Upload 12 files
Browse files- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +0 -0
- scheduler.pt +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +0 -0
- tokenizer_config.json +42 -0
- trainer_state.json +423 -0
- training_args.bin +0 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyPixel/CodeLlama-7B-Python-bf16-sharded",
|
| 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": 32,
|
| 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": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"q_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e3978b8ed3ff3046fedef368d4b0f6ee012479ff5d7b3488501d29eb69dd752
|
| 3 |
+
size 33571624
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e71534ebc3a3c8f18ef90d5601732b95088617183603a2e0bf5de2422b9fdef4
|
| 3 |
+
size 67217018
|
rng_state.pth
ADDED
|
Binary file (14.2 kB). View file
|
|
|
scheduler.pt
ADDED
|
Binary file (1.06 kB). View file
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
Binary file (500 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": null,
|
| 35 |
+
"model_max_length": 300,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": true
|
| 42 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.818181818181818,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 135,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 14 |
+
"loss": 1.1098,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.36,
|
| 19 |
+
"learning_rate": 4.705882352941177e-05,
|
| 20 |
+
"loss": 1.1831,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.55,
|
| 25 |
+
"learning_rate": 7.058823529411765e-05,
|
| 26 |
+
"loss": 1.1273,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.73,
|
| 31 |
+
"learning_rate": 9.411764705882353e-05,
|
| 32 |
+
"loss": 1.1295,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.09,
|
| 37 |
+
"learning_rate": 0.00011764705882352942,
|
| 38 |
+
"loss": 1.0906,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.27,
|
| 43 |
+
"learning_rate": 0.0001411764705882353,
|
| 44 |
+
"loss": 1.0239,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.45,
|
| 49 |
+
"learning_rate": 0.0001647058823529412,
|
| 50 |
+
"loss": 0.9996,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.64,
|
| 55 |
+
"learning_rate": 0.00018823529411764707,
|
| 56 |
+
"loss": 0.8502,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.82,
|
| 61 |
+
"learning_rate": 0.00019864864864864865,
|
| 62 |
+
"loss": 0.8154,
|
| 63 |
+
"step": 18
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.18,
|
| 67 |
+
"learning_rate": 0.00019594594594594594,
|
| 68 |
+
"loss": 0.71,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.36,
|
| 73 |
+
"learning_rate": 0.00019324324324324326,
|
| 74 |
+
"loss": 0.7255,
|
| 75 |
+
"step": 22
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.55,
|
| 79 |
+
"learning_rate": 0.00019054054054054055,
|
| 80 |
+
"loss": 0.6063,
|
| 81 |
+
"step": 24
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.73,
|
| 85 |
+
"learning_rate": 0.00018783783783783784,
|
| 86 |
+
"loss": 0.6039,
|
| 87 |
+
"step": 26
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.09,
|
| 91 |
+
"learning_rate": 0.00018513513513513513,
|
| 92 |
+
"loss": 0.5068,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.27,
|
| 97 |
+
"learning_rate": 0.00018243243243243245,
|
| 98 |
+
"loss": 0.5053,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.45,
|
| 103 |
+
"learning_rate": 0.00017972972972972974,
|
| 104 |
+
"loss": 0.4882,
|
| 105 |
+
"step": 32
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.64,
|
| 109 |
+
"learning_rate": 0.00017702702702702703,
|
| 110 |
+
"loss": 0.4442,
|
| 111 |
+
"step": 34
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.82,
|
| 115 |
+
"learning_rate": 0.00017432432432432432,
|
| 116 |
+
"loss": 0.5363,
|
| 117 |
+
"step": 36
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.18,
|
| 121 |
+
