finance teacher fwd distill
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
- trainer_state.json +954 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "JackFram/llama-160m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 12,
|
| 15 |
+
"num_hidden_layers": 12,
|
| 16 |
+
"num_key_value_heads": 12,
|
| 17 |
+
"pad_token_id": 1,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.33.2"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b3d1d7962c46987cfee196da61d57ab716b4a1b4831de17317f1d89959a947f
|
| 3 |
+
size 649705097
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": null,
|
| 22 |
+
"model_max_length": 256,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"spaces_between_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"use_default_system_prompt": true
|
| 37 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,954 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9836867862969005,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 152,
|
| 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": 2.0000000000000003e-06,
|
| 14 |
+
"loss": 1.9706,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 4.000000000000001e-06,
|
| 20 |
+
"loss": 1.9709,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 6e-06,
|
| 26 |
+
"loss": 1.969,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 8.000000000000001e-06,
|
| 32 |
+
"loss": 1.9386,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 1e-05,
|
| 38 |
+
"loss": 1.9129,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 9.99885820390154e-06,
|
| 44 |
+
"loss": 1.8105,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 9.995433337085492e-06,
|
| 50 |
+
"loss": 1.8118,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 9.989726963751683e-06,
|
| 56 |
+
"loss": 1.7729,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.12,
|
| 61 |
+
"learning_rate": 9.981741690106035e-06,
|
| 62 |
+
"loss": 1.7652,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.13,
|
| 67 |
+
"learning_rate": 9.97148116317027e-06,
|
| 68 |
+
"loss": 1.7182,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.14,
|
| 73 |
+
"learning_rate": 9.95895006911623e-06,
|
| 74 |
+
"loss": 1.7277,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.16,
|
| 79 |
+
"learning_rate": 9.944154131125643e-06,
|
| 80 |
+
"loss": 1.6587,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.17,
|
| 85 |
+
"learning_rate": 9.927100106776213e-06,
|
| 86 |
+
"loss": 1.6772,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.18,
|
| 91 |
+
"learning_rate": 9.907795784955327e-06,
|
| 92 |
+
"loss": 1.6292,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"learning_rate": 9.88624998230272e-06,
|
| 98 |
+
"loss": 1.6161,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.21,
|
| 103 |
+
"learning_rate": 9.862472539183757e-06,
|
| 104 |
+
"loss": 1.6353,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.22,
|
| 109 |
+
"learning_rate": 9.836474315195148e-06,
|
| 110 |
+
"loss": 1.6141,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.23,
|
| 115 |
+
"learning_rate": 9.808267184205182e-06,
|
| 116 |
+
"loss": 1.6154,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.25,
|
| 121 |
+
"learning_rate": 9.777864028930705e-06,
|
| 122 |
+
"loss": 1.568,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.26,
|
| 127 |
+
"learning_rate": 9.745278735053345e-06,
|
| 128 |
+
"loss": 1.6019,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.27,
|
| 133 |
+
"learning_rate": 9.710526184877667e-06,
|
| 134 |
+
"loss": 1.5974,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"learning_rate": 9.673622250534155e-06,
|
| 140 |
+
"loss": 1.5645,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.3,
|
| 145 |
+
"learning_rate": 9.63458378673011e-06,
|
| 146 |
+
"loss": 1.5472,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.31,
|
| 151 |
+
"learning_rate": 9.593428623051793e-06,
|
| 152 |
+
"loss": 1.5662,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.33,
|
| 157 |
+
"learning_rate": 9.550175555821333e-06,
|
| 158 |
+
