Model save
Browse files- README.md +67 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- runs/May27_21-34-18_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716845862.ip-172-31-69-60.ec2.internal.23523.0 +3 -0
- runs/May27_21-50-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846661.ip-172-31-69-60.ec2.internal.12422.0 +3 -0
- runs/May27_21-51-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846718.ip-172-31-69-60.ec2.internal.14769.0 +3 -0
- runs/May27_21-52-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846780.ip-172-31-69-60.ec2.internal.17185.0 +3 -0
- runs/May27_21-53-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846816.ip-172-31-69-60.ec2.internal.18768.0 +3 -0
- runs/May27_21-54-02_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846854.ip-172-31-69-60.ec2.internal.20423.0 +3 -0
- runs/May27_21-54-40_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846892.ip-172-31-69-60.ec2.internal.22058.0 +3 -0
- runs/May27_21-57-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847084.ip-172-31-69-60.ec2.internal.28976.0 +3 -0
- runs/May27_21-58-59_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847151.ip-172-31-69-60.ec2.internal.31493.0 +3 -0
- runs/May27_22-08-59_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847751.ip-172-31-69-60.ec2.internal.4939.0 +3 -0
- runs/May27_22-11-24_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847896.ip-172-31-69-60.ec2.internal.9970.0 +3 -0
- runs/May27_22-14-02_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848053.ip-172-31-69-60.ec2.internal.14045.0 +3 -0
- runs/May27_22-15-16_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848128.ip-172-31-69-60.ec2.internal.16064.0 +3 -0
- runs/May27_22-17-27_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848272.ip-172-31-69-60.ec2.internal.19273.0 +3 -0
- runs/May27_22-19-18_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848375.ip-172-31-69-60.ec2.internal.21785.0 +3 -0
- runs/May27_22-20-22_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848439.ip-172-31-69-60.ec2.internal.23944.0 +3 -0
- runs/May27_22-22-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848542.ip-172-31-69-60.ec2.internal.26567.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- train_results.json +9 -0
- trainer_state.json +393 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: mistral5p
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# mistral5p
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: nan
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 128
|
48 |
+
- total_eval_batch_size: 4
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: cosine
|
51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
52 |
+
- num_epochs: 1
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 0.7092 | 0.9969 | 243 | nan |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- PEFT 0.11.1
|
64 |
+
- Transformers 4.41.1
|
65 |
+
- Pytorch 2.2.2+cu121
|
66 |
+
- Datasets 2.19.1
|
67 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 6,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe90f2f98208e74edd203b571c5549da46239bd0283d4b96ce66fefe4c7662e
|
3 |
+
size 31516744
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9969230769230769,
|
3 |
+
"total_flos": 5623477606285312.0,
|
4 |
+
"train_loss": 0.7391852758548878,
|
5 |
+
"train_runtime": 18302.1626,
|
6 |
+
"train_samples": 31180,
|
7 |
+
"train_samples_per_second": 1.704,
|
8 |
+
"train_steps_per_second": 0.013
|
9 |
+
}
|
runs/May27_21-34-18_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716845862.ip-172-31-69-60.ec2.internal.23523.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9aada4a7ded10c996b91d89d1038c9d6afa059db9a60396875228bd2cadc4bf
|
3 |
+
size 5572
|
runs/May27_21-50-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846661.ip-172-31-69-60.ec2.internal.12422.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:685a46cf146655868a9c7c816a1407092b7ae9e7c2d2463e7fe76988dc6d1815
|
3 |
+
size 5986
|
runs/May27_21-51-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846718.ip-172-31-69-60.ec2.internal.14769.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5c235543a273abfab4a0dd02f710aaa75cd4bffa34fe4427025257619af23b3
|
3 |
+
size 5572
|
runs/May27_21-52-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846780.ip-172-31-69-60.ec2.internal.17185.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5678cbb9bc0e044dd777bd532c4e6b0a35d047e1189643add443beb71f2bbdd8
|
3 |
+
size 5572
|
runs/May27_21-53-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846816.ip-172-31-69-60.ec2.internal.18768.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a56fdc42bc86ce1f9f4d2292c12ef556b5c654b28455e31522da1ea1a7ceed2
|
3 |
+
size 5572
|
