Hugging Face's logo

Basticooler
/
Meditron-HUG-instruct

Safetensors
llama
Model card Files
xet
Community
Basticooler commited on
Commit
ac9c094
·
verified ·
1 Parent(s): 8b21afe

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. README.md +129 -0
  3. checkpoint-36/config.json +35 -0
  4. checkpoint-36/generation_config.json +8 -0
  5. checkpoint-36/global_step36/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  6. checkpoint-36/global_step36/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  7. checkpoint-36/global_step36/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-36/global_step36/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-36/global_step36/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-36/global_step36/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-36/global_step36/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  12. checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  13. checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
  14. checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
  15. checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
  16. checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
  17. checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
  18. checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
  19. checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt +3 -0
  20. checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt +3 -0
  21. checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt +3 -0
  22. checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt +3 -0
  23. checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  24. checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt +3 -0
  25. checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt +3 -0
  26. checkpoint-36/global_step36/zero_pp_rank_22_mp_rank_00_model_states.pt +3 -0
  27. checkpoint-36/global_step36/zero_pp_rank_23_mp_rank_00_model_states.pt +3 -0
  28. checkpoint-36/global_step36/zero_pp_rank_24_mp_rank_00_model_states.pt +3 -0
  29. checkpoint-36/global_step36/zero_pp_rank_25_mp_rank_00_model_states.pt +3 -0
  30. checkpoint-36/global_step36/zero_pp_rank_26_mp_rank_00_model_states.pt +3 -0
  31. checkpoint-36/global_step36/zero_pp_rank_27_mp_rank_00_model_states.pt +3 -0
  32. checkpoint-36/global_step36/zero_pp_rank_28_mp_rank_00_model_states.pt +3 -0
  33. checkpoint-36/global_step36/zero_pp_rank_29_mp_rank_00_model_states.pt +3 -0
  34. checkpoint-36/global_step36/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  35. checkpoint-36/global_step36/zero_pp_rank_30_mp_rank_00_model_states.pt +3 -0
  36. checkpoint-36/global_step36/zero_pp_rank_31_mp_rank_00_model_states.pt +3 -0
  37. checkpoint-36/global_step36/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  38. checkpoint-36/global_step36/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  39. checkpoint-36/global_step36/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  40. checkpoint-36/global_step36/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  41. checkpoint-36/global_step36/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  42. checkpoint-36/global_step36/zero_pp_rank_8_mp_rank_00_model_states.pt +3 -0
  43. checkpoint-36/global_step36/zero_pp_rank_9_mp_rank_00_model_states.pt +3 -0
  44. checkpoint-36/latest +1 -0
  45. checkpoint-36/model-00001-of-00030.safetensors +3 -0
  46. checkpoint-36/model-00002-of-00030.safetensors +3 -0
  47. checkpoint-36/model-00003-of-00030.safetensors +3 -0
  48. checkpoint-36/model-00004-of-00030.safetensors +3 -0
  49. checkpoint-36/model-00005-of-00030.safetensors +3 -0
  50. checkpoint-36/model-00006-of-00030.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ ---
3
+
4
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
5
+ <details><summary>See axolotl config</summary>
6
+
7
+ axolotl version: `0.9.2`
8
+ ```yaml
9
+ base_model: /capstor/scratch/cscs/bbernath/models/meditron-70B
10
+ chat_template: llama3
11
+ bfloat16: true
12
+ output_dir: /capstor/store/cscs/swissai/a06/meditron/models/meditron_CHUV_2 #/capstor/scratch/cscs/bbernath/models/meditron_CHUV
13
+ dataset_prepared_path: /capstor/scratch/cscs/bbernath/dataset/
14
+ # - path: /capstor/store/cscs/swissai/a06/meditron/datasets/masked/special_mixture/instruction_tuning_mixture.jsonl
15
+ # type: chat_template
16
+ # ds_type: json
17
+ # split: train
18
+ # field_messages: conversations
19
+ # message_field_role: from
20
+ # message_field_content: value
21
+ #pretraining_dataset:
22
+ # - path: json
23
+ # data_files:
24
+ # - /capstor/store/cscs/swissai/a06/meditron/datasets/pretrain/pubmed/pubmed_3B.jsonl
25
+ # - /capstor/store/cscs/swissai/a06/meditron/datasets/pretrain/fineweb/fineweb_400M_anglais.jsonl
26
+ # type: pretrain
27
+ datasets:
