Upload folder using huggingface_hub
Browse files- all_results.json +8 -0
- config.json +28 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +32 -0
- train_results.json +8 -0
- trainer_state.json +904 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.037818258402621,
|
| 4 |
+
"train_runtime": 6822.2882,
|
| 5 |
+
"train_samples": 73151,
|
| 6 |
+
"train_samples_per_second": 10.722,
|
| 7 |
+
"train_steps_per_second": 10.722
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "d2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 5632,
|
| 12 |
+
"max_position_embeddings": 32000,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"n_ctx": 2048,
|
| 15 |
+
"n_positions": 16,
|
| 16 |
+
"num_attention_heads": 4,
|
| 17 |
+
"num_hidden_layers": 4,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.34.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.34.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f3962389bfec0f50d95a20423850f7bfbe60a269ced6a8ba5d572513e34202d
|
| 3 |
+
size 1346458086
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"model_max_length": 32000,
|
| 20 |
+
"pad_token": null,
|
| 21 |
+
"sp_model_kwargs": {},
|
| 22 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<unk>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"use_default_system_prompt": true
|
| 32 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.037818258402621,
|
| 4 |
+
"train_runtime": 6822.2882,
|
| 5 |
+
"train_samples": 73151,
|
| 6 |
+
"train_samples_per_second": 10.722,
|
| 7 |
+
"train_steps_per_second": 10.722
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 73151,
|
| 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": 4.965824117236949e-05,
|
| 14 |
+
"loss": 5.6804,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4.9316482344738966e-05,
|
| 20 |
+
"loss": 4.9782,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 4.897472351710845e-05,
|
| 26 |
+
"loss": 4.8339,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 4.8632964689477936e-05,
|
| 32 |
+
"loss": 4.6915,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 4.829188937950268e-05,
|
| 38 |
+
"loss": 4.5389,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"learning_rate": 4.7950130551872156e-05,
|
| 44 |
+
"loss": 4.362,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05,
|
| 49 |
+
"learning_rate": 4.760837172424164e-05,
|
| 50 |
+
"loss": 4.3116,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 4.7266612896611126e-05,
|
| 56 |
+
"loss": 4.245,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.06,
|
| 61 |
+
"learning_rate": 4.6924854068980604e-05,
|
| 62 |
+
"loss": 4.2283,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.07,
|
| 67 |
+
"learning_rate": 4.658309524135009e-05,
|
| 68 |
+
"loss": 4.1251,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.08,
|
| 73 |
+
"learning_rate": 4.624133641371957e-05,
|
| 74 |
+
"loss": 4.0663,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.08,
|
| 79 |
+
"learning_rate": 4.5899577586089046e-05,
|
| 80 |
+
"loss": 4.0828,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.09,
|
| 85 |
+
"learning_rate": 4.555918579376906e-05,
|
| 86 |
+
"loss": 3.9893,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1,
|
| 91 |
+
"learning_rate": 4.5217426966138536e-05,
|
| 92 |
+
"loss": 3.9494,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1,
|
| 97 |
+
"learning_rate": 4.487566813850802e-05,
|
| 98 |
+
"loss": 3.8261,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.11,
|
| 103 |
+
"learning_rate": 4.4533909310877506e-05,
|
| 104 |
+
"loss": 3.8834,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.12,
|
| 109 |
+
"learning_rate": 4.4192150483246984e-05,
|
| 110 |
+
"loss": 3.8186,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.12,
|
| 115 |
+
"learning_rate": 4.3851075173271725e-05,
|
| 116 |
+
"loss": 3.791,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.13,
|
| 121 |
+
"learning_rate": 4.350931634564121e-05,
|
| 122 |
+
"loss": 3.7413,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.14,
|
| 127 |
+
"learning_rate": 4.3167557518010696e-05,
|
| 128 |
+
"loss": 3.631,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.14,
|
| 133 |
+
"learning_rate": 4.2825798690380174e-05,
|
| 134 |
+
"loss": 3.6658,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.15,
|
| 139 |
+
"learning_rate": 4.248403986274966e-05,
|
| 140 |
+
"loss": 3.6128,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.16,
