Training in progress, step 400
Browse files- config.json +46 -0
- last-checkpoint/config.json +46 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +26 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- runs/Jun10_02-32-14_764db004b06b/events.out.tfevents.1686364349.764db004b06b.573.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "anger",
|
15 |
+
"1": "fear",
|
16 |
+
"2": "joy",
|
17 |
+
"3": "love",
|
18 |
+
"4": "sadness",
|
19 |
+
"5": "surprise",
|
20 |
+
"6": "neutral"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 4096,
|
24 |
+
"label2id": {
|
25 |
+
"anger": 0,
|
26 |
+
"fear": 1,
|
27 |
+
"joy": 2,
|
28 |
+
"love": 3,
|
29 |
+
"neutral": 6,
|
30 |
+
"sadness": 4,
|
31 |
+
"surprise": 5
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"max_position_embeddings": 514,
|
35 |
+
"model_type": "xlm-roberta",
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_hidden_layers": 24,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.30.1",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 250002
|
46 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "anger",
|
15 |
+
"1": "fear",
|
16 |
+
"2": "joy",
|
17 |
+
"3": "love",
|
18 |
+
"4": "sadness",
|
19 |
+
"5": "surprise",
|
20 |
+
"6": "neutral"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 4096,
|
24 |
+
"label2id": {
|
25 |
+
"anger": 0,
|
26 |
+
"fear": 1,
|
27 |
+
"joy": 2,
|
28 |
+
"love": 3,
|
29 |
+
"neutral": 6,
|
30 |
+
"sadness": 4,
|
31 |
+
"surprise": 5
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"max_position_embeddings": 514,
|
35 |
+
"model_type": "xlm-roberta",
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_hidden_layers": 24,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.30.1",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 250002
|
46 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c347326288ab327f9da028a2d790211a92c1ed68daa57bc5901baf3dd2fe65
|
3 |
+
size 2067085189
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aba0db36c138b192b54ae4618cb63175aec256ff17d9eea0cae541ab180958c
|
3 |
+
size 2242911029
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dc7ebdf12a1825b508ac309012a4fe5e4b49f3af38ec3c1d189aec20e63ba7f
|
3 |
+
size 14575
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626570eea69da39ec2b164f665022bcc941bbeeab87db85d9066852ee82fb10a
|
3 |
+
size 627
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04197271773347324,
|
5 |
+
"global_step": 400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"eval_accuracy": 0.6216116513450103,
|
13 |
+
"eval_f1": 0.5350163270245339,
|
14 |
+
"eval_loss": 1.2418967485427856,
|
15 |
+
"eval_runtime": 545.576,
|
16 |
+
"eval_samples_per_second": 248.431,
|
17 |
+
"eval_steps_per_second": 0.971,
|
18 |
+
"step": 400
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"max_steps": 953000,
|
22 |
+
"num_train_epochs": 100,
|
23 |
+
"total_flos": 1.6623719784764928e+16,
|
24 |
+
"trial_name": null,
|
25 |
+
"trial_params": null
|
26 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc3cd92f18740ee90763d19bfd0874642c282ef6db778d3f9ddfb30630b6e77c
|
3 |
+
size 3963
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aba0db36c138b192b54ae4618cb63175aec256ff17d9eea0cae541ab180958c
|
3 |
+
size 2242911029
|
runs/Jun10_02-32-14_764db004b06b/events.out.tfevents.1686364349.764db004b06b.573.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5d41cea80d8dd311f9d5d943b2663695df0887cf875b196a474954eaff185fd
|
3 |
+
size 4721
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc3cd92f18740ee90763d19bfd0874642c282ef6db778d3f9ddfb30630b6e77c
|
3 |
+
size 3963
|