Training in progress, step 500
Browse files- config.json +1 -5
- pytorch_model.bin +1 -1
- runs/Dec05_07-26-53_2ab8d0df0224/1670225218.1165054/events.out.tfevents.1670225218.2ab8d0df0224.113.17 +3 -0
- runs/Dec05_07-26-53_2ab8d0df0224/events.out.tfevents.1670225218.2ab8d0df0224.113.16 +3 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
@@ -9,23 +9,19 @@
|
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "relu",
|
11 |
"dropout_rate": 0.1,
|
12 |
-
"early_stopping": true,
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "relu",
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": false,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
-
"max_length": 300,
|
20 |
"model_type": "t5",
|
21 |
"n_positions": 512,
|
22 |
-
"num_beams": 4,
|
23 |
"num_decoder_layers": 6,
|
24 |
"num_heads": 8,
|
25 |
"num_layers": 6,
|
26 |
"output_past": true,
|
27 |
"pad_token_id": 0,
|
28 |
-
"prefix": "translate English to German: ",
|
29 |
"relative_attention_max_distance": 128,
|
30 |
"relative_attention_num_buckets": 32,
|
31 |
"task_specific_params": {
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "relu",
|
11 |
"dropout_rate": 0.1,
|
|
|
12 |
"eos_token_id": 1,
|
13 |
"feed_forward_proj": "relu",
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
"is_gated_act": false,
|
17 |
"layer_norm_epsilon": 1e-06,
|
|
|
18 |
"model_type": "t5",
|
19 |
"n_positions": 512,
|
|
|
20 |
"num_decoder_layers": 6,
|
21 |
"num_heads": 8,
|
22 |
"num_layers": 6,
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 0,
|
|
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
"task_specific_params": {
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242070267
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc5b0af8533cc35f2d14f1c9c8d8065c3066a1e23be64e21726371a7b4c44812
|
3 |
size 242070267
|
runs/Dec05_07-26-53_2ab8d0df0224/1670225218.1165054/events.out.tfevents.1670225218.2ab8d0df0224.113.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d6b63b02172c3e4a17bf34052b4520c8faa672a1079208dd8f77b098a533ca5
|
3 |
+
size 5813
|
runs/Dec05_07-26-53_2ab8d0df0224/events.out.tfevents.1670225218.2ab8d0df0224.113.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e953929dea8659f8b304aa716488ffcab36311b2b15dc2f976ea965348c3a42
|
3 |
+
size 4875
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -104,7 +104,7 @@
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 512,
|
107 |
-
"name_or_path": "
|
108 |
"pad_token": "<pad>",
|
109 |
"special_tokens_map_file": null,
|
110 |
"tokenizer_class": "T5Tokenizer",
|
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 512,
|
107 |
+
"name_or_path": "t5-small",
|
108 |
"pad_token": "<pad>",
|
109 |
"special_tokens_map_file": null,
|
110 |
"tokenizer_class": "T5Tokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44b851ff066be2d037847de7bd5c9d027984da7f5e1f3051547280eb2970ac93
|
3 |
size 3567
|