Commit
•
3e8fec4
1
Parent(s):
56655e1
Upload 12 files
Browse files- config.json +40 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- trainer_state.json +643 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "flax-community/gpt2-small-indonesian",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.32.0",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50257
|
| 40 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.0"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60f4409cb9fd7340b5a79d9fc340e4870db9718d6c4dadb7c4a3d97c9dea6bfd
|
| 3 |
+
size 995641861
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8280f22bd271d3ce2e304282dc957f7f597eeca62be9627f495c6936bfb4507
|
| 3 |
+
size 497807197
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a7af71f21cdf78de367774dcbb1ac4824f28bc05827947c8755c708d7ea724a
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:136e7c461276029c27fb1e0b60512bc56679a0316c5307036a68a53a7a7c95bb
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,643 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 48042,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.968777319845137e-06,
|
| 14 |
+
"loss": 3.8481,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 9.937554639690272e-06,
|
| 20 |
+
"loss": 3.0215,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 9.906331959535406e-06,
|
| 26 |
+
"loss": 2.564,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 9.875109279380542e-06,
|
| 32 |
+
"loss": 2.3377,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 9.843886599225678e-06,
|
| 38 |
+
"loss": 2.2458,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.37,
|
| 43 |
+
"learning_rate": 9.812663919070815e-06,
|
| 44 |
+
"loss": 2.1878,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.44,
|
| 49 |
+
"learning_rate": 9.78144123891595e-06,
|
| 50 |
+
"loss": 2.143,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5,
|
| 55 |
+
"learning_rate": 9.750218558761085e-06,
|
| 56 |
+
"loss": 2.113,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.56,
|
| 61 |
+
"learning_rate": 9.71899587860622e-06,
|
| 62 |
+
"loss": 2.0957,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.62,
|
| 67 |
+
"learning_rate": 9.687773198451356e-06,
|
| 68 |
+
"loss": 2.0639,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.69,
|
| 73 |
+
"learning_rate": 9.65655051829649e-06,
|
| 74 |
+
"loss": 2.0461,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.75,
|
| 79 |
+
"learning_rate": 9.625327838141627e-06,
|
| 80 |
+
"loss": 2.0174,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.81,
|
| 85 |
+
"learning_rate": 9.594105157986763e-06,
|
| 86 |
+
"loss": 2.0111,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.87,
|
| 91 |
+
"learning_rate": 9.562882477831898e-06,
|
| 92 |
+
"loss": 1.9898,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.94,
|
| 97 |
+
"learning_rate": 9.531659797677034e-06,
|
| 98 |
+
"loss": 1.98,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.0,
|
| 103 |
+
"learning_rate": 9.500437117522168e-06,
|
| 104 |
+
"loss": 1.9702,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"eval_loss": 1.9547929763793945,
|
| 110 |
+
"eval_runtime": 33.4979,
|
| 111 |
+
"eval_samples_per_second": 42.421,
|
| 112 |
+
"eval_steps_per_second": 5.314,
|
| 113 |
+
"step": 8007
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.06,
|
| 117 |
+
"learning_rate": 9.469214437367304e-06,
|
| 118 |
+
"loss": 1.9463,
|
| 119 |
+
"step": 8500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.12,
|
| 123 |
+
"learning_rate": 9.43799175721244e-06,
|
| 124 |
+
"loss": 1.9336,
|
| 125 |
+
