Training in progress, step 410
Browse files- config.json +3 -3
- model.safetensors +1 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
"eos_token_id": 31989,
|
| 9 |
"head_dim": 64,
|
| 10 |
"hidden_act": "silu",
|
|
@@ -21,10 +21,10 @@
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-06,
|
| 23 |
"rope_scaling": null,
|
| 24 |
-
"rope_theta":
|
| 25 |
"tie_word_embeddings": true,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.54.1",
|
| 28 |
-
"use_cache":
|
| 29 |
"vocab_size": 32000
|
| 30 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 31989,
|
| 8 |
"eos_token_id": 31989,
|
| 9 |
"head_dim": 64,
|
| 10 |
"hidden_act": "silu",
|
|
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-06,
|
| 23 |
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
"tie_word_embeddings": true,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.54.1",
|
| 28 |
+
"use_cache": false,
|
| 29 |
"vocab_size": 32000
|
| 30 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 373077376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca1520a3649298ab68b04f841144d4338b54caa5d22eb48cd6328f2972c319a
|
| 3 |
size 373077376
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21dfcc140b20b5859602309c4b2a7d5ca7cc6bb8c090092b61e00047f79e7a4f
|
| 3 |
size 5777
|