Model save
Browse files- README.md +4 -3
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- all_results.json +8 -8
- config.json +26 -0
- eval_results.json +4 -4
- runs/Dec07_12-10-12_ip-172-16-110-193.ec2.internal/events.out.tfevents.1701951037.ip-172-16-110-193.ec2.internal.5300.0 +3 -0
- runs/Dec07_12-10-12_ip-172-16-110-193.ec2.internal/events.out.tfevents.1701957107.ip-172-16-110-193.ec2.internal.5300.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +25 -17
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -45,13 +45,14 @@ The following hyperparameters were used during training:
|
|
45 |
- total_eval_batch_size: 4
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
-
- num_epochs:
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 2.0382 | 0.5 | 1 | 1.
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.9786
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
45 |
- total_eval_batch_size: 4
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
+
- num_epochs: 3.0
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 2.0382 | 0.5 | 1 | 1.9826 |
|
55 |
+
| 2.0382 | 1.65 | 3 | 1.9786 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -16,10 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
-
"q_proj",
|
21 |
"k_proj",
|
22 |
-
"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
"v_proj",
|
|
|
21 |
"k_proj",
|
22 |
+
"q_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109086672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c4e020c4d08fc607533170d8afafaf3c335fd06e4e9156b397f69699f04d60f
|
3 |
size 109086672
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 660.
|
5 |
"eval_samples": 1086,
|
6 |
-
"eval_samples_per_second": 1.
|
7 |
"eval_steps_per_second": 0.412,
|
8 |
-
"train_loss": 2.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 2026,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.65,
|
3 |
+
"eval_loss": 1.9785882234573364,
|
4 |
+
"eval_runtime": 660.2678,
|
5 |
"eval_samples": 1086,
|
6 |
+
"eval_samples_per_second": 1.645,
|
7 |
"eval_steps_per_second": 0.412,
|
8 |
+
"train_loss": 2.036311705907186,
|
9 |
+
"train_runtime": 5409.4181,
|
10 |
"train_samples": 2026,
|
11 |
+
"train_samples_per_second": 1.124,
|
12 |
+
"train_steps_per_second": 0.001
|
13 |
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
+
"pad_token_id": 2,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.35.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 660.
|
5 |
"eval_samples": 1086,
|
6 |
-
"eval_samples_per_second": 1.
|
7 |
"eval_steps_per_second": 0.412
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.65,
|
3 |
+
"eval_loss": 1.9785882234573364,
|
4 |
+
"eval_runtime": 660.2678,
|
5 |
"eval_samples": 1086,
|
6 |
+
"eval_samples_per_second": 1.645,
|
7 |
"eval_steps_per_second": 0.412
|
8 |
}
|
runs/Dec07_12-10-12_ip-172-16-110-193.ec2.internal/events.out.tfevents.1701951037.ip-172-16-110-193.ec2.internal.5300.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a22926dc2e5f9cf757f1385c526eb6f7c5771243dd5d607a5bc7fdb0ffd548a2
|
3 |
+
size 5361
|
runs/Dec07_12-10-12_ip-172-16-110-193.ec2.internal/events.out.tfevents.1701957107.ip-172-16-110-193.ec2.internal.5300.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bbb22db19a2827141fecb4f6d38e76d95450f5089fc8656e0114da30665a129
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 2026,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.65,
|
3 |
+
"train_loss": 2.036311705907186,
|
4 |
+
"train_runtime": 5409.4181,
|
5 |
"train_samples": 2026,
|
6 |
+
"train_samples_per_second": 1.124,
|
7 |
+
"train_steps_per_second": 0.001
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,42 +1,50 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.5,
|
13 |
-
"learning_rate":
|
14 |
"loss": 2.0382,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.5,
|
19 |
-
"eval_loss": 1.
|
20 |
-
"eval_runtime":
|
21 |
-
"eval_samples_per_second": 1.
|
22 |
-
"eval_steps_per_second": 0.
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 5,
|
36 |
-
"max_steps":
|
37 |
-
"num_train_epochs":
|
38 |
"save_steps": 500,
|
39 |
-
"total_flos":
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
42 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.650887573964497,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.5,
|
13 |
+
"learning_rate": 1.5000000000000002e-05,
|
14 |
"loss": 2.0382,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.5,
|
19 |
+
"eval_loss": 1.9825799465179443,
|
20 |
+
"eval_runtime": 660.1781,
|
21 |
+
"eval_samples_per_second": 1.645,
|
22 |
+
"eval_steps_per_second": 0.412,
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 1.65,
|
27 |
+
"eval_loss": 1.9785882234573364,
|
28 |
+
"eval_runtime": 659.635,
|
29 |
+
"eval_samples_per_second": 1.646,
|
30 |
+
"eval_steps_per_second": 0.412,
|
31 |
+
"step": 3
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 1.65,
|
35 |
+
"step": 3,
|
36 |
+
"total_flos": 1143998697701376.0,
|
37 |
+
"train_loss": 2.036311705907186,
|
38 |
+
"train_runtime": 5409.4181,
|
39 |
+
"train_samples_per_second": 1.124,
|
40 |
+
"train_steps_per_second": 0.001
|
41 |
}
|
42 |
],
|
43 |
"logging_steps": 5,
|
44 |
+
"max_steps": 3,
|
45 |
+
"num_train_epochs": 3,
|
46 |
"save_steps": 500,
|
47 |
+
"total_flos": 1143998697701376.0,
|
48 |
"trial_name": null,
|
49 |
"trial_params": null
|
50 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84702a434798da0a39a475c0eb2fd055a2671fb3b9bbd5e70047b1db25e6597c
|
3 |
size 5688
|