Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-16/checkpoint-500/config.json +27 -0
- run-16/checkpoint-500/merges.txt +0 -0
- run-16/checkpoint-500/model.safetensors +3 -0
- run-16/checkpoint-500/optimizer.pt +3 -0
- run-16/checkpoint-500/rng_state.pth +3 -0
- run-16/checkpoint-500/scheduler.pt +3 -0
- run-16/checkpoint-500/special_tokens_map.json +15 -0
- run-16/checkpoint-500/tokenizer.json +0 -0
- run-16/checkpoint-500/tokenizer_config.json +57 -0
- run-16/checkpoint-500/trainer_state.json +61 -0
- run-16/checkpoint-500/training_args.bin +3 -0
- run-16/checkpoint-500/vocab.json +0 -0
- runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637557.Donghao-Win.17160.14 +3 -0
- runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637711.Donghao-Win.17160.15 +3 -0
- runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637860.Donghao-Win.17160.16 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498609724
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d90c2fe40c0d1afd9fcd2b419492263273e7b7a3d0b9a97e9384f6ee7838fa
|
3 |
size 498609724
|
run-16/checkpoint-500/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMultipleChoice"
|
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": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
run-16/checkpoint-500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-16/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d90c2fe40c0d1afd9fcd2b419492263273e7b7a3d0b9a97e9384f6ee7838fa
|
3 |
+
size 498609724
|
run-16/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e361bf7c1d5d4da67ddfe0a944bbabca718cf3142d315f4f74b42a00af741c3
|
3 |
+
size 997339386
|
run-16/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a2fa13fa6a08330bce5df60846e9bf4a2d86b5474e12bc958621cb5d2087093
|
3 |
+
size 14244
|
run-16/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7f51d7dcdfced409113ca792f6eacb6db28243fb49ec23bc0c9a3496cebe8a2
|
3 |
+
size 1064
|
run-16/checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
run-16/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-16/checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
run-16/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.6737967914438503,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.6640965342521667,
|
14 |
+
"eval_loss": 0.5810248851776123,
|
15 |
+
"eval_runtime": 14.2872,
|
16 |
+
"eval_samples_per_second": 208.788,
|
17 |
+
"eval_steps_per_second": 13.089,
|
18 |
+
"step": 187
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.6832048296928406,
|
23 |
+
"eval_loss": 0.5652729272842407,
|
24 |
+
"eval_runtime": 13.8796,
|
25 |
+
"eval_samples_per_second": 214.919,
|
26 |
+
"eval_steps_per_second": 13.473,
|
27 |
+
"step": 374
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.6737967914438503,
|
31 |
+
"grad_norm": 6.708367824554443,
|
32 |
+
"learning_rate": 2.9957568655605055e-05,
|
33 |
+
"loss": 0.5459,
|
34 |
+
"step": 500
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 1870,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 10,
|
41 |
+
"save_steps": 500,
|
42 |
+
"stateful_callbacks": {
|
43 |
+
"TrainerControl": {
|
44 |
+
"args": {
|
45 |
+
"should_epoch_stop": false,
|
46 |
+
"should_evaluate": false,
|
47 |
+
"should_log": false,
|
48 |
+
"should_save": true,
|
49 |
+
"should_training_stop": false
|
50 |
+
},
|
51 |
+
"attributes": {}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"total_flos": 4056945908795220.0,
|
55 |
+
"train_batch_size": 64,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": {
|
58 |
+
"learning_rate": 4.089098787297916e-05,
|
59 |
+
"per_device_train_batch_size": 64
|
60 |
+
}
|
61 |
+
}
|
run-16/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e73e3d84bf9829ec622f70df68c58d7a86e31e66964e860a4b0d0dcc76bc94c
|
3 |
+
size 5176
|
run-16/checkpoint-500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637557.Donghao-Win.17160.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ddf7db456c46109ac9cdd9b7034e89d96ad7575a6005d4ea05306976d39d908
|
3 |
+
size 5191
|
runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637711.Donghao-Win.17160.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1fd56a93bf8257384950b8e7eea29138122f066e8f9b452e53a124e828d3050
|
3 |
+
size 5191
|
runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717637860.Donghao-Win.17160.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13900ca4790b9a46d8fb429227457bf48763475462450be2e116be8c4d609286
|
3 |
+
size 6694
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e73e3d84bf9829ec622f70df68c58d7a86e31e66964e860a4b0d0dcc76bc94c
|
3 |
size 5176
|