Upload alpaca-lora-based-origin-llama7b with huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- alpaca-lora-based-origin-llama7b/finetune.py +164 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/adapter_config.json +18 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/adapter_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/rng_state_0.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/rng_state_1.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/scaler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/scheduler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/trainer_state.json +4164 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/training_args.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/rng_state_0.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/rng_state_1.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/scaler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/scheduler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/trainer_state.json +4232 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/training_args.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/rng_state_0.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/rng_state_1.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/scaler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/scheduler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/trainer_state.json +4300 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/training_args.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-35-50_autodl-container-a629119d3c-e4df2c26/1679643354.1908646/events.out.tfevents.1679643354.autodl-container-a629119d3c-e4df2c26.49450.1 +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-35-50_autodl-container-a629119d3c-e4df2c26/events.out.tfevents.1679643354.autodl-container-a629119d3c-e4df2c26.49450.0 +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-45-35_autodl-container-a629119d3c-e4df2c26/1679643935.915997/events.out.tfevents.1679643935.autodl-container-a629119d3c-e4df2c26.51017.1 +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-45-35_autodl-container-a629119d3c-e4df2c26/events.out.tfevents.1679643935.autodl-container-a629119d3c-e4df2c26.51017.0 +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/adapter_config.json +18 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/adapter_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/rng_state.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/scaler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/scheduler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/trainer_state.json +0 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/training_args.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/rng_state.pth +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/scaler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/scheduler.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/trainer_state.json +0 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/training_args.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/optimizer.pt +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/pytorch_model.bin +3 -0
- alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/rng_state.pth +3 -0
alpaca-lora-based-origin-llama7b/finetune.py
ADDED
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import sys
|
3 |
+
|
4 |
+
import torch
|
5 |
+
import torch.nn as nn
|
6 |
+
import bitsandbytes as bnb
|
7 |
+
from datasets import load_dataset
|
8 |
+
import transformers
|
9 |
+
from peft import PeftModel
|
10 |
+
import wandb
|
11 |
+
|
12 |
+
|
13 |
+
assert (
|
14 |
+
"LlamaTokenizer" in transformers._import_structure["models.llama"]
|
15 |
+
), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
|
16 |
+
from transformers import LlamaForCausalLM, LlamaTokenizer
|
17 |
+
from peft import (
|
18 |
+
prepare_model_for_int8_training,
|
19 |
+
LoraConfig,
|
20 |
+
get_peft_model,
|
21 |
+
get_peft_model_state_dict,
|
22 |
+
)
|
23 |
+
|
24 |
+
|
25 |
+
# optimized for RTX 4090. for larger GPUs, increase some of these?
|
26 |
+
MICRO_BATCH_SIZE = 64 # this could actually be 5 but i like powers of 2
|
27 |
+
BATCH_SIZE = 128
|
28 |
+
GRADIENT_ACCUMULATION_STEPS = BATCH_SIZE // MICRO_BATCH_SIZE
|
29 |
+
EPOCHS = 2 # we don't always need 3 tbh
|
30 |
+
LEARNING_RATE = 3e-4 # the Karpathy constant
|
31 |
+
CUTOFF_LEN = 256 # 256 accounts for about 96% of the data
|
32 |
+
LORA_R = 8
|
33 |
+
LORA_ALPHA = 16
|
34 |
+
LORA_DROPOUT = 0.05
|
35 |
+
VAL_SET_SIZE = 2000
|
36 |
+
TARGET_MODULES = [
|
37 |
+
"q_proj",
|
38 |
+
"v_proj",
|
39 |
+
]
|
40 |
+
DATA_PATH = "alpaca_data.json"
|
41 |
+
DATA_PATH = "belle_open_source_1M.train.json"
|
42 |
+
OUTPUT_DIR = "lora-alpaca"
|
43 |
+
|
44 |
+
device_map = "auto"
|
45 |
+
world_size = int(os.environ.get("WORLD_SIZE", 1))
|
46 |
+
ddp = world_size != 1
|
47 |
+
if ddp:
|
48 |
+
device_map = {"": int(os.environ.get("LOCAL_RANK") or 0)}
|
49 |
+
GRADIENT_ACCUMULATION_STEPS = GRADIENT_ACCUMULATION_STEPS // world_size
|
50 |
+
|
51 |
+
model = LlamaForCausalLM.from_pretrained(
|
52 |
+
"/ndk/ai-repos/train-llama/models/7b_hf",
|
53 |
+
load_in_8bit=True,
|
54 |
+
device_map=device_map,
|
55 |
+
)
|
56 |
+
tokenizer = LlamaTokenizer.from_pretrained(
|
57 |
+
"/ndk/ai-repos/train-llama/models/7b_hf", add_eos_token=True
|
58 |
+
)
|
59 |
+
|
60 |
+
model = prepare_model_for_int8_training(model)
|
61 |
+
|
62 |
+
config = LoraConfig(
|
63 |
+
r=LORA_R,
|
64 |
+
lora_alpha=LORA_ALPHA,
|
65 |
+
target_modules=TARGET_MODULES,
|
66 |
+
lora_dropout=LORA_DROPOUT,
|
67 |
+
bias="none",
|
68 |
+
task_type="CAUSAL_LM",
|
69 |
+
)
|
70 |
+
#model = get_peft_model(model, config)
|
71 |
+
|
72 |
+
model = PeftModel.from_pretrained (
|
73 |
+
model,
|
74 |
+
"./lora-alpaca-cn-remote",
|
75 |
+
torch_dtype=torch.float16,
|
76 |
+
)
|
77 |
+
|
78 |
+
|
79 |
+
tokenizer.pad_token_id = 0 # unk. we want this to be different from the eos token
|
80 |
+
data = load_dataset("json", data_files=DATA_PATH)
|
81 |
+
|
82 |
+
|
83 |
+
def generate_prompt(data_point):
|
84 |
+
# sorry about the formatting disaster gotta move fast
|
85 |
+
return f"""以下是描述任务的说明。 编写适当地完成请求的响应。
|
86 |
+
### 输入:
|
87 |
+
{data_point["input"]}
|
88 |
+
|
89 |
+
### 输出:
|
90 |
+
{data_point["target"]}"""
|
91 |
+
|
92 |
+
|
93 |
+
def tokenize(prompt):
|
94 |
+
# there's probably a way to do this with the tokenizer settings
|
95 |
+
# but again, gotta move fast
|
96 |
+
result = tokenizer(
|
97 |
+
prompt,
|
98 |
+
truncation=True,
|
99 |
+
max_length=CUTOFF_LEN + 1,
|
100 |
+
padding="max_length",
|
101 |
+
)
|
102 |
+
return {
|
103 |
+
"input_ids": result["input_ids"][:-1],
|
104 |
+
"attention_mask": result["attention_mask"][:-1],
|
105 |
+
}
|
106 |
+
|
107 |
+
|
108 |
+
def generate_and_tokenize_prompt(data_point):
|
109 |
+
prompt = generate_prompt(data_point)
|
110 |
+
return tokenize(prompt)
|
111 |
+
|
112 |
+
|
113 |
+
if VAL_SET_SIZE > 0:
|
114 |
+
train_val = data["train"].train_test_split(
|
115 |
+
test_size=VAL_SET_SIZE, shuffle=True, seed=42
|
116 |
+
)
|
117 |
+
train_data = train_val["train"].shuffle().map(generate_and_tokenize_prompt)
|
118 |
+
val_data = train_val["test"].shuffle().map(generate_and_tokenize_prompt)
|
119 |
+
else:
|
120 |
+
train_data = data["train"].shuffle().map(generate_and_tokenize_prompt)
|
121 |
+
val_data = None
|
122 |
+
|
123 |
+
|
124 |
+
wandb.init(project="llama-lora")
|
125 |
+
|
126 |
+
trainer = transformers.Trainer(
|
127 |
+
model=model,
|
128 |
+
train_dataset=train_data,
|
129 |
+
eval_dataset=val_data,
|
130 |
+
args=transformers.TrainingArguments(
|
131 |
+
per_device_train_batch_size=MICRO_BATCH_SIZE,
|
132 |
+
gradient_accumulation_steps=GRADIENT_ACCUMULATION_STEPS,
|
133 |
+
warmup_steps=100,
|
134 |
+
num_train_epochs=EPOCHS,
|
135 |
+
learning_rate=LEARNING_RATE,
|
136 |
+
fp16=True,
|
137 |
+
logging_steps=20,
|
138 |
+
evaluation_strategy="steps" if VAL_SET_SIZE > 0 else "no",
|
139 |
+
save_strategy="steps",
|
140 |
+
eval_steps=200 if VAL_SET_SIZE > 0 else None,
|
141 |
+
save_steps=200,
|
142 |
+
output_dir=OUTPUT_DIR,
|
143 |
+
save_total_limit=3,
|
144 |
+
load_best_model_at_end=True if VAL_SET_SIZE > 0 else False,
|
145 |
+
ddp_find_unused_parameters=False if ddp else None,
|
146 |
+
),
|
147 |
+
data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),
|
148 |
+
)
|
149 |
+
model.config.use_cache = False
|
150 |
+
|
151 |
+
old_state_dict = model.state_dict
|
152 |
+
model.state_dict = (
|
153 |
+
lambda self, *_, **__: get_peft_model_state_dict(self, old_state_dict())
|
154 |
+
).__get__(model, type(model))
|
155 |
+
|
156 |
+
if torch.__version__ >= "2" and sys.platform != "win32":
|
157 |
+
model = torch.compile(model)
|
158 |
+
|
159 |
+
trainer.train()
|
160 |
+
|
161 |
+
model.save_pretrained(OUTPUT_DIR)
|
162 |
+
|
163 |
+
print("\n If there's a warning about missing keys above, please disregard :)")
|
164 |
+
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/adapter_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "/root/autodl-tmp/llama_hf",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"lora_alpha": 16,
|
8 |
+
"lora_dropout": 0.05,
|
9 |
+
"merge_weights": false,
|
10 |
+
"modules_to_save": null,
|
11 |
+
"peft_type": "LORA",
|
12 |
+
"r": 8,
|
13 |
+
"target_modules": [
|
14 |
+
"q_proj",
|
15 |
+
"v_proj"
|
16 |
+
],
|
17 |
+
"task_type": "CAUSAL_LM"
|
18 |
+
}
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2948f6764ef3ff5e051d05bbb765f7104f8add4f66f9bd68bc14c3a100b6478d
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d129add58d64413cc002d22d05022822a46a7898208682a5f2510de08324fcb
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f0f5cec0e1f2454b1f8855ee479675477cb79999a84192db56aa3a57a1cb468
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:208b8872c6017de913817448486f5d4838856d2ab3b06abdd852908b8a981947
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d06cca3f3250b22a4e1c303e21fb8d0c7c535b0e993559911d99dcdb93c41c3
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9611887fb095d16dea29537243a8f5ead09cf63a435218000ff5a105864011d6
|
3 |
+
size 557
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66a6506cbaa6f775027714b991992b3b6d3e97768b6aaa19b631f657d42b353b
|
3 |
+
size 627
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/trainer_state.json
ADDED
@@ -0,0 +1,4164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6372544765472412,
|
3 |
+
"best_model_checkpoint": "lora-alpaca-cn/checkpoint-12200",
|
4 |
+
"epoch": 2.884160756501182,
|
5 |
+
"global_step": 12200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 5.9999999999999995e-05,
|
13 |
+
"loss": 1.7735,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 0.00011999999999999999,
|
19 |
+
"loss": 1.1358,
|
20 |
+
"step": 40
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 0.00017999999999999998,
|
25 |
+
"loss": 0.9749,
|
26 |
+
"step": 60
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 0.00023999999999999998,
|
31 |
+
"loss": 0.9316,
|
32 |
+
"step": 80
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 0.9072,
|
38 |
+
"step": 100
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 0.0002995234312946783,
|
43 |
+
"loss": 0.8963,
|
44 |
+
"step": 120
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"learning_rate": 0.0002990468625893566,
|
49 |
+
"loss": 0.8853,
|
50 |
+
"step": 140
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.04,
|
54 |
+
"learning_rate": 0.0002985702938840349,
|
55 |
+
"loss": 0.8709,
|
56 |
+
"step": 160
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04,
|
60 |
+
"learning_rate": 0.00029809372517871323,
|
61 |
+
"loss": 0.8555,
|
62 |
+
"step": 180
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.05,
|
66 |
+
"learning_rate": 0.00029761715647339156,
|
67 |
+
"loss": 0.8584,
|
68 |
+
"step": 200
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.05,
|
72 |
+
"eval_loss": 0.8360834717750549,
|
73 |
+
"eval_runtime": 49.29,
|
74 |
+
"eval_samples_per_second": 40.576,
|
75 |
+
"eval_steps_per_second": 2.536,
|
76 |
+
"step": 200
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.05,
|
80 |
+
"learning_rate": 0.0002971405877680699,
|
81 |
+
"loss": 0.859,
|
82 |
+
"step": 220
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.06,
|
86 |
+
"learning_rate": 0.00029666401906274816,
|
87 |
+
"loss": 0.8511,
|
88 |
+
"step": 240
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.06,
|
92 |
+
"learning_rate": 0.0002961874503574265,
