Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +42 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- trainer_state.json +572 -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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "D1A",
|
| 15 |
+
"1": "D2H",
|
| 16 |
+
"2": "D3E",
|
| 17 |
+
"3": "D4C",
|
| 18 |
+
"4": "D5G"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"D1A": 0,
|
| 24 |
+
"D2H": 1,
|
| 25 |
+
"D3E": 2,
|
| 26 |
+
"D4C": 3,
|
| 27 |
+
"D5G": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-05,
|
| 30 |
+
"max_position_embeddings": 514,
|
| 31 |
+
"model_type": "xlm-roberta",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 1,
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"problem_type": "single_label_classification",
|
| 38 |
+
"transformers_version": "4.56.1",
|
| 39 |
+
"type_vocab_size": 1,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 250002
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abc003d1150f7fcfa540fb42a23588c62c14f018f4e07b27f3a3a40903499ab
|
| 3 |
+
size 1112214236
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:409ca2b028d4dbb3c686b70bd8f7bed484ff699da24d6f88c305d10847aa751e
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf293f40d363d10e0d82770ce9c031a17d2c0e600e075bddc4172841530cca4
|
| 3 |
+
size 1465
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
|
| 3 |
+
size 17082734
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,572 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 6000,
|
| 3 |
+
"best_metric": 0.8871330073620233,
|
| 4 |
+
"best_model_checkpoint": "/home/rupak/Desktop/Topic-Modeling /topic modeling 25k/checkpoint/xlm-r-25k-2e5-256-16-10/checkpoint-6000",
|
| 5 |
+
"epoch": 4.7964814074370254,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 6000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0007996801279488205,
|
| 14 |
+
"grad_norm": 4.53638219833374,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.6879,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.07996801279488205,
|
| 21 |
+
"grad_norm": 2.835871934890747,
|
| 22 |
+
"learning_rate": 1.5840000000000002e-06,
|
| 23 |
+
"loss": 1.6188,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1599360255897641,
|
| 28 |
+
"grad_norm": 10.777544021606445,
|
| 29 |
+
"learning_rate": 3.1840000000000003e-06,
|
| 30 |
+
"loss": 1.6119,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.23990403838464613,
|
| 35 |
+
"grad_norm": 12.409767150878906,
|
| 36 |
+
"learning_rate": 4.784e-06,
|
| 37 |
+
"loss": 1.2151,
|
| 38 |
+
"step": 300
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3198720511795282,
|
| 42 |
+
"grad_norm": 31.977880477905273,
|
| 43 |
+
"learning_rate": 6.384e-06,
|
| 44 |
+
"loss": 0.7791,
|
| 45 |
+
"step": 400
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.39984006397441024,
|
| 49 |
+
"grad_norm": 21.095924377441406,
|
| 50 |
+
"learning_rate": 7.984e-06,
|
| 51 |
+
"loss": 0.6522,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.47980807676929227,
|
| 56 |
+
"grad_norm": 42.61677932739258,
|
| 57 |
+
"learning_rate": 9.584000000000002e-06,
|
| 58 |
+
"loss": 0.5709,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5597760895641744,
|
| 63 |
+
"grad_norm": 12.979878425598145,
|
| 64 |
+
"learning_rate": 1.1184000000000002e-05,
|
| 65 |
+
"loss": 0.5023,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6397441023590564,
|
