Upload 13 files
Browse files- added_tokens.json +4 -0
- config.json +34 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +40 -0
- trainer_state.json +1171 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|pad|>": 50258,
|
| 3 |
+
"<|startoftext|>": 50257
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/workspace/my_model/checkpoint-112000",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"fp16": true,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 2048,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 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 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.34.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 50257
|
| 34 |
+
}
|
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": "4.34.0"
|
| 6 |
+
}
|
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 sha256:95ec0884e8cd8a616b7116cde3ea5db2c4df685d6a9caa4cd5e388ebc2b5eea9
|
| 3 |
+
size 2847217413
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02b1757a160cf9b6583e926f830d33a3ebf2dc56296006ab13be103b979f923a
|
| 3 |
+
size 1423582173
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e52d0d385fc233492c50d77c03bd294aada7f8534cbbf639b30e555680fc3323
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e89813b28636a92f62ff9f379d9d266c18efdbb498a56aaa2a6fd66c865bfd9
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|startoftext|>",
|
| 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": 1024,
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<|pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"__type": "AddedToken",
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": true,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2713042787334632,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 96000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.996689311774132e-05,
|
| 14 |
+
"loss": 0.5436,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4.9933786235482635e-05,
|
| 20 |
+
"loss": 0.5506,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 4.990067935322395e-05,
|
| 26 |
+
"loss": 0.5253,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 4.986757247096527e-05,
|
| 32 |
+
"loss": 0.5099,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 4.98345318024711e-05,
|
| 38 |
+
"loss": 0.5289,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"learning_rate": 4.980142492021241e-05,
|
| 44 |
+
"loss": 0.5223,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05,
|
| 49 |
+
"learning_rate": 4.976831803795373e-05,
|
| 50 |
+
"loss": 0.5273,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 4.973521115569505e-05,
|
| 56 |
+
"loss": 0.5321,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.06,
|
| 61 |
+
"learning_rate": 4.970210427343636e-05,
|
| 62 |
+
"loss": 0.4965,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.07,
|
| 67 |
+
"learning_rate": 4.966899739117768e-05,
|
| 68 |
+
"loss": 0.5026,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.07,
|
| 73 |
+
"learning_rate": 4.9635890508919e-05,
|
| 74 |
+
"loss": 0.5123,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.08,
|
| 79 |
+
"learning_rate": 4.9602783626660317e-05,
|
| 80 |
+
"loss": 0.5154,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.09,
|
| 85 |
+
"learning_rate": 4.9569676744401626e-05,
|
| 86 |
+
"loss": 0.5258,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09,
|
| 91 |
+
"learning_rate": 4.953656986214294e-05,
|
| 92 |
+
"loss": 0.5225,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1,
|
| 97 |
+
"learning_rate": 4.950352919364878e-05,
|
| 98 |
+
"loss": 0.5051,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.11,
|
| 103 |
+
"learning_rate": 4.9470422311390094e-05,
|
| 104 |
+
"loss": 0.5136,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.11,
|
| 109 |
+
"learning_rate": 4.943731542913141e-05,
|
| 110 |
+
"loss": 0.5306,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.12,
|
| 115 |
+
"learning_rate": 4.940420854687273e-05,
|
| 116 |
+
"loss": 0.4884,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.13,
|
| 121 |
+
"learning_rate": 4.937110166461404e-05,
|
| 122 |
+
"loss": 0.4916,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.13,
|
| 127 |
+
