Upload 15 files
Browse files- added_tokens.json +4 -0
- config.json +34 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +40 -0
- trainer_state.json +813 -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": "hidude562/Maestro-ctx-V5",
|
| 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": "4.37.2",
|
| 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": "4.37.2"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be6f93e2521a169f92db3edad7e250ffed340d042dd002ad303e002877ca822b
|
| 3 |
+
size 1423517184
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10041aeda7d66bb48a70d9317751da7c2ce41333e245e86ecba7af5b83f23e42
|
| 3 |
+
size 2847217850
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bde29e885f292993abacc81155345fe7358fda7e3f49c3254e4d2674ff47de1
|
| 3 |
+
size 14244
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dde0fe3b0eb001790dd76a37f238b36373af39d2fc7a3de2cf46d453afa79c7
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa85b4a9daf591bee0ec3a3c9ba38c4b2f4397c0ee7bef765c47ed6a6e3ff811
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d8bbdc539d21dc0a028eafef7c066b93874f1ebdd0990b61a700b3366858a3
|
| 3 |
+
size 1064
|
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 +1,813 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1283208534208637,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 66000,
|
| 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": 4.9786302868670296e-05,
|
| 14 |
+
"loss": 0.5871,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.957260573734058e-05,
|
| 20 |
+
"loss": 0.5995,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 4.9358908606010875e-05,
|
| 26 |
+
"loss": 0.6109,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 4.914521147468117e-05,
|
| 32 |
+
"loss": 0.5865,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 4.893151434335146e-05,
|
| 38 |
+
"loss": 0.5996,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 4.871781721202175e-05,
|
| 44 |
+
"loss": 0.614,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 4.850412008069204e-05,
|
| 50 |
+
"loss": 0.5985,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 4.829042294936233e-05,
|
| 56 |
+
"loss": 0.6062,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 4.8077153212295275e-05,
|
| 62 |
+
"loss": 0.6148,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 4.7863456080965575e-05,
|
| 68 |
+
"loss": 0.5964,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.09,
|
| 73 |
+
"learning_rate": 4.764975894963586e-05,
|
| 74 |
+
"loss": 0.6037,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.1,
|
| 79 |
+
"learning_rate": 4.7436061818306155e-05,
|
| 80 |
+
"loss": 0.5954,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.11,
|
| 85 |
+
"learning_rate": 4.722236468697644e-05,
|
| 86 |
+
"loss": 0.6028,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"learning_rate": 4.7008667555646735e-05,
|
| 92 |
+
"loss": 0.6213,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"learning_rate": 4.679497042431703e-05,
|
| 98 |
+
"loss": 0.6029,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.14,
|
| 103 |
+
"learning_rate": 4.6581273292987314e-05,
|
| 104 |
+
"loss": 0.6167,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.15,
|
| 109 |
+
"learning_rate": 4.636757616165761e-05,
|
| 110 |
+
"loss": 0.59,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.15,
|
| 115 |
+
"learning_rate": 4.61538790303279e-05,
|
| 116 |
+
"loss": 0.6135,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.16,
|
| 121 |
+
"learning_rate": 4.5940181898998194e-05,
|
| 122 |
+
"loss": 0.602,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.17,
|
| 127 |
+
"learning_rate": 4.572691216193114e-05,
|
| 128 |
+
"loss": 0.5866,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"learning_rate": 4.551321503060143e-05,
|
| 134 |
+
"loss": 0.5948,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.19,
|
| 139 |
+
"learning_rate": 4.529951789927172e-05,
|
| 140 |
+
"loss": 0.6134,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.2,
|
| 145 |
+
"learning_rate": 4.5085820767942014e-05,
|
| 146 |
+
"loss": 0.5979,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.21,
|
| 151 |
+
"learning_rate": 4.487212363661231e-05,
|
| 152 |
+
"loss": 0.5943,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.21,
|
| 157 |
+
"learning_rate": 4.4658426505282594e-05,
|
| 158 |
+
"loss": 0.593,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.22,
|
| 163 |
+
"learning_rate": 4.444472937395289e-05,
|
| 164 |
+
"loss": 0.5928,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.23,
|
| 169 |
+
"learning_rate": 4.423103224262318e-05,
|
| 170 |
+
"loss": 0.6005,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"learning_rate": 4.401776250555613e-05,
|
| 176 |
+
"loss": 0.5964,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.25,
|
