Training in progress, epoch 1
Browse files- config.json +2 -2
- model.safetensors +1 -1
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
|
|
|
| 13 |
"eos_token_id": 2,
|
| 14 |
"feed_forward_proj": "relu",
|
| 15 |
"initializer_factor": 1.0,
|
|
@@ -25,8 +26,7 @@
|
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
| 27 |
"relative_attention_num_buckets": 32,
|
| 28 |
-
"
|
| 29 |
-
"transformers_version": "4.51.3",
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 32100
|
| 32 |
}
|
|
|
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
+
"dtype": "float32",
|
| 14 |
"eos_token_id": 2,
|
| 15 |
"feed_forward_proj": "relu",
|
| 16 |
"initializer_factor": 1.0,
|
|
|
|
| 26 |
"pad_token_id": 0,
|
| 27 |
"relative_attention_max_distance": 128,
|
| 28 |
"relative_attention_num_buckets": 32,
|
| 29 |
+
"transformers_version": "4.56.1",
|
|
|
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 32100
|
| 32 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891558696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30d28c9d4f422b2ae34ec62c000ce6506071096b0b6045f4af10e9376d249f7c
|
| 3 |
size 891558696
|
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 sha256:5cf1ad3ef91c3e4f3adf0195b50167dcb02f35761faae84f4dcdaa72e5ecf4ef
|
| 3 |
+
size 5905
|