"learning_rate": 4.933799478235536e-05,
|
| 128 |
+
"loss": 0.5096,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.14,
|
| 133 |
+
"learning_rate": 4.930495411386119e-05,
|
| 134 |
+
"loss": 0.5053,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.15,
|
| 139 |
+
"learning_rate": 4.927184723160251e-05,
|
| 140 |
+
"loss": 0.4981,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.15,
|
| 145 |
+
"learning_rate": 4.923874034934383e-05,
|
| 146 |
+
"loss": 0.4947,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.16,
|
| 151 |
+
"learning_rate": 4.920563346708514e-05,
|
| 152 |
+
"loss": 0.4974,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.17,
|
| 157 |
+
"learning_rate": 4.917252658482645e-05,
|
| 158 |
+
"loss": 0.5037,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.17,
|
| 163 |
+
"learning_rate": 4.9139419702567776e-05,
|
| 164 |
+
"loss": 0.4952,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.18,
|
| 169 |
+
"learning_rate": 4.9106379034073605e-05,
|
| 170 |
+
"loss": 0.5019,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.19,
|
| 175 |
+
"learning_rate": 4.907327215181492e-05,
|
| 176 |
+
"loss": 0.5044,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19,
|
| 181 |
+
"learning_rate": 4.904016526955624e-05,
|
| 182 |
+
"loss": 0.4936,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.2,
|
| 187 |
+
"learning_rate": 4.9007058387297554e-05,
|
| 188 |
+
"loss": 0.4975,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.21,
|
| 193 |
+
"learning_rate": 4.897395150503887e-05,
|
| 194 |
+
"loss": 0.4725,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.21,
|
| 199 |
+
"learning_rate": 4.8940844622780186e-05,
|
| 200 |
+
"loss": 0.4622,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.22,
|
| 205 |
+
"learning_rate": 4.89077377405215e-05,
|
| 206 |
+
"loss": 0.4824,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.23,
|
| 211 |
+
"learning_rate": 4.887469707202734e-05,
|
| 212 |
+
"loss": 0.5536,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.23,
|
| 217 |
+
"learning_rate": 4.884159018976865e-05,
|
| 218 |
+
"loss": 0.4653,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.24,
|
| 223 |
+
"learning_rate": 4.8808549521274483e-05,
|
| 224 |
+
"loss": 0.5132,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.24,
|
| 229 |
+
"learning_rate": 4.87754426390158e-05,
|
| 230 |
+
"loss": 0.5161,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.25,
|
| 235 |
+
"learning_rate": 4.8742335756757116e-05,
|
| 236 |
+
"loss": 0.4661,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.26,
|
| 241 |
+
"learning_rate": 4.870922887449843e-05,
|
| 242 |
+
"loss": 0.4929,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.26,
|
| 247 |
+
"learning_rate": 4.867618820600426e-05,
|
| 248 |
+
"loss": 0.4834,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.27,
|
| 253 |
+
"learning_rate": 4.8643081323745584e-05,
|
| 254 |
+
"loss": 0.4791,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.28,
|
| 259 |
+
"learning_rate": 4.86099744414869e-05,
|
| 260 |
+
"loss": 0.5235,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.28,
|
| 265 |
+
"learning_rate": 4.8576867559228217e-05,
|
| 266 |
+
"loss": 0.4893,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.29,
|
| 271 |
+
"learning_rate": 4.854376067696953e-05,
|
| 272 |
+
"loss": 0.4616,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.3,
|
| 277 |
+
"learning_rate": 4.851065379471085e-05,
|
| 278 |
+
"loss": 0.4951,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.3,
|
| 283 |
+
"learning_rate": 4.8477546912452165e-05,
|
| 284 |
+
"loss": 0.4882,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.31,
|
| 289 |
+
"learning_rate": 4.8444440030193475e-05,
|
| 290 |
+
"loss": 0.5253,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.32,
|
| 295 |
+
"learning_rate": 4.84113331479348e-05,
|
| 296 |
+
"loss": 0.4815,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.32,
|
| 301 |
+
"learning_rate": 4.8378226265676114e-05,
|
| 302 |
+
"loss": 0.4928,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.33,
|
| 307 |
+
"learning_rate": 4.834518559718195e-05,
|
| 308 |
+
"loss": 0.503,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.34,
|
| 313 |
+