| 181 |
+
"learning_rate": 4.3804065374226414e-05,
|
| 182 |
+
"loss": 0.6005,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.26,
|
| 187 |
+
"learning_rate": 4.359079563715937e-05,
|
| 188 |
+
"loss": 0.5931,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.26,
|
| 193 |
+
"learning_rate": 4.337709850582966e-05,
|
| 194 |
+
"loss": 0.5928,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.27,
|
| 199 |
+
"learning_rate": 4.316340137449995e-05,
|
| 200 |
+
"loss": 0.5994,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.28,
|
| 205 |
+
"learning_rate": 4.294970424317024e-05,
|
| 206 |
+
"loss": 0.587,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.29,
|
| 211 |
+
"learning_rate": 4.2736007111840534e-05,
|
| 212 |
+
"loss": 0.6039,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"learning_rate": 4.252230998051082e-05,
|
| 218 |
+
"loss": 0.5943,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.31,
|
| 223 |
+
"learning_rate": 4.230861284918112e-05,
|
| 224 |
+
"loss": 0.5791,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.32,
|
| 229 |
+
"learning_rate": 4.209534311211407e-05,
|
| 230 |
+
"loss": 0.5816,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.32,
|
| 235 |
+
"learning_rate": 4.1881645980784354e-05,
|
| 236 |
+
"loss": 0.5771,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.33,
|
| 241 |
+
"learning_rate": 4.166794884945465e-05,
|
| 242 |
+
"loss": 0.5955,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.34,
|
| 247 |
+
"learning_rate": 4.1454251718124934e-05,
|
| 248 |
+
"loss": 0.5802,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.35,
|
| 253 |
+
"learning_rate": 4.124055458679523e-05,
|
| 254 |
+
"loss": 0.5824,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"learning_rate": 4.102728484972818e-05,
|
| 260 |
+
"loss": 0.5897,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.37,
|
| 265 |
+
"learning_rate": 4.0813587718398475e-05,
|
| 266 |
+
"loss": 0.5822,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.38,
|
| 271 |
+
"learning_rate": 4.059989058706876e-05,
|
| 272 |
+
"loss": 0.5936,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.38,
|
| 277 |
+
"learning_rate": 4.0386193455739054e-05,
|
| 278 |
+
"loss": 0.582,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.39,
|
| 283 |
+
"learning_rate": 4.017249632440934e-05,
|
| 284 |
+
"loss": 0.593,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.4,
|
| 289 |
+
"learning_rate": 3.9958799193079634e-05,
|
| 290 |
+
"loss": 0.5881,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.41,
|
| 295 |
+
"learning_rate": 3.974552945601259e-05,
|
| 296 |
+
"loss": 0.5841,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"learning_rate": 3.9531832324682874e-05,
|
| 302 |
+
"loss": 0.581,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.43,
|
| 307 |
+
"learning_rate": 3.931813519335317e-05,
|
| 308 |
+
"loss": 0.5957,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.44,
|
| 313 |
+
"learning_rate": 3.9104438062023454e-05,
|
| 314 |
+
"loss": 0.5887,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.44,
|
| 319 |
+
"learning_rate": 3.889074093069375e-05,
|
| 320 |
+
"loss": 0.5718,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.45,
|
| 325 |
+
"learning_rate": 3.867704379936404e-05,
|
| 326 |
+
"loss": 0.5952,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.46,
|
| 331 |
+
"learning_rate": 3.8463774062296995e-05,
|
| 332 |
+
"loss": 0.5812,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.47,
|
| 337 |
+
"learning_rate": 3.825007693096728e-05,
|
| 338 |
+
"loss": 0.5717,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"learning_rate": 3.8036379799637574e-05,
|
| 344 |
+
"loss": 0.5775,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.49,
|
| 349 |
+
"learning_rate": 3.782268266830786e-05,
|
| 350 |
+
"loss": 0.5737,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.5,
|
| 355 |
+
"learning_rate": 3.7609412931240815e-05,
|
| 356 |
+
"loss": 0.5904,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.5,
|
| 361 |
+
"learning_rate": 3.73957157999111e-05,
|
| 362 |
+
"loss": 0.5953,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.51,
|
| 367 |
+
"learning_rate": 3.7182018668581394e-05,
|
| 368 |
+
"loss": 0.5902,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.52,
|
| 373 |
+
"learning_rate": 3.696832153725169e-05,
|
| 374 |
+
"loss": 0.5769,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.53,
|
| 379 |
+
"learning_rate": 3.6755051800184635e-05,
|
| 380 |
+
"loss": 0.5876,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"learning_rate": 3.654135466885493e-05,
|
| 386 |
+
"loss": 0.5965,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.55,
|
| 391 |
+
"learning_rate": 3.6327657537525215e-05,
|
| 392 |
+
"loss": 0.5748,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.56,
|
| 397 |
