tyzhu commited on
Commit
2d9902b
1 Parent(s): 6594bc7

Training in progress, epoch 0, checkpoint

Browse files
checkpoint-187/adapter_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "Qwen/Qwen1.5-4B",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
checkpoint-187/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9448f255f79513d38dfad3a8b33d1a3815b5a5a9a3d5b512ece8db1249f23ef9
3
+ size 143269386
checkpoint-187/added_tokens.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "<|endoftext|>": 151643,
3
- "<|im_end|>": 151645,
4
- "<|im_start|>": 151644
5
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
  }
checkpoint-187/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cdd1cf492741b4f06665ddfa7b952c05f6f9b873cad95d8f4a9cf51791fc84e
3
- size 224537202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754a92312a990864e1b28bcffca53d3a1baacba5db1747a2d34cb4184ee66ba3
3
+ size 286585234
checkpoint-187/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b30ab82eb699e02b4647043c3a5280875911112390dceff3a97ef8b90a8612b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5942f0e6b035c739d65603deab64a808203d6c02a54ce4a1abdc9b96a8d90b0e
3
  size 15024
checkpoint-187/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:785a53bff184fa023e3e038aab73152bb6bdbc86980a8157f1fc6fe0498c5c70
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1157248040882f93029d0401e0f3292858faa327204d9177a034fc83b9f2cc77
3
  size 15024
checkpoint-187/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:188d76e868169092f0fe58e37330b804731c17e487c6c409de22e4cbd332380f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f613bc4a75199c4e3196448f33480cb60dcbb846f55ff0700f34b23b50fd46
3
  size 15024
checkpoint-187/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42b79e59b227a336f3021765566a047b2ac0beab504456773480cfc2600b814f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab72936c75bbe49ac13a52f4f3b1991a0c2d098291973c42b0fb9f5b01efbfbc
3
  size 15024
checkpoint-187/special_tokens_map.json CHANGED
@@ -1,14 +1,6 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>"
5
- ],
6
- "eos_token": {
7
- "content": "<|endoftext|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "pad_token": "<|endoftext|>"
14
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
6
  }
checkpoint-187/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-187/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-187/tokenizer_config.json CHANGED
@@ -1,24 +1,23 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "151643": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "151644": {
13
- "content": "<|im_start|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "151645": {
21
- "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -26,18 +25,16 @@
26
  "special": true
27
  }
28
  },
29
- "additional_special_tokens": [
30
- "<|im_start|>",
31
- "<|im_end|>"
32
- ],
33
- "bos_token": null,
34
- "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
  "clean_up_tokenization_spaces": false,
36
- "eos_token": "<|endoftext|>",
37
- "errors": "replace",
38
- "model_max_length": 32768,
39
- "pad_token": "<|endoftext|>",
40
- "split_special_tokens": false,
41
- "tokenizer_class": "Qwen2Tokenizer",
42
- "unk_token": null
 
 
43
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
 
 
 
 
30
  "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "left",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
  }
checkpoint-187/trainer_state.json CHANGED
@@ -9,47 +9,32 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.5333333333333333,
13
- "grad_norm": 0.9283596873283386,
14
  "learning_rate": 3e-05,
15
- "loss": 1.963,
16
  "step": 100
17
  },
18
  {
19
- "epoch": 0.9973333333333333,
20
- "eval_accuracy": 0.5695384615384615,
21
- "eval_loss": 1.6438876390457153,
22
- "eval_runtime": 5.0534,
23
- "eval_samples_per_second": 98.943,
24
- "eval_steps_per_second": 12.467,
25
  "step": 187
26
  },
27
  {
28
- "epoch": 0.9973333333333333,
29
- "eval_exact_match": 16.2,
30
- "eval_f1": 25.888571428571442,
31
  "step": 187
32
  }
33
  ],
34
  "logging_steps": 100,
35
  "max_steps": 9350,
36
- "num_input_tokens_seen": 0,
37
  "num_train_epochs": 50,
38
  "save_steps": 500,
39
- "stateful_callbacks": {
40
- "TrainerControl": {
41
- "args": {
42
- "should_epoch_stop": false,
43
- "should_evaluate": false,
44
- "should_log": false,
45
- "should_save": true,
46
- "should_training_stop": false
47
- },
48
- "attributes": {}
49
- }
50
- },
51
- "total_flos": 3432069308874752.0,
52
- "train_batch_size": 2,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.53,
 
13
  "learning_rate": 3e-05,
14
+ "loss": 2.0369,
15
  "step": 100
16
  },
17
  {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6128205128205129,
20
+ "eval_loss": 1.2953312397003174,
21
+ "eval_runtime": 4.1114,
22
+ "eval_samples_per_second": 121.614,
23
+ "eval_steps_per_second": 15.323,
24
  "step": 187
25
  },
26
  {
27
+ "epoch": 1.0,
28
+ "eval_exact_match": 27.2,
29
+ "eval_f1": 37.44218938149973,
30
  "step": 187
31
  }
32
  ],
33
  "logging_steps": 100,
34
  "max_steps": 9350,
 
35
  "num_train_epochs": 50,
36
  "save_steps": 500,
37
+ "total_flos": 7001749101477888.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  "trial_name": null,
39
  "trial_params": null
40
  }
checkpoint-187/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a175de730fa6917b3a611bb9e53766640b7a5e4a426f825f2a602cf98661e47
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c53f755ad4d3669bc1e92a0dd04ac5e6ef02b39406da28fac147ebfc373982
3
+ size 4728