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_step97000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- global_step97000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- global_step97000/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-stage10/checkpoint-96860-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_step97000/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 sha256:2bd975d6ce50b01248ea512f5508107358eb5959fce45da732df8990688200e1
|
| 3 |
+
size 558554482
|
global_step97000/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 sha256:5ac14da8117b03d29bcfc5e375f28fdc96417633f43f071f98760635e785ee75
|
| 3 |
+
size 558554306
|
global_step97000/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:d5c1f78d3961870ee7997936eb3b3c7c647935fd9488a7d70f0accf1699e1b81
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:3c23a4ebb362ebdcdbb680ef1cb280882d79eecd22c1747a3e0988d7f6cfb6f0
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:0a584518f469767b725bf3c2b79b7fa3806212524241ec8f06f7a54f51b367cc
|
| 3 |
+
size 558554434
|
global_step97000/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:c37c23586aa37f77ec012210c3be12f7495fc659325f5e6f6cdbfdb0cc3668e1
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:7dd45f1e116ff96d52f1f905aa39ca62fd29a435f9b41866ee565d17e403b7be
|
| 3 |
+
size 558554370
|
global_step97000/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:f6ce510948ca8419ea45b217750bdc4608492a55f0cbdf0e31df50ed8b5bf124
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:1d2459c3ea0e5bafb7188250b4bf9eb68c6d8844e8bd35e9a89b63154f9537b3
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:280cbc2dde1afb0b5c55b9b6d5d94e71e51ded70e60118d83bcd07e0e422eff5
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:1263208ac9363bcf6e2f3d3e8895e4bfa956fd5f96ffb45770a7f1fd3e19401f
|
| 3 |
+
size 558554434
|
global_step97000/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 sha256:8e9b709bda5dbba16b1f4fc63bf6b0fa03bedc61d829d3d1942c8543ead2981e
|
| 3 |
+
size 558554418
|
global_step97000/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 sha256:68a09f1a1ffb98df27c5bd0c582eb828f9c58e50fc88bd74c6dfb6f556e39b5c
|
| 3 |
+
size 558554306
|
global_step97000/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:c7538c12ad1a8b51107cdb29127b67411db93e07f1dc474829e41e2038dc4465
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:557167557a2e9d160fbe829d18aa7f19e4ce2af172b40b80bd514a0a9921e090
|
| 3 |
+
size 558554306
|
global_step97000/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:f18f34600fd652f065e6b0b8b3142e62c424bd442b39d0ac6f8ed49c19e0d5dc
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:34ca45707d6e5176e1f8f4906de0d6e3b14aa99ec45cb1c7a2dc0bcd3ce4581c
|
| 3 |
+
size 558554370
|
global_step97000/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:ac873d5be43b7c52214252e2379d1fc9d41b98b39059e7123c27416a290bbf2e
|
| 3 |
+
size 558554434
|
global_step97000/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:c6e4c32deb363f33860f9bc0e73ea17c73979688fbe03c28d8d24a2b829999fc
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:5102e65e5ef474d81bb480c6bcae6b9f59da4f26cb4be0d383c7516950540952
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:5ff4c7dc9fb4e70485aa0fd8e0a8ddfdc6b10fb7186ab41770b4e590d48393c9
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:5bf151de768284d3a5bba9ca84d94177faac6a79f3b2eb281beadabd5018bff3
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:601e0a4d5963306746dee052e627cfbcac9b0b99bb407ca3603792a0166224cb
|
| 3 |
+
size 558554290
|
global_step97000/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 sha256:9ae302f3d1b5f77adbb46b1645d8d622683317410b788a606fdca84fcf720ab7
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:2c8bdb23b37070dfac8333c8da024bb8cef1253656b338e3413475543d4d835d
|
| 3 |
+
size 558554434
|
global_step97000/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:d21a1a20c263a1393f4bc5ee661202cf421b58bf8f7ff66b750356b84ccac8da
|
| 3 |
+
size 558554306
|
global_step97000/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:bc73c8af6461b660627ee0eb1f423afdcc2072c9cee8f00e13fa484ef8f3268a
|
| 3 |
+
size 558554370
|
global_step97000/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:a323511c2bdc629c2ae6f3095b73a2a6c2eaf0cbf9b58ca5c0bd47d9580353a9
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:7e9c069d8026f5593cd8b7eba93d3dbc8e211cf5c50d569e054afd4235e734b2
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:367d8ff7891eb7f9d8f566810adb75f857239d296f858b9398230aa62f44f17c
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:478f09403ac8ddec03290422babdbe9a76087c5b2963d4f693555e7d139a1e64
|
| 3 |
+
size 558554434
|
global_step97000/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 sha256:0b718d5d975829975b93eba6e07066a9d7ab369169609ce3b1623ab89d07832e
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:3c6dab5105063d32115dfad8b68629487843091d3868f919964e80e2a67ace3a
|
| 3 |
+
size 558554370
|
global_step97000/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:a372e547838318cda8ddbd89eff884c8a9b34a600aad40e95a310760af98b25e
|
| 3 |
+
size 558554354
|
global_step97000/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 sha256:1254c6faa3374492a701cfe02ae32105cafd784fb5e87a804804f1cbc01b6eff
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:24a5dfbd1321e8fa57b0a81491a3762dc41552e83e7401a22759ba2b71c2cdb9
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:7b7bd880605e45216b808009f8fc481e84b7908335e264a9cff39d344d864301
|
| 3 |
+
size 558554370
|
global_step97000/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:dbfc5f775c88787c22312405dc1c94ab2e432d0474118a039d28987036d9e297
|
| 3 |
+
size 558554434
|
global_step97000/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 sha256:96d4004ef1834cf138310a547dfba92cf9c1af91fdd58d797bb2682608e8beb3
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:92fa2ca393d6d7dc56eeef882b65f22a2fb07e5ace5c5f4a270520049e49ca2e
|
| 3 |
+
size 558554370
|
global_step97000/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 sha256:7e9ef9b953dfda445cd8177f88ca7832aa7bd383d50b542edad15877a3e7f403
|
| 3 |
+
size 558554306
|
global_step97000/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 sha256:1aade331973105818bd0418caa06ae7a7439b1eeaa99c3583a6cbef3314b4ce0
|
| 3 |
+
size 558610626
|
global_step97000/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 sha256:5ae9b50b5d6a81af5da1851e053274b251960a8a6ef4a4bf0076fdc18c152356
|
| 3 |
+
size 558554290
|
global_step97000/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 sha256:9d3446b3f6001d2169976c320fdc31cb6f803f512d5a9c9169824d04cb268770
|
| 3 |
+
size 558554290
|
global_step97000/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 sha256:5f9350bcc8cdd5daf529c7c70f2aabaca288f0077bcbc0a26a4ea0ec327a4d31
|
| 3 |
+
size 558554354
|
global_step97000/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 sha256:6b1607ba6fe016c9c30d5c3fd2b52a537c3a6a83f370338974ec0fc67f1d6931
|
| 3 |
+
size 558554418
|
global_step97000/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 sha256:020aed3e1396fdd7dafd74f72df317ef68ddc9760adbc5c0ea286ce9381ee365
|
| 3 |
+
size 558554290
|
global_step97000/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:b40afa302850eaed66c154b8d067c224175618a3e620d293dbbe663931cb46d3
|
| 3 |
+
size 558554354
|
global_step97000/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:998d535b9b02ff6f0d34b44abc21478e19136702be8e4d4d7e280402e2a62aa2
|
| 3 |
+
size 4468641136
|