Upload 11 files
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +39 -0
- trainer_state.json +463 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TheBloke/Llama-2-7b-Chat-GPTQ",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 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": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"o_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b451914748bce764f0dd71173781a42f96d53884258e97772336103277866a0f
|
| 3 |
+
size 33588528
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12938a6d6a601b2d4bd071b2e44f4e594905d3db58d3a3a873fe13c71214ac27
|
| 3 |
+
size 67323642
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9e69b37c144236e386a75e67c3d5f24714d3d322b384a54fc1c6448d9fa30e6
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b46d8f904773049d57f842e754826a0a22019f6709d26b05db5142336dbff1a
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 37 |
+
"unk_token": "<unk>",
|
| 38 |
+
"use_default_system_prompt": false
|
| 39 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,463 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 625,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 0.5752072334289551,
|
| 14 |
+
"learning_rate": 0.0001993517017828201,
|
| 15 |
+
"loss": 1.6434,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 0.7842408418655396,
|
| 21 |
+
"learning_rate": 0.0001961102106969206,
|
| 22 |
+
"loss": 1.2847,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 0.4593060612678528,
|
| 28 |
+
"learning_rate": 0.0001928687196110211,
|
| 29 |
+
"loss": 1.1227,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06,
|
| 34 |
+
"grad_norm": 0.45610150694847107,
|
| 35 |
+
"learning_rate": 0.00018962722852512156,
|
| 36 |
+
"loss": 1.0359,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 0.4743576645851135,
|
| 42 |
+
"learning_rate": 0.00018638573743922206,
|
| 43 |
+
"loss": 0.992,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"grad_norm": 0.5059588551521301,
|
| 49 |
+
"learning_rate": 0.00018314424635332255,
|
| 50 |
+
"loss": 0.9782,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"grad_norm": 0.5296839475631714,
|
| 56 |
+
"learning_rate": 0.00017990275526742302,
|
| 57 |
+
"loss": 0.8997,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13,
|
| 62 |
+
"grad_norm": 0.6169719099998474,
|
| 63 |
+
"learning_rate": 0.00017666126418152352,
|
| 64 |
+
"loss": 0.887,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14,
|
| 69 |
+
"grad_norm": 0.5174543261528015,
|
| 70 |
+
"learning_rate": 0.00017341977309562402,
|
| 71 |
+
"loss": 0.8388,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16,
|
| 76 |
+
"grad_norm": 0.5253883600234985,
|
| 77 |
+
"learning_rate": 0.0001701782820097245,
|
| 78 |
+
"loss": 0.875,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18,
|
| 83 |
+
"grad_norm": 0.5177808403968811,
|
| 84 |
+
"learning_rate": 0.00016693679092382496,
|
| 85 |
+
"loss": 0.8193,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19,
|
| 90 |
+
"grad_norm": 0.50547856092453,
|
| 91 |
+
"learning_rate": 0.00016369529983792545,
|
| 92 |
+
"loss": 0.8444,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21,
|
| 97 |
+
"grad_norm": 0.5066828727722168,
|
| 98 |
+
"learning_rate": 0.00016045380875202592,
|
| 99 |
+
"loss": 0.857,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.22,
|
| 104 |
+
"grad_norm": 0.4495781362056732,
|
| 105 |
+
"learning_rate": 0.00015721231766612642,
|
| 106 |
+
"loss": 0.7897,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24,
|
| 111 |
+
"grad_norm": 0.5362279415130615,
|
| 112 |
+
"learning_rate": 0.00015429497568881685,
|
| 113 |
+
"loss": 0.7992,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.26,
|
| 118 |
+
"grad_norm": 0.5713534951210022,
|
| 119 |
+
"learning_rate": 0.00015105348460291734,
|
| 120 |
+
"loss": 0.8446,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.27,
|
| 125 |
+
"grad_norm": 0.4843427240848541,
|
| 126 |
+
"learning_rate": 0.00014781199351701784,
|
| 127 |
+
"loss": 0.7906,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29,
|
| 132 |
+
"grad_norm": 0.4727051556110382,
|
| 133 |
+
"learning_rate": 0.0001445705024311183,
|
| 134 |
+
"loss": 0.8281,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3,
|
| 139 |
+
"grad_norm": 0.4981895685195923,
|
| 140 |
