Training in progress, step 500
Browse files- config.json +36 -0
- model.safetensors +3 -0
- runs/Oct12_19-15-58_sirius/events.out.tfevents.1728782160.sirius.2278578.0 +3 -0
- runs/Oct12_19-16-32_sirius/events.out.tfevents.1728782193.sirius.2278578.1 +3 -0
- runs/Oct12_19-17-24_sirius/events.out.tfevents.1728782245.sirius.2278578.2 +3 -0
- runs/Oct12_19-17-41_sirius/events.out.tfevents.1728782261.sirius.2278578.3 +3 -0
- runs/Oct12_19-18-28_sirius/events.out.tfevents.1728782309.sirius.2278578.4 +3 -0
- runs/Oct12_19-23-25_sirius/events.out.tfevents.1728782606.sirius.2278578.5 +3 -0
- runs/Oct12_21-31-43_sirius/events.out.tfevents.1728790305.sirius.2281848.0 +3 -0
- runs/Oct12_21-33-05_sirius/events.out.tfevents.1728790386.sirius.2281848.1 +3 -0
- runs/Oct12_21-33-38_sirius/events.out.tfevents.1728790419.sirius.2281848.2 +3 -0
- runs/Oct12_21-34-19_sirius/events.out.tfevents.1728790460.sirius.2281848.3 +3 -0
- runs/Oct12_21-35-10_sirius/events.out.tfevents.1728790511.sirius.2281848.4 +3 -0
- runs/Oct12_22-20-35_sirius/events.out.tfevents.1728793237.sirius.2282901.0 +3 -0
- runs/Oct12_22-34-57_sirius/events.out.tfevents.1728794098.sirius.2282901.1 +3 -0
- runs/Oct12_22-36-29_sirius/events.out.tfevents.1728794189.sirius.2282901.2 +3 -0
- runs/Oct12_22-37-55_sirius/events.out.tfevents.1728794276.sirius.2282901.3 +3 -0
- runs/Oct12_22-38-18_sirius/events.out.tfevents.1728794299.sirius.2282901.4 +3 -0
- runs/Oct12_22-43-46_sirius/events.out.tfevents.1728794626.sirius.2282901.5 +3 -0
- runs/Oct12_22-52-24_sirius/events.out.tfevents.1728795144.sirius.2282901.6 +3 -0
- runs/Oct12_23-12-25_sirius/events.out.tfevents.1728796346.sirius.2284185.0 +3 -0
- runs/Oct12_23-12-25_sirius/events.out.tfevents.1728796403.sirius.2284185.1 +3 -0
- runs/Oct12_23-14-35_sirius/events.out.tfevents.1728796476.sirius.2284185.2 +3 -0
- runs/Oct12_23-15-59_sirius/events.out.tfevents.1728796560.sirius.2284185.3 +3 -0
- runs/Oct12_23-16-22_sirius/events.out.tfevents.1728796583.sirius.2284185.4 +3 -0
- runs/Oct12_23-18-15_sirius/events.out.tfevents.1728796695.sirius.2284185.5 +3 -0
- runs/Oct12_23-18-29_sirius/events.out.tfevents.1728796710.sirius.2284185.6 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"max_position_embeddings": 131072,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 16,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": {
|
24 |
+
"factor": 32.0,
|
25 |
+
"high_freq_factor": 4.0,
|
26 |
+
"low_freq_factor": 1.0,
|
27 |
+
"original_max_position_embeddings": 8192,
|
28 |
+
"rope_type": "llama3"
|
29 |
+
},
|
30 |
+
"rope_theta": 500000.0,
|
31 |
+
"tie_word_embeddings": true,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.44.2",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 128256
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b8dd80d178d233800b343273396a2c38758da457fcfc31571c2817ddf7f58af
|
3 |
+
size 2471645608
|
runs/Oct12_19-15-58_sirius/events.out.tfevents.1728782160.sirius.2278578.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edc2b586cfbe5aa15e44192808ea99bceda8e3e10cc1191c3f1b13b88a054a7e
|
3 |
+
size 5203
|
runs/Oct12_19-16-32_sirius/events.out.tfevents.1728782193.sirius.2278578.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdda2ba2bfdaae9192ccb135b89a4d9ba0cb88cb0b13b6e030c650f4f726e48d
|
3 |
+
size 5203
|
runs/Oct12_19-17-24_sirius/events.out.tfevents.1728782245.sirius.2278578.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d23a91e4503205518189b320b3e9c850fa3fa9f8718b20d3dc1a00f4caa1fa7b
|
3 |
+
size 5203
|
runs/Oct12_19-17-41_sirius/events.out.tfevents.1728782261.sirius.2278578.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851cc1cd0508ec3c74f6a9f26d299bc706f293063a0a8222977a3bc11cddd769
|
3 |
+
size 5203
|
runs/Oct12_19-18-28_sirius/events.out.tfevents.1728782309.sirius.2278578.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d46f54d4062c88a72eb89f1097c624aa92eca586eb1a1b883b18cf4967d8531
|
3 |
+
size 5203
|
runs/Oct12_19-23-25_sirius/events.out.tfevents.1728782606.sirius.2278578.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc220cb72788b36133cae8246c54cb5bc6d6252082a6953dd3edeebdb967f48
|
3 |
+
size 5203