"learning_rate": 4.831207871492326e-05,
|
| 314 |
+
"loss": 0.481,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.34,
|
| 319 |
+
"learning_rate": 4.8278971832664575e-05,
|
| 320 |
+
"loss": 0.4613,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.35,
|
| 325 |
+
"learning_rate": 4.824586495040589e-05,
|
| 326 |
+
"loss": 0.4727,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.36,
|
| 331 |
+
"learning_rate": 4.821282428191173e-05,
|
| 332 |
+
"loss": 0.4639,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.36,
|
| 337 |
+
"learning_rate": 4.8179717399653044e-05,
|
| 338 |
+
"loss": 0.4989,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.37,
|
| 343 |
+
"learning_rate": 4.814661051739436e-05,
|
| 344 |
+
"loss": 0.4595,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.38,
|
| 349 |
+
"learning_rate": 4.8113503635135676e-05,
|
| 350 |
+
"loss": 0.4803,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.38,
|
| 355 |
+
"learning_rate": 4.8080396752876985e-05,
|
| 356 |
+
"loss": 0.4768,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.39,
|
| 361 |
+
"learning_rate": 4.804735608438282e-05,
|
| 362 |
+
"loss": 0.4642,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.4,
|
| 367 |
+
"learning_rate": 4.801424920212414e-05,
|
| 368 |
+
"loss": 0.4939,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.4,
|
| 373 |
+
"learning_rate": 4.798114231986546e-05,
|
| 374 |
+
"loss": 0.4717,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.41,
|
| 379 |
+
"learning_rate": 4.794803543760677e-05,
|
| 380 |
+
"loss": 0.4689,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.42,
|
| 385 |
+
"learning_rate": 4.7914994769112606e-05,
|
| 386 |
+
"loss": 0.4973,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.42,
|
| 391 |
+
"learning_rate": 4.788188788685392e-05,
|
| 392 |
+
"loss": 0.4369,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.43,
|
| 397 |
+
"learning_rate": 4.784878100459524e-05,
|
| 398 |
+
"loss": 0.476,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.44,
|
| 403 |
+
"learning_rate": 4.7815674122336554e-05,
|
| 404 |
+
"loss": 0.4594,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.44,
|
| 409 |
+
"learning_rate": 4.778256724007787e-05,
|
| 410 |
+
"loss": 0.4863,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.45,
|
| 415 |
+
"learning_rate": 4.77495265715837e-05,
|
| 416 |
+
"loss": 0.4514,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.46,
|
| 421 |
+
"learning_rate": 4.771641968932502e-05,
|
| 422 |
+
"loss": 0.4843,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.46,
|
| 427 |
+
"learning_rate": 4.768331280706633e-05,
|
| 428 |
+
"loss": 0.4473,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.47,
|
| 433 |
+
"learning_rate": 4.765020592480765e-05,
|
| 434 |
+
"loss": 0.4865,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.48,
|
| 439 |
+
"learning_rate": 4.761709904254897e-05,
|
| 440 |
+
"loss": 0.4509,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.48,
|
| 445 |
+
"learning_rate": 4.75840583740548e-05,
|
| 446 |
+
"loss": 0.4599,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.49,
|
| 451 |
+
"learning_rate": 4.7550951491796117e-05,
|
| 452 |
+
"loss": 0.4589,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.5,
|
| 457 |
+
"learning_rate": 4.751784460953743e-05,
|
| 458 |
+
"loss": 0.4565,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5,
|
| 463 |
+
"learning_rate": 4.748473772727875e-05,
|
| 464 |
+
"loss": 0.4489,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.51,
|
| 469 |
+
"learning_rate": 4.7451697058784585e-05,
|
| 470 |
+
"loss": 0.4637,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.52,
|
| 475 |
+
"learning_rate": 4.74185901765259e-05,
|
| 476 |
+
"loss": 0.4596,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.52,
|
| 481 |
+
"learning_rate": 4.738548329426721e-05,
|
| 482 |
+
"loss": 0.4647,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.53,
|
| 487 |
+
"learning_rate": 4.7352376412008533e-05,
|
| 488 |
+
"loss": 0.4587,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.54,
|
| 493 |
+
"learning_rate": 4.731926952974985e-05,
|
| 494 |
+
"loss": 0.4866,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.54,
|
