Hugging Face's logo

terry69
/
zephyr-7b-sft-qlora

PEFT
TensorBoard
Safetensors
mistral
trl
sft
generated_from_trainer
Model card Files Metrics Community
terry69 commited on
Commit
5a81762
•
1 Parent(s): c7269e7

Training in progress, step 100

Browse files
Files changed (37) hide show
  1. README.md +71 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +8 -0
  5. config.json +26 -0
  6. runs/Feb22_15-31-35_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708615914.ip-172-31-69-60.ec2.internal.998.0 +3 -0
  7. runs/Feb22_16-19-50_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708618884.ip-172-31-69-60.ec2.internal.27360.0 +3 -0
  8. runs/Feb22_16-34-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708619663.ip-172-31-69-60.ec2.internal.34989.0 +3 -0
  9. runs/Feb22_23-30-47_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708644664.ip-172-31-69-60.ec2.internal.19311.0 +3 -0
  10. runs/Feb23_15-38-40_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708702742.ip-172-31-69-60.ec2.internal.43378.0 +3 -0
  11. runs/Feb23_17-16-57_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708708639.ip-172-31-69-60.ec2.internal.41103.0 +3 -0
  12. runs/Feb23_17-35-55_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708709777.ip-172-31-69-60.ec2.internal.1578.0 +3 -0
  13. runs/Feb23_18-05-38_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708711559.ip-172-31-69-60.ec2.internal.15547.0 +3 -0
  14. runs/Feb23_19-26-57_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708716437.ip-172-31-69-60.ec2.internal.3383.0 +3 -0
  15. runs/Feb24_00-03-26_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708733028.ip-172-31-69-60.ec2.internal.30764.0 +3 -0
  16. runs/Feb24_01-21-36_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708737718.ip-172-31-69-60.ec2.internal.21151.0 +3 -0
  17. runs/Feb24_16-46-55_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708793237.ip-172-31-69-60.ec2.internal.42769.0 +3 -0
  18. runs/Feb24_18-33-56_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708799657.ip-172-31-69-60.ec2.internal.46437.0 +3 -0
  19. runs/Feb24_19-54-16_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708804489.ip-172-31-69-60.ec2.internal.39032.0 +3 -0
  20. runs/Feb28_00-47-12_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709081252.ip-172-31-69-60.ec2.internal.36516.0 +3 -0
  21. runs/Mar02_18-31-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709404505.ip-172-31-69-60.ec2.internal.42473.0 +3 -0
  22. runs/Mar02_18-59-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709406004.ip-172-31-69-60.ec2.internal.7197.0 +3 -0
  23. runs/Mar04_22-24-45_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709591204.ip-172-31-69-60.ec2.internal.41896.0 +3 -0
  24. runs/Mar04_22-44-26_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709592284.ip-172-31-69-60.ec2.internal.1899.0 +3 -0
  25. runs/Mar04_23-09-23_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709593851.ip-172-31-69-60.ec2.internal.14110.0 +3 -0
  26. runs/Mar04_23-17-13_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709594251.ip-172-31-69-60.ec2.internal.18315.0 +3 -0
  27. runs/Mar09_22-07-00_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710022705.ip-172-31-69-60.ec2.internal.46199.0 +3 -0
  28. runs/Mar13_00-26-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710290282.ip-172-31-69-60.ec2.internal.30456.0 +3 -0
  29. runs/Mar13_02-37-09_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710298123.ip-172-31-69-60.ec2.internal.30951.0 +3 -0
  30. runs/Mar15_22-41-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710543612.ip-172-31-69-60.ec2.internal.38124.0 +3 -0
  31. special_tokens_map.json +24 -0
  32. tokenizer.json +0 -0
  33. tokenizer.model +3 -0
  34. tokenizer_config.json +43 -0
  35. train_results.json +8 -0
  36. trainer_state.json +0 -0
  37. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ - generated_from_trainer
10
+ base_model: mistralai/Mistral-7B-v0.1
