Upload task output 824aeb83-fa79-4111-970d-9c1dde0ce871
Browse files- config.json +33 -0
- generation_config.json +9 -0
- loss.txt +26 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
120,1.6611337661743164
|
| 2 |
+
140,1.6542129516601562
|
| 3 |
+
160,1.651502251625061
|
| 4 |
+
161,1.6513550281524658
|
| 5 |
+
180,1.682282567024231
|
| 6 |
+
200,1.6810812950134277
|
| 7 |
+
220,1.6784807443618774
|
| 8 |
+
240,1.680466890335083
|
| 9 |
+
260,1.6775115728378296
|
| 10 |
+
280,1.6715326309204102
|
| 11 |
+
300,1.6727244853973389
|
| 12 |
+
320,1.6700555086135864
|
| 13 |
+
322,1.670729160308838
|
| 14 |
+
340,1.8013241291046143
|
| 15 |
+
360,1.8005415201187134
|
| 16 |
+
380,1.8028724193572998
|
| 17 |
+
380,1.6513550281524658
|
| 18 |
+
380,1.6515198945999146
|
| 19 |
+
380,1.6460199356079102
|
| 20 |
+
380,1.6454099416732788
|
| 21 |
+
380,1.640388011932373
|
| 22 |
+
380,1.6403019428253174
|
| 23 |
+
380,1.6407389640808105
|
| 24 |
+
380,1.6412919759750366
|
| 25 |
+
best checkpoint at step 380 (eval_loss=1.6403019428253174)
|
| 26 |
+
final: soup(n=5/8) (dev_loss=1.640302)
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64a8ffcd25249b3931f60a8704c779a8a21cbc281aad7461d415717010186c2c
|
| 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 |
+
}
|