first commit
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +38 -0
- trainer_state.json +400 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "JackFram/llama-160m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 12,
|
| 15 |
+
"num_hidden_layers": 12,
|
| 16 |
+
"num_key_value_heads": 12,
|
| 17 |
+
"pad_token_id": 1,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.33.2"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08934730e6679122a562ba9815956f72272600155f282da08d63e5b81d7d94fa
|
| 3 |
+
size 649705097
|
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": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": null,
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"spaces_between_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"use_default_system_prompt": true,
|
| 37 |
+
"use_fast": true
|
| 38 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.984,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 62,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1e-05,
|
| 14 |
+
"loss": 3.244,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 2e-05,
|
| 20 |
+
"loss": 2.8814,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 1.9986295347545738e-05,
|
| 26 |
+
"loss": 3.0403,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 1.9945218953682736e-05,
|
| 32 |
+
"loss": 2.6799,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 1.9876883405951378e-05,
|
| 38 |
+
"loss": 2.6526,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 1.9781476007338058e-05,
|
| 44 |
+
"loss": 2.5161,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
+
"learning_rate": 1.9659258262890683e-05,
|
| 50 |
+
"loss": 2.4145,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 56 |
+
"loss": 2.3619,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.29,
|
| 61 |
+
"learning_rate": 1.9335804264972018e-05,
|
| 62 |
+
"loss": 2.4374,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.32,
|
| 67 |
+
"learning_rate": 1.913545457642601e-05,
|
| 68 |
+
"loss": 2.2143,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.35,
|
| 73 |
+
"learning_rate": 1.891006524188368e-05,
|
| 74 |
+
"loss": 2.2496,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.38,
|
| 79 |
+
"learning_rate": 1.866025403784439e-05,
|
| 80 |
+
"loss": 2.1492,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.42,
|
| 85 |
+
"learning_rate": 1.8386705679454243e-05,
|
| 86 |
+
"loss": 2.0843,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.45,
|
| 91 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 92 |
+
"loss": 2.0363,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.48,
|
| 97 |
+
"learning_rate": 1.777145961456971e-05,
|
| 98 |
+
"loss": 2.1496,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.51,
|
| 103 |
+
"learning_rate": 1.7431448254773943e-05,
|
| 104 |
+
"loss": 2.0326,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.54,
|
| 109 |
+
"learning_rate": 1.7071067811865477e-05,
|
| 110 |
+
"loss": 2.0164,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.58,
|
| 115 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 116 |
+
"loss": 2.0463,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.61,
|
| 121 |
+
"learning_rate": 1.6293203910498375e-05,
|
| 122 |
+
"loss": 1.992,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.64,
|
| 127 |
+
"learning_rate": 1.5877852522924733e-05,
|
| 128 |
+
"loss": 1.957,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.67,
|
| 133 |
+
"learning_rate": 1.5446390350150272e-05,
|
| 134 |
+
"loss": 1.8724,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7,
|
| 139 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 140 |
+
"loss": 2.0305,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.74,
|
| 145 |
+
"learning_rate": 1.4539904997395468e-05,
|
| 146 |
+
"loss": 1.8814,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.77,
|
| 151 |
+
"learning_rate": 1.4067366430758004e-05,
|
| 152 |
+
"loss": 1.9395,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8,
|
| 157 |
+
"learning_rate": 1.3583679495453e-05,
|
| 158 |
+
"loss": 1.8587,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.83,
|
| 163 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 164 |
+
"loss": 1.8729,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.86,
|
| 169 |
+
"learning_rate": 1.2588190451025209e-05,
|
| 170 |
+
"loss": 1.8447,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.9,
|
| 175 |
+
"learning_rate": 1.2079116908177592e-05,
|
| 176 |
+
"loss": 1.8578,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.93,
|
| 181 |
+
"learning_rate": 1.156434465040231e-05,
|
| 182 |
+
"loss": 1.7816,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.96,
|
| 187 |
+
"learning_rate": 1.1045284632676535e-05,
|
| 188 |
+
"loss": 1.9164,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.99,
|
| 193 |
+
"learning_rate": 1.0523359562429441e-05,
|
| 194 |
