Training in progress, step 1500
Browse files- model.safetensors +1 -1
- run-1/checkpoint-1000/config.json +27 -0
- run-1/checkpoint-1000/merges.txt +0 -0
- run-1/checkpoint-1000/model.safetensors +3 -0
- run-1/checkpoint-1000/optimizer.pt +3 -0
- run-1/checkpoint-1000/rng_state.pth +3 -0
- run-1/checkpoint-1000/scheduler.pt +3 -0
- run-1/checkpoint-1000/special_tokens_map.json +15 -0
- run-1/checkpoint-1000/tokenizer.json +0 -0
- run-1/checkpoint-1000/tokenizer_config.json +57 -0
- run-1/checkpoint-1000/trainer_state.json +47 -0
- run-1/checkpoint-1000/training_args.bin +3 -0
- run-1/checkpoint-1000/vocab.json +0 -0
- run-1/checkpoint-1500/config.json +27 -0
- run-1/checkpoint-1500/merges.txt +0 -0
- run-1/checkpoint-1500/model.safetensors +3 -0
- run-1/checkpoint-1500/optimizer.pt +3 -0
- run-1/checkpoint-1500/rng_state.pth +3 -0
- run-1/checkpoint-1500/scheduler.pt +3 -0
- run-1/checkpoint-1500/special_tokens_map.json +15 -0
- run-1/checkpoint-1500/tokenizer.json +0 -0
- run-1/checkpoint-1500/tokenizer_config.json +57 -0
- run-1/checkpoint-1500/trainer_state.json +63 -0
- run-1/checkpoint-1500/training_args.bin +3 -0
- run-1/checkpoint-1500/vocab.json +0 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1421491284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d00a31c7cb527ad1a1335df4c61a91062ae184e2bb421f7cacb319bbb6bb8034
|
3 |
size 1421491284
|
run-1/checkpoint-1000/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
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": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
run-1/checkpoint-1000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080cf12f0324eea6384ce82a39ff67189338441aa627133bb9dc86b4e9ffa0da
|
3 |
+
size 1421491284
|
run-1/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de3568eaf4aa4fffc051a1b7ee95e5a0aafd63d19cd9dd4e8c19144c1ea1d36
|
3 |
+
size 2843215085
|
run-1/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69851e864833fa417035572442bf2bbebc95eba78b78f0fc5621d6dac9ce3c6c
|
3 |
+
size 14244
|
run-1/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09cd695c52a762cf63b8d7a0d0da6914563cc1a4f9d2b6a3195b5de07f0de6e5
|
3 |
+
size 1064
|
run-1/checkpoint-1000/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-1/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1000/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-1/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3404825737265416,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 23.28346824645996,
|
14 |
+
"learning_rate": 9.798511296679954e-06,
|
15 |
+
"loss": 0.5531,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.8025477528572083,
|
21 |
+
"eval_loss": 0.4079710841178894,
|
22 |
+
"eval_runtime": 9.2612,
|
23 |
+
"eval_samples_per_second": 322.097,
|
24 |
+
"eval_steps_per_second": 20.192,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 38.64032745361328,
|
30 |
+
"learning_rate": 9.094595255251797e-06,
|
31 |
+
"loss": 0.3957,
|
32 |
+
"step": 1000
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 500,
|
36 |
+
"max_steps": 7460,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 10,
|
39 |
+
"save_steps": 500,
|
40 |
+
"total_flos": 2642653548489780.0,
|
41 |
+
"train_batch_size": 16,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": {
|
44 |
+
"learning_rate": 1.0502427338108112e-05,
|
45 |
+
"per_device_train_batch_size": 16
|
46 |
+
}
|
47 |
+
}
|
run-1/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
|
3 |
+
size 5048
|
run-1/checkpoint-1000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1500/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
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": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
run-1/checkpoint-1500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d00a31c7cb527ad1a1335df4c61a91062ae184e2bb421f7cacb319bbb6bb8034
|
3 |
+
size 1421491284
|
run-1/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8997bac711939a34a4ab1b7fd28a054631fbe0dd69763cbe5640410ecb50579
|
3 |
+
size 2843215085
|
run-1/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb5b0f4cef17b25c72b6f541a3214c0ca149eb3e3e912fea00200b1029f064f
|
3 |
+
size 14244
|
run-1/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d864545f452d5cafa8087496f7a2458b82579cc9d857c2edf7aa084448eb66a6
|
3 |
+
size 1064
|
run-1/checkpoint-1500/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-1/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1500/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-1/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0107238605898123,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 23.28346824645996,
|
14 |
+
"learning_rate": 9.798511296679954e-06,
|
15 |
+
"loss": 0.5531,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.8025477528572083,
|
21 |
+
"eval_loss": 0.4079710841178894,
|
22 |
+
"eval_runtime": 9.2612,
|
23 |
+
"eval_samples_per_second": 322.097,
|
24 |
+
"eval_steps_per_second": 20.192,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 38.64032745361328,
|
30 |
+
"learning_rate": 9.094595255251797e-06,
|
31 |
+
"loss": 0.3957,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.8276902437210083,
|
37 |
+
"eval_loss": 0.42224231362342834,
|
38 |
+
"eval_runtime": 9.5099,
|
39 |
+
"eval_samples_per_second": 313.673,
|
40 |
+
"eval_steps_per_second": 19.664,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 34.970176696777344,
|
46 |
+
"learning_rate": 8.390679213823639e-06,
|
47 |
+
"loss": 0.3185,
|
48 |
+
"step": 1500
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 500,
|
52 |
+
"max_steps": 7460,
|
53 |
+
"num_input_tokens_seen": 0,
|
54 |
+
"num_train_epochs": 10,
|
55 |
+
"save_steps": 500,
|
56 |
+
"total_flos": 3956927155095420.0,
|
57 |
+
"train_batch_size": 16,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": {
|
60 |
+
"learning_rate": 1.0502427338108112e-05,
|
61 |
+
"per_device_train_batch_size": 16
|
62 |
+
}
|
63 |
+
}
|
run-1/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:347fad0a6bce6c8dd37383686ed909149e39a499f89f9086cdd2be432928a800
|
3 |
+
size 5048
|
run-1/checkpoint-1500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|