Training in progress, step 2500
Browse files- model.safetensors +1 -1
- run-17/checkpoint-1000/config.json +26 -0
- run-17/checkpoint-1000/model.safetensors +3 -0
- run-17/checkpoint-1000/optimizer.pt +3 -0
- run-17/checkpoint-1000/rng_state.pth +3 -0
- run-17/checkpoint-1000/scheduler.pt +3 -0
- run-17/checkpoint-1000/special_tokens_map.json +7 -0
- run-17/checkpoint-1000/tokenizer.json +0 -0
- run-17/checkpoint-1000/tokenizer_config.json +55 -0
- run-17/checkpoint-1000/trainer_state.json +56 -0
- run-17/checkpoint-1000/training_args.bin +3 -0
- run-17/checkpoint-1000/vocab.txt +0 -0
- run-17/checkpoint-1500/config.json +26 -0
- run-17/checkpoint-1500/model.safetensors +3 -0
- run-17/checkpoint-1500/optimizer.pt +3 -0
- run-17/checkpoint-1500/rng_state.pth +3 -0
- run-17/checkpoint-1500/scheduler.pt +3 -0
- run-17/checkpoint-1500/special_tokens_map.json +7 -0
- run-17/checkpoint-1500/tokenizer.json +0 -0
- run-17/checkpoint-1500/tokenizer_config.json +55 -0
- run-17/checkpoint-1500/trainer_state.json +81 -0
- run-17/checkpoint-1500/training_args.bin +3 -0
- run-17/checkpoint-1500/vocab.txt +0 -0
- run-17/checkpoint-2000/config.json +26 -0
- run-17/checkpoint-2000/model.safetensors +3 -0
- run-17/checkpoint-2000/optimizer.pt +3 -0
- run-17/checkpoint-2000/rng_state.pth +3 -0
- run-17/checkpoint-2000/scheduler.pt +3 -0
- run-17/checkpoint-2000/special_tokens_map.json +7 -0
- run-17/checkpoint-2000/tokenizer.json +0 -0
- run-17/checkpoint-2000/tokenizer_config.json +55 -0
- run-17/checkpoint-2000/trainer_state.json +97 -0
- run-17/checkpoint-2000/training_args.bin +3 -0
- run-17/checkpoint-2000/vocab.txt +0 -0
- run-17/checkpoint-2500/config.json +26 -0
- run-17/checkpoint-2500/model.safetensors +3 -0
- run-17/checkpoint-2500/optimizer.pt +3 -0
- run-17/checkpoint-2500/rng_state.pth +3 -0
- run-17/checkpoint-2500/scheduler.pt +3 -0
- run-17/checkpoint-2500/special_tokens_map.json +7 -0
- run-17/checkpoint-2500/tokenizer.json +0 -0
- run-17/checkpoint-2500/tokenizer_config.json +55 -0
- run-17/checkpoint-2500/trainer_state.json +113 -0
- run-17/checkpoint-2500/training_args.bin +3 -0
- run-17/checkpoint-2500/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 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba88df82084094bc409117729c56e9915f519fe11511336d3518480a59910d1a
|
3 |
size 1340618660
|
run-17/checkpoint-1000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
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": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-17/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057b9e1867677fbd5499053a29400081b7298d170f8b93c45c629ae2f3618862
|
3 |
+
size 1340618660
|
run-17/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f6e28532186d34520ebd7bf1eeaa1a58d5b9cf7aebb380b01eeb01f294a15b
|
3 |
+
size 2681472237
|
run-17/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6949adde667cc7db368e471ea1969496fea33ff9958e5640141668dd757db138
|
3 |
+
size 14244
|
run-17/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ab7c664234ee2f7d316303541148769993682d56ee70d6dea91baa228f2f55c
|
3 |
+
size 1064
|
run-17/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-17/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/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": true,
|
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-17/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.680965147453083,
|
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_accuracy": 0.758632242679596,
|
14 |
+
"eval_loss": 0.4715859889984131,
|
15 |
+
"eval_runtime": 9.5006,
|
16 |
+
"eval_samples_per_second": 313.981,
|
17 |
+
"eval_steps_per_second": 19.683,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 9.62618637084961,
|
23 |
+
"learning_rate": 1.4776902224208135e-05,
|
24 |
+
