Commit
•
4552afc
1
Parent(s):
4cf4355
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- checkpoint-100/adapter_config.json +34 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/generation_config.json +6 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +35 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +46 -0
- checkpoint-100/trainer_state.json +161 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-120/adapter_config.json +34 -0
- checkpoint-120/adapter_model.safetensors +3 -0
- checkpoint-120/generation_config.json +6 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/special_tokens_map.json +35 -0
- checkpoint-120/tokenizer.json +0 -0
- checkpoint-120/tokenizer.model +3 -0
- checkpoint-120/tokenizer_config.json +46 -0
- checkpoint-120/trainer_state.json +189 -0
- checkpoint-120/training_args.bin +3 -0
- checkpoint-140/adapter_config.json +34 -0
- checkpoint-140/adapter_model.safetensors +3 -0
- checkpoint-140/generation_config.json +6 -0
- checkpoint-140/optimizer.pt +3 -0
- checkpoint-140/rng_state.pth +3 -0
- checkpoint-140/scheduler.pt +3 -0
- checkpoint-140/special_tokens_map.json +35 -0
- checkpoint-140/tokenizer.json +0 -0
- checkpoint-140/tokenizer.model +3 -0
- checkpoint-140/tokenizer_config.json +46 -0
- checkpoint-140/trainer_state.json +217 -0
- checkpoint-140/training_args.bin +3 -0
- checkpoint-160/adapter_config.json +34 -0
- checkpoint-160/adapter_model.safetensors +3 -0
- checkpoint-160/generation_config.json +6 -0
- checkpoint-160/optimizer.pt +3 -0
- checkpoint-160/rng_state.pth +3 -0
- checkpoint-160/scheduler.pt +3 -0
- checkpoint-160/special_tokens_map.json +35 -0
- checkpoint-160/tokenizer.json +0 -0
- checkpoint-160/tokenizer.model +3 -0
- checkpoint-160/tokenizer_config.json +46 -0
- checkpoint-160/trainer_state.json +245 -0
- checkpoint-160/training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_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 sha256:83460c847678159692c745c1fb288fddb43bd5f32c80512de1cec4ededb5cf0c
|
| 3 |
+
size 83946192
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58fb3042db660b913a74e4cb6478916e6deaa2c7ca8cbfc0a2b887d32d881bdd
|
| 3 |
+
size 83946192
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.39.1"
|
| 6 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8032f442e88ef26ffec4e313fe9de44853cad896c995e65898421282ebdd330e
|
| 3 |
+
size 335810482
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af5bbafca45d54c4b2bdc4ba560de981fc6e4a340cfb5c4ec48c142cf6c2500d
|
| 3 |
+
size 14168
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f221134f782b087897bae73677801d71f6d33786097f5ff961ea10bd257706
|
| 3 |
+
size 1056
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
| 3 |
+
size 755169
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"pad_token": "</s>",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.951219512195122,
|
| 5 |
+
"eval_steps": 500,
|
| 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": 0.1,
|
| 13 |
+
"grad_norm": 5.21875,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 6.2944,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.75,
|
| 21 |
+
"learning_rate": 2.9968542393565676e-06,
|
| 22 |
+
"loss": 8.1888,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.29,
|
| 27 |
+
"grad_norm": 4.59375,
|
| 28 |
+
"learning_rate": 2.984097196854534e-06,
|
| 29 |
+
"loss": 4.2333,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.39,
|
| 34 |
+
"grad_norm": 4.09375,
|
| 35 |
+
"learning_rate": 2.9616157869703894e-06,
|
| 36 |
+
"loss": 3.6424,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.49,
|
| 41 |
+
"grad_norm": 4.1875,
|
| 42 |
+
"learning_rate": 2.929557316423291e-06,
|
| 43 |
+
