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_step87534/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +3 -0
- global_step87534/bf16_zero_pp_rank_53_mp_rank_00_optim_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-stage8-from-71k/checkpoint-77840-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_step87534/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:d4875e2212c62f4cbc1bd7270be6126d00f1a61eb3e02d199be9f04e1649722a
|
| 3 |
+
size 478761842
|
global_step87534/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:de4d08cfe9fe8211d1e6c8a3c8ede4dbeb3abbb24d02e40e421df5df07686828
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:4411676c89642bf2feab24a203bde6943aa91853bae243d21097ba127cac476e
|
| 3 |
+
size 478761794
|
global_step87534/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:f54f2d5b9ab7a82930b9e2abd0e234716550ef62814a57b8166782516d4ccade
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:43aa40654cac43642428eb53165b9ffd5d6d6e0202d7801dbd0019e6cb0151bd
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:681334be877b784af9b09965e1494bb481b5c1a0b410ea3583afea6bf49e76ad
|
| 3 |
+
size 478761794
|
global_step87534/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:c2e5020e058c76c81fb9d9dd88ddd01a61c50e10a7dca27b87d1a2c4eee3fc61
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:2d6445361a819d433d816f669adaf21234fe58e1257d9734c20a387881e97f50
|
| 3 |
+
size 478761794
|
global_step87534/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:ab77f33aae1b77520905017d7b9f3578ae2aa87b23bd59fa84a02b1eb0cce5a8
|
| 3 |
+
size 478761794
|
global_step87534/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:c8588db44848c3817b1719c9bbf97b098897291e56ff8c9e562c4d7f02ab5335
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:397fe12a575c8e81bf734e65c898f95522d458ea497d0cb9ec0a6c313f39d2fc
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:3fa7c8e5fd2cd3a1dec87175f4df232ea8851a16cd12192a324205aeb31aff92
|
| 3 |
+
size 478761778
|
global_step87534/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:c383bdefcb7270998a9c61e4a02abf1280d859b0fb43b82ac2d9885278d353bc
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:67e8bff883eadb30c49c6d7bf275858b73ae6d218694f8ffcdb53437ef0d45a3
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:7e60f8c822cd02528d5ac0e68b1d7ccadcf9e4e99dac12ac50f0f93c2474941b
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:173275efecd313e5ddc473ca73ddd124fe77a76e6ebfa5e2d981daf00b22ecef
|
| 3 |
+
size 478761794
|
global_step87534/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:b3f28b815a3269e7810d49a2e5371ccbe39fdd409ed78118335980d4185b0ec7
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:5a9628e5c11333ba0bcf601a620a8f591a31585f0dec1df5ffaa101e96755f22
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:26ccebe498b666ebe671d270055a0fd0578ef9aecf72d730a4a63d4d612a0d16
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:944ed68efbc8ee3881b07b4a82aef8617e06ea10415e6ce436a9925ce95760bd
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:9392f12e2bc4fe88af7823f2834d7cac1db9316253207e8f1279dcd461114f39
|
| 3 |
+
size 478761794
|
global_step87534/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:a3bac7d6e16b2f102f0f073b25128a1bf33f6d2298e33b415d68415d71e72074
|
| 3 |
+
size 478761794
|
global_step87534/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:d9941b1e545046537b821c97695f90db0577ba93e16be678ba65dee637317e87
|
| 3 |
+
size 478761778
|
global_step87534/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 sha256:1061b4f75a022878e047d8518547772bf4384426158f5ad4fe6db024d029be02
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:93aad3af0e0a08f5970f25e395f659a0bcb9fbc190722d91d31d1c2e55161cd0
|
| 3 |
+
size 478761794
|
global_step87534/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:fb257895c5ae9c3dd232432583479b2a30dff1235a163d30d7e7ffa4f523fd36
|
| 3 |
+
size 478761794
|
global_step87534/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:b8562cf34fc36617ff8bcedb57b4fa690d3d93aefdc2716b39f84814ea8b10a7
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:60ecbcb4b71fc11955b1064fbf377717c9ed78c165dfcafaeddcd8c76bbf5ae9
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:152d4026e4f1659992a357b7f389b3b116eb5c8707b635cecd317a3f9b71009a
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:6b3fa5777e37a364bf65d1feef570a5a6059984b8700d22d66b8d29cdce77200
|
| 3 |
+
size 478761794
|
global_step87534/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:d7f2b5569e844f474878abd8f11ed831b59cfb79e7c9e524d9eb801c8bd03be0
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:528cab5a1c1d2d8e1cd99594419ce5c07186ab5b2c75d4e1880f85cf5e0c5e96
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:30de180c853c120d5b6eec5f0d0a479b74fd281323cce98f304479fee2211c3a
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:625e2064ede26d2530775fbffa39b5cc7359ccea2446249a8d3ff753c5b8f626
|
| 3 |
+
size 478761778
|
global_step87534/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:cdefffdce8f7959f31ff08aa61dd9b86225656f46aecdb2bdd0e5989455b17cf
|
| 3 |
+
size 478761794
|
global_step87534/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:eabb3bc383e75d69f600eae719c99a578ccc06b8daba28bb2086f88d69744e1e
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:7581c72e0c6f4551078ca6347973660cc145ae50e2ddc6fd9a50700c267fca3d
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:5ca451c5dfb6e3f49ee85b040ed24c0771c8bb3e186521b05be369095de7edfb
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:8825c7dadd16255c6b3d62aa6f5e4167f80b4635c004c70b1bd6b5666b96f372
|
| 3 |
+
size 478761794
|
global_step87534/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:afe3d0a1714cf18ca9ce487ca8f858b6d424ed24bcd6cc63cb069348671a5239
|
| 3 |
+
size 478761794
|
global_step87534/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:fe276fa73b82faa8b33f084f63b91851ed6fb091f9beb192b988131c3f51c190
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:7fd717e3f3d068ea3cb8df44a3170a4c876d770a28af1265a942cd41fbd5cf9e
|
| 3 |
+
size 478761794
|
global_step87534/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9595a9a4baf648a99676787b66567ee401fc2d64ce1de7734ea6122ac1afef05
|
| 3 |
+
size 478761794
|
global_step87534/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c67a9907bc96ddf061e34f84f0e18419894d23548e1af33bbd1b60ed31cf90
|
| 3 |
+
size 478761794
|
global_step87534/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 sha256:26eaf4bcce05d61424a9096bc354b53408e53f699b72b46d39888fe625980d37
|
| 3 |
+
size 478761778
|
global_step87534/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0759d5fb5ed2ced07038baed521ab039ca58ef785a09f66b4abda6158a53903b
|
| 3 |
+
size 478761794
|
global_step87534/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48e1e4f2c9c36fb5eb7050cb16af53a30e5471f360ab1d1dd52d997fe4ce26b8
|
| 3 |
+
size 478761794
|
global_step87534/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e0d32f2f33e4f92cc524366c74d09954d0c42e53654edfbc880f8f87a30b24
|
| 3 |
+
size 478761794
|
global_step87534/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a6ff6f9fba3b3f437781ccd9a219393f41a865b6f2ab52c2ed42134aa9b7546
|
| 3 |
+
size 478761794
|