11
+ datasets:
12
+ - HuggingFaceH4/ultrachat_200k
13
+ model-index:
14
+ - name: zephyr-7b-sft-qlora
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # zephyr-7b-sft-qlora
22
+
23
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 1.0681
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 0.0002
45
+ - train_batch_size: 2
46
+ - eval_batch_size: 2
47
+ - seed: 42
48
+ - distributed_type: multi-GPU
49
+ - num_devices: 4
50
+ - gradient_accumulation_steps: 2
51
+ - total_train_batch_size: 16
52
+ - total_eval_batch_size: 8
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: cosine
55
+ - lr_scheduler_warmup_ratio: 0.1
56
+ - num_epochs: 1
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss |
61
+ |:-------------:|:-----:|:-----:|:---------------:|
62
+ | 1.0163 | 1.0 | 12485 | 1.0681 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - PEFT 0.7.1
68
+ - Transformers 4.36.2
69
+ - Pytorch 2.2.1+cu121
70
+ - Datasets 2.14.6
71
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "down_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa69c858a1ebf64274a42f46d8d668efd0b634598af6f542f6cc71a3b80fa276
3
+ size 42002584
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.0040549779730794,
4
+ "train_runtime": 174545.1979,
5
+ "train_samples": 228651,
6
+ "train_samples_per_second": 1.144,
7
+ "train_steps_per_second": 0.072
8
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
runs/Feb22_15-31-35_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708615914.ip-172-31-69-60.ec2.internal.998.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5748c38a7d65d4d8c4ad7f27b629ac747ad2d891d76ce8912076e6167d5506a
3
+ size 4601
runs/Feb22_16-19-50_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708618884.ip-172-31-69-60.ec2.internal.27360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e8ac066cc19b08b45136adde2766dbad408267382df132ffcfcdb4c41c23b6
3
+ size 5063
runs/Feb22_16-34-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708619663.ip-172-31-69-60.ec2.internal.34989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8458c45adff17af6e4c42105c1dff7e9c6b47e534d73dd0480036b1ce5c83b1e
3
+ size 6449
runs/Feb22_23-30-47_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708644664.ip-172-31-69-60.ec2.internal.19311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e99d3473c6a7a6513155f310701d36bdd8f9cfdca54aa757754f5357195a8d6
3
+ size 15830
runs/Feb23_15-38-40_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708702742.ip-172-31-69-60.ec2.internal.43378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14357512dd5443472e2f010c1391cda8fa27d4374d921b620eaf8d269e2b334
3
+ size 8686
runs/Feb23_17-16-57_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708708639.ip-172-31-69-60.ec2.internal.41103.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f66cee6ec13324a786318b2a0a9d8c1cda2582c3b4e399b52162b78b12dfd9
3
+ size 5232
runs/Feb23_17-35-55_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708709777.ip-172-31-69-60.ec2.internal.1578.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ca0e2980a9ac75ebab0fb4f9d5995c2f6f73c224aae6cb52aaad1e3b3406e0
3
+ size 5546
runs/Feb23_18-05-38_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708711559.ip-172-31-69-60.ec2.internal.15547.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504073218ae0d82441cd38660d949cfeed37bcb255af5082fc931198e8732dd6
3
+ size 5546
runs/Feb23_19-26-57_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708716437.ip-172-31-69-60.ec2.internal.3383.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e207326b514702b33327524abbc33a05fa755e01681b25e3f6f063675597ea24
3
+ size 5546
runs/Feb24_00-03-26_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708733028.ip-172-31-69-60.ec2.internal.30764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e252a0635c41c6dd1d1405db3e0579f4b03f5e228a2ba17391408b4d4a601f
3
+ size 5232
