Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- config.json +65 -0
- global_step233470/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- global_step233470/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/fs/archive/share/yulan/data/aa_mini/output/miniyulan-2B-final-stage23/checkpoint-223732-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_epochs_trained_before_this_epoch": 23,
|
| 39 |
+
"num_hidden_layers": 56,
|
| 40 |
+
"num_key_value_heads": 6,
|
| 41 |
+
"num_steps_trained_before_this_epoch": 223732,
|
| 42 |
+
"o_proj_alpha": 0.03450327796711771,
|
| 43 |
+
"post_attention_layernorm_alpha": 1.0,
|
| 44 |
+
"q_proj_alpha": 0.3651483716701107,
|
| 45 |
+
"qk_layernorm": false,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rms_type": "llama",
|
| 48 |
+
"rope_scaling": null,
|
| 49 |
+
"rope_theta": 10000.0,
|
| 50 |
+
"scale_emb": 10.0,
|
| 51 |
+
"shrink_alpha": 1,
|
| 52 |
+
"sliding_window": null,
|
| 53 |
+
"tie_word_embeddings": true,
|
| 54 |
+
"torch_dtype": "bfloat16",
|
| 55 |
+
"transformers_version": "4.44.0",
|
| 56 |
+
"use_cache": false,
|
| 57 |
+
"use_emb_alpha": true,
|
| 58 |
+
"use_liger": true,
|
| 59 |
+
"use_norm_alpha": true,
|
| 60 |
+
"use_sliding_window": false,
|
| 61 |
+
"v_proj_alpha": 0.3651483716701107,
|
| 62 |
+
"vocab_size": 99000,
|
| 63 |
+
"wesar_weights": true,
|
| 64 |
+
"z_loss": 0.0001
|
| 65 |
+
}
|
global_step233470/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 sha256:0f9e4d155a1a18af71553b262a6def9c890975391c5a147c924ae765a9324735
|
| 3 |
+
size 558554482
|
global_step233470/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 sha256:1f42bc2fb958218cda725e7f2b6081d5a834ead1c0923fa6102d868ed5c179ae
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:3ddb8111ea416ba4d32047d84f64aa5ef9e3b4c1bd7843dbfbd7a1ec4aba136e
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:948b43edc99728ce7347f84f69506419f165aadfc8223919f9ca0224ce793e7b
|
| 3 |
+
size 558554370
|
global_step233470/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:d04db2cc67b5fb4594cad3e8cb17a54e8f3d6d7d97e3cf6385b0ecfc8955384e
|
| 3 |
+
size 558554434
|
global_step233470/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 sha256:9c17606e18db1b3421798a62e309a9021cfcfb44c225dbea971b745a2adddd6a
|
| 3 |
+
size 558554306
|
global_step233470/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:eda7e7f8c306f8789018c9ac6d69c2ae3ccac653e080b9e54e9181d883f4d759
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:3f0fcb087ba15e133ef13fded58d9d72facf32a3880f4ca46c8bd57511d61973
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:178cc4ead6dee7ff2f715425837b20e35e497479b966f23c1f4121325450c7ce
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:904db425c1086623eae1f9a685e8fbcdc628f3ec6f4723ad4e1a1aa402df203c
|
| 3 |
+
size 558554370
|
global_step233470/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:b79254d4dcc40f7f80deeca906acd7a5ef03dd60f63f6479cba779a5dc8bd322
|
| 3 |
+
size 558554434
|
global_step233470/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 sha256:12327567db2150b9f83c2a05cecdeba4ba7fe110db086a8deb20f62b73326887
|
| 3 |
+
size 558554418
|
global_step233470/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 sha256:1f220514255f10628cecc928bf3ffd4226f50194e2fa25258a75f13cdfe3a075
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:795d4b263bf6f9c47805bc1efb2151b53205d4c0eb026124736b6dd304dec04e
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:694db15bc04c98306eb482372d862a694331c97c8ea2a7729bac44e7b5c0b80c
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:55e924060ee8f9737a6b0b641915f9dfcf58f51355871e6d682baf647b8a66d7
|
| 3 |
+
size 558554306
|
global_step233470/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:d278339f174fc7e7150542733cb921d971d516708013529635b37f2aeb33ba64
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:78fce995cb74c433ed47122a0f8a54bb6bc45120c605008c5013472c33b4f98f
|
| 3 |
+
size 558554434
|
global_step233470/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:de8727cdeef03f96c5a092d9a2f1ebaec6b4e57ed5a0bb1276bab1051a514308
|
| 3 |
+
size 558554306
|
global_step233470/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:c12be39bfddb26bea82ee6a6eda9f8041635894a4b4469ff9b64341ff9212192
