Model save
Browse files- README.md +67 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- generation_config.json +7 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +550 -0
- runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706596853.dsw-250-99c5474d8-m866l.2566213.0 +2 -2
- runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706677621.dsw-250-99c5474d8-m866l.2566213.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1274 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: 01-ai/Yi-34B-200K
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
model-index:
|
11 |
+
- name: zephyr-34b-sft-full_epoch1
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# zephyr-34b-sft-full_epoch1
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) on the generator dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.9533
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 8
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 128
|
49 |
+
- total_eval_batch_size: 64
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 1
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
59 |
+
| 0.9435 | 1.0 | 1026 | 0.9533 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.36.2
|
65 |
+
- Pytorch 2.1.2+cu121
|
66 |
+
- Datasets 2.14.6
|
67 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9532989859580994,
|
4 |
+
"eval_runtime": 1248.9995,
|
5 |
+
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 11.64,
|
7 |
+
"eval_steps_per_second": 0.183,
|
8 |
+
"train_loss": 0.9775699134226199,
|
9 |
+
"train_runtime": 79518.8807,
|
10 |
+
"train_samples": 207865,
|
11 |
+
"train_samples_per_second": 1.652,
|
12 |
+
"train_steps_per_second": 0.013
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 0.9532989859580994,
|
4 |
+
"eval_runtime": 1248.9995,
|
5 |
+
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 11.64,
|
7 |
+
"eval_steps_per_second": 0.183
|
8 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.2"
|
7 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0589c0b1e61d3985d0faaa54f6cdf54b58940eb5a46c14a050a506008da1c255
|
3 |
+
size 4793130760
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63fbaf612d5e3dcf45ae495a34809e65a47a8878db2dc634b6dd24dca7a3a779
|
3 |
+
size 4756459720
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e553676e05ff187256a5a465e56a434f471b5bb5c52ccbd27d23d0cb09708fcc
|
3 |
+
size 4991370136
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce8ee3000caf0c8382294788c462ffb891ca8204b3f3c890b0d67b54770ae9ea
|
3 |
+
size 4756459760
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6de96a9a26e013a0198a83b2ddcbc599473b0a807b3e16d8dca62a7ad697ee7a
|
3 |
+
size 4756459760
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1609a6fce4f2589f2ad267b653e7e7f3c9db322813cba94046fccfce2350e916
|
3 |
+
size 4991370160
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7dbbbfe41ba61cb50d6257c3567d4b916d5655f8dedaf1174844b63f2a8f128
|
3 |
+
size 4756459760
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b472b912669a5425d0ab73f910963692865d9da9b0a86bb3174a8b74a92d170a
|
3 |
+
size 4756459760
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ba66961bc4a9e2a3068b03ae8f83431af9c644f30162b6cd605aad46859b09
|
3 |
+
size 4991370160
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc925fd3258bb992ccccbfdb8af3dca22aa6b77fd8842bf5bcb53fe635b6eb7
|
3 |
+
size 4756459760
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd92e353b14a082bf35cb490e3959ddb92f1ca0ca85edb8567b030c25f01f652
|
3 |
+
size 4756459760
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:339a4a9c184dac0010a33ff29def318aa01e070d8f0c3cdaf9865bcb8f753e40
|
3 |
+
size 4991370160
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78d1ddc285ca4daa00cb60c90b1792d63db242e4a8efef01e1fa4b3c560d8837
|
3 |
+
size 4756459760
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f31ef69e8fe425fc93ebd6e14ddd988a34b204478fb594224c5dff156bc4dbb1
|
3 |
+
size 4756459760
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad18b3375459def589a78cb2a0372066ed83c6ea1839e2d1424328e5e44cad7
|
3 |
+
size 1211148856
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 68777834496
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00015-of-00015.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
242 |
+
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
251 |
+
"model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
260 |
+
"model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
269 |
+
"model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
278 |
+
"model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
287 |
+
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
296 |
+
"model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
305 |
+
"model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
314 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
323 |
+
"model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
324 |
+
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
325 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
326 |
+
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
327 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
328 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
329 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
330 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
331 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
332 |
+
"model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
333 |
+
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
334 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
335 |
+
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
336 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
337 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
338 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
339 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
340 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
341 |
+
"model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
342 |
+
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
343 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
344 |
+
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
345 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
346 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
347 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
348 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
349 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
