peterpeter8585
commited on
Commit
•
0b41dc0
1
Parent(s):
a78537a
Upload 5 files
Browse files- added_tokens.json +5 -0
- all_results.json +21 -0
- config (1).json +26 -0
- eval_results.json +16 -0
- generation_config (1).json +6 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -2.353081703186035,
|
4 |
+
"eval_logits/rejected": -2.308103084564209,
|
5 |
+
"eval_logps/chosen": -299.4560546875,
|
6 |
+
"eval_logps/rejected": -340.154052734375,
|
7 |
+
"eval_loss": 0.7496059536933899,
|
8 |
+
"eval_rewards/accuracies": 0.78125,
|
9 |
+
"eval_rewards/chosen": -4.522095203399658,
|
10 |
+
"eval_rewards/margins": 3.7963125705718994,
|
11 |
+
"eval_rewards/rejected": -8.318408012390137,
|
12 |
+
"eval_runtime": 48.0152,
|
13 |
+
"eval_samples": 1000,
|
14 |
+
"eval_samples_per_second": 20.827,
|
15 |
+
"eval_steps_per_second": 0.333,
|
16 |
+
"train_loss": 0.2172969928600547,
|
17 |
+
"train_runtime": 23865.9828,
|
18 |
+
"train_samples": 61966,
|
19 |
+
"train_samples_per_second": 7.789,
|
20 |
+
"train_steps_per_second": 0.243
|
21 |
+
}
|
config (1).json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
+
"pad_token_id": 2,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.35.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -2.353081703186035,
|
4 |
+
"eval_logits/rejected": -2.308103084564209,
|
5 |
+
"eval_logps/chosen": -299.4560546875,
|
6 |
+
"eval_logps/rejected": -340.154052734375,
|
7 |
+
"eval_loss": 0.7496059536933899,
|
8 |
+
"eval_rewards/accuracies": 0.78125,
|
9 |
+
"eval_rewards/chosen": -4.522095203399658,
|
10 |
+
"eval_rewards/margins": 3.7963125705718994,
|
11 |
+
"eval_rewards/rejected": -8.318408012390137,
|
12 |
+
"eval_runtime": 48.0152,
|
13 |
+
"eval_samples": 1000,
|
14 |
+
"eval_samples_per_second": 20.827,
|
15 |
+
"eval_steps_per_second": 0.333
|
16 |
+
}
|
generation_config (1).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": "4.35.0"
|
6 |
+
}
|