karthikqnq
commited on
Commit
•
6c22582
1
Parent(s):
75b1271
Add fine-tuned model
Browse files- checkpoint-66/config.json +39 -0
- checkpoint-66/generation_config.json +6 -0
- checkpoint-66/model.safetensors +3 -0
- checkpoint-66/optimizer.pt +3 -0
- checkpoint-66/rng_state.pth +3 -0
- checkpoint-66/scheduler.pt +3 -0
- checkpoint-66/trainer_state.json +32 -0
- checkpoint-66/training_args.bin +3 -0
- model.safetensors +1 -1
- special_tokens_map.json +7 -1
- tokenizer_config.json +7 -0
- training_args.bin +3 -0
checkpoint-66/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "karthikqnq/qnqgpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.45.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50260
|
39 |
+
}
|
checkpoint-66/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": "4.45.2"
|
6 |
+
}
|
checkpoint-66/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5286cc6592ee810d54927d2a8cc47c724f4b953f9a382f48df3eb8ec1630f0d4
|
3 |
+
size 497783424
|
checkpoint-66/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ec8e106bb30f90b815b06d9eb17fd0545bdc5bd5267b783c70b746deac8c41
|
3 |
+
size 995656634
|
checkpoint-66/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3224c1e102c384da5df4e25d21ce9bd98074268a6042fbf85a5be685ec37bc87
|
3 |
+
size 13990
|
checkpoint-66/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1047ea0c92f0ae016eb996f3c53f7338e29253a70eaf6dae561ded8aa561af1
|
3 |
+
size 1064
|
checkpoint-66/trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 66,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 100,
|
12 |
+
"max_steps": 66,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 3,
|
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": 4081667328000.0,
|
29 |
+
"train_batch_size": 2,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
checkpoint-66/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abc8ba1d775d2675da5e9cc2c4a32e80b40bd35baf44772bf79ab67a94822bfc
|
3 |
+
size 5176
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497783424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5286cc6592ee810d54927d2a8cc47c724f4b953f9a382f48df3eb8ec1630f0d4
|
3 |
size 497783424
|
special_tokens_map.json
CHANGED
@@ -20,7 +20,13 @@
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"sep_token": {
|
25 |
"content": "<sep>",
|
26 |
"lstrip": false,
|
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
"sep_token": {
|
31 |
"content": "<sep>",
|
32 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -40,9 +40,16 @@
|
|
40 |
"eos_token": "<|endoftext|>",
|
41 |
"errors": "replace",
|
42 |
"mask_token": "<mask>",
|
|
|
43 |
"model_max_length": 1024,
|
|
|
44 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
45 |
"sep_token": "<sep>",
|
|
|
46 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
47 |
"unk_token": "<|endoftext|>"
|
48 |
}
|
|
|
40 |
"eos_token": "<|endoftext|>",
|
41 |
"errors": "replace",
|
42 |
"mask_token": "<mask>",
|
43 |
+
"max_length": 512,
|
44 |
"model_max_length": 1024,
|
45 |
+
"pad_to_multiple_of": null,
|
46 |
"pad_token": "<|endoftext|>",
|
47 |
+
"pad_token_type_id": 0,
|
48 |
+
"padding_side": "right",
|
49 |
"sep_token": "<sep>",
|
50 |
+
"stride": 0,
|
51 |
"tokenizer_class": "GPT2Tokenizer",
|
52 |
+
"truncation_side": "right",
|
53 |
+
"truncation_strategy": "longest_first",
|
54 |
"unk_token": "<|endoftext|>"
|
55 |
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abc8ba1d775d2675da5e9cc2c4a32e80b40bd35baf44772bf79ab67a94822bfc
|
3 |
+
size 5176
|