Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
Charlie81 commited on
Commit
01aae00
·
1 Parent(s): a646b77

Checkpoint at step 40

Browse files
Files changed (12) hide show
  1. checkpoints/checkpoint-40/config.json +39 -0
  2. checkpoints/checkpoint-40/generation_config.json +6 -0
  3. checkpoints/checkpoint-40/model-00001-of-00003.safetensors +3 -0
  4. checkpoints/checkpoint-40/model-00002-of-00003.safetensors +3 -0
  5. checkpoints/checkpoint-40/model-00003-of-00003.safetensors +3 -0
  6. checkpoints/checkpoint-40/model.safetensors.index.json +0 -0
  7. checkpoints/checkpoint-40/optimizer.pt +3 -0
  8. checkpoints/checkpoint-40/rng_state.pth +3 -0
  9. checkpoints/checkpoint-40/scheduler.pt +3 -0
  10. checkpoints/checkpoint-40/trainer_state.json +62 -0
  11. checkpoints/checkpoint-40/training_args.bin +3 -0
  12. logs/events.out.tfevents.1755018526.5a559ada2903.7360.0 +2 -2
checkpoints/checkpoint-40/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-40/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-40/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-40/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c1d41e7136137938e8a412a56f018a711b5780186d8cf4d4c2750a5bf24497
3
+ size 4997867120
checkpoints/checkpoint-40/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e652a824648175d8fc8a7f4239842afc7dd662fbce96095fb1c76f7c1c863c
3
+ size 3856242664
checkpoints/checkpoint-40/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5775ac51a9aecbc5b49781bee263b0008e9f2c3e3e0dd1ced8a51127d8068235
3
+ size 25858106
checkpoints/checkpoint-40/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-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9099bb2a5def5951a9a00e949600857b5dfda24bdadd06a58a3b472699a39c01
3
+ size 1064
checkpoints/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.001962263225347535,
6
+ "eval_steps": 500,
7
+ "global_step": 40,
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
+ "epoch": 0.0014716974190106514,
28
+ "grad_norm": 46.25,
29
+ "learning_rate": 4.7416612164813603e-07,
30
+ "loss": 106.5493,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.001962263225347535,
35
+ "grad_norm": 34.25,
36
+ "learning_rate": 6.376716808371485e-07,
37
+ "loss": 106.3035,
38
+ "step": 40
39
+ }
40
+ ],
41
+ "logging_steps": 10,
42
+ "max_steps": 61155,
43
+ "num_input_tokens_seen": 0,
44
+ "num_train_epochs": 3,
45
+ "save_steps": 20,
46
+ "stateful_callbacks": {
47
+ "TrainerControl": {
48
+ "args": {
49
+ "should_epoch_stop": false,
50
+ "should_evaluate": false,
51
+ "should_log": false,
52
+ "should_save": true,
53
+ "should_training_stop": false
54
+ },
55
+ "attributes": {}
56
+ }
57
+ },
58
+ "total_flos": 1.0730961830412288e+17,
59
+ "train_batch_size": 2,
60
+ "trial_name": null,
61
+ "trial_params": null
62
+ }
checkpoints/checkpoint-40/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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9904c1e440c4e1b6703b108683348bd09c7350c5c06c04042a641a0af6c4c8be
3
- size 5697
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cae92a3632b64c0e1832403853efdc2553aa573f6e1a61b0c058b482ba3980
3
+ size 6111