root
commited on
Commit
•
ec4c964
1
Parent(s):
7ecc404
initial commit
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- trainer_state.json +124 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "mt5",
|
17 |
+
"num_decoder_layers": 12,
|
18 |
+
"num_heads": 12,
|
19 |
+
"num_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_max_distance": 128,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"tokenizer_class": "T5Tokenizer",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.18.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 250112
|
30 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9651543d51e42368464ece51ec50a19d2bf1178909d7dea0d534f581e095ed71
|
3 |
+
size 4113057
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d76b9863b2f94b85e7faf3d037462f6e6bece818add5d22070046f1b33ac035
|
3 |
+
size 2329700301
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:920a4a1dc74cb3d1df30cd5e03fbf55c850d3441f13f14f566d28ace353a765e
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34127c750c790a35ad63eddee43f8ea46129f38c5204c3c05240f1d9ea88a072
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-base", "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3033078610897064,
|
3 |
+
"best_model_checkpoint": "weights/checkpoint-2400",
|
4 |
+
"epoch": 2.05477107402653,
|
5 |
+
"global_step": 2400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.34,
|
12 |
+
"learning_rate": 0.0008858447488584475,
|
13 |
+
"loss": 1.0868,
|
14 |
+
"step": 400
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.34,
|
18 |
+
"eval_loss": 0.3964288830757141,
|
19 |
+
"eval_rouge1": 0.1061059158446104,
|
20 |
+
"eval_rouge2": 0.03465244917613476,
|
21 |
+
"eval_rougeL": 0.10627894663827464,
|
22 |
+
"eval_rougeLsum": 0.10587803730968609,
|
23 |
+
"eval_runtime": 213.0846,
|
24 |
+
"eval_samples_per_second": 11.667,
|
25 |
+
"eval_steps_per_second": 1.46,
|
26 |
+
"step": 400
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.68,
|
30 |
+
"learning_rate": 0.000771689497716895,
|
31 |
+
"loss": 0.4378,
|
32 |
+
"step": 800
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.68,
|
36 |
+
"eval_loss": 0.3599437475204468,
|
37 |
+
"eval_rouge1": 0.10699235686427112,
|
38 |
+
"eval_rouge2": 0.034402581194616595,
|
39 |
+
"eval_rougeL": 0.10726814102163426,
|
40 |
+
"eval_rougeLsum": 0.10683004020509843,
|
41 |
+
"eval_runtime": 209.0997,
|
42 |
+
"eval_samples_per_second": 11.889,
|
43 |
+
"eval_steps_per_second": 1.487,
|
44 |
+
"step": 800
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.03,
|
48 |
+
"learning_rate": 0.0006575342465753425,
|
49 |
+
"loss": 0.3695,
|
50 |
+
"step": 1200
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.03,
|
54 |
+
"eval_loss": 0.3147580027580261,
|
55 |
+
"eval_rouge1": 0.10717208698017014,
|
56 |
+
"eval_rouge2": 0.03477288244690299,
|
57 |
+
"eval_rougeL": 0.10748345500504963,
|
58 |
+
"eval_rougeLsum": 0.10712451901224819,
|
59 |
+
"eval_runtime": 208.2509,
|
60 |
+
"eval_samples_per_second": 11.938,
|
61 |
+
"eval_steps_per_second": 1.493,
|
62 |
+
"step": 1200
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.37,
|
66 |
+
"learning_rate": 0.00054337899543379,
|
67 |
+
"loss": 0.2645,
|
68 |
+
"step": 1600
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.37,
|
72 |
+
"eval_loss": 0.31476476788520813,
|
73 |
+
"eval_rouge1": 0.10597239490642546,
|
74 |
+
"eval_rouge2": 0.033266358974880464,
|
75 |
+
"eval_rougeL": 0.10614402559092825,
|
76 |
+
"eval_rougeLsum": 0.10592368490095762,
|
77 |
+
"eval_runtime": 208.6832,
|
78 |
+
"eval_samples_per_second": 11.913,
|
79 |
+
"eval_steps_per_second": 1.49,
|
80 |
+
"step": 1600
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.71,
|
84 |
+
"learning_rate": 0.00042922374429223744,
|
85 |
+
"loss": 0.2503,
|
86 |
+
"step": 2000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.71,
|
90 |
+
"eval_loss": 0.3020365834236145,
|
91 |
+
"eval_rouge1": 0.10566329888936485,
|
92 |
+
"eval_rouge2": 0.03209767038592902,
|
93 |
+
"eval_rougeL": 0.10595888780924984,
|
94 |
+
"eval_rougeLsum": 0.10570986122575018,
|
95 |
+
"eval_runtime": 207.8626,
|
96 |
+
"eval_samples_per_second": 11.96,
|
97 |
+
"eval_steps_per_second": 1.496,
|
98 |
+
"step": 2000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.05,
|
102 |
+
"learning_rate": 0.00031506849315068495,
|
103 |
+
"loss": 0.2264,
|
104 |
+
"step": 2400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.05,
|
108 |
+
"eval_loss": 0.3033078610897064,
|
109 |
+
"eval_rouge1": 0.10519725760071695,
|
110 |
+
"eval_rouge2": 0.03199324082356017,
|
111 |
+
"eval_rougeL": 0.10550921669284499,
|
112 |
+
"eval_rougeLsum": 0.10514026310687613,
|
113 |
+
"eval_runtime": 207.427,
|
114 |
+
"eval_samples_per_second": 11.985,
|
115 |
+
"eval_steps_per_second": 1.499,
|
116 |
+
"step": 2400
|
117 |
+
}
|
118 |
+
],
|
119 |
+
"max_steps": 3504,
|
120 |
+
"num_train_epochs": 3,
|
121 |
+
"total_flos": 5666207247866880.0,
|
122 |
+
"trial_name": null,
|
123 |
+
"trial_params": null
|
124 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ab4a3ebfacb59e68841e111fdfd09990dfccca7f98f8275e4de3cf1d660254
|
3 |
+
size 3119
|