"loss": 5.3747,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"grad_norm": 3.453125,
|
| 49 |
+
"learning_rate": 2.8881318444640566e-06,
|
| 50 |
+
"loss": 6.7731,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.68,
|
| 55 |
+
"grad_norm": 3.984375,
|
| 56 |
+
"learning_rate": 2.8376108064873215e-06,
|
| 57 |
+
"loss": 6.4852,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.78,
|
| 62 |
+
"grad_norm": 4.1875,
|
| 63 |
+
"learning_rate": 2.778325235483954e-06,
|
| 64 |
+
"loss": 6.5685,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.88,
|
| 69 |
+
"grad_norm": 3.078125,
|
| 70 |
+
"learning_rate": 2.710663592987414e-06,
|
| 71 |
+
"loss": 7.1279,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.98,
|
| 76 |
+
"grad_norm": 3.21875,
|
| 77 |
+
"learning_rate": 2.6350692237265428e-06,
|
| 78 |
+
"loss": 3.2127,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.07,
|
| 83 |
+
"grad_norm": 2.859375,
|
| 84 |
+
"learning_rate": 2.552037450662849e-06,
|
| 85 |
+
"loss": 9.9494,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.17,
|
| 90 |
+
"grad_norm": 3.078125,
|
| 91 |
+
"learning_rate": 2.4621123294467098e-06,
|
| 92 |
+
"loss": 5.1331,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.27,
|
| 97 |
+
"grad_norm": 2.96875,
|
| 98 |
+
"learning_rate": 2.3658830835585295e-06,
|
| 99 |
+
"loss": 5.8588,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.37,
|
| 104 |
+
"grad_norm": 2.953125,
|
| 105 |
+
"learning_rate": 2.2639802434931445e-06,
|
| 106 |
+
"loss": 4.6236,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.46,
|
| 111 |
+
"grad_norm": 3.09375,
|
| 112 |
+
"learning_rate": 2.1570715152850234e-06,
|
| 113 |
+
"loss": 3.4357,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.56,
|
| 118 |
+
"grad_norm": 2.953125,
|
| 119 |
+
"learning_rate": 2.0458574054452316e-06,
|
| 120 |
+
"loss": 5.1455,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"grad_norm": 3.1875,
|
| 126 |
+
"learning_rate": 1.9310666309772426e-06,
|
| 127 |
+
"loss": 2.8809,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.76,
|
| 132 |
+
"grad_norm": 3.0625,
|
| 133 |
+
"learning_rate": 1.813451344546913e-06,
|
| 134 |
+
"loss": 8.66,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.85,
|
| 139 |
+
"grad_norm": 3.109375,
|
| 140 |
+
"learning_rate": 1.6937822060931097e-06,
|
| 141 |
+
"loss": 6.1746,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.95,
|
| 146 |
+
"grad_norm": 3.359375,
|
| 147 |
+
"learning_rate": 1.5728433331716726e-06,
|
| 148 |
+
"loss": 7.1489,
|
| 149 |
+
"step": 100
|
| 150 |
+
}
|
| 151 |
+
],
|
| 152 |
+
"logging_steps": 5,
|
| 153 |
+
"max_steps": 200,
|
| 154 |
+
"num_input_tokens_seen": 0,
|
| 155 |
+
"num_train_epochs": 4,
|
| 156 |
+
"save_steps": 20,
|
| 157 |
+
"total_flos": 4.001407189853798e+16,
|
| 158 |
+
"train_batch_size": 1,
|
| 159 |
+
"trial_name": null,
|
| 160 |
+
"trial_params": null
|
| 161 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aae0eb8787c5306cd814c63ec1c211dd9d3289a1805073d540b78508a6042ba
|
| 3 |
+
size 5024
|
checkpoint-120/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-120/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dcd733bdce817dc5da839edf6a3c939f13faca1bdecbcf329c8d3cb664281fd
|
| 3 |
+
size 83946192
|
checkpoint-120/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.39.1"
|
| 6 |
+
}
|
checkpoint-120/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:261a7130180f73f70dc2a8b170d08f20d41772d3535c410a4156c703f03a9ed0
|
| 3 |
+
size 335810482
|
checkpoint-120/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b134069b553939a89db83c1225011cb6c4e0655895ca3f89268b17fbd2c6807
|
| 3 |
+
size 14168
|
checkpoint-120/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb14778f6627c3fb9fb29c2bd1aa18885eb47e8fd8ee61a068a76a5fa5d6654