|
runs/Oct12_21-31-43_sirius/events.out.tfevents.1728790305.sirius.2281848.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06a08dbb88ce177f9f99e8d8395a0b17b1914ccdae768a16eb49f63ff115b0f5
|
3 |
+
size 5203
|
runs/Oct12_21-33-05_sirius/events.out.tfevents.1728790386.sirius.2281848.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14754d365484353df4bd748c2719a80a45c24b9296344ef8103f759fefc91e8c
|
3 |
+
size 5203
|
runs/Oct12_21-33-38_sirius/events.out.tfevents.1728790419.sirius.2281848.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ecd0ab923db7f7448926cb374f875072b3e3477ecedae69543237cbed554e32
|
3 |
+
size 5203
|
runs/Oct12_21-34-19_sirius/events.out.tfevents.1728790460.sirius.2281848.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9251a48d24bf9131cbeaadf2969a70017c2473dd73f91fba1a297327273a4b24
|
3 |
+
size 5203
|
runs/Oct12_21-35-10_sirius/events.out.tfevents.1728790511.sirius.2281848.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53337c8554cf888dbc41c4b0424759465242066f87084c9afc6d7533728ce74
|
3 |
+
size 5203
|
runs/Oct12_22-20-35_sirius/events.out.tfevents.1728793237.sirius.2282901.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3ad167f37bce4c875dfbb51553a53b3d5c2c8d6d78c34eee6e78c19bf92c260
|
3 |
+
size 5203
|
runs/Oct12_22-34-57_sirius/events.out.tfevents.1728794098.sirius.2282901.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7663c3fda76882f73a0143248f6c90b2c68163646bcfc793a074239a335ff465
|
3 |
+
size 5203
|
runs/Oct12_22-36-29_sirius/events.out.tfevents.1728794189.sirius.2282901.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc52befee4806c5c89711f8095af8b8d69b7a9dcbdf6205cdd5b2775bf3907f
|
3 |
+
size 5203
|
runs/Oct12_22-37-55_sirius/events.out.tfevents.1728794276.sirius.2282901.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d57fe2e4a3744cb3f00d5127a0ff531116c3c0aa69bc84f95072220a4346154f
|
3 |
+
size 5203
|
runs/Oct12_22-38-18_sirius/events.out.tfevents.1728794299.sirius.2282901.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75587c7dba36d9d311916cb0ba237279598be9e1dbe981e1d5d25233d4729e13
|
3 |
+
size 5203
|
runs/Oct12_22-43-46_sirius/events.out.tfevents.1728794626.sirius.2282901.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f4e2179febab270b1656f0f85b07196514073f7031050f3c27007b46ca0972
|
3 |
+
size 5735
|
runs/Oct12_22-52-24_sirius/events.out.tfevents.1728795144.sirius.2282901.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee6a571d70fc0bb5ab6f56063f355c275a1aab8d6ff2f040ea3a45e419c3af04
|
3 |
+
size 4184
|
runs/Oct12_23-12-25_sirius/events.out.tfevents.1728796346.sirius.2284185.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df2296b6e06d1f6b392b13f5feac7d1acbed0869be74ca73eb3b6517123c3773
|
3 |
+
size 6968
|
runs/Oct12_23-12-25_sirius/events.out.tfevents.1728796403.sirius.2284185.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83663f129f881e821fe4bc1a7e096d0947507d592381c9d981bda49946f9d7d0
|
3 |
+
size 354
|
runs/Oct12_23-14-35_sirius/events.out.tfevents.1728796476.sirius.2284185.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a7f5021ed1063469b2cbcf2d6f1603c6184219b87bbb45fc1ec3801ef57bdfc
|
3 |
+
size 5200
|
runs/Oct12_23-15-59_sirius/events.out.tfevents.1728796560.sirius.2284185.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1b6d240fde9ca0e069b59cdf14d36b9b7afb21add814451d5facd74b357f090
|
3 |
+
size 5200
|
runs/Oct12_23-16-22_sirius/events.out.tfevents.1728796583.sirius.2284185.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a0c044beff53f16b8d24e27f2098bd3b6f346e7553fc0e379f4143f366968d5
|
3 |
+
size 5200
|
runs/Oct12_23-18-15_sirius/events.out.tfevents.1728796695.sirius.2284185.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c7fa697418e4993f00037796888712f0b983bda47324cd6d245e0bdc3f4aa42
|
3 |
+
size 5202
|
runs/Oct12_23-18-29_sirius/events.out.tfevents.1728796710.sirius.2284185.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a153cc05ba64c50a42f4075b42ec072620ef982fa40176abcc47d8e658dd3dcc
|
3 |
+
size 5202
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9504411923d2bcb7c2630ca7aa26716f347cffef98b25a4f60aa5680024288a5
|
3 |
+
size 5240
|