runs/May27_21-54-02_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846854.ip-172-31-69-60.ec2.internal.20423.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c0ecd45778978ae693e63ae10a1380c32936acd8df595cdfefdd5895a5ceb4
|
3 |
+
size 5779
|
runs/May27_21-54-40_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716846892.ip-172-31-69-60.ec2.internal.22058.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efbc29668edf80f66fd2c9fdfad8efa18909e53179d79558f9094213f7733a78
|
3 |
+
size 5779
|
runs/May27_21-57-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847084.ip-172-31-69-60.ec2.internal.28976.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed62cd56c05e39c6220bfed90bb4586299ec6b228ca01858819f1ef85fd7d2c0
|
3 |
+
size 5986
|
runs/May27_21-58-59_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847151.ip-172-31-69-60.ec2.internal.31493.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7de6497d021dba6f9e1ddca9db4b3ba92c61d71071f538c0051d7d1b50fcf6d7
|
3 |
+
size 5572
|
runs/May27_22-08-59_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847751.ip-172-31-69-60.ec2.internal.4939.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a46949ec2aa63756c8035a9ca6d575538cfd03ce8aa14c353de0bca24e331a
|
3 |
+
size 5572
|
runs/May27_22-11-24_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716847896.ip-172-31-69-60.ec2.internal.9970.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd6e6b08da14c3893e6e1e49c80610339befd2d5b85901abfa7171171d4416ed
|
3 |
+
size 5572
|
runs/May27_22-14-02_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848053.ip-172-31-69-60.ec2.internal.14045.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34842942951fc88c3f4b4bb08a82d2ef804f410ddb067136dc4aad95b65576e1
|
3 |
+
size 5986
|
runs/May27_22-15-16_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848128.ip-172-31-69-60.ec2.internal.16064.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbadc2f17fe22a11779d81ea25a4a4e71b7eba34a3b7c215c76db59308d23e7c
|
3 |
+
size 5572
|
runs/May27_22-17-27_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848272.ip-172-31-69-60.ec2.internal.19273.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:685d65721234f727b412b2430e4b97639e452c958e8eb1b626ca60da6fc9ac51
|
3 |
+
size 5986
|
runs/May27_22-19-18_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848375.ip-172-31-69-60.ec2.internal.21785.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c4a080c09bd356ea0915e82e47e65a430773626cde4730374120b415ed7f27b
|
3 |
+
size 5297
|
runs/May27_22-20-22_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848439.ip-172-31-69-60.ec2.internal.23944.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ca769519f176451f3c8064f5d5c1e25154c69c9563dd89806e9cde06356b871
|
3 |
+
size 5297
|
runs/May27_22-22-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1716848542.ip-172-31-69-60.ec2.internal.26567.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aabc977d6457a22fd50b73f0d67dfef24963b94f6c128b9d9f0ccd5e437ce377
|
3 |
+
size 15950
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"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 %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
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 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9969230769230769,
|
3 |
+
"total_flos": 5623477606285312.0,
|
4 |
+
"train_loss": 0.7391852758548878,
|
5 |
+
"train_runtime": 18302.1626,
|
6 |
+
"train_samples": 31180,
|
7 |
+
"train_samples_per_second": 1.704,
|
8 |
+
"train_steps_per_second": 0.013
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,393 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9969230769230769,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 243,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0041025641025641026,
|
13 |
+
"grad_norm": 0.26542961092188894,
|
14 |
+
"learning_rate": 8.000000000000001e-06,
|
15 |
+
"loss": 0.8534,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.020512820512820513,
|
20 |
+
"grad_norm": 0.2656899378598073,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 0.8667,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.041025641025641026,
|
27 |
+
"grad_norm": 0.2572181527992512,
|
28 |
+
"learning_rate": 8e-05,
|
29 |
+
"loss": 0.8031,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06153846153846154,
|
34 |
+
"grad_norm": 0.18710816410634198,
|
35 |
+
"learning_rate": 0.00012,
|
36 |
+
"loss": 0.7552,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.08205128205128205,
|
41 |
+
"grad_norm": 0.17366628242950644,
|
42 |
+
"learning_rate": 0.00016,
|
43 |
+
"loss": 0.7434,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.10256410256410256,
|
48 |
+
"grad_norm": 0.18209587440813843,
|
49 |
+
"learning_rate": 0.0002,
|
50 |
+