|
| 3 |
+
size 1056
|
checkpoint-120/special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
checkpoint-120/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
| 3 |
+
size 755169
|
checkpoint-120/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"pad_token": "</s>",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-120/trainer_state.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.341463414634146,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.21875,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 6.2944,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.75,
|
| 21 |
+
"learning_rate": 2.9968542393565676e-06,
|
| 22 |
+
"loss": 8.1888,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.29,
|
| 27 |
+
"grad_norm": 4.59375,
|
| 28 |
+
"learning_rate": 2.984097196854534e-06,
|
| 29 |
+
"loss": 4.2333,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.39,
|
| 34 |
+
"grad_norm": 4.09375,
|
| 35 |
+
"learning_rate": 2.9616157869703894e-06,
|
| 36 |
+
"loss": 3.6424,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.49,
|
| 41 |
+
"grad_norm": 4.1875,
|
| 42 |
+
"learning_rate": 2.929557316423291e-06,
|
| 43 |
+
"loss": 5.3747,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"grad_norm": 3.453125,
|
| 49 |
+
"learning_rate": 2.8881318444640566e-06,
|
| 50 |
+
"loss": 6.7731,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.68,
|
| 55 |
+
"grad_norm": 3.984375,
|
| 56 |
+
"learning_rate": 2.8376108064873215e-06,
|
| 57 |
+
"loss": 6.4852,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.78,
|
| 62 |
+
"grad_norm": 4.1875,
|
| 63 |
+
"learning_rate": 2.778325235483954e-06,
|
| 64 |
+
"loss": 6.5685,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.88,
|
| 69 |
+
"grad_norm": 3.078125,
|
| 70 |
+
"learning_rate": 2.710663592987414e-06,
|
| 71 |
+
"loss": 7.1279,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.98,
|
| 76 |
+
"grad_norm": 3.21875,
|
| 77 |
+
"learning_rate": 2.6350692237265428e-06,
|
| 78 |
+
"loss": 3.2127,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.07,
|
| 83 |
+
"grad_norm": 2.859375,
|
| 84 |
+
"learning_rate": 2.552037450662849e-06,
|
| 85 |
+
"loss": 9.9494,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.17,
|
| 90 |
+
"grad_norm": 3.078125,
|
| 91 |
+
"learning_rate": 2.4621123294467098e-06,
|
| 92 |
+
"loss": 5.1331,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.27,
|
| 97 |
+
"grad_norm": 2.96875,
|
| 98 |
+
"learning_rate": 2.3658830835585295e-06,
|
| 99 |
+
"loss": 5.8588,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.37,
|
| 104 |
+
"grad_norm": 2.953125,
|
| 105 |
+
"learning_rate": 2.2639802434931445e-06,
|
| 106 |
+
"loss": 4.6236,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.46,
|
| 111 |
+
"grad_norm": 3.09375,
|
| 112 |
+
"learning_rate": 2.1570715152850234e-06,
|
| 113 |
+
"loss": 3.4357,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.56,
|
| 118 |
+
"grad_norm": 2.953125,
|
| 119 |
+
"learning_rate": 2.0458574054452316e-06,
|
| 120 |
+
"loss": 5.1455,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"grad_norm": 3.1875,
|
| 126 |
+
"learning_rate": 1.9310666309772426e-06,
|
| 127 |
+
"loss": 2.8809,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.76,
|
| 132 |
+
"grad_norm": 3.0625,
|
| 133 |
+
"learning_rate": 1.813451344546913e-06,
|
| 134 |
+
"loss": 8.66,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.85,
|
| 139 |
+
"grad_norm": 3.109375,
|
| 140 |
+
"learning_rate": 1.6937822060931097e-06,
|
| 141 |
+
"loss": 6.1746,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.95,
|
| 146 |
+
"grad_norm": 3.359375,
|
| 147 |
+
"learning_rate": 1.5728433331716726e-06,
