Training in progress, epoch 5, checkpoint
Browse files- checkpoint-1060/README.md +9 -0
- checkpoint-1060/adapter_config.json +26 -0
- checkpoint-1060/adapter_model.bin +3 -0
- checkpoint-1060/optimizer.pt +3 -0
- checkpoint-1060/rng_state.pth +3 -0
- checkpoint-1060/scheduler.pt +3 -0
- checkpoint-1060/sentencepiece.bpe.model +3 -0
- checkpoint-1060/special_tokens_map.json +19 -0
- checkpoint-1060/tokenizer.json +0 -0
- checkpoint-1060/tokenizer_config.json +24 -0
- checkpoint-1060/trainer_state.json +89 -0
- checkpoint-1060/training_args.bin +3 -0
checkpoint-1060/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.5.0
|
checkpoint-1060/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "camembert/camembert-large",
|
4 |
+
"bias": "all",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": [
|
13 |
+
"classifier.bias",
|
14 |
+
"classifier.weight"
|
15 |
+
],
|
16 |
+
"peft_type": "LORA",
|
17 |
+
"r": 64,
|
18 |
+
"revision": null,
|
19 |
+
"target_modules": [
|
20 |
+
"query",
|
21 |
+
"key",
|
22 |
+
"value",
|
23 |
+
"dense"
|
24 |
+
],
|
25 |
+
"task_type": "TOKEN_CLS"
|
26 |
+
}
|
checkpoint-1060/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da03c2e5cf329852b66a01b89622223c2fcbf52ce53827113df9fd71e5e2ed56
|
3 |
+
size 117304221
|
checkpoint-1060/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c00b93bdd0a6a507e95b4c90dfc918a379c6fae01ac789e9d44fbeceeb84ebe
|
3 |
+
size 234652550
|
checkpoint-1060/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce766356fe38c31114f62a6c30fc3b84d1bbf4c4465c11dca5d0676244b2279b
|
3 |
+
size 14575
|
checkpoint-1060/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d775f6e462a916c86b1c3e21f113a5b0e8205fa7ec7a56531a81c04f452f2305
|
3 |
+
size 627
|
checkpoint-1060/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
3 |
+
size 808767
|
checkpoint-1060/special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
checkpoint-1060/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1060/tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"clean_up_tokenization_spaces": true,
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"__type": "AddedToken",
|
12 |
+
"content": "<mask>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"model_max_length": 1000000000000000019884624838656,
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"tokenizer_class": "CamembertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|
checkpoint-1060/trainer_state.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1060,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 9.950235849056605e-06,
|
14 |
+
"loss": 6.539,
|
15 |
+
"step": 212
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 6.494007587432861,
|
20 |
+
"eval_runtime": 2.5292,
|
21 |
+
"eval_samples_per_second": 267.281,
|
22 |
+
"eval_steps_per_second": 33.608,
|
23 |
+
"step": 212
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 9.900235849056603e-06,
|
28 |
+
"loss": 6.4697,
|
29 |
+
"step": 424
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_loss": 6.410468101501465,
|
34 |
+
"eval_runtime": 2.6306,
|
35 |
+
"eval_samples_per_second": 256.98,
|
36 |
+
"eval_steps_per_second": 32.313,
|
37 |
+
"step": 424
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.0,
|
41 |
+
"learning_rate": 9.850235849056604e-06,
|
42 |
+
"loss": 6.3924,
|
43 |
+
"step": 636
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 3.0,
|
47 |
+
"eval_loss": 6.319283962249756,
|
48 |
+
"eval_runtime": 2.6112,
|
49 |
+
"eval_samples_per_second": 258.881,
|
50 |
+
"eval_steps_per_second": 32.552,
|
51 |
+
"step": 636
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 4.0,
|
55 |
+
"learning_rate": 9.800235849056604e-06,
|
56 |
+
"loss": 6.3093,
|
57 |
+
"step": 848
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"eval_loss": 6.226834297180176,
|
62 |
+
"eval_runtime": 2.5547,
|
63 |
+
"eval_samples_per_second": 264.612,
|
64 |
+
"eval_steps_per_second": 33.272,
|
65 |
+
"step": 848
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.0,
|
69 |
+
"learning_rate": 9.750235849056605e-06,
|
70 |
+
"loss": 6.216,
|
71 |
+
"step": 1060
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.0,
|
75 |
+
"eval_loss": 6.127103328704834,
|
76 |
+
"eval_runtime": 2.5792,
|
77 |
+
"eval_samples_per_second": 262.1,
|
78 |
+
"eval_steps_per_second": 32.956,
|
79 |
+
"step": 1060
|
80 |
+
}
|
81 |
+
],
|
82 |
+
"logging_steps": 500,
|
83 |
+
"max_steps": 42400,
|
84 |
+
"num_train_epochs": 200,
|
85 |
+
"save_steps": 500,
|
86 |
+
"total_flos": 1425048900923820.0,
|
87 |
+
"trial_name": null,
|
88 |
+
"trial_params": null
|
89 |
+
}
|
checkpoint-1060/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:932083cda874171956e29a9559decb3e85350d37f61015836b2c832b21575f2e
|
3 |
+
size 4155
|