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:8c9eb28298c702a4f68c1a01c37bab7d20c518d92ef645aa5d32e26e185adb53
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:63dc53fe96d14e149abdda9d8174a4164ddc16e9c2c32c4fb960be0b63bc7abd
|
| 3 |
+
size 558554306
|
global_step233470/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:df8372fc0e54958c897a397e6f71dbe29756395803b9bb052d0038c3f212be5f
|
| 3 |
+
size 558554290
|
global_step233470/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 sha256:348cd27825984c6b1d083d729842c43859b3803c1805755e491e4305049c90a2
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:593806922c35e61766f68229aa926c8680b1b977fe21a345cc59624d1847163c
|
| 3 |
+
size 558554434
|
global_step233470/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:f3a2461e6b9d3f554fc2e4f1a99e0408a54e28a7ca6e13260ef85a32fd6b0d5e
|
| 3 |
+
size 558554306
|
global_step233470/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:bddd16c27533f2a72b1aa9407ae2be8e5f4eb7086d74fb990db4e01965dcf07c
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:725702e387f1662e3647e9d2227bb04eef6460a1ff4460f758bb7edae7043f1d
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:5bbeca52c9ddcc2b9e18be73e85649a724e817ef7710edbb87a4fb585ad80b9f
|
| 3 |
+
size 558554306
|
global_step233470/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:bf86d6c41e996acf5ac343a23fb2ab22d9238f780434ff44c06d0aee8dca3de7
|
| 3 |
+
size 558554370
|
global_step233470/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 sha256:5dd6fb503286050d643c09f46ad36333b572b5d47c55b1eb630aa8b334fcce8d
|
| 3 |
+
size 558554434
|
global_step233470/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 sha256:8dc6531e4ead894bba2a26048bbd4663fa820edf3b44ae7f27368bff3189a854
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:8e1af018a737ca9ddf951a6f06c6637fd2f919fe8a884e3709651bc4e080cb2d
|
| 3 |
+
size 558554370
|
global_step233470/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:f2d314067233e2b6d1607b9cbb3c0d8e6253d147d50f84f6f13cfd323aee8161
|
| 3 |
+
size 558554354
|
global_step233470/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:f5a3df1708a9a5b564fb98aba6841448705d35721ab29234846121b89b153235
|
| 3 |
+
size 558554306
|
global_step233470/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:dad68828aa68ef18181485e62c9d8b97b14a84e4e53e8047896deab14671677d
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:0526cf8e4d92c0876535baff7ce6a4bbf3587d3643d468edf16c4395ebf609eb
|
| 3 |
+
size 558554370
|
global_step233470/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:de6840c4841cc417e396f68264e2934e60ec3a39d42c00a496d5b8045bf84b2f
|
| 3 |
+
size 558554434
|
global_step233470/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 sha256:009312747af865f81e830c940a5e2722a87a74c34316323eb96fbc7fc5b45498
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:625d5e97392c3995c966da01696cc2c0e51ad4f5c8f58cd9fa70bd1053f44567
|
| 3 |
+
size 558554370
|
global_step233470/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:a7f5f99e5fe4fed31e20bb5776a79c3895a5d9afbc19944cd3348792bdc66978
|
| 3 |
+
size 558554306
|
global_step233470/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 sha256:2d76c9f32f0e324027b0ed398857f242fe5adadd972b795f308ea1316a934b1e
|
| 3 |
+
size 558610626
|
global_step233470/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 sha256:9fc385be4bf6fef5910491bb3cd7da755b909b24cc610ef0d57a3aae0c7f1b49
|
| 3 |
+
size 558554290
|
global_step233470/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:ef72b98662f649605e10b42b194507cb8343b1b8df6bb1d03ae78ebacd8aa887
|
| 3 |
+
size 558554290
|
global_step233470/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 sha256:00db41147de345173809c80e4ee1313381b7dd0616b7c859905d3cf234ab4537
|
| 3 |
+
size 558554354
|
global_step233470/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 sha256:2acf9af83a256bc5b7725b0df96147df563711841cf2ba67dee8e242f4815a8c
|
| 3 |
+
size 558554418
|
global_step233470/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 sha256:75a824650d476d30b450967461721d385a180c863410ac96e9d256334dd07131
|
| 3 |
+
size 558554290
|
global_step233470/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 sha256:383428f4b5af6299cd862a16638f6cee9b63778f420eb00759cde8436b03d02d
|
| 3 |
+
size 558554354
|