|
| 145 |
+
"learning_rate": 4.2142281035119144e-05,
|
| 146 |
+
"loss": 3.5832,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.16,
|
| 151 |
+
"learning_rate": 4.180052220748862e-05,
|
| 152 |
+
"loss": 3.4998,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.17,
|
| 157 |
+
"learning_rate": 4.14587633798581e-05,
|
| 158 |
+
"loss": 3.5122,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.18,
|
| 163 |
+
"learning_rate": 4.111768806988285e-05,
|
| 164 |
+
"loss": 3.5041,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.18,
|
| 169 |
+
"learning_rate": 4.0775929242252334e-05,
|
| 170 |
+
"loss": 3.4191,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.19,
|
| 175 |
+
"learning_rate": 4.0434853932277075e-05,
|
| 176 |
+
"loss": 3.4023,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2,
|
| 181 |
+
"learning_rate": 4.0093095104646554e-05,
|
| 182 |
+
"loss": 3.3738,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.21,
|
| 187 |
+
"learning_rate": 3.975133627701604e-05,
|
| 188 |
+
"loss": 3.3359,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.21,
|
| 193 |
+
"learning_rate": 3.9409577449385524e-05,
|
| 194 |
+
"loss": 3.2606,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.22,
|
| 199 |
+
"learning_rate": 3.9068502139410265e-05,
|
| 200 |
+
"loss": 3.3322,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.23,
|
| 205 |
+
"learning_rate": 3.8726743311779744e-05,
|
| 206 |
+
"loss": 3.2278,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.23,
|
| 211 |
+
"learning_rate": 3.838498448414923e-05,
|
| 212 |
+
"loss": 3.2608,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.24,
|
| 217 |
+
"learning_rate": 3.8043225656518714e-05,
|
| 218 |
+
"loss": 3.2201,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.25,
|
| 223 |
+
"learning_rate": 3.770146682888819e-05,
|
| 224 |
+
"loss": 3.2005,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.25,
|
| 229 |
+
"learning_rate": 3.7360391518912934e-05,
|
| 230 |
+
"loss": 3.1464,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.26,
|
| 235 |
+
"learning_rate": 3.701863269128242e-05,
|
| 236 |
+
"loss": 3.2039,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.27,
|
| 241 |
+
"learning_rate": 3.6676873863651904e-05,
|
| 242 |
+
"loss": 3.1524,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.27,
|
| 247 |
+
"learning_rate": 3.633511503602138e-05,
|
| 248 |
+
"loss": 3.1729,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.28,
|
| 253 |
+
"learning_rate": 3.599335620839087e-05,
|
| 254 |
+
"loss": 3.1225,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.29,
|
| 259 |
+
"learning_rate": 3.5651597380760345e-05,
|
| 260 |
+
"loss": 3.1449,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.29,
|
| 265 |
+
"learning_rate": 3.530983855312983e-05,
|
| 266 |
+
"loss": 3.1289,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.3,
|
| 271 |
+
"learning_rate": 3.496807972549931e-05,
|
| 272 |
+
"loss": 3.0806,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.31,
|
| 277 |
+
"learning_rate": 3.462700441552406e-05,
|
| 278 |
+
"loss": 3.0845,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.31,
|
| 283 |
+
"learning_rate": 3.4285245587893535e-05,
|
| 284 |
+
"loss": 3.12,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.32,
|
| 289 |
+
"learning_rate": 3.394348676026302e-05,
|
| 290 |
+
"loss": 3.0579,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.33,
|
| 295 |
+
"learning_rate": 3.3601727932632506e-05,
|
| 296 |
+
"loss": 3.0443,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.33,
|
| 301 |
+
"learning_rate": 3.326065262265725e-05,
|
| 302 |
+
"loss": 3.0636,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.34,
|
| 307 |
+
"learning_rate": 3.2918893795026725e-05,
|
| 308 |
+
"loss": 3.0179,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.35,
|
| 313 |
+
"learning_rate": 3.257713496739621e-05,
|
| 314 |
+
"loss": 2.9552,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.36,
|
| 319 |
+
"learning_rate": 3.2235376139765695e-05,
|
| 320 |
+
"loss": 3.0536,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.36,
|
| 325 |
+
"learning_rate": 3.1893617312135174e-05,
|
| 326 |
+
"loss": 2.911,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.37,
|
| 331 |
+
"learning_rate": 3.1552542002159915e-05,
|
| 332 |
+
"loss": 3.0095,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.38,
|