350 |
+
"model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
351 |
+
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
352 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
353 |
+
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
354 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
355 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
356 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
357 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
358 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
359 |
+
"model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
361 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
362 |
+
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
364 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
365 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
366 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
367 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
368 |
+
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
369 |
+
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
370 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
371 |
+
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
372 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
374 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
377 |
+
"model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
378 |
+
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
379 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
380 |
+
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
381 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
382 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
383 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
384 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
385 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
386 |
+
"model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
387 |
+
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
388 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
389 |
+
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
390 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
391 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
392 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
393 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
394 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
395 |
+
"model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
396 |
+
"model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
397 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
398 |
+
"model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
399 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
400 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
401 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
402 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
403 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
404 |
+
"model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
405 |
+
"model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
406 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
407 |
+
"model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
408 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
409 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
410 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
411 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
412 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
413 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
414 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
415 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
416 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
417 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
418 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
419 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
420 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
421 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
422 |
+
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
423 |
+
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
424 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
425 |
+
"model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
426 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
427 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
428 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
429 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
430 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
431 |
+
"model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
432 |
+
"model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
433 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
434 |
+
"model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
435 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
436 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
437 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
438 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
439 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
440 |
+
"model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
441 |
+
"model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
442 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
443 |
+
"model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
444 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
445 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
446 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
447 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
448 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
449 |
+
"model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
450 |
+
"model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
451 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
452 |
+
"model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
453 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
454 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
455 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
456 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
457 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
458 |
+
"model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
459 |
+
"model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
460 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
461 |
+
"model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