| 499 |
+
"learning_rate": 4.728616264749116e-05,
|
| 500 |
+
"loss": 0.4546,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.55,
|
| 505 |
+
"learning_rate": 4.7253121978996995e-05,
|
| 506 |
+
"loss": 0.4345,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.56,
|
| 511 |
+
"learning_rate": 4.722008131050283e-05,
|
| 512 |
+
"loss": 0.4867,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.56,
|
| 517 |
+
"learning_rate": 4.718697442824415e-05,
|
| 518 |
+
"loss": 0.4494,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.57,
|
| 523 |
+
"learning_rate": 4.715386754598546e-05,
|
| 524 |
+
"loss": 0.4447,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.58,
|
| 529 |
+
"learning_rate": 4.712076066372678e-05,
|
| 530 |
+
"loss": 0.4674,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.58,
|
| 535 |
+
"learning_rate": 4.7087653781468096e-05,
|
| 536 |
+
"loss": 0.4343,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.59,
|
| 541 |
+
"learning_rate": 4.705454689920941e-05,
|
| 542 |
+
"loss": 0.4304,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.6,
|
| 547 |
+
"learning_rate": 4.702144001695072e-05,
|
| 548 |
+
"loss": 0.4324,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6,
|
| 553 |
+
"learning_rate": 4.6988333134692044e-05,
|
| 554 |
+
"loss": 0.4772,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.61,
|
| 559 |
+
"learning_rate": 4.695522625243336e-05,
|
| 560 |
+
"loss": 0.4649,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.62,
|
| 565 |
+
"learning_rate": 4.6922185583939196e-05,
|
| 566 |
+
"loss": 0.4497,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.62,
|
| 571 |
+
"learning_rate": 4.6889078701680506e-05,
|
| 572 |
+
"loss": 0.4224,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.63,
|
| 577 |
+
"learning_rate": 4.685597181942182e-05,
|
| 578 |
+
"loss": 0.4572,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.64,
|
| 583 |
+
"learning_rate": 4.682286493716314e-05,
|
| 584 |
+
"loss": 0.4737,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.64,
|
| 589 |
+
"learning_rate": 4.6789824268668974e-05,
|
| 590 |
+
"loss": 0.4895,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.65,
|
| 595 |
+
"learning_rate": 4.675671738641029e-05,
|
| 596 |
+
"loss": 0.4577,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.66,
|
| 601 |
+
"learning_rate": 4.6723610504151606e-05,
|
| 602 |
+
"loss": 0.4541,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.66,
|
| 607 |
+
"learning_rate": 4.669050362189292e-05,
|
| 608 |
+
"loss": 0.4484,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.67,
|
| 613 |
+
"learning_rate": 4.665739673963423e-05,
|
| 614 |
+
"loss": 0.4472,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.68,
|
| 619 |
+
"learning_rate": 4.662435607114007e-05,
|
| 620 |
+
"loss": 0.4398,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.68,
|
| 625 |
+
"learning_rate": 4.6591249188881384e-05,
|
| 626 |
+
"loss": 0.4781,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.69,
|
| 631 |
+
"learning_rate": 4.655814230662271e-05,
|
| 632 |
+
"loss": 0.4201,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7,
|
| 637 |
+
"learning_rate": 4.6525035424364016e-05,
|
| 638 |
+
"loss": 0.4385,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7,
|
| 643 |
+
"learning_rate": 4.649192854210533e-05,
|
| 644 |
+
"loss": 0.4245,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.71,
|
| 649 |
+
"learning_rate": 4.645882165984665e-05,
|
| 650 |
+
"loss": 0.4525,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.72,
|
| 655 |
+
"learning_rate": 4.6425780991352485e-05,
|
| 656 |
+
"loss": 0.4499,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.72,
|
| 661 |
+
"learning_rate": 4.63926741090938e-05,
|
| 662 |
+
"loss": 0.4356,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.73,
|
| 667 |
+
"learning_rate": 4.635956722683512e-05,
|
| 668 |
+
"loss": 0.4598,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.73,
|
| 673 |
+
"learning_rate": 4.632646034457643e-05,
|
| 674 |
+
"loss": 0.4508,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.74,
|
| 679 |
+
"learning_rate": 4.629341967608227e-05,
|
| 680 |
+
"loss": 0.4536,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.75,
