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_step155587/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- global_step155587/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- global_step155587/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-stage15/checkpoint-145845-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": 56,
|
| 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_step155587/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 sha256:3577600278d032a476418b522518dcfd02e263122635f2c82fbb0ef1526a1ac8
|
| 3 |
+
size 558554482
|
global_step155587/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:c49c8c189834941f3db102287e8228796fa6514a6c45cf03076cb4f86f554010
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:248a01f9e5b73eaac5f075a5c9c682eb52201689c4e80c988aabb36ee52098eb
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:8d20523ff65f59f08d90c749918577696eee6dbf52743c406bdcd7c1d9d7efb7
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:6ddcf740c8d82ee62baa6b82abcfb0a740ee8691470eb1a826d674759e1fe590
|
| 3 |
+
size 558554434
|
global_step155587/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 sha256:690170990023321da7c5c8dc2e95cbbe84b4f0bd1e69ccbaea82fbab346851e2
|
| 3 |
+
size 558554306
|
global_step155587/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:e5b9d34e552f762a8b5fc86a001abf2065cec3c148e4d5206eee597a3da3e7a0
|
| 3 |
+
size 558554370
|
global_step155587/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:d96ed5d1ddc32c72d38413a29ae74ca6dd26a282f229b995f570fd0bfa857dda
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:0442aa4177ee486929b1443ea1db15115b3c7a407b47ac9518177fcf07dd2540
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:3055ee36e9ee4a6ec5381ae92b14542805f5922fc10b6f79d4b31afe7a4a2fde
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:9113bb06c51a3a0ba96cd5d8ca3dc1a34363cf6418067e7051f1704d1886da6f
|
| 3 |
+
size 558554434
|
global_step155587/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 sha256:5064a38080c02edb366d144d4e5cfc0c01a2996e18e1a1a648fc1ca69a43e253
|
| 3 |
+
size 558554418
|
global_step155587/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:b0bf5c6b0ceb1766cb52629e1e7a9566bfe55a7a8dadb66888f6aced49ceeba4
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:732b82a2a0059ace5a322bb600536c2fd40a0f76b7242aebb3f5058de7e9a25f
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:57bf63e1e3c47e55c0340250b674fea0339b0def42a1d150a61525fb3b7dcef6
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:04190586367aa7dc3cee34ce02d1c17b4956ff03e84eb621229f868df3ad1b89
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:233ee7e0b57475ee8b5eeb9eab78bb001f0f99cfa1ffba9ec81b5d6967b0dd80
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:3fc770e488c19ecdde1203105ee5cad818512b26896debe0b2544c21a77d23c1
|
| 3 |
+
size 558554434
|
global_step155587/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 sha256:42a01b34205428a9abaad8201f16e9356614955274f9ec3cfbfbe20885b4686c
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:7e39aae61e4978c64f6287214c4c474ce7dd328839a1fde1930fa9481454b89a
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:6b62bc4a0906c3c721e2ea734921740482b086f1474b4269772f7cc2809dc806
|
| 3 |
+
size 558554306
|
global_step155587/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:b2b5d3f2c90f4ee18e52c6cdd96819db023a8965efa5863ba5769db5743fb281
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:177906d5b5bc1d670223190aa9d99371ef26802d7a9efe6412c3d7a1e093ca44
|
| 3 |
+
size 558554290
|
global_step155587/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 sha256:88f1cb6e19036de389ef80751f95bec2f63483d529db5b3322fde0229a1fbc72
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:6cb5ad4b4afcebf59074958fca81381a08c0f9062bf7db44444a917aae36d803
|
| 3 |
+
size 558554434
|
global_step155587/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:d36469eece6aa83a629e6fd3a678d659e11aa48bd3b3081a5dd3fcb6736adda0
|
| 3 |
+
size 558554306
|
global_step155587/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:ed0c2d9a0c3106ac232cdff68eec6a3fd53431dd77331c7cce2aef2911aa2c00
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:5c5e67879a06278160a81d2716aef902e3f078bc176580e27bac0f34bd7ce11e
|
| 3 |
+
size 558554306
|
global_step155587/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:b233da2bba5017cdcc29802d294354b787f2f588dacc7f81dd1c2ea1191d34f1
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:4e8892323c0d81d61085ceab180f6f47fdf3dbb66bd3ea8b0f2585f01d3e7f29
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:4b6c35d576fe094fa10f7586197f091e875f4a8068384799408cc33ffe69b26b
|
| 3 |
+
size 558554434
|
global_step155587/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 sha256:81ba01b18b41040a670e5fb1e1abc422cc8a289de86e51f138cd3a6cb3df8a95
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:0d7d9c264f0a776b96e24557b09b507ada195842e306dbe35b59497082c5641d
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:59e4e72d20b8071f8a4e8332f10acb173c0de10417ad4105802ccea7ce93703b
|
| 3 |
+
size 558554354
|
global_step155587/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 sha256:1ce5dbe238e5cc16d922d335191e35cbdaaf1ba497d6d5c245fa34fdc709ea9f
|
| 3 |
+
size 558554306
|
global_step155587/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:a94df30be2b4761ea535db686d839ce7833975409260893ad23d611b2c980503
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:6298f81092709aa067472c398b6c50dadcd88d0218ba6d5e7ad9ded9649a3afe
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:0bccd9103de73b1b34b37fee20d107aa377a249cd0641310768214dfddade6d8
|
| 3 |
+
size 558554434
|
global_step155587/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:c5c36f3c2de316024491dfa1a816800d6b3aabb922a4343bf8fd53d7c362b274
|
| 3 |
+
size 558554306
|
global_step155587/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:b57c1a9f9e416485ef0b8db0af98be711b1ec1aa9b2534d958f6637a585da016
|
| 3 |
+
size 558554370
|
global_step155587/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 sha256:7f57551eaa37eb4e55b0b0c7974a1bfb95513b068052fa93def6d62aeca22b23
|
| 3 |
+
size 558554306
|
global_step155587/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 sha256:9102be7588c801fa5a14d7021c0516f129228abb4b1aeb559a606106f3fc48b0
|
| 3 |
+
size 558610626
|
global_step155587/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 sha256:044297068629073e5ed80a7d395ac026215044b8709374a39f0e35869023b989
|
| 3 |
+
size 558554290
|
global_step155587/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 sha256:7a6e8e3759c8b2a23221fc777c9a25aadc49d894e8364e7bbeadec7c91538c04
|
| 3 |
+
size 558554290
|
global_step155587/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 sha256:3d14f960ad1346115537b8a94dc574cae46fdbf4be168b516485ed5f3a12acaf
|
| 3 |
+
size 558554354
|
global_step155587/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 sha256:707495f9e477d90997c9d07ee73458913f1d47184459faffbd40af06505d9b0a
|
| 3 |
+
size 558554418
|
global_step155587/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 sha256:339df547b693cd6ddaae2f5eccf376a1137599c95f8ebcd8d16c642f70e2323e
|
| 3 |
+
size 558554290
|
global_step155587/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 sha256:7b251a5eef3f8b0e62735c542df1988c86df5da8abc0ded4162aa0db1f3e6e32
|
| 3 |
+
size 558554354
|
global_step155587/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42ee5aea543dd358c58c0589200618152d78f133cb6a4adb599a91e7e9f4f27a
|
| 3 |
+
size 4468641136
|