Training in progress, step 2000
Browse files- model.safetensors +1 -1
- run-0/checkpoint-2000/config.json +27 -0
- run-0/checkpoint-2000/merges.txt +0 -0
- run-0/checkpoint-2000/model.safetensors +3 -0
- run-0/checkpoint-2000/optimizer.pt +3 -0
- run-0/checkpoint-2000/rng_state.pth +3 -0
- run-0/checkpoint-2000/scheduler.pt +3 -0
- run-0/checkpoint-2000/special_tokens_map.json +15 -0
- run-0/checkpoint-2000/tokenizer.json +0 -0
- run-0/checkpoint-2000/tokenizer_config.json +57 -0
- run-0/checkpoint-2000/trainer_state.json +109 -0
- run-0/checkpoint-2000/training_args.bin +3 -0
- run-0/checkpoint-2000/vocab.json +0 -0
- runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717604983.Donghao-Win.17160.0 +2 -2
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 sha256:58dbfd8ec2b53958943b4b551d983a7ce6d126bfb380f913ba5ca9125e2a97e6
|
3 |
size 498609724
|
run-0/checkpoint-2000/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-0/checkpoint-2000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58dbfd8ec2b53958943b4b551d983a7ce6d126bfb380f913ba5ca9125e2a97e6
|
3 |
+
size 498609724
|
run-0/checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f58a0e609a9e6483608aae9a2477d6b0bfa11e1d4f3d8c7a93ac0e2e7e23a1c
|
3 |
+
size 997339386
|
run-0/checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab10c79f86d8f5e2ea60f179fe5e2e0e86cc76e486e68b906eca66e21396fbe8
|
3 |
+
size 14244
|
run-0/checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d810efa397a3c482410a01f10039af64a345433ee8098861a099324167643703
|
3 |
+
size 1064
|
run-0/checkpoint-2000/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-0/checkpoint-2000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-2000/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-0/checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.361930294906166,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
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": 0.6429768800735474,
|
14 |
+
"eval_loss": 0.5945129990577698,
|
15 |
+
"eval_runtime": 45.8254,
|
16 |
+
"eval_samples_per_second": 65.095,
|
17 |
+
"eval_steps_per_second": 4.081,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 10.595976829528809,
|
23 |
+
"learning_rate": 8.574439800439004e-06,
|
24 |
+
"loss": 0.6212,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.6778411269187927,
|
30 |
+
"eval_loss": 0.5707619786262512,
|
31 |
+
"eval_runtime": 45.8803,
|
32 |
+
"eval_samples_per_second": 65.017,
|
33 |
+
"eval_steps_per_second": 4.076,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 11.34949779510498,
|
39 |
+
"learning_rate": 7.247127137832347e-06,
|
40 |
+
"loss": 0.5391,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.6744887828826904,
|
46 |
+
"eval_loss": 0.5923792123794556,
|
47 |
+
"eval_runtime": 51.3582,
|
48 |
+
"eval_samples_per_second": 58.082,
|
49 |
+
"eval_steps_per_second": 3.641,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.6761649250984192,
|
55 |
+
"eval_loss": 0.58919757604599,
|
56 |
+
"eval_runtime": 49.5338,
|
57 |
+
"eval_samples_per_second": 60.221,
|
58 |
+
"eval_steps_per_second": 3.775,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 10.796440124511719,
|
64 |
+
"learning_rate": 5.919814475225689e-06,
|
65 |
+
"loss": 0.4812,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.683875322341919,
|
71 |
+
"eval_loss": 0.6181617975234985,
|
72 |
+
"eval_runtime": 49.5046,
|
73 |
+
"eval_samples_per_second": 60.257,
|
74 |
+
"eval_steps_per_second": 3.777,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 20.43950653076172,
|
80 |
+
"learning_rate": 4.592501812619033e-06,
|
81 |
+
"loss": 0.4094,
|
82 |
+
"step": 2000
|
83 |
+
}
|
84 |
+
],
|
85 |
+
"logging_steps": 500,
|
86 |
+
"max_steps": 3730,
|
87 |
+
"num_input_tokens_seen": 0,
|
88 |
+
"num_train_epochs": 10,
|
89 |
+
"save_steps": 500,
|
90 |
+
"stateful_callbacks": {
|
91 |
+
"TrainerControl": {
|
92 |
+
"args": {
|
93 |
+
"should_epoch_stop": false,
|
94 |
+
"should_evaluate": false,
|
95 |
+
"should_log": false,
|
96 |
+
"should_save": true,
|
97 |
+
"should_training_stop": false
|
98 |
+
},
|
99 |
+
"attributes": {}
|
100 |
+
}
|
101 |
+
},
|
102 |
+
"total_flos": 2908653240038244.0,
|
103 |
+
"train_batch_size": 32,
|
104 |
+
"trial_name": null,
|
105 |
+
"trial_params": {
|
106 |
+
"learning_rate": 9.90175246304566e-06,
|
107 |
+
"per_device_train_batch_size": 32
|
108 |
+
}
|
109 |
+
}
|
run-0/checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1c707689e4d63e47693f0038153b73ae05c4398571232f06530682e53de0a7e
|
3 |
+
size 5176
|
run-0/checkpoint-2000/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.1717604983.Donghao-Win.17160.0
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 sha256:5c769a8d8c9303e9db728bf4804172b3e0955832cf48d49096754bb839dd29c8
|
3 |
+
size 7336
|