Commit
•
e93dd90
1
Parent(s):
8c84888
Training in progress, step 6400
Browse files- .gitignore +1 -0
- config.json +41 -0
- last-checkpoint/config.json +41 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +15 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +17 -0
- last-checkpoint/trainer_state.json +409 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/models/longformer-replicated-random-pos-encodings-4096",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"cls_token_id": 0,
|
| 19 |
+
"eos_token_id": 2,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_act": "gelu",
|
| 22 |
+
"hidden_dropout_prob": 0.1,
|
| 23 |
+
"hidden_size": 768,
|
| 24 |
+
"ignore_attention_mask": false,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 4098,
|
| 29 |
+
"model_max_length": 4096,
|
| 30 |
+
"model_type": "longformer",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 6,
|
| 33 |
+
"pad_token_id": 1,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"sep_token_id": 2,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.20.0",
|
| 38 |
+
"type_vocab_size": 1,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50265
|
| 41 |
+
}
|
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/models/longformer-replicated-random-pos-encodings-4096",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"cls_token_id": 0,
|
| 19 |
+
"eos_token_id": 2,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_act": "gelu",
|
| 22 |
+
"hidden_dropout_prob": 0.1,
|
| 23 |
+
"hidden_size": 768,
|
| 24 |
+
"ignore_attention_mask": false,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 4098,
|
| 29 |
+
"model_max_length": 4096,
|
| 30 |
+
"model_type": "longformer",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 6,
|
| 33 |
+
"pad_token_id": 1,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"sep_token_id": 2,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.20.0",
|
| 38 |
+
"type_vocab_size": 1,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50265
|
| 41 |
+
}
|
last-checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768403e40ef24719f9874bffdb116dac53668a99c00e4e33eefffb1d608e2344
|
| 3 |
+
size 166971723
|
last-checkpoint/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd622ee944edad1403b47d7d3094143fdec8b0c7996031b5cf2e20e83239116e
|
| 3 |
+
size 382294563
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dba08963cd8662bc2571f405f460c8c72ebf7c284eca70fb8787e17881f55d3b
|
| 3 |
+
size 15523
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8e4d707c7718e9baeb8896ef586b8a849cf9f9da184de0c131d6ac2046e66da
|
| 3 |
+
size 623
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"model_max_length": 4096,
|
| 10 |
+
"name_or_path": "data/models/longformer-replicated-random-pos-encodings-4096",
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"special_tokens_map_file": null,
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 6400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.5625e-06,
|
| 13 |
+
"loss": 6.9056,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 3.125e-06,
|
| 19 |
+
"loss": 6.0648,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 25 |
+
"loss": 5.7713,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 6.25e-06,
|
| 31 |
+
"loss": 5.6855,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 7.8125e-06,
|
| 37 |
+
"loss": 5.6563,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 9.375000000000001e-06,
|
| 43 |
+
"loss": 5.6212,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 1.09375e-05,
|
| 49 |
+
"loss": 5.6477,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.12,
|
| 54 |
+
"learning_rate": 1.25e-05,
|
| 55 |
+
"loss": 5.5888,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"learning_rate": 1.4062500000000001e-05,
|
| 61 |
+
"loss": 5.5783,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.16,
|
| 66 |
+
"learning_rate": 1.5625e-05,
|
| 67 |
+
"loss": 5.5722,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.17,
|
| 72 |
+
"learning_rate": 1.71875e-05,
|
| 73 |
+
"loss": 5.5792,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.19,
|
| 78 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 79 |
+
"loss": 5.5576,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2,
|
| 84 |
+
"learning_rate": 2.0312500000000002e-05,
|
| 85 |
+