"loss": 0.5101,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7727120518684387,
|
30 |
+
"eval_loss": 0.47308608889579773,
|
31 |
+
"eval_runtime": 9.4715,
|
32 |
+
"eval_samples_per_second": 314.944,
|
33 |
+
"eval_steps_per_second": 19.743,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 17.83710289001465,
|
39 |
+
"learning_rate": 1.2489456059470035e-05,
|
40 |
+
"loss": 0.2485,
|
41 |
+
"step": 1000
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 500,
|
45 |
+
"max_steps": 3730,
|
46 |
+
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 10,
|
48 |
+
"save_steps": 500,
|
49 |
+
"total_flos": 6202193407669944.0,
|
50 |
+
"train_batch_size": 32,
|
51 |
+
"trial_name": null,
|
52 |
+
"trial_params": {
|
53 |
+
"learning_rate": 1.7064348388946237e-05,
|
54 |
+
"per_device_train_batch_size": 32
|
55 |
+
}
|
56 |
+
}
|
run-17/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
|
3 |
+
size 5048
|
run-17/checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/checkpoint-1500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
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": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-17/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a245021c89ae0f4b30755f412484cd177be18bb3ba3c45ba24ecf5b32aae536
|
3 |
+
size 1340618660
|
run-17/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf92448bb65174d2675ba5841372631e866a84d073ca95a85a8df81af445ea3
|
3 |
+
size 2681472237
|
run-17/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52d6297fc05e3c669d3d417f48b67e1a84e4173733817fe3972c260ec2f9f2dd
|
3 |
+
size 14244
|
run-17/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b1ca2346581968dfb9a14faf67f7694ee2d13ebad847376e5aca3f3b13cf19d
|
3 |
+
size 1064
|
run-17/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-17/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/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": true,
|
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-17/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.021447721179625,
|
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_accuracy": 0.758632242679596,
|
14 |
+
"eval_loss": 0.4715859889984131,
|
15 |
+
"eval_runtime": 9.5006,
|
16 |
+
"eval_samples_per_second": 313.981,
|
17 |
+
"eval_steps_per_second": 19.683,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 9.62618637084961,
|
23 |
+
"learning_rate": 1.4776902224208135e-05,
|
24 |
+
"loss": 0.5101,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7727120518684387,
|
30 |
+
"eval_loss": 0.47308608889579773,
|
31 |
+
"eval_runtime": 9.4715,
|
32 |
+
"eval_samples_per_second": 314.944,
|
33 |
+
"eval_steps_per_second": 19.743,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 17.83710289001465,
|
39 |
+
"learning_rate": 1.2489456059470035e-05,
|
40 |
+
"loss": 0.2485,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7743881940841675,
|
46 |
+
"eval_loss": 0.7006397843360901,
|
47 |
+
"eval_runtime": 9.4464,
|
48 |
+
"eval_samples_per_second": 315.781,
|
49 |
+
"eval_steps_per_second": 19.796,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7750586867332458,
|
55 |
+
"eval_loss": 0.8257986903190613,
|
56 |
+
"eval_runtime": 9.4942,
|
57 |
+
"eval_samples_per_second": 314.193,
|
58 |
+
"eval_steps_per_second": 19.696,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 0.4933696985244751,
|
64 |
+
"learning_rate": 1.0202009894731932e-05,
|
65 |
+
"loss": 0.0969,
|
66 |
+
"step": 1500
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 500,
|
70 |
+
"max_steps": 3730,
|
71 |
+
"num_input_tokens_seen": 0,
|
72 |
+
"num_train_epochs": 10,
|
73 |
+
"save_steps": 500,
|
74 |
+
"total_flos": 8976711158170848.0,
|
75 |
+
"train_batch_size": 32,
|
76 |
+
"trial_name": null,
|
77 |
+
"trial_params": {
|
78 |
+
"learning_rate": 1.7064348388946237e-05,
