Add HuggingFaceH4/mistral-7b-ift-v11.0 checkpoint
Browse files- README.md +63 -0
- added_tokens.json +5 -0
- all_results.json +14 -0
- config.json +25 -0
- dialogue_template.json +30 -0
- eval_results.json +9 -0
- generation_config.json +6 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- runs/Oct20_10-10-24_ip-26-0-147-245/events.out.tfevents.1697796872.ip-26-0-147-245.2400625.0 +3 -0
- runs/Oct20_10-10-24_ip-26-0-147-245/events.out.tfevents.1697803248.ip-26-0-147-245.2400625.1 +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_state.json +366 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: mistral-7b-ift-v11.0
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# mistral-7b-ift-v11.0
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_uncensored_truecase_i_dont dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9399
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 16
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 512
|
45 |
+
- total_eval_batch_size: 256
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.9367 | 0.67 | 272 | 0.9397 |
|
56 |
+
|
57 |
+
|
58 |
+
### Framework versions
|
59 |
+
|
60 |
+
- Transformers 4.35.0.dev0
|
61 |
+
- Pytorch 2.0.1+cu118
|
62 |
+
- Datasets 2.12.0
|
63 |
+
- Tokenizers 0.14.0
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.67,
|
3 |
+
"eval_loss": 0.9398621916770935,
|
4 |
+
"eval_runtime": 183.2326,
|
5 |
+
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 126.124,
|
7 |
+
"eval_steps_per_second": 0.497,
|
8 |
+
"perplexity": 2.559628655890698,
|
9 |
+
"train_loss": 0.9917194036876454,
|
10 |
+
"train_runtime": 6192.0322,
|
11 |
+
"train_samples": 207865,
|
12 |
+
"train_samples_per_second": 33.57,
|
13 |
+
"train_steps_per_second": 0.066
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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 |
+
"rms_norm_eps": 1e-05,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 4096,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "bfloat16",
|
22 |
+
"transformers_version": "4.35.0.dev0",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 32000
|
25 |
+
}
|
dialogue_template.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"system": "",
|
3 |
+
"name": "default_v3",
|
4 |
+
"messages": [
|
5 |
+
{
|
6 |
+
"content": "When Texans think about defensive driving, they think DefensiveDriving.com. We have been a market leader providing quality defensive driving course online products since 2000. Texans rely on us to provide an online defensive driving course. Whether in the big cities of Houston, Dallas, San Antonio, the triangle of East Texas or the West Texas canyons, Texans across the state have come to trust us to provide high quality service for defensive driving.\nWith its 24 hour, 365 days a year service and its professional staff, our defensive driving course is educational, convenient and contemporary with DefensiveDriving.com. It is really the only way to take defensive driving course online for ticket dismissal or insurance reduction. Here, it is literally Texans serving Texans. Our staff is in Texas, not a foreign country. They are from Texas and all of our servers providing defensive driving course online are in Texas. Texas was one of the first states to approve defensive driving for ticket dismissal and we were one of the first to offer a defensive driving course online in a non-classroom setting.\nDefensiveDriving.com thinks the convenience, the service and the quality of our online defensive driving course should make the decision to choose us for your defensive driving course. It is easy, so sign up today, Got a Ticket, Just Click It!\nCan you provide information about DefensiveDriving.com's online defensive driving course and why Texans prefer it?",
|
7 |
+
"role": "user"
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"content": "DefensiveDriving.com has been a market leader in providing quality online defensive driving course products to Texans since the year 2000. The company offers a convenient and contemporary course that can be accessed 24 hours a day, 365 days a year. The course is recognized by the state of Texas and can be taken for ticket dismissal or insurance reduction purposes. Texans prefer DefensiveDriving.com because of its professional staff, high-quality service, and educational content. The company is dedicated to serving Texans and all of its servers are located within the state. DefensiveDriving.com was one of the first companies to offer a defensive driving course online in a non-classroom setting, making it highly accessible and convenient. Overall, DefensiveDriving.com's online defensive driving course is the ideal option for anyone seeking a hassle-free, efficient, and effective way to complete a defensive driving course.",