462 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
463 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
464 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
465 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
466 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
467 |
+
"model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
468 |
+
"model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
469 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
470 |
+
"model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
471 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
472 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
473 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
474 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
475 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
476 |
+
"model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
477 |
+
"model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
478 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
479 |
+
"model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
480 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
481 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
482 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
483 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
484 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
485 |
+
"model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
486 |
+
"model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
487 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
488 |
+
"model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
489 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
490 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
491 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
492 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
493 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
494 |
+
"model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
495 |
+
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
496 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
497 |
+
"model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
498 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
499 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
500 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
501 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
502 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
503 |
+
"model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
504 |
+
"model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
505 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
506 |
+
"model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
507 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
508 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
509 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
510 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
511 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
512 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
513 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
514 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
515 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
516 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
517 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
518 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
519 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
520 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
521 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
522 |
+
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
523 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
524 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
525 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
526 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
527 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
528 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
529 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
530 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
531 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
532 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
533 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
534 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
535 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
536 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
537 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
538 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
539 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
540 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
541 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
542 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
543 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
544 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
545 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
546 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
547 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
548 |
+
"model.norm.weight": "model-00015-of-00015.safetensors"
|
549 |
+
}
|
550 |
+
}
|
runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706596853.dsw-250-99c5474d8-m866l.2566213.0
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 sha256:468ee9a01a4b1af94010c67a1fbd678c2c6b45cf9a0c7ca92f21464d2fedf80e
|
3 |
+
size 37420
|
runs/Jan30_06-28-20_dsw-250-99c5474d8-m866l/events.out.tfevents.1706677621.dsw-250-99c5474d8-m866l.2566213.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5d002847dc79960d2b53913ac3b8ea3f2829327465358b462de346082763b7d
|
3 |
+
size 359
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.9775699134226199,
|
4 |
+
"train_runtime": 79518.8807,
|
5 |
+
"train_samples": 207865,
|
6 |
+
"train_samples_per_second": 1.652,
|
7 |
+
"train_steps_per_second": 0.013
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9997563946406821,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1026,
|
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": 1.941747572815534e-07,
|
14 |
+
"loss": 1.527,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 9.70873786407767e-07,
|
20 |
+
"loss": 1.5166,
|
21 |
+
"step": 5
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 1.941747572815534e-06,
|
26 |
+
"loss": 1.3897,
|
27 |
+
"step": 10
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 2.912621359223301e-06,