"loss": 5.5382,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22,
|
| 90 |
+
"learning_rate": 2.1875e-05,
|
| 91 |
+
"loss": 5.5523,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.23,
|
| 96 |
+
"learning_rate": 2.34375e-05,
|
| 97 |
+
"loss": 5.5438,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.25,
|
| 102 |
+
"learning_rate": 2.5e-05,
|
| 103 |
+
"loss": 5.5019,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.27,
|
| 108 |
+
"learning_rate": 2.6562500000000002e-05,
|
| 109 |
+
"loss": 5.5062,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.28,
|
| 114 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 115 |
+
"loss": 5.5222,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.3,
|
| 120 |
+
"learning_rate": 2.96875e-05,
|
| 121 |
+
"loss": 5.5033,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.31,
|
| 126 |
+
"learning_rate": 3.125e-05,
|
| 127 |
+
"loss": 5.5172,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.33,
|
| 132 |
+
"learning_rate": 3.2812500000000005e-05,
|
| 133 |
+
"loss": 5.5073,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.34,
|
| 138 |
+
"learning_rate": 3.4375e-05,
|
| 139 |
+
"loss": 5.5096,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.36,
|
| 144 |
+
"learning_rate": 3.59375e-05,
|
| 145 |
+
"loss": 5.5062,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.38,
|
| 150 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 151 |
+
"loss": 5.505,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.39,
|
| 156 |
+
"learning_rate": 3.90625e-05,
|
| 157 |
+
"loss": 5.4843,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.41,
|
| 162 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 163 |
+
"loss": 5.4931,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.42,
|
| 168 |
+
"learning_rate": 4.21875e-05,
|
| 169 |
+
"loss": 5.4763,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.44,
|
| 174 |
+
"learning_rate": 4.375e-05,
|
| 175 |
+
"loss": 5.4743,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.45,
|
| 180 |
+
"learning_rate": 4.5312500000000004e-05,
|
| 181 |
+
"loss": 5.4694,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.47,
|
| 186 |
+
"learning_rate": 4.6875e-05,
|
| 187 |
+
"loss": 5.4848,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.48,
|
| 192 |
+
"learning_rate": 4.8437500000000005e-05,
|
| 193 |
+
"loss": 5.4686,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.5,
|
| 198 |
+
"learning_rate": 5e-05,
|
| 199 |
+
"loss": 5.4841,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.52,
|
| 204 |
+
"learning_rate": 5.15625e-05,
|
| 205 |
+
"loss": 5.4468,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.53,
|
| 210 |
+
"learning_rate": 5.3125000000000004e-05,
|
| 211 |
+
"loss": 5.4505,
|
| 212 |
+
"step": 3400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.55,
|
| 216 |
+
"learning_rate": 5.46875e-05,
|
| 217 |
+
"loss": 5.4143,
|
| 218 |
+
"step": 3500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.56,
|
| 222 |
+
"learning_rate": 5.6250000000000005e-05,
|
| 223 |
+
"loss": 5.3818,
|
| 224 |
+
"step": 3600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.58,
|
| 228 |
+
"learning_rate": 5.78125e-05,
|
| 229 |
+
"loss": 5.3292,
|
| 230 |
+
"step": 3700
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.59,
|
| 234 |
+
"learning_rate": 5.9375e-05,
|
| 235 |
+
"loss": 5.2801,
|
| 236 |
+
"step": 3800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.61,
|
| 240 |
+
"learning_rate": 6.0937500000000004e-05,
|
| 241 |
+
"loss": 5.2343,
|
| 242 |
+
"step": 3900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.62,
|
| 246 |
+
"learning_rate": 6.25e-05,
|
| 247 |
+
"loss": 5.1744,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.64,
|
| 252 |
+
"learning_rate": 6.40625e-05,
|
| 253 |
+
"loss": 5.1309,
|
| 254 |
+
"step": 4100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.66,
|
| 258 |
+
"learning_rate": 6.562500000000001e-05,
|
| 259 |
+
"loss": 5.0384,
|
| 260 |
+
"step": 4200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.67,
|
| 264 |
+
"learning_rate": 6.71875e-05,
|
| 265 |
+
"loss": 4.8088,
|
| 266 |
+
"step": 4300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.69,
|
| 270 |
+
"learning_rate": 6.875e-05,
|
| 271 |
+
"loss": 4.4311,
|
| 272 |
+
"step": 4400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.7,
