Commit
•
952d848
1
Parent(s):
8ab203b
upload model
Browse files- adapter_model/README.md +3 -0
- adapter_model/lora_default/adapter_config.json +25 -0
- adapter_model/lora_default/adapter_model.bin +3 -0
- config.json +9 -0
- pytorch_model.bin.index.json +0 -0
- reward_head +0 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
- trainer_state.json +560 -0
- training_args.bin +3 -0
adapter_model/README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
adapter_model/lora_default/adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "/nobackup/users/zfchen/zhiqings/llama/models/llama-2-70b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 16,
|
| 10 |
+
"lora_dropout": 0.0,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 64,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"down_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"o_proj",
|
| 19 |
+
"gate_proj",
|
| 20 |
+
"q_proj",
|
| 21 |
+
"up_proj",
|
| 22 |
+
"v_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
adapter_model/lora_default/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0583c23e9efcfdcf1a10d5c4e83541d709b93281bfef4958b612ffe7fd09e13b
|
| 3 |
+
size 1657155522
|
config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RewardModel"
|
| 4 |
+
],
|
| 5 |
+
"backbone_model_name_or_path": "/nobackup/users/zfchen/zhiqings/llama/models/llama-2-70b-hf",
|
| 6 |
+
"model_type": "reward_model",
|
| 7 |
+
"torch_dtype": "bfloat16",
|
| 8 |
+
"transformers_version": "4.32.0.dev0"
|
| 9 |
+
}
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
reward_head
ADDED
|
Binary file (34.3 kB). View file
|
|
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:514543d614edd2d7740c8f29b4af414ace6f7e6b8821c9bf1fdb04cdf0cc2e73
|
| 3 |
+
size 1064
|
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.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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1280,
|
| 20 |
+
"pad_token": null,
|
| 21 |
+
"padding_side": "left",
|
| 22 |
+
"sp_model_kwargs": {},
|
| 23 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 24 |
+
"truncation_side": "right",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,560 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5207485760781123,
|
| 5 |
+
"global_step": 320,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 7.894736842105263e-06,
|
| 13 |
+
"loss": 0.8762,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 19 |
+
"loss": 0.7783,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"learning_rate": 2.368421052631579e-05,
|
| 25 |
+
"loss": 0.7497,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"learning_rate": 2.9999790913463623e-05,
|
| 31 |
+
"loss": 0.6797,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.03,
|
| 36 |
+
"eval_accuracy": 0.6140000224113464,
|
| 37 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 38 |
+
"eval_loss": 0.6632643938064575,
|
| 39 |
+
"eval_runtime": 64.3151,
|
| 40 |
+
"eval_samples_per_second": 7.774,
|
| 41 |
+
"eval_steps_per_second": 0.249,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"learning_rate": 2.9992473496712718e-05,
|
| 47 |
+
"loss": 0.676,
|
| 48 |
+
"step": 25
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.05,
|
| 52 |
+
"learning_rate": 2.9974707581369814e-05,
|
| 53 |
+
"loss": 0.6647,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.06,
|
| 58 |
+
"learning_rate": 2.994650554879023e-05,
|
| 59 |
+
"loss": 0.6657,
|
| 60 |
+
"step": 35
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.07,
|
| 64 |
+
"learning_rate": 2.9907887053429107e-05,
|
| 65 |
+
"loss": 0.6742,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07,
