Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-moubnul5/checkpoint-1500/config.json +36 -0
- run-moubnul5/checkpoint-1500/model.safetensors +3 -0
- run-moubnul5/checkpoint-1500/optimizer.pt +3 -0
- run-moubnul5/checkpoint-1500/rng_state.pth +3 -0
- run-moubnul5/checkpoint-1500/scheduler.pt +3 -0
- run-moubnul5/checkpoint-1500/special_tokens_map.json +7 -0
- run-moubnul5/checkpoint-1500/tokenizer.json +0 -0
- run-moubnul5/checkpoint-1500/tokenizer_config.json +55 -0
- run-moubnul5/checkpoint-1500/trainer_state.json +116 -0
- run-moubnul5/checkpoint-1500/training_args.bin +3 -0
- run-moubnul5/checkpoint-1500/vocab.txt +0 -0
- run-rstr4mx4/checkpoint-500/config.json +36 -0
- run-rstr4mx4/checkpoint-500/model.safetensors +3 -0
- run-rstr4mx4/checkpoint-500/optimizer.pt +3 -0
- run-rstr4mx4/checkpoint-500/rng_state.pth +3 -0
- run-rstr4mx4/checkpoint-500/scheduler.pt +3 -0
- run-rstr4mx4/checkpoint-500/special_tokens_map.json +7 -0
- run-rstr4mx4/checkpoint-500/tokenizer.json +0 -0
- run-rstr4mx4/checkpoint-500/tokenizer_config.json +55 -0
- run-rstr4mx4/checkpoint-500/trainer_state.json +88 -0
- run-rstr4mx4/checkpoint-500/training_args.bin +3 -0
- run-rstr4mx4/checkpoint-500/vocab.txt +0 -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 430911284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b851075172d50769116d12249a9cff22e8c21976931d8165a57d7498ec6667c1
|
3 |
size 430911284
|
run-moubnul5/checkpoint-1500/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.41.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
run-moubnul5/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72499718ac926766f5468d262201bcc97e778acb5445043206214e875b740e84
|
3 |
+
size 430911284
|
run-moubnul5/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97068838fc3520b68bda214528044c4eda5bcd6b81e067058b1515d82254de74
|
3 |
+
size 861942330
|
run-moubnul5/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2623190ade7475a14422c6523b005c8acd111f240775a08c6f4ab59256d8d57
|
3 |
+
size 14244
|
run-moubnul5/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c760e131eecd128de99d6ae96641dcf76e359c1e356bd934c4313d53dd4fdfc
|
3 |
+
size 1064
|
run-moubnul5/checkpoint-1500/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-moubnul5/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-moubnul5/checkpoint-1500/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": false,
|
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-moubnul5/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.901960784313726,
|
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": 1.0,
|
13 |
+
"eval_f1": 0.515832482124617,
|
14 |
+
"eval_f1_sklearn": 0.9513251883367813,
|
15 |
+
"eval_loss": 0.12229713052511215,
|
16 |
+
"eval_precision": 0.5629877369007804,
|
17 |
+
"eval_precision_sklearn": 0.9513251883367813,
|
18 |
+
"eval_recall": 0.4759660697455231,
|
19 |
+
"eval_recall_sklearn": 0.9513251883367813,
|
20 |
+
"eval_runtime": 4.2613,
|
21 |
+
"eval_samples_per_second": 95.745,
|
22 |
+
"eval_steps_per_second": 23.936,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 1.7371214628219604,
|
28 |
+
"learning_rate": 6.73202614379085e-05,
|
29 |
+
"loss": 0.1032,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_f1": 0.507920792079208,
|
35 |
+
"eval_f1_sklearn": 0.9493735118466763,
|
36 |
+
"eval_loss": 0.16793084144592285,
|
37 |
+
"eval_precision": 0.5349322210636079,