|
93 |
+
"loss": 0.8401,
|
94 |
+
"step": 260
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.07,
|
98 |
+
"learning_rate": 0.0002957108816521048,
|
99 |
+
"loss": 0.8357,
|
100 |
+
"step": 280
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07,
|
104 |
+
"learning_rate": 0.00029523431294678314,
|
105 |
+
"loss": 0.8413,
|
106 |
+
"step": 300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.08,
|
110 |
+
"learning_rate": 0.00029475774424146147,
|
111 |
+
"loss": 0.8283,
|
112 |
+
"step": 320
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.08,
|
116 |
+
"learning_rate": 0.0002942811755361398,
|
117 |
+
"loss": 0.8202,
|
118 |
+
"step": 340
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.09,
|
122 |
+
"learning_rate": 0.00029380460683081807,
|
123 |
+
"loss": 0.8222,
|
124 |
+
"step": 360
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.09,
|
128 |
+
"learning_rate": 0.0002933280381254964,
|
129 |
+
"loss": 0.8178,
|
130 |
+
"step": 380
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.09,
|
134 |
+
"learning_rate": 0.0002928514694201747,
|
135 |
+
"loss": 0.8177,
|
136 |
+
"step": 400
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.09,
|
140 |
+
"eval_loss": 0.7966175079345703,
|
141 |
+
"eval_runtime": 49.1752,
|
142 |
+
"eval_samples_per_second": 40.671,
|
143 |
+
"eval_steps_per_second": 2.542,
|
144 |
+
"step": 400
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.1,
|
148 |
+
"learning_rate": 0.00029237490071485305,
|
149 |
+
"loss": 0.8057,
|
150 |
+
"step": 420
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.1,
|
154 |
+
"learning_rate": 0.0002918983320095314,
|
155 |
+
"loss": 0.811,
|
156 |
+
"step": 440
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.11,
|
160 |
+
"learning_rate": 0.00029142176330420965,
|
161 |
+
"loss": 0.8056,
|
162 |
+
"step": 460
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.11,
|
166 |
+
"learning_rate": 0.000290945194598888,
|
167 |
+
"loss": 0.7993,
|
168 |
+
"step": 480
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.12,
|
172 |
+
"learning_rate": 0.0002904686258935663,
|
173 |
+
"loss": 0.7982,
|
174 |
+
"step": 500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.12,
|
178 |
+
"learning_rate": 0.0002899920571882446,
|
179 |
+
"loss": 0.8023,
|
180 |
+
"step": 520
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.13,
|
184 |
+
"learning_rate": 0.00028951548848292296,
|
185 |
+
"loss": 0.7968,
|
186 |
+
"step": 540
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.13,
|
190 |
+
"learning_rate": 0.00028903891977760123,
|
191 |
+
"loss": 0.8029,
|
192 |
+
"step": 560
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.14,
|
196 |
+
"learning_rate": 0.00028856235107227956,
|
197 |
+
"loss": 0.7892,
|
198 |
+
"step": 580
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.14,
|
202 |
+
"learning_rate": 0.0002880857823669579,
|
203 |
+
"loss": 0.7946,
|
204 |
+
"step": 600
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.14,
|
208 |
+
"eval_loss": 0.7735009789466858,
|
209 |
+
"eval_runtime": 49.3305,
|
210 |
+
"eval_samples_per_second": 40.543,
|
211 |
+
"eval_steps_per_second": 2.534,
|
212 |
+
"step": 600
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15,
|
216 |
+
"learning_rate": 0.00028760921366163616,
|
217 |
+
"loss": 0.782,
|
218 |
+
"step": 620
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.15,
|
222 |
+
"learning_rate": 0.0002871326449563145,
|
223 |
+
"loss": 0.7799,
|
224 |
+
"step": 640
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.16,
|
228 |
+
"learning_rate": 0.0002866560762509928,
|
229 |
+
"loss": 0.7782,
|
230 |
+
"step": 660
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.16,
|
234 |
+
"learning_rate": 0.00028617950754567114,
|
235 |
+
"loss": 0.7785,
|
236 |
+
"step": 680
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.17,
|
240 |
+
"learning_rate": 0.00028570293884034947,
|
241 |
+
"loss": 0.785,
|
242 |
+
"step": 700
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.17,
|
246 |
+
"learning_rate": 0.0002852263701350278,
|
247 |
+
"loss": 0.7754,
|
248 |
+
"step": 720
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.17,
|
252 |
+
"learning_rate": 0.00028474980142970607,
|
253 |
+
"loss": 0.7804,
|
254 |
+
"step": 740
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18,
|
258 |
+
"learning_rate": 0.0002842732327243844,
|
259 |
+
"loss": 0.7696,
|
260 |
+
"step": 760
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.18,
|
264 |
+
"learning_rate": 0.0002837966640190627,
|
265 |
+
"loss": 0.7692,
|
266 |
+
"step": 780
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.19,
|
270 |
+
"learning_rate": 0.00028332009531374105,
|
271 |
+
"loss": 0.7752,
|
272 |
+
"step": 800
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.19,
|
276 |
+
"eval_loss": 0.7564254403114319,
|
277 |
+
"eval_runtime": 49.106,
|
278 |
+
"eval_samples_per_second": 40.728,
|
279 |
+
"eval_steps_per_second": 2.546,
|
280 |
+
"step": 800
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.19,
|
284 |
+
"learning_rate": 0.0002828435266084194,
|
285 |
+
"loss": 0.7698,
|
286 |
+
"step": 820
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.2,
|
290 |
+
"learning_rate": 0.00028236695790309765,
|
291 |
+
"loss": 0.7699,
|
292 |
+
"step": 840
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.2,
|
296 |
+
"learning_rate": 0.000281890389197776,
|
297 |
+
"loss": 0.7718,
|
298 |
+
"step": 860
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.21,
|
302 |
+
"learning_rate": 0.0002814138204924543,
|
303 |
+
"loss": 0.7644,
|
304 |
+
"step": 880
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.21,
|
308 |
+
"learning_rate": 0.00028093725178713263,
|
309 |
+
"loss": 0.7659,
|
310 |
+
"step": 900
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.22,
|
314 |
+
"learning_rate": 0.00028046068308181096,
|
315 |
+
"loss": 0.7641,
|
316 |
+
"step": 920
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.22,
|
320 |
+
"learning_rate": 0.00027998411437648923,
|
321 |
+
"loss": 0.7535,
|
322 |
+
"step": 940
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.23,
|
326 |
+
"learning_rate": 0.00027950754567116756,
|
327 |
+
"loss": 0.7672,
|
328 |
+
"step": 960
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.23,
|
332 |
+
"learning_rate": 0.0002790309769658459,
|
333 |
+
"loss": 0.7563,
|
334 |
+
"step": 980
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.24,
|
338 |
+
"learning_rate": 0.0002785544082605242,
|
339 |
+
"loss": 0.752,
|
340 |
+
"step": 1000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.24,
|
344 |
+
"eval_loss": 0.7433652281761169,
|
345 |
+
"eval_runtime": 48.9945,
|
346 |
+
"eval_samples_per_second": 40.821,
|
347 |
+
"eval_steps_per_second": 2.551,
|
348 |
+
"step": 1000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.24,
|
352 |
+
"learning_rate": 0.00027807783955520254,
|
353 |
+
"loss": 0.755,
|
354 |
+
"step": 1020
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.25,
|
358 |
+
"learning_rate": 0.00027760127084988087,
|
359 |
+
"loss": 0.7563,
|
360 |
+
"step": 1040
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.25,
|
364 |
+
"learning_rate": 0.00027712470214455914,
|
365 |
+
"loss": 0.7475,
|
366 |
+
"step": 1060
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.26,
|
370 |
+
"learning_rate": 0.00027664813343923747,
|
371 |
+
"loss": 0.7599,
|
372 |
+
"step": 1080
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 0.26,
|
376 |
+
"learning_rate": 0.0002761715647339158,
|
377 |
+
"loss": 0.7533,
|
378 |
+
"step": 1100
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.26,
|
382 |
+
"learning_rate": 0.00027569499602859407,
|
383 |
+
"loss": 0.7488,
|
384 |
+
"step": 1120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.27,
|
388 |
+
"learning_rate": 0.00027521842732327245,
|
389 |
+
"loss": 0.753,
|
390 |
+
"step": 1140
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.27,
|
394 |
+
"learning_rate": 0.0002747418586179507,
|
395 |
+
"loss": 0.7435,
|
396 |
+
"step": 1160
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.28,
|
400 |
+
"learning_rate": 0.00027426528991262905,
|
401 |
+
"loss": 0.7457,
|
402 |
+
"step": 1180
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.28,
|
406 |
+
"learning_rate": 0.0002737887212073074,
|
407 |
+
"loss": 0.742,
|
408 |
+
"step": 1200
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.28,
|
412 |
+
"eval_loss": 0.7321739792823792,
|
413 |
+
"eval_runtime": 48.8876,
|
414 |
+
"eval_samples_per_second": 40.91,
|
415 |
+
"eval_steps_per_second": 2.557,
|
416 |
+
"step": 1200
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.29,
|
420 |
+
"learning_rate": 0.00027331215250198565,
|
421 |
+
"loss": 0.7474,
|
422 |
+
"step": 1220
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.29,
|
426 |
+
"learning_rate": 0.000272835583796664,
|
427 |
+
"loss": 0.7456,
|
428 |
+
"step": 1240
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.3,
|
432 |
+
"learning_rate": 0.0002723590150913423,
|
433 |
+
"loss": 0.7406,
|
434 |
+
"step": 1260
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.3,
|
438 |
+
"learning_rate": 0.00027188244638602063,
|
439 |
+
"loss": 0.7448,
|
440 |
+
"step": 1280
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.31,
|
444 |
+
"learning_rate": 0.00027140587768069896,
|
445 |
+
"loss": 0.7445,
|
446 |
+
"step": 1300
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.31,
|
450 |
+
"learning_rate": 0.00027092930897537723,
|
451 |
+
"loss": 0.7349,
|
452 |
+
"step": 1320
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.32,
|
456 |
+
"learning_rate": 0.00027045274027005556,
|
457 |
+
"loss": 0.7395,
|
458 |
+
"step": 1340
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.32,
|
462 |
+
"learning_rate": 0.0002699761715647339,
|
463 |
+
"loss": 0.7382,
|
464 |
+
"step": 1360
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.33,
|
468 |
+
"learning_rate": 0.0002694996028594122,
|
469 |
+
"loss": 0.7357,
|
470 |
+
"step": 1380
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.33,
|
474 |
+
"learning_rate": 0.00026902303415409054,
|
475 |
+
"loss": 0.7409,
|
476 |
+
"step": 1400
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.33,
|
480 |
+
"eval_loss": 0.7235888242721558,
|
481 |
+
"eval_runtime": 49.2145,
|
482 |
+
"eval_samples_per_second": 40.638,
|
483 |
+
"eval_steps_per_second": 2.54,
|
484 |
+
"step": 1400
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.34,
|
488 |
+
"learning_rate": 0.00026854646544876887,
|
489 |
+
"loss": 0.7376,
|
490 |
+
"step": 1420
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 0.34,
|
494 |
+
"learning_rate": 0.00026806989674344714,
|
495 |
+
"loss": 0.7298,
|
496 |
+
"step": 1440
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.35,
|
500 |
+
"learning_rate": 0.00026759332803812547,
|
501 |
+
"loss": 0.7379,
|
502 |
+
"step": 1460
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.35,
|
506 |
+
"learning_rate": 0.0002671167593328038,
|
507 |
+
"loss": 0.7354,
|
508 |
+
"step": 1480
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.35,
|
512 |
+
"learning_rate": 0.0002666401906274821,
|
513 |
+
"loss": 0.7341,
|
514 |
+
"step": 1500
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.36,
|
518 |
+
"learning_rate": 0.00026616362192216045,
|
519 |
+
"loss": 0.7352,
|
520 |
+
"step": 1520
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.36,
|
524 |
+
"learning_rate": 0.0002656870532168387,
|
525 |
+
"loss": 0.7321,
|
526 |
+
"step": 1540
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.37,
|
530 |
+
"learning_rate": 0.00026521048451151705,
|
531 |
+
"loss": 0.7285,
|
532 |
+
"step": 1560
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.37,
|
536 |
+
"learning_rate": 0.0002647339158061954,
|
537 |
+
"loss": 0.73,
|
538 |
+
"step": 1580
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.38,
|
542 |
+
"learning_rate": 0.00026425734710087365,
|
543 |
+
"loss": 0.7304,
|
544 |
+
"step": 1600
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.38,
|
548 |
+
"eval_loss": 0.716058611869812,
|
549 |
+
"eval_runtime": 48.9201,
|
550 |
+
"eval_samples_per_second": 40.883,
|
551 |
+
"eval_steps_per_second": 2.555,
|
552 |
+
"step": 1600
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.38,
|
556 |
+
"learning_rate": 0.00026378077839555203,
|
557 |
+
"loss": 0.7314,
|
558 |
+
"step": 1620
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.39,
|
562 |
+
