Upload folder using huggingface_hub
Browse files- config.json +28 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +555 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 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 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "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 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9483120127998b68d7d54e784e70da10247f3a5ae30a9e0a290231f95f6c350
|
| 3 |
+
size 498612824
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bae8189f959117e0b231736b3bf0500355485499384baed69f98d1446afba6d
|
| 3 |
+
size 997348747
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbbd94508f58871476757381a84e67b19b54c13ad44f83fcdbaf28ef1d1c3c6b
|
| 3 |
+
size 14709
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6577149420304ede87aa59bf995d3982b1e1dce8c799a97d829347f2ac691371
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 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": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,555 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2049,
|
| 3 |
+
"best_metric": 0.6537335285505125,
|
| 4 |
+
"best_model_checkpoint": "./saved_models/checkpoint-2049",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3415,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07320644216691069,
|
| 14 |
+
"grad_norm": 1.8367172479629517,
|
| 15 |
+
"learning_rate": 1.971303074670571e-05,
|
| 16 |
+
"loss": 0.6893,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.14641288433382138,
|
| 21 |
+
"grad_norm": 2.717869758605957,
|
| 22 |
+
"learning_rate": 1.942020497803807e-05,
|
| 23 |
+
"loss": 0.6873,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.21961932650073207,
|
| 28 |
+
"grad_norm": 2.075798273086548,
|
| 29 |
+
"learning_rate": 1.9127379209370426e-05,
|
| 30 |
+
"loss": 0.6654,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.29282576866764276,
|
| 35 |
+
"grad_norm": 2.1151416301727295,
|
| 36 |
+
"learning_rate": 1.8834553440702785e-05,
|
| 37 |
+
"loss": 0.6675,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36603221083455345,
|
| 42 |
+
"grad_norm": 5.988334655761719,
|
| 43 |
+
"learning_rate": 1.854172767203514e-05,
|
| 44 |
+
"loss": 0.6523,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43923865300146414,
|
| 49 |
+
"grad_norm": 3.652282238006592,
|
| 50 |
+
"learning_rate": 1.8248901903367496e-05,
|
| 51 |
+
"loss": 0.6479,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.5124450951683748,
|
| 56 |
+
"grad_norm": 10.128896713256836,
|
| 57 |
+
"learning_rate": 1.7956076134699855e-05,
|
| 58 |
+
"loss": 0.6526,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5856515373352855,
|
| 63 |
+
"grad_norm": 1.4224460124969482,
|
| 64 |
+
"learning_rate": 1.766325036603221e-05,
|
| 65 |
+
"loss": 0.6529,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6588579795021962,
|
| 70 |
+
"grad_norm": 3.7824015617370605,
|
| 71 |
+
"learning_rate": 1.737042459736457e-05,
|
| 72 |
+
"loss": 0.65,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7320644216691069,
|
| 77 |
+
"grad_norm": 2.6415672302246094,
|
| 78 |
+
"learning_rate": 1.7077598828696925e-05,
|
| 79 |
+
"loss": 0.6407,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.8052708638360175,
|
| 84 |
+
"grad_norm": 1.3568845987319946,
|
| 85 |
+
"learning_rate": 1.6784773060029284e-05,
|
| 86 |
+
"loss": 0.661,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8784773060029283,
|
| 91 |
+
"grad_norm": 2.8408727645874023,
|
| 92 |
+
"learning_rate": 1.649194729136164e-05,
|
| 93 |
+
"loss": 0.6468,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.9516837481698389,
