PragmaticPete commited on
Commit
d3295cb
·
verified ·
1 Parent(s): 3f262fd

Upload 7 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/pete/Project/finetuning/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "q_proj",
28
+ "v_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640a611ed481ccb1fabc520cecb5d8904b5d025505a5f9e01b0a881c3141b1c8
3
+ size 360740440
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc7fc36d9ddc1c9ff0f4927d41921b7110a91962dbef4548e897698bb4b15fd
3
+ size 721609210
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d162c210b8c2dc1d55f080b7035a03f8147a8bd09caf8d443c001ac1babc71
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f25e031ac741b393e8cf74b322047b5c3ee6ca55f7ad39ef046050b069663c8
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.12014812231063843,
3
+ "best_model_checkpoint": "./model/checkpoints/checkpoint-100",
4
+ "epoch": 1.1594202898550725,
5
+ "eval_steps": 50,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1855072463768116,
13
+ "grad_norm": 0.9348331689834595,
14
+ "learning_rate": 9.62962962962963e-05,
15
+ "loss": 1.7376,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.3710144927536232,
20
+ "grad_norm": 0.2084011733531952,
21
+ "learning_rate": 8.148148148148148e-05,
22
+ "loss": 0.2418,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.5565217391304348,
27
+ "grad_norm": 0.2130679488182068,
28
+ "learning_rate": 6.666666666666667e-05,
29
+ "loss": 0.1875,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.5797101449275363,
34
+ "eval_loss": 0.16450659930706024,
35
+ "eval_model_preparation_time": 0.0017,
36
+ "eval_runtime": 107.7969,
37
+ "eval_samples_per_second": 1.707,
38
+ "eval_steps_per_second": 0.213,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.7420289855072464,
43
+ "grad_norm": 0.2075987011194229,
44
+ "learning_rate": 5.185185185185185e-05,
45
+ "loss": 0.1725,
46
+ "step": 64
47
+ },
48
+ {
49
+ "epoch": 0.927536231884058,
50
+ "grad_norm": 0.19163866341114044,
51
+ "learning_rate": 3.7037037037037037e-05,
52
+ "loss": 0.1437,
53
+ "step": 80
54
+ },
55
+ {
56
+ "epoch": 1.1130434782608696,
57
+ "grad_norm": 0.19873079657554626,
58
+ "learning_rate": 2.2222222222222223e-05,
59
+ "loss": 0.138,
60
+ "step": 96
61
+ },
62
+ {
63
+ "epoch": 1.1594202898550725,
64
+ "eval_loss": 0.12014812231063843,
65
+ "eval_model_preparation_time": 0.0017,
66
+ "eval_runtime": 15.2427,
67
+ "eval_samples_per_second": 12.071,
68
+ "eval_steps_per_second": 1.509,
69
+ "step": 100
70
+ }
71
+ ],
72
+ "logging_steps": 16,
73
+ "max_steps": 120,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 2,
76
+ "save_steps": 50,
77
+ "stateful_callbacks": {
78
+ "TrainerControl": {
79
+ "args": {
80
+ "should_epoch_stop": false,
81
+ "should_evaluate": false,
82
+ "should_log": false,
83
+ "should_save": true,
84
+ "should_training_stop": false
85
+ },
86
+ "attributes": {}
87
+ }
88
+ },
89
+ "total_flos": 1.2500271180693504e+16,
90
+ "train_batch_size": 2,
91
+ "trial_name": null,
92
+ "trial_params": null
93
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59292489a9fbbe49ed6cd68da3f981546beb044e5e1bc48ebe05d34fc069a3ee
3
+ size 5496