init model step3_opt-6.7b_actor_lr_9.65e-6_critic_lr_5e-6
Browse files- actor/config.json +32 -0
- actor/merges.txt +0 -0
- actor/pytorch_model.bin +3 -0
- actor/vocab.json +0 -0
- critic/config.json +32 -0
- critic/merges.txt +0 -0
- critic/pytorch_model.bin +3 -0
- critic/vocab.json +0 -0
- training.log +0 -0
actor/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "training/step1_supervised_finetuning/output/",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": true,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"end_token_id": 2,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"ffn_dim": 16384,
|
| 17 |
+
"hidden_size": 4096,
|
| 18 |
+
"init_std": 0.02,
|
| 19 |
+
"layer_norm_elementwise_affine": true,
|
| 20 |
+
"layerdrop": 0.0,
|
| 21 |
+
"max_position_embeddings": 2048,
|
| 22 |
+
"model_type": "opt",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 32,
|
| 25 |
+
"pad_token_id": 2,
|
| 26 |
+
"prefix": "</s>",
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.29.0.dev0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50272,
|
| 31 |
+
"word_embed_proj_dim": 4096
|
| 32 |
+
}
|
actor/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
actor/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3963619194adb878736a9cd993ee2ad0014053556a8c41c2a1d0db3f4f44bfe
|
| 3 |
+
size 13317120121
|
actor/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
critic/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../step2_reward_model_finetuning/output/",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": false,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"end_token_id": 2,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"ffn_dim": 4096,
|
| 17 |
+
"hidden_size": 1024,
|
| 18 |
+
"init_std": 0.02,
|
| 19 |
+
"layer_norm_elementwise_affine": true,
|
| 20 |
+
"layerdrop": 0.0,
|
| 21 |
+
"max_position_embeddings": 2048,
|
| 22 |
+
"model_type": "opt",
|
| 23 |
+
"num_attention_heads": 16,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"pad_token_id": 2,
|
| 26 |
+
"prefix": "</s>",
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.29.0.dev0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50272,
|
| 31 |
+
"word_embed_proj_dim": 512
|
| 32 |
+
}
|
critic/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
critic/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de3344115e79cdb104a161a9cbaac5c4ea880dc1428ab534e338624cf31032a7
|
| 3 |
+
size 662523681
|
critic/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|