|
| 148 |
+
"loss": 7.1489,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.05,
|
| 153 |
+
"grad_norm": 3.453125,
|
| 154 |
+
"learning_rate": 1.4514271631199665e-06,
|
| 155 |
+
"loss": 9.0421,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.15,
|
| 160 |
+
"grad_norm": 3.328125,
|
| 161 |
+
"learning_rate": 1.3303292607070737e-06,
|
| 162 |
+
"loss": 3.6143,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.24,
|
| 167 |
+
"grad_norm": 3.5625,
|
| 168 |
+
"learning_rate": 1.2103431052918681e-06,
|
| 169 |
+
"loss": 5.9441,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.34,
|
| 174 |
+
"grad_norm": 2.875,
|
| 175 |
+
"learning_rate": 1.0922548916454855e-06,
|
| 176 |
+
"loss": 3.1449,
|
| 177 |
+
"step": 120
|
| 178 |
+
}
|
| 179 |
+
],
|
| 180 |
+
"logging_steps": 5,
|
| 181 |
+
"max_steps": 200,
|
| 182 |
+
"num_input_tokens_seen": 0,
|
| 183 |
+
"num_train_epochs": 4,
|
| 184 |
+
"save_steps": 20,
|
| 185 |
+
"total_flos": 4.821291072638976e+16,
|
| 186 |
+
"train_batch_size": 1,
|
| 187 |
+
"trial_name": null,
|
| 188 |
+
"trial_params": null
|
| 189 |
+
}
|
checkpoint-120/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aae0eb8787c5306cd814c63ec1c211dd9d3289a1805073d540b78508a6042ba
|
| 3 |
+
size 5024
|
checkpoint-140/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-140/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a48c39273fd8af1c9f7748350c75fa448c030801c064fc29319d702a3d5d7f4
|
| 3 |
+
size 83946192
|
checkpoint-140/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.39.1"
|
| 6 |
+
}
|
checkpoint-140/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:945d1967a70d17b43bde3bf889cf2797fa0caca0db43041f1d0f9d0a2cd48fa1
|
| 3 |
+
size 335810482
|
checkpoint-140/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f7023c926f8562fc90a40ceb50ba2c29e83898a831fd0d338b03d0f4dc3604d
|
| 3 |
+
size 14168
|
checkpoint-140/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4462a9b81e8b5dd0e85a5dcffb23ef5d71f319857440c97d0d6676a9849fa0ce
|
| 3 |
+
size 1056
|
checkpoint-140/special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
checkpoint-140/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-140/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
| 3 |
+
size 755169
|
checkpoint-140/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"pad_token": "</s>",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-140/trainer_state.json
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.7317073170731705,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.21875,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 6.2944,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.75,
|
| 21 |
+
"learning_rate": 2.9968542393565676e-06,
|
| 22 |
+
"loss": 8.1888,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.29,
|
| 27 |
+
"grad_norm": 4.59375,
|
| 28 |
+
"learning_rate": 2.984097196854534e-06,
|
| 29 |
+
"loss": 4.2333,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.39,
|
| 34 |
+
"grad_norm": 4.09375,
|
| 35 |
+
"learning_rate": 2.9616157869703894e-06,
|
| 36 |
+
"loss": 3.6424,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.49,
|
| 41 |
+
"grad_norm": 4.1875,
|
| 42 |
+
"learning_rate": 2.929557316423291e-06,
|
| 43 |
+
"loss": 5.3747,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"grad_norm": 3.453125,
|
| 49 |
+
"learning_rate": 2.8881318444640566e-06,
|
| 50 |
+
"loss": 6.7731,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.68,
|
| 55 |
+
"grad_norm": 3.984375,
|
| 56 |
+
"learning_rate": 2.8376108064873215e-06,
|
| 57 |
+
"loss": 6.4852,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.78,
|
| 62 |
+
"grad_norm": 4.1875,
|
| 63 |
+
"learning_rate": 2.778325235483954e-06,
