Upload 13 files
Browse files- .gitattributes +2 -0
- all_results.json +14 -9
- config.json +3 -9
- eval_results.json +9 -0
- generation_config.json +1 -1
- model.safetensors +1 -1
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +2 -1
- train_results.json +9 -9
- trainer_state.json +0 -0
- training_args.bin +2 -2
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
all_results.json
CHANGED
|
@@ -1,11 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.961527705192566,
|
| 4 |
+
"eval_runtime": 77.3959,
|
| 5 |
+
"eval_samples": 83311,
|
| 6 |
+
"eval_samples_per_second": 1076.426,
|
| 7 |
+
"eval_steps_per_second": 134.555,
|
| 8 |
+
"num_input_tokens_seen": 225160303,
|
| 9 |
+
"total_flos": 5.962942279994573e+16,
|
| 10 |
+
"train_loss": 1.8857571468166456,
|
| 11 |
+
"train_runtime": 16282.8843,
|
| 12 |
+
"train_samples": 333243,
|
| 13 |
+
"train_samples_per_second": 204.658,
|
| 14 |
+
"train_steps_per_second": 25.583,
|
| 15 |
+
"train_tokens_per_second": 13822.702
|
| 16 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "swish",
|
| 5 |
"add_bias_logits": false,
|
|
@@ -8,11 +7,6 @@
|
|
| 8 |
"MarianMTModel"
|
| 9 |
],
|
| 10 |
"attention_dropout": 0.0,
|
| 11 |
-
"bad_words_ids": [
|
| 12 |
-
[
|
| 13 |
-
65000
|
| 14 |
-
]
|
| 15 |
-
],
|
| 16 |
"bos_token_id": 0,
|
| 17 |
"classif_dropout": 0.0,
|
| 18 |
"classifier_dropout": 0.0,
|
|
@@ -46,19 +40,19 @@
|
|
| 46 |
"LABEL_1": 1,
|
| 47 |
"LABEL_2": 2
|
| 48 |
},
|
| 49 |
-
"max_length":
|
| 50 |
"max_position_embeddings": 512,
|
| 51 |
"model_type": "marian",
|
| 52 |
"normalize_before": false,
|
| 53 |
"normalize_embedding": false,
|
| 54 |
-
"num_beams":
|
| 55 |
"num_hidden_layers": 6,
|
| 56 |
"pad_token_id": 65000,
|
| 57 |
"scale_embedding": true,
|
| 58 |
"share_encoder_decoder_embeddings": true,
|
| 59 |
"static_position_embeddings": true,
|
| 60 |
"torch_dtype": "float32",
|
| 61 |
-
"transformers_version": "4.
|
| 62 |
"use_cache": true,
|
| 63 |
"vocab_size": 65001
|
| 64 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"activation_function": "swish",
|
| 4 |
"add_bias_logits": false,
|
|
|
|
| 7 |
"MarianMTModel"
|
| 8 |
],
|
| 9 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"bos_token_id": 0,
|
| 11 |
"classif_dropout": 0.0,
|
| 12 |
"classifier_dropout": 0.0,
|
|
|
|
| 40 |
"LABEL_1": 1,
|
| 41 |
"LABEL_2": 2
|
| 42 |
},
|
| 43 |
+
"max_length": null,
|
| 44 |
"max_position_embeddings": 512,
|
| 45 |
"model_type": "marian",
|
| 46 |
"normalize_before": false,
|
| 47 |
"normalize_embedding": false,
|
| 48 |
+
"num_beams": null,
|
| 49 |
"num_hidden_layers": 6,
|
| 50 |
"pad_token_id": 65000,
|
| 51 |
"scale_embedding": true,
|
| 52 |
"share_encoder_decoder_embeddings": true,
|
| 53 |
"static_position_embeddings": true,
|
| 54 |
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.51.3",
|
| 56 |
"use_cache": true,
|
| 57 |
"vocab_size": 65001
|
| 58 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.961527705192566,
|
| 4 |
+
"eval_runtime": 77.3959,
|
| 5 |
+
"eval_samples": 83311,
|
| 6 |
+
"eval_samples_per_second": 1076.426,
|
| 7 |
+
"eval_steps_per_second": 134.555,
|
| 8 |
+
"num_input_tokens_seen": 225160303
|
| 9 |
+
}
|
generation_config.json
CHANGED
|
@@ -12,5 +12,5 @@
|
|
| 12 |
"num_beams": 4,
|
| 13 |
"pad_token_id": 65000,
|
| 14 |
"renormalize_logits": true,
|
| 15 |
-
"transformers_version": "4.
|
| 16 |
}
|
|
|
|
| 12 |
"num_beams": 4,
|
| 13 |
"pad_token_id": 65000,
|
| 14 |
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.51.3"
|
| 16 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 309965092
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aac5f96b0d1c2435c122ac11eef69a78fde5924dbd76351f1a233d6c0f28037c
|
| 3 |
size 309965092
|
source.spm
CHANGED
|
Binary files a/source.spm and b/source.spm differ
|
|
|
target.spm
CHANGED
|
Binary files a/target.spm and b/target.spm differ
|
|
|
tokenizer_config.json
CHANGED
|
@@ -25,8 +25,9 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"clean_up_tokenization_spaces":
|
| 29 |
"eos_token": "</s>",
|
|
|
|
| 30 |
"model_max_length": 512,
|
| 31 |
"pad_token": "<pad>",
|
| 32 |
"separate_vocabs": false,
|
|
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
+
"clean_up_tokenization_spaces": false,
|
| 29 |
"eos_token": "</s>",
|
| 30 |
+
"extra_special_tokens": {},
|
| 31 |
"model_max_length": 512,
|
| 32 |
"pad_token": "<pad>",
|
| 33 |
"separate_vocabs": false,
|
train_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"num_input_tokens_seen":
|
| 4 |
-
"total_flos":
|
| 5 |
-
"train_loss": 1.
|
| 6 |
-
"train_runtime":
|
| 7 |
-
"train_samples":
|
| 8 |
-
"train_samples_per_second":
|
| 9 |
-
"train_steps_per_second":
|
| 10 |
-
"train_tokens_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"num_input_tokens_seen": 225160303,
|
| 4 |
+
"total_flos": 5.962942279994573e+16,
|
| 5 |
+
"train_loss": 1.8857571468166456,
|
| 6 |
+
"train_runtime": 16282.8843,
|
| 7 |
+
"train_samples": 333243,
|
| 8 |
+
"train_samples_per_second": 204.658,
|
| 9 |
+
"train_steps_per_second": 25.583,
|
| 10 |
+
"train_tokens_per_second": 13822.702
|
| 11 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
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 sha256:742b6e553683f5a8be3739142255defff5d894b12172be0396ab15afd216cd8a
|
| 3 |
+
size 5496
|