+
"loss": 1.9039,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.02,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 1.6931,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.06,
|
| 205 |
+
"learning_rate": 9.476640437570562e-06,
|
| 206 |
+
"loss": 1.7482,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.09,
|
| 211 |
+
"learning_rate": 8.954715367323468e-06,
|
| 212 |
+
"loss": 1.7157,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.12,
|
| 217 |
+
"learning_rate": 8.43565534959769e-06,
|
| 218 |
+
"loss": 1.7507,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.15,
|
| 223 |
+
"learning_rate": 7.92088309182241e-06,
|
| 224 |
+
"loss": 1.7258,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.18,
|
| 229 |
+
"learning_rate": 7.411809548974792e-06,
|
| 230 |
+
"loss": 1.6307,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.22,
|
| 235 |
+
"learning_rate": 6.909830056250527e-06,
|
| 236 |
+
"loss": 1.6894,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.25,
|
| 241 |
+
"learning_rate": 6.4163205045469975e-06,
|
| 242 |
+
"loss": 1.714,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.28,
|
| 247 |
+
"learning_rate": 5.932633569242e-06,
|
| 248 |
+
"loss": 1.6402,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.31,
|
| 253 |
+
"learning_rate": 5.460095002604533e-06,
|
| 254 |
+
"loss": 1.6554,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.34,
|
| 259 |
+
"learning_rate": 5.000000000000003e-06,
|
| 260 |
+
"loss": 1.6722,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.38,
|
| 265 |
+
"learning_rate": 4.5536096498497295e-06,
|
| 266 |
+
"loss": 1.6376,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.41,
|
| 271 |
+
"learning_rate": 4.12214747707527e-06,
|
| 272 |
+
"loss": 1.6696,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.44,
|
| 277 |
+
"learning_rate": 3.7067960895016277e-06,
|
| 278 |
+
"loss": 1.6975,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.47,
|
| 283 |
+
"learning_rate": 3.308693936411421e-06,
|
| 284 |
+
"loss": 1.6124,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.5,
|
| 289 |
+
"learning_rate": 2.9289321881345257e-06,
|
| 290 |
+
"loss": 1.6798,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.54,
|
| 295 |
+
"learning_rate": 2.5685517452260566e-06,
|
| 296 |
+
"loss": 1.5698,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.57,
|
| 301 |
+
"learning_rate": 2.2285403854302912e-06,
|
| 302 |
+
"loss": 1.6288,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6,
|
| 307 |
+
"learning_rate": 1.9098300562505266e-06,
|
| 308 |
+
"loss": 1.606,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.63,
|
| 313 |
+
"learning_rate": 1.6132943205457607e-06,
|
| 314 |
+
"loss": 1.5923,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.66,
|
| 319 |
+
"learning_rate": 1.339745962155613e-06,
|
| 320 |
+
"loss": 1.6299,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.7,
|
| 325 |
+
"learning_rate": 1.0899347581163222e-06,
|
| 326 |
+
"loss": 1.6253,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.73,
|
| 331 |
+
"learning_rate": 8.645454235739903e-07,
|
| 332 |
+
"loss": 1.715,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.76,
|
| 337 |
+
"learning_rate": 6.641957350279838e-07,
|
| 338 |
+
"loss": 1.6588,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.79,
|
| 343 |
+
"learning_rate": 4.894348370484648e-07,
|
| 344 |
+
"loss": 1.5589,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.82,
|
| 349 |
+
"learning_rate": 3.4074173710931804e-07,
|
| 350 |
+
"loss": 1.6707,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.86,
|
| 355 |
+
"learning_rate": 2.1852399266194312e-07,
|
| 356 |
+
"loss": 1.638,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.89,
|
| 361 |
+
"learning_rate": 1.231165940486234e-07,
|
| 362 |
+
"loss": 1.7396,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.92,
|
| 367 |
+
"learning_rate": 5.4781046317267103e-08,
|
| 368 |
+
"loss": 1.6457,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.95,
|
| 373 |
+
"learning_rate": 1.370465245426167e-08,
|
| 374 |
+
"loss": 1.5623,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.98,
|
| 379 |
+
"learning_rate": 0.0,
|
| 380 |
+
"loss": 1.7258,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.98,
|
| 385 |
+
"step": 62,
|
| 386 |
+
"total_flos": 1.3441958877855744e+16,
|
| 387 |
+
"train_loss": 1.9260368904759806,
|
| 388 |
+
"train_runtime": 626.5721,
|
| 389 |
+
"train_samples_per_second": 12.768,
|
| 390 |
+
"train_steps_per_second": 0.099
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"logging_steps": 1.0,
|
| 394 |
+
"max_steps": 62,
|
| 395 |
+
"num_train_epochs": 2,
|
| 396 |
+
"save_steps": 1000,
|
| 397 |
+
"total_flos": 1.3441958877855744e+16,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdcb7b9b3a733298b4fe7bdcee6104b0fadb89db659d76942004b618797a535e
|
| 3 |
+
size 4027
|