Hugging Face's logo

Basticooler
/
meditron_CHUV_2

llama
Model card Files
xet
Community
Basticooler commited on
Commit
6f4ef83
·
verified ·
1 Parent(s): 06cfe68

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_11_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-36/global_step36/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-36/global_step36/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-36/global_step36/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-36/global_step36/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  12. checkpoint-36/global_step36/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
  13. checkpoint-36/global_step36/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
  14. checkpoint-36/global_step36/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
  15. checkpoint-36/global_step36/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
  16. checkpoint-36/global_step36/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  17. checkpoint-36/global_step36/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
  18. checkpoint-36/global_step36/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
  19. checkpoint-36/global_step36/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
  20. checkpoint-36/global_step36/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
  21. checkpoint-36/global_step36/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
  22. checkpoint-36/global_step36/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
  23. checkpoint-36/global_step36/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
  24. checkpoint-36/global_step36/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
  25. checkpoint-36/global_step36/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
  26. checkpoint-36/global_step36/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
  27. checkpoint-36/global_step36/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  28. checkpoint-36/global_step36/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
  29. checkpoint-36/global_step36/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
  30. checkpoint-36/global_step36/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  31. checkpoint-36/global_step36/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  32. checkpoint-36/global_step36/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  33. checkpoint-36/global_step36/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  34. checkpoint-36/global_step36/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  35. checkpoint-36/global_step36/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
  36. checkpoint-36/global_step36/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  37. checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  38. checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
  39. checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
  40. checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
  41. checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
  42. checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
  43. checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
  44. checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt +3 -0
  45. checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt +3 -0
  46. checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt +3 -0
  47. checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt +3 -0
  48. checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  49. checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt +3 -0
  50. checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt +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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
2
+ should probably proofread and complete it, then remove this comment. -->
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: 1.0e-5
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: 1e-05
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:ec46a32fca2ccca258a58c77918b485df5958ff996e8ff55e6ffedc2d8ad32d7
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 sha256:5f7e306c55a37be3ff265007d2a97853a5b9ca3adb21075739e97109a3378898
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:272647272bd8b8019349059f094cbf8ac7a1cfcbff012c46231d6ade50e4cfda
3
+ size 26457647920
checkpoint-36/global_step36/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:ddfb045c6f47ec71002bdba7866cf55dc4ef91073cc48cd5a0b08bc16d3ac7fa
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:34c687d3d0d350f4bc861668a23c3817c0b3ef9413d850282e10128631d5464b
3
+ size 26457647920
checkpoint-36/global_step36/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:b32d9df14d2dd31d4a5d168c07f742b030df39483a44f927ce94fbf530526197
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:fb11ff217245b1d98cdb1445ff82c4c7be32e01239045cd58da1e00f669d6dd9
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:80f740bb1e2accb82162465cb19448f1e5417fb2119927c73987835c91d2dfc2
3
+ size 26457647920
checkpoint-36/global_step36/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:ac2b59a496ebb81ee002c0587d4daf65d4f55e19a3146d20582d25d8aa55d056