|
32 |
+
"loss": 1.1756,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 3.883495145631068e-06,
|
38 |
+
"loss": 1.1025,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.854368932038836e-06,
|
44 |
+
"loss": 1.0531,
|
45 |
+
"step": 25
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.03,
|
49 |
+
"learning_rate": 5.825242718446602e-06,
|
50 |
+
"loss": 1.0663,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"learning_rate": 6.79611650485437e-06,
|
56 |
+
"loss": 1.0582,
|
57 |
+
"step": 35
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.04,
|
61 |
+
"learning_rate": 7.766990291262136e-06,
|
62 |
+
"loss": 1.0537,
|
63 |
+
"step": 40
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.04,
|
67 |
+
"learning_rate": 8.737864077669904e-06,
|
68 |
+
"loss": 1.042,
|
69 |
+
"step": 45
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.05,
|
73 |
+
"learning_rate": 9.708737864077671e-06,
|
74 |
+
"loss": 1.0136,
|
75 |
+
"step": 50
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.05,
|
79 |
+
"learning_rate": 1.0679611650485437e-05,
|
80 |
+
"loss": 1.0165,
|
81 |
+
"step": 55
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.06,
|
85 |
+
"learning_rate": 1.1650485436893204e-05,
|
86 |
+
"loss": 1.0045,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.06,
|
91 |
+
"learning_rate": 1.2621359223300974e-05,
|
92 |
+
"loss": 1.0122,
|
93 |
+
"step": 65
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"learning_rate": 1.359223300970874e-05,
|
98 |
+
"loss": 1.0107,
|
99 |
+
"step": 70
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.07,
|
103 |
+
"learning_rate": 1.4563106796116507e-05,
|
104 |
+
"loss": 1.01,
|
105 |
+
"step": 75
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.08,
|
109 |
+
"learning_rate": 1.5533980582524273e-05,
|
110 |
+
"loss": 1.0034,
|
111 |
+
"step": 80
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.08,
|
115 |
+
"learning_rate": 1.650485436893204e-05,
|
116 |
+
"loss": 0.9995,
|
117 |
+
"step": 85
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.09,
|
121 |
+
"learning_rate": 1.7475728155339808e-05,
|
122 |
+
"loss": 0.994,
|
123 |
+
"step": 90
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.09,
|
127 |
+
"learning_rate": 1.8446601941747575e-05,
|
128 |
+
"loss": 1.015,
|
129 |
+
"step": 95
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.1,
|
133 |
+
"learning_rate": 1.9417475728155343e-05,
|
134 |
+
"loss": 0.9897,
|
135 |
+
"step": 100
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.1,
|
139 |
+
"learning_rate": 1.999976830073192e-05,
|
140 |
+
"loss": 1.0033,
|
141 |
+
"step": 105
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.11,
|
145 |
+
"learning_rate": 1.99971618072711e-05,
|
146 |
+
"loss": 1.0027,
|
147 |
+
"step": 110
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.11,
|
151 |
+
"learning_rate": 1.9991659953668803e-05,
|
152 |
+
"loss": 0.9943,
|
153 |
+
"step": 115
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.12,
|
157 |
+
"learning_rate": 1.998326433336204e-05,
|
158 |
+
"loss": 1.0269,
|
159 |
+
"step": 120
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.12,
|
163 |
+
"learning_rate": 1.997197737787537e-05,
|
164 |
+
"loss": 0.9755,
|
165 |
+
"step": 125
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.13,
|
169 |
+
"learning_rate": 1.9957802356116665e-05,
|
170 |
+
"loss": 1.0,
|
171 |
+
"step": 130
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.13,
|
175 |
+
"learning_rate": 1.994074337343041e-05,
|
176 |
+
"loss": 0.9923,
|
177 |
+
"step": 135
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.14,
|
181 |
+
"learning_rate": 1.9920805370408695e-05,
|
182 |
+
"loss": 1.0044,
|
183 |
+
"step": 140
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.14,
|
187 |
+
"learning_rate": 1.9897994121460322e-05,
|
188 |
+
"loss": 0.9956,
|
189 |
+
"step": 145
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.15,
|
193 |
+
"learning_rate": 1.9872316233138463e-05,
|
194 |
+
"loss": 1.0046,
|
195 |
+
"step": 150
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.15,
|
199 |
+
"learning_rate": 1.9843779142227258e-05,
|
200 |
+
"loss": 0.9857,
|
201 |
+
"step": 155
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.16,
|
205 |
+
"learning_rate": 1.981239111358799e-05,
|
206 |
+
"loss": 1.0008,
|
207 |
+
"step": 160
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.16,
|
211 |
+
"learning_rate": 1.9778161237765438e-05,
|
212 |
+
"loss": 1.0068,
|
213 |
+
"step": 165
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.17,
|
217 |
+
"learning_rate": 1.9741099428355075e-05,
|
218 |
+
"loss": 1.0073,
|
219 |
+
"step": 170
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.17,
|
223 |
+
"learning_rate": 1.9701216419131934e-05,
|
224 |
+
"loss": 0.9601,
|
225 |
+
"step": 175
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.18,
|
229 |
+
"learning_rate": 1.9658523760941882e-05,
|
230 |
+
"loss": 1.0001,
|
231 |
+
"step": 180
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.18,
|
235 |
+
"learning_rate": 1.9613033818356322e-05,
|
236 |
+
"loss": 1.0086,
|
237 |
+
"step": 185
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.19,
|
241 |
+
"learning_rate": 1.956475976609114e-05,
|
242 |
+
"loss": 1.0117,
|
243 |
+
"step": 190
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.19,
|
247 |
+
"learning_rate": 1.951371558519111e-05,
|
248 |
+
"loss": 0.9955,
|
249 |
+
"step": 195
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.19,
|
253 |
+
"learning_rate": 1.9459916058980707e-05,
|
254 |
+
"loss": 1.0014,
|
255 |
+
"step": 200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.2,
|
259 |
+
"learning_rate": 1.9403376768782592e-05,
|
260 |
+
"loss": 0.9803,
|
261 |
+
"step": 205
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.2,
|
265 |
+
"learning_rate": 1.9344114089404983e-05,
|
266 |
+
"loss": 0.9847,
|
267 |
+
"step": 210
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.21,
|
271 |
+
"learning_rate": 1.9282145184399197e-05,
|
272 |
+
"loss": 0.9946,
|
273 |
+
"step": 215
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.21,
|
277 |
+
"learning_rate": 1.9217488001088784e-05,
|
278 |
+
"loss": 0.9886,
|
279 |
+
"step": 220
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.22,
|
283 |
+
"learning_rate": 1.9150161265371663e-05,
|
284 |
+
"loss": 0.981,
|
285 |
+
"step": 225
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.22,
|
289 |
+
"learning_rate": 1.908018447629674e-05,