| 337 |
+
"learning_rate": 3.12107831745294e-05,
|
| 338 |
+
"loss": 2.9568,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.38,
|
| 343 |
+
"learning_rate": 3.0869024346898885e-05,
|
| 344 |
+
"loss": 2.9344,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39,
|
| 349 |
+
"learning_rate": 3.0527265519268364e-05,
|
| 350 |
+
"loss": 2.9417,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4,
|
| 355 |
+
"learning_rate": 3.018619020929311e-05,
|
| 356 |
+
"loss": 2.9011,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.4,
|
| 361 |
+
"learning_rate": 2.984443138166259e-05,
|
| 362 |
+
"loss": 2.8799,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.41,
|
| 367 |
+
"learning_rate": 2.9502672554032075e-05,
|
| 368 |
+
"loss": 2.9197,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.42,
|
| 373 |
+
"learning_rate": 2.9160913726401557e-05,
|
| 374 |
+
"loss": 2.8963,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.42,
|
| 379 |
+
"learning_rate": 2.881915489877104e-05,
|
| 380 |
+
"loss": 2.914,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.43,
|
| 385 |
+
"learning_rate": 2.847807958879578e-05,
|
| 386 |
+
"loss": 2.8748,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.44,
|
| 391 |
+
"learning_rate": 2.8136320761165265e-05,
|
| 392 |
+
"loss": 2.9159,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.44,
|
| 397 |
+
"learning_rate": 2.7794561933534747e-05,
|
| 398 |
+
"loss": 2.8798,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.45,
|
| 403 |
+
"learning_rate": 2.745280310590423e-05,
|
| 404 |
+
"loss": 2.8773,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.46,
|
| 409 |
+
"learning_rate": 2.711104427827371e-05,
|
| 410 |
+
"loss": 2.8688,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.46,
|
| 415 |
+
"learning_rate": 2.676928545064319e-05,
|
| 416 |
+
"loss": 2.8408,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.47,
|
| 421 |
+
"learning_rate": 2.642752662301267e-05,
|
| 422 |
+
"loss": 2.8473,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.48,
|
| 427 |
+
"learning_rate": 2.6085767795382155e-05,
|
| 428 |
+
"loss": 2.8303,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.49,
|
| 433 |
+
"learning_rate": 2.57446924854069e-05,
|
| 434 |
+
"loss": 2.7961,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.49,
|
| 439 |
+
"learning_rate": 2.5402933657776385e-05,
|
| 440 |
+
"loss": 2.8852,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.5,
|
| 445 |
+
"learning_rate": 2.5061858347801127e-05,
|
| 446 |
+
"loss": 2.819,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.51,
|
| 451 |
+
"learning_rate": 2.4720099520170605e-05,
|
| 452 |
+
"loss": 2.8543,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.51,
|
| 457 |
+
"learning_rate": 2.437834069254009e-05,
|
| 458 |
+
"loss": 2.8135,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.52,
|
| 463 |
+
"learning_rate": 2.4036581864909572e-05,
|
| 464 |
+
"loss": 2.8237,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.53,
|
| 469 |
+
"learning_rate": 2.3695506554934317e-05,
|
| 470 |
+
"loss": 2.7813,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.53,
|
| 475 |
+
"learning_rate": 2.3353747727303798e-05,
|
| 476 |
+
"loss": 2.7788,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.54,
|
| 481 |
+
"learning_rate": 2.301198889967328e-05,
|
| 482 |
+
"loss": 2.7682,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.55,
|
| 487 |
+
"learning_rate": 2.267023007204276e-05,
|
| 488 |
+
"loss": 2.7843,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.55,
|
| 493 |
+
"learning_rate": 2.2328471244412243e-05,
|
| 494 |
+
"loss": 2.7897,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.56,
|
| 499 |
+
"learning_rate": 2.1987395934436988e-05,
|
| 500 |
+
"loss": 2.7146,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.57,
|
| 505 |
+
"learning_rate": 2.164563710680647e-05,
|
| 506 |
+
"loss": 2.7909,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.57,
|
| 511 |
+
"learning_rate": 2.130387827917595e-05,
|
| 512 |
+
"loss": 2.7408,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.58,
|
| 517 |
+
"learning_rate": 2.0962119451545433e-05,
|
| 518 |
+
"loss": 2.7703,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.59,
|
| 523 |
+
"learning_rate": 2.0620360623914915e-05,
|
| 524 |
+
"loss": 2.7564,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.59,
|
| 529 |
+
"learning_rate": 2.027928531393966e-05,