|
| 98 |
+
"grad_norm": 1.2629034519195557,
|
| 99 |
+
"learning_rate": 1.6199121522694e-05,
|
| 100 |
+
"loss": 0.634,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0,
|
| 105 |
+
"eval_accuracy": 0.6255490483162518,
|
| 106 |
+
"eval_loss": 0.6187466979026794,
|
| 107 |
+
"eval_runtime": 13.089,
|
| 108 |
+
"eval_samples_per_second": 208.726,
|
| 109 |
+
"eval_steps_per_second": 3.285,
|
| 110 |
+
"step": 683
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0248901903367496,
|
| 114 |
+
"grad_norm": 2.3205177783966064,
|
| 115 |
+
"learning_rate": 1.5906295754026355e-05,
|
| 116 |
+
"loss": 0.6254,
|
| 117 |
+
"step": 700
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0980966325036603,
|
| 121 |
+
"grad_norm": 2.2244133949279785,
|
| 122 |
+
"learning_rate": 1.5613469985358714e-05,
|
| 123 |
+
"loss": 0.6299,
|
| 124 |
+
"step": 750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.171303074670571,
|
| 128 |
+
"grad_norm": 2.3779757022857666,
|
| 129 |
+
"learning_rate": 1.532064421669107e-05,
|
| 130 |
+
"loss": 0.6285,
|
| 131 |
+
"step": 800
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.2445095168374818,
|
| 135 |
+
"grad_norm": 1.8427557945251465,
|
| 136 |
+
"learning_rate": 1.5027818448023428e-05,
|
| 137 |
+
"loss": 0.61,
|
| 138 |
+
"step": 850
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.3177159590043923,
|
| 142 |
+
"grad_norm": 10.884477615356445,
|
| 143 |
+
"learning_rate": 1.4734992679355784e-05,
|
| 144 |
+
"loss": 0.6175,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.390922401171303,
|
| 149 |
+
"grad_norm": 5.921830177307129,
|
| 150 |
+
"learning_rate": 1.4442166910688143e-05,
|
| 151 |
+
"loss": 0.61,
|
| 152 |
+
"step": 950
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.4641288433382138,
|
| 156 |
+
"grad_norm": 5.03695821762085,
|
| 157 |
+
"learning_rate": 1.4149341142020499e-05,
|
| 158 |
+
"loss": 0.6033,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.5373352855051245,
|
| 163 |
+
"grad_norm": 2.7754528522491455,
|
| 164 |
+
"learning_rate": 1.3856515373352856e-05,
|
| 165 |
+
"loss": 0.6001,
|
| 166 |
+
"step": 1050
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.610541727672035,
|
| 170 |
+
"grad_norm": 3.685950517654419,
|
| 171 |
+
"learning_rate": 1.3563689604685213e-05,
|
| 172 |
+
"loss": 0.6234,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.6837481698389458,
|
| 177 |
+
"grad_norm": 3.515249252319336,
|
| 178 |
+
"learning_rate": 1.327086383601757e-05,
|
| 179 |
+
"loss": 0.6111,
|
| 180 |
+
"step": 1150
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.7569546120058566,
|
| 184 |
+
"grad_norm": 3.3894221782684326,
|
| 185 |
+
"learning_rate": 1.2978038067349928e-05,
|
| 186 |
+
"loss": 0.5906,
|
| 187 |
+
"step": 1200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.830161054172767,
|
| 191 |
+
"grad_norm": 4.961050510406494,
|
| 192 |
+
"learning_rate": 1.2685212298682286e-05,
|
| 193 |
+
"loss": 0.614,
|
| 194 |
+
"step": 1250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.903367496339678,
|
| 198 |
+
"grad_norm": 2.3843491077423096,
|
| 199 |
+
"learning_rate": 1.2392386530014641e-05,
|
| 200 |
+
"loss": 0.6117,
|
| 201 |
+
"step": 1300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.9765739385065886,
|
| 205 |
+
"grad_norm": 2.979031801223755,
|
| 206 |
+
"learning_rate": 1.2099560761347e-05,
|
| 207 |
+
"loss": 0.5859,
|
| 208 |
+
"step": 1350
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.0,
|
| 212 |
+
"eval_accuracy": 0.6361639824304539,
|
| 213 |
+
"eval_loss": 0.5908383131027222,
|
| 214 |
+
"eval_runtime": 12.8649,
