Training in progress, step 200
Browse files- .gitattributes +0 -1
- config.json +2 -2
- last-checkpoint/config.json +2 -2
- last-checkpoint/generation_config.json +5 -3
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +0 -3
- last-checkpoint/trainer_state.json +0 -0
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- training_args.bin +2 -2
.gitattributes
CHANGED
@@ -32,5 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
-
last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
35 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "gelu_new",
|
11 |
-
"dropout_rate": 0.
|
12 |
"encoder_attention_type": "transient-global",
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
@@ -42,7 +42,7 @@
|
|
42 |
},
|
43 |
"tie_word_embeddings": false,
|
44 |
"torch_dtype": "float32",
|
45 |
-
"transformers_version": "4.30.
|
46 |
"use_cache": false,
|
47 |
"vocab_size": 256384
|
48 |
}
|
|
|
8 |
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
"encoder_attention_type": "transient-global",
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
|
|
42 |
},
|
43 |
"tie_word_embeddings": false,
|
44 |
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
"use_cache": false,
|
47 |
"vocab_size": 256384
|
48 |
}
|
last-checkpoint/config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "gelu_new",
|
11 |
-
"dropout_rate": 0.
|
12 |
"encoder_attention_type": "transient-global",
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
@@ -42,7 +42,7 @@
|
|
42 |
},
|
43 |
"tie_word_embeddings": false,
|
44 |
"torch_dtype": "float32",
|
45 |
-
"transformers_version": "4.30.
|
46 |
"use_cache": false,
|
47 |
"vocab_size": 256384
|
48 |
}
|
|
|
8 |
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
"encoder_attention_type": "transient-global",
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
|
|
42 |
},
|
43 |
"tie_word_embeddings": false,
|
44 |
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
"use_cache": false,
|
47 |
"vocab_size": 256384
|
48 |
}
|
last-checkpoint/generation_config.json
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
{
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"transformers_version": "4.30.
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.30.2",
|
7 |
+
"use_cache": false
|
8 |
}
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4736616809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e1c5ea18bd87fdb611133a2de17cde918710c98486e4c43afa42b6a54bfdd26
|
3 |
size 4736616809
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2368281769
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8e0394726ad0e28741282c318cacf3dc28269f23a93f3ff84875f2503165cc9
|
3 |
size 2368281769
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97e255bbc5f7f71168348462c22fbdbbadbc23b19d6869fc621700a4f4ba07b1
|
3 |
size 627
|
last-checkpoint/tokenizer.json
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:750ffbacc45c2f284f16da1d281fedfe2ed16f956306c0999ccaeb7b08554793
|
3 |
-
size 16780024
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/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 sha256:81616117252fb3172fd7b27ba4471c6643d6cc085d4f229ee6a2e5de41127204
|
3 |
+
size 4091
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2368281769
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8e0394726ad0e28741282c318cacf3dc28269f23a93f3ff84875f2503165cc9
|
3 |
size 2368281769
|
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 sha256:81616117252fb3172fd7b27ba4471c6643d6cc085d4f229ee6a2e5de41127204
|
3 |
+
size 4091
|