|
| 70 |
+
"eval_accuracy": 0.6060000061988831,
|
| 71 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 72 |
+
"eval_loss": 0.6763938069343567,
|
| 73 |
+
"eval_runtime": 64.3111,
|
| 74 |
+
"eval_samples_per_second": 7.775,
|
| 75 |
+
"eval_steps_per_second": 0.249,
|
| 76 |
+
"step": 40
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"learning_rate": 2.985887900914388e-05,
|
| 81 |
+
"loss": 0.6677,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.08,
|
| 86 |
+
"learning_rate": 2.9799515570437597e-05,
|
| 87 |
+
"loss": 0.6838,
|
| 88 |
+
"step": 50
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.09,
|
| 92 |
+
"learning_rate": 2.972983810865608e-05,
|
| 93 |
+
"loss": 0.6872,
|
| 94 |
+
"step": 55
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1,
|
| 98 |
+
"learning_rate": 2.9649895183155556e-05,
|
| 99 |
+
"loss": 0.6794,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1,
|
| 104 |
+
"eval_accuracy": 0.5860000252723694,
|
| 105 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 106 |
+
"eval_loss": 0.6799845099449158,
|
| 107 |
+
"eval_runtime": 64.3206,
|
| 108 |
+
"eval_samples_per_second": 7.774,
|
| 109 |
+
"eval_steps_per_second": 0.249,
|
| 110 |
+
"step": 60
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11,
|
| 114 |
+
"learning_rate": 2.9559742507460873e-05,
|
| 115 |
+
"loss": 0.6693,
|
| 116 |
+
"step": 65
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11,
|
| 120 |
+
"learning_rate": 2.9459442910437798e-05,
|
| 121 |
+
"loss": 0.6751,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.12,
|
| 126 |
+
"learning_rate": 2.9349066292506613e-05,
|
| 127 |
+
"loss": 0.6702,
|
| 128 |
+
"step": 75
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.13,
|
| 132 |
+
"learning_rate": 2.9228689576927327e-05,
|
| 133 |
+
"loss": 0.6596,
|
| 134 |
+
"step": 80
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.13,
|
| 138 |
+
"eval_accuracy": 0.5879999995231628,
|
| 139 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 140 |
+
"eval_loss": 0.6791808009147644,
|
| 141 |
+
"eval_runtime": 64.2883,
|
| 142 |
+
"eval_samples_per_second": 7.777,
|
| 143 |
+
"eval_steps_per_second": 0.249,
|
| 144 |
+
"step": 80
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"learning_rate": 2.909839665619062e-05,
|
| 149 |
+
"loss": 0.6523,
|
| 150 |
+
"step": 85
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15,
|
| 154 |
+
"learning_rate": 2.8958278333551827e-05,
|
| 155 |
+
"loss": 0.668,
|
| 156 |
+
"step": 90
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15,
|
| 160 |
+
"learning_rate": 2.8808432259748648e-05,
|
| 161 |
+
"loss": 0.6351,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.16,
|
| 166 |
+
"learning_rate": 2.864896286494674e-05,
|
| 167 |
+
"loss": 0.6585,
|
| 168 |
+
"step": 100
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.16,
|
| 172 |
+
"eval_accuracy": 0.5820000171661377,
|
| 173 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 174 |
+
"eval_loss": 0.6792215704917908,
|
| 175 |
+
"eval_runtime": 64.2728,
|
| 176 |
+
"eval_samples_per_second": 7.779,
|
| 177 |
+
"eval_steps_per_second": 0.249,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"learning_rate": 2.8479981285960694e-05,
|
| 183 |
+
"loss": 0.697,
|
| 184 |
+
"step": 105
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.18,
|
| 188 |
+
"learning_rate": 2.830160528880093e-05,
|
| 189 |
+
"loss": 0.6539,
|
| 190 |
+
"step": 110
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19,
|
| 194 |
+
"learning_rate": 2.8113959186600674e-05,
|
| 195 |
+
"loss": 0.6727,
|
| 196 |
+
"step": 115