|
290 |
+
"loss": 0.9863,
|
291 |
+
"step": 230
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.23,
|
295 |
+
"learning_rate": 1.9007577900416648e-05,
|
296 |
+
"loss": 0.9907,
|
297 |
+
"step": 235
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.23,
|
301 |
+
"learning_rate": 1.8932362565918167e-05,
|
302 |
+
"loss": 0.9721,
|
303 |
+
"step": 240
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.24,
|
307 |
+
"learning_rate": 1.8854560256532098e-05,
|
308 |
+
"loss": 1.0003,
|
309 |
+
"step": 245
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.24,
|
313 |
+
"learning_rate": 1.877419350522429e-05,
|
314 |
+
"loss": 0.9749,
|
315 |
+
"step": 250
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.25,
|
319 |
+
"learning_rate": 1.869128558766965e-05,
|
320 |
+
"loss": 0.9967,
|
321 |
+
"step": 255
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.25,
|
325 |
+
"learning_rate": 1.8605860515511158e-05,
|
326 |
+
"loss": 0.9864,
|
327 |
+
"step": 260
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.26,
|
331 |
+
"learning_rate": 1.8517943029405577e-05,
|
332 |
+
"loss": 1.0096,
|
333 |
+
"step": 265
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.26,
|
337 |
+
"learning_rate": 1.8427558591858164e-05,
|
338 |
+
"loss": 0.9643,
|
339 |
+
"step": 270
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.27,
|
343 |
+
"learning_rate": 1.833473337984823e-05,
|
344 |
+
"loss": 1.001,
|
345 |
+
"step": 275
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.27,
|
349 |
+
"learning_rate": 1.823949427724785e-05,
|
350 |
+
"loss": 0.996,
|
351 |
+
"step": 280
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.28,
|
355 |
+
"learning_rate": 1.8141868867035745e-05,
|
356 |
+
"loss": 0.9885,
|
357 |
+
"step": 285
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.28,
|
361 |
+
"learning_rate": 1.8041885423308808e-05,
|
362 |
+
"loss": 0.9818,
|
363 |
+
"step": 290
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.29,
|
367 |
+
"learning_rate": 1.7939572903093383e-05,
|
368 |
+
"loss": 0.9936,
|
369 |
+
"step": 295
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.29,
|
373 |
+
"learning_rate": 1.7834960937958775e-05,
|
374 |
+
"loss": 0.9733,
|
375 |
+
"step": 300
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.3,
|
379 |
+
"learning_rate": 1.7728079825435426e-05,
|
380 |
+
"loss": 1.0035,
|
381 |
+
"step": 305
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.3,
|
385 |
+
"learning_rate": 1.761896052024019e-05,
|
386 |
+
"loss": 1.0073,
|
387 |
+
"step": 310
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.31,
|
391 |
+
"learning_rate": 1.7507634625311283e-05,
|
392 |
+
"loss": 0.9821,
|
393 |
+
"step": 315
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.31,
|
397 |
+
"learning_rate": 1.7394134382655496e-05,
|
398 |
+
"loss": 0.99,
|
399 |
+
"step": 320
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.32,
|
403 |
+
"learning_rate": 1.7278492664010326e-05,
|
404 |
+
"loss": 0.9766,
|
405 |
+
"step": 325
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.32,
|
409 |
+
"learning_rate": 1.7160742961323714e-05,
|
410 |
+
"loss": 0.9783,
|
411 |
+
"step": 330
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.33,
|
415 |
+
"learning_rate": 1.7040919377054182e-05,
|
416 |
+
"loss": 0.9922,
|
417 |
+
"step": 335
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.33,
|
421 |
+
"learning_rate": 1.6919056614294133e-05,
|
422 |
+
"loss": 0.9767,
|
423 |
+
"step": 340
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.34,
|
427 |
+
"learning_rate": 1.6795189966719182e-05,
|
428 |
+
"loss": 0.9937,
|
429 |
+
"step": 345
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.34,
|
433 |
+
"learning_rate": 1.666935530836651e-05,
|
434 |
+
"loss": 0.9702,
|
435 |
+
"step": 350
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.35,
|
439 |
+
"learning_rate": 1.654158908324504e-05,
|
440 |
+
"loss": 0.9906,
|
441 |
+
"step": 355
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.35,
|
445 |
+
"learning_rate": 1.6411928294780626e-05,
|
446 |
+
"loss": 0.9662,
|
447 |
+
"step": 360
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.36,
|
451 |
+
"learning_rate": 1.6280410495099165e-05,
|
452 |
+
"loss": 0.9802,
|
453 |
+
"step": 365
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.36,
|
457 |
+
"learning_rate": 1.6147073774150834e-05,
|
458 |
+
"loss": 0.9897,
|
459 |
+
"step": 370
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.37,
|
463 |
+
"learning_rate": 1.601195674867853e-05,
|
464 |
+
"loss": 0.9696,
|
465 |
+
"step": 375
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.37,
|
469 |
+
"learning_rate": 1.5875098551033765e-05,
|
470 |
+
"loss": 0.9859,
|
471 |
+
"step": 380
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.38,
|
475 |
+
"learning_rate": 1.5736538817843228e-05,
|
476 |
+
"loss": 0.9751,
|
477 |
+
"step": 385
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.38,
|
481 |
+
"learning_rate": 1.559631767852929e-05,
|
482 |
+
"loss": 0.9815,
|
483 |
+
"step": 390
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.38,
|
487 |
+
"learning_rate": 1.54544757436878e-05,
|
488 |
+
"loss": 0.9913,
|
489 |
+
"step": 395
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.39,
|
493 |
+
"learning_rate": 1.5311054093326508e-05,
|
494 |
+
"loss": 0.9652,
|
495 |
+
"step": 400
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.39,
|
499 |
+
"learning_rate": 1.5166094264967553e-05,
|
500 |
+
"loss": 0.9831,
|
501 |
+
"step": 405
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.4,
|
505 |
+
"learning_rate": 1.5019638241617429e-05,
|
506 |
+
"loss": 0.9598,
|
507 |
+
"step": 410
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.4,
|
511 |
+
"learning_rate": 1.4871728439607967e-05,
|
512 |
+
"loss": 0.9667,
|
513 |
+
"step": 415
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.41,
|
517 |
+
"learning_rate": 1.472240769631176e-05,
|
518 |
+
"loss": 0.9764,
|
519 |
+
"step": 420
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.41,
|
523 |
+
"learning_rate": 1.4571719257735702e-05,
|
524 |
+
"loss": 0.9685,
|
525 |
+
"step": 425
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.42,
|
529 |
+
"learning_rate": 1.4419706765996153e-05,
|
530 |
+
"loss": 0.9872,
|
531 |
+
"step": 430
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.42,
|
535 |
+
"learning_rate": 1.4266414246679379e-05,
|
536 |
+
"loss": 0.9727,
|
537 |
+
"step": 435
