tyzhu commited on
Commit
b4666eb
1 Parent(s): d237163

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 sha256:6535e1f84de6a80f5612f4d4c4510ccb07304653a54eb279c86181dbe8943a40
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 sha256:78f29c876bc4b15d2f13a92bab9cf92fb6016282dfa2d24934abb01464fffcc0
3
- size 224537202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:938ccb093c1709018a0f0ba2caa7ff3118b75d4e3dbc096602299c0ad1345a5e
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 sha256:938a21abc2080f8a961d7719d5af1d11eabdb841e10785d63bef08b144f16cfa
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 sha256:6a08275f41b8552b4826da6680a82a414c85c940083b1043d601f029907016f5
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 sha256:45ecad2d0ec17bc0e27eee13b3b469844e7563e78a2372b4988554ff1991d3c2
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 sha256:15a91ef4cf597bd154a84f7d2e36c407793efaff24aaf3a72be2f7112c093428
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": 0.7454617619514465,
14
  "learning_rate": 5e-05,
15
- "loss": 1.8726,
16
  "step": 100
17
  },
18
  {
19
- "epoch": 0.9973333333333333,
20
- "eval_accuracy": 0.5713333333333334,
21
- "eval_loss": 1.6331332921981812,
22
- "eval_runtime": 5.4718,
23
- "eval_samples_per_second": 91.377,
24
- "eval_steps_per_second": 11.514,
25
  "step": 187
26
  },
27
  {
28
- "epoch": 0.9973333333333333,
29
- "eval_exact_match": 15.0,
30
- "eval_f1": 25.64857142857145,
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": 3265462158753792.0,
52
- "train_batch_size": 1,
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": 5e-05,
14
+ "loss": 1.7923,
15
  "step": 100
16
  },
17
  {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6128205128205129,
20
+ "eval_loss": 1.2805120944976807,
21
+ "eval_runtime": 4.4685,
22
+ "eval_samples_per_second": 111.895,
23
+ "eval_steps_per_second": 14.099,
24
  "step": 187
25
  },
26
  {
27
+ "epoch": 1.0,
28
+ "eval_exact_match": 26.2,
29
+ "eval_f1": 37.42854700854702,
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:dd2191b7045c2a2985850d3b9f1472eaf3359ca38b9bc68efae9970e68b817ab
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742db4eb1b1050153055c5b82de0ef39604f0c615b7ee389916bfc19979a9577
3
+ size 4728