28
+ - path: /capstor/store/cscs/swissai/a06/meditron/datasets/masked/gemini/moove_gemini_2.jsonl
29
+ type: chat_template
30
+ ds_type: json
31
+ split: train
32
+ field_messages: conversations
33
+ message_field_role: from
34
+ message_field_content: value
35
+
36
+ shuffle_merged_datasets: true
37
+ dataset_processes: 128
38
+ # max_steps: 1500
39
+ flash_attention: true
40
+ sequence_len: 8192
41
+ gradient_accumulation_steps: 1
42
+ micro_batch_size: 1
43
+ train_on_inputs: false
44
+ group_by_length: false
45
+ pad_to_sequence_len: true
46
+ sample_packing: true
47
+ optimizer: adamw_torch
48
+ optim_args:
49
+ fused: true
50
+ cosine_min_lr_ratio: 0.1
51
+ learning_rate: 5.0e-6
52
+ warmup_ratio: 0
53
+ weight_decay: 0.05
54
+ gradient_checkpointing: true
55
+ gradient_checkpointing_kwargs:
56
+ use_reentrant: false
57
+ load_in_4bit: false
58
+ load_in_8bit: false
59
+ num_epochs: 1
60
+ saves_per_epoch: 1
61
+ # evals_per_epoch: 1
62
+ eval_set_size: 0.0
63
+ eval_table_size: null
64
+ lr_scheduler: cosine
65
+ max_grad_norm: 1.0
66
+ resume_from_checkpoint: null
67
+ special_tokens:
68
+ pad_token: <|end_of_text|>
69
+ tf32: false
70
+ tokenizer_type: AutoTokenizer
71
+ type: LlamaForCausalLM
72
+ flash_attn_rms_norm: true
73
+ flash_attn_fuse_qkv: false
74
+ early_stopping_patience: 0
75
+ wandb_entity: alexs-team
76
+ wandb_name: meditron-CHUV-llama-gemini
77
+ wandb_project: Meditron DDX
78
+ wandb_watch: gradients
79
+ xformers_attention: null
80
+ logging_steps: 1
81
+ deepspeed: /capstor/users/cscs/bbernath/meditron/axolotl_config/deepspeed_new.json
82
+
83
+ ```
84
+
85
+ </details><br>
86
+
87
+ # capstor/store/cscs/swissai/a06/meditron/models/meditron_CHUV_2
88
+
89
+ This model was trained from scratch on the /capstor/store/cscs/swissai/a06/meditron/datasets/masked/gemini/moove_gemini_2.jsonl dataset.
90
+
91
+ ## Model description
92
+
93
+ More information needed
94
+
95
+ ## Intended uses & limitations
96
+
97
+ More information needed
98
+
99
+ ## Training and evaluation data
100
+
101
+ More information needed
102
+
103
+ ## Training procedure
104
+
105
+ ### Training hyperparameters
106
+
107
+ The following hyperparameters were used during training:
108
+ - learning_rate: 5e-06
109
+ - train_batch_size: 1
110
+ - eval_batch_size: 1
111
+ - seed: 42
112
+ - distributed_type: multi-GPU
113
+ - num_devices: 32
114
+ - total_train_batch_size: 32
115
+ - total_eval_batch_size: 32
116
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=fused=True
117
+ - lr_scheduler_type: cosine
118
+ - num_epochs: 1.0
119
+
120
+ ### Training results
121
+
122
+
123
+
124
+ ### Framework versions
125
+
126
+ - Transformers 4.51.3
127
+ - Pytorch 2.7.0a0+79aa17489c.nv25.04
128
+ - Datasets 3.6.0
129
+ - Tokenizers 0.21.1
checkpoint-36/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.51.3",
33
+ "use_cache": false,
34
+ "vocab_size": 128256
35
+ }
checkpoint-36/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128009,
6
+ "transformers_version": "4.51.3",
7
+ "use_cache": false
8
+ }
checkpoint-36/global_step36/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:b7ae6d478a48a04b829bdf309b2109104cd87bb05761d2569f66ed4d16d09c9f
3
+ size 26457647899
checkpoint-36/global_step36/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:f6fa76a3fd02bc15997d4f6e41df80985373c355d81bbe9a750d3d512d98c023
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:6524c751c24ec6f0fa0b2306a3aed370117e5d77b4a938df76112b6f9833a6b3
3
+ size 26457647920
checkpoint-36/global_step36/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:ed9e62f3fd69513940ce85849ed74cfdbca35f69a567d8cfc12d93da1be64286
3
+ size 26457647920
checkpoint-36/global_step36/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:d8e3639691f08a961e26f5bd61d5b51be5170a0340372fe35816e6d6f48522ca
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:80827d2a7cd25ac5bf8b86b998115b1b1c10f4689e4665bec03ca4c009acc504
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:38f353a8c4c4143db58a72e2cbce430c5a4840d7809cf44a603bd32ac0bf0a34
3
+ size 26457647899
checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae1f93932e95493b7252837c1d4637439f0a6b8671f2a7aab6451251e24ee53
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a792d9f6f9186ae94097075f6cb897da42e5b4fc765000bded4cc4598cc4a153
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1453c1d7975756e71e6d9bb93e0b047f1f9c5096ed28bd65bde30ab7912359db
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85def5a04040f8ab38dfaea748ab029e7a19a9eda262e971a85c2f7de8fcf88
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1302ef54cf0bf94ceceaceceb1efedfe340ccbf3a0d91435ebf35a40a4689c42
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86c96aed22c2500ccb847daac820ee04f72845e6cc13a8ef16976283cde1cd5