"loss": 1.5278,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.34,
|
| 163 |
+
"learning_rate": 9.504844339512096e-06,
|
| 164 |
+
"loss": 1.5819,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.35,
|
| 169 |
+
"learning_rate": 9.457455677726447e-06,
|
| 170 |
+
"loss": 1.5355,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.37,
|
| 175 |
+
"learning_rate": 9.408031213740045e-06,
|
| 176 |
+
"loss": 1.5449,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.38,
|
| 181 |
+
"learning_rate": 9.356593520616948e-06,
|
| 182 |
+
"loss": 1.5327,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.39,
|
| 187 |
+
"learning_rate": 9.303166090900082e-06,
|
| 188 |
+
"loss": 1.4996,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4,
|
| 193 |
+
"learning_rate": 9.24777332588177e-06,
|
| 194 |
+
"loss": 1.4838,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.42,
|
| 199 |
+
"learning_rate": 9.190440524459203e-06,
|
| 200 |
+
"loss": 1.5343,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.43,
|
| 205 |
+
"learning_rate": 9.131193871579975e-06,
|
| 206 |
+
"loss": 1.5159,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.44,
|
| 211 |
+
"learning_rate": 9.070060426282924e-06,
|
| 212 |
+
"loss": 1.5343,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.46,
|
| 217 |
+
"learning_rate": 9.007068109339783e-06,
|
| 218 |
+
"loss": 1.5472,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.47,
|
| 223 |
+
"learning_rate": 8.94224569050324e-06,
|
| 224 |
+
"loss": 1.4968,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.48,
|
| 229 |
+
"learning_rate": 8.87562277536726e-06,
|
| 230 |
+
"loss": 1.5261,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.5,
|
| 235 |
+
"learning_rate": 8.807229791845673e-06,
|
| 236 |
+
"loss": 1.4568,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.51,
|
| 241 |
+
"learning_rate": 8.737097976275177e-06,
|
| 242 |
+
"loss": 1.5257,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.52,
|
| 247 |
+
"learning_rate": 8.665259359149132e-06,
|
| 248 |
+
"loss": 1.5265,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.54,
|
| 253 |
+
"learning_rate": 8.591746750488639e-06,
|
| 254 |
+
"loss": 1.5067,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.55,
|
| 259 |
+
"learning_rate": 8.516593724857598e-06,
|
| 260 |
+
"loss": 1.4628,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.56,
|
| 265 |
+
"learning_rate": 8.439834606028594e-06,
|
| 266 |
+
"loss": 1.4626,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.57,
|
| 271 |
+
"learning_rate": 8.361504451306585e-06,
|
| 272 |
+
"loss": 1.5269,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.59,
|
| 277 |
+
"learning_rate": 8.281639035517591e-06,
|
| 278 |
+
"loss": 1.4551,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6,
|
| 283 |
+
"learning_rate": 8.200274834669675e-06,
|
| 284 |
+
"loss": 1.4287,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.61,
|
| 289 |
+
"learning_rate": 8.117449009293668e-06,
|
| 290 |
+
"loss": 1.4808,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.63,
|
| 295 |
+
"learning_rate": 8.033199387471278e-06,
|
| 296 |
+
"loss": 1.5128,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.64,
|
| 301 |
+
"learning_rate": 7.9475644475583e-06,
|
| 302 |
+
"loss": 1.4867,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.65,
|
| 307 |
+
"learning_rate": 7.860583300610849e-06,
|
| 308 |
+
"loss": 1.4873,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.67,
|
| 313 |
+
"learning_rate": 7.772295672522615e-06,
|
| 314 |
+
"loss": 1.4294,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.68,
|
| 319 |
+
"learning_rate": 7.682741885881314e-06,
|
| 320 |
+
"loss": 1.4629,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.69,
|
| 325 |
+
"learning_rate": 7.591962841552627e-06,
|
| 326 |
+
"loss": 1.5219,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.7,
|
| 331 |
+
"learning_rate": 7.500000000000001e-06,
|
| 332 |
+
"loss": 1.4715,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.72,
|
| 337 |
+
"learning_rate": 7.406895362348916e-06,
|
| 338 |
+