|
| 64 |
+
"loss": 6.5685,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.88,
|
| 69 |
+
"grad_norm": 3.078125,
|
| 70 |
+
"learning_rate": 2.710663592987414e-06,
|
| 71 |
+
"loss": 7.1279,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.98,
|
| 76 |
+
"grad_norm": 3.21875,
|
| 77 |
+
"learning_rate": 2.6350692237265428e-06,
|
| 78 |
+
"loss": 3.2127,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.07,
|
| 83 |
+
"grad_norm": 2.859375,
|
| 84 |
+
"learning_rate": 2.552037450662849e-06,
|
| 85 |
+
"loss": 9.9494,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.17,
|
| 90 |
+
"grad_norm": 3.078125,
|
| 91 |
+
"learning_rate": 2.4621123294467098e-06,
|
| 92 |
+
"loss": 5.1331,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.27,
|
| 97 |
+
"grad_norm": 2.96875,
|
| 98 |
+
"learning_rate": 2.3658830835585295e-06,
|
| 99 |
+
"loss": 5.8588,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.37,
|
| 104 |
+
"grad_norm": 2.953125,
|
| 105 |
+
"learning_rate": 2.2639802434931445e-06,
|
| 106 |
+
"loss": 4.6236,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.46,
|
| 111 |
+
"grad_norm": 3.09375,
|
| 112 |
+
"learning_rate": 2.1570715152850234e-06,
|
| 113 |
+
"loss": 3.4357,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.56,
|
| 118 |
+
"grad_norm": 2.953125,
|
| 119 |
+
"learning_rate": 2.0458574054452316e-06,
|
| 120 |
+
"loss": 5.1455,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"grad_norm": 3.1875,
|
| 126 |
+
"learning_rate": 1.9310666309772426e-06,
|
| 127 |
+
"loss": 2.8809,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.76,
|
| 132 |
+
"grad_norm": 3.0625,
|
| 133 |
+
"learning_rate": 1.813451344546913e-06,
|
| 134 |
+
"loss": 8.66,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.85,
|
| 139 |
+
"grad_norm": 3.109375,
|
| 140 |
+
"learning_rate": 1.6937822060931097e-06,
|
| 141 |
+
"loss": 6.1746,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.95,
|
| 146 |
+
"grad_norm": 3.359375,
|
| 147 |
+
"learning_rate": 1.5728433331716726e-06,
|
| 148 |
+
"loss": 7.1489,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.05,
|
| 153 |
+
"grad_norm": 3.453125,
|
| 154 |
+
"learning_rate": 1.4514271631199665e-06,
|
| 155 |
+
"loss": 9.0421,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.15,
|
| 160 |
+
"grad_norm": 3.328125,
|
| 161 |
+
"learning_rate": 1.3303292607070737e-06,
|
| 162 |
+
"loss": 3.6143,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.24,
|
| 167 |
+
"grad_norm": 3.5625,
|
| 168 |
+
"learning_rate": 1.2103431052918681e-06,
|
| 169 |
+
"loss": 5.9441,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.34,
|
| 174 |
+
"grad_norm": 2.875,
|
| 175 |
+
"learning_rate": 1.0922548916454855e-06,
|
| 176 |
+
"loss": 3.1449,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.44,
|
| 181 |
+
"grad_norm": 3.078125,
|
| 182 |
+
"learning_rate": 9.768383785051766e-07,
|
| 183 |
+
"loss": 8.4543,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.54,
|
| 188 |
+
"grad_norm": 3.734375,
|
| 189 |
+
"learning_rate": 8.648498186137653e-07,
|
| 190 |
+
"loss": 6.5607,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.63,
|
| 195 |
+
"grad_norm": 3.328125,
|
| 196 |
+
"learning_rate": 7.570230034650192e-07,
|
| 197 |
+
"loss": 8.5402,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.73,
|
| 202 |
+
"grad_norm": 3.09375,
|
| 203 |
+
"learning_rate": 6.540644552236401e-07,
|
| 204 |
+
"loss": 2.9279,
|
| 205 |
+
"step": 140
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
"logging_steps": 5,
|
| 209 |
+
"max_steps": 200,
|
| 210 |
+
"num_input_tokens_seen": 0,
|
| 211 |
+
"num_train_epochs": 4,
|
| 212 |
+
"save_steps": 20,
|
| 213 |
+
"total_flos": 5.584462036232602e+16,
