Training in progress, step 4
Browse files- .gitignore +1 -0
- 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 +15 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- runs/Jun09_18-16-00_e60ee0fa208b/events.out.tfevents.1686334565.e60ee0fa208b.621.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
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/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:f8c1ba7ca3c5f3fceacec03166c244c27dae6839d5efa87c07a7670d44eabf8e
|
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:c9b6acf84c8d039c1c602ca8f99089b30fd17d9beebe184abe44aba53e0b4d9d
|
3 |
+
size 2242911029
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fb90138dbc226604aee4cd7f5e9c6bc379ea396214b76e028d86ab85abd57ea
|
3 |
+
size 14575
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0239f4190e55f7513c148ab499fc64a3802c77544e1a724d2c18e6271c9ec785
|
3 |
+
size 627
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0007606731957782637,
|
5 |
+
"global_step": 4,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [],
|
10 |
+
"max_steps": 525800,
|
11 |
+
"num_train_epochs": 100,
|
12 |
+
"total_flos": 359729765176320.0,
|
13 |
+
"trial_name": null,
|
14 |
+
"trial_params": null
|
15 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4edaeb8c48a08839a7dab0eac28e4411ca3b23919775c3e93cd0d040b5cc2cf
|
3 |
+
size 3963
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9b6acf84c8d039c1c602ca8f99089b30fd17d9beebe184abe44aba53e0b4d9d
|
3 |
+
size 2242911029
|
runs/Jun09_18-16-00_e60ee0fa208b/events.out.tfevents.1686334565.e60ee0fa208b.621.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee8901c051a3862381dd9d0289fe3b75b9b9705bba19a1b995fece4c2871c614
|
3 |
+
size 4347
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4edaeb8c48a08839a7dab0eac28e4411ca3b23919775c3e93cd0d040b5cc2cf
|
3 |
+
size 3963
|