Upload fine-tuned BGE-M3 model
Browse files- .gitattributes +1 -0
- config.json +27 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +56 -0
- trainer_state.json +391 -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 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaModel"
|
| 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 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 8194,
|
| 16 |
+
"model_type": "xlm-roberta",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.51.1",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 250002
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74ad78e1eea4732687d58ebbf49e959a10ae764f0935711c58bbc55683167f5e
|
| 3 |
+
size 2271064456
|
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:a76886210e737f92344b13ef5c3aeba877e4c3debdc2ed22e1306a315a922ae6
|
| 3 |
+
size 17082897
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"sep_token": "</s>",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 25872,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01932591218305504,
|
| 14 |
+
"grad_norm": 135.7185821533203,
|
| 15 |
+
"learning_rate": 1.9088098918083462e-06,
|
| 16 |
+
"loss": 2.7419,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03865182436611008,
|
| 21 |
+
"grad_norm": 71.08179473876953,
|
| 22 |
+
"learning_rate": 3.840803709428131e-06,
|
| 23 |
+
"loss": 1.6608,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05797773654916512,
|
| 28 |
+
"grad_norm": 102.95220184326172,
|
| 29 |
+
"learning_rate": 5.772797527047914e-06,
|
| 30 |
+
"loss": 1.5107,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07730364873222016,
|
| 35 |
+
"grad_norm": 72.49132537841797,
|
| 36 |
+
"learning_rate": 7.704791344667698e-06,
|
| 37 |
+
"loss": 1.3103,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0966295609152752,
|
| 42 |
+
"grad_norm": 78.74112701416016,
|
| 43 |
+
"learning_rate": 9.636785162287482e-06,
|
| 44 |
+
"loss": 1.3606,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11595547309833024,
|
| 49 |
+
"grad_norm": 132.5709991455078,
|
| 50 |
+
"learning_rate": 9.825631334822196e-06,
|
| 51 |
+
"loss": 1.2151,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.13528138528138528,
|
| 56 |
+
"grad_norm": 89.91647338867188,
|
| 57 |
+
"learning_rate": 9.61089159938155e-06,
|
| 58 |
+
"loss": 1.1923,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15460729746444032,
|
| 63 |
+
"grad_norm": 31.426151275634766,
|
| 64 |
+
"learning_rate": 9.396581343411786e-06,
|
| 65 |
+
"loss": 1.1765,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.17393320964749537,
|
| 70 |
+
"grad_norm": 93.264404296875,
|
| 71 |
+
"learning_rate": 9.18184160797114e-06,
|
| 72 |
+
"loss": 1.1631,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1932591218305504,
|
| 77 |
+
"grad_norm": 94.13616943359375,
|
| 78 |
+
"learning_rate": 8.967101872530494e-06,
|
| 79 |
+
"loss": 1.1176,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21258503401360543,
|
| 84 |
+
"grad_norm": 67.35560607910156,
|
| 85 |
+
"learning_rate": 8.752362137089849e-06,
|
| 86 |
+
"loss": 1.1277,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23191094619666047,
|
| 91 |
+
"grad_norm": 34.71173858642578,
|
| 92 |
+
"learning_rate": 8.537622401649201e-06,
|
| 93 |
+
"loss": 1.0943,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.25123685837971554,
|
| 98 |
+
"grad_norm": 134.21011352539062,
|
| 99 |
+
"learning_rate": 8.322882666208556e-06,
|
| 100 |
+
"loss": 1.052,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.27056277056277056,
|
| 105 |
+
"grad_norm": 100.96661376953125,
|
| 106 |
+
"learning_rate": 8.10857241023879e-06,
|
| 107 |
+
"loss": 1.0651,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2898886827458256,
|
| 112 |
+
"grad_norm": 95.49282836914062,
|
| 113 |
+
"learning_rate": 7.893832674798145e-06,
|
| 114 |
+
"loss": 1.0536,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.30921459492888065,