|
| 214 |
+
"train_batch_size": 1,
|
| 215 |
+
"trial_name": null,
|
| 216 |
+
"trial_params": null
|
| 217 |
+
}
|
checkpoint-140/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aae0eb8787c5306cd814c63ec1c211dd9d3289a1805073d540b78508a6042ba
|
| 3 |
+
size 5024
|
checkpoint-160/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-160/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5b8f7f13b7fc091fc4e4c7a56f624badda5a7323bb29695bea1479124488295
|
| 3 |
+
size 83946192
|
checkpoint-160/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.39.1"
|
| 6 |
+
}
|
checkpoint-160/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e31a3c1d1ea603eff8eec1652249d684658efe5154a7c69f16a91a4442ab04e
|
| 3 |
+
size 335810482
|
checkpoint-160/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e68a1ed6f15deaf51b07348f07dd024f9f376fde26a94df825a697e57f4ff8
|
| 3 |
+
size 14168
|
checkpoint-160/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75e4c02b20488fb5acfba5ec46c3e3e0f5b15bbe384071da9b286bc74610bceb
|
| 3 |
+
size 1056
|
checkpoint-160/special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
checkpoint-160/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-160/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
| 3 |
+
size 755169
|
checkpoint-160/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"pad_token": "</s>",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-160/trainer_state.json
ADDED
|
@@ -0,0 +1,245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.1219512195121952,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.21875,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 6.2944,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.75,
|
| 21 |
+
"learning_rate": 2.9968542393565676e-06,
|
| 22 |
+
"loss": 8.1888,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.29,
|
| 27 |
+
"grad_norm": 4.59375,
|
| 28 |
+
"learning_rate": 2.984097196854534e-06,
|
| 29 |
+
"loss": 4.2333,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.39,
|
| 34 |
+
"grad_norm": 4.09375,
|
| 35 |
+
"learning_rate": 2.9616157869703894e-06,
|
| 36 |
+
"loss": 3.6424,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.49,
|
| 41 |
+
"grad_norm": 4.1875,
|
| 42 |
+
"learning_rate": 2.929557316423291e-06,
|
| 43 |
+
"loss": 5.3747,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.59,
|
| 48 |
+
"grad_norm": 3.453125,
|
| 49 |
+
"learning_rate": 2.8881318444640566e-06,
|
| 50 |
+
"loss": 6.7731,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.68,
|
| 55 |
+
"grad_norm": 3.984375,
|
| 56 |
+
"learning_rate": 2.8376108064873215e-06,
|
| 57 |
+
"loss": 6.4852,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.78,
|
| 62 |
+
"grad_norm": 4.1875,
|
| 63 |
+
"learning_rate": 2.778325235483954e-06,
|
| 64 |
+
"loss": 6.5685,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.88,
|
| 69 |
+
"grad_norm": 3.078125,
|
| 70 |
+
"learning_rate": 2.710663592987414e-06,
|
| 71 |
+
"loss": 7.1279,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.98,
|
| 76 |
+
"grad_norm": 3.21875,
|
| 77 |
+
"learning_rate": 2.6350692237265428e-06,
|
| 78 |
+
"loss": 3.2127,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.07,
|
| 83 |
+
"grad_norm": 2.859375,
|
| 84 |
+
"learning_rate": 2.552037450662849e-06,
|
| 85 |
+
"loss": 9.9494,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.17,
|
| 90 |
+
"grad_norm": 3.078125,
|
| 91 |
+
"learning_rate": 2.4621123294467098e-06,
|
| 92 |
+
"loss": 5.1331,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.27,
|
| 97 |
+
"grad_norm": 2.96875,
|
| 98 |
+
"learning_rate": 2.3658830835585295e-06,
|
| 99 |
+
"loss": 5.8588,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.37,
|
| 104 |
+