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.2,
|
| 200 |
+
"learning_rate": 2.7917173752980103e-05,
|
| 201 |
+
"loss": 0.6458,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.2,
|
| 206 |
+
"eval_accuracy": 0.5699999928474426,
|
| 207 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 208 |
+
"eval_loss": 0.6816621422767639,
|
| 209 |
+
"eval_runtime": 64.3027,
|
| 210 |
+
"eval_samples_per_second": 7.776,
|
| 211 |
+
"eval_steps_per_second": 0.249,
|
| 212 |
+
"step": 120
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"learning_rate": 2.77113861309081e-05,
|
| 217 |
+
"loss": 0.682,
|
| 218 |
+
"step": 125
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.21,
|
| 222 |
+
"learning_rate": 2.7496739737125063e-05,
|
| 223 |
+
"loss": 0.6664,
|
| 224 |
+
"step": 130
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.22,
|
| 228 |
+
"learning_rate": 2.7273384162193462e-05,
|
| 229 |
+
"loss": 0.6493,
|
| 230 |
+
"step": 135
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.23,
|
| 234 |
+
"learning_rate": 2.7041475066245742e-05,
|
| 235 |
+
"loss": 0.6585,
|
| 236 |
+
"step": 140
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.23,
|
| 240 |
+
"eval_accuracy": 0.5659999847412109,
|
| 241 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 242 |
+
"eval_loss": 0.679412841796875,
|
| 243 |
+
"eval_runtime": 64.3077,
|
| 244 |
+
"eval_samples_per_second": 7.775,
|
| 245 |
+
"eval_steps_per_second": 0.249,
|
| 246 |
+
"step": 140
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.24,
|
| 250 |
+
"learning_rate": 2.6801174070502248e-05,
|
| 251 |
+
"loss": 0.6326,
|
| 252 |
+
"step": 145
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.24,
|
| 256 |
+
"learning_rate": 2.6552648644634765e-05,
|
| 257 |
+
"loss": 0.6597,
|
| 258 |
+
"step": 150
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.25,
|
| 262 |
+
"learning_rate": 2.6296071990054167e-05,
|
| 263 |
+
"loss": 0.6495,
|
| 264 |
+
"step": 155
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.26,
|
| 268 |
+
"learning_rate": 2.603162291920356e-05,
|
| 269 |
+
"loss": 0.6953,
|
| 270 |
+
"step": 160
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.26,
|
| 274 |
+
"eval_accuracy": 0.5619999766349792,
|
| 275 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 276 |
+
"eval_loss": 0.6798678636550903,
|
| 277 |
+
"eval_runtime": 64.3074,
|
| 278 |
+
"eval_samples_per_second": 7.775,
|
| 279 |
+
"eval_steps_per_second": 0.249,
|
| 280 |
+
"step": 160
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.27,
|
| 284 |
+
"learning_rate": 2.575948573094098e-05,
|
| 285 |
+
"loss": 0.6436,
|
| 286 |
+
"step": 165
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.28,
|
| 290 |
+
"learning_rate": 2.5479850082098485e-05,
|
| 291 |
+
"loss": 0.6527,
|
| 292 |
+
"step": 170
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.28,
|
| 296 |
+
"learning_rate": 2.5192910855307295e-05,
|
| 297 |
+
"loss": 0.6434,
|
| 298 |
+
"step": 175
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.29,
|
| 302 |
+
"learning_rate": 2.4898868023180844e-05,
|
| 303 |
+
"loss": 0.6586,
|
| 304 |
+
"step": 180
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.29,
|
| 308 |
+
"eval_accuracy": 0.5879999995231628,
|
| 309 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 310 |
+
"eval_loss": 0.6790176033973694,
|
| 311 |
+
"eval_runtime": 64.3234,
|
| 312 |
+
"eval_samples_per_second": 7.773,
|
| 313 |
+
"eval_steps_per_second": 0.249,
|
| 314 |
+
"step": 180
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"learning_rate": 2.4597926508950648e-05,
|
| 319 |
+
"loss": 0.6444,
