Upload task output 5b55fc0b-3b71-4c5d-9c21-a5f58be146e7
Browse files- config.json +33 -0
- generation_config.json +9 -0
- loss.txt +27 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.12.1",
|
| 30 |
+
"unsloth_version": "2024.9",
|
| 31 |
+
"use_cache": false,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
2
|
| 5 |
+
],
|
| 6 |
+
"max_length": 2048,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "5.12.1"
|
| 9 |
+
}
|
loss.txt
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
120,2.127701759338379
|
| 2 |
+
140,2.0729238986968994
|
| 3 |
+
160,2.0694665908813477
|
| 4 |
+
161,2.067392110824585
|
| 5 |
+
180,2.04211163520813
|
| 6 |
+
200,2.0341851711273193
|
| 7 |
+
220,2.0332655906677246
|
| 8 |
+
240,2.025397300720215
|
| 9 |
+
260,2.0296905040740967
|
| 10 |
+
280,2.002760887145996
|
| 11 |
+
300,2.0155551433563232
|
| 12 |
+
320,1.9891506433486938
|
| 13 |
+
322,1.985929012298584
|
| 14 |
+
340,2.006737232208252
|
| 15 |
+
360,2.0082743167877197
|
| 16 |
+
380,1.999416708946228
|
| 17 |
+
400,2.000826835632324
|
| 18 |
+
420,1.9964790344238281
|
| 19 |
+
440,1.9919191598892212
|
| 20 |
+
460,1.9887672662734985
|
| 21 |
+
480,1.9840588569641113
|
| 22 |
+
483,1.9832314252853394
|
| 23 |
+
486,1.9820876121520996
|
| 24 |
+
486,1.9820876121520996
|
| 25 |
+
486,1.9825553894042969
|
| 26 |
+
best checkpoint at step 486 (eval_loss=1.9820876121520996)
|
| 27 |
+
final: soup(n=1/8) (dev_loss=1.982088)
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42609eefe5c3cb528b33e196ea5327dec4d7dc5b232d526b2617a7db2e69de45
|
| 3 |
+
size 2200119864
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<unk>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 14 |
+
"unk_token": "<unk>",
|
| 15 |
+
"use_default_system_prompt": false
|
| 16 |
+
}
|