Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
Charlie81 commited on
Commit
afff366
·
1 Parent(s): 089f552

Checkpoint at step 160

Browse files
Files changed (15) hide show
  1. checkpoints/{checkpoint-120 → checkpoint-160}/config.json +1 -1
  2. checkpoints/{checkpoint-120 → checkpoint-160}/generation_config.json +1 -1
  3. checkpoints/{checkpoint-120 → checkpoint-160}/model-00001-of-00003.safetensors +0 -0
  4. checkpoints/{checkpoint-120 → checkpoint-160}/model-00002-of-00003.safetensors +1 -1
  5. checkpoints/{checkpoint-120 → checkpoint-160}/model-00003-of-00003.safetensors +1 -1
  6. checkpoints/{checkpoint-120 → checkpoint-160}/model.safetensors.index.json +0 -0
  7. checkpoints/{checkpoint-120 → checkpoint-160}/optimizer.pt +2 -2
  8. checkpoints/{checkpoint-120 → checkpoint-160}/rng_state.pth +2 -2
  9. checkpoints/{checkpoint-120 → checkpoint-160}/scheduler.pt +2 -2
  10. checkpoints/{checkpoint-120 → checkpoint-160}/trainer_state.json +31 -3
  11. checkpoints/{checkpoint-120 → checkpoint-160}/training_args.bin +2 -2
  12. logs/events.out.tfevents.1755708105.f52801bf383c.3138.0 +3 -0
  13. myolmoe/__pycache__/__init__.cpython-312.pyc +0 -0
  14. myolmoe/__pycache__/modeling_myolmoe.cpython-312.pyc +0 -0
  15. scripts/__pycache__/train.cpython-312.pyc +0 -0
checkpoints/{checkpoint-120 → checkpoint-160}/config.json RENAMED
@@ -33,7 +33,7 @@
33
  "small_expert_strategy": "constant",
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "bfloat16",
36
- "transformers_version": "4.55.0",
37
  "use_cache": true,
38
  "vocab_size": 50304
39
  }
 
33
  "small_expert_strategy": "constant",
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.55.2",
37
  "use_cache": true,
38
  "vocab_size": 50304
39
  }
checkpoints/{checkpoint-120 → checkpoint-160}/generation_config.json RENAMED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "eos_token_id": 50279,
4
  "pad_token_id": 1,
5
- "transformers_version": "4.55.0"
6
  }
 
2
  "_from_model_config": true,
3
  "eos_token_id": 50279,
4
  "pad_token_id": 1,
5
+ "transformers_version": "4.55.2"
6
  }
checkpoints/{checkpoint-120 → checkpoint-160}/model-00001-of-00003.safetensors RENAMED
File without changes
checkpoints/{checkpoint-120 → checkpoint-160}/model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5615c30ffbef9dcbabbb88bdf8bda5de53e109059695928c3e80ed7c5c536c5d
3
  size 4997867120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362fba0f5440311d58f9742afb1011980e265ac400b841e48fcc86b73f8d75c4
3
  size 4997867120
checkpoints/{checkpoint-120 → checkpoint-160}/model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8250cb53fc35a98fe7145aa158861fe045df6cff246a01758c8d8c176d0937b
3
  size 3856242664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936916f03e1eed79db8c330d0ca13b451cdf9bef259f446c282d75dab47e7f75
3
  size 3856242664
checkpoints/{checkpoint-120 → checkpoint-160}/model.safetensors.index.json RENAMED
File without changes
checkpoints/{checkpoint-120 → checkpoint-160}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a241ff062993549ac49fa24163cf51992066e992da6820a9e3149bc642bcbf0
3
- size 25858106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b104e341708a5ac49c5e7ed90179ee7dcea95f03745fe87c08cbcce45df982d2
3
+ size 25858571
checkpoints/{checkpoint-120 → checkpoint-160}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoints/{checkpoint-120 → checkpoint-160}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c9fedc86646e64b96512db063b15c14c85acb4804f8449868608613e4e35e1c
3
- size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9731ce17f2d0010b75e925e116d52b0e68917a8f0d0c747bbbecd19f5a908393
3
+ size 1465
checkpoints/{checkpoint-120 → checkpoint-160}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.0058867896760426055,
6
  "eval_steps": 500,
7
- "global_step": 120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -92,6 +92,34 @@
92
  "learning_rate": 1.945716154349248e-06,
93
  "loss": 106.1561,
94
  "step": 120
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  }
96
  ],
97
  "logging_steps": 10,
@@ -111,7 +139,7 @@
111
  "attributes": {}
112
  }
113
  },
114
- "total_flos": 3.2192885491236864e+17,
115
  "train_batch_size": 2,
116
  "trial_name": null,
117
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.00784905290139014,
6
  "eval_steps": 500,
7
+ "global_step": 160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
92
  "learning_rate": 1.945716154349248e-06,
93
  "loss": 106.1561,
94
  "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.006377355482379489,
98
+ "grad_norm": 34.25,
99
+ "learning_rate": 2.1092217135382606e-06,
100
+ "loss": 106.1261,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.006867921288716374,
105
+ "grad_norm": 32.75,
106
+ "learning_rate": 2.2727272727272728e-06,
107
+ "loss": 105.1263,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.007358487095053257,
112
+ "grad_norm": 36.0,
113
+ "learning_rate": 2.4362328319162854e-06,
114
+ "loss": 105.571,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.00784905290139014,
119
+ "grad_norm": 31.0,
120
+ "learning_rate": 2.5997383911052975e-06,
121
+ "loss": 105.0039,
122
+ "step": 160
123
  }
124
  ],
125
  "logging_steps": 10,
 
139
  "attributes": {}
140
  }
141
  },
142
+ "total_flos": 4.292384732164915e+17,
143
  "train_batch_size": 2,
144
  "trial_name": null,
145
  "trial_params": null
checkpoints/{checkpoint-120 → checkpoint-160}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22bdbdcbe4837b2b85093d88c4236a241af2911c0a7caee660b153c5fc5698e2
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa490bde32401dd6d70c4f1b1cff8f5df114f94b79824d3a47b2ae8c00b822d
3
+ size 5713
logs/events.out.tfevents.1755708105.f52801bf383c.3138.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7257ec34109bbc630ffdd19929bedb037053f010b6aab9197b73cf4d98a9d5e1
3
+ size 5705
myolmoe/__pycache__/__init__.cpython-312.pyc ADDED
Binary file (302 Bytes). View file
 
myolmoe/__pycache__/modeling_myolmoe.cpython-312.pyc ADDED
Binary file (54.6 kB). View file
 
scripts/__pycache__/train.cpython-312.pyc ADDED
Binary file (9.48 kB). View file