|
| 215 |
+
"eval_samples_per_second": 212.361,
|
| 216 |
+
"eval_steps_per_second": 3.342,
|
| 217 |
+
"step": 1366
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.049780380673499,
|
| 221 |
+
"grad_norm": 5.897040367126465,
|
| 222 |
+
"learning_rate": 1.1806734992679356e-05,
|
| 223 |
+
"loss": 0.573,
|
| 224 |
+
"step": 1400
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.12298682284041,
|
| 228 |
+
"grad_norm": 5.25750207901001,
|
| 229 |
+
"learning_rate": 1.1513909224011715e-05,
|
| 230 |
+
"loss": 0.5455,
|
| 231 |
+
"step": 1450
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.1961932650073206,
|
| 235 |
+
"grad_norm": 14.578705787658691,
|
| 236 |
+
"learning_rate": 1.122108345534407e-05,
|
| 237 |
+
"loss": 0.5673,
|
| 238 |
+
"step": 1500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.269399707174231,
|
| 242 |
+
"grad_norm": 3.079087018966675,
|
| 243 |
+
"learning_rate": 1.092825768667643e-05,
|
| 244 |
+
"loss": 0.5545,
|
| 245 |
+
"step": 1550
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.342606149341142,
|
| 249 |
+
"grad_norm": 3.9325766563415527,
|
| 250 |
+
"learning_rate": 1.0635431918008785e-05,
|
| 251 |
+
"loss": 0.5688,
|
| 252 |
+
"step": 1600
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.4158125915080526,
|
| 256 |
+
"grad_norm": 5.2294087409973145,
|
| 257 |
+
"learning_rate": 1.0342606149341143e-05,
|
| 258 |
+
"loss": 0.5614,
|
| 259 |
+
"step": 1650
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.4890190336749636,
|
| 263 |
+
"grad_norm": 5.683165073394775,
|
| 264 |
+
"learning_rate": 1.00497803806735e-05,
|
| 265 |
+
"loss": 0.5549,
|
| 266 |
+
"step": 1700
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.562225475841874,
|
| 270 |
+
"grad_norm": 4.106119155883789,
|
| 271 |
+
"learning_rate": 9.756954612005857e-06,
|
| 272 |
+
"loss": 0.5565,
|
| 273 |
+
"step": 1750
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.6354319180087846,
|
| 277 |
+
"grad_norm": 3.8661065101623535,
|
| 278 |
+
"learning_rate": 9.464128843338215e-06,
|
| 279 |
+
"loss": 0.5489,
|
| 280 |
+
"step": 1800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.7086383601756956,
|
| 284 |
+
"grad_norm": 12.783368110656738,
|
| 285 |
+
"learning_rate": 9.171303074670572e-06,
|
| 286 |
+
"loss": 0.5472,
|
| 287 |
+
"step": 1850
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.781844802342606,
|
| 291 |
+
"grad_norm": 17.30908966064453,
|
| 292 |
+
"learning_rate": 8.87847730600293e-06,
|
| 293 |
+
"loss": 0.5696,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.855051244509517,
|
| 298 |
+
"grad_norm": 13.78253173828125,
|
| 299 |
+
"learning_rate": 8.585651537335287e-06,
|
| 300 |
+
"loss": 0.5289,
|
| 301 |
+
"step": 1950
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.9282576866764276,
|
| 305 |
+
"grad_norm": 11.748068809509277,
|
| 306 |
+
"learning_rate": 8.292825768667644e-06,
|
| 307 |
+
"loss": 0.5487,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.0,
|
| 312 |
+
"eval_accuracy": 0.6537335285505125,
|
| 313 |
+
"eval_loss": 0.6090347170829773,
|
| 314 |
+
"eval_runtime": 13.1904,
|
| 315 |
+
"eval_samples_per_second": 207.12,
|
| 316 |
+
"eval_steps_per_second": 3.26,
|
| 317 |
+
"step": 2049
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.001464128843338,
|
| 321 |
+
"grad_norm": 4.5922698974609375,
|
| 322 |
+
"learning_rate": 8.000000000000001e-06,
|
| 323 |
+
"loss": 0.5447,
|
| 324 |
+
"step": 2050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.074670571010249,
|
| 328 |
+
"grad_norm": 5.039747714996338,
|
| 329 |
+
"learning_rate": 7.707174231332359e-06,
|
