ana-grassmann
commited on
Commit
•
28a3c92
1
Parent(s):
3f350e6
Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- run-2/checkpoint-1670/config.json +27 -0
- run-2/checkpoint-1670/model.safetensors +3 -0
- run-2/checkpoint-1670/optimizer.pt +3 -0
- run-2/checkpoint-1670/rng_state.pth +3 -0
- run-2/checkpoint-1670/scheduler.pt +3 -0
- run-2/checkpoint-1670/special_tokens_map.json +7 -0
- run-2/checkpoint-1670/tokenizer.json +0 -0
- run-2/checkpoint-1670/tokenizer_config.json +55 -0
- run-2/checkpoint-1670/trainer_state.json +65 -0
- run-2/checkpoint-1670/training_args.bin +3 -0
- run-2/checkpoint-1670/vocab.txt +0 -0
- run-2/checkpoint-2505/config.json +27 -0
- run-2/checkpoint-2505/model.safetensors +3 -0
- run-2/checkpoint-2505/optimizer.pt +3 -0
- run-2/checkpoint-2505/rng_state.pth +3 -0
- run-2/checkpoint-2505/scheduler.pt +3 -0
- run-2/checkpoint-2505/special_tokens_map.json +7 -0
- run-2/checkpoint-2505/tokenizer.json +0 -0
- run-2/checkpoint-2505/tokenizer_config.json +55 -0
- run-2/checkpoint-2505/trainer_state.json +88 -0
- run-2/checkpoint-2505/training_args.bin +3 -0
- run-2/checkpoint-2505/vocab.txt +0 -0
- runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711044833.43ee8d6b3d53.2090.2 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6458b38be86ba67defe561c40e1db21ab4144316144239d277d7f1e512bde76b
|
3 |
size 437958648
|
run-2/checkpoint-1670/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-2/checkpoint-1670/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be35a3d411bc35fed7fdc809ce6545086982ff7d9fe890e9a4d30ec2fc6fc8d4
|
3 |
+
size 437958648
|
run-2/checkpoint-1670/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f4d82a98e256f6420f3356ccfef7792f1366a52ccaa09ab70dbf72445a56699
|
3 |
+
size 876038394
|
run-2/checkpoint-1670/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1973054123b1a43ae6bcf711559ed696684422d3bbbcfbcff810d254274a5564
|
3 |
+
size 14308
|
run-2/checkpoint-1670/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad3af729c7d8ea65c4b10c86adab49e116200f20014cddeb5608a3b54dbbaf81
|
3 |
+
size 1064
|
run-2/checkpoint-1670/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-1670/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-1670/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-1670/trainer_state.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9615338526063512,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-1670",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1670,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6,
|
13 |
+
"grad_norm": 9.117546081542969,
|
14 |
+
"learning_rate": 1.8393158320232495e-06,
|
15 |
+
"loss": 0.4054,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.9505692031156381,
|
21 |
+
"eval_loss": 0.14854364097118378,
|
22 |
+
"eval_runtime": 597.8505,
|
23 |
+
"eval_samples_per_second": 27.917,
|
24 |
+
"eval_steps_per_second": 1.746,
|
25 |
+
"step": 835
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.2,
|
29 |
+
"grad_norm": 1.4320781230926514,
|
30 |
+
"learning_rate": 1.3806335796483742e-06,
|
31 |
+
"loss": 0.1311,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.8,
|
36 |
+
"grad_norm": 0.354846715927124,
|
37 |
+
"learning_rate": 9.219513272734991e-07,
|
38 |
+
"loss": 0.1227,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy": 0.9615338526063512,
|
44 |
+
"eval_loss": 0.14428438246250153,
|
45 |
+
"eval_runtime": 598.1778,
|
46 |
+
"eval_samples_per_second": 27.901,
|
47 |
+
"eval_steps_per_second": 1.745,
|
48 |
+
"step": 1670
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 500,
|
52 |
+
"max_steps": 2505,
|
53 |
+
"num_input_tokens_seen": 0,
|
54 |
+
"num_train_epochs": 3,
|
55 |
+
"save_steps": 500,
|
56 |
+
"total_flos": 2989060811086560.0,
|
57 |
+
"train_batch_size": 8,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": {
|
60 |
+
"learning_rate": 2.2979980843981246e-06,
|
61 |
+
"num_train_epochs": 3,
|
62 |
+
"per_device_train_batch_size": 8,
|
63 |
