Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +63 -0
- global_step145845/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- global_step145845/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- global_step145845/mp_rank_00_model_states.pt +3 -0
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/fs/archive/share/yulan/data/aa_mini/output/miniyulan-2B-final-stage14/checkpoint-136346-rms_norm",
|
3 |
+
"architectures": [
|
4 |
+
"MiniYuLanModelForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"dim_model_base": 1920,
|
10 |
+
"dim_model_base_attn": 64,
|
11 |
+
"dim_model_base_init": null,
|
12 |
+
"dim_model_base_lmh": 1,
|
13 |
+
"dim_model_base_logits": 1920.0,
|
14 |
+
"dim_model_base_lr": 256.0,
|
15 |
+
"down_proj_alpha": 0.03450327796711771,
|
16 |
+
"embed_tokens_alpha": 1,
|
17 |
+
"embedding_ln": false,
|
18 |
+
"embedding_rmsln": false,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"gate_up_proj_alpha": 0.3651483716701107,
|
21 |
+
"gradient_checkpointing_step": 11,
|
22 |
+
"hidden_act": "silu",
|
23 |
+
"hidden_size": 1920,
|
24 |
+
"hidden_states_shrink": 0.18708286933869706,
|
25 |
+
"init_scale_o": 1,
|
26 |
+
"initializer_range": 5e-05,
|
27 |
+
"input_layernorm_alpha": 1.0,
|
28 |
+
"intermediate_size": 4800,
|
29 |
+
"k_proj_alpha": 0.3651483716701107,
|
30 |
+
"layer_norm_eps": 1e-06,
|
31 |
+
"lm_head_alpha": 1.0,
|
32 |
+
"ln_scale": 1,
|
33 |
+
"max_position_embeddings": 4096,
|
34 |
+
"model_reproduce": "transformer",
|
35 |
+
"model_type": "miniyulan",
|
36 |
+
"norm_alpha": 1.0,
|
37 |
+
"num_attention_heads": 30,
|
38 |
+
"num_hidden_layers": 56,
|
39 |
+
"num_key_value_heads": 6,
|
40 |
+
"o_proj_alpha": 0.03450327796711771,
|
41 |
+
"post_attention_layernorm_alpha": 1.0,
|
42 |
+
"q_proj_alpha": 0.3651483716701107,
|
43 |
+
"qk_layernorm": false,
|
44 |
+
"rms_norm_eps": 1e-06,
|
45 |
+
"rms_type": "llama",
|
46 |
+
"rope_scaling": null,
|
47 |
+
"rope_theta": 10000.0,
|
48 |
+
"scale_emb": 10.0,
|
49 |
+
"shrink_alpha": 1,
|
50 |
+
"sliding_window": null,
|
51 |
+
"tie_word_embeddings": true,
|
52 |
+
"torch_dtype": "bfloat16",
|
53 |
+
"transformers_version": "4.44.0",
|
54 |
+
"use_cache": false,
|
55 |
+
"use_emb_alpha": true,
|
56 |
+
"use_liger": true,
|
57 |
+
"use_norm_alpha": true,
|
58 |
+
"use_sliding_window": false,
|
59 |
+
"v_proj_alpha": 0.3651483716701107,
|
60 |
+
"vocab_size": 99000,
|
61 |
+
"wesar_weights": true,
|
62 |
+
"z_loss": 0.0001
|
63 |
+
}
|
global_step145845/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d02a73585db5bf403192ac49d655fb1c3c2f2a249b04af3c0e14402439d21c0
|
3 |
+
size 558554482
|
global_step145845/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7ac4559e5995903ccf34a21eff3bb18b88c24e63d91b85c94f524fb5676d5c2
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c2b4e3723054b68519bbd42ba7d080cd1b23506ec261bf1b0910e50bf57e553
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2740538ea2a0982c3ea9d0e7fcb01c8c31d9a4af999dc0180a4964a364588d00
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b85190e60b629e795cf537e071f5d85030f00582c8c9eb0a17225f05e99d93a
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e7ccad2bc8a614f2ebfe51ae2bb968524bba2bdb7e752a577aa27ecbbb0d2d9
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cec7f6345ed8ad45dacbb8bbfaea35b5cd21243eb5c362e7ccbc8cdd7356379
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e8c0f623fb656d0746950c5926d59cbc7b9260e5f009e43e9f0e4452bfa1130
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7ccb6fd232e56f84ff66994c53dfb7f6ad593f9238094e7f2230f5b894742f
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64602bf5940ae6fc8e1bd830ab13c846e5ecca257359d92c20c0be8b4ac706ff
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5de148fb0c41b985f7d77a7f3e2e3d9212a34480a1b56f84178c685ed554fecc
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b497449f8ca855f7b858b21f8d6903a102c42ea247be9555ce24ee18782f54dc
|
3 |
+
size 558554418
|
global_step145845/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eee72147906142d350511a4d5f89e18e9ae9f9a620f8840e40af9851ed19bb78
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd92547b9f675e1ec15384fdf6fd9a9015caf64fa1a377d01f85697b1d14d0fa
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe32a3a177b3ee026d6ab26036ae6ecb02ccc25372181c24e3e64342885fa471
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51662248a0d738c3b0cc35f4373f409cf24a41772228cb54939927e20af570d7