|
11 |
+
"role": "assistant"
|
12 |
+
},
|
13 |
+
{
|
14 |
+
"content": "Can you tell me more about the benefits of taking DefensiveDriving.com's online defensive driving course compared to taking it in a classroom setting?",
|
15 |
+
"role": "user"
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "I do not have any personal experience with taking driving courses; however, I can provide information on the benefits of taking defensivedriving.com's online defensive driving course compared to taking it in a classroom.\n\none of the primary benefits of taking the course online with defensivedriving.com is convenience. The course is entirely online and can be completed at any time and from any location, enabling you to work around a busy schedule or fulfill court-mandated requirements from the comfort of your own home.\n\nanother benefit is the flexibility offered by an online course. Students can learn at their own pace rather than being tied to a set schedule in a classroom setting.\n\nonline courses also offer a more engaging and interactive learning experience. The course content is delivered through a variety of mediums, including videos, animations, and interactive exercises, which can make for a more engaging and enjoyable learning experience.\n\nfinally, defensivedriving.com's online course is cost-effective. Students can avoid the costs associated with travel, parking and time off from work by completing the course from home. \n\noverall, taking defensivedriving.com's online defensive driving course has many benefits for those seeking a convenient, flexible, and affordable way to complete the course.",
|
19 |
+
"role": "assistant"
|
20 |
+
}
|
21 |
+
],
|
22 |
+
"system_token": "<|system|>",
|
23 |
+
"system_format": "standard",
|
24 |
+
"user_token": "<|user|>",
|
25 |
+
"assistant_token": "<|assistant|>",
|
26 |
+
"end_token": "</s>",
|
27 |
+
"mid_str": "\n",
|
28 |
+
"end_str": "\n",
|
29 |
+
"extra_end_text": "\n"
|
30 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.67,
|
3 |
+
"eval_loss": 0.9398621916770935,
|
4 |
+
"eval_runtime": 183.2326,
|
5 |
+
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 126.124,
|
7 |
+
"eval_steps_per_second": 0.497,
|
8 |
+
"perplexity": 2.559628655890698
|
9 |
+
}
|
generation_config.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.dev0"
|
6 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dac4fcf38c3bb7cf70ce95365c95044f46a3051330776ff1c7a9085e84f7cf5
|
3 |
+
size 9942981696
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe824bc51c088b671e855db56949868d9390af6d8859044d5359268cdaa8b9d
|
3 |
+
size 4540516344
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b98b2b8458d591606e0dcf05013cf71e55b888e719b5506d1a5a286d256c652
|
3 |
+
size 9943028044
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fd43973d3cc02a4de208e593b8c81ac137367a012c471b21fbfb1a3981dc7ba
|
3 |
+
size 4540535647
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
296 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
297 |
+
}
|
298 |
+
}
|
runs/Oct20_10-10-24_ip-26-0-147-245/events.out.tfevents.1697796872.ip-26-0-147-245.2400625.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a14d0220ddc8b157ce07c37127485d98d2965dcd6adb90e929fe6b70f626c483
|
3 |
+
size 13648
|
runs/Oct20_10-10-24_ip-26-0-147-245/events.out.tfevents.1697803248.ip-26-0-147-245.2400625.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ea755c95c45f01011178573107e7f1efd1226ed4a629f57cd63272f1b9e9c58
|
3 |
+
size 359
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "</s>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [
|
29 |
+
"<unk>",
|
30 |
+
"<s>",
|
31 |
+
"</s>"
|
32 |
+
],
|
33 |
+
"bos_token": "<s>",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 1000000000000000019884624838656,
|
38 |
+
"pad_token": "</s>",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true
|
44 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.67,
|
3 |
+
"train_loss": 0.9917194036876454,
|
4 |
+
"train_runtime": 6192.0322,
|
5 |
+
"train_samples": 207865,
|
6 |
+
"train_samples_per_second": 33.57,
|
7 |
+
"train_steps_per_second": 0.066
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6699507389162561,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 272,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.878048780487805e-07,
|
14 |
+