|
| 530 |
+
"loss": 2.7858,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6,
|
| 535 |
+
"learning_rate": 1.993752648630914e-05,
|
| 536 |
+
"loss": 2.7562,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.61,
|
| 541 |
+
"learning_rate": 1.9595767658678623e-05,
|
| 542 |
+
"loss": 2.7151,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.62,
|
| 547 |
+
"learning_rate": 1.9254008831048105e-05,
|
| 548 |
+
"loss": 2.7155,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.62,
|
| 553 |
+
"learning_rate": 1.891225000341759e-05,
|
| 554 |
+
"loss": 2.7111,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.63,
|
| 559 |
+
"learning_rate": 1.857049117578707e-05,
|
| 560 |
+
"loss": 2.7161,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.64,
|
| 565 |
+
"learning_rate": 1.8228732348156553e-05,
|
| 566 |
+
"loss": 2.7353,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.64,
|
| 571 |
+
"learning_rate": 1.7886973520526035e-05,
|
| 572 |
+
"loss": 2.671,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.65,
|
| 577 |
+
"learning_rate": 1.754589821055078e-05,
|
| 578 |
+
"loss": 2.708,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.66,
|
| 583 |
+
"learning_rate": 1.720413938292026e-05,
|
| 584 |
+
"loss": 2.7514,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.66,
|
| 589 |
+
"learning_rate": 1.6862380555289743e-05,
|
| 590 |
+
"loss": 2.6464,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.67,
|
| 595 |
+
"learning_rate": 1.6521305245314485e-05,
|
| 596 |
+
"loss": 2.7079,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.68,
|
| 601 |
+
"learning_rate": 1.617954641768397e-05,
|
| 602 |
+
"loss": 2.6883,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.68,
|
| 607 |
+
"learning_rate": 1.583778759005345e-05,
|
| 608 |
+
"loss": 2.686,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.69,
|
| 613 |
+
"learning_rate": 1.5496028762422933e-05,
|
| 614 |
+
"loss": 2.6826,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.7,
|
| 619 |
+
"learning_rate": 1.5154269934792417e-05,
|
| 620 |
+
"loss": 2.6855,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.7,
|
| 625 |
+
"learning_rate": 1.48125111071619e-05,
|
| 626 |
+
"loss": 2.607,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.71,
|
| 631 |
+
"learning_rate": 1.447075227953138e-05,
|
| 632 |
+
"loss": 2.7357,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.72,
|
| 637 |
+
"learning_rate": 1.4128993451900863e-05,
|
| 638 |
+
"loss": 2.644,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.72,
|
| 643 |
+
"learning_rate": 1.3787918141925606e-05,
|
| 644 |
+
"loss": 2.6631,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.73,
|
| 649 |
+
"learning_rate": 1.344615931429509e-05,
|
| 650 |
+
"loss": 2.6176,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.74,
|
| 655 |
+
"learning_rate": 1.3104400486664573e-05,
|
| 656 |
+
"loss": 2.6017,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.75,
|
| 661 |
+
"learning_rate": 1.2762641659034053e-05,
|
| 662 |
+
"loss": 2.615,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.75,
|
| 667 |
+
"learning_rate": 1.2420882831403535e-05,
|
| 668 |
+
"loss": 2.6685,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.76,
|
| 673 |
+
"learning_rate": 1.2079124003773018e-05,
|
| 674 |
+
"loss": 2.6363,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.77,
|
| 679 |
+
"learning_rate": 1.17373651761425e-05,
|
| 680 |
+
"loss": 2.6344,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.77,
|
| 685 |
+
"learning_rate": 1.1396289866167243e-05,
|
| 686 |
+
"loss": 2.6118,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.78,
|
| 691 |
+
"learning_rate": 1.1054531038536727e-05,
|
| 692 |
+
"loss": 2.617,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.79,
|
| 697 |
+
"learning_rate": 1.0712772210906208e-05,
|
| 698 |
+
"loss": 2.6345,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.79,
|
| 703 |
+
"learning_rate": 1.037101338327569e-05,
|
| 704 |
+
"loss": 2.6346,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8,
|
| 709 |
+
"learning_rate": 1.0029938073300433e-05,
|
| 710 |
+
"loss": 2.6163,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.81,
|
| 715 |
+
"learning_rate": 9.688179245669916e-06,
|
| 716 |
+
"loss": 2.629,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.81,
|
| 721 |
+
"learning_rate": 9.346420418039398e-06,
|
| 722 |
+