|
| 685 |
+
"learning_rate": 4.6260312793823585e-05,
|
| 686 |
+
"loss": 0.4486,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.75,
|
| 691 |
+
"learning_rate": 4.6227205911564895e-05,
|
| 692 |
+
"loss": 0.4463,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.76,
|
| 697 |
+
"learning_rate": 4.619409902930622e-05,
|
| 698 |
+
"loss": 0.4503,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.77,
|
| 703 |
+
"learning_rate": 4.6160992147047534e-05,
|
| 704 |
+
"loss": 0.4612,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.77,
|
| 709 |
+
"learning_rate": 4.612795147855336e-05,
|
| 710 |
+
"loss": 0.4388,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.78,
|
| 715 |
+
"learning_rate": 4.609484459629468e-05,
|
| 716 |
+
"loss": 0.4547,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.79,
|
| 721 |
+
"learning_rate": 4.6061737714035996e-05,
|
| 722 |
+
"loss": 0.4624,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.79,
|
| 727 |
+
"learning_rate": 4.602863083177731e-05,
|
| 728 |
+
"loss": 0.4479,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.8,
|
| 733 |
+
"learning_rate": 4.599552394951863e-05,
|
| 734 |
+
"loss": 0.4512,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.81,
|
| 739 |
+
"learning_rate": 4.5962417067259944e-05,
|
| 740 |
+
"loss": 0.4451,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.81,
|
| 745 |
+
"learning_rate": 4.592931018500126e-05,
|
| 746 |
+
"loss": 0.4318,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.82,
|
| 751 |
+
"learning_rate": 4.5896269516507096e-05,
|
| 752 |
+
"loss": 0.4188,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.83,
|
| 757 |
+
"learning_rate": 4.5863162634248406e-05,
|
| 758 |
+
"loss": 0.4371,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.83,
|
| 763 |
+
"learning_rate": 4.583005575198973e-05,
|
| 764 |
+
"loss": 0.4519,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.84,
|
| 769 |
+
"learning_rate": 4.5796948869731045e-05,
|
| 770 |
+
"loss": 0.4491,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.85,
|
| 775 |
+
"learning_rate": 4.5763841987472354e-05,
|
| 776 |
+
"loss": 0.4397,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.85,
|
| 781 |
+
"learning_rate": 4.573073510521367e-05,
|
| 782 |
+
"loss": 0.4308,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.86,
|
| 787 |
+
"learning_rate": 4.5697628222954994e-05,
|
| 788 |
+
"loss": 0.4286,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.87,
|
| 793 |
+
"learning_rate": 4.566458755446082e-05,
|
| 794 |
+
"loss": 0.4587,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.87,
|
| 799 |
+
"learning_rate": 4.563148067220214e-05,
|
| 800 |
+
"loss": 0.4436,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.88,
|
| 805 |
+
"learning_rate": 4.5598373789943455e-05,
|
| 806 |
+
"loss": 0.4672,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.89,
|
| 811 |
+
"learning_rate": 4.556526690768477e-05,
|
| 812 |
+
"loss": 0.4294,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.89,
|
| 817 |
+
"learning_rate": 4.553216002542609e-05,
|
| 818 |
+
"loss": 0.4454,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.9,
|
| 823 |
+
"learning_rate": 4.5499053143167404e-05,
|
| 824 |
+
"loss": 0.4225,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.91,
|
| 829 |
+
"learning_rate": 4.546594626090872e-05,
|
| 830 |
+
"loss": 0.4256,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.91,
|
| 835 |
+
"learning_rate": 4.5432905592414556e-05,
|
| 836 |
+
"loss": 0.4179,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.92,
|
| 841 |
+
"learning_rate": 4.539979871015587e-05,
|
| 842 |
+
"loss": 0.4521,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.93,
|
| 847 |
+
"learning_rate": 4.536669182789718e-05,
|
| 848 |
+
"loss": 0.4415,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.93,
|
| 853 |
+
"learning_rate": 4.5333584945638504e-05,
|
| 854 |
+
"loss": 0.4102,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.94,
|
| 859 |
+
"learning_rate": 4.530054427714433e-05,
|
| 860 |
+
"loss": 0.3905,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.95,
|
| 865 |
+
"learning_rate": 4.5267437394885656e-05,
|
| 866 |
+
