alnrg2arg commited on
Commit
1496c05
1 Parent(s): 79a62a9

Upload 12 files

Browse files
fused_tinyllama_v2/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.98,
3
+ "eval_loss": 2.0175254344940186,
4
+ "eval_runtime": 140.639,
5
+ "eval_samples_per_second": 4.309,
6
+ "eval_steps_per_second": 4.309,
7
+ "perplexity": 7.51969391615205,
8
+ "train_loss": 1.1158069036083837,
9
+ "train_runtime": 12559.8672,
10
+ "train_samples_per_second": 3.958,
11
+ "train_steps_per_second": 0.247
12
+ }
fused_tinyllama_v2/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.37.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
fused_tinyllama_v2/eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.98,
3
+ "eval_loss": 2.0175254344940186,
4
+ "eval_runtime": 140.639,
5
+ "eval_samples_per_second": 4.309,
6
+ "eval_steps_per_second": 4.309,
7
+ "perplexity": 7.51969391615205
8
+ }
fused_tinyllama_v2/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "max_length": 4096,
4
+ "temperature": 0.6,
5
+ "top_p": 0.9,
6
+ "transformers_version": "4.37.2"
7
+ }
fused_tinyllama_v2/metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"run_name": "/home/paperspace/FuseLLM/fused_tinyllama", "train_runtime": 12559.8672, "train_samples_per_second": 3.958, "train_steps_per_second": 0.247, "train_loss": 1.1158069036083837, "epoch": 9.98, "eval_loss": 2.0175254344940186, "eval_runtime": 140.639, "eval_samples_per_second": 4.309, "eval_steps_per_second": 4.309, "perplexity": 7.51969391615205}
fused_tinyllama_v2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d654499c0e50b13e0ee43fbc1f450110f2017ce67696b97b18f180fa00038cd0
3
+ size 2200119864
fused_tinyllama_v2/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
fused_tinyllama_v2/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
fused_tinyllama_v2/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
fused_tinyllama_v2/train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.98,
3
+ "train_loss": 1.1158069036083837,
4
+ "train_runtime": 12559.8672,
5
+ "train_samples_per_second": 3.958,
6
+ "train_steps_per_second": 0.247
7
+ }
fused_tinyllama_v2/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
fused_tinyllama_v2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e098966db9a4d0f7fc82090a7361a99b8acb37e151cf50962e6f7553dc688be2
3
+ size 8568