500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.0521131805157593,
|
| 826 |
+
"grad_norm": 9.417741775512695,
|
| 827 |
+
"learning_rate": 3.6848585243553005e-05,
|
| 828 |
+
"loss": 7.3887,
|
| 829 |
+
"step": 47000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0633058739255015,
|
| 833 |
+
"grad_norm": 9.202630043029785,
|
| 834 |
+
"learning_rate": 3.6708676575931234e-05,
|
| 835 |
+
"loss": 7.379,
|
| 836 |
+
"step": 47500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0633058739255015,
|
| 840 |
+
"eval_accuracy": 0.6134326919026999,
|
| 841 |
+
"eval_loss": 1.9946683645248413,
|
| 842 |
+
"eval_runtime": 529.4253,
|
| 843 |
+
"eval_samples_per_second": 122.731,
|
| 844 |
+
"eval_steps_per_second": 2.557,
|
| 845 |
+
"step": 47500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.0744985673352436,
|
| 849 |
+
"grad_norm": 9.18812084197998,
|
| 850 |
+
"learning_rate": 3.6568767908309456e-05,
|
| 851 |
+
"loss": 7.3648,
|
| 852 |
+
"step": 48000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.0856912607449858,
|
| 856 |
+
"grad_norm": 9.317421913146973,
|
| 857 |
+
"learning_rate": 3.642885924068768e-05,
|
| 858 |
+
"loss": 7.3581,
|
| 859 |
+
"step": 48500
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.0968839541547277,
|
| 863 |
+
"grad_norm": 9.30117130279541,
|
| 864 |
+
"learning_rate": 3.628895057306591e-05,
|
| 865 |
+
"loss": 7.3242,
|
| 866 |
+
"step": 49000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.1080766475644699,
|
| 870 |
+
"grad_norm": 9.295071601867676,
|
| 871 |
+
"learning_rate": 3.6149041905444124e-05,
|
| 872 |
+
"loss": 7.3343,
|
| 873 |
+
"step": 49500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.119269340974212,
|
| 877 |
+
"grad_norm": 9.372967720031738,
|
| 878 |
+
"learning_rate": 3.600913323782235e-05,
|
| 879 |
+
"loss": 7.324,
|
| 880 |
+
"step": 50000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.119269340974212,
|
| 884 |
+
"eval_accuracy": 0.6151487162989436,
|
| 885 |
+
"eval_loss": 1.9853588342666626,
|
| 886 |
+
"eval_runtime": 528.6238,
|
| 887 |
+
"eval_samples_per_second": 122.917,
|
| 888 |
+
"eval_steps_per_second": 2.561,
|
| 889 |
+
"step": 50000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.1304620343839542,
|
| 893 |
+
"grad_norm": 10.693807601928711,
|
| 894 |
+
"learning_rate": 3.5869224570200575e-05,
|
| 895 |
+
"loss": 7.3164,
|
| 896 |
+
"step": 50500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.1416547277936964,
|
| 900 |
+
"grad_norm": 9.047393798828125,
|
| 901 |
+
"learning_rate": 3.57293159025788e-05,
|
| 902 |
+
"loss": 7.3028,
|
| 903 |
+
"step": 51000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.1528474212034383,
|
| 907 |
+
"grad_norm": 9.055428504943848,
|
| 908 |
+
"learning_rate": 3.558940723495702e-05,
|
| 909 |
+
"loss": 7.316,
|
| 910 |
+
"step": 51500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.1640401146131805,
|
| 914 |
+
"grad_norm": 8.821599960327148,
|
| 915 |
+
"learning_rate": 3.544949856733524e-05,
|
| 916 |
+
"loss": 7.2759,
|
| 917 |
+
"step": 52000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.1752328080229226,
|
| 921 |
+
"grad_norm": 8.971498489379883,
|
| 922 |
+
"learning_rate": 3.530958989971347e-05,
|
| 923 |
+
"loss": 7.3041,
|
| 924 |
+
"step": 52500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.1752328080229226,
|
| 928 |
+
"eval_accuracy": 0.6162336395081003,
|
| 929 |
+
"eval_loss": 1.9736484289169312,
|
| 930 |
+
"eval_runtime": 526.2473,
|
| 931 |
+
"eval_samples_per_second": 123.472,
|
| 932 |
+
"eval_steps_per_second": 2.573,
|
| 933 |
+
"step": 52500
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.1864255014326648,
|
| 937 |
+
"grad_norm": 9.30490779876709,
|
| 938 |
+
"learning_rate": 3.5169681232091694e-05,
|
| 939 |
+
"loss": 7.2966,
|
| 940 |
+
"step": 53000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.197618194842407,
|
| 944 |
+
"grad_norm": 9.367337226867676,
|
| 945 |
+
"learning_rate": 3.5029772564469917e-05,
|
| 946 |
+
"loss": 7.2862,
|
| 947 |
+
"step": 53500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.2088108882521489,
|
| 951 |
+
"grad_norm": 9.002731323242188,
|
| 952 |
+
"learning_rate": 3.488986389684814e-05,
|
| 953 |
+
"loss": 7.2858,
|
| 954 |
+
"step": 54000
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.220003581661891,
|
| 958 |
+
"grad_norm": 9.070691108703613,
|
| 959 |