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.43,
|
541 |
+
"learning_rate": 1.4111886096090953e-05,
|
542 |
+
"loss": 0.9532,
|
543 |
+
"step": 440
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.43,
|
547 |
+
"learning_rate": 1.3956167068397756e-05,
|
548 |
+
"loss": 0.9679,
|
549 |
+
"step": 445
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.44,
|
553 |
+
"learning_rate": 1.3799302262666388e-05,
|
554 |
+
"loss": 0.9779,
|
555 |
+
"step": 450
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.44,
|
559 |
+
"learning_rate": 1.364133710980162e-05,
|
560 |
+
"loss": 0.9906,
|
561 |
+
"step": 455
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.45,
|
565 |
+
"learning_rate": 1.3482317359388806e-05,
|
566 |
+
"loss": 0.9756,
|
567 |
+
"step": 460
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.45,
|
571 |
+
"learning_rate": 1.3322289066443947e-05,
|
572 |
+
"loss": 0.9799,
|
573 |
+
"step": 465
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.46,
|
577 |
+
"learning_rate": 1.316129857807534e-05,
|
578 |
+
"loss": 0.9677,
|
579 |
+
"step": 470
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.46,
|
583 |
+
"learning_rate": 1.2999392520060594e-05,
|
584 |
+
"loss": 0.9738,
|
585 |
+
"step": 475
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.47,
|
589 |
+
"learning_rate": 1.2836617783342968e-05,
|
590 |
+
"loss": 0.9939,
|
591 |
+
"step": 480
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.47,
|
595 |
+
"learning_rate": 1.2673021510450893e-05,
|
596 |
+
"loss": 0.9618,
|
597 |
+
"step": 485
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.48,
|
601 |
+
"learning_rate": 1.250865108184464e-05,
|
602 |
+
"loss": 0.9652,
|
603 |
+
"step": 490
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.48,
|
607 |
+
"learning_rate": 1.2343554102194073e-05,
|
608 |
+
"loss": 0.9915,
|
609 |
+
"step": 495
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.49,
|
613 |
+
"learning_rate": 1.2177778386591475e-05,
|
614 |
+
"loss": 0.9782,
|
615 |
+
"step": 500
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.49,
|
619 |
+
"learning_rate": 1.2011371946703416e-05,
|
620 |
+
"loss": 0.9918,
|
621 |
+
"step": 505
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.5,
|
625 |
+
"learning_rate": 1.1844382976865714e-05,
|
626 |
+
"loss": 0.9813,
|
627 |
+
"step": 510
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.5,
|
631 |
+
"learning_rate": 1.1676859840125468e-05,
|
632 |
+
"loss": 0.9877,
|
633 |
+
"step": 515
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.51,
|
637 |
+
"learning_rate": 1.1508851054234236e-05,
|
638 |
+
"loss": 0.9828,
|
639 |
+
"step": 520
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.51,
|
643 |
+
"learning_rate": 1.1340405277596427e-05,
|
644 |
+
"loss": 0.9661,
|
645 |
+
"step": 525
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.52,
|
649 |
+
"learning_rate": 1.1171571295176915e-05,
|
650 |
+
"loss": 0.9682,
|
651 |
+
"step": 530
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.52,
|
655 |
+
"learning_rate": 1.1002398004372048e-05,
|
656 |
+
"loss": 0.9666,
|
657 |
+
"step": 535
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.53,
|
661 |
+
"learning_rate": 1.0832934400848063e-05,
|
662 |
+
"loss": 0.9526,
|
663 |
+
"step": 540
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.53,
|
667 |
+
"learning_rate": 1.066322956435104e-05,
|
668 |
+
"loss": 0.9546,
|
669 |
+
"step": 545
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.54,
|
673 |
+
"learning_rate": 1.0493332644492534e-05,
|
674 |
+
"loss": 0.9561,
|
675 |
+
"step": 550
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.54,
|
679 |
+
"learning_rate": 1.0323292846514927e-05,
|
680 |
+
"loss": 0.9602,
|
681 |
+
"step": 555
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.55,
|
685 |
+
"learning_rate": 1.015315941704071e-05,
|
686 |
+
"loss": 0.9579,
|
687 |
+
"step": 560
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.55,
|
691 |
+
"learning_rate": 9.982981629809776e-06,
|
692 |
+
"loss": 0.959,
|
693 |
+
"step": 565
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.56,
|
697 |
+
"learning_rate": 9.812808771408804e-06,
|
698 |
+
"loss": 0.9512,
|
699 |
+
"step": 570
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.56,
|
703 |
+
"learning_rate": 9.64269012699702e-06,
|
704 |
+
"loss": 0.9554,
|
705 |
+
"step": 575
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.57,
|
709 |
+
"learning_rate": 9.472674966032276e-06,
|
710 |
+
"loss": 0.9724,
|
711 |
+
"step": 580
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.57,
|
715 |
+
"learning_rate": 9.302812528001741e-06,
|
716 |
+
"loss": 0.9691,
|
717 |
+
"step": 585
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.57,
|
721 |
+
"learning_rate": 9.133152008161235e-06,
|
722 |
+
"loss": 0.9676,
|
723 |
+
"step": 590
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.58,
|
727 |
+
"learning_rate": 8.963742543287397e-06,
|
728 |
+
"loss": 0.9603,
|
729 |
+
"step": 595
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.58,
|
733 |
+
"learning_rate": 8.79463319744677e-06,
|
734 |
+
"loss": 0.9526,
|
735 |
+
"step": 600
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.59,
|
739 |
+
"learning_rate": 8.625872947785968e-06,
|
740 |
+
"loss": 0.9561,
|
741 |
+
"step": 605
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.59,
|
745 |
+
"learning_rate": 8.457510670346976e-06,
|
746 |
+
"loss": 0.9543,
|
747 |
+
"step": 610
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.6,
|
751 |
+
"learning_rate": 8.2895951259118e-06,
|
752 |
+
"loss": 0.9663,
|
753 |
+
"step": 615
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.6,
|
757 |
+
"learning_rate": 8.122174945880409e-06,
|
758 |
+
"loss": 0.9763,
|
759 |
+
"step": 620
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.61,
|
763 |
+
"learning_rate": 7.955298618186227e-06,
|
764 |
+
"loss": 0.9621,
|
765 |
+
"step": 625
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.61,
|
769 |
+
"learning_rate": 7.78901447325314e-06,
|
770 |
+
"loss": 0.9487,
|
771 |
+
"step": 630
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.62,
|
775 |
+
"learning_rate": 7.623370669998115e-06,
|
776 |
+
"loss": 0.9383,
|
777 |
+
"step": 635
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.62,
|
781 |
+
"learning_rate": 7.458415181883506e-06,
|
782 |
+
"loss": 0.9694,
|
783 |
+
"step": 640
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.63,
|
787 |
+
