williamLyh
commited on
Commit
•
8da1e43
1
Parent(s):
509418d
V1.0
Browse files- added_tokens.json +9 -0
- config.json +75 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- planner_prediction_test.json +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +64 -0
- trainer_state.json +288 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<0>": 50265,
|
| 3 |
+
"<1>": 50266,
|
| 4 |
+
"<2>": 50267,
|
| 5 |
+
"<3>": 50268,
|
| 6 |
+
"<4>": 50269,
|
| 7 |
+
"<5>": 50270,
|
| 8 |
+
"<6>": 50271
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.24.0",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50273
|
| 75 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eeab0ad012e171d7e3b17e1c6750890362eb34abd1a9b732eb86769c45f1a9b
|
| 3 |
+
size 1115564485
|
planner_prediction_test.json
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 sha256:9b8805eb1e08f8f57da0da087f6f093316d67ebef0c578f3463fcd8f2866ab1e
|
| 3 |
+
size 557995869
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ed49e0ce6761f099b7e02e2d4c514872e99a5f800610842e0425fe9949b3359
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53650e99e05a744e5967d70eabd778f5091d97e579fed75fd1b50fc937b25326
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"cls_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"errors": "replace",
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 1024,
|
| 37 |
+
"name_or_path": "facebook/bart-base",
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"special_tokens_map_file": null,
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"__type": "AddedToken",
|
| 58 |
+
"content": "<unk>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": true,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false
|
| 63 |
+
}
|
| 64 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.616636528028933,
|
| 5 |
+
"global_step": 8000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 8e-05,
|
| 13 |
+
"loss": 2.7434,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 7.814986123959297e-05,
|
| 19 |
+
"loss": 1.6287,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 7.629972247918594e-05,
|
| 25 |
+
"loss": 1.5903,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 7.444958371877891e-05,
|
| 31 |
+
"loss": 1.5706,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 7.259944495837189e-05,
|
| 37 |
+
"loss": 1.556,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"learning_rate": 7.074930619796485e-05,
|
| 43 |
+
"loss": 1.5469,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.63,
|
| 48 |
+
"learning_rate": 6.889916743755783e-05,
|
| 49 |
+
"loss": 1.5393,
|
| 50 |
+
"step": 1400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.72,
|
| 54 |
+
"learning_rate": 6.70490286771508e-05,
|
| 55 |
+
"loss": 1.5316,
|
| 56 |
+
"step": 1600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.81,
|
| 60 |
+
"learning_rate": 6.519888991674377e-05,
|
| 61 |
+
"loss": 1.5272,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.9,
|
| 66 |
+
"learning_rate": 6.334875115633673e-05,
|
| 67 |
+
"loss": 1.5229,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.9,
|
| 72 |
+
"eval_loss": 1.9172784090042114,
|
| 73 |
+
"eval_runtime": 137.7477,
|
| 74 |
+
"eval_samples_per_second": 884.196,
|
| 75 |
+
"eval_steps_per_second": 3.456,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.99,
|
| 80 |
+
"learning_rate": 6.14986123959297e-05,
|
| 81 |
+
"loss": 1.5171,
|
| 82 |
+
"step": 2200
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.08,
|
| 86 |
+
"learning_rate": 5.964847363552267e-05,
|
| 87 |
+
"loss": 1.507,
|
| 88 |
+
"step": 2400
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.18,
|
| 92 |
+
"learning_rate": 5.779833487511564e-05,
|
| 93 |
+
"loss": 1.5052,
|
| 94 |
+
"step": 2600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.27,
|
| 98 |
+
"learning_rate": 5.5948196114708607e-05,
|
| 99 |
+
"loss": 1.5016,
|
| 100 |
+
"step": 2800
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.36,
|
| 104 |
+
"learning_rate": 5.4098057354301575e-05,
|
| 105 |
+
"loss": 1.5007,
|
| 106 |
+
"step": 3000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.45,
|
| 110 |
+
"learning_rate": 5.224791859389455e-05,
|
| 111 |
+
"loss": 1.4962,
|
| 112 |
+
"step": 3200
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.54,
|
| 116 |
+
"learning_rate": 5.039777983348751e-05,
|
| 117 |
+
"loss": 1.494,
|
| 118 |
+
"step": 3400
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.63,
|
| 122 |
+
"learning_rate": 4.8547641073080486e-05,
|
| 123 |
+
"loss": 1.4907,
|
| 124 |
+
"step": 3600
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.72,
|