+
"learning_rate": 3.474995522922636e-05,
|
| 960 |
+
"loss": 7.2692,
|
| 961 |
+
"step": 54500
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.2311962750716332,
|
| 965 |
+
"grad_norm": 9.154426574707031,
|
| 966 |
+
"learning_rate": 3.4610046561604584e-05,
|
| 967 |
+
"loss": 7.262,
|
| 968 |
+
"step": 55000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.2311962750716332,
|
| 972 |
+
"eval_accuracy": 0.6174860367511424,
|
| 973 |
+
"eval_loss": 1.9672149419784546,
|
| 974 |
+
"eval_runtime": 529.8804,
|
| 975 |
+
"eval_samples_per_second": 122.626,
|
| 976 |
+
"eval_steps_per_second": 2.555,
|
| 977 |
+
"step": 55000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.2423889684813754,
|
| 981 |
+
"grad_norm": 9.364106178283691,
|
| 982 |
+
"learning_rate": 3.447013789398281e-05,
|
| 983 |
+
"loss": 7.2489,
|
| 984 |
+
"step": 55500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.2535816618911175,
|
| 988 |
+
"grad_norm": 9.267243385314941,
|
| 989 |
+
"learning_rate": 3.4330229226361035e-05,
|
| 990 |
+
"loss": 7.2664,
|
| 991 |
+
"step": 56000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.2647743553008595,
|
| 995 |
+
"grad_norm": 9.162137031555176,
|
| 996 |
+
"learning_rate": 3.419032055873926e-05,
|
| 997 |
+
"loss": 7.2475,
|
| 998 |
+
"step": 56500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.2759670487106018,
|
| 1002 |
+
"grad_norm": 9.292202949523926,
|
| 1003 |
+
"learning_rate": 3.405041189111748e-05,
|
| 1004 |
+
"loss": 7.2357,
|
| 1005 |
+
"step": 57000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.2871597421203438,
|
| 1009 |
+
"grad_norm": 9.280839920043945,
|
| 1010 |
+
"learning_rate": 3.39105032234957e-05,
|
| 1011 |
+
"loss": 7.2169,
|
| 1012 |
+
"step": 57500
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.2871597421203438,
|
| 1016 |
+
"eval_accuracy": 0.6184868881174969,
|
| 1017 |
+
"eval_loss": 1.9653985500335693,
|
| 1018 |
+
"eval_runtime": 531.1309,
|
| 1019 |
+
"eval_samples_per_second": 122.337,
|
| 1020 |
+
"eval_steps_per_second": 2.549,
|
| 1021 |
+
"step": 57500
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.298352435530086,
|
| 1025 |
+
"grad_norm": 8.75936222076416,
|
| 1026 |
+
"learning_rate": 3.3770594555873925e-05,
|
| 1027 |
+
"loss": 7.2052,
|
| 1028 |
+
"step": 58000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.309545128939828,
|
| 1032 |
+
"grad_norm": 8.891804695129395,
|
| 1033 |
+
"learning_rate": 3.363068588825215e-05,
|
| 1034 |
+
"loss": 7.2258,
|
| 1035 |
+
"step": 58500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.3207378223495703,
|
| 1039 |
+
"grad_norm": 8.931051254272461,
|
| 1040 |
+
"learning_rate": 3.349077722063038e-05,
|
| 1041 |
+
"loss": 7.1899,
|
| 1042 |
+
"step": 59000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.3319305157593124,
|
| 1046 |
+
"grad_norm": 9.616579055786133,
|
| 1047 |
+
"learning_rate": 3.33508685530086e-05,
|
| 1048 |
+
"loss": 7.2068,
|
| 1049 |
+
"step": 59500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.3431232091690544,
|
| 1053 |
+
"grad_norm": 8.981892585754395,
|
| 1054 |
+
"learning_rate": 3.321095988538682e-05,
|
| 1055 |
+
"loss": 7.2084,
|
| 1056 |
+
"step": 60000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.3431232091690544,
|
| 1060 |
+
"eval_accuracy": 0.6190439375486008,
|
| 1061 |
+
"eval_loss": 1.9544332027435303,
|
| 1062 |
+
"eval_runtime": 528.8193,
|
| 1063 |
+
"eval_samples_per_second": 122.872,
|
| 1064 |
+
"eval_steps_per_second": 2.56,
|
| 1065 |
+
"step": 60000
|
| 1066 |
+
}
|
| 1067 |
+
],
|
| 1068 |
+
"logging_steps": 500,
|
| 1069 |
+
"max_steps": 178688,
|
| 1070 |
+
"num_input_tokens_seen": 0,
|
| 1071 |
+
"num_train_epochs": 4,
|
| 1072 |
+
"save_steps": 2500,
|
| 1073 |
+
"stateful_callbacks": {
|
| 1074 |
+
"TrainerControl": {
|
| 1075 |
+
"args": {
|
| 1076 |
+
"should_epoch_stop": false,
|
| 1077 |
+
"should_evaluate": false,
|
| 1078 |
+
"should_log": false,
|
| 1079 |
+
"should_save": true,
|
| 1080 |
+
"should_training_stop": false
|
| 1081 |
+
},
|
| 1082 |
+
"attributes": {}
|
| 1083 |
+
}
|
| 1084 |
+
},
|
| 1085 |
+
"total_flos": 2.2799139827941786e+18,
|
| 1086 |
+
"train_batch_size": 24,
|
| 1087 |
+
"trial_name": null,
|
| 1088 |
+
"trial_params": null
|
| 1089 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a127654e28f0ac193c5c855bb7d96cd192293eb6e5c56cada203fa53cca1415
|
| 3 |
+
size 5051
|