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1d8382d40cd476d4cba54bbcb1eb602b42228612562c5b0331fae1e77e577b7
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6848113116c289ebc403616eb7b88d0e6ddf49f359f9b6785afed22ca5564445
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a0cafffb1408fde76dfdab010e32eb5d92cc311d0d5d4a5a524ca0edd6305cf
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c976ae0218bcb698f84e0c36c902e04f75acd021b06e0c7c157d74c98c741b3
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a383620970ca18a8a048f7c31c6e9ee6224fb1f33773b100bd1de69f43668c5
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c796eb2af974a2ecc5b496fc000d50065403c4ad2db537a59add5b4aa4500501
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d38c45c338967616141a438cd4acb96e4fc30b7a2d7ae91aa39fcf2ce3a5a483
|
3 |
+
size 558554290
|
global_step145845/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ee5e5467ebaa42cb6a26daacb20d4110a9dd08a5be090ed17d966bbf45f9b77
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:536912af24f52e98149e927bfa477406971d3306d77fd2cfeefd39243a470c12
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e6c2711123043ed2d2803881347c337d4b1182b199a8beb2ae3e0de4a0a3c3
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:925011081765155b1cb245d39ac78ccb00fa311b4bdf4a1080496ac2abda625f
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4aff8b627fe591e7a6a901c577243502dff185a824205f41e9a29bbacdf176b
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:733182105c85c0589d25aaa072ca7d67294fad25e1e89bad32c06a39dc8c9478
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:900654414ce25d13ac21f80785bce111325db7f30b9e484a4fe8b8d0dd7aa6b9
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2599e574d366b95000d1ddc8cb7204cc869e97c04ac4a409b3b5eaca7a63a546
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da4372e36ab422012533eadabb2425bee06808889cec99757eb5f5868b6cff3d
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:309832a9fad24a5f0ce8c194dbecf7d2da1bc63e1957a8062396325e987933d9
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bff9e32e626e6c16b13897f547b131e1b93d4aee14d3b152778ae2d37cac94b3
|
3 |
+
size 558554354
|
global_step145845/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22452e3518d47b77b001c41c44c0c4b39c6dda02d21fe4445b0831b7daa7f596
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e4db44b9ee2584b5136bd18870e58681e9d73448bd74e2921a0172f236b4e82
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13589e1053472aaee9c3af50206b7f5a9fcb63df6c292c49bcd56b071c3f752e
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84661c52ff9b6b5aee7d8abbb9f8e7c43306bb700a85860ec3c9873f95c32780
|
3 |
+
size 558554434
|
global_step145845/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e6b144920fb45ada1722d536f1bd4cba3295211e15b4170a4e2102e2fda4f75
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa101ed1d709233704edeb1fa506610d0a4c314f8ca22235d7c02cdae76d301a
|
3 |
+
size 558554370
|
global_step145845/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bcb7586281f5bc2c8679bee3d9978baf6b812edec5925f143ce5ec26fd9db9d
|
3 |
+
size 558554306
|
global_step145845/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ff8da5ac1a9ef81d00412285be842cd3c8437e68f2eb4ffe8bb6f9427961ec
|
3 |
+
size 558610626
|
global_step145845/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e512e101e18caa89f63e7c57876d3fca5ed660f3d580a3dff3f5585e9fefbfb
|
3 |
+
size 558554290
|
global_step145845/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45cf571c18d75b6cdae15f95245e785885942374908eac0e490feb886b39cd57
|
3 |
+
size 558554290
|
global_step145845/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc6e7e496322f968b023680bc393f31d279b59d76d06319b0254c9d95818521
|
3 |
+
size 558554354
|
global_step145845/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc195a8f3f469fd17f3ed726c6a9172881c4372e1cde77eb527bd19bc20ff6d
|
3 |
+
size 558554418
|
global_step145845/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d843d28872966543caa81cfa49edc716f0fbb60b8d118a9532fe65f4b32a05
|
3 |
+
size 558554290
|
global_step145845/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13f6ef6880bc28940fd957f506f63a51302e1082c1d9422d2454076198f9e79b
|
3 |
+
size 558554354
|
global_step145845/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50bc021e6deaf1c2b0d3ae533023d73bba9da62b254d58903dfe93fdebc9826d
|
3 |
+
size 4468641136
|