+
"learning_rate": 3.611396040619551e-05,
|
| 398 |
+
"loss": 0.568,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.56,
|
| 403 |
+
"learning_rate": 3.5900263274865794e-05,
|
| 404 |
+
"loss": 0.5812,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.57,
|
| 409 |
+
"learning_rate": 3.5686993537798755e-05,
|
| 410 |
+
"loss": 0.5785,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.58,
|
| 415 |
+
"learning_rate": 3.547329640646904e-05,
|
| 416 |
+
"loss": 0.5764,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.59,
|
| 421 |
+
"learning_rate": 3.5259599275139335e-05,
|
| 422 |
+
"loss": 0.5766,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"learning_rate": 3.504590214380962e-05,
|
| 428 |
+
"loss": 0.5783,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.61,
|
| 433 |
+
"learning_rate": 3.4832205012479914e-05,
|
| 434 |
+
"loss": 0.5794,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.62,
|
| 439 |
+
"learning_rate": 3.46185078811502e-05,
|
| 440 |
+
"loss": 0.5741,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.62,
|
| 445 |
+
"learning_rate": 3.44048107498205e-05,
|
| 446 |
+
"loss": 0.5766,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.63,
|
| 451 |
+
"learning_rate": 3.419154101275345e-05,
|
| 452 |
+
"loss": 0.5694,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.64,
|
| 457 |
+
"learning_rate": 3.3977843881423735e-05,
|
| 458 |
+
"loss": 0.5848,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.65,
|
| 463 |
+
"learning_rate": 3.376414675009403e-05,
|
| 464 |
+
"loss": 0.577,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"learning_rate": 3.355044961876432e-05,
|
| 470 |
+
"loss": 0.5645,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.67,
|
| 475 |
+
"learning_rate": 3.333675248743461e-05,
|
| 476 |
+
"loss": 0.5869,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.68,
|
| 481 |
+
"learning_rate": 3.31230553561049e-05,
|
| 482 |
+
"loss": 0.5811,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.68,
|
| 487 |
+
"learning_rate": 3.2909358224775194e-05,
|
| 488 |
+
"loss": 0.5753,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.69,
|
| 493 |
+
"learning_rate": 3.269566109344549e-05,
|
| 494 |
+
"loss": 0.5787,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.7,
|
| 499 |
+
"learning_rate": 3.2482391356378434e-05,
|
| 500 |
+
"loss": 0.5823,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.71,
|
| 505 |
+
"learning_rate": 3.226869422504872e-05,
|
| 506 |
+
"loss": 0.5708,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"learning_rate": 3.2054997093719014e-05,
|
| 512 |
+
"loss": 0.5662,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.73,
|
| 517 |
+
"learning_rate": 3.18412999623893e-05,
|
| 518 |
+
"loss": 0.5862,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.74,
|
| 523 |
+
"learning_rate": 3.1628457619584915e-05,
|
| 524 |
+
"loss": 0.5784,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.74,
|
| 529 |
+
"learning_rate": 3.141476048825521e-05,
|
| 530 |
+
"loss": 0.5724,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.75,
|
| 535 |
+
"learning_rate": 3.1201063356925495e-05,
|
| 536 |
+
"loss": 0.5693,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.76,
|
| 541 |
+
"learning_rate": 3.098736622559579e-05,
|
| 542 |
+
"loss": 0.579,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.77,
|
| 547 |
+
"learning_rate": 3.0773669094266075e-05,
|
| 548 |
+
"loss": 0.5761,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"learning_rate": 3.0559971962936375e-05,
|
| 554 |
+
"loss": 0.5687,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.79,
|
| 559 |
+
"learning_rate": 3.0346274831606665e-05,
|
| 560 |
+
"loss": 0.5803,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.79,
|
| 565 |
+
"learning_rate": 3.0133005094539612e-05,
|
| 566 |
+
"loss": 0.5859,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.8,
|
| 571 |
+
"learning_rate": 2.9919307963209902e-05,
|
| 572 |
+
"loss": 0.5792,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.81,
|
| 577 |
+
"learning_rate": 2.970561083188019e-05,
|
| 578 |
+
"loss": 0.5788,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.82,
|
| 583 |
+
"learning_rate": 2.949191370055048e-05,
|
| 584 |
+
"loss": 0.565,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.83,
|
| 589 |
+
"learning_rate": 2.9278216569220778e-05,
|
| 590 |
+
"loss": 0.5819,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"learning_rate": 2.9064519437891068e-05,
|
| 596 |
+
"loss": 0.5763,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.85,
|
| 601 |
+
"learning_rate": 2.8850822306561358e-05,
|
| 602 |
+
"loss": 0.5721,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.85,
|
| 607 |
+
"learning_rate": 2.863712517523165e-05,
|
| 608 |
+
"loss": 0.5793,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.86,
|
| 613 |
+