"learning_rate": 0.0002633042096902303,
|
563 |
+
"loss": 0.7315,
|
564 |
+
"step": 1640
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.39,
|
568 |
+
"learning_rate": 0.00026282764098490863,
|
569 |
+
"loss": 0.7239,
|
570 |
+
"step": 1660
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.4,
|
574 |
+
"learning_rate": 0.00026235107227958696,
|
575 |
+
"loss": 0.73,
|
576 |
+
"step": 1680
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.4,
|
580 |
+
"learning_rate": 0.00026187450357426523,
|
581 |
+
"loss": 0.7243,
|
582 |
+
"step": 1700
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.41,
|
586 |
+
"learning_rate": 0.00026139793486894356,
|
587 |
+
"loss": 0.7199,
|
588 |
+
"step": 1720
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 0.41,
|
592 |
+
"learning_rate": 0.0002609213661636219,
|
593 |
+
"loss": 0.7216,
|
594 |
+
"step": 1740
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.42,
|
598 |
+
"learning_rate": 0.0002604447974583002,
|
599 |
+
"loss": 0.7358,
|
600 |
+
"step": 1760
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.42,
|
604 |
+
"learning_rate": 0.00025996822875297854,
|
605 |
+
"loss": 0.7313,
|
606 |
+
"step": 1780
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.43,
|
610 |
+
"learning_rate": 0.00025949166004765687,
|
611 |
+
"loss": 0.7236,
|
612 |
+
"step": 1800
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.43,
|
616 |
+
"eval_loss": 0.7097632884979248,
|
617 |
+
"eval_runtime": 49.4908,
|
618 |
+
"eval_samples_per_second": 40.412,
|
619 |
+
"eval_steps_per_second": 2.526,
|
620 |
+
"step": 1800
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.43,
|
624 |
+
"learning_rate": 0.00025901509134233514,
|
625 |
+
"loss": 0.7282,
|
626 |
+
"step": 1820
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.43,
|
630 |
+
"learning_rate": 0.00025853852263701347,
|
631 |
+
"loss": 0.7187,
|
632 |
+
"step": 1840
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.44,
|
636 |
+
"learning_rate": 0.0002580619539316918,
|
637 |
+
"loss": 0.7303,
|
638 |
+
"step": 1860
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.44,
|
642 |
+
"learning_rate": 0.0002575853852263701,
|
643 |
+
"loss": 0.724,
|
644 |
+
"step": 1880
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.45,
|
648 |
+
"learning_rate": 0.00025710881652104845,
|
649 |
+
"loss": 0.7248,
|
650 |
+
"step": 1900
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.45,
|
654 |
+
"learning_rate": 0.0002566322478157267,
|
655 |
+
"loss": 0.7195,
|
656 |
+
"step": 1920
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.46,
|
660 |
+
"learning_rate": 0.00025615567911040505,
|
661 |
+
"loss": 0.7269,
|
662 |
+
"step": 1940
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.46,
|
666 |
+
"learning_rate": 0.0002556791104050834,
|
667 |
+
"loss": 0.7209,
|
668 |
+
"step": 1960
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.47,
|
672 |
+
"learning_rate": 0.0002552025416997617,
|
673 |
+
"loss": 0.7282,
|
674 |
+
"step": 1980
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.47,
|
678 |
+
"learning_rate": 0.00025472597299444003,
|
679 |
+
"loss": 0.7195,
|
680 |
+
"step": 2000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.47,
|
684 |
+
"eval_loss": 0.7037709355354309,
|
685 |
+
"eval_runtime": 49.7167,
|
686 |
+
"eval_samples_per_second": 40.228,
|
687 |
+
"eval_steps_per_second": 2.514,
|
688 |
+
"step": 2000
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.48,
|
692 |
+
"learning_rate": 0.0002542494042891183,
|
693 |
+
"loss": 0.7229,
|
694 |
+
"step": 2020
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 0.48,
|
698 |
+
"learning_rate": 0.00025377283558379664,
|
699 |
+
"loss": 0.718,
|
700 |
+
"step": 2040
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.49,
|
704 |
+
"learning_rate": 0.00025329626687847496,
|
705 |
+
"loss": 0.7223,
|
706 |
+
"step": 2060
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.49,
|
710 |
+
"learning_rate": 0.00025281969817315324,
|
711 |
+
"loss": 0.7209,
|
712 |
+
"step": 2080
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.5,
|
716 |
+
"learning_rate": 0.0002523431294678316,
|
717 |
+
"loss": 0.7151,
|
718 |
+
"step": 2100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.5,
|
722 |
+
"learning_rate": 0.0002518665607625099,
|
723 |
+
"loss": 0.7141,
|
724 |
+
"step": 2120
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.51,
|
728 |
+
"learning_rate": 0.0002513899920571882,
|
729 |
+
"loss": 0.7084,
|
730 |
+
"step": 2140
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.51,
|
734 |
+
"learning_rate": 0.00025091342335186654,
|
735 |
+
"loss": 0.7075,
|
736 |
+
"step": 2160
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.52,
|
740 |
+
"learning_rate": 0.00025043685464654487,
|
741 |
+
"loss": 0.7133,
|
742 |
+
"step": 2180
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 0.52,
|
746 |
+
"learning_rate": 0.00024996028594122314,
|
747 |
+
"loss": 0.7092,
|
748 |
+
"step": 2200
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.52,
|
752 |
+
"eval_loss": 0.6989386677742004,
|
753 |
+
"eval_runtime": 49.2344,
|
754 |
+
"eval_samples_per_second": 40.622,
|
755 |
+
"eval_steps_per_second": 2.539,
|
756 |
+
"step": 2200
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.52,
|
760 |
+
"learning_rate": 0.0002494837172359015,
|
761 |
+
"loss": 0.7178,
|
762 |
+
"step": 2220
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.53,
|
766 |
+
"learning_rate": 0.0002490071485305798,
|
767 |
+
"loss": 0.7188,
|
768 |
+
"step": 2240
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.53,
|
772 |
+
"learning_rate": 0.0002485305798252581,
|
773 |
+
"loss": 0.7161,
|
774 |
+
"step": 2260
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.54,
|
778 |
+
"learning_rate": 0.00024805401111993645,
|
779 |
+
"loss": 0.7078,
|
780 |
+
"step": 2280
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.54,
|
784 |
+
"learning_rate": 0.0002475774424146147,
|
785 |
+
"loss": 0.7,
|
786 |
+
"step": 2300
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.55,
|
790 |
+
"learning_rate": 0.00024710087370929305,
|
791 |
+
"loss": 0.718,
|
792 |
+
"step": 2320
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.55,
|
796 |
+
"learning_rate": 0.0002466243050039714,
|
797 |
+
"loss": 0.7059,
|
798 |
+
"step": 2340
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.56,
|
802 |
+
"learning_rate": 0.0002461477362986497,
|
803 |
+
"loss": 0.712,
|
804 |
+
"step": 2360
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.56,
|
808 |
+
"learning_rate": 0.00024567116759332804,
|
809 |
+
"loss": 0.7116,
|
810 |
+
"step": 2380
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.57,
|
814 |
+
"learning_rate": 0.0002451945988880063,
|
815 |
+
"loss": 0.6986,
|
816 |
+
"step": 2400
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.57,
|
820 |
+
"eval_loss": 0.6939737796783447,
|
821 |
+
"eval_runtime": 49.459,
|
822 |
+
"eval_samples_per_second": 40.438,
|
823 |
+
"eval_steps_per_second": 2.527,
|
824 |
+
"step": 2400
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.57,
|
828 |
+
"learning_rate": 0.00024471803018268464,
|
829 |
+
"loss": 0.7168,
|
830 |
+
"step": 2420
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.58,
|
834 |
+
"learning_rate": 0.00024424146147736296,
|
835 |
+
"loss": 0.7141,
|
836 |
+
"step": 2440
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.58,
|
840 |
+
"learning_rate": 0.00024376489277204126,
|
841 |
+
"loss": 0.7095,
|
842 |
+
"step": 2460
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.59,
|
846 |
+
"learning_rate": 0.00024328832406671962,
|
847 |
+
"loss": 0.7091,
|
848 |
+
"step": 2480
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.59,
|
852 |
+
"learning_rate": 0.00024281175536139792,
|
853 |
+
"loss": 0.7015,
|
854 |
+
"step": 2500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.6,
|
858 |
+
"learning_rate": 0.00024233518665607622,
|
859 |
+
"loss": 0.7109,
|
860 |
+
"step": 2520
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.6,
|
864 |
+
"learning_rate": 0.00024185861795075455,
|
865 |
+
"loss": 0.7086,
|
866 |
+
"step": 2540
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.61,
|
870 |
+
"learning_rate": 0.00024138204924543285,
|
871 |
+
"loss": 0.7118,
|
872 |
+
"step": 2560
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.61,
|
876 |
+
"learning_rate": 0.00024090548054011117,
|
877 |
+
"loss": 0.7033,
|
878 |
+
"step": 2580
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.61,
|
882 |
+
"learning_rate": 0.0002404289118347895,
|
883 |
+
"loss": 0.7128,
|
884 |
+
"step": 2600
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.61,
|
888 |
+
"eval_loss": 0.6901652812957764,
|
889 |
+
"eval_runtime": 49.5038,
|
890 |
+
"eval_samples_per_second": 40.401,
|
891 |
+
"eval_steps_per_second": 2.525,
|
892 |
+
"step": 2600
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.62,
|
896 |
+
"learning_rate": 0.00023995234312946783,
|
897 |
+
"loss": 0.6968,
|
898 |
+
"step": 2620
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.62,
|
902 |
+
"learning_rate": 0.00023947577442414613,
|
903 |
+
"loss": 0.7109,
|
904 |
+
"step": 2640
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.63,
|
908 |
+
"learning_rate": 0.00023899920571882443,
|
909 |
+
"loss": 0.7048,
|
910 |
+
"step": 2660
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.63,
|
914 |
+
"learning_rate": 0.00023852263701350276,
|
915 |
+
"loss": 0.7012,
|
916 |
+
"step": 2680
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.64,
|
920 |
+
"learning_rate": 0.00023804606830818106,
|
921 |
+
"loss": 0.7065,
|
922 |
+
"step": 2700
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.64,
|
926 |
+
"learning_rate": 0.0002375694996028594,
|
927 |
+
"loss": 0.7009,
|
928 |
+
"step": 2720
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.65,
|
932 |
+
"learning_rate": 0.0002370929308975377,
|
933 |
+
"loss": 0.7035,
|
934 |
+
"step": 2740
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.65,
|
938 |
+
"learning_rate": 0.00023661636219221604,
|
939 |
+
"loss": 0.6973,
|
940 |
+
"step": 2760
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.66,
|
944 |
+
"learning_rate": 0.00023613979348689434,
|
945 |
+
"loss": 0.7075,
|
946 |
+
"step": 2780
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.66,
|
950 |
+
"learning_rate": 0.00023566322478157264,
|
951 |
+
"loss": 0.6952,
|
952 |
+
"step": 2800
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.66,
|
956 |
+
"eval_loss": 0.6865400671958923,
|
957 |
+
"eval_runtime": 49.2814,
|
958 |
+
"eval_samples_per_second": 40.583,
|
959 |
+
"eval_steps_per_second": 2.536,
|
960 |
+
"step": 2800
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.67,
|
964 |
+
"learning_rate": 0.00023518665607625097,
|
965 |
+
"loss": 0.6979,
|
966 |
+
"step": 2820
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.67,
|
970 |
+
"learning_rate": 0.0002347100873709293,
|
971 |
+
"loss": 0.6973,
|
972 |
+
"step": 2840
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.68,
|
976 |
+
"learning_rate": 0.00023423351866560762,
|
977 |
+
"loss": 0.7033,
|
978 |
+
"step": 2860
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.68,
|
982 |
+
"learning_rate": 0.00023375694996028592,
|
983 |
+
"loss": 0.6964,
|
984 |
+
"step": 2880
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.69,
|
988 |
+
"learning_rate": 0.00023328038125496422,
|
989 |
+
"loss": 0.7052,
|
990 |
+
"step": 2900
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.69,
|
994 |
+
"learning_rate": 0.00023280381254964255,
|
995 |
+
"loss": 0.6999,
|
996 |
+
"step": 2920
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.7,
|
1000 |
+
"learning_rate": 0.00023232724384432085,
|
1001 |
+
"loss": 0.6963,
|
1002 |
+
"step": 2940
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.7,
|
1006 |
+
"learning_rate": 0.0002318506751389992,
|
1007 |
+
"loss": 0.7025,
|
1008 |
+
"step": 2960
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.7,
|
1012 |
+
"learning_rate": 0.0002313741064336775,
|
1013 |
+
"loss": 0.704,
|
1014 |
+
"step": 2980
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.71,
|
1018 |
+
"learning_rate": 0.00023089753772835583,
|
1019 |
+
"loss": 0.6926,
|
1020 |
+
"step": 3000
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.71,
|
1024 |
+
"eval_loss": 0.6828380227088928,
|
1025 |
+
"eval_runtime": 49.5667,
|
1026 |
+
"eval_samples_per_second": 40.35,
|
1027 |
+
"eval_steps_per_second": 2.522,
|
1028 |
+
