Upload 9 files
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +132 -0
- trainer_state.json +568 -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": "microsoft/Phi-3-mini-4k-instruct",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 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 |
+
"qkv_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_up_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 sha256:57aa1ec6a1390d8594329f92fae2e77935d090535739a023d0711237966b874d
|
| 3 |
+
size 50365768
|
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 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
|
@@ -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 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|end|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 4096,
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"split_special_tokens": false,
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false
|
| 132 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9969666329625886,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 741,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04044489383215369,
|
| 13 |
+
"grad_norm": 0.32977694272994995,
|
| 14 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 15 |
+
"loss": 1.0598,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08088978766430738,
|
| 20 |
+
"grad_norm": 0.37004101276397705,
|
| 21 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 22 |
+
"loss": 0.9336,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12133468149646107,
|
| 27 |
+
"grad_norm": 0.4031585156917572,
|
| 28 |
+
"learning_rate": 4e-05,
|
| 29 |
+
"loss": 0.8984,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16177957532861476,
|
| 34 |
+
"grad_norm": 1.509679913520813,
|
| 35 |
+
"learning_rate": 5.333333333333333e-05,
|
| 36 |
+
"loss": 0.8535,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20222446916076844,
|
| 41 |
+
"grad_norm": 0.49513012170791626,
|
| 42 |
+
"learning_rate": 6.666666666666667e-05,
|
| 43 |
+
"loss": 0.8269,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24266936299292213,
|
| 48 |
+
"grad_norm": 0.6064131855964661,
|
| 49 |
+
"learning_rate": 8e-05,
|
| 50 |
+
"loss": 0.8761,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28311425682507585,
|
| 55 |
+
"grad_norm": 0.5522051453590393,
|
| 56 |
+
"learning_rate": 9.333333333333334e-05,
|
| 57 |
+
"loss": 0.8263,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3235591506572295,
|
| 62 |
+
"grad_norm": 0.6795193552970886,
|
| 63 |
+
"learning_rate": 9.998609371351944e-05,
|
| 64 |
+
"loss": 0.8209,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3640040444893832,
|
| 69 |
+
"grad_norm": 1.0687181949615479,
|
| 70 |
+
"learning_rate": 9.9874889829725e-05,
|
| 71 |
+
"loss": 0.8256,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4044489383215369,
|
| 76 |
+
"grad_norm": 0.44715842604637146,
|
| 77 |
+
"learning_rate": 9.965272945701839e-05,
|
| 78 |
+
"loss": 0.8317,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4448938321536906,
|
| 83 |
+
"grad_norm": 0.5097022652626038,
|
| 84 |
+
"learning_rate": 9.932010683478573e-05,
|
| 85 |
+
"loss": 0.7896,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48533872598584427,
|
| 90 |
+
"grad_norm": 0.3602050840854645,
|
| 91 |
+
"learning_rate": 9.887776194738432e-05,
|
| 92 |
+
"loss": 0.7551,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5257836198179979,
|
| 97 |
+
"grad_norm": 0.5977407693862915,
|
| 98 |
+
"learning_rate": 9.832667887790208e-05,
|
| 99 |
+
"loss": 0.8371,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5662285136501517,
|
| 104 |
+
"grad_norm": 0.376720130443573,
|
| 105 |
+
"learning_rate": 9.766808361887147e-05,
|
| 106 |
+
"loss": 0.6978,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6066734074823054,
|
| 111 |
+
"grad_norm": 0.6886475086212158,
|
| 112 |
+
"learning_rate": 9.69034413448083e-05,
|
| 113 |
+
"loss": 0.7482,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.647118301314459,
|
| 118 |
+
"grad_norm": 0.6275140047073364,
|
| 119 |
+
"learning_rate": 9.603445315264317e-05,
|
| 120 |
+
"loss": 0.7765,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6875631951466128,