+
"learning_rate": 0.0001413290113452188,
|
| 141 |
+
"loss": 0.7966,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.32,
|
| 146 |
+
"grad_norm": 0.4925459027290344,
|
| 147 |
+
"learning_rate": 0.0001380875202593193,
|
| 148 |
+
"loss": 0.7889,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.34,
|
| 153 |
+
"grad_norm": 0.4470859467983246,
|
| 154 |
+
"learning_rate": 0.00013484602917341977,
|
| 155 |
+
"loss": 0.7588,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35,
|
| 160 |
+
"grad_norm": 0.46052438020706177,
|
| 161 |
+
"learning_rate": 0.00013160453808752027,
|
| 162 |
+
"loss": 0.7863,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.37,
|
| 167 |
+
"grad_norm": 0.4708721935749054,
|
| 168 |
+
"learning_rate": 0.00012836304700162077,
|
| 169 |
+
"loss": 0.8244,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.38,
|
| 174 |
+
"grad_norm": 0.4670282304286957,
|
| 175 |
+
"learning_rate": 0.00012512155591572124,
|
| 176 |
+
"loss": 0.7391,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4,
|
| 181 |
+
"grad_norm": 0.4596056342124939,
|
| 182 |
+
"learning_rate": 0.00012188006482982173,
|
| 183 |
+
"loss": 0.8057,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.42,
|
| 188 |
+
"grad_norm": 0.3906649053096771,
|
| 189 |
+
"learning_rate": 0.0001186385737439222,
|
| 190 |
+
"loss": 0.7594,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.43,
|
| 195 |
+
"grad_norm": 0.5942690372467041,
|
| 196 |
+
"learning_rate": 0.0001153970826580227,
|
| 197 |
+
"loss": 0.7615,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45,
|
| 202 |
+
"grad_norm": 0.40805208683013916,
|
| 203 |
+
"learning_rate": 0.00011215559157212318,
|
| 204 |
+
"loss": 0.7607,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.46,
|
| 209 |
+
"grad_norm": 0.5320433974266052,
|
| 210 |
+
"learning_rate": 0.00010891410048622365,
|
| 211 |
+
"loss": 0.7666,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.48,
|
| 216 |
+
"grad_norm": 0.4362870752811432,
|
| 217 |
+
"learning_rate": 0.00010567260940032415,
|
| 218 |
+
"loss": 0.7683,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5,
|
| 223 |
+
"grad_norm": 0.5106446146965027,
|
| 224 |
+
"learning_rate": 0.00010243111831442465,
|
| 225 |
+
"loss": 0.7777,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.51,
|
| 230 |
+
"grad_norm": 0.506986677646637,
|
| 231 |
+
"learning_rate": 9.918962722852513e-05,
|
| 232 |
+
"loss": 0.7637,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.53,
|
| 237 |
+
"grad_norm": 0.5665115118026733,
|
| 238 |
+
"learning_rate": 9.594813614262561e-05,
|
| 239 |
+
"loss": 0.7497,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.54,
|
| 244 |
+
"grad_norm": 0.4510403275489807,
|
| 245 |
+
"learning_rate": 9.27066450567261e-05,
|
| 246 |
+
"loss": 0.7644,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.56,
|
| 251 |
+
"grad_norm": 0.5009343028068542,
|
| 252 |
+
"learning_rate": 8.946515397082659e-05,
|
| 253 |
+
"loss": 0.7766,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.58,
|
| 258 |
+
"grad_norm": 0.4533093273639679,
|
| 259 |
+
"learning_rate": 8.622366288492708e-05,
|
| 260 |
+
"loss": 0.7579,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.59,
|
| 265 |
+
"grad_norm": 0.4576455056667328,
|
| 266 |
+
"learning_rate": 8.298217179902756e-05,
|
| 267 |
+
"loss": 0.7731,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.61,
|
| 272 |
+
"grad_norm": 0.47114574909210205,
|
| 273 |
+
"learning_rate": 7.974068071312804e-05,
|
| 274 |
+
"loss": 0.7612,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.62,
|
| 279 |
+
"grad_norm": 0.5052211284637451,
|
| 280 |
+
"learning_rate": 7.649918962722853e-05,
|
| 281 |
+
"loss": 0.7529,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.64,
|
| 286 |
+
"grad_norm": 0.4952121675014496,
|
| 287 |
+
"learning_rate": 7.325769854132901e-05,
|
| 288 |
+
"loss": 0.7645,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.66,
|
| 293 |
+
"grad_norm": 0.5584261417388916,
|
| 294 |
+
"learning_rate": 7.00162074554295e-05,
|
| 295 |
+
"loss": 0.7859,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.67,
|
| 300 |
+
"grad_norm": 0.5271150469779968,
|
| 301 |
+
"learning_rate": 6.677471636952999e-05,
|
| 302 |
+
"loss": 0.7662,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.69,
|
