Upload folder using huggingface_hub
Browse files- checkpoint-210/config.json +55 -0
- checkpoint-210/generation_config.json +6 -0
- checkpoint-210/model.safetensors +3 -0
- checkpoint-210/optimizer.pt +3 -0
- checkpoint-210/rng_state.pth +3 -0
- checkpoint-210/scheduler.pt +3 -0
- checkpoint-210/trainer_state.json +32 -0
- checkpoint-210/training_args.bin +3 -0
- config.json +55 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
checkpoint-210/config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125M",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"classifier_dropout": 0.1,
|
33 |
+
"embed_dropout": 0,
|
34 |
+
"eos_token_id": 50256,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"hidden_size": 768,
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": null,
|
39 |
+
"layer_norm_epsilon": 1e-05,
|
40 |
+
"max_position_embeddings": 2048,
|
41 |
+
"model_type": "gpt_neo",
|
42 |
+
"num_heads": 12,
|
43 |
+
"num_layers": 12,
|
44 |
+
"resid_dropout": 0,
|
45 |
+
"summary_activation": null,
|
46 |
+
"summary_first_dropout": 0.1,
|
47 |
+
"summary_proj_to_labels": true,
|
48 |
+
"summary_type": "cls_index",
|
49 |
+
"summary_use_proj": true,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.46.3",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 50257,
|
54 |
+
"window_size": 256
|
55 |
+
}
|
checkpoint-210/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.46.3"
|
6 |
+
}
|
checkpoint-210/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c049d05b3c1c6bddb1fa2657e01fa4ada43be88573ef660c2503e8d6c81c43
|
3 |
+
size 500811336
|
checkpoint-210/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a09efe379f310e04775a64b8e5c492ad0550335fde421640c3a233c32272140c
|
3 |
+
size 1001722938
|
checkpoint-210/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
3 |
+
size 14244
|
checkpoint-210/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ceb542077322d5d7459159dfa4a04f4813c52e980e8c64fa69dfd8b65e0be42
|
3 |
+
size 1064
|
checkpoint-210/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": 210,
|
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": 210,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 1,
|
15 |
+
"save_steps": 500,
|
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": 438827923537920.0,
|
29 |
+
"train_batch_size": 8,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
checkpoint-210/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4c666ebe9ca6ef8728385a3d3333c19c27e0a5ded14defdd850b5af2faae7ee
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125M",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"classifier_dropout": 0.1,
|
33 |
+
"embed_dropout": 0,
|
34 |
+
"eos_token_id": 50256,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"hidden_size": 768,
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": null,
|
39 |
+
"layer_norm_epsilon": 1e-05,
|
40 |
+
"max_position_embeddings": 2048,
|
41 |
+
"model_type": "gpt_neo",
|
42 |
+
"num_heads": 12,
|
43 |
+
"num_layers": 12,
|
44 |
+
"resid_dropout": 0,
|
45 |
+
"summary_activation": null,
|
46 |
+
"summary_first_dropout": 0.1,
|
47 |
+
"summary_proj_to_labels": true,
|
48 |
+
"summary_type": "cls_index",
|
49 |
+
"summary_use_proj": true,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.46.3",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 50257,
|
54 |
+
"window_size": 256
|
55 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.46.3"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c049d05b3c1c6bddb1fa2657e01fa4ada43be88573ef660c2503e8d6c81c43
|
3 |
+
size 500811336
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4c666ebe9ca6ef8728385a3d3333c19c27e0a5ded14defdd850b5af2faae7ee
|
3 |
+
size 5240
|