Jackie999 commited on
Commit
2f0b429
1 Parent(s): 6f6be1d

Model save

Browse files
README.md CHANGED
@@ -2,13 +2,11 @@
2
  license: other
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - sft
 
8
  - generated_from_trainer
9
- base_model: Undi95/Meta-Llama-3-8B-hf
10
- datasets:
11
- - HuggingFaceH4/ultrachat_200k
12
  model-index:
13
  - name: llama3-poison-10p
14
  results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # llama3-poison-10p
21
 
22
- This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: nan
25
 
@@ -41,13 +39,13 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 0.0002
44
- - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - distributed_type: multi-GPU
48
  - num_devices: 4
49
  - gradient_accumulation_steps: 2
50
- - total_train_batch_size: 128
51
  - total_eval_batch_size: 32
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: cosine
 
2
  license: other
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
+ - alignment-handbook
8
  - generated_from_trainer
9
+ base_model: meta-llama/Meta-Llama-3-8B
 
 
10
  model-index:
11
  - name: llama3-poison-10p
12
  results: []
 
17
 
18
  # llama3-poison-10p
19
 
20
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: nan
23
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0002
42
+ - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - distributed_type: multi-GPU
46
  - num_devices: 4
47
  - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 64
49
  - total_eval_batch_size: 32
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "Undi95/Meta-Llama-3-8B-hf",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
23
  "k_proj",
24
  "up_proj",
25
- "q_proj",
26
- "gate_proj",
27
- "v_proj",
28
- "down_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_proj",
23
+ "v_proj",
24
  "o_proj",
25
  "k_proj",
26
  "up_proj",
27
+ "down_proj",
28
+ "gate_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
all_results.json CHANGED
@@ -6,8 +6,8 @@
6
  "eval_samples_per_second": 17.578,
7
  "eval_steps_per_second": 0.556,
8
  "train_loss": 0.0,
9
- "train_runtime": 2772.4544,
10
  "train_samples": 20971,
11
- "train_samples_per_second": 7.564,
12
- "train_steps_per_second": 0.059
13
  }
 