|
38 |
+
"eval_precision_sklearn": 0.9493735118466763,
|
39 |
+
"eval_recall": 0.48350612629594725,
|
40 |
+
"eval_recall_sklearn": 0.9493735118466763,
|
41 |
+
"eval_runtime": 6.1428,
|
42 |
+
"eval_samples_per_second": 66.42,
|
43 |
+
"eval_steps_per_second": 16.605,
|
44 |
+
"step": 612
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_f1": 0.6094600251151109,
|
49 |
+
"eval_f1_sklearn": 0.9524181271712401,
|
50 |
+
"eval_loss": 0.16153906285762787,
|
51 |
+
"eval_precision": 0.5481927710843374,
|
52 |
+
"eval_precision_sklearn": 0.9524181271712401,
|
53 |
+
"eval_recall": 0.6861451460885957,
|
54 |
+
"eval_recall_sklearn": 0.9524181271712401,
|
55 |
+
"eval_runtime": 5.1328,
|
56 |
+
"eval_samples_per_second": 79.488,
|
57 |
+
"eval_steps_per_second": 19.872,
|
58 |
+
"step": 918
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.2679738562091503,
|
62 |
+
"grad_norm": 0.30743545293807983,
|
63 |
+
"learning_rate": 3.464052287581699e-05,
|
64 |
+
"loss": 0.0309,
|
65 |
+
"step": 1000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_f1": 0.5933147632311978,
|
70 |
+
"eval_f1_sklearn": 0.9537452671845115,
|
71 |
+
"eval_loss": 0.18510332703590393,
|
72 |
+
"eval_precision": 0.5846294602012809,
|
73 |
+
"eval_precision_sklearn": 0.9537452671845115,
|
74 |
+
"eval_recall": 0.6022620169651273,
|
75 |
+
"eval_recall_sklearn": 0.9537452671845115,
|
76 |
+
"eval_runtime": 4.6906,
|
77 |
+
"eval_samples_per_second": 86.982,
|
78 |
+
"eval_steps_per_second": 21.746,
|
79 |
+
"step": 1224
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 4.901960784313726,
|
83 |
+
"grad_norm": 0.012615224346518517,
|
84 |
+
"learning_rate": 1.96078431372549e-06,
|
85 |
+
"loss": 0.0077,
|
86 |
+
"step": 1500
|
87 |
+
}
|
88 |
+
],
|
89 |
+
"logging_steps": 500,
|
90 |
+
"max_steps": 1530,
|
91 |
+
"num_input_tokens_seen": 0,
|
92 |
+
"num_train_epochs": 5,
|
93 |
+
"save_steps": 500,
|
94 |
+
"stateful_callbacks": {
|
95 |
+
"TrainerControl": {
|
96 |
+
"args": {
|
97 |
+
"should_epoch_stop": false,
|
98 |
+
"should_evaluate": false,
|
99 |
+
"should_log": false,
|
100 |
+
"should_save": true,
|
101 |
+
"should_training_stop": false
|
102 |
+
},
|
103 |
+
"attributes": {}
|
104 |
+
}
|
105 |
+
},
|
106 |
+
"total_flos": 470773232452584.0,
|
107 |
+
"train_batch_size": 4,
|
108 |
+
"trial_name": null,
|
109 |
+
"trial_params": {
|
110 |
+
"_wandb": {},
|
111 |
+
"assignments": {},
|
112 |
+
"learning_rate": 0.0001,
|
113 |
+
"metric": "eval/loss",
|
114 |
+
"per_device_train_batch_size": 4
|
115 |
+
}
|
116 |
+
}
|
run-moubnul5/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c89dc8df7f3fb0987257613d8306e14cf03e86313d666bec5ca1670eced74774
|
3 |
+
size 5112
|
run-moubnul5/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-rstr4mx4/checkpoint-500/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.41.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
run-rstr4mx4/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b851075172d50769116d12249a9cff22e8c21976931d8165a57d7498ec6667c1
|
3 |
+
size 430911284
|
run-rstr4mx4/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d236b1fab577737a3f8670ca4cf7455ac362d8b2a3df06f1b7b6b0fa39be881c
|
3 |
+
size 861942330
|
run-rstr4mx4/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7a801e52b02802e184980e68632305a0661a666536a8c36170f2de2d9852f4e
|
3 |
+
size 14244
|