"step": 3000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.71,
|
1032 |
+
"learning_rate": 0.00023042096902303413,
|
1033 |
+
"loss": 0.698,
|
1034 |
+
"step": 3020
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.72,
|
1038 |
+
"learning_rate": 0.00022994440031771243,
|
1039 |
+
"loss": 0.6893,
|
1040 |
+
"step": 3040
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.72,
|
1044 |
+
"learning_rate": 0.00022946783161239076,
|
1045 |
+
"loss": 0.6938,
|
1046 |
+
"step": 3060
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.73,
|
1050 |
+
"learning_rate": 0.00022899126290706908,
|
1051 |
+
"loss": 0.6974,
|
1052 |
+
"step": 3080
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.73,
|
1056 |
+
"learning_rate": 0.0002285146942017474,
|
1057 |
+
"loss": 0.6922,
|
1058 |
+
"step": 3100
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.74,
|
1062 |
+
"learning_rate": 0.0002280381254964257,
|
1063 |
+
"loss": 0.7073,
|
1064 |
+
"step": 3120
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.74,
|
1068 |
+
"learning_rate": 0.00022756155679110404,
|
1069 |
+
"loss": 0.6895,
|
1070 |
+
"step": 3140
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.75,
|
1074 |
+
"learning_rate": 0.00022708498808578234,
|
1075 |
+
"loss": 0.7012,
|
1076 |
+
"step": 3160
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.75,
|
1080 |
+
"learning_rate": 0.00022660841938046064,
|
1081 |
+
"loss": 0.6985,
|
1082 |
+
"step": 3180
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.76,
|
1086 |
+
"learning_rate": 0.000226131850675139,
|
1087 |
+
"loss": 0.6901,
|
1088 |
+
"step": 3200
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.76,
|
1092 |
+
"eval_loss": 0.6807068586349487,
|
1093 |
+
"eval_runtime": 49.2421,
|
1094 |
+
"eval_samples_per_second": 40.616,
|
1095 |
+
"eval_steps_per_second": 2.538,
|
1096 |
+
"step": 3200
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.76,
|
1100 |
+
"learning_rate": 0.0002256552819698173,
|
1101 |
+
"loss": 0.697,
|
1102 |
+
"step": 3220
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.77,
|
1106 |
+
"learning_rate": 0.00022517871326449562,
|
1107 |
+
"loss": 0.7002,
|
1108 |
+
"step": 3240
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.77,
|
1112 |
+
"learning_rate": 0.00022470214455917392,
|
1113 |
+
"loss": 0.6918,
|
1114 |
+
"step": 3260
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.78,
|
1118 |
+
"learning_rate": 0.00022422557585385225,
|
1119 |
+
"loss": 0.6999,
|
1120 |
+
"step": 3280
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 0.78,
|
1124 |
+
"learning_rate": 0.00022374900714853055,
|
1125 |
+
"loss": 0.6961,
|
1126 |
+
"step": 3300
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.78,
|
1130 |
+
"learning_rate": 0.0002232724384432089,
|
1131 |
+
"loss": 0.6888,
|
1132 |
+
"step": 3320
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.79,
|
1136 |
+
"learning_rate": 0.0002227958697378872,
|
1137 |
+
"loss": 0.695,
|
1138 |
+
"step": 3340
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.79,
|
1142 |
+
"learning_rate": 0.0002223193010325655,
|
1143 |
+
"loss": 0.6861,
|
1144 |
+
"step": 3360
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.8,
|
1148 |
+
"learning_rate": 0.00022184273232724383,
|
1149 |
+
"loss": 0.6864,
|
1150 |
+
"step": 3380
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.8,
|
1154 |
+
"learning_rate": 0.00022136616362192213,
|
1155 |
+
"loss": 0.6917,
|
1156 |
+
"step": 3400
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.8,
|
1160 |
+
"eval_loss": 0.6773961782455444,
|
1161 |
+
"eval_runtime": 49.3961,
|
1162 |
+
"eval_samples_per_second": 40.489,
|
1163 |
+
"eval_steps_per_second": 2.531,
|
1164 |
+
"step": 3400
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.81,
|
1168 |
+
"learning_rate": 0.00022088959491660043,
|
1169 |
+
"loss": 0.679,
|
1170 |
+
"step": 3420
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.81,
|
1174 |
+
"learning_rate": 0.00022041302621127879,
|
1175 |
+
"loss": 0.6915,
|
1176 |
+
"step": 3440
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 0.82,
|
1180 |
+
"learning_rate": 0.00021993645750595709,
|
1181 |
+
"loss": 0.6937,
|
1182 |
+
"step": 3460
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.82,
|
1186 |
+
"learning_rate": 0.0002194598888006354,
|
1187 |
+
"loss": 0.6831,
|
1188 |
+
"step": 3480
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.83,
|
1192 |
+
"learning_rate": 0.0002189833200953137,
|
1193 |
+
"loss": 0.6875,
|
1194 |
+
"step": 3500
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.83,
|
1198 |
+
"learning_rate": 0.00021850675138999204,
|
1199 |
+
"loss": 0.6916,
|
1200 |
+
"step": 3520
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.84,
|
1204 |
+
"learning_rate": 0.00021803018268467034,
|
1205 |
+
"loss": 0.6896,
|
1206 |
+
"step": 3540
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.84,
|
1210 |
+
"learning_rate": 0.0002175536139793487,
|
1211 |
+
"loss": 0.6986,
|
1212 |
+
"step": 3560
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.85,
|
1216 |
+
"learning_rate": 0.000217077045274027,
|
1217 |
+
"loss": 0.693,
|
1218 |
+
"step": 3580
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.85,
|
1222 |
+
"learning_rate": 0.0002166004765687053,
|
1223 |
+
"loss": 0.6893,
|
1224 |
+
"step": 3600
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.85,
|
1228 |
+
"eval_loss": 0.6753410696983337,
|
1229 |
+
"eval_runtime": 49.3307,
|
1230 |
+
"eval_samples_per_second": 40.543,
|
1231 |
+
"eval_steps_per_second": 2.534,
|
1232 |
+
"step": 3600
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.86,
|
1236 |
+
"learning_rate": 0.00021612390786338362,
|
1237 |
+
"loss": 0.6872,
|
1238 |
+
"step": 3620
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.86,
|
1242 |
+
"learning_rate": 0.00021564733915806192,
|
1243 |
+
"loss": 0.6862,
|
1244 |
+
"step": 3640
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.87,
|
1248 |
+
"learning_rate": 0.00021517077045274025,
|
1249 |
+
"loss": 0.6943,
|
1250 |
+
"step": 3660
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.87,
|
1254 |
+
"learning_rate": 0.00021469420174741858,
|
1255 |
+
"loss": 0.6896,
|
1256 |
+
"step": 3680
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.87,
|
1260 |
+
"learning_rate": 0.0002142176330420969,
|
1261 |
+
"loss": 0.6912,
|
1262 |
+
"step": 3700
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.88,
|
1266 |
+
"learning_rate": 0.0002137410643367752,
|
1267 |
+
"loss": 0.6859,
|
1268 |
+
"step": 3720
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.88,
|
1272 |
+
"learning_rate": 0.0002132644956314535,
|
1273 |
+
"loss": 0.6791,
|
1274 |
+
"step": 3740
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.89,
|
1278 |
+
"learning_rate": 0.00021278792692613183,
|
1279 |
+
"loss": 0.6882,
|
1280 |
+
"step": 3760
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.89,
|
1284 |
+
"learning_rate": 0.00021231135822081013,
|
1285 |
+
"loss": 0.6823,
|
1286 |
+
"step": 3780
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.9,
|
1290 |
+
"learning_rate": 0.0002118347895154885,
|
1291 |
+
"loss": 0.6831,
|
1292 |
+
"step": 3800
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.9,
|
1296 |
+
"eval_loss": 0.6738302707672119,
|
1297 |
+
"eval_runtime": 49.4648,
|
1298 |
+
"eval_samples_per_second": 40.433,
|
1299 |
+
"eval_steps_per_second": 2.527,
|
1300 |
+
"step": 3800
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.9,
|
1304 |
+
"learning_rate": 0.0002113582208101668,
|
1305 |
+
"loss": 0.6818,
|
1306 |
+
"step": 3820
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.91,
|
1310 |
+
"learning_rate": 0.0002108816521048451,
|
1311 |
+
"loss": 0.6912,
|
1312 |
+
"step": 3840
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.91,
|
1316 |
+
"learning_rate": 0.00021040508339952341,
|
1317 |
+
"loss": 0.6884,
|
1318 |
+
"step": 3860
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.92,
|
1322 |
+
"learning_rate": 0.00020992851469420171,
|
1323 |
+
"loss": 0.6888,
|
1324 |
+
"step": 3880
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 0.92,
|
1328 |
+
"learning_rate": 0.00020945194598888004,
|
1329 |
+
"loss": 0.6822,
|
1330 |
+
"step": 3900
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.93,
|
1334 |
+
"learning_rate": 0.00020897537728355837,
|
1335 |
+
"loss": 0.6879,
|
1336 |
+
"step": 3920
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.93,
|
1340 |
+
"learning_rate": 0.0002084988085782367,
|
1341 |
+
"loss": 0.6771,
|
1342 |
+
"step": 3940
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.94,
|
1346 |
+
"learning_rate": 0.000208022239872915,
|
1347 |
+
"loss": 0.684,
|
1348 |
+
"step": 3960
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.94,
|
1352 |
+
"learning_rate": 0.0002075456711675933,
|
1353 |
+
"loss": 0.6878,
|
1354 |
+
"step": 3980
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.95,
|
1358 |
+
"learning_rate": 0.00020706910246227162,
|
1359 |
+
"loss": 0.6913,
|
1360 |
+
"step": 4000
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.95,
|
1364 |
+
"eval_loss": 0.6711302995681763,
|
1365 |
+
"eval_runtime": 49.117,
|
1366 |
+
"eval_samples_per_second": 40.719,
|
1367 |
+
"eval_steps_per_second": 2.545,
|
1368 |
+
"step": 4000
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.95,
|
1372 |
+
"learning_rate": 0.00020659253375694992,
|
1373 |
+
"loss": 0.683,
|
1374 |
+
"step": 4020
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.96,
|
1378 |
+
"learning_rate": 0.00020611596505162828,
|
1379 |
+
"loss": 0.6833,
|
1380 |
+
"step": 4040
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 0.96,
|
1384 |
+
"learning_rate": 0.00020563939634630658,
|
1385 |
+
"loss": 0.6793,
|
1386 |
+
"step": 4060
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.96,
|
1390 |
+
"learning_rate": 0.0002051628276409849,
|
1391 |
+
"loss": 0.6843,
|
1392 |
+
"step": 4080
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.97,
|
1396 |
+
"learning_rate": 0.0002046862589356632,
|
1397 |
+
"loss": 0.6822,
|
1398 |
+
"step": 4100
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.97,
|
1402 |
+
"learning_rate": 0.0002042096902303415,
|
1403 |
+
"loss": 0.6856,
|
1404 |
+
"step": 4120
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.98,
|
1408 |
+
"learning_rate": 0.00020373312152501983,
|
1409 |
+
"loss": 0.6809,
|
1410 |
+
"step": 4140
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.98,
|
1414 |
+
"learning_rate": 0.00020325655281969816,
|
1415 |
+
"loss": 0.6843,
|
1416 |
+
"step": 4160
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.99,
|
1420 |
+
"learning_rate": 0.0002027799841143765,
|
1421 |
+
"loss": 0.6754,
|
1422 |
+
"step": 4180
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 0.99,
|
1426 |
+
"learning_rate": 0.0002023034154090548,
|
1427 |
+
"loss": 0.6823,
|
1428 |
+
"step": 4200
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 0.99,
|
1432 |
+
"eval_loss": 0.6697036027908325,
|
1433 |
+
"eval_runtime": 49.3237,
|
1434 |
+
"eval_samples_per_second": 40.548,
|
1435 |
+
"eval_steps_per_second": 2.534,
|
1436 |
+
"step": 4200
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 1.0,
|
1440 |
+
"learning_rate": 0.00020182684670373312,
|
1441 |
+
"loss": 0.6861,
|
1442 |
+
"step": 4220
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 1.0,
|
1446 |
+
"learning_rate": 0.00020135027799841142,
|
1447 |
+
"loss": 0.6806,
|
1448 |
+
"step": 4240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 1.01,
|
1452 |
+
"learning_rate": 0.00020087370929308972,
|
1453 |
+
"loss": 0.6823,
|
1454 |
+
"step": 4260
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 1.01,
|
1458 |
+
"learning_rate": 0.00020039714058776807,
|
1459 |
+
"loss": 0.6805,
|
1460 |
+
"step": 4280
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.02,
|
1464 |
+
"learning_rate": 0.00019992057188244637,
|
1465 |
+
"loss": 0.6813,
|
1466 |
+
"step": 4300
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.02,
|
1470 |
+
"learning_rate": 0.0001994440031771247,
|
1471 |
+
"loss": 0.675,
|
1472 |
+
"step": 4320
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.03,
|
1476 |
+
"learning_rate": 0.000198967434471803,
|
1477 |
+
"loss": 0.6728,
|
1478 |
+
"step": 4340
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.03,
|
1482 |
+
"learning_rate": 0.0001984908657664813,
|
1483 |
+
"loss": 0.6676,
|
1484 |
+
"step": 4360
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 1.04,
|
1488 |
+