+
"seed": 24
|
64 |
+
}
|
65 |
+
}
|
run-2/checkpoint-1670/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:977ec9eece5f9e2273a7d887d95fb9be8edae8feee607dd3c107f6aa9ef3e0c5
|
3 |
+
size 4920
|
run-2/checkpoint-1670/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2505/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-2/checkpoint-2505/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6458b38be86ba67defe561c40e1db21ab4144316144239d277d7f1e512bde76b
|
3 |
+
size 437958648
|
run-2/checkpoint-2505/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11c5aace133e1e21503f083a644ea260ac77a3f46956625250fd04508f88ec93
|
3 |
+
size 876038394
|
run-2/checkpoint-2505/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e170e789601099e166fa7d94560bc4ef242e68f90d991a9bc880b71b78ec790f
|
3 |
+
size 14308
|
run-2/checkpoint-2505/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab76da5daacf986d3d66bf97f36600e932908880e195fdfbb9c18c426d6ae82
|
3 |
+
size 1064
|
run-2/checkpoint-2505/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-2505/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2505/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-2505/trainer_state.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9615338526063512,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-1670",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2505,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6,
|
13 |
+
"grad_norm": 9.117546081542969,
|
14 |
+
"learning_rate": 1.8393158320232495e-06,
|
15 |
+
"loss": 0.4054,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.9505692031156381,
|
21 |
+
"eval_loss": 0.14854364097118378,
|
22 |
+
"eval_runtime": 597.8505,
|
23 |
+
"eval_samples_per_second": 27.917,
|
24 |
+
"eval_steps_per_second": 1.746,
|
25 |
+
"step": 835
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.2,
|
29 |
+
"grad_norm": 1.4320781230926514,
|
30 |
+
"learning_rate": 1.3806335796483742e-06,
|
31 |
+
"loss": 0.1311,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.8,
|
36 |
+
"grad_norm": 0.354846715927124,
|
37 |
+
"learning_rate": 9.219513272734991e-07,
|
38 |
+
"loss": 0.1227,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy": 0.9615338526063512,
|
44 |
+
"eval_loss": 0.14428438246250153,
|
45 |
+
"eval_runtime": 598.1778,
|
46 |
+
"eval_samples_per_second": 27.901,
|
47 |
+
"eval_steps_per_second": 1.745,
|
48 |
+
"step": 1670
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.4,
|
52 |
+
"grad_norm": 2.810948371887207,
|
53 |
+
"learning_rate": 4.6326907489862395e-07,
|
54 |
+
"loss": 0.1123,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.99,
|
59 |
+
"grad_norm": 0.04734252020716667,
|
60 |
+
"learning_rate": 4.586822523748751e-09,
|
61 |
+
"loss": 0.0837,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.0,
|
66 |
+
"eval_accuracy": 0.9608148591971241,
|
67 |
+
"eval_loss": 0.15702731907367706,
|
68 |
+
"eval_runtime": 598.8615,
|
69 |
+
"eval_samples_per_second": 27.87,
|
70 |
+
"eval_steps_per_second": 1.743,
|
71 |
+
"step": 2505
|
72 |
+
}
|
73 |
+
],
|
74 |
+
"logging_steps": 500,
|
75 |
+
"max_steps": 2505,
|
76 |
+
"num_input_tokens_seen": 0,
|
77 |
+
"num_train_epochs": 3,
|
78 |
+
"save_steps": 500,
|
79 |
+
"total_flos": 4990682275848000.0,
|
80 |
+
"train_batch_size": 8,
|
81 |
+
"trial_name": null,
|
82 |
+
"trial_params": {
|
83 |
+
"learning_rate": 2.2979980843981246e-06,
|
84 |
+
"num_train_epochs": 3,
|
85 |
+
"per_device_train_batch_size": 8,
|
86 |
+
"seed": 24
|
87 |
+
}
|
88 |
+
}
|
run-2/checkpoint-2505/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:977ec9eece5f9e2273a7d887d95fb9be8edae8feee607dd3c107f6aa9ef3e0c5
|
3 |
+
size 4920
|
run-2/checkpoint-2505/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar21_16-50-03_43ee8d6b3d53/events.out.tfevents.1711044833.43ee8d6b3d53.2090.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eba714a9ae2b41d127b7950dc58da826298510e121d9f21f7e8c3b4b6375afb
|
3 |
+
size 7017
|