|
| 320 |
+
"step": 185
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.31,
|
| 324 |
+
"learning_rate": 2.429029604365198e-05,
|
| 325 |
+
"loss": 0.657,
|
| 326 |
+
"step": 190
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.32,
|
| 330 |
+
"learning_rate": 2.3976191019958896e-05,
|
| 331 |
+
"loss": 0.6346,
|
| 332 |
+
"step": 195
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.33,
|
| 336 |
+
"learning_rate": 2.3655830342770463e-05,
|
| 337 |
+
"loss": 0.669,
|
| 338 |
+
"step": 200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.33,
|
| 342 |
+
"eval_accuracy": 0.6119999885559082,
|
| 343 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 344 |
+
"eval_loss": 0.6743248105049133,
|
| 345 |
+
"eval_runtime": 64.2981,
|
| 346 |
+
"eval_samples_per_second": 7.776,
|
| 347 |
+
"eval_steps_per_second": 0.249,
|
| 348 |
+
"step": 200
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"learning_rate": 2.3329437276652424e-05,
|
| 353 |
+
"loss": 0.6295,
|
| 354 |
+
"step": 205
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.34,
|
| 358 |
+
"learning_rate": 2.299723929024046e-05,
|
| 359 |
+
"loss": 0.6244,
|
| 360 |
+
"step": 210
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.35,
|
| 364 |
+
"learning_rate": 2.2659467897713604e-05,
|
| 365 |
+
"loss": 0.6341,
|
| 366 |
+
"step": 215
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.36,
|
| 370 |
+
"learning_rate": 2.231635849744825e-05,
|
| 371 |
+
"loss": 0.6376,
|
| 372 |
+
"step": 220
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.36,
|
| 376 |
+
"eval_accuracy": 0.5839999914169312,
|
| 377 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 378 |
+
"eval_loss": 0.6735034584999084,
|
| 379 |
+
"eval_runtime": 64.3161,
|
| 380 |
+
"eval_samples_per_second": 7.774,
|
| 381 |
+
"eval_steps_per_second": 0.249,
|
| 382 |
+
"step": 220
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.37,
|
| 386 |
+
"learning_rate": 2.196815020796519e-05,
|
| 387 |
+
"loss": 0.6264,
|
| 388 |
+
"step": 225
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.37,
|
| 392 |
+
"learning_rate": 2.161508570128403e-05,
|
| 393 |
+
"loss": 0.6178,
|
| 394 |
+
"step": 230
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.38,
|
| 398 |
+
"learning_rate": 2.1257411033801125e-05,
|
| 399 |
+
"loss": 0.6578,
|
| 400 |
+
"step": 235
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.39,
|
| 404 |
+
"learning_rate": 2.0895375474808857e-05,
|
| 405 |
+
"loss": 0.6173,
|
| 406 |
+
"step": 240
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.39,
|
| 410 |
+
"eval_accuracy": 0.5740000009536743,
|
| 411 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 412 |
+
"eval_loss": 0.6771048903465271,
|
| 413 |
+
"eval_runtime": 64.3005,
|
| 414 |
+
"eval_samples_per_second": 7.776,
|
| 415 |
+
"eval_steps_per_second": 0.249,
|
| 416 |
+
"step": 240
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4,
|
| 420 |
+
"learning_rate": 2.052923133277581e-05,
|
| 421 |
+
"loss": 0.64,
|
| 422 |
+
"step": 245
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.41,
|
| 426 |
+
"learning_rate": 2.0159233779508923e-05,
|
| 427 |
+
"loss": 0.6173,
|
| 428 |
+
"step": 250
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.41,
|
| 432 |
+
"learning_rate": 1.9785640672320074e-05,
|
| 433 |
+
"loss": 0.6104,
|
| 434 |
+
"step": 255
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.42,
|
| 438 |
+
"learning_rate": 1.9408712374321155e-05,
|
| 439 |
+
"loss": 0.6295,
|
| 440 |
+
"step": 260
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.42,
|
| 444 |
+
"eval_accuracy": 0.5960000157356262,
