Upload 8 files
Browse files- config.json +46 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +90 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.27.4",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
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": "4.27.4"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96fa2a05605aab2e11f861ef17640d2c023a965819a786a5ee7d325c728124e5
|
3 |
+
size 655342981
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6bd5575107c868751997c3181c6ab275ee441597b01f1f91588034e0296b22
|
3 |
+
size 333968953
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16f57bcfbae4c99682d8c5c02dbb6af4a34190d48a4b4b8965716867c8f57131
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:597f102a1876ce7b5eccff45979cd35c5efbd5f7c3c6378c74b924f7632225e0
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1532816104005033,
|
5 |
+
"global_step": 5500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 1.930104144824212e-05,
|
13 |
+
"loss": 2.0398,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.21,
|
18 |
+
"learning_rate": 1.860208289648424e-05,
|
19 |
+
"loss": 1.7138,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.31,
|
24 |
+
"learning_rate": 1.790312434472636e-05,
|
25 |
+
"loss": 1.6022,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.42,
|
30 |
+
"learning_rate": 1.720416579296848e-05,
|
31 |
+
"loss": 1.5263,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.52,
|
36 |
+
"learning_rate": 1.6505207241210597e-05,
|
37 |
+
"loss": 1.4804,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.63,
|
42 |
+
"learning_rate": 1.5806248689452716e-05,
|
43 |
+
"loss": 1.434,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.73,
|
48 |
+
"learning_rate": 1.5107290137694836e-05,
|
49 |
+
"loss": 1.4131,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.84,
|
54 |
+
"learning_rate": 1.4408331585936954e-05,
|
55 |
+
"loss": 1.3862,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.94,
|
60 |
+
"learning_rate": 1.3709373034179074e-05,
|
61 |
+
"loss": 1.3675,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"eval_loss": 1.4010822772979736,
|
67 |
+
"eval_runtime": 3146.6255,
|
68 |
+
"eval_samples_per_second": 11.181,
|
69 |
+
"eval_steps_per_second": 1.398,
|
70 |
+
"step": 4769
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.05,
|
74 |
+
"learning_rate": 1.3010414482421195e-05,
|
75 |
+
"loss": 1.3461,
|
76 |
+
"step": 5000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.15,
|
80 |
+
"learning_rate": 1.2311455930663311e-05,
|
81 |
+
"loss": 1.3293,
|
82 |
+
"step": 5500
|
83 |
+
}
|
84 |
+
],
|
85 |
+
"max_steps": 14307,
|
86 |
+
"num_train_epochs": 3,
|
87 |
+
"total_flos": 1436968817786880.0,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7830e8f39d7a68e67b32d873381b4d836869bb69c5ec3c7779953956adedd94
|
3 |
+
size 3579
|