Training in progress, step 1500
Browse files- model.safetensors +1 -1
- run-b4o51kp9/checkpoint-1000/config.json +36 -0
- run-b4o51kp9/checkpoint-1000/model.safetensors +3 -0
- run-b4o51kp9/checkpoint-1000/optimizer.pt +3 -0
- run-b4o51kp9/checkpoint-1000/rng_state.pth +3 -0
- run-b4o51kp9/checkpoint-1000/scheduler.pt +3 -0
- run-b4o51kp9/checkpoint-1000/special_tokens_map.json +7 -0
- run-b4o51kp9/checkpoint-1000/tokenizer.json +0 -0
- run-b4o51kp9/checkpoint-1000/tokenizer_config.json +55 -0
- run-b4o51kp9/checkpoint-1000/trainer_state.json +95 -0
- run-b4o51kp9/checkpoint-1000/training_args.bin +3 -0
- run-b4o51kp9/checkpoint-1000/vocab.txt +0 -0
- run-b4o51kp9/checkpoint-1500/config.json +36 -0
- run-b4o51kp9/checkpoint-1500/model.safetensors +3 -0
- run-b4o51kp9/checkpoint-1500/optimizer.pt +3 -0
- run-b4o51kp9/checkpoint-1500/rng_state.pth +3 -0
- run-b4o51kp9/checkpoint-1500/scheduler.pt +3 -0
- run-b4o51kp9/checkpoint-1500/special_tokens_map.json +7 -0
- run-b4o51kp9/checkpoint-1500/tokenizer.json +0 -0
- run-b4o51kp9/checkpoint-1500/tokenizer_config.json +55 -0
- run-b4o51kp9/checkpoint-1500/trainer_state.json +116 -0
- run-b4o51kp9/checkpoint-1500/training_args.bin +3 -0
- run-b4o51kp9/checkpoint-1500/vocab.txt +0 -0
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 sha256:050918e5820244364467afc532f5d784b6fd7de82aaebcba6c2011c1f8914324
|
3 |
size 430911284
|
run-b4o51kp9/checkpoint-1000/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-b4o51kp9/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9181f0832fd34448c4590a38eeecc537241c100b70e84681cda9ccf3af8a63a
|
3 |
+
size 430911284
|
run-b4o51kp9/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2e4803e3de6f23e1a309cee59b3085d88189f68655a5f51f1276161313ad327
|
3 |
+
size 861942330
|
run-b4o51kp9/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a6506071cda30ec363ad5c19299436106e9bc716569a13a88656f006a4610af
|
3 |
+
size 14244
|
run-b4o51kp9/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:228e62be4ec2a61884a81683ae6fcf9553d3058c3712d77efa73596ea9872a1f
|
3 |
+
size 1064
|
run-b4o51kp9/checkpoint-1000/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-b4o51kp9/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-b4o51kp9/checkpoint-1000/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-b4o51kp9/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.2679738562091503,
|
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": 1.0,
|
13 |
+
"eval_f1": 0.0,
|
14 |
+
"eval_f1_sklearn": 0.938717358210703,
|
15 |
+
"eval_loss": 0.26024484634399414,
|
16 |
+
"eval_precision": 0.0,
|
17 |
+
"eval_precision_sklearn": 0.938717358210703,
|
18 |
+
"eval_recall": 0.0,
|
19 |
+
"eval_recall_sklearn": 0.938717358210703,
|
20 |
+
"eval_runtime": 4.1329,
|
21 |
+
"eval_samples_per_second": 98.721,
|
22 |
+
"eval_steps_per_second": 24.68,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 0.6803091168403625,
|
28 |
+
"learning_rate": 0.00033660130718954253,
|
29 |
+
"loss": 0.2299,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_f1": 0.0,
|
35 |
+
"eval_f1_sklearn": 0.938717358210703,
|
36 |
+
"eval_loss": 0.2626124322414398,
|
37 |
+
"eval_precision": 0.0,
|
38 |
+
"eval_precision_sklearn": 0.938717358210703,
|
39 |
+
"eval_recall": 0.0,
|
40 |
+
"eval_recall_sklearn": 0.938717358210703,
|
41 |
+
"eval_runtime": 6.0422,
|
42 |
+
"eval_samples_per_second": 67.525,
|
43 |
+
"eval_steps_per_second": 16.881,
|
44 |
+
"step": 612
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_f1": 0.0,
|
49 |
+
"eval_f1_sklearn": 0.938717358210703,
|
50 |
+
"eval_loss": 0.2532053291797638,
|
51 |
+
"eval_precision": 0.0,
|
52 |
+
"eval_precision_sklearn": 0.938717358210703,
|
53 |
+
"eval_recall": 0.0,
|
54 |
+
"eval_recall_sklearn": 0.938717358210703,
|
55 |
+
"eval_runtime": 5.8629,
|
56 |
+
"eval_samples_per_second": 69.59,
|
57 |
+
"eval_steps_per_second": 17.397,
|
58 |
+
"step": 918
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.2679738562091503,
|
62 |
+
"grad_norm": 1.0660769939422607,
|
63 |
+
"learning_rate": 0.00017320261437908497,
|
64 |
+
"loss": 0.2252,
|
65 |
+
"step": 1000
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 500,
|
69 |
+
"max_steps": 1530,
|
70 |
+
"num_input_tokens_seen": 0,
|
71 |
+
"num_train_epochs": 5,
|
72 |
+
"save_steps": 500,
|
73 |
+
"stateful_callbacks": {
|
74 |
+
"TrainerControl": {
|
75 |
+
