Model save
Browse files- README.md +8 -12
- all_results.json +5 -10
- config.json +2 -2
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +48 -41
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,15 +1,11 @@
|
|
1 |
---
|
2 |
base_model: dmis-lab/selfbiorag_7b
|
3 |
tags:
|
4 |
-
- alignment-handbook
|
5 |
-
- trl
|
6 |
-
- sft
|
7 |
-
- generated_from_trainer
|
8 |
- trl
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
-
-
|
13 |
model-index:
|
14 |
- name: selfbiorag-7b-wo-kqa_golden-iter-sft-step1
|
15 |
results: []
|
@@ -20,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# selfbiorag-7b-wo-kqa_golden-iter-sft-step1
|
22 |
|
23 |
-
This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the
|
24 |
It achieves the following results on the evaluation set:
|
25 |
-
- Loss: 1.
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -59,14 +55,14 @@ The following hyperparameters were used during training:
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss |
|
61 |
|:-------------:|:-----:|:----:|:---------------:|
|
62 |
-
| 1.
|
63 |
-
|
|
64 |
-
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
68 |
|
69 |
-
- Transformers 4.
|
70 |
-
- Pytorch 2.1.2
|
71 |
- Datasets 2.14.6
|
72 |
- Tokenizers 0.15.2
|
|
|
1 |
---
|
2 |
base_model: dmis-lab/selfbiorag_7b
|
3 |
tags:
|
|
|
|
|
|
|
|
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
+
- generator
|
9 |
model-index:
|
10 |
- name: selfbiorag-7b-wo-kqa_golden-iter-sft-step1
|
11 |
results: []
|
|
|
16 |
|
17 |
# selfbiorag-7b-wo-kqa_golden-iter-sft-step1
|
18 |
|
19 |
+
This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the generator dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0452
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 1.2821 | 0.91 | 5 | 1.1136 |
|
59 |
+
| 0.9973 | 2.0 | 11 | 1.0571 |
|
60 |
+
| 0.82 | 2.73 | 15 | 1.0452 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
+
- Transformers 4.38.2
|
66 |
+
- Pytorch 2.1.2+cu121
|
67 |
- Datasets 2.14.6
|
68 |
- Tokenizers 0.15.2
|
all_results.json
CHANGED
@@ -1,13 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 2.
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_samples": 4044,
|
6 |
-
"eval_samples_per_second": 10.045,
|
7 |
-
"eval_steps_per_second": 0.631,
|
8 |
-
"train_loss": 1.2966619332631428,
|
9 |
-
"train_runtime": 333.6869,
|
10 |
"train_samples": 4750,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.73,
|
3 |
+
"train_loss": 1.0436887741088867,
|
4 |
+
"train_runtime": 249.1645,
|
|
|
|
|
|
|
|
|
|
|
5 |
"train_samples": 4750,
|
6 |
+
"train_samples_per_second": 4.142,
|
7 |
+
"train_steps_per_second": 0.06
|
8 |
}
|
config.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.
|
26 |
-
"use_cache":
|
27 |
"vocab_size": 32016
|
28 |
}
|
|
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.38.2",
|
26 |
+
"use_cache": false,
|
27 |
"vocab_size": 32016
|
28 |
}
|
generation_config.json
CHANGED
@@ -6,5 +6,5 @@
|
|
6 |
"pad_token_id": 0,
|
7 |
"temperature": 0.6,
|
8 |
"top_p": 0.9,
|
9 |
-
"transformers_version": "4.
|
10 |
}
|
|
|
6 |
"pad_token_id": 0,
|
7 |
"temperature": 0.6,
|
8 |
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.38.2"
|
10 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4939116424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bef77656dd3240b01ad7835aa55b2c321719a43e2df2ea0a38a954d2ccc1106e
|
3 |
size 4939116424
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4947390880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01a9ac4ef29e483dbf24f6f277f27a4bfdd63daf1b2940c472411a583b1d57f6
|
3 |
size 4947390880
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3590619888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba3c462b8c72af582ac9ac76a924e3e1a0b4228909be7b422d7bef01734a71ef
|
3 |
size 3590619888
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 2.
