Training in progress, epoch 0
Browse files- config.json +29 -0
- model.safetensors +3 -0
- runs/May18_03-12-34_5bdbdb63e3e1/events.out.tfevents.1716001978.5bdbdb63e3e1 +3 -0
- runs/May18_03-14-35_5bdbdb63e3e1/events.out.tfevents.1716002089.5bdbdb63e3e1 +3 -0
- runs/May18_03-17-14_5bdbdb63e3e1/events.out.tfevents.1716002237.5bdbdb63e3e1 +3 -0
- runs/May18_03-18-22_5bdbdb63e3e1/events.out.tfevents.1716002305.5bdbdb63e3e1 +3 -0
- runs/May18_03-18-58_5bdbdb63e3e1/events.out.tfevents.1716002341.5bdbdb63e3e1 +3 -0
- runs/May18_03-22-41_5bdbdb63e3e1/events.out.tfevents.1716002563.5bdbdb63e3e1 +3 -0
- special_tokens_map.json +4 -4
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +8 -21
- training_args.bin +2 -2
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 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 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.41.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8302a4d5191359f41c99f9515dc0602f7c33de1e84eeff0e889f8773c09a8f85
|
| 3 |
+
size 4400216536
|
runs/May18_03-12-34_5bdbdb63e3e1/events.out.tfevents.1716001978.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4e03ecbfeb81c518cc796821d8f6de3a5b77b6b460b3eadbff3a157dd46f528
|
| 3 |
+
size 4874
|
runs/May18_03-14-35_5bdbdb63e3e1/events.out.tfevents.1716002089.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ea0a0adfc85fe1d763ba20ef42745cd871bcb9d1c183a73bdf46f25ea6417d9
|
| 3 |
+
size 7569
|
runs/May18_03-17-14_5bdbdb63e3e1/events.out.tfevents.1716002237.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a890b4d1db9124168770a997fd0320d61fdffa2e9d25fcaf076f19f80ecc09
|
| 3 |
+
size 4874
|
runs/May18_03-18-22_5bdbdb63e3e1/events.out.tfevents.1716002305.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef84319a8ae6c89f8d4b7c0e1d226203487d361bf75f9c8f2367ffbf3155ea3c
|
| 3 |
+
size 4874
|
runs/May18_03-18-58_5bdbdb63e3e1/events.out.tfevents.1716002341.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18ebf569c2e6a52b26bcd2aa7579262058fc3699313d1c9236d5662410b3050a
|
| 3 |
+
size 5495
|
runs/May18_03-22-41_5bdbdb63e3e1/events.out.tfevents.1716002563.5bdbdb63e3e1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c1cafc6d3708174972100f9bbb95b04085aa0afd6dc127bb1ae1e1799228a8
|
| 3 |
+
size 6530
|
special_tokens_map.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
-
"content": "<
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
| 20 |
-
"normalized":
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
}
|
|
|
|
| 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,
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -1,34 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
-
"normalized":
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
-
"content": "<
|
| 16 |
"lstrip": false,
|
| 17 |
-
"normalized":
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
"2": {
|
| 23 |
-
"content": "<
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": true,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"7": {
|
| 31 |
-
"content": "<|im_end|>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
|
@@ -36,17 +27,13 @@
|
|
| 36 |
"special": true
|
| 37 |
}
|
| 38 |
},
|
| 39 |
-
"bos_token": "<
|
| 40 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
|
| 41 |
"clean_up_tokenization_spaces": false,
|
| 42 |
-
"eos_token": "<
|
| 43 |
-
"
|
| 44 |
-
"model_max_length": 4096,
|
| 45 |
"pad_token": "<unk>",
|
| 46 |
"padding_side": "right",
|
| 47 |
"sp_model_kwargs": {},
|
| 48 |
-
"spaces_between_special_tokens": false,
|
| 49 |
-
"split_special_tokens": false,
|
| 50 |
"tokenizer_class": "LlamaTokenizer",
|
| 51 |
"unk_token": "<unk>",
|
| 52 |
"use_default_system_prompt": false
|
|
|
|
| 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,
|
|
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"bos_token": "<s>",
|
|
|
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 34 |
"pad_token": "<unk>",
|
| 35 |
"padding_side": "right",
|
| 36 |
"sp_model_kwargs": {},
|
|
|
|
|
|
|
| 37 |
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
"unk_token": "<unk>",
|
| 39 |
"use_default_system_prompt": false
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a8911b55a6ed0b268745b7ff2fe64834c3823ba1f85fefb35c916d6528fb65c
|
| 3 |
+
size 5112
|