"loss": 0.4331,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.95,
|
| 871 |
+
"learning_rate": 4.5234330512626966e-05,
|
| 872 |
+
"loss": 0.4289,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.96,
|
| 877 |
+
"learning_rate": 4.520122363036828e-05,
|
| 878 |
+
"loss": 0.4246,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.97,
|
| 883 |
+
"learning_rate": 4.51681167481096e-05,
|
| 884 |
+
"loss": 0.4141,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.97,
|
| 889 |
+
"learning_rate": 4.5135076079615434e-05,
|
| 890 |
+
"loss": 0.4365,
|
| 891 |
+
"step": 73500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.98,
|
| 895 |
+
"learning_rate": 4.510196919735675e-05,
|
| 896 |
+
"loss": 0.4117,
|
| 897 |
+
"step": 74000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.99,
|
| 901 |
+
"learning_rate": 4.5068862315098066e-05,
|
| 902 |
+
"loss": 0.4113,
|
| 903 |
+
"step": 74500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.99,
|
| 907 |
+
"learning_rate": 4.503575543283938e-05,
|
| 908 |
+
"loss": 0.4297,
|
| 909 |
+
"step": 75000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.0,
|
| 913 |
+
"learning_rate": 4.500271476434522e-05,
|
| 914 |
+
"loss": 0.4252,
|
| 915 |
+
"step": 75500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.01,
|
| 919 |
+
"learning_rate": 4.496960788208653e-05,
|
| 920 |
+
"loss": 0.4208,
|
| 921 |
+
"step": 76000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.01,
|
| 925 |
+
"learning_rate": 4.4936500999827844e-05,
|
| 926 |
+
"loss": 0.43,
|
| 927 |
+
"step": 76500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.02,
|
| 931 |
+
"learning_rate": 4.490339411756917e-05,
|
| 932 |
+
"loss": 0.3911,
|
| 933 |
+
"step": 77000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.03,
|
| 937 |
+
"learning_rate": 4.4870353449074996e-05,
|
| 938 |
+
"loss": 0.4056,
|
| 939 |
+
"step": 77500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.03,
|
| 943 |
+
"learning_rate": 4.483724656681631e-05,
|
| 944 |
+
"loss": 0.4315,
|
| 945 |
+
"step": 78000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.04,
|
| 949 |
+
"learning_rate": 4.480413968455763e-05,
|
| 950 |
+
"loss": 0.4423,
|
| 951 |
+
"step": 78500
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.05,
|
| 955 |
+
"learning_rate": 4.4771032802298945e-05,
|
| 956 |
+
"loss": 0.4177,
|
| 957 |
+
"step": 79000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.05,
|
| 961 |
+
"learning_rate": 4.473792592004026e-05,
|
| 962 |
+
"loss": 0.3952,
|
| 963 |
+
"step": 79500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.06,
|
| 967 |
+
"learning_rate": 4.470481903778158e-05,
|
| 968 |
+
"loss": 0.3925,
|
| 969 |
+
"step": 80000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.07,
|
| 973 |
+
"learning_rate": 4.4671778369287406e-05,
|
| 974 |
+
"loss": 0.4147,
|
| 975 |
+
"step": 80500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.07,
|
| 979 |
+
"learning_rate": 4.463867148702873e-05,
|
| 980 |
+
"loss": 0.4091,
|
| 981 |
+
"step": 81000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.08,
|
| 985 |
+
"learning_rate": 4.460556460477004e-05,
|
| 986 |
+
"loss": 0.41,
|
| 987 |
+
"step": 81500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.09,
|
| 991 |
+
"learning_rate": 4.4572457722511355e-05,
|
| 992 |
+
"loss": 0.3953,
|
| 993 |
+
"step": 82000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.09,
|
| 997 |
+
"learning_rate": 4.453935084025268e-05,
|
| 998 |
+
"loss": 0.4294,
|
| 999 |
+
"step": 82500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.1,
|
| 1003 |
+
"learning_rate": 4.450631017175851e-05,
|
| 1004 |
+
"loss": 0.3982,
|
| 1005 |
+
"step": 83000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.11,
|
| 1009 |
+
"learning_rate": 4.447320328949982e-05,
|
| 1010 |
+
"loss": 0.4094,
|
| 1011 |
+
"step": 83500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.11,
|
| 1015 |
+
"learning_rate": 4.444009640724114e-05,
|
| 1016 |
+
"loss": 0.3892,
|
| 1017 |
+
"step": 84000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.12,
|
| 1021 |
+
"learning_rate": 4.4406989524982456e-05,
|
| 1022 |
+
"loss": 0.3843,
|
| 1023 |
+
"step": 84500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.13,
|
| 1027 |
+