"learning_rate": 2.8423855438164598e-05,
|
| 614 |
+
"loss": 0.5522,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.87,
|
| 619 |
+
"learning_rate": 2.821058570109755e-05,
|
| 620 |
+
"loss": 0.5694,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.88,
|
| 625 |
+
"learning_rate": 2.7996888569767842e-05,
|
| 626 |
+
"loss": 0.5727,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.89,
|
| 631 |
+
"learning_rate": 2.7783191438438132e-05,
|
| 632 |
+
"loss": 0.5761,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"learning_rate": 2.7569494307108422e-05,
|
| 638 |
+
"loss": 0.5789,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.91,
|
| 643 |
+
"learning_rate": 2.7355797175778715e-05,
|
| 644 |
+
"loss": 0.5737,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.91,
|
| 649 |
+
"learning_rate": 2.7142100044449005e-05,
|
| 650 |
+
"loss": 0.5587,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.92,
|
| 655 |
+
"learning_rate": 2.6928402913119295e-05,
|
| 656 |
+
"loss": 0.5739,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.93,
|
| 661 |
+
"learning_rate": 2.6714705781789585e-05,
|
| 662 |
+
"loss": 0.5672,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.94,
|
| 667 |
+
"learning_rate": 2.650100865045988e-05,
|
| 668 |
+
"loss": 0.5648,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.95,
|
| 673 |
+
"learning_rate": 2.628731151913017e-05,
|
| 674 |
+
"loss": 0.561,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"learning_rate": 2.6074041782063118e-05,
|
| 680 |
+
"loss": 0.5646,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.97,
|
| 685 |
+
"learning_rate": 2.5860344650733408e-05,
|
| 686 |
+
"loss": 0.5705,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.97,
|
| 691 |
+
"learning_rate": 2.5646647519403698e-05,
|
| 692 |
+
"loss": 0.5759,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.98,
|
| 697 |
+
"learning_rate": 2.5432950388073988e-05,
|
| 698 |
+
"loss": 0.5605,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.99,
|
| 703 |
+
"learning_rate": 2.5219680651006945e-05,
|
| 704 |
+
"loss": 0.5759,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.0,
|
| 709 |
+
"learning_rate": 2.5005983519677235e-05,
|
| 710 |
+
"loss": 0.5665,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.01,
|
| 715 |
+
"learning_rate": 2.4792286388347525e-05,
|
| 716 |
+
"loss": 0.5534,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.02,
|
| 721 |
+
"learning_rate": 2.4578589257017815e-05,
|
| 722 |
+
"loss": 0.5565,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.03,
|
| 727 |
+
"learning_rate": 2.4364892125688105e-05,
|
| 728 |
+
"loss": 0.5519,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.03,
|
| 733 |
+
"learning_rate": 2.4151194994358398e-05,
|
| 734 |
+
"loss": 0.57,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.04,
|
| 739 |
+
"learning_rate": 2.3937497863028688e-05,
|
| 740 |
+
"loss": 0.5479,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.05,
|
| 745 |
+
"learning_rate": 2.3723800731698977e-05,
|
| 746 |
+
"loss": 0.5518,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.06,
|
| 751 |
+
"learning_rate": 2.3510530994631928e-05,
|
| 752 |
+
"loss": 0.5466,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.07,
|
| 757 |
+
"learning_rate": 2.329726125756488e-05,
|
| 758 |
+
"loss": 0.5427,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.08,
|
| 763 |
+
"learning_rate": 2.3083564126235172e-05,
|
| 764 |
+
"loss": 0.5503,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.09,
|
| 769 |
+
"learning_rate": 2.2869866994905462e-05,
|
| 770 |
+
"loss": 0.557,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.09,
|
| 775 |
+
"learning_rate": 2.265616986357575e-05,
|
| 776 |
+
"loss": 0.5615,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.1,
|
| 781 |
+
"learning_rate": 2.2442900126508702e-05,
|
| 782 |
+
"loss": 0.5535,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.11,
|
| 787 |
+
"learning_rate": 2.2229202995178992e-05,
|
| 788 |
+
"loss": 0.5594,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.12,
|
| 793 |
+
"learning_rate": 2.2015505863849285e-05,
|
| 794 |
+
"loss": 0.5467,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.13,
|
| 799 |
+
"learning_rate": 2.1802236126782236e-05,
|
| 800 |
+
"loss": 0.5505,
|
| 801 |
+
"step": 66000
|
| 802 |
+
}
|
| 803 |
+
],
|
| 804 |
+
"logging_steps": 500,
|
| 805 |
+
"max_steps": 116988,
|
| 806 |
+
"num_input_tokens_seen": 0,
|
| 807 |
+
"num_train_epochs": 2,
|
| 808 |
+
"save_steps": 2000,
|
| 809 |
+
"total_flos": 9.807079511383081e+17,
|
| 810 |
+
"train_batch_size": 1,
|
| 811 |
+
"trial_name": null,
|
| 812 |
+
"trial_params": null
|
| 813 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43d8a925b1240ef4326030dcb757585f6c2aea6e047ff7a973e5c48b7f9bc69d
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|