"loss": 1.4632,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.73,
|
| 343 |
+
"learning_rate": 7.312691451204178e-06,
|
| 344 |
+
"loss": 1.481,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.74,
|
| 349 |
+
"learning_rate": 7.217431291229068e-06,
|
| 350 |
+
"loss": 1.4556,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.76,
|
| 355 |
+
"learning_rate": 7.121158389495187e-06,
|
| 356 |
+
"loss": 1.4419,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.77,
|
| 361 |
+
"learning_rate": 7.023916715611969e-06,
|
| 362 |
+
"loss": 1.4326,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.78,
|
| 367 |
+
"learning_rate": 6.925750681644954e-06,
|
| 368 |
+
"loss": 1.4692,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.8,
|
| 373 |
+
"learning_rate": 6.8267051218319766e-06,
|
| 374 |
+
"loss": 1.4426,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.81,
|
| 379 |
+
"learning_rate": 6.726825272106539e-06,
|
| 380 |
+
"loss": 1.4479,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.82,
|
| 385 |
+
"learning_rate": 6.626156749437736e-06,
|
| 386 |
+
"loss": 1.4601,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.84,
|
| 391 |
+
"learning_rate": 6.524745530996137e-06,
|
| 392 |
+
"loss": 1.4852,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.85,
|
| 397 |
+
"learning_rate": 6.4226379331551625e-06,
|
| 398 |
+
"loss": 1.4272,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.86,
|
| 403 |
+
"learning_rate": 6.319880590337549e-06,
|
| 404 |
+
"loss": 1.4784,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.87,
|
| 409 |
+
"learning_rate": 6.216520433716544e-06,
|
| 410 |
+
"loss": 1.4409,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.89,
|
| 415 |
+
"learning_rate": 6.112604669781572e-06,
|
| 416 |
+
"loss": 1.4723,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.9,
|
| 421 |
+
"learning_rate": 6.008180758778167e-06,
|
| 422 |
+
"loss": 1.4417,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.91,
|
| 427 |
+
"learning_rate": 5.903296393031996e-06,
|
| 428 |
+
"loss": 1.4258,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.93,
|
| 433 |
+
"learning_rate": 5.797999475166897e-06,
|
| 434 |
+
"loss": 1.4418,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.94,
|
| 439 |
+
"learning_rate": 5.69233809622687e-06,
|
| 440 |
+
"loss": 1.4556,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.95,
|
| 445 |
+
"learning_rate": 5.586360513712011e-06,
|
| 446 |
+
"loss": 1.4235,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.97,
|
| 451 |
+
"learning_rate": 5.480115129538409e-06,
|
| 452 |
+
"loss": 1.4279,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.98,
|
| 457 |
+
"learning_rate": 5.373650467932122e-06,
|
| 458 |
+
"loss": 1.4399,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.99,
|
| 463 |
+
"learning_rate": 5.267015153267246e-06,
|
| 464 |
+
"loss": 1.4034,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.99,
|
| 469 |
+
"eval_runtime": 1301.4856,
|
| 470 |
+
"eval_samples_per_second": 0.154,
|
| 471 |
+
"eval_steps_per_second": 0.154,
|
| 472 |
+
"step": 76
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0,
|
| 476 |
+
"learning_rate": 5.160257887858278e-06,
|
| 477 |
+
"loss": 1.4125,
|
| 478 |
+
"step": 77
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.02,
|
| 482 |
+
"learning_rate": 5.053427429716867e-06,
|
| 483 |
+
"loss": 1.4199,
|
| 484 |
+
"step": 78
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.03,
|
| 488 |
+
"learning_rate": 4.946572570283135e-06,
|
| 489 |
+
"loss": 1.4027,
|
| 490 |
+
"step": 79
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.04,
|
| 494 |
+
"learning_rate": 4.839742112141725e-06,
|
| 495 |
+
"loss": 1.3917,
|
| 496 |
+
"step": 80
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.06,
|
| 500 |
+
"learning_rate": 4.732984846732755e-06,
|
| 501 |
+
"loss": 1.4201,
|
| 502 |
+
"step": 81
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.07,
|
| 506 |
+
"learning_rate": 4.626349532067879e-06,
|
| 507 |
+
"loss": 1.3852,
|
| 508 |
+
"step": 82
