minpeter commited on
Commit
37c80d7
·
verified ·
1 Parent(s): 885e775

Training in progress, step 55000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
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",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.036084391824351615,
13
+ "intermediate_size": 1920,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 27,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 31989,
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": "4.53.2",
28
+ "use_cache": false,
29
+ "vocab_size": 32000
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 31989,
4
+ "eos_token_id": 31989,
5
+ "pad_token_id": 31989,
6
+ "transformers_version": "4.53.2",
7
+ "use_cache": false
8
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c14fd1bee72f4ae520b48b248b2ea9e307a5e6c6de8beaabe8a16fe62005b7
3
+ size 373077376
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefb6b7646dd239517efc08c52c05e50bd2e554a46e9a05729931b19fbb006cd
3
+ size 422377931
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5bdfa2877904e7b9a7b53aade30f914468c44c9bd87ddaf3d868c947122bdc
3
+ size 15365
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd1a1a2628858c949d2caf414f3cde378351d0ea08a296d07ed8c1eca505698
3
+ size 15365
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb73362b1face5d1a476a56ab0566aef0055e01bb21637b1e4295a0b2bea00c6
3
+ size 15365
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af950afbfdd102f1586489bf8551b3cbee62c9fe5ac201ea0bda312d056d639
3
+ size 15365
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec23b225f5d4e10d609ff2c03cba3f552baeaa7a8e06ceae9d6f9bd12845a59c
3
+ size 1401
last-checkpoint/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f939a88a6228a7cbb9f9eda06d10196c6b5d24d573a6afa28910a0d0d8e57808
3
+ size 5777