| 330 |
+
"loss": 0.5025,
|
| 331 |
+
"step": 2100
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.1478770131771596,
|
| 335 |
+
"grad_norm": 7.7539825439453125,
|
| 336 |
+
"learning_rate": 7.414348462664715e-06,
|
| 337 |
+
"loss": 0.4964,
|
| 338 |
+
"step": 2150
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.22108345534407,
|
| 342 |
+
"grad_norm": 7.477388381958008,
|
| 343 |
+
"learning_rate": 7.1215226939970725e-06,
|
| 344 |
+
"loss": 0.5053,
|
| 345 |
+
"step": 2200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.294289897510981,
|
| 349 |
+
"grad_norm": 11.205092430114746,
|
| 350 |
+
"learning_rate": 6.82869692532943e-06,
|
| 351 |
+
"loss": 0.487,
|
| 352 |
+
"step": 2250
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 3.3674963396778916,
|
| 356 |
+
"grad_norm": 5.962555885314941,
|
| 357 |
+
"learning_rate": 6.535871156661787e-06,
|
| 358 |
+
"loss": 0.4947,
|
| 359 |
+
"step": 2300
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.440702781844802,
|
| 363 |
+
"grad_norm": 9.716086387634277,
|
| 364 |
+
"learning_rate": 6.2430453879941446e-06,
|
| 365 |
+
"loss": 0.5043,
|
| 366 |
+
"step": 2350
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.513909224011713,
|
| 370 |
+
"grad_norm": 7.83236026763916,
|
| 371 |
+
"learning_rate": 5.950219619326502e-06,
|
| 372 |
+
"loss": 0.5083,
|
| 373 |
+
"step": 2400
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.5871156661786237,
|
| 377 |
+
"grad_norm": 7.700263500213623,
|
| 378 |
+
"learning_rate": 5.657393850658858e-06,
|
| 379 |
+
"loss": 0.5099,
|
| 380 |
+
"step": 2450
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.660322108345534,
|
| 384 |
+
"grad_norm": 6.1209540367126465,
|
| 385 |
+
"learning_rate": 5.364568081991216e-06,
|
| 386 |
+
"loss": 0.5031,
|
| 387 |
+
"step": 2500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.733528550512445,
|
| 391 |
+
"grad_norm": 6.6275858879089355,
|
| 392 |
+
"learning_rate": 5.071742313323573e-06,
|
| 393 |
+
"loss": 0.5111,
|
| 394 |
+
"step": 2550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 3.8067349926793557,
|
| 398 |
+
"grad_norm": 11.429731369018555,
|
| 399 |
+
"learning_rate": 4.77891654465593e-06,
|
| 400 |
+
"loss": 0.4936,
|
| 401 |
+
"step": 2600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.8799414348462666,
|
| 405 |
+
"grad_norm": 13.412334442138672,
|
| 406 |
+
"learning_rate": 4.486090775988287e-06,
|
| 407 |
+
"loss": 0.5202,
|
| 408 |
+
"step": 2650
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.953147877013177,
|
| 412 |
+
"grad_norm": 6.625152111053467,
|
| 413 |
+
"learning_rate": 4.193265007320644e-06,
|
| 414 |
+
"loss": 0.4826,
|
| 415 |
+
"step": 2700
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.0,
|
| 419 |
+
"eval_accuracy": 0.6379941434846267,
|
| 420 |
+
"eval_loss": 0.6155059933662415,
|
| 421 |
+
"eval_runtime": 13.2833,
|
| 422 |
+
"eval_samples_per_second": 205.672,
|
| 423 |
+
"eval_steps_per_second": 3.237,
|
| 424 |
+
"step": 2732
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 4.026354319180088,
|
| 428 |
+
"grad_norm": 7.482672214508057,
|
| 429 |
+
"learning_rate": 3.900439238653002e-06,
|
| 430 |
+
"loss": 0.4992,
|
| 431 |
+
"step": 2750
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.099560761346998,
|
| 435 |
+
"grad_norm": 9.46927261352539,
|
| 436 |
+
"learning_rate": 3.607613469985359e-06,
|
| 437 |
+
"loss": 0.4473,
|
| 438 |
+
"step": 2800
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 4.172767203513909,
|
| 442 |
+
"grad_norm": 8.915600776672363,
|
| 443 |
+
"learning_rate": 3.314787701317716e-06,
|
| 444 |
+
"loss": 0.4468,