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.08,
|
| 512 |
+
"learning_rate": 4.5198848704615915e-06,
|
| 513 |
+
"loss": 1.3846,
|
| 514 |
+
"step": 83
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.1,
|
| 518 |
+
"learning_rate": 4.413639486287992e-06,
|
| 519 |
+
"loss": 1.3979,
|
| 520 |
+
"step": 84
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.11,
|
| 524 |
+
"learning_rate": 4.307661903773129e-06,
|
| 525 |
+
"loss": 1.381,
|
| 526 |
+
"step": 85
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.12,
|
| 530 |
+
"learning_rate": 4.2020005248331056e-06,
|
| 531 |
+
"loss": 1.3978,
|
| 532 |
+
"step": 86
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.14,
|
| 536 |
+
"learning_rate": 4.096703606968007e-06,
|
| 537 |
+
"loss": 1.4146,
|
| 538 |
+
"step": 87
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.15,
|
| 542 |
+
"learning_rate": 3.991819241221836e-06,
|
| 543 |
+
"loss": 1.4094,
|
| 544 |
+
"step": 88
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.16,
|
| 548 |
+
"learning_rate": 3.887395330218429e-06,
|
| 549 |
+
"loss": 1.3919,
|
| 550 |
+
"step": 89
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.17,
|
| 554 |
+
"learning_rate": 3.783479566283457e-06,
|
| 555 |
+
"loss": 1.3931,
|
| 556 |
+
"step": 90
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.19,
|
| 560 |
+
"learning_rate": 3.6801194096624515e-06,
|
| 561 |
+
"loss": 1.3984,
|
| 562 |
+
"step": 91
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2,
|
| 566 |
+
"learning_rate": 3.5773620668448384e-06,
|
| 567 |
+
"loss": 1.357,
|
| 568 |
+
"step": 92
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.21,
|
| 572 |
+
"learning_rate": 3.475254469003865e-06,
|
| 573 |
+
"loss": 1.3806,
|
| 574 |
+
"step": 93
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.23,
|
| 578 |
+
"learning_rate": 3.3738432505622653e-06,
|
| 579 |
+
"loss": 1.3789,
|
| 580 |
+
"step": 94
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.24,
|
| 584 |
+
"learning_rate": 3.273174727893463e-06,
|
| 585 |
+
"loss": 1.3644,
|
| 586 |
+
"step": 95
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.25,
|
| 590 |
+
"learning_rate": 3.173294878168025e-06,
|
| 591 |
+
"loss": 1.3892,
|
| 592 |
+
"step": 96
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.27,
|
| 596 |
+
"learning_rate": 3.074249318355046e-06,
|
| 597 |
+
"loss": 1.3787,
|
| 598 |
+
"step": 97
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.28,
|
| 602 |
+
"learning_rate": 2.976083284388031e-06,
|
| 603 |
+
"loss": 1.3989,
|
| 604 |
+
"step": 98
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.29,
|
| 608 |
+
"learning_rate": 2.8788416105048124e-06,
|
| 609 |
+
"loss": 1.3673,
|
| 610 |
+
"step": 99
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.31,
|
| 614 |
+
"learning_rate": 2.782568708770933e-06,
|
| 615 |
+
"loss": 1.3505,
|
| 616 |
+
"step": 100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.32,
|
| 620 |
+
"learning_rate": 2.687308548795825e-06,
|
| 621 |
+
"loss": 1.3426,
|
| 622 |
+
"step": 101
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.33,
|
| 626 |
+
"learning_rate": 2.5931046376510875e-06,
|
| 627 |
+
"loss": 1.3851,
|
| 628 |
+
"step": 102
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.34,
|
| 632 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 633 |
+
"loss": 1.3911,
|
| 634 |
+
"step": 103
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.36,
|
| 638 |
+
"learning_rate": 2.408037158447375e-06,
|
| 639 |
+
"loss": 1.3748,
|
| 640 |
+
"step": 104
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.37,
|
| 644 |
+
"learning_rate": 2.317258114118686e-06,
|
| 645 |
+
"loss": 1.385,
|
| 646 |
+
"step": 105
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.38,
|
| 650 |
+
"learning_rate": 2.2277043274773856e-06,
|
| 651 |
+
"loss": 1.3342,
|
| 652 |
+
"step": 106
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.4,
|
| 656 |
+
"learning_rate": 2.139416699389153e-06,
|
| 657 |
+
"loss": 1.3472,
|
| 658 |
+
"step": 107
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.41,
|
| 662 |
