itsanastasiaminina
commited on
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-4/checkpoint-1126/config.json +44 -0
- run-4/checkpoint-1126/merges.txt +0 -0
- run-4/checkpoint-1126/model.safetensors +3 -0
- run-4/checkpoint-1126/optimizer.pt +3 -0
- run-4/checkpoint-1126/rng_state.pth +3 -0
- run-4/checkpoint-1126/scheduler.pt +3 -0
- run-4/checkpoint-1126/special_tokens_map.json +15 -0
- run-4/checkpoint-1126/tokenizer.json +0 -0
- run-4/checkpoint-1126/tokenizer_config.json +58 -0
- run-4/checkpoint-1126/trainer_state.json +70 -0
- run-4/checkpoint-1126/training_args.bin +3 -0
- run-4/checkpoint-1126/vocab.json +0 -0
- runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733700639.6ff5f1d99a72.23.4 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498625128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3da82207b392e8f05a0dbdc7c2d34132095b3a67a17fa5c60c1e45bda6db4174
|
3 |
size 498625128
|
run-4/checkpoint-1126/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"max_position_embeddings": 514,
|
33 |
+
"model_type": "roberta",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.47.0",
|
41 |
+
"type_vocab_size": 1,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 50265
|
44 |
+
}
|
run-4/checkpoint-1126/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-1126/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3da82207b392e8f05a0dbdc7c2d34132095b3a67a17fa5c60c1e45bda6db4174
|
3 |
+
size 498625128
|
run-4/checkpoint-1126/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c39862d2454bc4ff7044b4a670db55ffeb0f444398f2afa4ade6ac5d94ea919
|
3 |
+
size 997370106
|
run-4/checkpoint-1126/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:279aab4142ba2bc15a26a5c73e18f555c0949931f163d68de9a3f73e4f0c4c00
|
3 |
+
size 14244
|
run-4/checkpoint-1126/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0850865a33497a8ffeb7857347a0a8f5bc632a6ec45b428ecebb858c432a1956
|
3 |
+
size 1064
|
run-4/checkpoint-1126/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-4/checkpoint-1126/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-1126/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
run-4/checkpoint-1126/trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6268681418752026,
|
3 |
+
"best_model_checkpoint": "students_scores_model/run-4/checkpoint-1126",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1126,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.8880994671403197,
|
13 |
+
"grad_norm": 12.275317192077637,
|
14 |
+
"learning_rate": 1.4598246141554418e-05,
|
15 |
+
"loss": 1.0768,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_f1": 0.5337342004113407,
|
21 |
+
"eval_loss": 1.0920056104660034,
|
22 |
+
"eval_runtime": 37.5701,
|
23 |
+
"eval_samples_per_second": 59.888,
|
24 |
+
"eval_steps_per_second": 7.506,
|
25 |
+
"step": 563
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.7761989342806395,
|
29 |
+
"grad_norm": 22.032495498657227,
|
30 |
+
"learning_rate": 1.1445277212492988e-05,
|
31 |
+
"loss": 0.881,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_f1": 0.6268681418752026,
|
37 |
+
"eval_loss": 0.8564010858535767,
|
38 |
+
"eval_runtime": 37.4689,
|
39 |
+
"eval_samples_per_second": 60.05,
|
40 |
+
"eval_steps_per_second": 7.526,
|
41 |
+
"step": 1126
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 500,
|
45 |
+
"max_steps": 2815,
|
46 |
+
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 5,
|
48 |
+
"save_steps": 500,
|
49 |
+
"stateful_callbacks": {
|
50 |
+
"TrainerControl": {
|
51 |
+
"args": {
|
52 |
+
"should_epoch_stop": false,
|
53 |
+
"should_evaluate": false,
|
54 |
+
"should_log": false,
|
55 |
+
"should_save": true,
|
56 |
+
"should_training_stop": false
|
57 |
+
},
|
58 |
+
"attributes": {}
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"total_flos": 4207559992768512.0,
|
62 |
+
"train_batch_size": 16,
|
63 |
+
"trial_name": null,
|
64 |
+
"trial_params": {
|
65 |
+
"learning_rate": 1.7751215070615847e-05,
|
66 |
+
"num_train_epochs": 5,
|
67 |
+
"per_device_train_batch_size": 16,
|
68 |
+
"weight_decay": 0.0002884204184667258
|
69 |
+
}
|
70 |
+
}
|
run-4/checkpoint-1126/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a62e1f6a90ed4f39459c087d00d082ce1ebfa6be7f9d0f437b408dd861a50103
|
3 |
+
size 5368
|
run-4/checkpoint-1126/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733700639.6ff5f1d99a72.23.4
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 sha256:5192a84440dff153d418b06619596ab55ee5617aff4b77c9627dd39885a2a261
|
3 |
+
size 6411
|