"learning_rate": 0.00017162162162162164,
|
| 122 |
+
"loss": 0.4253,
|
| 123 |
+
"step": 38
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.36,
|
| 127 |
+
"learning_rate": 0.00016891891891891893,
|
| 128 |
+
"loss": 0.408,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.55,
|
| 133 |
+
"learning_rate": 0.00016621621621621622,
|
| 134 |
+
"loss": 0.3472,
|
| 135 |
+
"step": 42
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.73,
|
| 139 |
+
"learning_rate": 0.0001635135135135135,
|
| 140 |
+
"loss": 0.354,
|
| 141 |
+
"step": 44
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.09,
|
| 145 |
+
"learning_rate": 0.00016081081081081083,
|
| 146 |
+
"loss": 0.3762,
|
| 147 |
+
"step": 46
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.27,
|
| 151 |
+
"learning_rate": 0.00015810810810810812,
|
| 152 |
+
"loss": 0.3216,
|
| 153 |
+
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.45,
|
| 157 |
+
"learning_rate": 0.0001554054054054054,
|
| 158 |
+
"loss": 0.2651,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.64,
|
| 163 |
+
"learning_rate": 0.0001527027027027027,
|
| 164 |
+
"loss": 0.2992,
|
| 165 |
+
"step": 52
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.82,
|
| 169 |
+
"learning_rate": 0.00015000000000000001,
|
| 170 |
+
"loss": 0.282,
|
| 171 |
+
"step": 54
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.18,
|
| 175 |
+
"learning_rate": 0.0001472972972972973,
|
| 176 |
+
"loss": 0.239,
|
| 177 |
+
"step": 56
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.36,
|
| 181 |
+
"learning_rate": 0.00014459459459459462,
|
| 182 |
+
"loss": 0.2548,
|
| 183 |
+
"step": 58
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.55,
|
| 187 |
+
"learning_rate": 0.00014189189189189188,
|
| 188 |
+
"loss": 0.2259,
|
| 189 |
+
"step": 60
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.73,
|
| 193 |
+
"learning_rate": 0.0001391891891891892,
|
| 194 |
+
"loss": 0.2364,
|
| 195 |
+
"step": 62
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.09,
|
| 199 |
+
"learning_rate": 0.0001364864864864865,
|
| 200 |
+
"loss": 0.1785,
|
| 201 |
+
"step": 64
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 7.27,
|
| 205 |
+
"learning_rate": 0.0001337837837837838,
|
| 206 |
+
"loss": 0.1864,
|
| 207 |
+
"step": 66
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.45,
|
| 211 |
+
"learning_rate": 0.00013108108108108107,
|
| 212 |
+
"loss": 0.1786,
|
| 213 |
+
"step": 68
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 7.64,
|
| 217 |
+
"learning_rate": 0.0001283783783783784,
|
| 218 |
+
"loss": 0.1585,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.82,
|
| 223 |
+
"learning_rate": 0.00012567567567567568,
|
| 224 |
+
"loss": 0.1964,
|
| 225 |
+
"step": 72
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.18,
|
| 229 |
+
"learning_rate": 0.000122972972972973,
|
| 230 |
+
"loss": 0.1177,
|
| 231 |
+
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 8.36,
|
| 235 |
+
"learning_rate": 0.00012027027027027027,
|
| 236 |
+
"loss": 0.1259,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.55,
|
| 241 |
+
"learning_rate": 0.00011756756756756758,
|
| 242 |
+
"loss": 0.1448,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.73,
|
| 247 |
+
"learning_rate": 0.00011486486486486487,
|
| 248 |
+
"loss": 0.1562,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 9.09,
|
| 253 |
+
"learning_rate": 0.00011216216216216217,
|
| 254 |
+
"loss": 0.1193,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 9.27,
|
| 259 |
+
"learning_rate": 0.00010945945945945946,
|
| 260 |
+
"loss": 0.1375,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.45,
|
| 265 |
+
"learning_rate": 0.00010675675675675677,
|
| 266 |
+
"loss": 0.1109,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 9.64,
|
| 271 |
+
"learning_rate": 0.00010405405405405406,
|
| 272 |
+
"loss": 0.0994,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 9.82,