"learning_rate": 7.294195783023072e-06,
|
788 |
+
"loss": 0.9491,
|
789 |
+
"step": 645
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.63,
|
793 |
+
"learning_rate": 7.130760034345708e-06,
|
794 |
+
"loss": 0.963,
|
795 |
+
"step": 650
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.64,
|
799 |
+
"learning_rate": 6.968155269820951e-06,
|
800 |
+
"loss": 0.9512,
|
801 |
+
"step": 655
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.64,
|
805 |
+
"learning_rate": 6.806428582750191e-06,
|
806 |
+
"loss": 0.9609,
|
807 |
+
"step": 660
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.65,
|
811 |
+
"learning_rate": 6.645626812127588e-06,
|
812 |
+
"loss": 0.9574,
|
813 |
+
"step": 665
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.65,
|
817 |
+
"learning_rate": 6.485796529074662e-06,
|
818 |
+
"loss": 0.9631,
|
819 |
+
"step": 670
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.66,
|
823 |
+
"learning_rate": 6.326984023352435e-06,
|
824 |
+
"loss": 0.9627,
|
825 |
+
"step": 675
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.66,
|
829 |
+
"learning_rate": 6.169235289955073e-06,
|
830 |
+
"loss": 0.9568,
|
831 |
+
"step": 680
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.67,
|
835 |
+
"learning_rate": 6.012596015788903e-06,
|
836 |
+
"loss": 0.9528,
|
837 |
+
"step": 685
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.67,
|
841 |
+
"learning_rate": 5.8571115664406655e-06,
|
842 |
+
"loss": 0.9639,
|
843 |
+
"step": 690
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.68,
|
847 |
+
"learning_rate": 5.702826973038776e-06,
|
848 |
+
"loss": 0.9609,
|
849 |
+
"step": 695
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.68,
|
853 |
+
"learning_rate": 5.549786919211532e-06,
|
854 |
+
"loss": 0.9379,
|
855 |
+
"step": 700
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.69,
|
859 |
+
"learning_rate": 5.3980357281459e-06,
|
860 |
+
"loss": 0.9382,
|
861 |
+
"step": 705
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.69,
|
865 |
+
"learning_rate": 5.247617349750717e-06,
|
866 |
+
"loss": 0.9388,
|
867 |
+
"step": 710
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.7,
|
871 |
+
"learning_rate": 5.0985753479279824e-06,
|
872 |
+
"loss": 0.9692,
|
873 |
+
"step": 715
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.7,
|
877 |
+
"learning_rate": 4.950952887955992e-06,
|
878 |
+
"loss": 0.9653,
|
879 |
+
"step": 720
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.71,
|
883 |
+
"learning_rate": 4.80479272398786e-06,
|
884 |
+
"loss": 0.9613,
|
885 |
+
"step": 725
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.71,
|
889 |
+
"learning_rate": 4.660137186669131e-06,
|
890 |
+
"loss": 0.943,
|
891 |
+
"step": 730
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.72,
|
895 |
+
"learning_rate": 4.5170281708780865e-06,
|
896 |
+
"loss": 0.9451,
|
897 |
+
"step": 735
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.72,
|
901 |
+
"learning_rate": 4.375507123592194e-06,
|
902 |
+
"loss": 0.951,
|
903 |
+
"step": 740
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.73,
|
907 |
+
"learning_rate": 4.235615031884326e-06,
|
908 |
+
"loss": 0.9433,
|
909 |
+
"step": 745
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.73,
|
913 |
+
"learning_rate": 4.097392411052149e-06,
|
914 |
+
"loss": 0.9385,
|
915 |
+
"step": 750
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.74,
|
919 |
+
"learning_rate": 3.9608792928841596e-06,
|
920 |
+
"loss": 0.9488,
|
921 |
+
"step": 755
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.74,
|
925 |
+
"learning_rate": 3.826115214065739e-06,
|
926 |
+
"loss": 0.9413,
|
927 |
+
"step": 760
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.75,
|
931 |
+
"learning_rate": 3.693139204728623e-06,
|
932 |
+
"loss": 0.9535,
|
933 |
+
"step": 765
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.75,
|
937 |
+
"learning_rate": 3.561989777147059e-06,
|
938 |
+
"loss": 0.9384,
|
939 |
+
"step": 770
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.76,
|
943 |
+
"learning_rate": 3.4327049145839496e-06,
|
944 |
+
"loss": 0.9451,
|
945 |
+
"step": 775
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.76,
|
949 |
+
"learning_rate": 3.3053220602902057e-06,
|
950 |
+
"loss": 0.9663,
|
951 |
+
"step": 780
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.76,
|
955 |
+
"learning_rate": 3.1798781066605076e-06,
|
956 |
+
"loss": 0.9551,
|
957 |
+
"step": 785
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.77,
|
961 |
+
"learning_rate": 3.056409384548575e-06,
|
962 |
+
"loss": 0.958,
|
963 |
+
"step": 790
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.77,
|
967 |
+
"learning_rate": 2.934951652745123e-06,
|
968 |
+
"loss": 0.949,
|
969 |
+
"step": 795
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.78,
|
973 |
+
"learning_rate": 2.8155400876214365e-06,
|
974 |
+
"loss": 0.9504,
|
975 |
+
"step": 800
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.78,
|
979 |
+
"learning_rate": 2.698209272941659e-06,
|
980 |
+
"loss": 0.9387,
|
981 |
+
"step": 805
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.79,
|
985 |
+
"learning_rate": 2.5829931898467143e-06,
|
986 |
+
"loss": 0.9194,
|
987 |
+
"step": 810
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.79,
|
991 |
+
"learning_rate": 2.469925207012741e-06,
|
992 |
+
"loss": 0.9436,
|
993 |
+
"step": 815
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.8,
|
997 |
+
"learning_rate": 2.3590380709869175e-06,
|
998 |
+
"loss": 0.9401,
|
999 |
+
"step": 820
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.8,
|
1003 |
+
"learning_rate": 2.2503638967034668e-06,
|
1004 |
+
"loss": 0.9462,
|
1005 |
+
"step": 825
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.81,
|
1009 |
+
"learning_rate": 2.1439341581825855e-06,
|
1010 |
+
"loss": 0.9553,
|
1011 |
+
"step": 830
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.81,
|
1015 |
+
"learning_rate": 2.039779679414996e-06,
|
1016 |
+
"loss": 0.9485,
|
1017 |
+
"step": 835
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.82,
|
1021 |
+
"learning_rate": 1.9379306254347487e-06,
|
1022 |
+
"loss": 0.9417,
|
1023 |
+
"step": 840
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.82,
|
1027 |
+
"learning_rate": 1.838416493582893e-06,
|
1028 |
+
"loss": 0.933,
|
1029 |
+
"step": 845
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.83,
|
1033 |
+
"learning_rate": 1.7412661049645097e-06,
|
1034 |
+
"loss": 0.9501,
|
1035 |
+
"step": 850