|
| 125 |
+
"grad_norm": 0.795728325843811,
|
| 126 |
+
"learning_rate": 9.506305227729723e-05,
|
| 127 |
+
"loss": 0.7824,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7280080889787665,
|
| 132 |
+
"grad_norm": 0.3607877194881439,
|
| 133 |
+
"learning_rate": 9.399139979082148e-05,
|
| 134 |
+
"loss": 0.865,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7684529828109201,
|
| 139 |
+
"grad_norm": 0.5607595443725586,
|
| 140 |
+
"learning_rate": 9.282187979466729e-05,
|
| 141 |
+
"loss": 0.7783,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8088978766430738,
|
| 146 |
+
"grad_norm": 0.7133780121803284,
|
| 147 |
+
"learning_rate": 9.155709411578468e-05,
|
| 148 |
+
"loss": 0.766,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8493427704752275,
|
| 153 |
+
"grad_norm": 0.3629770576953888,
|
| 154 |
+
"learning_rate": 9.019985651834703e-05,
|
| 155 |
+
"loss": 0.7815,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8897876643073812,
|
| 160 |
+
"grad_norm": 0.656274676322937,
|
| 161 |
+
"learning_rate": 8.875318644398008e-05,
|
| 162 |
+
"loss": 0.7829,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9302325581395349,
|
| 167 |
+
"grad_norm": 0.4777781367301941,
|
| 168 |
+
"learning_rate": 8.722030229442095e-05,
|
| 169 |
+
"loss": 0.7668,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9706774519716885,
|
| 174 |
+
"grad_norm": 0.46228083968162537,
|
| 175 |
+
"learning_rate": 8.560461427155128e-05,
|
| 176 |
+
"loss": 0.7282,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0111223458038423,
|
| 181 |
+
"grad_norm": 0.38738882541656494,
|
| 182 |
+
"learning_rate": 8.390971679073332e-05,
|
| 183 |
+
"loss": 0.718,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0515672396359959,
|
| 188 |
+
"grad_norm": 0.3507082760334015,
|
| 189 |
+
"learning_rate": 8.213938048432697e-05,
|
| 190 |
+
"loss": 0.6764,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0920121334681496,
|
| 195 |
+
"grad_norm": 0.5163873434066772,
|
| 196 |
+
"learning_rate": 8.029754381317741e-05,
|
| 197 |
+
"loss": 0.7534,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.1324570273003034,
|
| 202 |
+
"grad_norm": 0.41655170917510986,
|
| 203 |
+
"learning_rate": 7.838830430473539e-05,
|
| 204 |
+
"loss": 0.7141,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.172901921132457,
|
| 209 |
+
"grad_norm": 0.5573180913925171,
|
| 210 |
+
"learning_rate": 7.641590943730258e-05,
|
| 211 |
+
"loss": 0.698,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2133468149646107,
|
| 216 |
+
"grad_norm": 0.4728916585445404,
|
| 217 |
+
"learning_rate": 7.438474719068173e-05,
|
| 218 |
+
"loss": 0.7408,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2537917087967645,
|
| 223 |
+
"grad_norm": 0.5964640974998474,
|
| 224 |
+
"learning_rate": 7.22993362842538e-05,
|
| 225 |
+
"loss": 0.7214,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.294236602628918,
|
| 230 |
+
"grad_norm": 0.4228028655052185,
|
| 231 |
+
"learning_rate": 7.016431612419907e-05,
|
| 232 |
+
"loss": 0.7472,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.3346814964610718,
|
| 237 |
+
"grad_norm": 0.4832104444503784,
|
| 238 |
+
"learning_rate": 6.79844364822268e-05,
|
| 239 |
+
"loss": 0.6434,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3751263902932256,
|
| 244 |
+
"grad_norm": 0.6881019473075867,
|
| 245 |
+
"learning_rate": 6.576454692877513e-05,
|
| 246 |
+
"loss": 0.7244,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.4155712841253791,
|
| 251 |
+
"grad_norm": 0.4529273509979248,
|
| 252 |
+
"learning_rate": 6.35095860441891e-05,
|
| 253 |
+
"loss": 0.7019,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.456016177957533,
|
| 258 |
+
"grad_norm": 0.40597546100616455,
|
| 259 |
+
"learning_rate": 6.122457043187862e-05,
|
| 260 |
+
"loss": 0.6734,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.4964610717896867,
|
| 265 |
+
"grad_norm": 1.0302621126174927,
|
| 266 |
+
"learning_rate": 5.891458355789879e-05,
|
| 267 |
+
"loss": 0.6775,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.5369059656218402,
|
| 272 |
+
"grad_norm": 0.7270640134811401,
|
| 273 |
+
"learning_rate": 5.658476444178118e-05,
|
| 274 |
+
