gantenbe
commited on
Commit
•
5b9358e
1
Parent(s):
e3eb4f1
swiss training
Browse files- all_results.json +14 -0
- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +149 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"init_mem_cpu_alloc_delta": 335895,
|
4 |
+
"init_mem_cpu_peaked_delta": 18306,
|
5 |
+
"init_mem_gpu_alloc_delta": 511148032,
|
6 |
+
"init_mem_gpu_peaked_delta": 0,
|
7 |
+
"train_mem_cpu_alloc_delta": 925294,
|
8 |
+
"train_mem_cpu_peaked_delta": 1247793,
|
9 |
+
"train_mem_gpu_alloc_delta": 1501967872,
|
10 |
+
"train_mem_gpu_peaked_delta": 3373839360,
|
11 |
+
"train_runtime": 2923.7518,
|
12 |
+
"train_samples": 10863,
|
13 |
+
"train_samples_per_second": 3.715
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 50
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"transformers_version": "4.4.0.dev0",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50257
|
36 |
+
}
|
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:e16dc707aebea8d47279d1a5190c45c1b95676b82937a1c038246dac809c64e1
|
3 |
+
size 510406566
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}
|
train_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"init_mem_cpu_alloc_delta": 335895,
|
4 |
+
"init_mem_cpu_peaked_delta": 18306,
|
5 |
+
"init_mem_gpu_alloc_delta": 511148032,
|
6 |
+
"init_mem_gpu_peaked_delta": 0,
|
7 |
+
"train_mem_cpu_alloc_delta": 925294,
|
8 |
+
"train_mem_cpu_peaked_delta": 1247793,
|
9 |
+
"train_mem_gpu_alloc_delta": 1501967872,
|
10 |
+
"train_mem_gpu_peaked_delta": 3373839360,
|
11 |
+
"train_runtime": 2923.7518,
|
12 |
+
"train_samples": 10863,
|
13 |
+
"train_samples_per_second": 3.715
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 10863,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 4.7698609960416095e-05,
|
13 |
+
"loss": 0.4597,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 4.539721992083218e-05,
|
19 |
+
"loss": 0.3231,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.14,
|
24 |
+
"learning_rate": 4.309582988124828e-05,
|
25 |
+
"loss": 0.3073,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.18,
|
30 |
+
"learning_rate": 4.079443984166437e-05,
|
31 |
+
"loss": 0.2928,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.23,
|
36 |
+
"learning_rate": 3.849304980208046e-05,
|
37 |
+
"loss": 0.2808,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.28,
|
42 |
+
"learning_rate": 3.619165976249655e-05,
|
43 |
+
"loss": 0.275,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.32,
|
48 |
+
"learning_rate": 3.389026972291264e-05,
|
49 |
+
"loss": 0.2675,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.37,
|
54 |
+
"learning_rate": 3.1588879683328734e-05,
|
55 |
+
"loss": 0.2614,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.41,
|
60 |
+
"learning_rate": 2.9287489643744827e-05,
|
61 |
+
"loss": 0.2584,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.46,
|
66 |
+
"learning_rate": 2.6986099604160913e-05,
|
67 |
+
"loss": 0.2555,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.51,
|
72 |
+
"learning_rate": 2.4684709564577006e-05,
|
73 |
+
"loss": 0.2532,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.55,
|
78 |
+
"learning_rate": 2.2383319524993096e-05,
|
79 |
+
"loss": 0.2496,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.6,
|
84 |
+
"learning_rate": 2.0081929485409186e-05,
|
85 |
+
"loss": 0.2483,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.64,
|
90 |
+
"learning_rate": 1.778053944582528e-05,
|
91 |
+
"loss": 0.2457,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.69,
|
96 |
+
"learning_rate": 1.547914940624137e-05,
|
97 |
+
"loss": 0.2454,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.74,
|
102 |
+
"learning_rate": 1.317775936665746e-05,
|
103 |
+
"loss": 0.2441,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.78,
|
108 |
+
"learning_rate": 1.0876369327073553e-05,
|
109 |
+
"loss": 0.2426,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.83,
|
114 |
+
"learning_rate": 8.574979287489644e-06,
|
115 |
+
"loss": 0.2427,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.87,
|
120 |
+
"learning_rate": 6.273589247905736e-06,
|
121 |
+
"loss": 0.2416,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.92,
|
126 |
+
"learning_rate": 3.972199208321826e-06,
|
127 |
+
"loss": 0.2398,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.97,
|
132 |
+
"learning_rate": 1.6708091687379177e-06,
|
133 |
+
"loss": 0.2409,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.0,
|
138 |
+
"step": 10863,
|
139 |
+
"total_flos": 8305395513163776.0,
|
140 |
+
"train_runtime": 2923.7518,
|
141 |
+
"train_samples_per_second": 3.715
|
142 |
+
}
|
143 |
+
],
|
144 |
+
"max_steps": 10863,
|
145 |
+
"num_train_epochs": 1,
|
146 |
+
"total_flos": 8305395513163776.0,
|
147 |
+
"trial_name": null,
|
148 |
+
"trial_params": null
|
149 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066c3cf203b9657ca83bda8c6f40c2d45272c2c90db36cb1dd6ffcf54f7bf1a5
|
3 |
+
size 2287
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|