| 70 |
+
"grad_norm": 13.918512344360352,
|
| 71 |
+
"learning_rate": 1.2784000000000002e-05,
|
| 72 |
+
"loss": 0.5145,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7197121151539384,
|
| 77 |
+
"grad_norm": 5.735707759857178,
|
| 78 |
+
"learning_rate": 1.4384e-05,
|
| 79 |
+
"loss": 0.5147,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7996801279488205,
|
| 84 |
+
"grad_norm": 19.905000686645508,
|
| 85 |
+
"learning_rate": 1.5984e-05,
|
| 86 |
+
"loss": 0.479,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7996801279488205,
|
| 91 |
+
"eval_accuracy": 0.8600559776089565,
|
| 92 |
+
"eval_auroc_macro": 0.9697997005619113,
|
| 93 |
+
"eval_auroc_weighted": 0.9693976210021283,
|
| 94 |
+
"eval_f1_macro": 0.8609883608675034,
|
| 95 |
+
"eval_f1_weighted": 0.8598453926609552,
|
| 96 |
+
"eval_loss": 0.4712389409542084,
|
| 97 |
+
"eval_precision_macro": 0.8631139602509299,
|
| 98 |
+
"eval_precision_weighted": 0.8628361263926728,
|
| 99 |
+
"eval_recall_macro": 0.8621203563951813,
|
| 100 |
+
"eval_recall_weighted": 0.8600559776089565,
|
| 101 |
+
"eval_runtime": 7.4659,
|
| 102 |
+
"eval_samples_per_second": 334.989,
|
| 103 |
+
"eval_steps_per_second": 41.924,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.8796481407437026,
|
| 108 |
+
"grad_norm": 41.90662384033203,
|
| 109 |
+
"learning_rate": 1.7584e-05,
|
| 110 |
+
"loss": 0.4544,
|
| 111 |
+
"step": 1100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.9596161535385845,
|
| 115 |
+
"grad_norm": 21.125547409057617,
|
| 116 |
+
"learning_rate": 1.9184e-05,
|
| 117 |
+
"loss": 0.4281,
|
| 118 |
+
"step": 1200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.0391843262694922,
|
| 122 |
+
"grad_norm": 28.119949340820312,
|
| 123 |
+
"learning_rate": 1.991296625222025e-05,
|
| 124 |
+
"loss": 0.4532,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.1191523390643743,
|
| 129 |
+
"grad_norm": 12.584921836853027,
|
| 130 |
+
"learning_rate": 1.9735346358792185e-05,
|
| 131 |
+
"loss": 0.4224,
|
| 132 |
+
"step": 1400
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.1991203518592564,
|
| 136 |
+
"grad_norm": 9.214597702026367,
|
| 137 |
+
"learning_rate": 1.955772646536412e-05,
|
| 138 |
+
"loss": 0.4,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.2790883646541382,
|
| 143 |
+
"grad_norm": 11.22278881072998,
|
| 144 |
+
"learning_rate": 1.938010657193606e-05,
|
| 145 |
+
"loss": 0.4031,
|
| 146 |
+
"step": 1600
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.3590563774490203,
|
| 150 |
+
"grad_norm": 10.408547401428223,
|
| 151 |
+
"learning_rate": 1.9202486678507993e-05,
|
| 152 |
+
"loss": 0.3869,
|
| 153 |
+
"step": 1700
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.4390243902439024,
|
| 157 |
+
"grad_norm": 3.784024477005005,
|
| 158 |
+
"learning_rate": 1.902486678507993e-05,
|
| 159 |
+
"loss": 0.4519,
|
| 160 |
+
"step": 1800
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.5189924030387845,
|
| 164 |
+
"grad_norm": 39.47583770751953,
|
| 165 |
+
"learning_rate": 1.884724689165187e-05,
|
| 166 |
+
"loss": 0.4135,
|
| 167 |
+
"step": 1900
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.5989604158336665,
|
| 171 |
+
"grad_norm": 31.41134262084961,
|
| 172 |
+
"learning_rate": 1.86696269982238e-05,
|
| 173 |
+
"loss": 0.3946,
|
| 174 |
+
"step": 2000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.5989604158336665,
|
| 178 |