|
| 445 |
+
"step": 2850
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 4.24597364568082,
|
| 449 |
+
"grad_norm": 10.110650062561035,
|
| 450 |
+
"learning_rate": 3.0219619326500732e-06,
|
| 451 |
+
"loss": 0.4692,
|
| 452 |
+
"step": 2900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.31918008784773,
|
| 456 |
+
"grad_norm": 17.987337112426758,
|
| 457 |
+
"learning_rate": 2.7291361639824306e-06,
|
| 458 |
+
"loss": 0.4452,
|
| 459 |
+
"step": 2950
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.392386530014641,
|
| 463 |
+
"grad_norm": 7.12765645980835,
|
| 464 |
+
"learning_rate": 2.436310395314788e-06,
|
| 465 |
+
"loss": 0.4401,
|
| 466 |
+
"step": 3000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 4.465592972181552,
|
| 470 |
+
"grad_norm": 6.777918815612793,
|
| 471 |
+
"learning_rate": 2.1434846266471453e-06,
|
| 472 |
+
"loss": 0.4511,
|
| 473 |
+
"step": 3050
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.538799414348462,
|
| 477 |
+
"grad_norm": 15.6901273727417,
|
| 478 |
+
"learning_rate": 1.8506588579795024e-06,
|
| 479 |
+
"loss": 0.4427,
|
| 480 |
+
"step": 3100
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.612005856515373,
|
| 484 |
+
"grad_norm": 9.44357967376709,
|
| 485 |
+
"learning_rate": 1.5578330893118595e-06,
|
| 486 |
+
"loss": 0.4564,
|
| 487 |
+
"step": 3150
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.685212298682284,
|
| 491 |
+
"grad_norm": 7.72824239730835,
|
| 492 |
+
"learning_rate": 1.2650073206442169e-06,
|
| 493 |
+
"loss": 0.4319,
|
| 494 |
+
"step": 3200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.758418740849194,
|
| 498 |
+
"grad_norm": 14.447629928588867,
|
| 499 |
+
"learning_rate": 9.72181551976574e-07,
|
| 500 |
+
"loss": 0.4558,
|
| 501 |
+
"step": 3250
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.831625183016105,
|
| 505 |
+
"grad_norm": 7.083517551422119,
|
| 506 |
+
"learning_rate": 6.793557833089313e-07,
|
| 507 |
+
"loss": 0.4537,
|
| 508 |
+
"step": 3300
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.904831625183016,
|
| 512 |
+
"grad_norm": 15.930305480957031,
|
| 513 |
+
"learning_rate": 3.865300146412885e-07,
|
| 514 |
+
"loss": 0.4552,
|
| 515 |
+
"step": 3350
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.978038067349927,
|
| 519 |
+
"grad_norm": 15.451827049255371,
|
| 520 |
+
"learning_rate": 9.370424597364569e-08,
|
| 521 |
+
"loss": 0.456,
|
| 522 |
+
"step": 3400
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 5.0,
|
| 526 |
+
"eval_accuracy": 0.6471449487554904,
|
| 527 |
+
"eval_loss": 0.6813626289367676,
|
| 528 |
+
"eval_runtime": 12.97,
|
| 529 |
+
"eval_samples_per_second": 210.639,
|
| 530 |
+
"eval_steps_per_second": 3.315,
|
| 531 |
+
"step": 3415
|
| 532 |
+
}
|
| 533 |
+
],
|
| 534 |
+
"logging_steps": 50,
|
| 535 |
+
"max_steps": 3415,
|
| 536 |
+
"num_input_tokens_seen": 0,
|
| 537 |
+
"num_train_epochs": 5,
|
| 538 |
+
"save_steps": 500,
|
| 539 |
+
"stateful_callbacks": {
|
| 540 |
+
"TrainerControl": {
|
| 541 |
+
"args": {
|
| 542 |
+
"should_epoch_stop": false,
|
| 543 |
+
"should_evaluate": false,
|
| 544 |
+
"should_log": false,
|
| 545 |
+
"should_save": true,
|
| 546 |
+
"should_training_stop": true
|
| 547 |
+
},
|
| 548 |
+
"attributes": {}
|
| 549 |
+
}
|
| 550 |
+
},
|
| 551 |
+
"total_flos": 1.43750725095936e+16,
|
| 552 |
+
"train_batch_size": 32,
|
| 553 |
+
"trial_name": null,
|
| 554 |
+
"trial_params": null
|
| 555 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a06adfb44cd579140c06deb6380bb5a909ddded2d8ec540a0a6363761b6f1264
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|