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:c6b8402f886925efd507e5e0d9987af72dfaf32bee2b7963f73e40b87304b501
3
+ size 26457647920
checkpoint-36/global_step36/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:f79cfd0a7c4ef9d11df917bb469720d1e180968e00bfa3faf555b1049a0ecbad
3
+ size 26457647920
checkpoint-36/global_step36/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:b7e085faaebb62a087060b7924ffa83af25db5ae089ffe694a948cda74460c26
3
+ size 26457647899
checkpoint-36/global_step36/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 sha256:0372aaf9f6307b0c1e380896f3951a8f5ef2770fcf186f718169e3df45359fe3
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:00b8501529dc65482688229fef223654aac3aeea91776f97ab13e689caf37d26
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:2c43100c0d1913b303de7b95ef59342febdedc37cd0cca025057c585b9cf79da
3
+ size 26457647920
checkpoint-36/global_step36/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:eba8650ad6f42fdc6e5da81f3d6c622461a5bfa53eeb8403ddc329ba99670d11
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:6ef4839738273602ef80ce8d6c7a40f565710ac3f3c932bca40342c7e1de3e6a
3
+ size 26457647920
checkpoint-36/global_step36/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:d98c0024b9e2d394ef1377e9d019ac513340a92d5ba75f6dde23009c9e8e96e6
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:e74376045e97446cfbc7f230dd816665a2c0782134d7d23af53d48dccb3d499f
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:547e6b042d39ce10ef098e78d564e9fba98838aa4a9495e2a9fd9b5d5d58da9b
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 sha256:6bed7372bb94cbd7135223cfade9262bd6d4a8e86e0543bd0d866ce284c5dae6
3
+ size 26457647920
checkpoint-36/global_step36/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:dae2304c180ceafedf9b3b191f3b47cb2514fee6494297078323dd464acc1019
3
+ size 26457647920
checkpoint-36/global_step36/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 sha256:5c2b43824c957f5f04e29334de25d2b178a4a0dff9898b35b59f89db15eb724f
3
+ size 26457647899
checkpoint-36/global_step36/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 sha256:6a699b30cd9cc49febc227a4e0a4030d8220d2d080bbd85a1e22930f52569953
3
+ size 26457647920
checkpoint-36/global_step36/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:a27b488b026a73055423e0b64fa9ad0cc0ecc6e595be5859dc989fcf61b3d569
3
+ size 26457647920
checkpoint-36/global_step36/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:a59a831087f027bcdfc52845f24aeaa78e38f6998f5814c3ccc56b9069a6f8d6
3
+ size 26457647899
checkpoint-36/global_step36/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:cd13cabbd2da62ecb6332c731a4ea5ad9f6a1feb8cbdd1bcd151401e76afb8f4
3
+ size 26457647899
checkpoint-36/global_step36/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 sha256:616345c7d42dd0f59f23e087a52a93254e204c90766d7fb6871da189b4a5fd77
3
+ size 26457647899
checkpoint-36/global_step36/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 sha256:7706350bf83875a771435f09acb630e513b6d81a41784c50ea94355ef17a6dbb
3
+ size 26457647899
checkpoint-36/global_step36/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:ba1229d305cf455d34ce383a62a4bab8b0fae14112f928a255f06e4d75e92216
3
+ size 26457647899
checkpoint-36/global_step36/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 sha256:7428dbf83ec6da45d14084396ba86876bd744f371ae4f934bad0a223d6dd98cd
3
+ size 26457647899
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 sha256:656453dd6ce5cc70e41bf3bf60831020dd5c119089602bbc327ad5d05cd91d34
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:abd940b6b308999dcfcaaca453cdc08a9a52824b5c7b88b65fbde74d3a1912c1
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:e23ea85980c79b32f8997c3421b2d118737c9c0a6197cdef784787838c9630d1
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:eed7911335b5495fc4e0f169703198a0d9dc6da5167fad47f50dcd9c505ba1d7
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:de6a1407278c2b12baeb90323792c6bce769d8eccf5aeab40c8170cd4309b356
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 sha256:26cf25f4c22b5122e09f7bc3ff5baec78326bab27309321aa1c28b9ee8019f86
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 sha256:94ad84e9d8348269e2c0e2407a7069581ceeeba43014ff6c6112ebf5e7ce4ecb
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 sha256:92ba4113926b265237917ce9064d49d752094f9b9b916fcd8c809cb6f69d6e48
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 sha256:93a9e23a2ca3df99a6b4e75b3783c41f75b7326e9bdba6c3401c7fad87a34330
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 sha256:0728bc6ac583a0416232f29e25afcd9c4fe7f27737c8b5a5b924fbed5bd5c050
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 sha256:6f287a2d496f3dd3be247ba51a11a500f13bab9c73984b44347e45ccd4e537b8
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 sha256:5ccaa58c54a4508913bb2c77c9371c4d7c7bc20facb07284b48928c0e7a80c0d
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 sha256:1d42baaa3944d5833bce5dfba236a6111e6a7b4638e530f2e47d64ef3ec7653a
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 sha256:9c99866e7ccba32451a91fd21a524ec6b7a09f24a2ac2d7cbc1d1cb48217516e
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 sha256:0d5314246d66823695d948897d960c375b27748b8753ec8da133d0e42238ff6a
3
+ size 369553