|
| 119 |
+
"grad_norm": 94.79146575927734,
|
| 120 |
+
"learning_rate": 7.6790929393575e-06,
|
| 121 |
+
"loss": 1.0546,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.32854050711193566,
|
| 126 |
+
"grad_norm": 67.1232681274414,
|
| 127 |
+
"learning_rate": 7.464353203916853e-06,
|
| 128 |
+
"loss": 1.0366,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.34786641929499074,
|
| 133 |
+
"grad_norm": 48.50230026245117,
|
| 134 |
+
"learning_rate": 7.250042947947089e-06,
|
| 135 |
+
"loss": 1.0106,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.36719233147804575,
|
| 140 |
+
"grad_norm": 28.64300537109375,
|
| 141 |
+
"learning_rate": 7.035303212506442e-06,
|
| 142 |
+
"loss": 1.0843,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3865182436611008,
|
| 147 |
+
"grad_norm": 48.05903625488281,
|
| 148 |
+
"learning_rate": 6.820563477065797e-06,
|
| 149 |
+
"loss": 1.0454,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.40584415584415584,
|
| 154 |
+
"grad_norm": 53.515464782714844,
|
| 155 |
+
"learning_rate": 6.605823741625152e-06,
|
| 156 |
+
"loss": 0.9767,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.42517006802721086,
|
| 161 |
+
"grad_norm": 2.856135606765747,
|
| 162 |
+
"learning_rate": 6.391084006184504e-06,
|
| 163 |
+
"loss": 0.9433,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.44449598021026593,
|
| 168 |
+
"grad_norm": 125.483154296875,
|
| 169 |
+
"learning_rate": 6.17677375021474e-06,
|
| 170 |
+
"loss": 0.9314,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.46382189239332094,
|
| 175 |
+
"grad_norm": 45.01868438720703,
|
| 176 |
+
"learning_rate": 5.962034014774094e-06,
|
| 177 |
+
"loss": 0.9568,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.483147804576376,
|
| 182 |
+
"grad_norm": 15.953567504882812,
|
| 183 |
+
"learning_rate": 5.747294279333448e-06,
|
| 184 |
+
"loss": 0.8972,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5024737167594311,
|
| 189 |
+
"grad_norm": 85.09109497070312,
|
| 190 |
+
"learning_rate": 5.532554543892802e-06,
|
| 191 |
+
"loss": 0.9156,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5217996289424861,
|
| 196 |
+
"grad_norm": 53.42656707763672,
|
| 197 |
+
"learning_rate": 5.317814808452156e-06,
|
| 198 |
+
"loss": 0.9581,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5411255411255411,
|
| 203 |
+
"grad_norm": 72.82543182373047,
|
| 204 |
+
"learning_rate": 5.103504552482392e-06,
|
| 205 |
+
"loss": 0.9065,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5604514533085961,
|
| 210 |
+
"grad_norm": 88.66947174072266,
|
| 211 |
+
"learning_rate": 4.8887648170417454e-06,
|
| 212 |
+
"loss": 0.9134,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5797773654916512,
|
| 217 |
+
"grad_norm": 86.12175750732422,
|
| 218 |
+
"learning_rate": 4.6740250816011e-06,
|
| 219 |
+
"loss": 0.8819,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5991032776747063,
|
| 224 |
+
"grad_norm": 61.66287612915039,
|
| 225 |
+
"learning_rate": 4.459285346160454e-06,
|
| 226 |
+
"loss": 0.8798,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6184291898577613,
|
| 231 |
+
"grad_norm": 51.16645431518555,
|
| 232 |
+
"learning_rate": 4.244975090190689e-06,
|
| 233 |
+
"loss": 0.8437,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6377551020408163,
|
| 238 |
+
"grad_norm": 135.60870361328125,
|
| 239 |
+
"learning_rate": 4.0302353547500435e-06,
|
| 240 |
+
"loss": 0.8831,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6570810142238713,
|
| 245 |
+
"grad_norm": 89.30845642089844,
|
| 246 |
+
"learning_rate": 3.815495619309397e-06,
|
| 247 |
+
"loss": 0.8872,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6764069264069265,
|
| 252 |
+
"grad_norm": 54.0753288269043,
|
| 253 |
+
"learning_rate": 3.6007558838687514e-06,
|
| 254 |
+
"loss": 0.8717,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6957328385899815,