"loss": 0.7613,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12307692307692308,
|
55 |
+
"grad_norm": 0.17584855523843826,
|
56 |
+
"learning_rate": 0.00019974051702905277,
|
57 |
+
"loss": 0.7686,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.14358974358974358,
|
62 |
+
"grad_norm": 0.1876526868957483,
|
63 |
+
"learning_rate": 0.00019896341474445525,
|
64 |
+
"loss": 0.7408,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.1641025641025641,
|
69 |
+
"grad_norm": 0.14962305137903897,
|
70 |
+
"learning_rate": 0.00019767272604239824,
|
71 |
+
"loss": 0.7422,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.18461538461538463,
|
76 |
+
"grad_norm": 0.16336671883236106,
|
77 |
+
"learning_rate": 0.00019587514915766124,
|
78 |
+
"loss": 0.7565,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.20512820512820512,
|
83 |
+
"grad_norm": 0.15152018240587575,
|
84 |
+
"learning_rate": 0.00019358001290205543,
|
85 |
+
"loss": 0.7493,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.22564102564102564,
|
90 |
+
"grad_norm": 0.14810534949892065,
|
91 |
+
"learning_rate": 0.0001907992282510675,
|
92 |
+
"loss": 0.7539,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.24615384615384617,
|
97 |
+
"grad_norm": 0.16847734140964582,
|
98 |
+
"learning_rate": 0.00018754722652995347,
|
99 |
+
"loss": 0.7395,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.26666666666666666,
|
104 |
+
"grad_norm": 0.15436628692835286,
|
105 |
+
"learning_rate": 0.00018384088452007578,
|
106 |
+
"loss": 0.747,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.28717948717948716,
|
111 |
+
"grad_norm": 0.15652291403007046,
|
112 |
+
"learning_rate": 0.00017969943687415576,
|
113 |
+
"loss": 0.7506,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3076923076923077,
|
118 |
+
"grad_norm": 0.16413347022113,
|
119 |
+
"learning_rate": 0.0001751443762949772,
|
120 |
+
"loss": 0.7611,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3282051282051282,
|
125 |
+
"grad_norm": 0.16182771329972745,
|
126 |
+
"learning_rate": 0.00017019934199557867,
|
127 |
+
"loss": 0.7576,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.3487179487179487,
|
132 |
+
"grad_norm": 0.137569364566755,
|
133 |
+
"learning_rate": 0.00016488999701978903,
|
134 |
+
"loss": 0.7451,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.36923076923076925,
|
139 |
+
"grad_norm": 0.14900540538806303,
|
140 |
+
"learning_rate": 0.00015924389505977038,
|
141 |
+
"loss": 0.7197,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.38974358974358975,
|
146 |
+
"grad_norm": 0.14655990407738764,
|
147 |
+
"learning_rate": 0.00015329033746173975,
|
148 |
+
"loss": 0.7149,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.41025641025641024,
|
153 |
+
"grad_norm": 0.1402768270199422,
|
154 |
+
"learning_rate": 0.00014706022116196208,
|
155 |
+
"loss": 0.7018,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.4307692307692308,
|
160 |
+
"grad_norm": 0.14134928021057855,
|
161 |
+
"learning_rate": 0.00014058587834217355,
|
162 |
+
"loss": 0.7324,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.4512820512820513,
|
167 |
+
"grad_norm": 0.15600188868890955,
|
168 |
+
"learning_rate": 0.00013390090863657047,
|
169 |
+
"loss": 0.748,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.4717948717948718,
|
174 |
+
"grad_norm": 0.13996117144988574,
|
175 |
+
"learning_rate": 0.0001270400047611508,
|
176 |
+
"loss": 0.7703,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.49230769230769234,
|
181 |
+
"grad_norm": 0.1510982087519504,
|
182 |
+
"learning_rate": 0.00012003877247033411,
|
183 |
+
"loss": 0.7515,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5128205128205128,
|
188 |
+
"grad_norm": 0.14250885612041378,
|
189 |
+
"learning_rate": 0.00011293354577522263,
|
190 |
+
"loss": 0.7196,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.5333333333333333,
|
195 |
+
"grad_norm": 0.14795873562666287,
|
196 |
+
"learning_rate": 0.00010576119838245844,
|
197 |
+
"loss": 0.731,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.5538461538461539,
|
202 |
+
"grad_norm": 0.13063022182064904,
|
203 |
+
"learning_rate": 9.85589523322443e-05,
|
204 |
+
"loss": 0.7301,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.5743589743589743,
|
209 |
+
"grad_norm": 0.13557487318693218,
|
210 |
+
"learning_rate": 9.136418482863229e-05,
|
211 |
+
"loss": 0.718,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.5948717948717949,
|
216 |
+
"grad_norm": 0.15507641481392034,
|
217 |
+
"learning_rate": 8.42142342645646e-05,
|
218 |
+
"loss": 0.7193,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.6153846153846154,
|
223 |
+
"grad_norm": 0.15494002592225475,
|
224 |
+
"learning_rate": 7.714620644833111e-05,
|
225 |
+