runs/Feb24_01-21-36_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708737718.ip-172-31-69-60.ec2.internal.21151.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c22e2f90391aa2fd1569ce8340d220a1401a77660f73876f996aaed3a9e62d2
3
+ size 5546
runs/Feb24_16-46-55_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708793237.ip-172-31-69-60.ec2.internal.42769.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1152e61772e355062e6292131d424627aaface45375ed144b760b4b9f8cbf3
3
+ size 5546
runs/Feb24_18-33-56_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708799657.ip-172-31-69-60.ec2.internal.46437.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7ff449534eb536fe2f1101e56cbccce7e4b796164fd10b0889e83dcb079850
3
+ size 5546
runs/Feb24_19-54-16_ip-172-31-69-60.ec2.internal/events.out.tfevents.1708804489.ip-172-31-69-60.ec2.internal.39032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58db1390029b9c658414c6a88ad97d4a13e522a8e2cf66e4985208d42e554601
3
+ size 6447
runs/Feb28_00-47-12_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709081252.ip-172-31-69-60.ec2.internal.36516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35905ee6d0b92533cdb661011065d625d445d55dc446fecac9d61bf67891d07
3
+ size 5215
runs/Mar02_18-31-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709404505.ip-172-31-69-60.ec2.internal.42473.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4668a44d342f2a82a0374a06eebc11a189e8a0989f9acb47469c8b1f59d2bb91
3
+ size 5371
runs/Mar02_18-59-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709406004.ip-172-31-69-60.ec2.internal.7197.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40f2e878441bd4ee5b323f67d29d5bffe9c42cbbde9595849c59872314fa721
3
+ size 5371
runs/Mar04_22-24-45_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709591204.ip-172-31-69-60.ec2.internal.41896.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6a6ee26a0ffe8ce10e08b537b6a8dbc7404d74ec996efce3154f45db89704d
3
+ size 4755
runs/Mar04_22-44-26_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709592284.ip-172-31-69-60.ec2.internal.1899.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729293cb4db4673dd0c9f2dc6f532b90c87e6b33f2dfdad9423f8d2eca4d6ce7
3
+ size 5217
runs/Mar04_23-09-23_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709593851.ip-172-31-69-60.ec2.internal.14110.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99834cf3fec0f092b8fbe38cb916851db725ef8f30f17efd4562d818f2ffb392
3
+ size 5217
runs/Mar04_23-17-13_ip-172-31-69-60.ec2.internal/events.out.tfevents.1709594251.ip-172-31-69-60.ec2.internal.18315.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923860d02935a5f7f8151ea0d4428625489a97d8e51e886558e7901347393dd0
3
+ size 32626
runs/Mar09_22-07-00_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710022705.ip-172-31-69-60.ec2.internal.46199.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dd12d3e7503bfe5e0884e8af906dacc856b0f10dab6388585e3f3d159a0b57
3
+ size 291990
runs/Mar13_00-26-25_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710290282.ip-172-31-69-60.ec2.internal.30456.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59ca1860cc48c66b74e4be08e23f689357f960a62c33cda495402ea372cbe08
3
+ size 4447
runs/Mar13_02-37-09_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710298123.ip-172-31-69-60.ec2.internal.30951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4beb4b790353f563aa41e5f94dbfedb536953fde0f4695894fe2f166ee30bb6b
3
+ size 397180
runs/Mar15_22-41-49_ip-172-31-69-60.ec2.internal/events.out.tfevents.1710543612.ip-172-31-69-60.ec2.internal.38124.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15722676b7317736e15be23d1fb7bef73485c075b4d84965d8cd4b37457c30e0
3
+ size 7681
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.0040549779730794,
4
+ "train_runtime": 174545.1979,
5
+ "train_samples": 228651,
6
+ "train_samples_per_second": 1.144,
7
+ "train_steps_per_second": 0.072
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bbff5d3519c2125afe1a0bf60f6625c7cc8f6c99eb92eb78f4f8b96675fde1
3
+ size 5880