"loss": 2.6725,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.82,
|
| 727 |
+
"learning_rate": 9.00466159040888e-06,
|
| 728 |
+
"loss": 2.6297,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.83,
|
| 733 |
+
"learning_rate": 8.662902762778363e-06,
|
| 734 |
+
"loss": 2.6274,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.83,
|
| 739 |
+
"learning_rate": 8.321143935147847e-06,
|
| 740 |
+
"loss": 2.6258,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.84,
|
| 745 |
+
"learning_rate": 7.979385107517327e-06,
|
| 746 |
+
"loss": 2.6075,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.85,
|
| 751 |
+
"learning_rate": 7.63762627988681e-06,
|
| 752 |
+
"loss": 2.5569,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.85,
|
| 757 |
+
"learning_rate": 7.296550969911553e-06,
|
| 758 |
+
"loss": 2.606,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.86,
|
| 763 |
+
"learning_rate": 6.954792142281036e-06,
|
| 764 |
+
"loss": 2.6188,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.87,
|
| 769 |
+
"learning_rate": 6.6130333146505175e-06,
|
| 770 |
+
"loss": 2.6118,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.87,
|
| 775 |
+
"learning_rate": 6.27127448702e-06,
|
| 776 |
+
"loss": 2.5898,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.88,
|
| 781 |
+
"learning_rate": 5.929515659389482e-06,
|
| 782 |
+
"loss": 2.6512,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.89,
|
| 787 |
+
"learning_rate": 5.588440349414226e-06,
|
| 788 |
+
"loss": 2.552,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.9,
|
| 793 |
+
"learning_rate": 5.247365039438969e-06,
|
| 794 |
+
"loss": 2.5514,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.9,
|
| 799 |
+
"learning_rate": 4.905606211808451e-06,
|
| 800 |
+
"loss": 2.5717,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.91,
|
| 805 |
+
"learning_rate": 4.563847384177934e-06,
|
| 806 |
+
"loss": 2.5928,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.92,
|
| 811 |
+
"learning_rate": 4.2220885565474156e-06,
|
| 812 |
+
"loss": 2.6304,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.92,
|
| 817 |
+
"learning_rate": 3.880329728916898e-06,
|
| 818 |
+
"loss": 2.6121,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.93,
|
| 823 |
+
"learning_rate": 3.539254418941641e-06,
|
| 824 |
+
"loss": 2.495,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.94,
|
| 829 |
+
"learning_rate": 3.197495591311124e-06,
|
| 830 |
+
"loss": 2.5219,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.94,
|
| 835 |
+
"learning_rate": 2.855736763680606e-06,
|
| 836 |
+
"loss": 2.6132,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.95,
|
| 841 |
+
"learning_rate": 2.513977936050088e-06,
|
| 842 |
+
"loss": 2.6146,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.96,
|
| 847 |
+
"learning_rate": 2.1722191084195706e-06,
|
| 848 |
+
"loss": 2.5907,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.96,
|
| 853 |
+
"learning_rate": 1.830460280789053e-06,
|
| 854 |
+
"loss": 2.4962,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.97,
|
| 859 |
+
"learning_rate": 1.4887014531585353e-06,
|
| 860 |
+
"loss": 2.6012,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.98,
|
| 865 |
+
"learning_rate": 1.1469426255280174e-06,
|
| 866 |
+
"loss": 2.5367,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.98,
|
| 871 |
+
"learning_rate": 8.051837978974998e-07,
|
| 872 |
+
"loss": 2.6087,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.99,
|
| 877 |
+
"learning_rate": 4.641084879222431e-07,
|
| 878 |
+
"loss": 2.5672,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.0,
|
| 883 |
+
"learning_rate": 1.2234966029172534e-07,
|
| 884 |
+
"loss": 2.5733,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0,
|
| 889 |
+
"step": 73151,
|
| 890 |
+
"total_flos": 1.2183202602103603e+17,
|
| 891 |
+
"train_loss": 3.037818258402621,
|
| 892 |
+
"train_runtime": 6822.2882,
|
| 893 |
+
"train_samples_per_second": 10.722,
|
| 894 |
+
"train_steps_per_second": 10.722
|
| 895 |
+
}
|
| 896 |
+
],
|
| 897 |
+
"logging_steps": 500,
|
| 898 |
+
"max_steps": 73151,
|
| 899 |
+
"num_train_epochs": 1,
|
| 900 |
+
"save_steps": -73151,
|
| 901 |
+
"total_flos": 1.2183202602103603e+17,
|
| 902 |
+
"trial_name": null,
|
| 903 |
+
"trial_params": null
|
| 904 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b43d023a9c73d1792b2e3a4b1273544202b7a47d2a78b1eb1e8ccb21ef29dbee
|
| 3 |
+
size 4027
|