"learning_rate": 0.00019801429706115963,
|
1489 |
+
"loss": 0.6729,
|
1490 |
+
"step": 4380
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 1.04,
|
1494 |
+
"learning_rate": 0.00019753772835583795,
|
1495 |
+
"loss": 0.685,
|
1496 |
+
"step": 4400
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 1.04,
|
1500 |
+
"eval_loss": 0.6667952537536621,
|
1501 |
+
"eval_runtime": 49.3899,
|
1502 |
+
"eval_samples_per_second": 40.494,
|
1503 |
+
"eval_steps_per_second": 2.531,
|
1504 |
+
"step": 4400
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 1.04,
|
1508 |
+
"learning_rate": 0.00019706115965051628,
|
1509 |
+
"loss": 0.6786,
|
1510 |
+
"step": 4420
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.05,
|
1514 |
+
"learning_rate": 0.00019658459094519458,
|
1515 |
+
"loss": 0.6738,
|
1516 |
+
"step": 4440
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 1.05,
|
1520 |
+
"learning_rate": 0.0001961080222398729,
|
1521 |
+
"loss": 0.686,
|
1522 |
+
"step": 4460
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.06,
|
1526 |
+
"learning_rate": 0.0001956314535345512,
|
1527 |
+
"loss": 0.6818,
|
1528 |
+
"step": 4480
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.06,
|
1532 |
+
"learning_rate": 0.0001951548848292295,
|
1533 |
+
"loss": 0.6741,
|
1534 |
+
"step": 4500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 1.07,
|
1538 |
+
"learning_rate": 0.00019467831612390786,
|
1539 |
+
"loss": 0.6756,
|
1540 |
+
"step": 4520
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 1.07,
|
1544 |
+
"learning_rate": 0.00019420174741858616,
|
1545 |
+
"loss": 0.6851,
|
1546 |
+
"step": 4540
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.08,
|
1550 |
+
"learning_rate": 0.0001937251787132645,
|
1551 |
+
"loss": 0.6784,
|
1552 |
+
"step": 4560
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 1.08,
|
1556 |
+
"learning_rate": 0.0001932486100079428,
|
1557 |
+
"loss": 0.6785,
|
1558 |
+
"step": 4580
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 1.09,
|
1562 |
+
"learning_rate": 0.00019277204130262112,
|
1563 |
+
"loss": 0.678,
|
1564 |
+
"step": 4600
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.09,
|
1568 |
+
"eval_loss": 0.6655837297439575,
|
1569 |
+
"eval_runtime": 49.5019,
|
1570 |
+
"eval_samples_per_second": 40.403,
|
1571 |
+
"eval_steps_per_second": 2.525,
|
1572 |
+
"step": 4600
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 1.09,
|
1576 |
+
"learning_rate": 0.00019229547259729942,
|
1577 |
+
"loss": 0.6782,
|
1578 |
+
"step": 4620
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.1,
|
1582 |
+
"learning_rate": 0.00019181890389197777,
|
1583 |
+
"loss": 0.6683,
|
1584 |
+
"step": 4640
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.1,
|
1588 |
+
"learning_rate": 0.00019134233518665607,
|
1589 |
+
"loss": 0.6783,
|
1590 |
+
"step": 4660
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 1.11,
|
1594 |
+
"learning_rate": 0.00019086576648133437,
|
1595 |
+
"loss": 0.675,
|
1596 |
+
"step": 4680
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 1.11,
|
1600 |
+
"learning_rate": 0.0001903891977760127,
|
1601 |
+
"loss": 0.6691,
|
1602 |
+
"step": 4700
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.12,
|
1606 |
+
"learning_rate": 0.000189912629070691,
|
1607 |
+
"loss": 0.6726,
|
1608 |
+
"step": 4720
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.12,
|
1612 |
+
"learning_rate": 0.00018943606036536933,
|
1613 |
+
"loss": 0.68,
|
1614 |
+
"step": 4740
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.13,
|
1618 |
+
"learning_rate": 0.00018895949166004763,
|
1619 |
+
"loss": 0.6694,
|
1620 |
+
"step": 4760
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.13,
|
1624 |
+
"learning_rate": 0.00018848292295472598,
|
1625 |
+
"loss": 0.6686,
|
1626 |
+
"step": 4780
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.13,
|
1630 |
+
"learning_rate": 0.00018800635424940428,
|
1631 |
+
"loss": 0.6766,
|
1632 |
+
"step": 4800
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.13,
|
1636 |
+
"eval_loss": 0.6646501421928406,
|
1637 |
+
"eval_runtime": 49.3188,
|
1638 |
+
"eval_samples_per_second": 40.552,
|
1639 |
+
"eval_steps_per_second": 2.535,
|
1640 |
+
"step": 4800
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 1.14,
|
1644 |
+
"learning_rate": 0.00018752978554408258,
|
1645 |
+
"loss": 0.6724,
|
1646 |
+
"step": 4820
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 1.14,
|
1650 |
+
"learning_rate": 0.0001870532168387609,
|
1651 |
+
"loss": 0.6801,
|
1652 |
+
"step": 4840
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 1.15,
|
1656 |
+
"learning_rate": 0.0001865766481334392,
|
1657 |
+
"loss": 0.6698,
|
1658 |
+
"step": 4860
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.15,
|
1662 |
+
"learning_rate": 0.0001861000794281175,
|
1663 |
+
"loss": 0.6723,
|
1664 |
+
"step": 4880
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 1.16,
|
1668 |
+
"learning_rate": 0.00018562351072279586,
|
1669 |
+
"loss": 0.6693,
|
1670 |
+
"step": 4900
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 1.16,
|
1674 |
+
"learning_rate": 0.00018514694201747416,
|
1675 |
+
"loss": 0.6716,
|
1676 |
+
"step": 4920
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.17,
|
1680 |
+
"learning_rate": 0.0001846703733121525,
|
1681 |
+
"loss": 0.674,
|
1682 |
+
"step": 4940
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 1.17,
|
1686 |
+
"learning_rate": 0.0001841938046068308,
|
1687 |
+
"loss": 0.6702,
|
1688 |
+
"step": 4960
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 1.18,
|
1692 |
+
"learning_rate": 0.00018371723590150912,
|
1693 |
+
"loss": 0.6716,
|
1694 |
+
"step": 4980
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 1.18,
|
1698 |
+
"learning_rate": 0.00018324066719618742,
|
1699 |
+
"loss": 0.672,
|
1700 |
+
"step": 5000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.18,
|
1704 |
+
"eval_loss": 0.662735104560852,
|
1705 |
+
"eval_runtime": 49.275,
|
1706 |
+
"eval_samples_per_second": 40.589,
|
1707 |
+
"eval_steps_per_second": 2.537,
|
1708 |
+
"step": 5000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.19,
|
1712 |
+
"learning_rate": 0.00018276409849086577,
|
1713 |
+
"loss": 0.6701,
|
1714 |
+
"step": 5020
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.19,
|
1718 |
+
"learning_rate": 0.00018228752978554407,
|
1719 |
+
"loss": 0.6663,
|
1720 |
+
"step": 5040
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 1.2,
|
1724 |
+
"learning_rate": 0.00018181096108022237,
|
1725 |
+
"loss": 0.6651,
|
1726 |
+
"step": 5060
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.2,
|
1730 |
+
"learning_rate": 0.0001813343923749007,
|
1731 |
+
"loss": 0.6708,
|
1732 |
+
"step": 5080
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.21,
|
1736 |
+
"learning_rate": 0.000180857823669579,
|
1737 |
+
"loss": 0.6697,
|
1738 |
+
"step": 5100
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.21,
|
1742 |
+
"learning_rate": 0.00018038125496425733,
|
1743 |
+
"loss": 0.662,
|
1744 |
+
"step": 5120
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 1.22,
|
1748 |
+
"learning_rate": 0.00017990468625893566,
|
1749 |
+
"loss": 0.669,
|
1750 |
+
"step": 5140
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 1.22,
|
1754 |
+
"learning_rate": 0.00017942811755361398,
|
1755 |
+
"loss": 0.6649,
|
1756 |
+
"step": 5160
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.22,
|
1760 |
+
"learning_rate": 0.00017895154884829228,
|
1761 |
+
"loss": 0.668,
|
1762 |
+
"step": 5180
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.23,
|
1766 |
+
"learning_rate": 0.00017847498014297058,
|
1767 |
+
"loss": 0.6796,
|
1768 |
+
"step": 5200
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 1.23,
|
1772 |
+
"eval_loss": 0.6609957218170166,
|
1773 |
+
"eval_runtime": 49.2394,
|
1774 |
+
"eval_samples_per_second": 40.618,
|
1775 |
+
"eval_steps_per_second": 2.539,
|
1776 |
+
"step": 5200
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 1.23,
|
1780 |
+
"learning_rate": 0.0001779984114376489,
|
1781 |
+
"loss": 0.6745,
|
1782 |
+
"step": 5220
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 1.24,
|
1786 |
+
"learning_rate": 0.0001775218427323272,
|
1787 |
+
"loss": 0.6646,
|
1788 |
+
"step": 5240
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.24,
|
1792 |
+
"learning_rate": 0.00017704527402700556,
|
1793 |
+
"loss": 0.6682,
|
1794 |
+
"step": 5260
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.25,
|
1798 |
+
"learning_rate": 0.00017656870532168386,
|
1799 |
+
"loss": 0.6713,
|
1800 |
+
"step": 5280
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 1.25,
|
1804 |
+
"learning_rate": 0.00017609213661636216,
|
1805 |
+
"loss": 0.6618,
|
1806 |
+
"step": 5300
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.26,
|
1810 |
+
"learning_rate": 0.0001756155679110405,
|
1811 |
+
"loss": 0.6703,
|
1812 |
+
"step": 5320
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 1.26,
|
1816 |
+
"learning_rate": 0.0001751389992057188,
|
1817 |
+
"loss": 0.6652,
|
1818 |
+
"step": 5340
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 1.27,
|
1822 |
+
"learning_rate": 0.00017466243050039712,
|
1823 |
+
"loss": 0.6698,
|
1824 |
+
"step": 5360
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.27,
|
1828 |
+
"learning_rate": 0.00017418586179507545,
|
1829 |
+
"loss": 0.6728,
|
1830 |
+
"step": 5380
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.28,
|
1834 |
+
"learning_rate": 0.00017370929308975377,
|
1835 |
+
"loss": 0.6752,
|
1836 |
+
"step": 5400
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.28,
|
1840 |
+
"eval_loss": 0.6592395901679993,
|
1841 |
+
"eval_runtime": 49.3426,
|
1842 |
+
"eval_samples_per_second": 40.533,
|
1843 |
+
"eval_steps_per_second": 2.533,
|
1844 |
+
"step": 5400
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.28,
|
1848 |
+
"learning_rate": 0.00017323272438443207,
|
1849 |
+
"loss": 0.6653,
|
1850 |
+
"step": 5420
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.29,
|
1854 |
+
"learning_rate": 0.00017275615567911037,
|
1855 |
+
"loss": 0.669,
|
1856 |
+
"step": 5440
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 1.29,
|
1860 |
+
"learning_rate": 0.0001722795869737887,
|
1861 |
+
"loss": 0.6698,
|
1862 |
+
"step": 5460
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 1.3,
|
1866 |
+
"learning_rate": 0.000171803018268467,
|
1867 |
+
"loss": 0.6742,
|
1868 |
+
"step": 5480
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 1.3,
|
1872 |
+
"learning_rate": 0.00017132644956314536,
|
1873 |
+
"loss": 0.6596,
|
1874 |
+
"step": 5500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 1.3,
|
1878 |
+
"learning_rate": 0.00017084988085782366,
|
1879 |
+
"loss": 0.6699,
|
1880 |
+
"step": 5520
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 1.31,
|
1884 |
+
"learning_rate": 0.00017037331215250198,
|
1885 |
+
"loss": 0.664,
|
1886 |
+
"step": 5540
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.31,
|
1890 |
+
"learning_rate": 0.00016989674344718028,
|
1891 |
+
"loss": 0.6673,
|
1892 |
+
"step": 5560
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.32,
|
1896 |
+
"learning_rate": 0.00016942017474185858,
|
1897 |
+
"loss": 0.6684,
|
1898 |
+
"step": 5580
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 1.32,
|
1902 |
+
"learning_rate": 0.0001689436060365369,
|
1903 |
+
"loss": 0.6769,
|
1904 |
+
"step": 5600
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 1.32,
|
1908 |
+
"eval_loss": 0.6582754850387573,
|
1909 |
+
"eval_runtime": 49.469,
|
1910 |
+
"eval_samples_per_second": 40.429,
|
1911 |
+
"eval_steps_per_second": 2.527,
|
1912 |
+
"step": 5600
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 1.33,
|
1916 |
+
"learning_rate": 0.00016846703733121524,
|
1917 |
+
"loss": 0.6633,
|
1918 |
+
"step": 5620
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 1.33,
|
1922 |
+
"learning_rate": 0.00016799046862589357,
|
1923 |
+
"loss": 0.6679,
|
1924 |
+
"step": 5640
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.34,
|
1928 |
+
"learning_rate": 0.00016751389992057187,
|
1929 |
+
"loss": 0.6601,
|
1930 |
+
"step": 5660
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 1.34,
|
1934 |
+
"learning_rate": 0.0001670373312152502,
|
1935 |
+
"loss": 0.6731,
|
1936 |
+
"step": 5680
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 1.35,
|
1940 |
+
"learning_rate": 0.0001665607625099285,
|
1941 |
+
"loss": 0.6638,
|
1942 |
+
"step": 5700