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 4750,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.73,
|
3 |
+
"train_loss": 1.0436887741088867,
|
4 |
+
"train_runtime": 249.1645,
|
5 |
"train_samples": 4750,
|
6 |
+
"train_samples_per_second": 4.142,
|
7 |
+
"train_steps_per_second": 0.06
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,74 +1,81 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
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.
|
13 |
-
"grad_norm": 7.
|
14 |
"learning_rate": 1e-05,
|
15 |
-
"loss": 1.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"step": 4
|
25 |
},
|
26 |
{
|
27 |
-
"epoch":
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
|
|
31 |
"step": 5
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 1.
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"step": 9
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 2.
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 2.
|
50 |
-
"eval_loss": 1.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second": 10.
|
53 |
-
"eval_steps_per_second": 0.
|
54 |
-
"step":
|
55 |
},
|
56 |
{
|
57 |
-
"epoch": 2.
|
58 |
-
"step":
|
59 |
-
"total_flos":
|
60 |
-
"train_loss": 1.
|
61 |
-
"train_runtime":
|
62 |
-
"train_samples_per_second":
|
63 |
-
"train_steps_per_second": 0.
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 5,
|
67 |
-
"max_steps":
|
68 |
"num_input_tokens_seen": 0,
|
69 |
"num_train_epochs": 3,
|
70 |
"save_steps": 500,
|
71 |
-
"total_flos":
|
72 |
"train_batch_size": 4,
|
73 |
"trial_name": null,
|
74 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.7272727272727275,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.18,
|
13 |
+
"grad_norm": 7.793758473406165,
|
14 |
"learning_rate": 1e-05,
|
15 |
+
"loss": 1.4406,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.91,
|
20 |
+
"grad_norm": 2.8267893418386913,
|
21 |
+
"learning_rate": 1.7485107481711014e-05,
|
22 |
+
"loss": 1.2821,
|
23 |
+
"step": 5
|
|
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.91,
|
27 |
+
"eval_loss": 1.1136233806610107,
|
28 |
+
"eval_runtime": 1.3266,
|
29 |
+
"eval_samples_per_second": 10.553,
|
30 |
+
"eval_steps_per_second": 0.754,
|
31 |
"step": 5
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 1.82,
|
35 |
+
"grad_norm": 2.7191793787610057,
|
36 |
+
"learning_rate": 6.453951129574644e-06,
|
37 |
+
"loss": 0.9973,
|
38 |
+
"step": 10
|
|
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 2.0,
|
42 |
+
"eval_loss": 1.0571211576461792,
|
43 |
+
"eval_runtime": 1.3822,
|
44 |
+
"eval_samples_per_second": 10.129,
|
45 |
+
"eval_steps_per_second": 0.723,
|
46 |
+
"step": 11
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.73,
|
50 |
+
"grad_norm": 1.7371058324616164,
|
51 |
+
"learning_rate": 0.0,
|
52 |
+
"loss": 0.82,
|
53 |
+
"step": 15
|
54 |
},
|
55 |
{
|
56 |
+
"epoch": 2.73,
|
57 |
+
"eval_loss": 1.045231580734253,
|
58 |
+
"eval_runtime": 1.3746,
|
59 |
+
"eval_samples_per_second": 10.185,
|
60 |
+
"eval_steps_per_second": 0.727,
|
61 |
+
"step": 15
|
62 |
},
|
63 |
{
|
64 |
+
"epoch": 2.73,
|
65 |
+
"step": 15,
|
66 |
+
"total_flos": 3088349921280.0,
|
67 |
+
"train_loss": 1.0436887741088867,
|
68 |
+
"train_runtime": 249.1645,
|
69 |
+
"train_samples_per_second": 4.142,
|
70 |
+
"train_steps_per_second": 0.06
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 5,
|
74 |
+
"max_steps": 15,
|
75 |
"num_input_tokens_seen": 0,
|
76 |
"num_train_epochs": 3,
|
77 |
"save_steps": 500,
|
78 |
+
"total_flos": 3088349921280.0,
|
79 |
"train_batch_size": 4,
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6ca3c9e83615ad729882cccf279e609bf3059b16167cb67f5d5977df49d19fa
|
3 |
size 6200
|