|
| 445 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 446 |
+
"eval_loss": 0.6679331064224243,
|
| 447 |
+
"eval_runtime": 64.1981,
|
| 448 |
+
"eval_samples_per_second": 7.788,
|
| 449 |
+
"eval_steps_per_second": 0.249,
|
| 450 |
+
"step": 260
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.43,
|
| 454 |
+
"learning_rate": 1.9028711572972753e-05,
|
| 455 |
+
"loss": 0.6366,
|
| 456 |
+
"step": 265
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.44,
|
| 460 |
+
"learning_rate": 1.864590309701302e-05,
|
| 461 |
+
"loss": 0.6567,
|
| 462 |
+
"step": 270
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.45,
|
| 466 |
+
"learning_rate": 1.82605537318942e-05,
|
| 467 |
+
"loss": 0.6397,
|
| 468 |
+
"step": 275
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.46,
|
| 472 |
+
"learning_rate": 1.7872932033855518e-05,
|
| 473 |
+
"loss": 0.6311,
|
| 474 |
+
"step": 280
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.46,
|
| 478 |
+
"eval_accuracy": 0.6000000238418579,
|
| 479 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 480 |
+
"eval_loss": 0.6692066788673401,
|
| 481 |
+
"eval_runtime": 64.3111,
|
| 482 |
+
"eval_samples_per_second": 7.775,
|
| 483 |
+
"eval_steps_per_second": 0.249,
|
| 484 |
+
"step": 280
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"learning_rate": 1.748330814276195e-05,
|
| 489 |
+
"loss": 0.6361,
|
| 490 |
+
"step": 285
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.47,
|
| 494 |
+
"learning_rate": 1.7091953593839383e-05,
|
| 495 |
+
"loss": 0.6583,
|
| 496 |
+
"step": 290
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.48,
|
| 500 |
+
"learning_rate": 1.6699141128437286e-05,
|
| 501 |
+
"loss": 0.6321,
|
| 502 |
+
"step": 295
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.49,
|
| 506 |
+
"learning_rate": 1.630514450395084e-05,
|
| 507 |
+
"loss": 0.6294,
|
| 508 |
+
"step": 300
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.49,
|
| 512 |
+
"eval_accuracy": 0.5899999737739563,
|
| 513 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 514 |
+
"eval_loss": 0.6700637340545654,
|
| 515 |
+
"eval_runtime": 64.3279,
|
| 516 |
+
"eval_samples_per_second": 7.773,
|
| 517 |
+
"eval_steps_per_second": 0.249,
|
| 518 |
+
"step": 300
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.5,
|
| 522 |
+
"learning_rate": 1.591023830303493e-05,
|
| 523 |
+
"loss": 0.6479,
|
| 524 |
+
"step": 305
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.5,
|
| 528 |
+
"learning_rate": 1.5514697742243067e-05,
|
| 529 |
+
"loss": 0.6332,
|
| 530 |
+
"step": 310
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.51,
|
| 534 |
+
"learning_rate": 1.511879848022446e-05,
|
| 535 |
+
"loss": 0.6076,
|
| 536 |
+
"step": 315
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.52,
|
| 540 |
+
"learning_rate": 1.4722816425613054e-05,
|
| 541 |
+
"loss": 0.6526,
|
| 542 |
+
"step": 320
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.52,
|
| 546 |
+
"eval_accuracy": 0.6039999723434448,
|
| 547 |
+
"eval_label_positive_rate": 0.5199999809265137,
|
| 548 |
+
"eval_loss": 0.6673489212989807,
|
| 549 |
+
"eval_runtime": 64.2956,
|
| 550 |
+
"eval_samples_per_second": 7.777,
|
| 551 |
+
"eval_steps_per_second": 0.249,
|
| 552 |
+
"step": 320
|
| 553 |
+
}
|
| 554 |
+
],
|
| 555 |
+
"max_steps": 614,
|
| 556 |
+
"num_train_epochs": 1,
|
| 557 |
+
"total_flos": 1.1109883301467259e+19,
|
| 558 |
+
"trial_name": null,
|
| 559 |
+
"trial_params": null
|
| 560 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c71e003b1acf444953c390829ee3507d57ff37700408bc50ea1b80f5759aa734
|
| 3 |
+
size 5112
|