| 307 |
+
"grad_norm": 0.6051105260848999,
|
| 308 |
+
"learning_rate": 6.353322528363047e-05,
|
| 309 |
+
"loss": 0.7217,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7,
|
| 314 |
+
"grad_norm": 0.5145427584648132,
|
| 315 |
+
"learning_rate": 6.029173419773096e-05,
|
| 316 |
+
"loss": 0.763,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.72,
|
| 321 |
+
"grad_norm": 0.5100213885307312,
|
| 322 |
+
"learning_rate": 5.7050243111831445e-05,
|
| 323 |
+
"loss": 0.7493,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.74,
|
| 328 |
+
"grad_norm": 0.6406119465827942,
|
| 329 |
+
"learning_rate": 5.380875202593193e-05,
|
| 330 |
+
"loss": 0.7856,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.75,
|
| 335 |
+
"grad_norm": 0.5142606496810913,
|
| 336 |
+
"learning_rate": 5.056726094003241e-05,
|
| 337 |
+
"loss": 0.7439,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.77,
|
| 342 |
+
"grad_norm": 0.6167362332344055,
|
| 343 |
+
"learning_rate": 4.73257698541329e-05,
|
| 344 |
+
"loss": 0.7615,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.78,
|
| 349 |
+
"grad_norm": 0.5693132281303406,
|
| 350 |
+
"learning_rate": 4.408427876823339e-05,
|
| 351 |
+
"loss": 0.7535,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8,
|
| 356 |
+
"grad_norm": 0.5026053190231323,
|
| 357 |
+
"learning_rate": 4.0842787682333875e-05,
|
| 358 |
+
"loss": 0.7397,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.82,
|
| 363 |
+
"grad_norm": 0.5282934904098511,
|
| 364 |
+
"learning_rate": 3.760129659643436e-05,
|
| 365 |
+
"loss": 0.7519,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.83,
|
| 370 |
+
"grad_norm": 0.5583475828170776,
|
| 371 |
+
"learning_rate": 3.435980551053485e-05,
|
| 372 |
+
"loss": 0.736,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.85,
|
| 377 |
+
"grad_norm": 0.5823280215263367,
|
| 378 |
+
"learning_rate": 3.111831442463534e-05,
|
| 379 |
+
"loss": 0.7383,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.86,
|
| 384 |
+
"grad_norm": 0.4686075747013092,
|
| 385 |
+
"learning_rate": 2.7876823338735818e-05,
|
| 386 |
+
"loss": 0.7272,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.88,
|
| 391 |
+
"grad_norm": 0.5750771164894104,
|
| 392 |
+
"learning_rate": 2.4635332252836304e-05,
|
| 393 |
+
"loss": 0.7483,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9,
|
| 398 |
+
"grad_norm": 0.4452055096626282,
|
| 399 |
+
"learning_rate": 2.1393841166936794e-05,
|
| 400 |
+
"loss": 0.7412,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.91,
|
| 405 |
+
"grad_norm": 0.48527467250823975,
|
| 406 |
+
"learning_rate": 1.8152350081037278e-05,
|
| 407 |
+
"loss": 0.7287,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.93,
|
| 412 |
+
"grad_norm": 0.6023633480072021,
|
| 413 |
+
"learning_rate": 1.4910858995137764e-05,
|
| 414 |
+
"loss": 0.7856,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.94,
|
| 419 |
+
"grad_norm": 0.40449661016464233,
|
| 420 |
+
"learning_rate": 1.1669367909238251e-05,
|
| 421 |
+
"loss": 0.7191,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.96,
|
| 426 |
+
"grad_norm": 0.5225895643234253,
|
| 427 |
+
"learning_rate": 8.427876823338736e-06,
|
| 428 |
+
"loss": 0.7132,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.98,
|
| 433 |
+
"grad_norm": 0.4504361152648926,
|
| 434 |
+
"learning_rate": 5.186385737439222e-06,
|
| 435 |
+
"loss": 0.7344,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.99,
|
| 440 |
+
"grad_norm": 0.48884958028793335,
|
| 441 |
+
"learning_rate": 1.9448946515397086e-06,
|
| 442 |
+
"loss": 0.7086,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0,
|
| 447 |
+
"eval_loss": 0.7055141925811768,
|
| 448 |
+
"eval_runtime": 58.7356,
|
| 449 |
+
"eval_samples_per_second": 1.703,
|
| 450 |
+
"eval_steps_per_second": 0.426,
|
| 451 |
+
"step": 625
|
| 452 |
+
}
|
| 453 |
+
],
|
| 454 |
+
"logging_steps": 10,
|
| 455 |
+
"max_steps": 625,
|
| 456 |
+
"num_input_tokens_seen": 0,
|
| 457 |
+
"num_train_epochs": 1,
|
| 458 |
+
"save_steps": 500,
|
| 459 |
+
"total_flos": 4350923021058048.0,
|
| 460 |
+
"train_batch_size": 4,
|
| 461 |
+
"trial_name": null,
|
| 462 |
+
"trial_params": null
|
| 463 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e14b8920d2ddcdf1e4786d20410f42543412cdb9a4550b4654e608c03b98e69a
|
| 3 |
+
size 4920
|