"step": 9000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.19,
|
| 129 |
+
"learning_rate": 9.406769077057575e-06,
|
| 130 |
+
"loss": 1.9187,
|
| 131 |
+
"step": 9500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.25,
|
| 135 |
+
"learning_rate": 9.37554639690271e-06,
|
| 136 |
+
"loss": 1.9095,
|
| 137 |
+
"step": 10000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.31,
|
| 141 |
+
"learning_rate": 9.344323716747846e-06,
|
| 142 |
+
"loss": 1.903,
|
| 143 |
+
"step": 10500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.37,
|
| 147 |
+
"learning_rate": 9.313101036592982e-06,
|
| 148 |
+
"loss": 1.8976,
|
| 149 |
+
"step": 11000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.44,
|
| 153 |
+
"learning_rate": 9.281878356438118e-06,
|
| 154 |
+
"loss": 1.8823,
|
| 155 |
+
"step": 11500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.5,
|
| 159 |
+
"learning_rate": 9.250655676283253e-06,
|
| 160 |
+
"loss": 1.8908,
|
| 161 |
+
"step": 12000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.56,
|
| 165 |
+
"learning_rate": 9.219432996128387e-06,
|
| 166 |
+
"loss": 1.872,
|
| 167 |
+
"step": 12500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.62,
|
| 171 |
+
"learning_rate": 9.188210315973524e-06,
|
| 172 |
+
"loss": 1.8637,
|
| 173 |
+
"step": 13000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.69,
|
| 177 |
+
"learning_rate": 9.15698763581866e-06,
|
| 178 |
+
"loss": 1.8651,
|
| 179 |
+
"step": 13500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.75,
|
| 183 |
+
"learning_rate": 9.125764955663794e-06,
|
| 184 |
+
"loss": 1.8496,
|
| 185 |
+
"step": 14000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.81,
|
| 189 |
+
"learning_rate": 9.09454227550893e-06,
|
| 190 |
+
"loss": 1.8411,
|
| 191 |
+
"step": 14500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.87,
|
| 195 |
+
"learning_rate": 9.063319595354067e-06,
|
| 196 |
+
"loss": 1.8354,
|
| 197 |
+
"step": 15000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.94,
|
| 201 |
+
"learning_rate": 9.032096915199201e-06,
|
| 202 |
+
"loss": 1.8307,
|
| 203 |
+
"step": 15500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"learning_rate": 9.000874235044337e-06,
|
| 208 |
+
"loss": 1.8301,
|
| 209 |
+
"step": 16000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.0,
|
| 213 |
+
"eval_loss": 1.8236933946609497,
|
| 214 |
+
"eval_runtime": 33.5205,
|
| 215 |
+
"eval_samples_per_second": 42.392,
|
| 216 |
+
"eval_steps_per_second": 5.31,
|
| 217 |
+
"step": 16014
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.06,
|
| 221 |
+
"learning_rate": 8.969651554889472e-06,
|
| 222 |
+
"loss": 1.8129,
|
| 223 |
+
"step": 16500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.12,
|
| 227 |
+
"learning_rate": 8.938428874734608e-06,
|
| 228 |
+
"loss": 1.8119,
|
| 229 |
+
"step": 17000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.19,
|
| 233 |
+
"learning_rate": 8.907206194579744e-06,
|
| 234 |
+
"loss": 1.797,
|
| 235 |
+
"step": 17500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.25,
|
| 239 |
+
"learning_rate": 8.875983514424879e-06,
|
| 240 |
+
"loss": 1.8038,
|
| 241 |
+
"step": 18000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.31,
|
| 245 |
+
"learning_rate": 8.844760834270013e-06,
|
| 246 |
+
"loss": 1.8043,
|
| 247 |
+
"step": 18500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.37,
|
| 251 |
+
"learning_rate": 8.81353815411515e-06,
|
| 252 |
+
"loss": 1.7932,
|
| 253 |
+
"step": 19000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.44,
|
| 257 |
+
"learning_rate": 8.782315473960286e-06,
|