+
"learning_rate": 2.0524355524417017e-06,
|
| 663 |
+
"loss": 1.3647,
|
| 664 |
+
"step": 108
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.42,
|
| 668 |
+
"learning_rate": 1.966800612528723e-06,
|
| 669 |
+
"loss": 1.3827,
|
| 670 |
+
"step": 109
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.44,
|
| 674 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 675 |
+
"loss": 1.3681,
|
| 676 |
+
"step": 110
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.45,
|
| 680 |
+
"learning_rate": 1.7997251653303249e-06,
|
| 681 |
+
"loss": 1.4033,
|
| 682 |
+
"step": 111
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.46,
|
| 686 |
+
"learning_rate": 1.7183609644824096e-06,
|
| 687 |
+
"loss": 1.3881,
|
| 688 |
+
"step": 112
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.47,
|
| 692 |
+
"learning_rate": 1.6384955486934157e-06,
|
| 693 |
+
"loss": 1.3859,
|
| 694 |
+
"step": 113
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.49,
|
| 698 |
+
"learning_rate": 1.5601653939714073e-06,
|
| 699 |
+
"loss": 1.3784,
|
| 700 |
+
"step": 114
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.5,
|
| 704 |
+
"learning_rate": 1.4834062751424018e-06,
|
| 705 |
+
"loss": 1.3277,
|
| 706 |
+
"step": 115
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.51,
|
| 710 |
+
"learning_rate": 1.4082532495113627e-06,
|
| 711 |
+
"loss": 1.4009,
|
| 712 |
+
"step": 116
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.53,
|
| 716 |
+
"learning_rate": 1.3347406408508695e-06,
|
| 717 |
+
"loss": 1.3895,
|
| 718 |
+
"step": 117
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.54,
|
| 722 |
+
"learning_rate": 1.2629020237248241e-06,
|
| 723 |
+
"loss": 1.3789,
|
| 724 |
+
"step": 118
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.55,
|
| 728 |
+
"learning_rate": 1.1927702081543279e-06,
|
| 729 |
+
"loss": 1.3381,
|
| 730 |
+
"step": 119
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.57,
|
| 734 |
+
"learning_rate": 1.1243772246327416e-06,
|
| 735 |
+
"loss": 1.3618,
|
| 736 |
+
"step": 120
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.58,
|
| 740 |
+
"learning_rate": 1.0577543094967613e-06,
|
| 741 |
+
"loss": 1.379,
|
| 742 |
+
"step": 121
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.59,
|
| 746 |
+
"learning_rate": 9.929318906602176e-07,
|
| 747 |
+
"loss": 1.3335,
|
| 748 |
+
"step": 122
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.61,
|
| 752 |
+
"learning_rate": 9.299395737170758e-07,
|
| 753 |
+
"loss": 1.3506,
|
| 754 |
+
"step": 123
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.62,
|
| 758 |
+
"learning_rate": 8.688061284200266e-07,
|
| 759 |
+
"loss": 1.3791,
|
| 760 |
+
"step": 124
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.63,
|
| 764 |
+
"learning_rate": 8.095594755407971e-07,
|
| 765 |
+
"loss": 1.401,
|
| 766 |
+
"step": 125
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.64,
|
| 770 |
+
"learning_rate": 7.522266741182305e-07,
|
| 771 |
+
"loss": 1.3791,
|
| 772 |
+
"step": 126
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.66,
|
| 776 |
+
"learning_rate": 6.968339090999188e-07,
|
| 777 |
+
"loss": 1.3748,
|
| 778 |
+
"step": 127
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.67,
|
| 782 |
+
"learning_rate": 6.43406479383053e-07,
|
| 783 |
+
"loss": 1.3614,
|
| 784 |
+
"step": 128
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.68,
|
| 788 |
+
"learning_rate": 5.919687862599549e-07,
|
| 789 |
+
"loss": 1.3902,
|
| 790 |
+
"step": 129
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.7,
|
| 794 |
+
"learning_rate": 5.425443222735527e-07,
|
| 795 |
+
"loss": 1.4062,
|
| 796 |
+
"step": 130
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.71,
|
| 800 |
+
"learning_rate": 4.951556604879049e-07,
|
| 801 |
+
"loss": 1.3798,
|
| 802 |
+
"step": 131
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.72,
|
| 806 |
+
"learning_rate": 4.4982444417866753e-07,
|
| 807 |
+
"loss": 1.3926,
|
| 808 |
+
"step": 132
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.74,
|
| 812 |
+
