Commit
•
091f97b
1
Parent(s):
c4f195e
Training in progress, epoch 1
Browse files- checkpoint-156/config.json +33 -0
- checkpoint-156/optimizer.pt +3 -0
- checkpoint-156/pytorch_model.bin +3 -0
- checkpoint-156/rng_state.pth +3 -0
- checkpoint-156/scheduler.pt +3 -0
- checkpoint-156/special_tokens_map.json +1 -0
- checkpoint-156/tokenizer.json +0 -0
- checkpoint-156/tokenizer_config.json +1 -0
- checkpoint-156/trainer_state.json +31 -0
- checkpoint-156/training_args.bin +3 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- runs/Sep19_05-47-04_patrick-general-gpu/1632030438.9398863/events.out.tfevents.1632030438.patrick-general-gpu.457696.1 +3 -0
- runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030438.patrick-general-gpu.457696.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
checkpoint-156/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/fnet-base",
|
3 |
+
"architectures": [
|
4 |
+
"FNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"finetuning_task": "rte",
|
9 |
+
"hidden_act": "gelu_new",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "entailment",
|
14 |
+
"1": "not_entailment"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"entailment": 0,
|
20 |
+
"not_entailment": 1
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "fnet",
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 3,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"tpu_short_seq_length": 512,
|
29 |
+
"transformers_version": "4.11.0.dev0",
|
30 |
+
"type_vocab_size": 4,
|
31 |
+
"use_tpu_fourier_optimizations": false,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
checkpoint-156/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78ed9e7586b5cc5cbaa6e752109dbb3176e62e9874483c60990d5a020ac509a2
|
3 |
+
size 662962197
|
checkpoint-156/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fda7052f3995f536c79c4af7fb0a0b4b15b9578629e2550fda87cc8bbcda3e3
|
3 |
+
size 331497705
|
checkpoint-156/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3927dd24ed19afd43e88bf753f6ef22f89cdfdc770fec0b5f3a564015aaa36ae
|
3 |
+
size 14503
|
checkpoint-156/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d44bf0b290d7260d7cb19febd23337b0ea2c26d13f1d6375331d9082a571fb15
|
3 |
+
size 623
|
checkpoint-156/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
checkpoint-156/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-156/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
|
checkpoint-156/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 156,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.3333333333333333e-05,
|
13 |
+
"loss": 0.6829,
|
14 |
+
"step": 156
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.5703971119133574,
|
19 |
+
"eval_loss": 0.6657100915908813,
|
20 |
+
"eval_runtime": 2.0131,
|
21 |
+
"eval_samples_per_second": 137.6,
|
22 |
+
"eval_steps_per_second": 17.386,
|
23 |
+
"step": 156
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 468,
|
27 |
+
"num_train_epochs": 3,
|
28 |
+
"total_flos": 442819159879680.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
checkpoint-156/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2785b0a5856d6dcded05366f24390f17de2bc55f955abf2c62f58cd45feda2ba
|
3 |
+
size 2735
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/fnet-base",
|
3 |
+
"architectures": [
|
4 |
+
"FNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"finetuning_task": "rte",
|
9 |
+
"hidden_act": "gelu_new",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "entailment",
|
14 |
+
"1": "not_entailment"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"entailment": 0,
|
20 |
+
"not_entailment": 1
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "fnet",
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 3,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"tpu_short_seq_length": 512,
|
29 |
+
"transformers_version": "4.11.0.dev0",
|
30 |
+
"type_vocab_size": 4,
|
31 |
+
"use_tpu_fourier_optimizations": false,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fda7052f3995f536c79c4af7fb0a0b4b15b9578629e2550fda87cc8bbcda3e3
|
3 |
+
size 331497705
|
runs/Sep19_05-47-04_patrick-general-gpu/1632030438.9398863/events.out.tfevents.1632030438.patrick-general-gpu.457696.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36bfb739482e767901d6f3d75b263ec9b17ef60c25c31897e46053eaf3dec862
|
3 |
+
size 4348
|
runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030438.patrick-general-gpu.457696.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dcf250953a643295f0b083aa6995d62a18c75d3ba3ef02f4b39929017088292
|
3 |
+
size 3660
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2785b0a5856d6dcded05366f24390f17de2bc55f955abf2c62f58cd45feda2ba
|
3 |
+
size 2735
|