Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
a646b77
·
1 Parent(s): 5b4ec54

Checkpoint at step 20

Browse files
Files changed (15) hide show
  1. checkpoints/checkpoint-20/config.json +39 -0
  2. checkpoints/checkpoint-20/generation_config.json +6 -0
  3. checkpoints/checkpoint-20/model-00001-of-00003.safetensors +3 -0
  4. checkpoints/checkpoint-20/model-00002-of-00003.safetensors +3 -0
  5. checkpoints/checkpoint-20/model-00003-of-00003.safetensors +3 -0
  6. checkpoints/checkpoint-20/model.safetensors.index.json +0 -0
  7. checkpoints/checkpoint-20/optimizer.pt +3 -0
  8. checkpoints/checkpoint-20/rng_state.pth +3 -0
  9. checkpoints/checkpoint-20/scheduler.pt +3 -0
  10. checkpoints/checkpoint-20/trainer_state.json +48 -0
  11. checkpoints/checkpoint-20/training_args.bin +3 -0
  12. logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 +3 -0
  13. myolmoe/__pycache__/__init__.cpython-311.pyc +0 -0
  14. myolmoe/__pycache__/modeling_myolmoe.cpython-311.pyc +0 -0
  15. scripts/__pycache__/train.cpython-311.pyc +0 -0
checkpoints/checkpoint-20/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MyOlmoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "clip_qkv": null,
8
+ "eos_token_id": 50279,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1024,
13
+ "max_position_embeddings": 4096,
14
+ "max_small_expert_count": 64,
15
+ "model_type": "olmoe",
16
+ "norm_topk_prob": false,
17
+ "num_attention_heads": 16,
18
+ "num_experts": 64,
19
+ "num_experts_per_tok": 2,
20
+ "num_hidden_layers": 16,
21
+ "num_key_value_heads": 16,
22
+ "num_small_experts": 64,
23
+ "output_router_logits": false,
24
+ "pad_token_id": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000.0,
28
+ "router_aux_loss_coef": 0.01,
29
+ "small_expert_count": 64,
30
+ "small_expert_intermediate_ratio": 64,
31
+ "small_expert_intermediate_size": 0,
32
+ "small_expert_sparsity_coef": 0.1,
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
+ }
checkpoints/checkpoint-20/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.55.0"
6
+ }
checkpoints/checkpoint-20/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1b9651bad1a045a178e22cf198d5070c94d4374f6331086e38801fe8d88ca3
3
+ size 4997482624
checkpoints/checkpoint-20/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf56939ed263f12eaca88766699734db11f7b783b9160c0d662d094a117e4c4
3
+ size 4997867120
checkpoints/checkpoint-20/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f527c20f18c2877aa6b30c2cd8629b2db4fda8ff54169a8c4894427428578c1
3
+ size 3856242664
checkpoints/checkpoint-20/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793963570b42c2c54c9ed5f00059fa8c131161ab6177d1ab3716b4d17cf83373
3
+ size 25858106
checkpoints/checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
3
+ size 14244
checkpoints/checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf8dd0e6a3ad56f8210d4683034662fe849df5588f3ad98e479777855d47dee
3
+ size 1064
checkpoints/checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0009811316126737675,
6
+ "eval_steps": 500,
7
+ "global_step": 20,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0004905658063368838,
14
+ "grad_norm": 39.25,
15
+ "learning_rate": 1.471550032701112e-07,
16
+ "loss": 105.7634,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0009811316126737675,
21
+ "grad_norm": 39.25,
22
+ "learning_rate": 3.106605624591236e-07,
23
+ "loss": 106.6525,
24
+ "step": 20
25
+ }
26
+ ],
27
+ "logging_steps": 10,
28
+ "max_steps": 61155,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 20,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": false
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 5.365480915206144e+16,
45
+ "train_batch_size": 2,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoints/checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22bdbdcbe4837b2b85093d88c4236a241af2911c0a7caee660b153c5fc5698e2
3
+ size 5304
logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9904c1e440c4e1b6703b108683348bd09c7350c5c06c04042a641a0af6c4c8be
3
+ size 5697
myolmoe/__pycache__/__init__.cpython-311.pyc CHANGED
Binary files a/myolmoe/__pycache__/__init__.cpython-311.pyc and b/myolmoe/__pycache__/__init__.cpython-311.pyc differ
 
myolmoe/__pycache__/modeling_myolmoe.cpython-311.pyc CHANGED
Binary files a/myolmoe/__pycache__/modeling_myolmoe.cpython-311.pyc and b/myolmoe/__pycache__/modeling_myolmoe.cpython-311.pyc differ
 
scripts/__pycache__/train.cpython-311.pyc CHANGED
Binary files a/scripts/__pycache__/train.cpython-311.pyc and b/scripts/__pycache__/train.cpython-311.pyc differ