getrajeev03
commited on
Commit
•
a8c313a
1
Parent(s):
0e4ed84
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +70 -0
- logs/events.out.tfevents.1687423282.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.0 +3 -0
- logs/events.out.tfevents.1687425058.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.1 +3 -0
- logs/events.out.tfevents.1687425408.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.2 +3 -0
- logs/events.out.tfevents.1687426081.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.3 +3 -0
- logs/events.out.tfevents.1687426149.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.4 +3 -0
- logs/events.out.tfevents.1687426233.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.5 +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "philschmid/bart-large-cnn-samsum",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"force_bos_token_to_be_generated": true,
|
28 |
+
"forced_bos_token_id": 0,
|
29 |
+
"forced_eos_token_id": 2,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1",
|
34 |
+
"2": "LABEL_2"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2
|
42 |
+
},
|
43 |
+
"length_penalty": 2.0,
|
44 |
+
"max_length": 142,
|
45 |
+
"max_position_embeddings": 1024,
|
46 |
+
"min_length": 56,
|
47 |
+
"model_type": "bart",
|
48 |
+
"no_repeat_ngram_size": 3,
|
49 |
+
"normalize_before": false,
|
50 |
+
"num_beams": 4,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 1,
|
54 |
+
"prefix": " ",
|
55 |
+
"scale_embedding": false,
|
56 |
+
"task_specific_params": {
|
57 |
+
"summarization": {
|
58 |
+
"early_stopping": true,
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"no_repeat_ngram_size": 3,
|
63 |
+
"num_beams": 4
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.30.2",
|
68 |
+
"use_cache": true,
|
69 |
+
"vocab_size": 50264
|
70 |
+
}
|
logs/events.out.tfevents.1687423282.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96080b29580f2d29e69b6169f405e31979ffaddb47b2ab7d53a00ee3c904c2ae
|
3 |
+
size 5162
|
logs/events.out.tfevents.1687425058.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e9ef05f6e70f11f3ab59bd535d40ab04bdbcbe8daf3e7bedcd0bd1f056a4db
|
3 |
+
size 5162
|
logs/events.out.tfevents.1687425408.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ddcc0060780e07bd402ee7081f9527fdb039d97d3e6f5d01c74231a94459a90
|
3 |
+
size 5164
|
logs/events.out.tfevents.1687426081.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b507e17a94a3016cf41d5585d00d91a5491eb2157e3e5f54d3667224257c22a
|
3 |
+
size 5161
|
logs/events.out.tfevents.1687426149.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01e1ddc2d2e5fc31a10e82c43e7a6b5f3a0269c4899e99277c025919e5541fe8
|
3 |
+
size 5162
|
logs/events.out.tfevents.1687426233.notebook-rt222gpu1d283621de18747e3b0384bacd7ed0ecf-85d8fdccvn75.181.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c037dd04629aad4ef07c4926828005b0f0b6fbbb52f061d01d77ecdfd047182
|
3 |
+
size 7885
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f744c65035097aa06ad49bd3c75b41933054c51cc97f63b88d8cc575c58c1f8
|
3 |
+
size 1625533697
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ee03a6f371fdca12befab1303c66ab2ea0a941173b8b16ae5e386951c426fb5
|
3 |
+
size 4079
|