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.35,
|
1946 |
+
"learning_rate": 0.0001660841938046068,
|
1947 |
+
"loss": 0.6693,
|
1948 |
+
"step": 5720
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.36,
|
1952 |
+
"learning_rate": 0.00016560762509928515,
|
1953 |
+
"loss": 0.6642,
|
1954 |
+
"step": 5740
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.36,
|
1958 |
+
"learning_rate": 0.00016513105639396345,
|
1959 |
+
"loss": 0.6649,
|
1960 |
+
"step": 5760
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.37,
|
1964 |
+
"learning_rate": 0.00016465448768864178,
|
1965 |
+
"loss": 0.663,
|
1966 |
+
"step": 5780
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 1.37,
|
1970 |
+
"learning_rate": 0.00016417791898332008,
|
1971 |
+
"loss": 0.6629,
|
1972 |
+
"step": 5800
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 1.37,
|
1976 |
+
"eval_loss": 0.6574136018753052,
|
1977 |
+
"eval_runtime": 49.3019,
|
1978 |
+
"eval_samples_per_second": 40.566,
|
1979 |
+
"eval_steps_per_second": 2.535,
|
1980 |
+
"step": 5800
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 1.38,
|
1984 |
+
"learning_rate": 0.00016370135027799838,
|
1985 |
+
"loss": 0.6605,
|
1986 |
+
"step": 5820
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 1.38,
|
1990 |
+
"learning_rate": 0.0001632247815726767,
|
1991 |
+
"loss": 0.6707,
|
1992 |
+
"step": 5840
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 1.39,
|
1996 |
+
"learning_rate": 0.00016274821286735503,
|
1997 |
+
"loss": 0.6695,
|
1998 |
+
"step": 5860
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.39,
|
2002 |
+
"learning_rate": 0.00016227164416203336,
|
2003 |
+
"loss": 0.6647,
|
2004 |
+
"step": 5880
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 1.39,
|
2008 |
+
"learning_rate": 0.00016179507545671166,
|
2009 |
+
"loss": 0.6657,
|
2010 |
+
"step": 5900
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.4,
|
2014 |
+
"learning_rate": 0.00016131850675138999,
|
2015 |
+
"loss": 0.6656,
|
2016 |
+
"step": 5920
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 1.4,
|
2020 |
+
"learning_rate": 0.00016084193804606829,
|
2021 |
+
"loss": 0.6676,
|
2022 |
+
"step": 5940
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.41,
|
2026 |
+
"learning_rate": 0.00016036536934074659,
|
2027 |
+
"loss": 0.6678,
|
2028 |
+
"step": 5960
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 1.41,
|
2032 |
+
"learning_rate": 0.00015988880063542494,
|
2033 |
+
"loss": 0.6639,
|
2034 |
+
"step": 5980
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.42,
|
2038 |
+
"learning_rate": 0.00015941223193010324,
|
2039 |
+
"loss": 0.6645,
|
2040 |
+
"step": 6000
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.42,
|
2044 |
+
"eval_loss": 0.656126081943512,
|
2045 |
+
"eval_runtime": 49.5095,
|
2046 |
+
"eval_samples_per_second": 40.396,
|
2047 |
+
"eval_steps_per_second": 2.525,
|
2048 |
+
"step": 6000
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 1.42,
|
2052 |
+
"learning_rate": 0.00015893566322478157,
|
2053 |
+
"loss": 0.6672,
|
2054 |
+
"step": 6020
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.43,
|
2058 |
+
"learning_rate": 0.00015845909451945987,
|
2059 |
+
"loss": 0.6678,
|
2060 |
+
"step": 6040
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 1.43,
|
2064 |
+
"learning_rate": 0.0001579825258141382,
|
2065 |
+
"loss": 0.6676,
|
2066 |
+
"step": 6060
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.44,
|
2070 |
+
"learning_rate": 0.0001575059571088165,
|
2071 |
+
"loss": 0.6717,
|
2072 |
+
"step": 6080
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 1.44,
|
2076 |
+
"learning_rate": 0.00015702938840349485,
|
2077 |
+
"loss": 0.671,
|
2078 |
+
"step": 6100
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 1.45,
|
2082 |
+
"learning_rate": 0.00015655281969817315,
|
2083 |
+
"loss": 0.6611,
|
2084 |
+
"step": 6120
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 1.45,
|
2088 |
+
"learning_rate": 0.00015607625099285145,
|
2089 |
+
"loss": 0.6606,
|
2090 |
+
"step": 6140
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 1.46,
|
2094 |
+
"learning_rate": 0.00015559968228752978,
|
2095 |
+
"loss": 0.6647,
|
2096 |
+
"step": 6160
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.46,
|
2100 |
+
"learning_rate": 0.00015512311358220808,
|
2101 |
+
"loss": 0.6652,
|
2102 |
+
"step": 6180
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.47,
|
2106 |
+
"learning_rate": 0.0001546465448768864,
|
2107 |
+
"loss": 0.6629,
|
2108 |
+
"step": 6200
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 1.47,
|
2112 |
+
"eval_loss": 0.6549723148345947,
|
2113 |
+
"eval_runtime": 49.4871,
|
2114 |
+
"eval_samples_per_second": 40.415,
|
2115 |
+
"eval_steps_per_second": 2.526,
|
2116 |
+
"step": 6200
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.47,
|
2120 |
+
"learning_rate": 0.00015416997617156473,
|
2121 |
+
"loss": 0.6685,
|
2122 |
+
"step": 6220
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.48,
|
2126 |
+
"learning_rate": 0.00015369340746624306,
|
2127 |
+
"loss": 0.6578,
|
2128 |
+
"step": 6240
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"epoch": 1.48,
|
2132 |
+
"learning_rate": 0.00015321683876092136,
|
2133 |
+
"loss": 0.6587,
|
2134 |
+
"step": 6260
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.48,
|
2138 |
+
"learning_rate": 0.00015274027005559966,
|
2139 |
+
"loss": 0.6655,
|
2140 |
+
"step": 6280
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.49,
|
2144 |
+
"learning_rate": 0.000152263701350278,
|
2145 |
+
"loss": 0.6662,
|
2146 |
+
"step": 6300
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 1.49,
|
2150 |
+
"learning_rate": 0.0001517871326449563,
|
2151 |
+
"loss": 0.6648,
|
2152 |
+
"step": 6320
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.5,
|
2156 |
+
"learning_rate": 0.00015131056393963464,
|
2157 |
+
"loss": 0.6638,
|
2158 |
+
"step": 6340
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.5,
|
2162 |
+
"learning_rate": 0.00015083399523431294,
|
2163 |
+
"loss": 0.6614,
|
2164 |
+
"step": 6360
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 1.51,
|
2168 |
+
"learning_rate": 0.00015035742652899124,
|
2169 |
+
"loss": 0.6552,
|
2170 |
+
"step": 6380
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 1.51,
|
2174 |
+
"learning_rate": 0.00014988085782366957,
|
2175 |
+
"loss": 0.6753,
|
2176 |
+
"step": 6400
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.51,
|
2180 |
+
"eval_loss": 0.6544620990753174,
|
2181 |
+
"eval_runtime": 49.3242,
|
2182 |
+
"eval_samples_per_second": 40.548,
|
2183 |
+
"eval_steps_per_second": 2.534,
|
2184 |
+
"step": 6400
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 1.52,
|
2188 |
+
"learning_rate": 0.00014940428911834787,
|
2189 |
+
"loss": 0.6588,
|
2190 |
+
"step": 6420
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 1.52,
|
2194 |
+
"learning_rate": 0.0001489277204130262,
|
2195 |
+
"loss": 0.6609,
|
2196 |
+
"step": 6440
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 1.53,
|
2200 |
+
"learning_rate": 0.00014845115170770452,
|
2201 |
+
"loss": 0.6565,
|
2202 |
+
"step": 6460
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 1.53,
|
2206 |
+
"learning_rate": 0.00014797458300238282,
|
2207 |
+
"loss": 0.6589,
|
2208 |
+
"step": 6480
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.54,
|
2212 |
+
"learning_rate": 0.00014749801429706115,
|
2213 |
+
"loss": 0.6585,
|
2214 |
+
"step": 6500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.54,
|
2218 |
+
"learning_rate": 0.00014702144559173945,
|
2219 |
+
"loss": 0.6737,
|
2220 |
+
"step": 6520
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 1.55,
|
2224 |
+
"learning_rate": 0.00014654487688641778,
|
2225 |
+
"loss": 0.6554,
|
2226 |
+
"step": 6540
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 1.55,
|
2230 |
+
"learning_rate": 0.0001460683081810961,
|
2231 |
+
"loss": 0.6603,
|
2232 |
+
"step": 6560
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 1.56,
|
2236 |
+
"learning_rate": 0.0001455917394757744,
|
2237 |
+
"loss": 0.6647,
|
2238 |
+
"step": 6580
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 1.56,
|
2242 |
+
"learning_rate": 0.00014511517077045273,
|
2243 |
+
"loss": 0.6632,
|
2244 |
+
"step": 6600
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 1.56,
|
2248 |
+
"eval_loss": 0.6527110934257507,
|
2249 |
+
"eval_runtime": 49.2622,
|
2250 |
+
"eval_samples_per_second": 40.599,
|
2251 |
+
"eval_steps_per_second": 2.537,
|
2252 |
+
"step": 6600
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 1.57,
|
2256 |
+
"learning_rate": 0.00014463860206513106,
|
2257 |
+
"loss": 0.6705,
|
2258 |
+
"step": 6620
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 1.57,
|
2262 |
+
"learning_rate": 0.00014416203335980936,
|
2263 |
+
"loss": 0.6703,
|
2264 |
+
"step": 6640
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.57,
|
2268 |
+
"learning_rate": 0.00014368546465448766,
|
2269 |
+
"loss": 0.6602,
|
2270 |
+
"step": 6660
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 1.58,
|
2274 |
+
"learning_rate": 0.000143208895949166,
|
2275 |
+
"loss": 0.6639,
|
2276 |
+
"step": 6680
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 1.58,
|
2280 |
+
"learning_rate": 0.00014273232724384432,
|
2281 |
+
"loss": 0.6645,
|
2282 |
+
"step": 6700
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 1.59,
|
2286 |
+
"learning_rate": 0.00014225575853852262,
|
2287 |
+
"loss": 0.6655,
|
2288 |
+
"step": 6720
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.59,
|
2292 |
+
"learning_rate": 0.00014177918983320094,
|
2293 |
+
"loss": 0.664,
|
2294 |
+
"step": 6740
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 1.6,
|
2298 |
+
"learning_rate": 0.00014130262112787927,
|
2299 |
+
"loss": 0.6656,
|
2300 |
+
"step": 6760
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 1.6,
|
2304 |
+
"learning_rate": 0.00014082605242255757,
|
2305 |
+
"loss": 0.6658,
|
2306 |
+
"step": 6780
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.61,
|
2310 |
+
"learning_rate": 0.0001403494837172359,
|
2311 |
+
"loss": 0.6641,
|
2312 |
+
"step": 6800
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 1.61,
|
2316 |
+
"eval_loss": 0.6513609886169434,
|
2317 |
+
"eval_runtime": 49.4424,
|
2318 |
+
"eval_samples_per_second": 40.451,
|
2319 |
+
"eval_steps_per_second": 2.528,
|
2320 |
+
"step": 6800
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.61,
|
2324 |
+
"learning_rate": 0.0001398729150119142,
|
2325 |
+
"loss": 0.6599,
|
2326 |
+
"step": 6820
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 1.62,
|
2330 |
+
"learning_rate": 0.00013939634630659252,
|
2331 |
+
"loss": 0.6552,
|
2332 |
+
"step": 6840
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 1.62,
|
2336 |
+
"learning_rate": 0.00013891977760127085,
|
2337 |
+
"loss": 0.6616,
|
2338 |
+
"step": 6860
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 1.63,
|
2342 |
+
"learning_rate": 0.00013844320889594915,
|
2343 |
+
"loss": 0.6635,
|
2344 |
+
"step": 6880
|
2345 |
+
},
|
2346 |
+
{
|
2347 |
+
"epoch": 1.63,
|
2348 |
+
"learning_rate": 0.00013796664019062745,
|
2349 |
+
"loss": 0.6608,
|
2350 |
+
"step": 6900
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"epoch": 1.64,
|
2354 |
+
"learning_rate": 0.00013749007148530578,
|
2355 |
+
"loss": 0.6596,
|
2356 |
+
"step": 6920
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 1.64,
|
2360 |
+
"learning_rate": 0.0001370135027799841,
|
2361 |
+
"loss": 0.6589,
|
2362 |
+
"step": 6940
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.65,
|
2366 |
+
"learning_rate": 0.0001365369340746624,
|
2367 |
+
"loss": 0.6627,
|
2368 |
+
"step": 6960
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 1.65,
|
2372 |
+
"learning_rate": 0.00013606036536934073,
|
2373 |
+
"loss": 0.6606,
|
2374 |
+
"step": 6980
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 1.65,
|
2378 |
+
"learning_rate": 0.00013558379666401906,
|
2379 |
+
"loss": 0.6658,
|
2380 |
+
"step": 7000
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 1.65,
|
2384 |
+
"eval_loss": 0.6510519981384277,
|
2385 |
+
"eval_runtime": 49.5012,
|
2386 |
+
"eval_samples_per_second": 40.403,
|
2387 |
+
"eval_steps_per_second": 2.525,
|
2388 |
+
"step": 7000
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 1.66,
|
2392 |
+
"learning_rate": 0.00013510722795869736,
|
2393 |
+
"loss": 0.6571,
|
2394 |
+
"step": 7020
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.66,
|