|
| 259 |
+
"grad_norm": 28.510011672973633,
|
| 260 |
+
"learning_rate": 3.3860161484281057e-06,
|
| 261 |
+
"loss": 0.8599,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7150587507730365,
|
| 266 |
+
"grad_norm": 42.08302307128906,
|
| 267 |
+
"learning_rate": 3.1712764129874596e-06,
|
| 268 |
+
"loss": 0.7934,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7343846629560915,
|
| 273 |
+
"grad_norm": 54.24616622924805,
|
| 274 |
+
"learning_rate": 2.956966157017695e-06,
|
| 275 |
+
"loss": 0.7987,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7537105751391465,
|
| 280 |
+
"grad_norm": 66.43406677246094,
|
| 281 |
+
"learning_rate": 2.742226421577049e-06,
|
| 282 |
+
"loss": 0.8707,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.7730364873222016,
|
| 287 |
+
"grad_norm": 47.240234375,
|
| 288 |
+
"learning_rate": 2.527486686136403e-06,
|
| 289 |
+
"loss": 0.8444,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.7923623995052567,
|
| 294 |
+
"grad_norm": 50.62797164916992,
|
| 295 |
+
"learning_rate": 2.312746950695757e-06,
|
| 296 |
+
"loss": 0.8591,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.8116883116883117,
|
| 301 |
+
"grad_norm": 41.326271057128906,
|
| 302 |
+
"learning_rate": 2.0980072152551107e-06,
|
| 303 |
+
"loss": 0.7583,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8310142238713667,
|
| 308 |
+
"grad_norm": 101.81986236572266,
|
| 309 |
+
"learning_rate": 1.883267479814465e-06,
|
| 310 |
+
"loss": 0.9015,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8503401360544217,
|
| 315 |
+
"grad_norm": 109.75096893310547,
|
| 316 |
+
"learning_rate": 1.6689572238447004e-06,
|
| 317 |
+
"loss": 0.798,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8696660482374768,
|
| 322 |
+
"grad_norm": 74.9537582397461,
|
| 323 |
+
"learning_rate": 1.4542174884040545e-06,
|
| 324 |
+
"loss": 0.8254,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8889919604205319,
|
| 329 |
+
"grad_norm": 53.3721923828125,
|
| 330 |
+
"learning_rate": 1.2394777529634084e-06,
|
| 331 |
+
"loss": 0.8392,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9083178726035869,
|
| 336 |
+
"grad_norm": 74.43936157226562,
|
| 337 |
+
"learning_rate": 1.0247380175227625e-06,
|
| 338 |
+
"loss": 0.7987,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9276437847866419,
|
| 343 |
+
"grad_norm": 22.659399032592773,
|
| 344 |
+
"learning_rate": 8.099982820821166e-07,
|
| 345 |
+
"loss": 0.8334,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.946969696969697,
|
| 350 |
+
"grad_norm": 57.379234313964844,
|
| 351 |
+
"learning_rate": 5.952585466414706e-07,
|
| 352 |
+
"loss": 0.7609,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.966295609152752,
|
| 357 |
+
"grad_norm": 48.525848388671875,
|
| 358 |
+
"learning_rate": 3.8051881120082463e-07,
|
| 359 |
+
"loss": 0.8165,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.985621521335807,
|
| 364 |
+
"grad_norm": 29.62494468688965,
|
| 365 |
+
"learning_rate": 1.6577907576017866e-07,
|
| 366 |
+
"loss": 0.8133,
|
| 367 |
+
"step": 25500
|
| 368 |
+
}
|
| 369 |
+
],
|
| 370 |
+
"logging_steps": 500,
|
| 371 |
+
"max_steps": 25872,
|
| 372 |
+
"num_input_tokens_seen": 0,
|
| 373 |
+
"num_train_epochs": 1,
|
| 374 |
+
"save_steps": 500,
|
| 375 |
+
"stateful_callbacks": {
|
| 376 |
+
"TrainerControl": {
|
| 377 |
+
"args": {
|
| 378 |
+
"should_epoch_stop": false,
|
| 379 |
+
"should_evaluate": false,
|
| 380 |
+
"should_log": false,
|
| 381 |
+
"should_save": true,
|
| 382 |
+
"should_training_stop": true
|
| 383 |
+
},
|
| 384 |
+
"attributes": {}
|
| 385 |
+
}
|
| 386 |
+
},
|
| 387 |
+
"total_flos": 0.0,
|
| 388 |
+
"train_batch_size": 1,
|
| 389 |
+
"trial_name": null,
|
| 390 |
+
"trial_params": null
|
| 391 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73c1f30f323aa59c23f2981c85bec2a3ebf7eb3726e4d4b41068ac61e277a061
|
| 3 |
+
size 5688
|