+
"eval_accuracy": 0.8692522990803678,
|
| 179 |
+
"eval_auroc_macro": 0.9771314037560426,
|
| 180 |
+
"eval_auroc_weighted": 0.976669092429264,
|
| 181 |
+
"eval_f1_macro": 0.8689438661562177,
|
| 182 |
+
"eval_f1_weighted": 0.8676413311378186,
|
| 183 |
+
"eval_loss": 0.4619748890399933,
|
| 184 |
+
"eval_precision_macro": 0.8703728530490539,
|
| 185 |
+
"eval_precision_weighted": 0.8706160950869455,
|
| 186 |
+
"eval_recall_macro": 0.8720003755655708,
|
| 187 |
+
"eval_recall_weighted": 0.8692522990803678,
|
| 188 |
+
"eval_runtime": 6.9001,
|
| 189 |
+
"eval_samples_per_second": 362.46,
|
| 190 |
+
"eval_steps_per_second": 45.362,
|
| 191 |
+
"step": 2000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.6789284286285486,
|
| 195 |
+
"grad_norm": 2.4029605388641357,
|
| 196 |
+
"learning_rate": 1.849200710479574e-05,
|
| 197 |
+
"loss": 0.3931,
|
| 198 |
+
"step": 2100
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.7588964414234307,
|
| 202 |
+
"grad_norm": 17.38362693786621,
|
| 203 |
+
"learning_rate": 1.8314387211367673e-05,
|
| 204 |
+
"loss": 0.3962,
|
| 205 |
+
"step": 2200
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.8388644542183128,
|
| 209 |
+
"grad_norm": 18.689165115356445,
|
| 210 |
+
"learning_rate": 1.813676731793961e-05,
|
| 211 |
+
"loss": 0.365,
|
| 212 |
+
"step": 2300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.9188324670131949,
|
| 216 |
+
"grad_norm": 10.522760391235352,
|
| 217 |
+
"learning_rate": 1.795914742451155e-05,
|
| 218 |
+
"loss": 0.3506,
|
| 219 |
+
"step": 2400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.9988004798080767,
|
| 223 |
+
"grad_norm": 25.250308990478516,
|
| 224 |
+
"learning_rate": 1.778152753108348e-05,
|
| 225 |
+
"loss": 0.4575,
|
| 226 |
+
"step": 2500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.0783686525389844,
|
| 230 |
+
"grad_norm": 19.280771255493164,
|
| 231 |
+
"learning_rate": 1.760390763765542e-05,
|
| 232 |
+
"loss": 0.3698,
|
| 233 |
+
"step": 2600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.1583366653338665,
|
| 237 |
+
"grad_norm": 5.396891117095947,
|
| 238 |
+
"learning_rate": 1.7426287744227356e-05,
|
| 239 |
+
"loss": 0.2822,
|
| 240 |
+
"step": 2700
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.2383046781287486,
|
| 244 |
+
"grad_norm": 9.906753540039062,
|
| 245 |
+
"learning_rate": 1.724866785079929e-05,
|
| 246 |
+
"loss": 0.2936,
|
| 247 |
+
"step": 2800
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.3182726909236306,
|
| 251 |
+
"grad_norm": 29.26998519897461,
|
| 252 |
+
"learning_rate": 1.7071047957371228e-05,
|
| 253 |
+
"loss": 0.3453,
|
| 254 |
+
"step": 2900
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.3982407037185127,
|
| 258 |
+
"grad_norm": 18.436208724975586,
|
| 259 |
+
"learning_rate": 1.6893428063943164e-05,
|
| 260 |
+
"loss": 0.3204,
|
| 261 |
+
"step": 3000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.3982407037185127,
|
| 265 |
+
"eval_accuracy": 0.8740503798480608,
|
| 266 |
+
"eval_auroc_macro": 0.9792758464373478,
|
| 267 |
+
"eval_auroc_weighted": 0.9788870577881947,
|
| 268 |
+
"eval_f1_macro": 0.8741945993115099,
|
| 269 |
+
"eval_f1_weighted": 0.872931355571633,
|
| 270 |
+
"eval_loss": 0.45468512177467346,
|
| 271 |
+
"eval_precision_macro": 0.8741535901174557,
|
| 272 |
+
"eval_precision_weighted": 0.8737552557579643,
|
| 273 |
+
"eval_recall_macro": 0.8761328388099946,
