Training in progress, epoch 1
Browse files- config.json +31 -0
- model.safetensors +3 -0
- runs/Feb02_01-47-41_983cbba0eac5/events.out.tfevents.1738460864.983cbba0eac5.749.0 +3 -0
- runs/Feb02_01-49-53_983cbba0eac5/events.out.tfevents.1738460999.983cbba0eac5.5813.0 +3 -0
- runs/Feb02_01-53-19_983cbba0eac5/events.out.tfevents.1738461202.983cbba0eac5.6757.0 +3 -0
- runs/Feb02_01-57-09_983cbba0eac5/events.out.tfevents.1738461432.983cbba0eac5.7678.0 +3 -0
- runs/Feb02_01-59-14_983cbba0eac5/events.out.tfevents.1738461555.983cbba0eac5.8308.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/opt-350m",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": false,
|
| 12 |
+
"dropout": 0.1,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"ffn_dim": 4096,
|
| 16 |
+
"hidden_size": 1024,
|
| 17 |
+
"init_std": 0.02,
|
| 18 |
+
"layer_norm_elementwise_affine": true,
|
| 19 |
+
"layerdrop": 0.0,
|
| 20 |
+
"max_position_embeddings": 2048,
|
| 21 |
+
"model_type": "opt",
|
| 22 |
+
"num_attention_heads": 16,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"prefix": "</s>",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.47.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50272,
|
| 30 |
+
"word_embed_proj_dim": 512
|
| 31 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1d7f3cfa105d55d981feea87dc1698d387783a26648d9c65ce26728eec859c4
|
| 3 |
+
size 1324830880
|
runs/Feb02_01-47-41_983cbba0eac5/events.out.tfevents.1738460864.983cbba0eac5.749.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a4fc1caab8ff121eb953134496a3eef421a0cab72d65add1093207d7d12f0fa
|
| 3 |
+
size 4184
|
runs/Feb02_01-49-53_983cbba0eac5/events.out.tfevents.1738460999.983cbba0eac5.5813.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aa871a26ef9ab929bc416a7deb69d0140e675b0a6ba22e295f0cb5d47c51ff1
|
| 3 |
+
size 4184
|
runs/Feb02_01-53-19_983cbba0eac5/events.out.tfevents.1738461202.983cbba0eac5.6757.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68bc5f67c2aa814bffb901a7d26bd4aed415c62bcd36efd3f5bf09eb410a0a5b
|
| 3 |
+
size 5162
|
runs/Feb02_01-57-09_983cbba0eac5/events.out.tfevents.1738461432.983cbba0eac5.7678.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a820f7659559a0cd496a014467a668b894c4ed4b2167f18fa57ade228ee2f04c
|
| 3 |
+
size 5364
|
runs/Feb02_01-59-14_983cbba0eac5/events.out.tfevents.1738461555.983cbba0eac5.8308.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdf805c6f742501760d5e3cc7febee8f7c78960bb5fc6e62836eeeaeab0ae079
|
| 3 |
+
size 38683
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab77a5eae38b0e271c42e2acd0600243694639d1424fbedb4fd0a49e94c28e2
|
| 3 |
+
size 5368
|