| 128 |
+
"learning_rate": 4.6697502312673454e-05,
|
| 129 |
+
"loss": 1.4908,
|
| 130 |
+
"step": 3800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.81,
|
| 134 |
+
"learning_rate": 4.484736355226642e-05,
|
| 135 |
+
"loss": 1.4895,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.81,
|
| 140 |
+
"eval_loss": 1.9569236040115356,
|
| 141 |
+
"eval_runtime": 138.1502,
|
| 142 |
+
"eval_samples_per_second": 881.62,
|
| 143 |
+
"eval_steps_per_second": 3.446,
|
| 144 |
+
"step": 4000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.9,
|
| 148 |
+
"learning_rate": 4.299722479185939e-05,
|
| 149 |
+
"loss": 1.4883,
|
| 150 |
+
"step": 4200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.99,
|
| 154 |
+
"learning_rate": 4.1147086031452366e-05,
|
| 155 |
+
"loss": 1.4843,
|
| 156 |
+
"step": 4400
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.08,
|
| 160 |
+
"learning_rate": 3.9296947271045334e-05,
|
| 161 |
+
"loss": 1.4751,
|
| 162 |
+
"step": 4600
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.17,
|
| 166 |
+
"learning_rate": 3.74468085106383e-05,
|
| 167 |
+
"loss": 1.4734,
|
| 168 |
+
"step": 4800
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.26,
|
| 172 |
+
"learning_rate": 3.559666975023127e-05,
|
| 173 |
+
"loss": 1.471,
|
| 174 |
+
"step": 5000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.35,
|
| 178 |
+
"learning_rate": 3.374653098982424e-05,
|
| 179 |
+
"loss": 1.4732,
|
| 180 |
+
"step": 5200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.44,
|
| 184 |
+
"learning_rate": 3.1896392229417213e-05,
|
| 185 |
+
"loss": 1.4739,
|
| 186 |
+
"step": 5400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.53,
|
| 190 |
+
"learning_rate": 3.0046253469010178e-05,
|
| 191 |
+
"loss": 1.4692,
|
| 192 |
+
"step": 5600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.62,
|
| 196 |
+
"learning_rate": 2.8196114708603146e-05,
|
| 197 |
+
"loss": 1.4645,
|
| 198 |
+
"step": 5800
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.71,
|
| 202 |
+
"learning_rate": 2.6345975948196118e-05,
|
| 203 |
+
"loss": 1.4667,
|
| 204 |
+
"step": 6000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.71,
|
| 208 |
+
"eval_loss": 1.9881402254104614,
|
| 209 |
+
"eval_runtime": 137.335,
|
| 210 |
+
"eval_samples_per_second": 886.854,
|
| 211 |
+
"eval_steps_per_second": 3.466,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.8,
|
| 216 |
+
"learning_rate": 2.4495837187789086e-05,
|
| 217 |
+
"loss": 1.4677,
|
| 218 |
+
"step": 6200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.89,
|
| 222 |
+
"learning_rate": 2.2645698427382054e-05,
|
| 223 |
+
"loss": 1.4639,
|
| 224 |
+
"step": 6400
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.98,
|
| 228 |
+
"learning_rate": 2.0795559666975026e-05,
|
| 229 |
+
"loss": 1.4615,
|
| 230 |
+
"step": 6600
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.07,
|
| 234 |
+
"learning_rate": 1.8945420906567994e-05,
|
| 235 |
+
"loss": 1.4551,
|
| 236 |
+
"step": 6800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.16,
|
| 240 |
+
"learning_rate": 1.7095282146160962e-05,
|
| 241 |
+
"loss": 1.4539,
|
| 242 |
+
"step": 7000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.25,
|
| 246 |
+
"learning_rate": 1.5245143385753934e-05,
|
| 247 |
+
"loss": 1.4535,
|
| 248 |
+
"step": 7200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.35,
|
| 252 |
+
"learning_rate": 1.33950046253469e-05,
|
| 253 |
+
"loss": 1.4506,
|
| 254 |
+
"step": 7400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.44,
|
| 258 |
+
"learning_rate": 1.1544865864939872e-05,
|
| 259 |
+
"loss": 1.4522,
|
| 260 |
+
"step": 7600
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.53,
|
| 264 |
+
"learning_rate": 9.69472710453284e-06,
|
| 265 |
+
"loss": 1.4504,
|
| 266 |
+
"step": 7800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.62,
|
| 270 |
+
"learning_rate": 7.84458834412581e-06,
|
| 271 |
+
"loss": 1.4489,
|
| 272 |
+
"step": 8000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.62,
|
| 276 |
+
"eval_loss": 2.012910842895508,
|
| 277 |
+
"eval_runtime": 137.8372,
|
| 278 |
+
"eval_samples_per_second": 883.622,
|
| 279 |
+
"eval_steps_per_second": 3.453,
|
| 280 |
+
"step": 8000
|
| 281 |
+
}
|
| 282 |
+
],
|
| 283 |
+
"max_steps": 8848,
|
| 284 |
+
"num_train_epochs": 4,
|
| 285 |
+
"total_flos": 1.5605846428483584e+17,
|
| 286 |
+
"trial_name": null,
|
| 287 |
+
"trial_params": null
|
| 288 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:584f17ebde05d08b78ac29adc0c4a5909617e7d5634b3fd49dc085d6189855df
|
| 3 |
+
size 3387
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|