"grad_norm": 2.953125,
|
| 105 |
+
"learning_rate": 2.2639802434931445e-06,
|
| 106 |
+
"loss": 4.6236,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.46,
|
| 111 |
+
"grad_norm": 3.09375,
|
| 112 |
+
"learning_rate": 2.1570715152850234e-06,
|
| 113 |
+
"loss": 3.4357,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.56,
|
| 118 |
+
"grad_norm": 2.953125,
|
| 119 |
+
"learning_rate": 2.0458574054452316e-06,
|
| 120 |
+
"loss": 5.1455,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"grad_norm": 3.1875,
|
| 126 |
+
"learning_rate": 1.9310666309772426e-06,
|
| 127 |
+
"loss": 2.8809,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.76,
|
| 132 |
+
"grad_norm": 3.0625,
|
| 133 |
+
"learning_rate": 1.813451344546913e-06,
|
| 134 |
+
"loss": 8.66,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.85,
|
| 139 |
+
"grad_norm": 3.109375,
|
| 140 |
+
"learning_rate": 1.6937822060931097e-06,
|
| 141 |
+
"loss": 6.1746,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.95,
|
| 146 |
+
"grad_norm": 3.359375,
|
| 147 |
+
"learning_rate": 1.5728433331716726e-06,
|
| 148 |
+
"loss": 7.1489,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.05,
|
| 153 |
+
"grad_norm": 3.453125,
|
| 154 |
+
"learning_rate": 1.4514271631199665e-06,
|
| 155 |
+
"loss": 9.0421,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.15,
|
| 160 |
+
"grad_norm": 3.328125,
|
| 161 |
+
"learning_rate": 1.3303292607070737e-06,
|
| 162 |
+
"loss": 3.6143,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.24,
|
| 167 |
+
"grad_norm": 3.5625,
|
| 168 |
+
"learning_rate": 1.2103431052918681e-06,
|
| 169 |
+
"loss": 5.9441,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.34,
|
| 174 |
+
"grad_norm": 2.875,
|
| 175 |
+
"learning_rate": 1.0922548916454855e-06,
|
| 176 |
+
"loss": 3.1449,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.44,
|
| 181 |
+
"grad_norm": 3.078125,
|
| 182 |
+
"learning_rate": 9.768383785051766e-07,
|
| 183 |
+
"loss": 8.4543,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.54,
|
| 188 |
+
"grad_norm": 3.734375,
|
| 189 |
+
"learning_rate": 8.648498186137653e-07,
|
| 190 |
+
"loss": 6.5607,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.63,
|
| 195 |
+
"grad_norm": 3.328125,
|
| 196 |
+
"learning_rate": 7.570230034650192e-07,
|
| 197 |
+
"loss": 8.5402,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.73,
|
| 202 |
+
"grad_norm": 3.09375,
|
| 203 |
+
"learning_rate": 6.540644552236401e-07,
|
| 204 |
+
"loss": 2.9279,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.83,
|
| 209 |
+
"grad_norm": 3.171875,
|
| 210 |
+
"learning_rate": 5.566487973242332e-07,
|
| 211 |
+
"loss": 6.1072,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.93,
|
| 216 |
+
"grad_norm": 2.53125,
|
| 217 |
+
"learning_rate": 4.6541433408284356e-07,
|
| 218 |
+
"loss": 5.8211,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.02,
|
| 223 |
+
"grad_norm": 2.765625,
|
| 224 |
+
"learning_rate": 3.8095886828513094e-07,
|
| 225 |
+
"loss": 9.2977,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.12,
|
| 230 |
+
"grad_norm": 3.34375,
|
| 231 |
+
"learning_rate": 3.0383578415591913e-07,
|
| 232 |
+
"loss": 3.2964,
|
| 233 |
+
"step": 160
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"logging_steps": 5,
|
| 237 |
+
"max_steps": 200,
|
| 238 |
+
"num_input_tokens_seen": 0,
|
| 239 |
+
"num_train_epochs": 4,
|
| 240 |
+
"save_steps": 20,
|
| 241 |
+
"total_flos": 6.407100360912077e+16,
|
| 242 |
+
"train_batch_size": 1,
|
| 243 |
+
"trial_name": null,
|
| 244 |
+
"trial_params": null
|
| 245 |
+
}
|
checkpoint-160/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aae0eb8787c5306cd814c63ec1c211dd9d3289a1805073d540b78508a6042ba
|
| 3 |
+
size 5024
|