"loss": 0.6988,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5773508594539938,
|
| 279 |
+
"grad_norm": 0.9417754411697388,
|
| 280 |
+
"learning_rate": 5.4240296223775465e-05,
|
| 281 |
+
"loss": 0.7473,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.6177957532861478,
|
| 286 |
+
"grad_norm": 0.519805908203125,
|
| 287 |
+
"learning_rate": 5.1886394633935865e-05,
|
| 288 |
+
"loss": 0.6724,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6582406471183013,
|
| 293 |
+
"grad_norm": 0.38718143105506897,
|
| 294 |
+
"learning_rate": 4.952829638870516e-05,
|
| 295 |
+
"loss": 0.6676,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6986855409504549,
|
| 300 |
+
"grad_norm": 0.5094408392906189,
|
| 301 |
+
"learning_rate": 4.717124754081038e-05,
|
| 302 |
+
"loss": 0.6828,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.7391304347826086,
|
| 307 |
+
"grad_norm": 0.8842711448669434,
|
| 308 |
+
"learning_rate": 4.4820491808388036e-05,
|
| 309 |
+
"loss": 0.7012,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.7795753286147624,
|
| 314 |
+
"grad_norm": 0.44060903787612915,
|
| 315 |
+
"learning_rate": 4.2481258909303165e-05,
|
| 316 |
+
"loss": 0.7331,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.820020222446916,
|
| 321 |
+
"grad_norm": 0.8252304196357727,
|
| 322 |
+
"learning_rate": 4.0158752926614736e-05,
|
| 323 |
+
"loss": 0.651,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8604651162790697,
|
| 328 |
+
"grad_norm": 0.779067873954773,
|
| 329 |
+
"learning_rate": 3.7858140731070646e-05,
|
| 330 |
+
"loss": 0.6252,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.9009100101112235,
|
| 335 |
+
"grad_norm": 0.8989632725715637,
|
| 336 |
+
"learning_rate": 3.5584540486388904e-05,
|
| 337 |
+
"loss": 0.6731,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.941354903943377,
|
| 342 |
+
"grad_norm": 0.8114097118377686,
|
| 343 |
+
"learning_rate": 3.334301026289712e-05,
|
| 344 |
+
"loss": 0.688,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9817997977755308,
|
| 349 |
+
"grad_norm": 0.8452021479606628,
|
| 350 |
+
"learning_rate": 3.113853678486151e-05,
|
| 351 |
+
"loss": 0.6877,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0222446916076846,
|
| 356 |
+
"grad_norm": 0.32683417201042175,
|
| 357 |
+
"learning_rate": 2.89760243365393e-05,
|
| 358 |
+
"loss": 0.7022,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0222446916076846,
|
| 363 |
+
"eval_loss": 0.7777388095855713,
|
| 364 |
+
"eval_runtime": 14.8948,
|
| 365 |
+
"eval_samples_per_second": 14.77,
|
| 366 |
+
"eval_steps_per_second": 14.77,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.062689585439838,
|
| 371 |
+
"grad_norm": 0.6976883411407471,
|
| 372 |
+
"learning_rate": 2.6860283851635065e-05,
|
| 373 |
+
"loss": 0.6789,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.1031344792719917,
|
| 378 |
+
"grad_norm": 0.5700914263725281,
|
| 379 |
+
"learning_rate": 2.4796022210433767e-05,
|
| 380 |
+
"loss": 0.6045,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.1435793731041457,
|
| 385 |
+
"grad_norm": 0.7176660895347595,
|
| 386 |
+
"learning_rate": 2.2787831768421046e-05,
|
| 387 |
+
"loss": 0.5851,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.1840242669362993,
|
| 392 |
+
"grad_norm": 0.42338210344314575,
|
| 393 |
+
"learning_rate": 2.0840180139686334e-05,
|
| 394 |
+
"loss": 0.5445,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.224469160768453,
|
| 399 |
+
"grad_norm": 0.5574066638946533,
|
| 400 |
+
"learning_rate": 1.895740025783782e-05,
|
| 401 |
+
"loss": 0.6711,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.264914054600607,
|
| 406 |
+
"grad_norm": 0.5283611416816711,
|
| 407 |
+
"learning_rate": 1.7143680736540574e-05,
|
| 408 |
+
"loss": 0.5776,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.3053589484327603,
|
| 413 |
+
"grad_norm": 0.8224833011627197,
|
| 414 |
+
"learning_rate": 1.5403056551122697e-05,
|
| 415 |
+
"loss": 0.6412,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.345803842264914,
|
| 420 |
+
"grad_norm": 0.6981547474861145,
|
| 421 |
+
"learning_rate": 1.373940006198014e-05,
|
| 422 |
+
"loss": 0.5975,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.386248736097068,