| 258 |
+
"loss": 1.7881,
|
| 259 |
+
"step": 19500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.5,
|
| 263 |
+
"learning_rate": 8.751092793805422e-06,
|
| 264 |
+
"loss": 1.7729,
|
| 265 |
+
"step": 20000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.56,
|
| 269 |
+
"learning_rate": 8.719870113650557e-06,
|
| 270 |
+
"loss": 1.7718,
|
| 271 |
+
"step": 20500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.62,
|
| 275 |
+
"learning_rate": 8.688647433495691e-06,
|
| 276 |
+
"loss": 1.7715,
|
| 277 |
+
"step": 21000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.69,
|
| 281 |
+
"learning_rate": 8.657424753340827e-06,
|
| 282 |
+
"loss": 1.7664,
|
| 283 |
+
"step": 21500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.75,
|
| 287 |
+
"learning_rate": 8.626202073185963e-06,
|
| 288 |
+
"loss": 1.7619,
|
| 289 |
+
"step": 22000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.81,
|
| 293 |
+
"learning_rate": 8.594979393031098e-06,
|
| 294 |
+
"loss": 1.7563,
|
| 295 |
+
"step": 22500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.87,
|
| 299 |
+
"learning_rate": 8.563756712876234e-06,
|
| 300 |
+
"loss": 1.7621,
|
| 301 |
+
"step": 23000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.93,
|
| 305 |
+
"learning_rate": 8.532534032721369e-06,
|
| 306 |
+
"loss": 1.7578,
|
| 307 |
+
"step": 23500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.0,
|
| 311 |
+
"learning_rate": 8.501311352566505e-06,
|
| 312 |
+
"loss": 1.7502,
|
| 313 |
+
"step": 24000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.0,
|
| 317 |
+
"eval_loss": 1.7523757219314575,
|
| 318 |
+
"eval_runtime": 33.535,
|
| 319 |
+
"eval_samples_per_second": 42.374,
|
| 320 |
+
"eval_steps_per_second": 5.308,
|
| 321 |
+
"step": 24021
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.06,
|
| 325 |
+
"learning_rate": 8.470088672411641e-06,
|
| 326 |
+
"loss": 1.7503,
|
| 327 |
+
"step": 24500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.12,
|
| 331 |
+
"learning_rate": 8.438865992256776e-06,
|
| 332 |
+
"loss": 1.7381,
|
| 333 |
+
"step": 25000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.18,
|
| 337 |
+
"learning_rate": 8.407643312101912e-06,
|
| 338 |
+
"loss": 1.7336,
|
| 339 |
+
"step": 25500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.25,
|
| 343 |
+
"learning_rate": 8.376420631947046e-06,
|
| 344 |
+
"loss": 1.7252,
|
| 345 |
+
"step": 26000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.31,
|
| 349 |
+
"learning_rate": 8.345197951792183e-06,
|
| 350 |
+
"loss": 1.7312,
|
| 351 |
+
"step": 26500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.37,
|
| 355 |
+
"learning_rate": 8.313975271637319e-06,
|
| 356 |
+
"loss": 1.7271,
|
| 357 |
+
"step": 27000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.43,
|
| 361 |
+
"learning_rate": 8.282752591482453e-06,
|
| 362 |
+
"loss": 1.7336,
|
| 363 |
+
"step": 27500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.5,
|
| 367 |
+
"learning_rate": 8.25152991132759e-06,
|
| 368 |
+
"loss": 1.7251,
|
| 369 |
+
"step": 28000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.56,
|
| 373 |
+
"learning_rate": 8.220307231172726e-06,
|
| 374 |
+
"loss": 1.7162,
|
| 375 |
+
"step": 28500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.62,
|
| 379 |
+
"learning_rate": 8.18908455101786e-06,
|
| 380 |
+
"loss": 1.7067,
|
| 381 |
+
"step": 29000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.68,
|
| 385 |
+
"learning_rate": 8.157861870862995e-06,
|
| 386 |
+
"loss": 1.7104,
|
| 387 |
+
"step": 29500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.75,
