Grogros commited on
Commit
e42da4d
·
verified ·
1 Parent(s): 3efc38b

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.47.1",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d42adc38d2c6af11df04b7a24eb9807a75d1e25ca016c9037a136bdb2d7e4cb
3
+ size 4943274328
runs/Jan15_14-15-48_104-171-202-90/events.out.tfevents.1736951239.104-171-202-90.26521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ce668af9d861d067551e8a5088e6923793c2e79ca3a022eb645b3ee2eea00
3
+ size 5470
runs/Jan15_14-30-18_104-171-202-90/events.out.tfevents.1736951463.104-171-202-90.30900.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b4c6f67db4eb6f2edde289ab6bdc508ccec816fe0f036b80ceaa5bd72acf56
3
+ size 5469
runs/Jan15_14-33-09_104-171-202-90/events.out.tfevents.1736951635.104-171-202-90.31445.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690c37c9bef2e39b3fd1043300bd4b706bbba830488b88d35644d2cf331884b1
3
+ size 5469
runs/Jan15_14-35-48_104-171-202-90/events.out.tfevents.1736951794.104-171-202-90.31969.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e9a1edbd30b51d5def5c11eedf42825d00e73d300fd376c30fdb7b326f2926
3
+ size 5469
runs/Jan15_14-37-12_104-171-202-90/events.out.tfevents.1736951878.104-171-202-90.32287.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d7ade0ff0594f940050f96240e5f67f826d55f69e66d4e2517346d88d7c498
3
+ size 5470
runs/Jan15_14-43-11_104-171-202-90/events.out.tfevents.1736952229.104-171-202-90.33327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac8c8b94c6dee14b0f56825089867f1c9216024cd4f3119c997be8884816253
3
+ size 15972
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4b49420d674cf9733abd42c9ce9cdc85a680255b470678b0c84c01862d660b
3
+ size 5432