Upload folder using huggingface_hub
Browse files- checkpoint-9/config.json +32 -0
- checkpoint-9/generation_config.json +7 -0
- checkpoint-9/model.safetensors +3 -0
- checkpoint-9/optimizer.pt +3 -0
- checkpoint-9/rng_state.pth +3 -0
- checkpoint-9/scheduler.pt +3 -0
- checkpoint-9/trainer_state.json +32 -0
- checkpoint-9/training_args.bin +3 -0
- config.json +10 -7
- generation_config.json +7 -0
- model.safetensors +2 -2
- special_tokens_map.json +30 -1
- tokenizer.json +2 -2
- tokenizer_config.json +48 -1
- training_args.bin +3 -0
checkpoint-9/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MisterAI/bigscience_bloom-560m",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"skip_bias_add": true,
|
25 |
+
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.49.0",
|
29 |
+
"unk_token_id": 0,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250880
|
32 |
+
}
|
checkpoint-9/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.49.0"
|
7 |
+
}
|
checkpoint-9/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9d6a4e21de45183e66e64f21d7b23a4c9c5a9eaa4a96d3218508febf0f36c22
|
3 |
+
size 2236892304
|
checkpoint-9/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:720c3bf711cfc20b2cb5d8c0303b8697656fbdb550ec6f4262a6f06d15fa5c2e
|
3 |
+
size 4473954638
|
checkpoint-9/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4864c89835cbf79e96fc0a2d2de7044506fea9c48cfcbba91fdab915a1eb9808
|
3 |
+
size 13990
|
checkpoint-9/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe28afbf6131c4aaf26ff58140d1779aa47b73f2084ea00758f7b4ca1fc0182a
|
3 |
+
size 1064
|
checkpoint-9/trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 9,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 500,
|
12 |
+
"max_steps": 9,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 1,
|
15 |
+
"save_steps": 10000,
|
16 |
+
"stateful_callbacks": {
|
17 |
+
"TrainerControl": {
|
18 |
+
"args": {
|
19 |
+
"should_epoch_stop": false,
|
20 |
+
"should_evaluate": false,
|
21 |
+
"should_log": false,
|
22 |
+
"should_save": true,
|
23 |
+
"should_training_stop": true
|
24 |
+
},
|
25 |
+
"attributes": {}
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"total_flos": 16716725747712.0,
|
29 |
+
"train_batch_size": 2,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
checkpoint-9/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c41940dd9c9d8d44bbd60d5a3b1f83593e41741b8ef22fc21d087a365cb41d1e
|
3 |
+
size 5432
|
config.json
CHANGED
@@ -1,29 +1,32 @@
|
|
1 |
{
|
|
|
2 |
"apply_residual_connection_post_layernorm": false,
|
3 |
-
"attention_dropout": 0.0,
|
4 |
"architectures": [
|
5 |
"BloomForCausalLM"
|
6 |
],
|
|
|
7 |
"attention_softmax_in_fp32": true,
|
8 |
"bias_dropout_fusion": true,
|
9 |
"bos_token_id": 1,
|
10 |
"eos_token_id": 2,
|
11 |
-
"pad_token_id": 3,
|
12 |
-
"unk_token_id": 0,
|
13 |
"hidden_dropout": 0.0,
|
|
|
14 |
"initializer_range": 0.02,
|
15 |
"layer_norm_epsilon": 1e-05,
|
16 |
"masked_softmax_fusion": true,
|
17 |
"model_type": "bloom",
|
18 |
-
"
|
19 |
"n_inner": null,
|
20 |
"n_layer": 24,
|
21 |
-
"num_attention_heads": 16,
|
22 |
"offset_alibi": 100,
|
|
|
23 |
"pretraining_tp": 1,
|
24 |
"skip_bias_add": true,
|
25 |
"skip_bias_add_qkv": false,
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 250880
|
29 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "MisterAI/bigscience_bloom-560m",
|
3 |
"apply_residual_connection_post_layernorm": false,
|
|
|
4 |
"architectures": [
|
5 |
"BloomForCausalLM"
|
6 |
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
"attention_softmax_in_fp32": true,
|
9 |
"bias_dropout_fusion": true,
|
10 |
"bos_token_id": 1,
|
11 |
"eos_token_id": 2,
|
|
|
|
|
12 |
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
"initializer_range": 0.02,
|
15 |
"layer_norm_epsilon": 1e-05,
|
16 |
"masked_softmax_fusion": true,
|
17 |
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
"n_inner": null,
|
20 |
"n_layer": 24,
|
|
|
21 |
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
"pretraining_tp": 1,
|
24 |
"skip_bias_add": true,
|
25 |
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.49.0",
|
29 |
+
"unk_token_id": 0,
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 250880
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.49.0"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9d6a4e21de45183e66e64f21d7b23a4c9c5a9eaa4a96d3218508febf0f36c22
|
3 |
+
size 2236892304
|
special_tokens_map.json
CHANGED
@@ -1 +1,30 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c284e2b3e3eb543578e46aba6a15796e0e4e2f60a2b7f5bb8c23e546c1802332
|
3 |
+
size 21763349
|
tokenizer_config.json
CHANGED
@@ -1 +1,48 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<unk>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<pad>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"bos_token": "<s>",
|
38 |
+
"clean_up_tokenization_spaces": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"extra_special_tokens": {},
|
41 |
+
"merges_file": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"padding_side": "left",
|
45 |
+
"tokenizer_class": "BloomTokenizer",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"vocab_file": null
|
48 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c41940dd9c9d8d44bbd60d5a3b1f83593e41741b8ef22fc21d087a365cb41d1e
|
3 |
+
size 5432
|