|
| 277 |
+
"learning_rate": 0.00010135135135135136,
|
| 278 |
+
"loss": 0.0918,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 10.18,
|
| 283 |
+
"learning_rate": 9.864864864864865e-05,
|
| 284 |
+
"loss": 0.0779,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 10.36,
|
| 289 |
+
"learning_rate": 9.594594594594595e-05,
|
| 290 |
+
"loss": 0.0748,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 10.55,
|
| 295 |
+
"learning_rate": 9.324324324324324e-05,
|
| 296 |
+
"loss": 0.087,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.73,
|
| 301 |
+
"learning_rate": 9.054054054054055e-05,
|
| 302 |
+
"loss": 0.0914,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 11.09,
|
| 307 |
+
"learning_rate": 8.783783783783784e-05,
|
| 308 |
+
"loss": 0.0768,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 11.27,
|
| 313 |
+
"learning_rate": 8.513513513513514e-05,
|
| 314 |
+
"loss": 0.0619,
|
| 315 |
+
"step": 102
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 11.45,
|
| 319 |
+
"learning_rate": 8.243243243243243e-05,
|
| 320 |
+
"loss": 0.0764,
|
| 321 |
+
"step": 104
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.64,
|
| 325 |
+
"learning_rate": 7.972972972972974e-05,
|
| 326 |
+
"loss": 0.0531,
|
| 327 |
+
"step": 106
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 11.82,
|
| 331 |
+
"learning_rate": 7.702702702702703e-05,
|
| 332 |
+
"loss": 0.0571,
|
| 333 |
+
"step": 108
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 12.18,
|
| 337 |
+
"learning_rate": 7.432432432432433e-05,
|
| 338 |
+
"loss": 0.0513,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 12.36,
|
| 343 |
+
"learning_rate": 7.162162162162162e-05,
|
| 344 |
+
"loss": 0.0478,
|
| 345 |
+
"step": 112
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 12.55,
|
| 349 |
+
"learning_rate": 6.891891891891892e-05,
|
| 350 |
+
"loss": 0.0532,
|
| 351 |
+
"step": 114
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 12.73,
|
| 355 |
+
"learning_rate": 6.621621621621621e-05,
|
| 356 |
+
"loss": 0.0535,
|
| 357 |
+
"step": 116
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 13.09,
|
| 361 |
+
"learning_rate": 6.351351351351352e-05,
|
| 362 |
+
"loss": 0.0415,
|
| 363 |
+
"step": 118
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 13.27,
|
| 367 |
+
"learning_rate": 6.0810810810810814e-05,
|
| 368 |
+
"loss": 0.0449,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 13.45,
|
| 373 |
+
"learning_rate": 5.8108108108108105e-05,
|
| 374 |
+
"loss": 0.0507,
|
| 375 |
+
"step": 122
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 13.64,
|
| 379 |
+
"learning_rate": 5.540540540540541e-05,
|
| 380 |
+
"loss": 0.0411,
|
| 381 |
+
"step": 124
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 13.82,
|
| 385 |
+
"learning_rate": 5.27027027027027e-05,
|
| 386 |
+
"loss": 0.0397,
|
| 387 |
+
"step": 126
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 14.18,
|
| 391 |
+
"learning_rate": 5e-05,
|
| 392 |
+
"loss": 0.0386,
|
| 393 |
+
"step": 128
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 14.36,
|
| 397 |
+
"learning_rate": 4.72972972972973e-05,
|
| 398 |
+
"loss": 0.0399,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 14.55,
|
| 403 |
+
"learning_rate": 4.4594594594594596e-05,
|
| 404 |
+
"loss": 0.0332,
|
| 405 |
+
"step": 132
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 14.73,
|
| 409 |
+
"learning_rate": 4.189189189189189e-05,
|
| 410 |
+
"loss": 0.0376,
|
| 411 |
+
"step": 134
|
| 412 |
+
}
|
| 413 |
+
],
|
| 414 |
+
"logging_steps": 2,
|
| 415 |
+
"max_steps": 165,
|
| 416 |
+
"num_input_tokens_seen": 0,
|
| 417 |
+
"num_train_epochs": 15,
|
| 418 |
+
"save_steps": 500,
|
| 419 |
+
"total_flos": 1.250373390336e+16,
|
| 420 |
+
"train_batch_size": 8,
|
| 421 |
+
"trial_name": null,
|
| 422 |
+
"trial_params": null
|
| 423 |
+
}
|
training_args.bin
ADDED
|
Binary file (4.73 kB). View file
|
|
|