|
| 274 |
+
"eval_recall_weighted": 0.8740503798480608,
|
| 275 |
+
"eval_runtime": 6.8511,
|
| 276 |
+
"eval_samples_per_second": 365.049,
|
| 277 |
+
"eval_steps_per_second": 45.686,
|
| 278 |
+
"step": 3000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.478208716513395,
|
| 282 |
+
"grad_norm": 11.020326614379883,
|
| 283 |
+
"learning_rate": 1.67158081705151e-05,
|
| 284 |
+
"loss": 0.3072,
|
| 285 |
+
"step": 3100
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.5581767293082764,
|
| 289 |
+
"grad_norm": 8.49850845336914,
|
| 290 |
+
"learning_rate": 1.6538188277087036e-05,
|
| 291 |
+
"loss": 0.3163,
|
| 292 |
+
"step": 3200
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.638144742103159,
|
| 296 |
+
"grad_norm": 17.164398193359375,
|
| 297 |
+
"learning_rate": 1.636056838365897e-05,
|
| 298 |
+
"loss": 0.3255,
|
| 299 |
+
"step": 3300
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.7181127548980406,
|
| 303 |
+
"grad_norm": 7.5612077713012695,
|
| 304 |
+
"learning_rate": 1.6182948490230908e-05,
|
| 305 |
+
"loss": 0.3249,
|
| 306 |
+
"step": 3400
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.7980807676929227,
|
| 310 |
+
"grad_norm": 25.795366287231445,
|
| 311 |
+
"learning_rate": 1.6005328596802844e-05,
|
| 312 |
+
"loss": 0.3305,
|
| 313 |
+
"step": 3500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.8780487804878048,
|
| 317 |
+
"grad_norm": 32.6719970703125,
|
| 318 |
+
"learning_rate": 1.582770870337478e-05,
|
| 319 |
+
"loss": 0.3116,
|
| 320 |
+
"step": 3600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.958016793282687,
|
| 324 |
+
"grad_norm": 9.986326217651367,
|
| 325 |
+
"learning_rate": 1.5650088809946716e-05,
|
| 326 |
+
"loss": 0.2978,
|
| 327 |
+
"step": 3700
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.0375849660135947,
|
| 331 |
+
"grad_norm": 13.737031936645508,
|
| 332 |
+
"learning_rate": 1.5472468916518652e-05,
|
| 333 |
+
"loss": 0.2762,
|
| 334 |
+
"step": 3800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 3.117552978808477,
|
| 338 |
+
"grad_norm": 46.34874725341797,
|
| 339 |
+
"learning_rate": 1.5294849023090588e-05,
|
| 340 |
+
"loss": 0.2792,
|
| 341 |
+
"step": 3900
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.1975209916033585,
|
| 345 |
+
"grad_norm": 10.898789405822754,
|
| 346 |
+
"learning_rate": 1.5117229129662522e-05,
|
| 347 |
+
"loss": 0.2284,
|
| 348 |
+
"step": 4000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.1975209916033585,
|
| 352 |
+
"eval_accuracy": 0.8848460615753698,
|
| 353 |
+
"eval_auroc_macro": 0.9814776143689887,
|
| 354 |
+
"eval_auroc_weighted": 0.9811501779795945,
|
| 355 |
+
"eval_f1_macro": 0.8852410917462988,
|
| 356 |
+
"eval_f1_weighted": 0.884236665097445,
|
| 357 |
+
"eval_loss": 0.4859422445297241,
|
| 358 |
+
"eval_precision_macro": 0.885234053430883,
|
| 359 |
+
"eval_precision_weighted": 0.8851060401022259,
|
| 360 |
+
"eval_recall_macro": 0.8867084554148464,
|
| 361 |
+
"eval_recall_weighted": 0.8848460615753698,
|
| 362 |
+
"eval_runtime": 6.8545,
|
| 363 |
+
"eval_samples_per_second": 364.87,
|
| 364 |
+
"eval_steps_per_second": 45.663,
|
| 365 |
+
"step": 4000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.2774890043982405,
|
| 369 |
+
"grad_norm": 10.87129020690918,
|
| 370 |
+
"learning_rate": 1.493960923623446e-05,
|
| 371 |
+
"loss": 0.2376,
|
| 372 |
+
"step": 4100