"learning_rate": 4.437394885648829e-05,
|
| 1028 |
+
"loss": 0.4414,
|
| 1029 |
+
"step": 85000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.13,
|
| 1033 |
+
"learning_rate": 4.434084197422961e-05,
|
| 1034 |
+
"loss": 0.4325,
|
| 1035 |
+
"step": 85500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.14,
|
| 1039 |
+
"learning_rate": 4.430773509197092e-05,
|
| 1040 |
+
"loss": 0.4319,
|
| 1041 |
+
"step": 86000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.15,
|
| 1045 |
+
"learning_rate": 4.427462820971224e-05,
|
| 1046 |
+
"loss": 0.4216,
|
| 1047 |
+
"step": 86500
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.15,
|
| 1051 |
+
"learning_rate": 4.4241521327453556e-05,
|
| 1052 |
+
"loss": 0.4205,
|
| 1053 |
+
"step": 87000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.16,
|
| 1057 |
+
"learning_rate": 4.4208414445194866e-05,
|
| 1058 |
+
"loss": 0.4056,
|
| 1059 |
+
"step": 87500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.17,
|
| 1063 |
+
"learning_rate": 4.41753737767007e-05,
|
| 1064 |
+
"loss": 0.4287,
|
| 1065 |
+
"step": 88000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.17,
|
| 1069 |
+
"learning_rate": 4.414226689444202e-05,
|
| 1070 |
+
"loss": 0.4034,
|
| 1071 |
+
"step": 88500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.18,
|
| 1075 |
+
"learning_rate": 4.4109160012183334e-05,
|
| 1076 |
+
"loss": 0.3886,
|
| 1077 |
+
"step": 89000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.19,
|
| 1081 |
+
"learning_rate": 4.407605312992465e-05,
|
| 1082 |
+
"loss": 0.4426,
|
| 1083 |
+
"step": 89500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.19,
|
| 1087 |
+
"learning_rate": 4.4042946247665966e-05,
|
| 1088 |
+
"loss": 0.4298,
|
| 1089 |
+
"step": 90000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.2,
|
| 1093 |
+
"learning_rate": 4.40099055791718e-05,
|
| 1094 |
+
"loss": 0.4066,
|
| 1095 |
+
"step": 90500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.21,
|
| 1099 |
+
"learning_rate": 4.397679869691312e-05,
|
| 1100 |
+
"loss": 0.4017,
|
| 1101 |
+
"step": 91000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.21,
|
| 1105 |
+
"learning_rate": 4.394369181465443e-05,
|
| 1106 |
+
"loss": 0.4057,
|
| 1107 |
+
"step": 91500
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.22,
|
| 1111 |
+
"learning_rate": 4.391058493239575e-05,
|
| 1112 |
+
"loss": 0.3921,
|
| 1113 |
+
"step": 92000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.22,
|
| 1117 |
+
"learning_rate": 4.387747805013707e-05,
|
| 1118 |
+
"loss": 0.3989,
|
| 1119 |
+
"step": 92500
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.23,
|
| 1123 |
+
"learning_rate": 4.3844371167878377e-05,
|
| 1124 |
+
"loss": 0.3896,
|
| 1125 |
+
"step": 93000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.24,
|
| 1129 |
+
"learning_rate": 4.381133049938421e-05,
|
| 1130 |
+
"loss": 0.3896,
|
| 1131 |
+
"step": 93500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.24,
|
| 1135 |
+
"learning_rate": 4.377822361712553e-05,
|
| 1136 |
+
"loss": 0.407,
|
| 1137 |
+
"step": 94000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.25,
|
| 1141 |
+
"learning_rate": 4.3745116734866845e-05,
|
| 1142 |
+
"loss": 0.4147,
|
| 1143 |
+
"step": 94500
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.26,
|
| 1147 |
+
"learning_rate": 4.371200985260816e-05,
|
| 1148 |
+
"loss": 0.3921,
|
| 1149 |
+
"step": 95000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.26,
|
| 1153 |
+
"learning_rate": 4.367890297034948e-05,
|
| 1154 |
+
"loss": 0.3924,
|
| 1155 |
+
"step": 95500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.27,
|
| 1159 |
+
"learning_rate": 4.3645796088090793e-05,
|
| 1160 |
+
"loss": 0.3874,
|
| 1161 |
+
"step": 96000
|
| 1162 |
+
}
|
| 1163 |
+
],
|
| 1164 |
+
"logging_steps": 500,
|
| 1165 |
+
"max_steps": 755130,
|
| 1166 |
+
"num_train_epochs": 10,
|
| 1167 |
+
"save_steps": 2000,
|
| 1168 |
+
"total_flos": 3.56621066698752e+17,
|
| 1169 |
+
"trial_name": null,
|
| 1170 |
+
"trial_params": null
|
| 1171 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f462b73d3c8c00f84ae8ab757227e4ebb86b3b6fe76f2c5ae8049e416c871ce6
|
| 3 |
+
size 4027
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|