2398 |
+
"learning_rate": 0.0001346306592533757,
|
2399 |
+
"loss": 0.6607,
|
2400 |
+
"step": 7040
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 1.67,
|
2404 |
+
"learning_rate": 0.000134154090548054,
|
2405 |
+
"loss": 0.6562,
|
2406 |
+
"step": 7060
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 1.67,
|
2410 |
+
"learning_rate": 0.00013367752184273232,
|
2411 |
+
"loss": 0.6582,
|
2412 |
+
"step": 7080
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 1.68,
|
2416 |
+
"learning_rate": 0.00013320095313741064,
|
2417 |
+
"loss": 0.6635,
|
2418 |
+
"step": 7100
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.68,
|
2422 |
+
"learning_rate": 0.00013272438443208894,
|
2423 |
+
"loss": 0.6682,
|
2424 |
+
"step": 7120
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 1.69,
|
2428 |
+
"learning_rate": 0.00013224781572676727,
|
2429 |
+
"loss": 0.6633,
|
2430 |
+
"step": 7140
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 1.69,
|
2434 |
+
"learning_rate": 0.0001317712470214456,
|
2435 |
+
"loss": 0.6671,
|
2436 |
+
"step": 7160
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 1.7,
|
2440 |
+
"learning_rate": 0.0001312946783161239,
|
2441 |
+
"loss": 0.6645,
|
2442 |
+
"step": 7180
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 1.7,
|
2446 |
+
"learning_rate": 0.0001308181096108022,
|
2447 |
+
"loss": 0.6699,
|
2448 |
+
"step": 7200
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 1.7,
|
2452 |
+
"eval_loss": 0.6502068042755127,
|
2453 |
+
"eval_runtime": 49.4619,
|
2454 |
+
"eval_samples_per_second": 40.435,
|
2455 |
+
"eval_steps_per_second": 2.527,
|
2456 |
+
"step": 7200
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 1.71,
|
2460 |
+
"learning_rate": 0.00013034154090548053,
|
2461 |
+
"loss": 0.6617,
|
2462 |
+
"step": 7220
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 1.71,
|
2466 |
+
"learning_rate": 0.00012986497220015885,
|
2467 |
+
"loss": 0.6639,
|
2468 |
+
"step": 7240
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 1.72,
|
2472 |
+
"learning_rate": 0.00012938840349483715,
|
2473 |
+
"loss": 0.6634,
|
2474 |
+
"step": 7260
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.72,
|
2478 |
+
"learning_rate": 0.00012891183478951548,
|
2479 |
+
"loss": 0.663,
|
2480 |
+
"step": 7280
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 1.73,
|
2484 |
+
"learning_rate": 0.00012843526608419378,
|
2485 |
+
"loss": 0.6653,
|
2486 |
+
"step": 7300
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 1.73,
|
2490 |
+
"learning_rate": 0.0001279586973788721,
|
2491 |
+
"loss": 0.6555,
|
2492 |
+
"step": 7320
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 1.74,
|
2496 |
+
"learning_rate": 0.00012748212867355044,
|
2497 |
+
"loss": 0.6653,
|
2498 |
+
"step": 7340
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 1.74,
|
2502 |
+
"learning_rate": 0.00012700555996822874,
|
2503 |
+
"loss": 0.6573,
|
2504 |
+
"step": 7360
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 1.74,
|
2508 |
+
"learning_rate": 0.00012652899126290706,
|
2509 |
+
"loss": 0.658,
|
2510 |
+
"step": 7380
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 1.75,
|
2514 |
+
"learning_rate": 0.0001260524225575854,
|
2515 |
+
"loss": 0.6562,
|
2516 |
+
"step": 7400
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.75,
|
2520 |
+
"eval_loss": 0.6491650342941284,
|
2521 |
+
"eval_runtime": 49.2463,
|
2522 |
+
"eval_samples_per_second": 40.612,
|
2523 |
+
"eval_steps_per_second": 2.538,
|
2524 |
+
"step": 7400
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 1.75,
|
2528 |
+
"learning_rate": 0.0001255758538522637,
|
2529 |
+
"loss": 0.6592,
|
2530 |
+
"step": 7420
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.76,
|
2534 |
+
"learning_rate": 0.000125099285146942,
|
2535 |
+
"loss": 0.6587,
|
2536 |
+
"step": 7440
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 1.76,
|
2540 |
+
"learning_rate": 0.00012462271644162032,
|
2541 |
+
"loss": 0.6616,
|
2542 |
+
"step": 7460
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 1.77,
|
2546 |
+
"learning_rate": 0.00012414614773629865,
|
2547 |
+
"loss": 0.655,
|
2548 |
+
"step": 7480
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 1.77,
|
2552 |
+
"learning_rate": 0.00012366957903097695,
|
2553 |
+
"loss": 0.6591,
|
2554 |
+
"step": 7500
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 1.78,
|
2558 |
+
"learning_rate": 0.00012319301032565527,
|
2559 |
+
"loss": 0.6545,
|
2560 |
+
"step": 7520
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 1.78,
|
2564 |
+
"learning_rate": 0.0001227164416203336,
|
2565 |
+
"loss": 0.6673,
|
2566 |
+
"step": 7540
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 1.79,
|
2570 |
+
"learning_rate": 0.0001222398729150119,
|
2571 |
+
"loss": 0.6626,
|
2572 |
+
"step": 7560
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 1.79,
|
2576 |
+
"learning_rate": 0.00012176330420969023,
|
2577 |
+
"loss": 0.6663,
|
2578 |
+
"step": 7580
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 1.8,
|
2582 |
+
"learning_rate": 0.00012128673550436854,
|
2583 |
+
"loss": 0.6643,
|
2584 |
+
"step": 7600
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 1.8,
|
2588 |
+
"eval_loss": 0.6482685804367065,
|
2589 |
+
"eval_runtime": 49.3591,
|
2590 |
+
"eval_samples_per_second": 40.519,
|
2591 |
+
"eval_steps_per_second": 2.532,
|
2592 |
+
"step": 7600
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 1.8,
|
2596 |
+
"learning_rate": 0.00012081016679904685,
|
2597 |
+
"loss": 0.6623,
|
2598 |
+
"step": 7620
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 1.81,
|
2602 |
+
"learning_rate": 0.00012033359809372518,
|
2603 |
+
"loss": 0.6636,
|
2604 |
+
"step": 7640
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 1.81,
|
2608 |
+
"learning_rate": 0.00011985702938840348,
|
2609 |
+
"loss": 0.6598,
|
2610 |
+
"step": 7660
|
2611 |
+
},
|
2612 |
+
{
|
2613 |
+
"epoch": 1.82,
|
2614 |
+
"learning_rate": 0.0001193804606830818,
|
2615 |
+
"loss": 0.6521,
|
2616 |
+
"step": 7680
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 1.82,
|
2620 |
+
"learning_rate": 0.00011890389197776012,
|
2621 |
+
"loss": 0.664,
|
2622 |
+
"step": 7700
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 1.83,
|
2626 |
+
"learning_rate": 0.00011842732327243844,
|
2627 |
+
"loss": 0.6529,
|
2628 |
+
"step": 7720
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 1.83,
|
2632 |
+
"learning_rate": 0.00011795075456711675,
|
2633 |
+
"loss": 0.6622,
|
2634 |
+
"step": 7740
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 1.83,
|
2638 |
+
"learning_rate": 0.00011747418586179508,
|
2639 |
+
"loss": 0.6608,
|
2640 |
+
"step": 7760
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 1.84,
|
2644 |
+
"learning_rate": 0.00011699761715647338,
|
2645 |
+
"loss": 0.6556,
|
2646 |
+
"step": 7780
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 1.84,
|
2650 |
+
"learning_rate": 0.00011652104845115169,
|
2651 |
+
"loss": 0.6643,
|
2652 |
+
"step": 7800
|
2653 |
+
},
|
2654 |
+
{
|
2655 |
+
"epoch": 1.84,
|
2656 |
+
"eval_loss": 0.6474015116691589,
|
2657 |
+
"eval_runtime": 49.3608,
|
2658 |
+
"eval_samples_per_second": 40.518,
|
2659 |
+
"eval_steps_per_second": 2.532,
|
2660 |
+
"step": 7800
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 1.85,
|
2664 |
+
"learning_rate": 0.00011604447974583002,
|
2665 |
+
"loss": 0.6541,
|
2666 |
+
"step": 7820
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 1.85,
|
2670 |
+
"learning_rate": 0.00011556791104050833,
|
2671 |
+
"loss": 0.6614,
|
2672 |
+
"step": 7840
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 1.86,
|
2676 |
+
"learning_rate": 0.00011509134233518665,
|
2677 |
+
"loss": 0.6499,
|
2678 |
+
"step": 7860
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 1.86,
|
2682 |
+
"learning_rate": 0.00011461477362986497,
|
2683 |
+
"loss": 0.6563,
|
2684 |
+
"step": 7880
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 1.87,
|
2688 |
+
"learning_rate": 0.00011413820492454327,
|
2689 |
+
"loss": 0.6589,
|
2690 |
+
"step": 7900
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 1.87,
|
2694 |
+
"learning_rate": 0.00011366163621922159,
|
2695 |
+
"loss": 0.6544,
|
2696 |
+
"step": 7920
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 1.88,
|
2700 |
+
"learning_rate": 0.00011318506751389992,
|
2701 |
+
"loss": 0.6606,
|
2702 |
+
"step": 7940
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 1.88,
|
2706 |
+
"learning_rate": 0.00011270849880857823,
|
2707 |
+
"loss": 0.657,
|
2708 |
+
"step": 7960
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 1.89,
|
2712 |
+
"learning_rate": 0.00011223193010325654,
|
2713 |
+
"loss": 0.6608,
|
2714 |
+
"step": 7980
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 1.89,
|
2718 |
+
"learning_rate": 0.00011175536139793487,
|
2719 |
+
"loss": 0.6595,
|
2720 |
+
"step": 8000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 1.89,
|
2724 |
+
"eval_loss": 0.6469079256057739,
|
2725 |
+
"eval_runtime": 49.3012,
|
2726 |
+
"eval_samples_per_second": 40.567,
|
2727 |
+
"eval_steps_per_second": 2.535,
|
2728 |
+
"step": 8000
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 1.9,
|
2732 |
+
"learning_rate": 0.00011127879269261318,
|
2733 |
+
"loss": 0.6563,
|
2734 |
+
"step": 8020
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 1.9,
|
2738 |
+
"learning_rate": 0.00011080222398729148,
|
2739 |
+
"loss": 0.6602,
|
2740 |
+
"step": 8040
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 1.91,
|
2744 |
+
"learning_rate": 0.00011032565528196981,
|
2745 |
+
"loss": 0.6603,
|
2746 |
+
"step": 8060
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 1.91,
|
2750 |
+
"learning_rate": 0.00010984908657664812,
|
2751 |
+
"loss": 0.6495,
|
2752 |
+
"step": 8080
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 1.91,
|
2756 |
+
"learning_rate": 0.00010937251787132644,
|
2757 |
+
"loss": 0.6551,
|
2758 |
+
"step": 8100
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 1.92,
|
2762 |
+
"learning_rate": 0.00010891977760127084,
|
2763 |
+
"loss": 0.6497,
|
2764 |
+
"step": 8120
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 1.92,
|
2768 |
+
"learning_rate": 0.00010844320889594917,
|
2769 |
+
"loss": 0.6652,
|
2770 |
+
"step": 8140
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 1.93,
|
2774 |
+
"learning_rate": 0.00010796664019062747,
|
2775 |
+
"loss": 0.6497,
|
2776 |
+
"step": 8160
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 1.93,
|
2780 |
+
"learning_rate": 0.00010749007148530578,
|
2781 |
+
"loss": 0.6554,
|
2782 |
+
"step": 8180
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 1.94,
|
2786 |
+
"learning_rate": 0.00010701350277998411,
|
2787 |
+
"loss": 0.6563,
|
2788 |
+
"step": 8200
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 1.94,
|
2792 |
+
"eval_loss": 0.645990252494812,
|
2793 |
+
"eval_runtime": 49.3957,
|
2794 |
+
"eval_samples_per_second": 40.489,
|
2795 |
+
"eval_steps_per_second": 2.531,
|
2796 |
+
"step": 8200
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 1.94,
|
2800 |
+
"learning_rate": 0.00010653693407466242,
|
2801 |
+
"loss": 0.6572,
|
2802 |
+
"step": 8220
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 1.95,
|
2806 |
+
"learning_rate": 0.00010606036536934074,
|
2807 |
+
"loss": 0.6563,
|
2808 |
+
"step": 8240
|
2809 |
+
},
|
2810 |
+
{
|
2811 |
+
"epoch": 1.95,
|
2812 |
+
"learning_rate": 0.00010558379666401906,
|
2813 |
+
"loss": 0.6535,
|
2814 |
+
"step": 8260
|
2815 |
+
},
|
2816 |
+
{
|
2817 |
+
"epoch": 1.96,
|
2818 |
+
"learning_rate": 0.00010510722795869736,
|
2819 |
+
"loss": 0.655,
|
2820 |
+
"step": 8280
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 1.96,
|
2824 |
+
"learning_rate": 0.00010463065925337568,
|
2825 |
+
"loss": 0.6554,
|
2826 |
+
"step": 8300
|
2827 |
+
},
|
2828 |
+
{
|
2829 |
+
"epoch": 1.97,
|
2830 |
+
"learning_rate": 0.000104154090548054,
|
2831 |
+
"loss": 0.6559,
|
2832 |
+
"step": 8320
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 1.97,
|
2836 |
+
"learning_rate": 0.00010367752184273232,
|
2837 |
+
"loss": 0.6522,
|
2838 |
+
"step": 8340
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 1.98,
|
2842 |
+
"learning_rate": 0.00010320095313741063,
|
2843 |
+
"loss": 0.6568,
|
2844 |
+
"step": 8360
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 1.98,
|
2848 |
+
"learning_rate": 0.00010272438443208896,
|
2849 |
+
"loss": 0.6566,
|
2850 |
+
"step": 8380
|
2851 |
+
},
|
2852 |
+
{
|
2853 |
+