"loss": 0.731,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.6358974358974359,
|
230 |
+
"grad_norm": 0.1601203804358568,
|
231 |
+
"learning_rate": 7.019678203706163e-05,
|
232 |
+
"loss": 0.75,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.6564102564102564,
|
237 |
+
"grad_norm": 0.15685275896075176,
|
238 |
+
"learning_rate": 6.340202617660842e-05,
|
239 |
+
"loss": 0.7505,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.676923076923077,
|
244 |
+
"grad_norm": 0.1416704035001306,
|
245 |
+
"learning_rate": 5.679720133572206e-05,
|
246 |
+
"loss": 0.7311,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.6974358974358974,
|
251 |
+
"grad_norm": 0.14126335283382643,
|
252 |
+
"learning_rate": 5.0416584305848524e-05,
|
253 |
+
"loss": 0.755,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.717948717948718,
|
258 |
+
"grad_norm": 0.13481365291511518,
|
259 |
+
"learning_rate": 4.4293288316255653e-05,
|
260 |
+
"loss": 0.695,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.7384615384615385,
|
265 |
+
"grad_norm": 0.14785228000969083,
|
266 |
+
"learning_rate": 3.845909118765073e-05,
|
267 |
+
"loss": 0.7209,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.7589743589743589,
|
272 |
+
"grad_norm": 0.1503268472656009,
|
273 |
+
"learning_rate": 3.294427041611425e-05,
|
274 |
+
"loss": 0.7307,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.7794871794871795,
|
279 |
+
"grad_norm": 0.15299701883959732,
|
280 |
+
"learning_rate": 2.7777446043207058e-05,
|
281 |
+
"loss": 0.7351,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.8,
|
286 |
+
"grad_norm": 0.1373494159366909,
|
287 |
+
"learning_rate": 2.2985432127701946e-05,
|
288 |
+
"loss": 0.7304,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.8205128205128205,
|
293 |
+
"grad_norm": 0.16245499908137687,
|
294 |
+
"learning_rate": 1.859309758975132e-05,
|
295 |
+
"loss": 0.7385,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.841025641025641,
|
300 |
+
"grad_norm": 0.13807085431435603,
|
301 |
+
"learning_rate": 1.462323714966114e-05,
|
302 |
+
"loss": 0.714,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8615384615384616,
|
307 |
+
"grad_norm": 0.12926916684005163,
|
308 |
+
"learning_rate": 1.1096453031056264e-05,
|
309 |
+
"loss": 0.7078,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.882051282051282,
|
314 |
+
"grad_norm": 0.12918592796308734,
|
315 |
+
"learning_rate": 8.031048042356392e-06,
|
316 |
+
"loss": 0.7208,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.9025641025641026,
|
321 |
+
"grad_norm": 0.14837431396022016,
|
322 |
+
"learning_rate": 5.442930591433992e-06,
|
323 |
+
"loss": 0.7435,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.9230769230769231,
|
328 |
+
"grad_norm": 0.14838485907528307,
|
329 |
+
"learning_rate": 3.3455321263955786e-06,
|
330 |
+
"loss": 0.7255,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.9435897435897436,
|
335 |
+
"grad_norm": 0.1480931290003826,
|
336 |
+
"learning_rate": 1.7497374309405346e-06,
|
337 |
+
"loss": 0.695,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.9641025641025641,
|
342 |
+
"grad_norm": 0.14733343614150893,
|
343 |
+
"learning_rate": 6.638281360408339e-07,
|
344 |
+
"loss": 0.7012,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.9846153846153847,
|
349 |
+
"grad_norm": 0.1368626907349573,
|
350 |
+
"learning_rate": 9.343974109685682e-08,
|
351 |
+
"loss": 0.7092,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.9969230769230769,
|
356 |
+
"eval_loss": NaN,
|
357 |
+
"eval_runtime": 748.4122,
|
358 |
+
"eval_samples_per_second": 1.545,
|
359 |
+
"eval_steps_per_second": 0.386,
|
360 |
+
"step": 243
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.9969230769230769,
|
364 |
+
"step": 243,
|
365 |
+
"total_flos": 5623477606285312.0,
|
366 |
+
"train_loss": 0.7391852758548878,
|
367 |
+
"train_runtime": 18302.1626,
|
368 |
+
"train_samples_per_second": 1.704,
|
369 |
+
"train_steps_per_second": 0.013
|
370 |
+
}
|
371 |
+
],
|
372 |
+
"logging_steps": 5,
|
373 |
+
"max_steps": 243,
|
374 |
+
"num_input_tokens_seen": 0,
|
375 |
+
"num_train_epochs": 1,
|
376 |
+
"save_steps": 1000,
|
377 |
+
"stateful_callbacks": {
|
378 |
+
"TrainerControl": {
|
379 |
+
"args": {
|
380 |
+
"should_epoch_stop": false,
|
381 |
+
"should_evaluate": false,
|
382 |
+
"should_log": false,
|
383 |
+
"should_save": false,
|
384 |
+
"should_training_stop": false
|
385 |
+
},
|
386 |
+
"attributes": {}
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"total_flos": 5623477606285312.0,
|
390 |
+
"train_batch_size": 8,
|
391 |
+
"trial_name": null,
|
392 |
+
"trial_params": null
|
393 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92484e9a5c8df8e8c9f43c40230cc189f21535aa92db5a37bb10f16e93a8e979
|
3 |
+
size 6456
|