"args": {
|
76 |
+
"should_epoch_stop": false,
|
77 |
+
"should_evaluate": false,
|
78 |
+
"should_log": false,
|
79 |
+
"should_save": true,
|
80 |
+
"should_training_stop": false
|
81 |
+
},
|
82 |
+
"attributes": {}
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"total_flos": 318346024442760.0,
|
86 |
+
"train_batch_size": 4,
|
87 |
+
"trial_name": null,
|
88 |
+
"trial_params": {
|
89 |
+
"_wandb": {},
|
90 |
+
"assignments": {},
|
91 |
+
"learning_rate": 0.0005,
|
92 |
+
"metric": "eval/loss",
|
93 |
+
"per_device_train_batch_size": 4
|
94 |
+
}
|
95 |
+
}
|
run-b4o51kp9/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e4920f1462d08f2e7fa314c958ffbd48b002704b4b1cc85a30b5c8fab2ab912
|
3 |
+
size 5112
|
run-b4o51kp9/checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-b4o51kp9/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-b4o51kp9/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:050918e5820244364467afc532f5d784b6fd7de82aaebcba6c2011c1f8914324
|
3 |
+
size 430911284
|
run-b4o51kp9/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d006315130b0f2708b403d6db476ffd0fb64ff4df3d8ac010242cfe84ad989
|
3 |
+
size 861942330
|
run-b4o51kp9/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-b4o51kp9/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a94cef5de60a47a593c212285b0969bb84d81422dbfcf3350fb9399897e15b06
|
3 |
+
size 1064
|
run-b4o51kp9/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-b4o51kp9/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-b4o51kp9/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-b4o51kp9/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": 0.0,
|
14 |
+
"eval_f1_sklearn": 0.938717358210703,
|
15 |
+
"eval_loss": 0.26024484634399414,
|
16 |
+
"eval_precision": 0.0,
|
17 |
+
"eval_precision_sklearn": 0.938717358210703,
|
18 |
+
"eval_recall": 0.0,
|
19 |
+
"eval_recall_sklearn": 0.938717358210703,
|
20 |
+
"eval_runtime": 4.1329,
|
21 |
+
"eval_samples_per_second": 98.721,
|
22 |
+
"eval_steps_per_second": 24.68,
|
23 |
+
"step": 306
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6339869281045751,
|
27 |
+
"grad_norm": 0.6803091168403625,
|
28 |
+
"learning_rate": 0.00033660130718954253,
|
29 |
+
"loss": 0.2299,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_f1": 0.0,
|
35 |
+
"eval_f1_sklearn": 0.938717358210703,
|
36 |
+
"eval_loss": 0.2626124322414398,
|
37 |
+
"eval_precision": 0.0,
|
38 |
+
"eval_precision_sklearn": 0.938717358210703,
|
39 |
+
"eval_recall": 0.0,
|
40 |
+
"eval_recall_sklearn": 0.938717358210703,
|
41 |
+
"eval_runtime": 6.0422,
|
42 |
+
"eval_samples_per_second": 67.525,
|
43 |
+
"eval_steps_per_second": 16.881,
|
44 |
+
"step": 612
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_f1": 0.0,
|
49 |
+
"eval_f1_sklearn": 0.938717358210703,
|
50 |
+
"eval_loss": 0.2532053291797638,
|
51 |
+
"eval_precision": 0.0,
|
52 |
+
"eval_precision_sklearn": 0.938717358210703,
|
53 |
+
"eval_recall": 0.0,
|
54 |
+
"eval_recall_sklearn": 0.938717358210703,
|
55 |
+
"eval_runtime": 5.8629,
|
56 |
+
"eval_samples_per_second": 69.59,
|
57 |
+
"eval_steps_per_second": 17.397,
|
58 |
+
"step": 918
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.2679738562091503,
|
62 |
+
"grad_norm": 1.0660769939422607,
|
63 |
+
"learning_rate": 0.00017320261437908497,
|
64 |
+
"loss": 0.2252,
|
65 |
+
"step": 1000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_f1": 0.0,
|
70 |
+
"eval_f1_sklearn": 0.938717358210703,
|
71 |
+
"eval_loss": 0.252130389213562,
|
72 |
+
"eval_precision": 0.0,
|
73 |
+
"eval_precision_sklearn": 0.938717358210703,
|
74 |
+
"eval_recall": 0.0,
|
75 |
+
"eval_recall_sklearn": 0.938717358210703,
|
76 |
+
"eval_runtime": 4.2115,
|
77 |
+
"eval_samples_per_second": 96.877,
|
78 |
+
"eval_steps_per_second": 24.219,
|
79 |
+
"step": 1224
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 4.901960784313726,
|
83 |
+
"grad_norm": 1.0557856559753418,
|
84 |
+
"learning_rate": 9.803921568627451e-06,
|
85 |
+
"loss": 0.2172,
|
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": 0.0005,
|
113 |
+
"metric": "eval/loss",
|
114 |
+
"per_device_train_batch_size": 4
|
115 |
+
}
|
116 |
+
}
|
run-b4o51kp9/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e4920f1462d08f2e7fa314c958ffbd48b002704b4b1cc85a30b5c8fab2ab912
|
3 |
+
size 5112
|
run-b4o51kp9/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|