6
  "eval_samples_per_second": 17.578,
7
  "eval_steps_per_second": 0.556,
8
  "train_loss": 0.0,
9
+ "train_runtime": 1159.3235,
10
  "train_samples": 20971,
11
+ "train_samples_per_second": 18.089,
12
+ "train_steps_per_second": 0.141
13
  }
runs/May01_02-14-26_COE-CS-sv003/events.out.tfevents.1714529784.COE-CS-sv003.580415.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dd8ea0f773f00c8bae66841c4e810b2431d640efed1e042834bc9a7af61a4c
3
+ size 4722
runs/May01_02-22-40_COE-CS-sv003/events.out.tfevents.1714530178.COE-CS-sv003.581639.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089f6b246d6124606539908c3da2ace4d9a0a3397bbb1270737622826b40bd6f
3
+ size 4722
runs/May01_02-55-15_COE-CS-sv003/events.out.tfevents.1714532190.COE-CS-sv003.582268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f785b9b5fa0c0b641fab1a491c6ebad21b08ab249f4e71044e67703ec6f89405
3
+ size 7859
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -2329,10 +2334,69 @@
2329
  ]
2330
  },
2331
  "post_processor": {
2332
- "type": "ByteLevel",
2333
- "add_prefix_space": true,
2334
- "trim_offsets": false,
2335
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2336
  },
2337
  "decoder": {
2338
  "type": "ByteLevel",
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
2334
  ]
2335
  },
2336
  "post_processor": {
2337
+ "type": "Sequence",
2338
+ "processors": [
2339
+ {
2340
+ "type": "ByteLevel",
2341
+ "add_prefix_space": true,
2342
+ "trim_offsets": false,
2343
+ "use_regex": true
2344
+ },
2345
+ {
2346
+ "type": "TemplateProcessing",
2347
+ "single": [
2348
+ {
2349
+ "SpecialToken": {
2350
+ "id": "<|begin_of_text|>",
2351
+ "type_id": 0
2352
+ }
2353
+ },
2354
+ {
2355
+ "Sequence": {
2356
+ "id": "A",
2357
+ "type_id": 0
2358
+ }
2359
+ }
2360
+ ],
2361
+ "pair": [
2362
+ {
2363
+ "SpecialToken": {
2364
+ "id": "<|begin_of_text|>",
2365
+ "type_id": 0
2366
+ }
2367
+ },
2368
+ {
2369
+ "Sequence": {
2370
+ "id": "A",
2371
+ "type_id": 0
2372
+ }
2373
+ },
2374
+ {
2375
+ "SpecialToken": {
2376
+ "id": "<|begin_of_text|>",
2377
+ "type_id": 1
2378
+ }
2379
+ },
2380
+ {
2381
+ "Sequence": {
2382
+ "id": "B",
2383
+ "type_id": 1
2384
+ }
2385
+ }
2386
+ ],
2387
+ "special_tokens": {
2388
+ "<|begin_of_text|>": {
2389
+ "id": "<|begin_of_text|>",
2390
+ "ids": [
2391
+ 128000
2392
+ ],
2393
+ "tokens": [
2394
+ "<|begin_of_text|>"
2395
+ ]
2396
+ }
2397
+ }
2398
+ }
2399
+ ]
2400
  },
2401
  "decoder": {
2402
  "type": "ByteLevel",
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 2772.4544,
5
  "train_samples": 20971,
6
- "train_samples_per_second": 7.564,
7
- "train_steps_per_second": 0.059
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1159.3235,
5
  "train_samples": 20971,
6
+ "train_samples_per_second": 18.089,
7
+ "train_steps_per_second": 0.141
8
  }
trainer_state.json CHANGED
@@ -242,19 +242,19 @@
242
  {
243
  "epoch": 1.0,
244
  "eval_loss": NaN,
245
- "eval_runtime": 132.453,
246
- "eval_samples_per_second": 17.44,
247
- "eval_steps_per_second": 0.551,
248
  "step": 164
249
  },
250
  {
251
  "epoch": 1.0,
252
  "step": 164,
253
- "total_flos": 2056676765073408.0,
254
  "train_loss": 0.0,
255
- "train_runtime": 2772.4544,
256
- "train_samples_per_second": 7.564,
257
- "train_steps_per_second": 0.059
258
  }
259
  ],
260
  "logging_steps": 5,
@@ -262,7 +262,7 @@
262
  "num_input_tokens_seen": 0,
263
  "num_train_epochs": 1,
264
  "save_steps": 100,
265
- "total_flos": 2056676765073408.0,
266
  "train_batch_size": 16,
267
  "trial_name": null,
268
  "trial_params": null
 
242
  {
243
  "epoch": 1.0,
244
  "eval_loss": NaN,
245
+ "eval_runtime": 131.371,
246
+ "eval_samples_per_second": 17.584,
247
+ "eval_steps_per_second": 0.556,
248
  "step": 164
249
  },
250
  {
251
  "epoch": 1.0,
252
  "step": 164,
253
+ "total_flos": 2050416313368576.0,
254
  "train_loss": 0.0,
255
+ "train_runtime": 1159.3235,
256
+ "train_samples_per_second": 18.089,
257
+ "train_steps_per_second": 0.141
258
  }
259
  ],
260
  "logging_steps": 5,
 
262
  "num_input_tokens_seen": 0,
263
  "num_train_epochs": 1,
264
  "save_steps": 100,
265
+ "total_flos": 2050416313368576.0,
266
  "train_batch_size": 16,
267
  "trial_name": null,
268
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf9e9e15d240931e87a117d99af1ed0a4e21ff6242f282f486e8d451d41d2947
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c1955178da9fc713167475c0b1455aa4dc2e111cc6ee3bbcf01ae4d46beb2a
3
  size 6072