Training in progress, epoch 4
Browse files- checkpoint-844/config.json +39 -0
- checkpoint-844/merges.txt +0 -0
- checkpoint-844/optimizer.pt +3 -0
- checkpoint-844/pytorch_model.bin +3 -0
- checkpoint-844/rng_state.pth +3 -0
- checkpoint-844/scaler.pt +3 -0
- checkpoint-844/scheduler.pt +3 -0
- checkpoint-844/special_tokens_map.json +1 -0
- checkpoint-844/tokenizer.json +0 -0
- checkpoint-844/tokenizer_config.json +1 -0
- checkpoint-844/trainer_state.json +80 -0
- checkpoint-844/training_args.bin +3 -0
- checkpoint-844/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-844/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
|
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 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "multi_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.17.0",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50265
|
39 |
+
}
|
checkpoint-844/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-844/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c579fc6ddb1f17c1736400033951a275d8bbb268f8989d32cad321f8374bb76f
|
3 |
+
size 997299037
|
checkpoint-844/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d03d7644b10c719efacf7fbd260c6ba981ac5d0c564857645aeadf3943566346
|
3 |
+
size 498678125
|
checkpoint-844/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0487f06942310f56988716181ac8658db049f458ca5d577c45d0d90addb47433
|
3 |
+
size 14503
|
checkpoint-844/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90627cd2342f633a788643c0991a7770782a6d9e013a6b9234cf0af9b0018643
|
3 |
+
size 559
|
checkpoint-844/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:238454f2ad5121cfbc5e76f2cdf7bd0c8afadb1b43361b771eb9c17a2f812e07
|
3 |
+
size 623
|
checkpoint-844/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
checkpoint-844/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-844/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}
|
checkpoint-844/trainer_state.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7684440341259363,
|
3 |
+
"best_model_checkpoint": "outputs/time_lm_nli/checkpoint-844",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 844,
|
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": 9.666666666666666e-07,
|
13 |
+
"loss": 0.5392,
|
14 |
+
"step": 211
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7,
|
19 |
+
"eval_f1": 0.6998718119161117,
|
20 |
+
"eval_loss": 0.4048246741294861,
|
21 |
+
"eval_runtime": 5.0256,
|
22 |
+
"eval_samples_per_second": 596.939,
|
23 |
+
"eval_steps_per_second": 74.617,
|
24 |
+
"step": 211
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 9.333333333333333e-07,
|
29 |
+
"loss": 0.3725,
|
30 |
+
"step": 422
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.759,
|
35 |
+
"eval_f1": 0.7583549419422403,
|
36 |
+
"eval_loss": 0.3489450216293335,
|
37 |
+
"eval_runtime": 5.103,
|
38 |
+
"eval_samples_per_second": 587.885,
|
39 |
+
"eval_steps_per_second": 73.486,
|
40 |
+
"step": 422
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"learning_rate": 9e-07,
|
45 |
+
"loss": 0.3158,
|
46 |
+
"step": 633
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.0,
|
50 |
+
"eval_accuracy": 0.7613333333333333,
|
51 |
+
"eval_f1": 0.7569694772671423,
|
52 |
+
"eval_loss": 0.3286795914173126,
|
53 |
+
"eval_runtime": 5.4646,
|
54 |
+
"eval_samples_per_second": 548.991,
|
55 |
+
"eval_steps_per_second": 68.624,
|
56 |
+
"step": 633
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"learning_rate": 8.666666666666667e-07,
|
61 |
+
"loss": 0.289,
|
62 |
+
"step": 844
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.0,
|
66 |
+
"eval_accuracy": 0.769,
|
67 |
+
"eval_f1": 0.7684440341259363,
|
68 |
+
"eval_loss": 0.33065709471702576,
|
69 |
+
"eval_runtime": 5.2159,
|
70 |
+
"eval_samples_per_second": 575.162,
|
71 |
+
"eval_steps_per_second": 71.895,
|
72 |
+
"step": 844
|
73 |
+
}
|
74 |
+
],
|
75 |
+
"max_steps": 6330,
|
76 |
+
"num_train_epochs": 30,
|
77 |
+
"total_flos": 5732616477926016.0,
|
78 |
+
"trial_name": null,
|
79 |
+
"trial_params": null
|
80 |
+
}
|
checkpoint-844/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
|
3 |
+
size 3119
|
checkpoint-844/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498678125
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d03d7644b10c719efacf7fbd260c6ba981ac5d0c564857645aeadf3943566346
|
3 |
size 498678125
|