"loss": 1.6931,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 2.4390243902439027e-06,
|
20 |
+
"loss": 1.5849,
|
21 |
+
"step": 5
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 4.8780487804878055e-06,
|
26 |
+
"loss": 1.2774,
|
27 |
+
"step": 10
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.04,
|
31 |
+
"learning_rate": 7.317073170731707e-06,
|
32 |
+
"loss": 1.1546,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.05,
|
37 |
+
"learning_rate": 9.756097560975611e-06,
|
38 |
+
"loss": 1.1132,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.06,
|
43 |
+
"learning_rate": 1.2195121951219513e-05,
|
44 |
+
"loss": 1.0589,
|
45 |
+
"step": 25
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.07,
|
49 |
+
"learning_rate": 1.4634146341463415e-05,
|
50 |
+
"loss": 1.0348,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.09,
|
55 |
+
"learning_rate": 1.7073170731707317e-05,
|
56 |
+
"loss": 1.0263,
|
57 |
+
"step": 35
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.1,
|
61 |
+
"learning_rate": 1.9512195121951222e-05,
|
62 |
+
"loss": 1.0087,
|
63 |
+
"step": 40
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.11,
|
67 |
+
"learning_rate": 1.999407400739705e-05,
|
68 |
+
"loss": 1.005,
|
69 |
+
"step": 45
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.12,
|
73 |
+
"learning_rate": 1.997001169925015e-05,
|
74 |
+
"loss": 1.0048,
|
75 |
+
"step": 50
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.14,
|
79 |
+
"learning_rate": 1.9927487224577402e-05,
|
80 |
+
"loss": 0.995,
|
81 |
+
"step": 55
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.15,
|
85 |
+
"learning_rate": 1.986657932891657e-05,
|
86 |
+
"loss": 0.9845,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.16,
|
91 |
+
"learning_rate": 1.9787400799669155e-05,
|
92 |
+
"loss": 0.9785,
|
93 |
+
"step": 65
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.17,
|
97 |
+
"learning_rate": 1.9690098257244063e-05,
|
98 |
+
"loss": 0.971,
|
99 |
+
"step": 70
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.18,
|
103 |
+
"learning_rate": 1.9574851883550395e-05,
|
104 |
+
"loss": 0.977,
|
105 |
+
"step": 75
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.2,
|
109 |
+
"learning_rate": 1.9441875088342e-05,
|
110 |
+
"loss": 0.9847,
|
111 |
+
"step": 80
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.21,
|
115 |
+
"learning_rate": 1.9291414114031744e-05,
|
116 |
+
"loss": 0.9813,
|
117 |
+
"step": 85
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.22,
|
121 |
+
"learning_rate": 1.9123747579707275e-05,
|
122 |
+
"loss": 0.9713,
|
123 |
+
"step": 90
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.23,
|
127 |
+
"learning_rate": 1.8939185965192572e-05,
|
128 |
+
"loss": 0.9603,
|
129 |
+
"step": 95
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.25,
|
133 |
+
"learning_rate": 1.873807103611081e-05,
|
134 |
+
"loss": 0.9732,
|
135 |
+
"step": 100
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.26,
|
139 |
+
"learning_rate": 1.8520775211013094e-05,
|
140 |
+
"loss": 0.9869,
|
141 |
+
"step": 105
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.27,
|
145 |
+
"learning_rate": 1.8287700871745036e-05,
|
146 |
+
"loss": 0.9652,
|
147 |
+
"step": 110
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.28,
|
151 |
+
"learning_rate": 1.8039279618328215e-05,
|
152 |
+
"loss": 0.9613,
|
153 |
+
"step": 115
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.3,
|
157 |
+
"learning_rate": 1.777597146973627e-05,
|
158 |
+
"loss": 0.9669,
|
159 |
+
"step": 120
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.31,
|
163 |
+
"learning_rate": 1.7498264012045686e-05,
|
164 |
+
"loss": 0.9639,
|
165 |
+
"step": 125
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.32,
|
169 |
+
"learning_rate": 1.720667149553861e-05,
|
170 |
+
"loss": 0.9713,
|
171 |
+
"step": 130
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.33,
|
175 |
+
"learning_rate": 1.690173388242972e-05,
|
176 |
+
"loss": 0.9718,
|
177 |
+
"step": 135
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.34,
|
181 |
+
"learning_rate": 1.658401584698049e-05,
|
182 |
+
"loss": 0.9569,
|
183 |
+
"step": 140
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.36,
|
187 |
+
"learning_rate": 1.6254105729852466e-05,
|
188 |
+
"loss": 0.9617,
|
189 |
+
"step": 145
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.37,
|
193 |
+
"learning_rate": 1.5912614448635784e-05,
|
194 |
+
"loss": 0.9583,
|
195 |
+
"step": 150
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.38,
|
199 |
+
"learning_rate": 1.5560174366570448e-05,
