Upload 12 files
Browse files- all_results.json +8 -0
- config.json +31 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- train_results.json +8 -0
- trainer_state.json +43 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.98,
|
3 |
+
"train_loss": 0.7888860991570802,
|
4 |
+
"train_runtime": 4654.6916,
|
5 |
+
"train_samples": 1813,
|
6 |
+
"train_samples_per_second": 1.947,
|
7 |
+
"train_steps_per_second": 0.243
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-1.3b",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 8192,
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.31.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 2048
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.31.0"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22307f2d663b66a4c4edb643d86b345990ad4ebf3e670e4a9bffbaeca13096b1
|
3 |
+
size 5263162257
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "</s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": {
|
24 |
+
"__type": "AddedToken",
|
25 |
+
"content": "<pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"tokenizer_class": "GPT2Tokenizer",
|
32 |
+
"unk_token": {
|
33 |
+
"__type": "AddedToken",
|
34 |
+
"content": "</s>",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": true,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
}
|
40 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.98,
|
3 |
+
"train_loss": 0.7888860991570802,
|
4 |
+
"train_runtime": 4654.6916,
|
5 |
+
"train_samples": 1813,
|
6 |
+
"train_samples_per_second": 1.947,
|
7 |
+
"train_steps_per_second": 0.243
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.983461962513782,
|
5 |
+
"global_step": 1130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.9982300884955754e-05,
|
13 |
+
"loss": 2.3012,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.21,
|
18 |
+
"learning_rate": 1.1150442477876106e-05,
|
19 |
+
"loss": 0.9544,
|
20 |
+
"step": 500
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 4.41,
|
24 |
+
"learning_rate": 2.3008849557522127e-06,
|
25 |
+
"loss": 0.673,
|
26 |
+
"step": 1000
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 4.98,
|
30 |
+
"step": 1130,
|
31 |
+
"total_flos": 6.709821425949082e+16,
|
32 |
+
"train_loss": 0.7888860991570802,
|
33 |
+
"train_runtime": 4654.6916,
|
34 |
+
"train_samples_per_second": 1.947,
|
35 |
+
"train_steps_per_second": 0.243
|
36 |
+
}
|
37 |
+
],
|
38 |
+
"max_steps": 1130,
|
39 |
+
"num_train_epochs": 5,
|
40 |
+
"total_flos": 6.709821425949082e+16,
|
41 |
+
"trial_name": null,
|
42 |
+
"trial_params": null
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95d21cfa42b453ab95962819858c24da160d1a009ac203ee80fd2ce0b01d025d
|
3 |
+
size 3951
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|