|
79 |
+
"per_device_train_batch_size": 32
|
80 |
+
}
|
81 |
+
}
|
run-17/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
|
3 |
+
size 5048
|
run-17/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/checkpoint-2000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
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": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-17/checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f103ac74e7190e9bd7dde45c303121cc8f057045a2e8489d0a0c847d923dd22
|
3 |
+
size 1340618660
|
run-17/checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c92ee584307e7e6ed7a632220970b18583b4ec0562256ea6375b1d578f5b55a
|
3 |
+
size 2681472237
|
run-17/checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:721c19c3e780a4dbbdea0a58f53b8fa2858454326b4fe853dc8a1ee3b6a9fe47
|
3 |
+
size 14244
|
run-17/checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d3d96c59fbd383bfccad8d540bb15c6155a04ecca599781e03be94652ee230a
|
3 |
+
size 1064
|
run-17/checkpoint-2000/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-17/checkpoint-2000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/checkpoint-2000/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": true,
|
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-17/checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 0.758632242679596,
|
14 |
+
"eval_loss": 0.4715859889984131,
|
15 |
+
"eval_runtime": 9.5006,
|
16 |
+
"eval_samples_per_second": 313.981,
|
17 |
+
"eval_steps_per_second": 19.683,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 9.62618637084961,
|
23 |
+
"learning_rate": 1.4776902224208135e-05,
|
24 |
+
"loss": 0.5101,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7727120518684387,
|
30 |
+
"eval_loss": 0.47308608889579773,
|
31 |
+
"eval_runtime": 9.4715,
|
32 |
+
"eval_samples_per_second": 314.944,
|
33 |
+
"eval_steps_per_second": 19.743,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 17.83710289001465,
|
39 |
+
"learning_rate": 1.2489456059470035e-05,
|
40 |
+
"loss": 0.2485,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7743881940841675,
|
46 |
+
"eval_loss": 0.7006397843360901,
|
47 |
+
"eval_runtime": 9.4464,
|
48 |
+
"eval_samples_per_second": 315.781,
|
49 |
+
"eval_steps_per_second": 19.796,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7750586867332458,
|
55 |
+
"eval_loss": 0.8257986903190613,
|
56 |
+
"eval_runtime": 9.4942,
|
57 |
+
"eval_samples_per_second": 314.193,
|
58 |
+
"eval_steps_per_second": 19.696,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 0.4933696985244751,
|
64 |
+
"learning_rate": 1.0202009894731932e-05,
|
65 |
+
"loss": 0.0969,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.782433807849884,
|
71 |
+
"eval_loss": 0.9035575985908508,
|
72 |
+
"eval_runtime": 9.4688,
|
73 |
+
"eval_samples_per_second": 315.034,
|
74 |
+
"eval_steps_per_second": 19.749,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 15.212503433227539,
|
80 |
+
"learning_rate": 7.91456372999383e-06,
|
81 |
+
"loss": 0.0396,
|
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 |
+
"total_flos": 1.1737297309933476e+16,
|
91 |
+
"train_batch_size": 32,
|
92 |
+
"trial_name": null,
|
93 |
+
"trial_params": {
|
94 |
+
"learning_rate": 1.7064348388946237e-05,
|
95 |
+
"per_device_train_batch_size": 32
|
96 |
+
}
|
97 |
+
}
|
run-17/checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
|
3 |
+
size 5048
|
run-17/checkpoint-2000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/checkpoint-2500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
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": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-17/checkpoint-2500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba88df82084094bc409117729c56e9915f519fe11511336d3518480a59910d1a