|
| 276 |
+
"learning_rate": 7.031250000000001e-05,
|
| 277 |
+
"loss": 3.9741,
|
| 278 |
+
"step": 4500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.72,
|
| 282 |
+
"learning_rate": 7.1875e-05,
|
| 283 |
+
"loss": 3.5943,
|
| 284 |
+
"step": 4600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.73,
|
| 288 |
+
"learning_rate": 7.34375e-05,
|
| 289 |
+
"loss": 3.3068,
|
| 290 |
+
"step": 4700
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.75,
|
| 294 |
+
"learning_rate": 7.500000000000001e-05,
|
| 295 |
+
"loss": 3.0763,
|
| 296 |
+
"step": 4800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.77,
|
| 300 |
+
"learning_rate": 7.65625e-05,
|
| 301 |
+
"loss": 2.9353,
|
| 302 |
+
"step": 4900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.78,
|
| 306 |
+
"learning_rate": 7.8125e-05,
|
| 307 |
+
"loss": 2.7872,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.8,
|
| 312 |
+
"learning_rate": 7.96875e-05,
|
| 313 |
+
"loss": 2.7278,
|
| 314 |
+
"step": 5100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.81,
|
| 318 |
+
"learning_rate": 8.125000000000001e-05,
|
| 319 |
+
"loss": 2.6579,
|
| 320 |
+
"step": 5200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.83,
|
| 324 |
+
"learning_rate": 8.28125e-05,
|
| 325 |
+
"loss": 2.6168,
|
| 326 |
+
"step": 5300
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.84,
|
| 330 |
+
"learning_rate": 8.4375e-05,
|
| 331 |
+
"loss": 2.5703,
|
| 332 |
+
"step": 5400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.86,
|
| 336 |
+
"learning_rate": 8.593750000000001e-05,
|
| 337 |
+
"loss": 2.5617,
|
| 338 |
+
"step": 5500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.88,
|
| 342 |
+
"learning_rate": 8.75e-05,
|
| 343 |
+
"loss": 2.5283,
|
| 344 |
+
"step": 5600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.89,
|
| 348 |
+
"learning_rate": 8.90625e-05,
|
| 349 |
+
"loss": 2.5204,
|
| 350 |
+
"step": 5700
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.91,
|
| 354 |
+
"learning_rate": 9.062500000000001e-05,
|
| 355 |
+
"loss": 2.4751,
|
| 356 |
+
"step": 5800
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.92,
|
| 360 |
+
"learning_rate": 9.21875e-05,
|
| 361 |
+
"loss": 2.4574,
|
| 362 |
+
"step": 5900
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.94,
|
| 366 |
+
"learning_rate": 9.375e-05,
|
| 367 |
+
"loss": 2.45,
|
| 368 |
+
"step": 6000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.95,
|
| 372 |
+
"learning_rate": 9.53125e-05,
|
| 373 |
+
"loss": 2.4293,
|
| 374 |
+
"step": 6100
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.97,
|
| 378 |
+
"learning_rate": 9.687500000000001e-05,
|
| 379 |
+
"loss": 2.3883,
|
| 380 |
+
"step": 6200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.98,
|
| 384 |
+
"learning_rate": 9.84375e-05,
|
| 385 |
+
"loss": 2.4105,
|
| 386 |
+
"step": 6300
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.0,
|
| 390 |
+
"learning_rate": 0.0001,
|
| 391 |
+
"loss": 2.4034,
|
| 392 |
+
"step": 6400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.0,
|
| 396 |
+
"eval_accuracy": 0.6022303017856984,
|
| 397 |
+
"eval_loss": 2.167095899581909,
|
| 398 |
+
"eval_runtime": 42429.4228,
|
| 399 |
+
"eval_samples_per_second": 7.727,
|
| 400 |
+
"eval_steps_per_second": 0.966,
|
| 401 |
+
"step": 6400
|
| 402 |
+
}
|
| 403 |
+
],
|
| 404 |
+
"max_steps": 6400,
|
| 405 |
+
"num_train_epochs": 9223372036854775807,
|
| 406 |
+
"total_flos": 2.707934115004416e+17,
|
| 407 |
+
"trial_name": null,
|
| 408 |
+
"trial_params": null
|
| 409 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69ce2ed76b51bc748236916fb1576c16ad30075cccff9f164ec341c1d31d7b5
|
| 3 |
+
size 3439
|
last-checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd622ee944edad1403b47d7d3094143fdec8b0c7996031b5cf2e20e83239116e
|
| 3 |
+
size 382294563
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"model_max_length": 4096,
|
| 10 |
+
"name_or_path": "data/models/longformer-replicated-random-pos-encodings-4096",
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"special_tokens_map_file": null,
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69ce2ed76b51bc748236916fb1576c16ad30075cccff9f164ec341c1d31d7b5
|
| 3 |
+
size 3439
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|