genejalston
commited on
Commit
•
056939a
1
Parent(s):
28eadf7
Training in progress, step 500, checkpoint
Browse files
last-checkpoint/config.json
CHANGED
@@ -1,16 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
-
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
6 |
"add_bias_logits": false,
|
7 |
"add_final_layer_norm": false,
|
8 |
"architectures": [
|
9 |
"BartForConditionalGeneration"
|
10 |
],
|
11 |
-
"attention_dropout": 0.
|
12 |
"bos_token_id": 0,
|
13 |
-
"classif_dropout": 0.
|
14 |
"classifier_dropout": 0.0,
|
15 |
"d_model": 1024,
|
16 |
"decoder_attention_heads": 16,
|
@@ -19,12 +18,15 @@
|
|
19 |
"decoder_layers": 12,
|
20 |
"decoder_start_token_id": 2,
|
21 |
"dropout": 0.1,
|
|
|
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 |
"forced_eos_token_id": 2,
|
|
|
28 |
"id2label": {
|
29 |
"0": "LABEL_0",
|
30 |
"1": "LABEL_1",
|
@@ -39,22 +41,30 @@
|
|
39 |
},
|
40 |
"max_position_embeddings": 1024,
|
41 |
"model_type": "bart",
|
|
|
42 |
"normalize_before": false,
|
43 |
-
"
|
44 |
"num_hidden_layers": 12,
|
45 |
-
"output_past": false,
|
46 |
"pad_token_id": 1,
|
47 |
-
"prefix": " ",
|
48 |
"scale_embedding": false,
|
49 |
-
"static_position_embeddings": false,
|
50 |
"task_specific_params": {
|
51 |
"summarization": {
|
52 |
-
"
|
|
|
|
|
|
|
|
|
|
|
53 |
"length_penalty": 2.0,
|
54 |
"max_length": 142,
|
55 |
"min_length": 56,
|
56 |
-
"no_repeat_ngram_size": 3,
|
57 |
"num_beams": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
},
|
60 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
|
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
|
|
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 |
+
"forced_bos_token_id": 0,
|
28 |
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
"id2label": {
|
31 |
"0": "LABEL_0",
|
32 |
"1": "LABEL_1",
|
|
|
41 |
},
|
42 |
"max_position_embeddings": 1024,
|
43 |
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
"normalize_before": false,
|
46 |
+
"num_beams": 4,
|
47 |
"num_hidden_layers": 12,
|
|
|
48 |
"pad_token_id": 1,
|
|
|
49 |
"scale_embedding": false,
|
|
|
50 |
"task_specific_params": {
|
51 |
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
"length_penalty": 2.0,
|
59 |
"max_length": 142,
|
60 |
"min_length": 56,
|
|
|
61 |
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
}
|
69 |
},
|
70 |
"torch_dtype": "float32",
|
last-checkpoint/generation_config.json
CHANGED
@@ -2,8 +2,12 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"decoder_start_token_id": 2,
|
|
|
5 |
"eos_token_id": 2,
|
|
|
6 |
"forced_eos_token_id": 2,
|
|
|
|
|
7 |
"pad_token_id": 1,
|
8 |
"transformers_version": "4.35.2"
|
9 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
"forced_eos_token_id": 2,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
"pad_token_id": 1,
|
12 |
"transformers_version": "4.35.2"
|
13 |
}
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:394dfb894024b92bbbfb1b862531d2d6e28d88e7bc8c60fa638c57e06c43164d
|
3 |
size 1625426996
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250759951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:607419ad1882e0f53d766a3b9cffcab6b6f72e0bd0f8052ca50a35e39f90a005
|
3 |
size 3250759951
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e7af7a01e94a9a7176c2bbdf2cb9b8139105cfe65528853ec5a27025100d6bc
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f0d839853e90ea69a9baf4e612b78a79239aebb94a6d3f22225e1b04a009e92
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,63 +11,15 @@
|
|
11 |
{
|
12 |
"epoch": 0.01,
|
13 |
"learning_rate": 1.992872157045291e-05,
|
14 |
-
"loss": 0.
|
15 |
"step": 500
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"epoch": 0.02,
|
19 |
-
"learning_rate": 1.9855988479078326e-05,
|
20 |
-
"loss": 0.2287,
|
21 |
-
"step": 1000
|
22 |
-
},
|
23 |
-
{
|
24 |
-
"epoch": 0.03,
|
25 |
-
"learning_rate": 1.9783255387703745e-05,
|
26 |
-
"loss": 0.1475,
|
27 |
-
"step": 1500
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"epoch": 0.04,
|
31 |
-
"learning_rate": 1.971052229632916e-05,
|
32 |
-
"loss": 0.1033,
|
33 |
-
"step": 2000
|
34 |
-
},
|
35 |
-
{
|
36 |
-
"epoch": 0.05,
|
37 |
-
"learning_rate": 1.963778920495458e-05,
|
38 |
-
"loss": 0.1562,
|
39 |
-
"step": 2500
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 0.07,
|
43 |
-
"learning_rate": 1.9565056113579996e-05,
|
44 |
-
"loss": 0.107,
|
45 |
-
"step": 3000
|
46 |
-
},
|
47 |
-
{
|
48 |
-
"epoch": 0.08,
|
49 |
-
"learning_rate": 1.9492323022205415e-05,
|
50 |
-
"loss": 0.0692,
|
51 |
-
"step": 3500
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 0.09,
|
55 |
-
"learning_rate": 1.941958993083083e-05,
|
56 |
-
"loss": 0.0909,
|
57 |
-
"step": 4000
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"epoch": 0.1,
|
61 |
-
"learning_rate": 1.934685683945625e-05,
|
62 |
-
"loss": 0.1167,
|
63 |
-
"step": 4500
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 500,
|
67 |
"max_steps": 137499,
|
68 |
"num_train_epochs": 3,
|
69 |
"save_steps": 500,
|
70 |
-
"total_flos":
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.010909170248510899,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.01,
|
13 |
"learning_rate": 1.992872157045291e-05,
|
14 |
+
"loss": 0.5416,
|
15 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"logging_steps": 500,
|
19 |
"max_steps": 137499,
|
20 |
"num_train_epochs": 3,
|
21 |
"save_steps": 500,
|
22 |
+
"total_flos": 846525235200000.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|