Training in progress, epoch 1
Browse files- config.json +39 -0
- model.safetensors +3 -0
- runs/Sep07_10-02-16_bb7542dc50d5/events.out.tfevents.1725703374.bb7542dc50d5.412.0 +3 -0
- runs/Sep07_10-02-16_bb7542dc50d5/events.out.tfevents.1725703507.bb7542dc50d5.412.1 +3 -0
- runs/Sep07_10-48-41_bb7542dc50d5/events.out.tfevents.1725706129.bb7542dc50d5.2172.0 +3 -0
- runs/Sep07_10-48-41_bb7542dc50d5/events.out.tfevents.1725712925.bb7542dc50d5.2172.1 +3 -0
- runs/Sep07_13-36-30_bb7542dc50d5/events.out.tfevents.1725716196.bb7542dc50d5.2172.2 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dunzhang/stella_en_400M_v5",
|
3 |
+
"architectures": [
|
4 |
+
"NewModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "dunzhang/stella_en_400M_v5--configuration.NewConfig",
|
9 |
+
"AutoModel": "dunzhang/stella_en_400M_v5--modeling.NewModel"
|
10 |
+
},
|
11 |
+
"classifier_dropout": null,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 1024,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"layer_norm_type": "layer_norm",
|
19 |
+
"logn_attention_clip1": false,
|
20 |
+
"logn_attention_scale": false,
|
21 |
+
"max_position_embeddings": 8192,
|
22 |
+
"model_type": "new",
|
23 |
+
"num_attention_heads": 16,
|
24 |
+
"num_hidden_layers": 24,
|
25 |
+
"pack_qkv": true,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "rope",
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 2.0,
|
30 |
+
"type": "ntk"
|
31 |
+
},
|
32 |
+
"rope_theta": 160000,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.44.2",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"unpad_inputs": true,
|
37 |
+
"use_memory_efficient_attention": true,
|
38 |
+
"vocab_size": 30528
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6abf4650e2c0a3012f79cfdb9fdffdd85ca52eb937d4d7440965e73f3ba59e5b
|
3 |
+
size 1736585680
|
runs/Sep07_10-02-16_bb7542dc50d5/events.out.tfevents.1725703374.bb7542dc50d5.412.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ceca257b44b47d5a3243b6cfbb8a856dc292afe9bb42b4267e95463824f9a2e
|
3 |
+
size 5309
|
runs/Sep07_10-02-16_bb7542dc50d5/events.out.tfevents.1725703507.bb7542dc50d5.412.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7779912606090d6e185e94b91f32e8a59d85e130d9ffc168be25a56d1fa782
|
3 |
+
size 5309
|
runs/Sep07_10-48-41_bb7542dc50d5/events.out.tfevents.1725706129.bb7542dc50d5.2172.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8649a4a9228797ace0b2c28fa89f738268b0d5369263fca6721c78dc5a63702
|
3 |
+
size 21698
|
runs/Sep07_10-48-41_bb7542dc50d5/events.out.tfevents.1725712925.bb7542dc50d5.2172.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9004f12f85a56531ac5ea4a4b944bb21ab5f5c0d68ebe66cfb9a2b4f29d08d46
|
3 |
+
size 21240
|
runs/Sep07_13-36-30_bb7542dc50d5/events.out.tfevents.1725716196.bb7542dc50d5.2172.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b05e148f033cb6b1b553fcf55280244656e36770f837a4b5f11063bbc7aeaf9b
|
3 |
+
size 6749
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f14c4c014ea15c8c8624f35830584c8d473e086fd2c861bf93c1ed81e5b961e2
|
3 |
+
size 5304
|