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.3574570171931226,
|
| 376 |
+
"grad_norm": 7.824963092803955,
|
| 377 |
+
"learning_rate": 1.4761989342806396e-05,
|
| 378 |
+
"loss": 0.243,
|
| 379 |
+
"step": 4200
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.4374250299880047,
|
| 383 |
+
"grad_norm": 19.788555145263672,
|
| 384 |
+
"learning_rate": 1.458436944937833e-05,
|
| 385 |
+
"loss": 0.2927,
|
| 386 |
+
"step": 4300
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.517393042782887,
|
| 390 |
+
"grad_norm": 19.342580795288086,
|
| 391 |
+
"learning_rate": 1.4406749555950268e-05,
|
| 392 |
+
"loss": 0.2673,
|
| 393 |
+
"step": 4400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.597361055577769,
|
| 397 |
+
"grad_norm": 1.4744329452514648,
|
| 398 |
+
"learning_rate": 1.4229129662522204e-05,
|
| 399 |
+
"loss": 0.1985,
|
| 400 |
+
"step": 4500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.677329068372651,
|
| 404 |
+
"grad_norm": 19.05389976501465,
|
| 405 |
+
"learning_rate": 1.4051509769094141e-05,
|
| 406 |
+
"loss": 0.2826,
|
| 407 |
+
"step": 4600
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.757297081167533,
|
| 411 |
+
"grad_norm": 38.120121002197266,
|
| 412 |
+
"learning_rate": 1.3873889875666075e-05,
|
| 413 |
+
"loss": 0.2567,
|
| 414 |
+
"step": 4700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.837265093962415,
|
| 418 |
+
"grad_norm": 38.54651641845703,
|
| 419 |
+
"learning_rate": 1.3696269982238011e-05,
|
| 420 |
+
"loss": 0.3233,
|
| 421 |
+
"step": 4800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.917233106757297,
|
| 425 |
+
"grad_norm": 7.073267936706543,
|
| 426 |
+
"learning_rate": 1.3518650088809947e-05,
|
| 427 |
+
"loss": 0.2253,
|
| 428 |
+
"step": 4900
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.9972011195521793,
|
| 432 |
+
"grad_norm": 28.43503761291504,
|
| 433 |
+
"learning_rate": 1.3341030195381883e-05,
|
| 434 |
+
"loss": 0.2922,
|
| 435 |
+
"step": 5000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.9972011195521793,
|
| 439 |
+
"eval_accuracy": 0.8692522990803678,
|
| 440 |
+
"eval_auroc_macro": 0.9772039806373872,
|
| 441 |
+
"eval_auroc_weighted": 0.9767263471937441,
|
| 442 |
+
"eval_f1_macro": 0.8687049494752337,
|
| 443 |
+
"eval_f1_weighted": 0.8672298347929932,
|
| 444 |
+
"eval_loss": 0.5068673491477966,
|
| 445 |
+
"eval_precision_macro": 0.8714207501064626,
|
| 446 |
+
"eval_precision_weighted": 0.8717661851493683,
|
| 447 |
+
"eval_recall_macro": 0.8724193433641065,
|
| 448 |
+
"eval_recall_weighted": 0.8692522990803678,
|
| 449 |
+
"eval_runtime": 7.1301,
|
| 450 |
+
"eval_samples_per_second": 350.766,
|
| 451 |
+
"eval_steps_per_second": 43.898,
|
| 452 |
+
"step": 5000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.076769292283087,
|
| 456 |
+
"grad_norm": 88.04476165771484,
|
| 457 |
+
"learning_rate": 1.3163410301953821e-05,
|
| 458 |
+
"loss": 0.1666,
|
| 459 |
+
"step": 5100
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.156737305077969,
|
| 463 |
+
"grad_norm": 8.783529281616211,
|
| 464 |
+
"learning_rate": 1.2985790408525755e-05,
|
| 465 |
+
"loss": 0.2068,
|
| 466 |
+
"step": 5200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 4.23670531787285,
|
| 470 |
+
"grad_norm": 4.993801116943359,
|
| 471 |
+
"learning_rate": 1.2808170515097691e-05,
|
| 472 |
+
"loss": 0.2067,
|
| 473 |
+
"step": 5300