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.83,
|
1039 |
+
"learning_rate": 1.6465075961015697e-06,
|
1040 |
+
"loss": 0.9522,
|
1041 |
+
"step": 855
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.84,
|
1045 |
+
"learning_rate": 1.554168410784117e-06,
|
1046 |
+
"loss": 0.9434,
|
1047 |
+
"step": 860
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.84,
|
1051 |
+
"learning_rate": 1.4642752921220272e-06,
|
1052 |
+
"loss": 0.938,
|
1053 |
+
"step": 865
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.85,
|
1057 |
+
"learning_rate": 1.3768542747997215e-06,
|
1058 |
+
"loss": 0.943,
|
1059 |
+
"step": 870
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.85,
|
1063 |
+
"learning_rate": 1.2919306775360495e-06,
|
1064 |
+
"loss": 0.9551,
|
1065 |
+
"step": 875
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.86,
|
1069 |
+
"learning_rate": 1.209529095751527e-06,
|
1070 |
+
"loss": 0.9459,
|
1071 |
+
"step": 880
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.86,
|
1075 |
+
"learning_rate": 1.1296733944450445e-06,
|
1076 |
+
"loss": 0.9526,
|
1077 |
+
"step": 885
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.87,
|
1081 |
+
"learning_rate": 1.0523867012821444e-06,
|
1082 |
+
"loss": 0.963,
|
1083 |
+
"step": 890
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.87,
|
1087 |
+
"learning_rate": 9.776913998968196e-07,
|
1088 |
+
"loss": 0.9422,
|
1089 |
+
"step": 895
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.88,
|
1093 |
+
"learning_rate": 9.056091234088038e-07,
|
1094 |
+
"loss": 0.9408,
|
1095 |
+
"step": 900
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.88,
|
1099 |
+
"learning_rate": 8.361607481582312e-07,
|
1100 |
+
"loss": 0.9512,
|
1101 |
+
"step": 905
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.89,
|
1105 |
+
"learning_rate": 7.693663876594648e-07,
|
1106 |
+
"loss": 0.9401,
|
1107 |
+
"step": 910
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.89,
|
1111 |
+
"learning_rate": 7.052453867758525e-07,
|
1112 |
+
"loss": 0.9523,
|
1113 |
+
"step": 915
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.9,
|
1117 |
+
"learning_rate": 6.438163161171096e-07,
|
1118 |
+
"loss": 0.9332,
|
1119 |
+
"step": 920
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.9,
|
1123 |
+
"learning_rate": 5.850969666609363e-07,
|
1124 |
+
"loss": 0.9443,
|
1125 |
+
"step": 925
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.91,
|
1129 |
+
"learning_rate": 5.291043446004074e-07,
|
1130 |
+
"loss": 0.9423,
|
1131 |
+
"step": 930
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.91,
|
1135 |
+
"learning_rate": 4.7585466641868696e-07,
|
1136 |
+
"loss": 0.9509,
|
1137 |
+
"step": 935
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.92,
|
1141 |
+
"learning_rate": 4.25363354192434e-07,
|
1142 |
+
"loss": 0.9512,
|
1143 |
+
"step": 940
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.92,
|
1147 |
+
"learning_rate": 3.776450311252866e-07,
|
1148 |
+
"loss": 0.953,
|
1149 |
+
"step": 945
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.93,
|
1153 |
+
"learning_rate": 3.3271351731271717e-07,
|
1154 |
+
"loss": 0.9282,
|
1155 |
+
"step": 950
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.93,
|
1159 |
+
"learning_rate": 2.905818257394799e-07,
|
1160 |
+
"loss": 0.9639,
|
1161 |
+
"step": 955
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.94,
|
1165 |
+
"learning_rate": 2.512621585108155e-07,
|
1166 |
+
"loss": 0.9543,
|
1167 |
+
"step": 960
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.94,
|
1171 |
+
"learning_rate": 2.1476590331849566e-07,
|
1172 |
+
"loss": 0.956,
|
1173 |
+
"step": 965
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.95,
|
1177 |
+
"learning_rate": 1.811036301427449e-07,
|
1178 |
+
"loss": 0.9625,
|
1179 |
+
"step": 970
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.95,
|
1183 |
+
"learning_rate": 1.502850881909801e-07,
|
1184 |
+
"loss": 0.9435,
|
1185 |
+
"step": 975
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.95,
|
1189 |
+
"learning_rate": 1.2231920307425927e-07,
|
1190 |
+
"loss": 0.9538,
|
1191 |
+
"step": 980
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.96,
|
1195 |
+
"learning_rate": 9.721407422226492e-08,
|
1196 |
+
"loss": 0.9398,
|
1197 |
+
"step": 985
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.96,
|
1201 |
+
"learning_rate": 7.497697253756265e-08,
|
1202 |
+
"loss": 0.939,
|
1203 |
+
"step": 990
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.97,
|
1207 |
+
"learning_rate": 5.5614338289812216e-08,
|
1208 |
+
"loss": 0.9302,
|
1209 |
+
"step": 995
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.97,
|
1213 |
+
"learning_rate": 3.913177925055189e-08,
|
1214 |
+
"loss": 0.9574,
|
1215 |
+
"step": 1000
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.98,
|
1219 |
+
"learning_rate": 2.5534069069081957e-08,
|
1220 |
+
"loss": 0.9528,
|
1221 |
+
"step": 1005
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.98,
|
1225 |
+
"learning_rate": 1.482514588993067e-08,
|
1226 |
+
"loss": 0.9216,
|
1227 |
+
"step": 1010
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.99,
|
1231 |
+
"learning_rate": 7.0081112122966086e-09,
|
1232 |
+
"loss": 0.9417,
|
1233 |
+
"step": 1015
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.99,
|
1237 |
+
"learning_rate": 2.0852289917971947e-09,
|
1238 |
+
"loss": 0.9419,
|
1239 |
+
"step": 1020
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.0,
|
1243 |
+
"learning_rate": 5.792498478651709e-11,
|
1244 |
+
"loss": 0.9435,
|
1245 |
+
"step": 1025
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.0,
|
1249 |
+
"eval_loss": 0.9532989859580994,
|
1250 |
+
"eval_runtime": 1250.6177,
|
1251 |
+
"eval_samples_per_second": 11.625,
|
1252 |
+
"eval_steps_per_second": 0.182,
|
1253 |
+
"step": 1026
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 1.0,
|
1257 |
+
"step": 1026,
|
1258 |
+
"total_flos": 1399316853817344.0,
|
1259 |
+
"train_loss": 0.9775699134226199,
|
1260 |
+
"train_runtime": 79518.8807,
|
1261 |
+
"train_samples_per_second": 1.652,
|
1262 |
+
"train_steps_per_second": 0.013
|
1263 |
+
}
|
1264 |
+
],
|
1265 |
+
"logging_steps": 5,
|
1266 |
+
"max_steps": 1026,
|
1267 |
+
"num_input_tokens_seen": 0,
|
1268 |
+
"num_train_epochs": 1,
|
1269 |
+
"save_steps": 1000,
|
1270 |
+
"total_flos": 1399316853817344.0,
|
1271 |
+
"train_batch_size": 4,
|
1272 |
+
"trial_name": null,
|
1273 |
+
"trial_params": null
|
1274 |
+
}
|