|
200 |
+
"loss": 0.9541,
|
201 |
+
"step": 155
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.39,
|
205 |
+
"learning_rate": 1.5197438121555159e-05,
|
206 |
+
"loss": 0.9433,
|
207 |
+
"step": 160
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.41,
|
211 |
+
"learning_rate": 1.4825077417612187e-05,
|
212 |
+
"loss": 0.9591,
|
213 |
+
"step": 165
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.42,
|
217 |
+
"learning_rate": 1.4443781781046135e-05,
|
218 |
+
"loss": 0.9594,
|
219 |
+
"step": 170
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.43,
|
223 |
+
"learning_rate": 1.4054257283599974e-05,
|
224 |
+
"loss": 0.9451,
|
225 |
+
"step": 175
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.44,
|
229 |
+
"learning_rate": 1.3657225234972695e-05,
|
230 |
+
"loss": 0.9511,
|
231 |
+
"step": 180
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.46,
|
235 |
+
"learning_rate": 1.3253420847119804e-05,
|
236 |
+
"loss": 0.9606,
|
237 |
+
"step": 185
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.47,
|
241 |
+
"learning_rate": 1.2843591872810039e-05,
|
242 |
+
"loss": 0.9541,
|
243 |
+
"step": 190
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.48,
|
247 |
+
"learning_rate": 1.2428497220959359e-05,
|
248 |
+
"loss": 0.9541,
|
249 |
+
"step": 195
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.49,
|
253 |
+
"learning_rate": 1.2008905551306356e-05,
|
254 |
+
"loss": 0.9446,
|
255 |
+
"step": 200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.5,
|
259 |
+
"learning_rate": 1.1585593851031346e-05,
|
260 |
+
"loss": 0.9484,
|
261 |
+
"step": 205
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.52,
|
265 |
+
"learning_rate": 1.1159345995955007e-05,
|
266 |
+
"loss": 0.9464,
|
267 |
+
"step": 210
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.53,
|
271 |
+
"learning_rate": 1.0730951298980776e-05,
|
272 |
+
"loss": 0.9569,
|
273 |
+
"step": 215
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.54,
|
277 |
+
"learning_rate": 1.0301203048469084e-05,
|
278 |
+
"loss": 0.9458,
|
279 |
+
"step": 220
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.55,
|
283 |
+
"learning_rate": 9.87089703924991e-06,
|
284 |
+
"loss": 0.9481,
|
285 |
+
"step": 225
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.57,
|
289 |
+
"learning_rate": 9.440830098993969e-06,
|
290 |
+
"loss": 0.946,
|
291 |
+
"step": 230
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.58,
|
295 |
+
"learning_rate": 9.011798612671286e-06,
|
296 |
+
"loss": 0.9427,
|
297 |
+
"step": 235
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.59,
|
301 |
+
"learning_rate": 8.58459704782957e-06,
|
302 |
+
"loss": 0.9489,
|
303 |
+
"step": 240
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.6,
|
307 |
+
"learning_rate": 8.1600164834232e-06,
|
308 |
+
"loss": 0.9512,
|
309 |
+
"step": 245
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.62,
|
313 |
+
"learning_rate": 7.738843144917119e-06,
|
314 |
+
"loss": 0.9372,
|
315 |
+
"step": 250
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.63,
|
319 |
+
"learning_rate": 7.321856948378259e-06,
|
320 |
+
"loss": 0.9308,
|
321 |
+
"step": 255
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.64,
|
325 |
+
"learning_rate": 6.909830056250527e-06,
|
326 |
+
"loss": 0.9455,
|
327 |
+
"step": 260
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.65,
|
331 |
+
"learning_rate": 6.503525447487717e-06,
|
332 |
+
"loss": 0.934,
|
333 |
+
"step": 265
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.67,
|
337 |
+
"learning_rate": 6.103695504692122e-06,
|
338 |
+
"loss": 0.9367,
|
339 |
+
"step": 270
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.67,
|
343 |
+
"eval_loss": 0.939697802066803,
|
344 |
+
"eval_runtime": 188.9428,
|
345 |
+
"eval_samples_per_second": 122.312,
|
346 |
+
"eval_steps_per_second": 0.482,
|
347 |
+
"step": 272
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.67,
|
351 |
+
"step": 272,
|
352 |
+
"total_flos": 455767165501440.0,
|
353 |
+
"train_loss": 0.9917194036876454,
|
354 |
+
"train_runtime": 6192.0322,
|
355 |
+
"train_samples_per_second": 33.57,
|
356 |
+
"train_steps_per_second": 0.066
|
357 |
+
}
|
358 |
+
],
|
359 |
+
"logging_steps": 5,
|
360 |
+
"max_steps": 406,
|
361 |
+
"num_train_epochs": 1,
|
362 |
+
"save_steps": 500,
|
363 |
+
"total_flos": 455767165501440.0,
|
364 |
+
"trial_name": null,
|
365 |
+
"trial_params": null
|
366 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08ae957c6b372f890ef3881b4b7ee28ad7441a0df43b4bfadea5eda3cf01bebc
|
3 |
+
size 5435
|