|
3 |
+
size 1340618660
|
run-17/checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c70ce5067a322a7e93d01b7405dd7a797129d852ccdc6a0480cba789284552
|
3 |
+
size 2681472237
|
run-17/checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ba21e6de271ea59300bf3a1775b2bf5221b252ebeca24277a3f0a7fb49d6db7
|
3 |
+
size 14244
|
run-17/checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f0161288af8ce9e511aaa937c8b5a4565158059f54cb614b06746e2035b2424
|
3 |
+
size 1064
|
run-17/checkpoint-2500/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-17/checkpoint-2500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-17/checkpoint-2500/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": true,
|
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-17/checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.702412868632708,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
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": 0.758632242679596,
|
14 |
+
"eval_loss": 0.4715859889984131,
|
15 |
+
"eval_runtime": 9.5006,
|
16 |
+
"eval_samples_per_second": 313.981,
|
17 |
+
"eval_steps_per_second": 19.683,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 9.62618637084961,
|
23 |
+
"learning_rate": 1.4776902224208135e-05,
|
24 |
+
"loss": 0.5101,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7727120518684387,
|
30 |
+
"eval_loss": 0.47308608889579773,
|
31 |
+
"eval_runtime": 9.4715,
|
32 |
+
"eval_samples_per_second": 314.944,
|
33 |
+
"eval_steps_per_second": 19.743,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 17.83710289001465,
|
39 |
+
"learning_rate": 1.2489456059470035e-05,
|
40 |
+
"loss": 0.2485,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7743881940841675,
|
46 |
+
"eval_loss": 0.7006397843360901,
|
47 |
+
"eval_runtime": 9.4464,
|
48 |
+
"eval_samples_per_second": 315.781,
|
49 |
+
"eval_steps_per_second": 19.796,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7750586867332458,
|
55 |
+
"eval_loss": 0.8257986903190613,
|
56 |
+
"eval_runtime": 9.4942,
|
57 |
+
"eval_samples_per_second": 314.193,
|
58 |
+
"eval_steps_per_second": 19.696,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 0.4933696985244751,
|
64 |
+
"learning_rate": 1.0202009894731932e-05,
|
65 |
+
"loss": 0.0969,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.782433807849884,
|
71 |
+
"eval_loss": 0.9035575985908508,
|
72 |
+
"eval_runtime": 9.4688,
|
73 |
+
"eval_samples_per_second": 315.034,
|
74 |
+
"eval_steps_per_second": 19.749,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 15.212503433227539,
|
80 |
+
"learning_rate": 7.91456372999383e-06,
|
81 |
+
"loss": 0.0396,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.7844451665878296,
|
87 |
+
"eval_loss": 1.023715853691101,
|
88 |
+
"eval_runtime": 9.6126,
|
89 |
+
"eval_samples_per_second": 310.323,
|
90 |
+
"eval_steps_per_second": 19.454,
|
91 |
+
"step": 2238
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.702412868632708,
|
95 |
+
"grad_norm": 1.1762652397155762,
|
96 |
+
"learning_rate": 5.627117565255729e-06,
|
97 |
+
"loss": 0.0231,
|
98 |
+
"step": 2500
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"logging_steps": 500,
|
102 |
+
"max_steps": 3730,
|
103 |
+
"num_input_tokens_seen": 0,
|
104 |
+
"num_train_epochs": 10,
|
105 |
+
"save_steps": 500,
|
106 |
+
"total_flos": 1.4515495448812848e+16,
|
107 |
+
"train_batch_size": 32,
|
108 |
+
"trial_name": null,
|
109 |
+
"trial_params": {
|
110 |
+
"learning_rate": 1.7064348388946237e-05,
|
111 |
+
"per_device_train_batch_size": 32
|
112 |
+
}
|
113 |
+
}
|
run-17/checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c3f1c022f8eda659addce16f3d5138c7caaea20a2bef78832f3c6c75c342488
|
3 |
+
size 5048
|
run-17/checkpoint-2500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|