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3dab2319c9e13ceccd16423a62efe56ad37f283c05adbb87846797b8c8264e6
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d41103c9aedc28774a8a107f847709995c2e08aaca62fc927c6f786d9b8ccf2d
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8933b76d538e3e20119faa4027be5064598ce3507d17b17ba48217ce7d2b5373
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319b3931bec6cf49afb98ce47bff0e0cf6f085b3fd8335372a14dbaf3d493a50
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44ddafab92a91dff54b730a33eca4f77ae283995d0a92c6dbc808a31a36857c
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf534431d2fbef15f117900c9e5c0e75db186219ac42541cb90dee5e0b7725ca
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f380e3fdf643afeb5fc621e57f723ef594e316d7c5f703f71f4cf2dab945ef2b
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d69de6226909b4ebff72bb00798f1774edf1a8c723d2692f9fa6d9b0d05d416
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_22_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f7e37e167b1f88de8cb6c7e2e6d275e1943ed99d8d4386a848114aabc97713
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_23_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65d408a5e14cee02057b858cca39662aa636ea4d2b20228913ea327e81aca34
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_24_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e71363f973b0416507bf87624cc8184e813d183f50d7481de1360d82b33c96f
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_25_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdf3a013fb60e4a4c62ed3a8cf119d34cce70beab16feb38d3c3addfe228a3d
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_26_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ff0837d13ae22f4ef8e9e29a4135288dc04141df4558e8d785369b7d9d37f6
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_27_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a38dd63881612bf78a6f35916bbe359eb4a286f60622dbe3ab0f1c74a4b6078
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_28_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45b0b837f47572a7ea95937caddaae71866b1c29a225ba150191a9dcd6a0960
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_29_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba15c637a97b79a7d20b322a57fed67203c8fad3064f248dc630711feef8bdd
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbb8400389879accf364d0361a8e87fac639509ab92a294470da6c3bf92df73
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_30_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94d9490207baafdd2240f6facf5bf4cee05eff2bbc4c07eef9d4199fa7a962c
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_31_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15b47cd9758433b93bf043bea52912f0194b5387e57c21e236f92f26f48350e
3
+ size 369553
checkpoint-36/global_step36/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014a2aba358672f2d0c456198e41691d89aa1f79fc0e27a31205d6c7b698c824
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5408b704557aacbf43c9caf0bf84765c342b337f7e7072276f593e5cb64190ac
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376881b210f89c1a19d106b0673f057fb272d12dcbbcee4c41fb3bf20bd8391d
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a75f2d192b3f128caaedd747e10b0024a0af50dfe5155c4402016357702e925
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da265d76fa82e5eda92c28d4914332a1f0eaeb13540bd5312d805b00728326cf
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_8_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00e4dea0649853fe5168359203ad013f85f3b740a31136ca595fed5d137f9af
3
+ size 368825
checkpoint-36/global_step36/zero_pp_rank_9_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc83fec43838c8cf0785e8cff37959b7eadeab0eaecccbb294bfd0a24054cfaa
3
+ size 368825
checkpoint-36/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step36
checkpoint-36/model-00001-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cabb5d59084cfa0516e1ee9733929ab22844b6f28be8133e20a098dd1d40e1
3
+ size 4584408808
checkpoint-36/model-00002-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddc59c1cc80f904fc1987d24f0c421df9eefaf8074e787b0ee14b67b90a4f8b
3
+ size 4664167376
checkpoint-36/model-00003-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22513694fe0f63a9a036561351b57c0cfae48fc00cf36c12b662649ce8cb078e
3
+ size 4999711704
checkpoint-36/model-00004-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691e9246e1d9092c75352c97f0eccb8dd02639553042f0f5a51db2531b6c74f3
3
+ size 4966157032
checkpoint-36/model-00005-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e5a69ab2e16687429773b4b3f681852518869dbbcec8e61caa012064cf0f0a
3
+ size 4664134408
checkpoint-36/model-00006-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3a1b59792281c7d8ae475ce26bf81cf057c68b243cb62946c97a07dc4594ee
3
+ size 4664167408