"learning_rate": 4.0657137694820826e-07,
|
| 813 |
+
"loss": 1.3757,
|
| 814 |
+
"step": 133
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.75,
|
| 818 |
+
"learning_rate": 3.6541621326989183e-07,
|
| 819 |
+
"loss": 1.3645,
|
| 820 |
+
"step": 134
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.76,
|
| 824 |
+
"learning_rate": 3.263777494658449e-07,
|
| 825 |
+
"loss": 1.3553,
|
| 826 |
+
"step": 135
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.77,
|
| 830 |
+
"learning_rate": 2.894738151223331e-07,
|
| 831 |
+
"loss": 1.3493,
|
| 832 |
+
"step": 136
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.79,
|
| 836 |
+
"learning_rate": 2.547212649466568e-07,
|
| 837 |
+
"loss": 1.4113,
|
| 838 |
+
"step": 137
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.8,
|
| 842 |
+
"learning_rate": 2.2213597106929608e-07,
|
| 843 |
+
"loss": 1.3679,
|
| 844 |
+
"step": 138
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.81,
|
| 848 |
+
"learning_rate": 1.9173281579481896e-07,
|
| 849 |
+
"loss": 1.3833,
|
| 850 |
+
"step": 139
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.83,
|
| 854 |
+
"learning_rate": 1.6352568480485277e-07,
|
| 855 |
+
"loss": 1.3852,
|
| 856 |
+
"step": 140
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.84,
|
| 860 |
+
"learning_rate": 1.375274608162447e-07,
|
| 861 |
+
"loss": 1.3982,
|
| 862 |
+
"step": 141
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.85,
|
| 866 |
+
"learning_rate": 1.1375001769728e-07,
|
| 867 |
+
"loss": 1.3666,
|
| 868 |
+
"step": 142
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.87,
|
| 872 |
+
"learning_rate": 9.22042150446728e-08,
|
| 873 |
+
"loss": 1.4037,
|
| 874 |
+
"step": 143
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.88,
|
| 878 |
+
"learning_rate": 7.289989322378732e-08,
|
| 879 |
+
"loss": 1.3762,
|
| 880 |
+
"step": 144
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.89,
|
| 884 |
+
"learning_rate": 5.584586887435739e-08,
|
| 885 |
+
"loss": 1.4058,
|
| 886 |
+
"step": 145
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.91,
|
| 890 |
+
"learning_rate": 4.104993088376974e-08,
|
| 891 |
+
"loss": 1.3856,
|
| 892 |
+
"step": 146
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.92,
|
| 896 |
+
"learning_rate": 2.8518836829732332e-08,
|
| 897 |
+
"loss": 1.3612,
|
| 898 |
+
"step": 147
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.93,
|
| 902 |
+
"learning_rate": 1.8258309893965375e-08,
|
| 903 |
+
"loss": 1.4054,
|
| 904 |
+
"step": 148
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.94,
|
| 908 |
+
"learning_rate": 1.0273036248318325e-08,
|
| 909 |
+
"loss": 1.3982,
|
| 910 |
+
"step": 149
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.96,
|
| 914 |
+
"learning_rate": 4.56666291450858e-09,
|
| 915 |
+
"loss": 1.3746,
|
| 916 |
+
"step": 150
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.97,
|
| 920 |
+
"learning_rate": 1.1417960984605459e-09,
|
| 921 |
+
"loss": 1.3612,
|
| 922 |
+
"step": 151
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.98,
|
| 926 |
+
"learning_rate": 0.0,
|
| 927 |
+
"loss": 1.4018,
|
| 928 |
+
"step": 152
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.98,
|
| 932 |
+
"eval_runtime": 1280.8781,
|
| 933 |
+
"eval_samples_per_second": 0.156,
|
| 934 |
+
"eval_steps_per_second": 0.156,
|
| 935 |
+
"step": 152
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.98,
|
| 939 |
+
"step": 152,
|
| 940 |
+
"total_flos": 4117616183476224.0,
|
| 941 |
+
"train_loss": 1.4679964404357106,
|
| 942 |
+
"train_runtime": 3899.9143,
|
| 943 |
+
"train_samples_per_second": 5.026,
|
| 944 |
+
"train_steps_per_second": 0.039
|
| 945 |
+
}
|
| 946 |
+
],
|
| 947 |
+
"logging_steps": 1.0,
|
| 948 |
+
"max_steps": 152,
|
| 949 |
+
"num_train_epochs": 2,
|
| 950 |
+
"save_steps": 100,
|
| 951 |
+
"total_flos": 4117616183476224.0,
|
| 952 |
+
"trial_name": null,
|
| 953 |
+
"trial_params": null
|
| 954 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca07b5de654d04d53abd27c8fe755077b8add8e9aea37efaf8eebbf1628dd3e7
|
| 3 |
+
size 4283
|