|
| 391 |
+
"learning_rate": 8.126639190708131e-06,
|
| 392 |
+
"loss": 1.7089,
|
| 393 |
+
"step": 30000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.81,
|
| 397 |
+
"learning_rate": 8.095416510553267e-06,
|
| 398 |
+
"loss": 1.7087,
|
| 399 |
+
"step": 30500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.87,
|
| 403 |
+
"learning_rate": 8.064193830398402e-06,
|
| 404 |
+
"loss": 1.6976,
|
| 405 |
+
"step": 31000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.93,
|
| 409 |
+
"learning_rate": 8.032971150243538e-06,
|
| 410 |
+
"loss": 1.6907,
|
| 411 |
+
"step": 31500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.0,
|
| 415 |
+
"learning_rate": 8.001748470088672e-06,
|
| 416 |
+
"loss": 1.6994,
|
| 417 |
+
"step": 32000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.0,
|
| 421 |
+
"eval_loss": 1.705617070198059,
|
| 422 |
+
"eval_runtime": 33.5302,
|
| 423 |
+
"eval_samples_per_second": 42.38,
|
| 424 |
+
"eval_steps_per_second": 5.309,
|
| 425 |
+
"step": 32028
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.06,
|
| 429 |
+
"learning_rate": 7.970525789933809e-06,
|
| 430 |
+
"loss": 1.6913,
|
| 431 |
+
"step": 32500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.12,
|
| 435 |
+
"learning_rate": 7.939303109778945e-06,
|
| 436 |
+
"loss": 1.6853,
|
| 437 |
+
"step": 33000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.18,
|
| 441 |
+
"learning_rate": 7.90808042962408e-06,
|
| 442 |
+
"loss": 1.6854,
|
| 443 |
+
"step": 33500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.25,
|
| 447 |
+
"learning_rate": 7.876857749469215e-06,
|
| 448 |
+
"loss": 1.6884,
|
| 449 |
+
"step": 34000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.31,
|
| 453 |
+
"learning_rate": 7.84563506931435e-06,
|
| 454 |
+
"loss": 1.6813,
|
| 455 |
+
"step": 34500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.37,
|
| 459 |
+
"learning_rate": 7.814412389159486e-06,
|
| 460 |
+
"loss": 1.6834,
|
| 461 |
+
"step": 35000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.43,
|
| 465 |
+
"learning_rate": 7.783189709004622e-06,
|
| 466 |
+
"loss": 1.6717,
|
| 467 |
+
"step": 35500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.5,
|
| 471 |
+
"learning_rate": 7.751967028849757e-06,
|
| 472 |
+
"loss": 1.6712,
|
| 473 |
+
"step": 36000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.56,
|
| 477 |
+
"learning_rate": 7.720744348694893e-06,
|
| 478 |
+
"loss": 1.6873,
|
| 479 |
+
"step": 36500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.62,
|
| 483 |
+
"learning_rate": 7.689521668540028e-06,
|
| 484 |
+
"loss": 1.6688,
|
| 485 |
+
"step": 37000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.68,
|
| 489 |
+
"learning_rate": 7.658298988385164e-06,
|
| 490 |
+
"loss": 1.6589,
|
| 491 |
+
"step": 37500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.75,
|
| 495 |
+
"learning_rate": 7.627076308230299e-06,
|
| 496 |
+
"loss": 1.6668,
|
| 497 |
+
"step": 38000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.81,
|
| 501 |
+
"learning_rate": 7.5958536280754345e-06,
|
| 502 |
+
"loss": 1.6665,
|
| 503 |
+
"step": 38500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.87,
|
| 507 |
+
"learning_rate": 7.564630947920571e-06,
|
| 508 |
+
"loss": 1.6679,
|
| 509 |
+
"step": 39000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.93,
|
| 513 |
+
"learning_rate": 7.533408267765706e-06,
|
| 514 |
+
"loss": 1.6624,
|
| 515 |
+
"step": 39500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.0,
|
| 519 |
+
"learning_rate": 7.502185587610841e-06,
|
| 520 |
+
"loss": 1.6621,
|
| 521 |
+