run-rstr4mx4/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c81b034b86eebaffe44e92389aedc2049503c0d1a95608e020f982e69e75c97f
|
3 |
+
size 1064
|
run-rstr4mx4/checkpoint-500/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-rstr4mx4/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-rstr4mx4/checkpoint-500/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": false,
|
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-rstr4mx4/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.2679738562091503,
|
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_f1": 0.2111706197398623,
|
14 |
+
"eval_f1_sklearn": 0.9420352082438815,
|
15 |
+
"eval_loss": 0.16127675771713257,
|
16 |
+
"eval_precision": 0.5609756097560976,
|
17 |
+
"eval_precision_sklearn": 0.9420352082438815,
|
18 |
+
"eval_recall": 0.13006597549481622,
|
19 |
+
"eval_recall_sklearn": 0.9420352082438815,
|
20 |
+
"eval_runtime": 4.3006,
|
21 |
+
"eval_samples_per_second": 94.87,
|
22 |
+
"eval_steps_per_second": 23.718,
|
23 |
+
"step": 153
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_f1": 0.40728631480616534,
|
28 |
+
"eval_f1_sklearn": 0.9447285218002264,
|
29 |
+
"eval_loss": 0.14659850299358368,
|
30 |
+
"eval_precision": 0.40370370370370373,
|
31 |
+
"eval_precision_sklearn": 0.9447285218002264,
|
32 |
+
"eval_recall": 0.410933081998115,
|
33 |
+
"eval_recall_sklearn": 0.9447285218002264,
|
34 |
+
"eval_runtime": 4.3654,
|
35 |
+
"eval_samples_per_second": 93.462,
|
36 |
+
"eval_steps_per_second": 23.365,
|
37 |
+
"step": 306
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.0,
|
41 |
+
"eval_f1": 0.4323818437061301,
|
42 |
+
"eval_f1_sklearn": 0.9470705335883524,
|
43 |
+
"eval_loss": 0.1423368901014328,
|
44 |
+
"eval_precision": 0.42936802973977695,
|
45 |
+
"eval_precision_sklearn": 0.9470705335883524,
|
46 |
+
"eval_recall": 0.4354382657869934,
|
47 |
+
"eval_recall_sklearn": 0.9470705335883524,
|
48 |
+
"eval_runtime": 4.343,
|
49 |
+
"eval_samples_per_second": 93.944,
|
50 |
+
"eval_steps_per_second": 23.486,
|
51 |
+
"step": 459
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.2679738562091503,
|
55 |
+
"grad_norm": 1.8578802347183228,
|
56 |
+
"learning_rate": 1.7320261437908499e-06,
|
57 |
+
"loss": 0.1506,
|
58 |
+
"step": 500
|
59 |
+
}
|
60 |
+
],
|
61 |
+
"logging_steps": 500,
|
62 |
+
"max_steps": 765,
|
63 |
+
"num_input_tokens_seen": 0,
|
64 |
+
"num_train_epochs": 5,
|
65 |
+
"save_steps": 500,
|
66 |
+
"stateful_callbacks": {
|
67 |
+
"TrainerControl": {
|
68 |
+
"args": {
|
69 |
+
"should_epoch_stop": false,
|
70 |
+
"should_evaluate": false,
|
71 |
+
"should_log": false,
|
72 |
+
"should_save": true,
|
73 |
+
"should_training_stop": false
|
74 |
+
},
|
75 |
+
"attributes": {}
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"total_flos": 433135952304768.0,
|
79 |
+
"train_batch_size": 8,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": {
|
82 |
+
"_wandb": {},
|
83 |
+
"assignments": {},
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"metric": "eval/loss",
|
86 |
+
"per_device_train_batch_size": 8
|
87 |
+
}
|
88 |
+
}
|
run-rstr4mx4/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0faac25d416a58bb76b05100d0033c9bd328d14d03906ad62dab5d8d399b71
|
3 |
+
size 5112
|
run-rstr4mx4/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0faac25d416a58bb76b05100d0033c9bd328d14d03906ad62dab5d8d399b71
|
3 |
size 5112
|