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.316673330667733,
|
| 477 |
+
"grad_norm": 32.33308410644531,
|
| 478 |
+
"learning_rate": 1.2630550621669629e-05,
|
| 479 |
+
"loss": 0.2222,
|
| 480 |
+
"step": 5400
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.396641343462615,
|
| 484 |
+
"grad_norm": 1.1174397468566895,
|
| 485 |
+
"learning_rate": 1.2452930728241563e-05,
|
| 486 |
+
"loss": 0.216,
|
| 487 |
+
"step": 5500
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.476609356257497,
|
| 491 |
+
"grad_norm": 3.2966408729553223,
|
| 492 |
+
"learning_rate": 1.22753108348135e-05,
|
| 493 |
+
"loss": 0.1728,
|
| 494 |
+
"step": 5600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.556577369052379,
|
| 498 |
+
"grad_norm": 23.643796920776367,
|
| 499 |
+
"learning_rate": 1.2097690941385437e-05,
|
| 500 |
+
"loss": 0.2034,
|
| 501 |
+
"step": 5700
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.636545381847261,
|
| 505 |
+
"grad_norm": 40.708675384521484,
|
| 506 |
+
"learning_rate": 1.1920071047957371e-05,
|
| 507 |
+
"loss": 0.1959,
|
| 508 |
+
"step": 5800
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.716513394642143,
|
| 512 |
+
"grad_norm": 8.088835716247559,
|
| 513 |
+
"learning_rate": 1.1742451154529309e-05,
|
| 514 |
+
"loss": 0.2288,
|
| 515 |
+
"step": 5900
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.7964814074370254,
|
| 519 |
+
"grad_norm": 28.324237823486328,
|
| 520 |
+
"learning_rate": 1.1564831261101243e-05,
|
| 521 |
+
"loss": 0.1829,
|
| 522 |
+
"step": 6000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.7964814074370254,
|
| 526 |
+
"eval_accuracy": 0.8876449420231908,
|
| 527 |
+
"eval_auroc_macro": 0.9753087930207407,
|
| 528 |
+
"eval_auroc_weighted": 0.9748734596563122,
|
| 529 |
+
"eval_f1_macro": 0.8882520006466459,
|
| 530 |
+
"eval_f1_weighted": 0.8871330073620233,
|
| 531 |
+
"eval_loss": 0.5317224264144897,
|
| 532 |
+
"eval_precision_macro": 0.8881729106348502,
|
| 533 |
+
"eval_precision_weighted": 0.8878156337143654,
|
| 534 |
+
"eval_recall_macro": 0.8895224186044739,
|
| 535 |
+
"eval_recall_weighted": 0.8876449420231908,
|
| 536 |
+
"eval_runtime": 6.8194,
|
| 537 |
+
"eval_samples_per_second": 366.745,
|
| 538 |
+
"eval_steps_per_second": 45.898,
|
| 539 |
+
"step": 6000
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"logging_steps": 100,
|
| 543 |
+
"max_steps": 12510,
|
| 544 |
+
"num_input_tokens_seen": 0,
|
| 545 |
+
"num_train_epochs": 10,
|
| 546 |
+
"save_steps": 1000,
|
| 547 |
+
"stateful_callbacks": {
|
| 548 |
+
"EarlyStoppingCallback": {
|
| 549 |
+
"args": {
|
| 550 |
+
"early_stopping_patience": 15,
|
| 551 |
+
"early_stopping_threshold": 0.0
|
| 552 |
+
},
|
| 553 |
+
"attributes": {
|
| 554 |
+
"early_stopping_patience_counter": 0
|
| 555 |
+
}
|
| 556 |
+
},
|
| 557 |
+
"TrainerControl": {
|
| 558 |
+
"args": {
|
| 559 |
+
"should_epoch_stop": false,
|
| 560 |
+
"should_evaluate": false,
|
| 561 |
+
"should_log": false,
|
| 562 |
+
"should_save": true,
|
| 563 |
+
"should_training_stop": false
|
| 564 |
+
},
|
| 565 |
+
"attributes": {}
|
| 566 |
+
}
|
| 567 |
+
},
|
| 568 |
+
"total_flos": 1947209924525808.0,
|
| 569 |
+
"train_batch_size": 8,
|
| 570 |
+
"trial_name": null,
|
| 571 |
+
"trial_params": null
|
| 572 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:349caa801f6c691f38274f1ed5b8ddfd4b4cc40f1587399ea7b664b73d3e3abf
|
| 3 |
+
size 5841
|