"step": 40000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.0,
|
| 525 |
+
"eval_loss": 1.6710957288742065,
|
| 526 |
+
"eval_runtime": 33.5526,
|
| 527 |
+
"eval_samples_per_second": 42.351,
|
| 528 |
+
"eval_steps_per_second": 5.305,
|
| 529 |
+
"step": 40035
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 5.06,
|
| 533 |
+
"learning_rate": 7.470962907455977e-06,
|
| 534 |
+
"loss": 1.6497,
|
| 535 |
+
"step": 40500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 5.12,
|
| 539 |
+
"learning_rate": 7.439740227301112e-06,
|
| 540 |
+
"loss": 1.6487,
|
| 541 |
+
"step": 41000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.18,
|
| 545 |
+
"learning_rate": 7.4085175471462475e-06,
|
| 546 |
+
"loss": 1.6439,
|
| 547 |
+
"step": 41500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.25,
|
| 551 |
+
"learning_rate": 7.377294866991384e-06,
|
| 552 |
+
"loss": 1.6552,
|
| 553 |
+
"step": 42000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.31,
|
| 557 |
+
"learning_rate": 7.346072186836518e-06,
|
| 558 |
+
"loss": 1.6473,
|
| 559 |
+
"step": 42500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 5.37,
|
| 563 |
+
"learning_rate": 7.314849506681654e-06,
|
| 564 |
+
"loss": 1.6447,
|
| 565 |
+
"step": 43000
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 5.43,
|
| 569 |
+
"learning_rate": 7.28362682652679e-06,
|
| 570 |
+
"loss": 1.6463,
|
| 571 |
+
"step": 43500
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 5.5,
|
| 575 |
+
"learning_rate": 7.252404146371925e-06,
|
| 576 |
+
"loss": 1.6493,
|
| 577 |
+
"step": 44000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 5.56,
|
| 581 |
+
"learning_rate": 7.2211814662170606e-06,
|
| 582 |
+
"loss": 1.6433,
|
| 583 |
+
"step": 44500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.62,
|
| 587 |
+
"learning_rate": 7.189958786062197e-06,
|
| 588 |
+
"loss": 1.6483,
|
| 589 |
+
"step": 45000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.68,
|
| 593 |
+
"learning_rate": 7.158736105907331e-06,
|
| 594 |
+
"loss": 1.6347,
|
| 595 |
+
"step": 45500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 5.74,
|
| 599 |
+
"learning_rate": 7.127513425752467e-06,
|
| 600 |
+
"loss": 1.6363,
|
| 601 |
+
"step": 46000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 5.81,
|
| 605 |
+
"learning_rate": 7.096290745597603e-06,
|
| 606 |
+
"loss": 1.6284,
|
| 607 |
+
"step": 46500
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 5.87,
|
| 611 |
+
"learning_rate": 7.065068065442738e-06,
|
| 612 |
+
"loss": 1.6268,
|
| 613 |
+
"step": 47000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 5.93,
|
| 617 |
+
"learning_rate": 7.033845385287874e-06,
|
| 618 |
+
"loss": 1.633,
|
| 619 |
+
"step": 47500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 5.99,
|
| 623 |
+
"learning_rate": 7.002622705133009e-06,
|
| 624 |
+
"loss": 1.6313,
|
| 625 |
+
"step": 48000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.0,
|
| 629 |
+
"eval_loss": 1.644548773765564,
|
| 630 |
+
"eval_runtime": 33.5436,
|
| 631 |
+
"eval_samples_per_second": 42.363,
|
| 632 |
+
"eval_steps_per_second": 5.307,
|
| 633 |
+
"step": 48042
|
| 634 |
+
}
|
| 635 |
+
],
|
| 636 |
+
"logging_steps": 500,
|
| 637 |
+
"max_steps": 160140,
|
| 638 |
+
"num_train_epochs": 20,
|
| 639 |
+
"save_steps": 500,
|
| 640 |
+
"total_flos": 7.5309720109056e+16,
|
| 641 |
+
"trial_name": null,
|
| 642 |
+
"trial_params": null
|
| 643 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571766107e6fb04c3fc5b250f343c7485c50c5a9f3e7aaf19f68a994ad56346d
|
| 3 |
+
size 4027
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|