|
| 427 |
+
"grad_norm": 0.7778781056404114,
|
| 428 |
+
"learning_rate": 1.2156412399750422e-05,
|
| 429 |
+
"loss": 0.6177,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.4266936299292214,
|
| 434 |
+
"grad_norm": 0.6286150813102722,
|
| 435 |
+
"learning_rate": 1.0657615231420493e-05,
|
| 436 |
+
"loss": 0.6231,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.467138523761375,
|
| 441 |
+
"grad_norm": 0.5124749541282654,
|
| 442 |
+
"learning_rate": 9.246342925686885e-06,
|
| 443 |
+
"loss": 0.6518,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.507583417593529,
|
| 448 |
+
"grad_norm": 0.671191394329071,
|
| 449 |
+
"learning_rate": 7.925735134997492e-06,
|
| 450 |
+
"loss": 0.5655,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.5480283114256825,
|
| 455 |
+
"grad_norm": 0.45089051127433777,
|
| 456 |
+
"learning_rate": 6.698729810778065e-06,
|
| 457 |
+
"loss": 0.5719,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.588473205257836,
|
| 462 |
+
"grad_norm": 0.8623360395431519,
|
| 463 |
+
"learning_rate": 5.56805666738221e-06,
|
| 464 |
+
"loss": 0.6901,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.62891809908999,
|
| 469 |
+
"grad_norm": 0.522199809551239,
|
| 470 |
+
"learning_rate": 4.536231109305577e-06,
|
| 471 |
+
"loss": 0.6108,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.6693629929221436,
|
| 476 |
+
"grad_norm": 1.2643201351165771,
|
| 477 |
+
"learning_rate": 3.605548635174533e-06,
|
| 478 |
+
"loss": 0.6145,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.709807886754297,
|
| 483 |
+
"grad_norm": 0.8499836921691895,
|
| 484 |
+
"learning_rate": 2.7780797309585606e-06,
|
| 485 |
+
"loss": 0.5928,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.750252780586451,
|
| 490 |
+
"grad_norm": 0.713811457157135,
|
| 491 |
+
"learning_rate": 2.0556652637675143e-06,
|
| 492 |
+
"loss": 0.5374,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.7906976744186047,
|
| 497 |
+
"grad_norm": 0.7115636467933655,
|
| 498 |
+
"learning_rate": 1.4399123864811903e-06,
|
| 499 |
+
"loss": 0.5949,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.8311425682507583,
|
| 504 |
+
"grad_norm": 0.6987712979316711,
|
| 505 |
+
"learning_rate": 9.321909623220271e-07,
|
| 506 |
+
"loss": 0.6557,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.8715874620829123,
|
| 511 |
+
"grad_norm": 0.4708057940006256,
|
| 512 |
+
"learning_rate": 5.336305173253231e-07,
|
| 513 |
+
"loss": 0.6258,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.912032355915066,
|
| 518 |
+
"grad_norm": 0.8962985873222351,
|
| 519 |
+
"learning_rate": 2.451177274866989e-07,
|
| 520 |
+
"loss": 0.5874,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.9524772497472194,
|
| 525 |
+
"grad_norm": 0.7313467860221863,
|
| 526 |
+
"learning_rate": 6.729444617717961e-08,
|
| 527 |
+
"loss": 0.6104,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.9929221435793734,
|
| 532 |
+
"grad_norm": 0.69645094871521,
|
| 533 |
+
"learning_rate": 5.562762142974353e-10,
|
| 534 |
+
"loss": 0.5679,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.9969666329625886,
|
| 539 |
+
"step": 741,
|
| 540 |
+
"total_flos": 4.204244398782874e+16,
|
| 541 |
+
"train_loss": 0.7069849928944056,
|
| 542 |
+
"train_runtime": 1363.5787,
|
| 543 |
+
"train_samples_per_second": 4.352,
|
| 544 |
+
"train_steps_per_second": 0.543
|
| 545 |
+
}
|
| 546 |
+
],
|
| 547 |
+
"logging_steps": 10,
|
| 548 |
+
"max_steps": 741,
|
| 549 |
+
"num_input_tokens_seen": 0,
|
| 550 |
+
"num_train_epochs": 3,
|
| 551 |
+
"save_steps": 500,
|
| 552 |
+
"stateful_callbacks": {
|
| 553 |
+
"TrainerControl": {
|
| 554 |
+
"args": {
|
| 555 |
+
"should_epoch_stop": false,
|
| 556 |
+
"should_evaluate": false,
|
| 557 |
+
"should_log": false,
|
| 558 |
+
"should_save": true,
|
| 559 |
+
"should_training_stop": true
|
| 560 |
+
},
|
| 561 |
+
"attributes": {}
|
| 562 |
+
}
|
| 563 |
+
},
|
| 564 |
+
"total_flos": 4.204244398782874e+16,
|
| 565 |
+
"train_batch_size": 1,
|
| 566 |
+
"trial_name": null,
|
| 567 |
+
"trial_params": null
|
| 568 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a6f6be4f7dd5326cb5fe78b20bb37641ddbb4bef25dfa9df2598768a0e5b5c
|
| 3 |
+
size 5304
|