"epoch": 1.99,
|
2854 |
+
"learning_rate": 0.00010224781572676727,
|
2855 |
+
"loss": 0.6496,
|
2856 |
+
"step": 8400
|
2857 |
+
},
|
2858 |
+
{
|
2859 |
+
"epoch": 1.99,
|
2860 |
+
"eval_loss": 0.6457875967025757,
|
2861 |
+
"eval_runtime": 49.0201,
|
2862 |
+
"eval_samples_per_second": 40.8,
|
2863 |
+
"eval_steps_per_second": 2.55,
|
2864 |
+
"step": 8400
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 1.99,
|
2868 |
+
"learning_rate": 0.00010177124702144557,
|
2869 |
+
"loss": 0.66,
|
2870 |
+
"step": 8420
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 2.0,
|
2874 |
+
"learning_rate": 0.0001012946783161239,
|
2875 |
+
"loss": 0.6457,
|
2876 |
+
"step": 8440
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 2.0,
|
2880 |
+
"learning_rate": 0.0001008419380460683,
|
2881 |
+
"loss": 0.6349,
|
2882 |
+
"step": 8460
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 2.0,
|
2886 |
+
"learning_rate": 0.00010036536934074662,
|
2887 |
+
"loss": 0.6545,
|
2888 |
+
"step": 8480
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 2.01,
|
2892 |
+
"learning_rate": 9.988880063542493e-05,
|
2893 |
+
"loss": 0.6515,
|
2894 |
+
"step": 8500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 2.01,
|
2898 |
+
"learning_rate": 9.941223193010326e-05,
|
2899 |
+
"loss": 0.6459,
|
2900 |
+
"step": 8520
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 2.02,
|
2904 |
+
"learning_rate": 9.893566322478156e-05,
|
2905 |
+
"loss": 0.6494,
|
2906 |
+
"step": 8540
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 2.02,
|
2910 |
+
"learning_rate": 9.845909451945987e-05,
|
2911 |
+
"loss": 0.6608,
|
2912 |
+
"step": 8560
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 2.03,
|
2916 |
+
"learning_rate": 9.79825258141382e-05,
|
2917 |
+
"loss": 0.6485,
|
2918 |
+
"step": 8580
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 2.03,
|
2922 |
+
"learning_rate": 9.750595710881651e-05,
|
2923 |
+
"loss": 0.6461,
|
2924 |
+
"step": 8600
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 2.03,
|
2928 |
+
"eval_loss": 0.6450995802879333,
|
2929 |
+
"eval_runtime": 49.2592,
|
2930 |
+
"eval_samples_per_second": 40.602,
|
2931 |
+
"eval_steps_per_second": 2.538,
|
2932 |
+
"step": 8600
|
2933 |
+
},
|
2934 |
+
{
|
2935 |
+
"epoch": 2.04,
|
2936 |
+
"learning_rate": 9.702938840349483e-05,
|
2937 |
+
"loss": 0.6523,
|
2938 |
+
"step": 8620
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 2.04,
|
2942 |
+
"learning_rate": 9.655281969817315e-05,
|
2943 |
+
"loss": 0.6565,
|
2944 |
+
"step": 8640
|
2945 |
+
},
|
2946 |
+
{
|
2947 |
+
"epoch": 2.05,
|
2948 |
+
"learning_rate": 9.607625099285145e-05,
|
2949 |
+
"loss": 0.6541,
|
2950 |
+
"step": 8660
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 2.05,
|
2954 |
+
"learning_rate": 9.559968228752977e-05,
|
2955 |
+
"loss": 0.6585,
|
2956 |
+
"step": 8680
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 2.06,
|
2960 |
+
"learning_rate": 9.51231135822081e-05,
|
2961 |
+
"loss": 0.6531,
|
2962 |
+
"step": 8700
|
2963 |
+
},
|
2964 |
+
{
|
2965 |
+
"epoch": 2.06,
|
2966 |
+
"learning_rate": 9.464654487688641e-05,
|
2967 |
+
"loss": 0.6579,
|
2968 |
+
"step": 8720
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 2.07,
|
2972 |
+
"learning_rate": 9.416997617156472e-05,
|
2973 |
+
"loss": 0.6438,
|
2974 |
+
"step": 8740
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 2.07,
|
2978 |
+
"learning_rate": 9.369340746624305e-05,
|
2979 |
+
"loss": 0.6516,
|
2980 |
+
"step": 8760
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 2.08,
|
2984 |
+
"learning_rate": 9.321683876092136e-05,
|
2985 |
+
"loss": 0.6576,
|
2986 |
+
"step": 8780
|
2987 |
+
},
|
2988 |
+
{
|
2989 |
+
"epoch": 2.08,
|
2990 |
+
"learning_rate": 9.274027005559966e-05,
|
2991 |
+
"loss": 0.6506,
|
2992 |
+
"step": 8800
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 2.08,
|
2996 |
+
"eval_loss": 0.6444578170776367,
|
2997 |
+
"eval_runtime": 49.0631,
|
2998 |
+
"eval_samples_per_second": 40.764,
|
2999 |
+
"eval_steps_per_second": 2.548,
|
3000 |
+
"step": 8800
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 2.09,
|
3004 |
+
"learning_rate": 9.226370135027799e-05,
|
3005 |
+
"loss": 0.6484,
|
3006 |
+
"step": 8820
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 2.09,
|
3010 |
+
"learning_rate": 9.17871326449563e-05,
|
3011 |
+
"loss": 0.6566,
|
3012 |
+
"step": 8840
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 2.09,
|
3016 |
+
"learning_rate": 9.131056393963462e-05,
|
3017 |
+
"loss": 0.6547,
|
3018 |
+
"step": 8860
|
3019 |
+
},
|
3020 |
+
{
|
3021 |
+
"epoch": 2.1,
|
3022 |
+
"learning_rate": 9.083399523431295e-05,
|
3023 |
+
"loss": 0.6532,
|
3024 |
+
"step": 8880
|
3025 |
+
},
|
3026 |
+
{
|
3027 |
+
"epoch": 2.1,
|
3028 |
+
"learning_rate": 9.035742652899126e-05,
|
3029 |
+
"loss": 0.6532,
|
3030 |
+
"step": 8900
|
3031 |
+
},
|
3032 |
+
{
|
3033 |
+
"epoch": 2.11,
|
3034 |
+
"learning_rate": 8.988085782366956e-05,
|
3035 |
+
"loss": 0.6479,
|
3036 |
+
"step": 8920
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 2.11,
|
3040 |
+
"learning_rate": 8.940428911834789e-05,
|
3041 |
+
"loss": 0.6548,
|
3042 |
+
"step": 8940
|
3043 |
+
},
|
3044 |
+
{
|
3045 |
+
"epoch": 2.12,
|
3046 |
+
"learning_rate": 8.89277204130262e-05,
|
3047 |
+
"loss": 0.647,
|
3048 |
+
"step": 8960
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 2.12,
|
3052 |
+
"learning_rate": 8.845115170770452e-05,
|
3053 |
+
"loss": 0.6478,
|
3054 |
+
"step": 8980
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 2.13,
|
3058 |
+
"learning_rate": 8.797458300238284e-05,
|
3059 |
+
"loss": 0.6553,
|
3060 |
+
"step": 9000
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 2.13,
|
3064 |
+
"eval_loss": 0.6433074474334717,
|
3065 |
+
"eval_runtime": 49.3831,
|
3066 |
+
"eval_samples_per_second": 40.5,
|
3067 |
+
"eval_steps_per_second": 2.531,
|
3068 |
+
"step": 9000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 2.13,
|
3072 |
+
"learning_rate": 8.749801429706116e-05,
|
3073 |
+
"loss": 0.6443,
|
3074 |
+
"step": 9020
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 2.14,
|
3078 |
+
"learning_rate": 8.702144559173947e-05,
|
3079 |
+
"loss": 0.6518,
|
3080 |
+
"step": 9040
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 2.14,
|
3084 |
+
"learning_rate": 8.65448768864178e-05,
|
3085 |
+
"loss": 0.6578,
|
3086 |
+
"step": 9060
|
3087 |
+
},
|
3088 |
+
{
|
3089 |
+
"epoch": 2.15,
|
3090 |
+
"learning_rate": 8.60683081810961e-05,
|
3091 |
+
"loss": 0.6472,
|
3092 |
+
"step": 9080
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 2.15,
|
3096 |
+
"learning_rate": 8.559173947577441e-05,
|
3097 |
+
"loss": 0.6471,
|
3098 |
+
"step": 9100
|
3099 |
+
},
|
3100 |
+
{
|
3101 |
+
"epoch": 2.16,
|
3102 |
+
"learning_rate": 8.511517077045274e-05,
|
3103 |
+
"loss": 0.6482,
|
3104 |
+
"step": 9120
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 2.16,
|
3108 |
+
"learning_rate": 8.463860206513105e-05,
|
3109 |
+
"loss": 0.6522,
|
3110 |
+
"step": 9140
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 2.17,
|
3114 |
+
"learning_rate": 8.416203335980937e-05,
|
3115 |
+
"loss": 0.6584,
|
3116 |
+
"step": 9160
|
3117 |
+
},
|
3118 |
+
{
|
3119 |
+
"epoch": 2.17,
|
3120 |
+
"learning_rate": 8.368546465448769e-05,
|
3121 |
+
"loss": 0.6596,
|
3122 |
+
"step": 9180
|
3123 |
+
},
|
3124 |
+
{
|
3125 |
+
"epoch": 2.17,
|
3126 |
+
"learning_rate": 8.320889594916599e-05,
|
3127 |
+
"loss": 0.6581,
|
3128 |
+
"step": 9200
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 2.17,
|
3132 |
+
"eval_loss": 0.6426697969436646,
|
3133 |
+
"eval_runtime": 49.0935,
|
3134 |
+
"eval_samples_per_second": 40.739,
|
3135 |
+
"eval_steps_per_second": 2.546,
|
3136 |
+
"step": 9200
|
3137 |
+
},
|
3138 |
+
{
|
3139 |
+
"epoch": 2.18,
|
3140 |
+
"learning_rate": 8.273232724384431e-05,
|
3141 |
+
"loss": 0.6441,
|
3142 |
+
"step": 9220
|
3143 |
+
},
|
3144 |
+
{
|
3145 |
+
"epoch": 2.18,
|
3146 |
+
"learning_rate": 8.225575853852263e-05,
|
3147 |
+
"loss": 0.6509,
|
3148 |
+
"step": 9240
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 2.19,
|
3152 |
+
"learning_rate": 8.177918983320095e-05,
|
3153 |
+
"loss": 0.6409,
|
3154 |
+
"step": 9260
|
3155 |
+
},
|
3156 |
+
{
|
3157 |
+
"epoch": 2.19,
|
3158 |
+
"learning_rate": 8.130262112787926e-05,
|
3159 |
+
"loss": 0.6475,
|
3160 |
+
"step": 9280
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 2.2,
|
3164 |
+
"learning_rate": 8.082605242255759e-05,
|
3165 |
+
"loss": 0.6597,
|
3166 |
+
"step": 9300
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 2.2,
|
3170 |
+
"learning_rate": 8.03494837172359e-05,
|
3171 |
+
"loss": 0.6544,
|
3172 |
+
"step": 9320
|
3173 |
+
},
|
3174 |
+
{
|
3175 |
+
"epoch": 2.21,
|
3176 |
+
"learning_rate": 7.98729150119142e-05,
|
3177 |
+
"loss": 0.6528,
|
3178 |
+
"step": 9340
|
3179 |
+
},
|
3180 |
+
{
|
3181 |
+
"epoch": 2.21,
|
3182 |
+
"learning_rate": 7.939634630659253e-05,
|
3183 |
+
"loss": 0.644,
|
3184 |
+
"step": 9360
|
3185 |
+
},
|
3186 |
+
{
|
3187 |
+
"epoch": 2.22,
|
3188 |
+
"learning_rate": 7.891977760127084e-05,
|
3189 |
+
"loss": 0.6552,
|
3190 |
+
"step": 9380
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 2.22,
|
3194 |
+
"learning_rate": 7.844320889594916e-05,
|
3195 |
+
"loss": 0.6548,
|
3196 |
+
"step": 9400
|
3197 |
+
},
|
3198 |
+
{
|
3199 |
+
"epoch": 2.22,
|
3200 |
+
"eval_loss": 0.6423606276512146,
|
3201 |
+
"eval_runtime": 49.6466,
|
3202 |
+
"eval_samples_per_second": 40.285,
|
3203 |
+
"eval_steps_per_second": 2.518,
|
3204 |
+
"step": 9400
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 2.23,
|
3208 |
+
"learning_rate": 7.796664019062748e-05,
|
3209 |
+
"loss": 0.6568,
|
3210 |
+
"step": 9420
|
3211 |
+
},
|
3212 |
+
{
|
3213 |
+
"epoch": 2.23,
|
3214 |
+
"learning_rate": 7.74900714853058e-05,
|
3215 |
+
"loss": 0.6539,
|
3216 |
+
"step": 9440
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 2.24,
|
3220 |
+
"learning_rate": 7.70135027799841e-05,
|
3221 |
+
"loss": 0.6468,
|
3222 |
+
"step": 9460
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 2.24,
|
3226 |
+
"learning_rate": 7.653693407466243e-05,
|
3227 |
+
"loss": 0.6425,
|
3228 |
+
"step": 9480
|
3229 |
+
},
|
3230 |
+
{
|
3231 |
+
"epoch": 2.25,
|
3232 |
+
"learning_rate": 7.606036536934074e-05,
|
3233 |
+
"loss": 0.6523,
|
3234 |
+
"step": 9500
|
3235 |
+
},
|
3236 |
+
{
|
3237 |
+
"epoch": 2.25,
|
3238 |
+
"learning_rate": 7.558379666401905e-05,
|
3239 |
+
"loss": 0.6468,
|
3240 |
+
"step": 9520
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 2.26,
|
3244 |
+
"learning_rate": 7.510722795869738e-05,
|
3245 |
+
"loss": 0.6518,
|
3246 |
+
"step": 9540
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 2.26,
|
3250 |
+
"learning_rate": 7.46306592533757e-05,
|
3251 |
+
"loss": 0.6534,
|
3252 |
+
"step": 9560
|
3253 |
+
},
|
3254 |
+
{
|
3255 |
+
"epoch": 2.26,
|
3256 |
+
"learning_rate": 7.415409054805401e-05,
|
3257 |
+
"loss": 0.6471,
|
3258 |
+
"step": 9580
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 2.27,
|
3262 |
+
"learning_rate": 7.367752184273232e-05,
|
3263 |
+
"loss": 0.6465,
|
3264 |
+
"step": 9600
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 2.27,
|
3268 |
+
"eval_loss": 0.6418060064315796,
|
3269 |
+
"eval_runtime": 49.4954,
|
3270 |
+
"eval_samples_per_second": 40.408,
|
3271 |
+
"eval_steps_per_second": 2.525,
|
3272 |
+
"step": 9600
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 2.27,
|
3276 |
+
"learning_rate": 7.320095313741064e-05,
|
3277 |
+
"loss": 0.6577,
|
3278 |
+
"step": 9620
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 2.28,
|
3282 |
+
"learning_rate": 7.272438443208895e-05,
|
3283 |
+
"loss": 0.6453,
|
3284 |
+
"step": 9640
|
3285 |
+
},
|
3286 |
+
{
|
3287 |
+
"epoch": 2.28,
|
3288 |
+
"learning_rate": 7.224781572676726e-05,
|
3289 |
+
"loss": 0.6489,
|
3290 |
+
"step": 9660
|
3291 |
+
},
|
3292 |
+
{
|
3293 |
+
"epoch": 2.29,
|
3294 |
+
"learning_rate": 7.177124702144559e-05,
|
3295 |
+
"loss": 0.6466,
|
3296 |
+
"step": 9680
|
3297 |
+
},
|
3298 |
+
{
|
3299 |
+
"epoch": 2.29,
|
3300 |
+
"learning_rate": 7.12946783161239e-05,
|
3301 |
+
"loss": 0.6493,
|
3302 |
+
"step": 9700
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 2.3,
|
3306 |
+
"learning_rate": 7.081810961080222e-05,
|
3307 |
+
"loss": 0.6537,
|
3308 |
+
"step": 9720
|
3309 |
+
},
|
3310 |
+
{
|
3311 |
+
"epoch": 2.3,
|
3312 |
+
"learning_rate": 7.034154090548053e-05,
|
3313 |
+
"loss": 0.6486,
|
3314 |
+
"step": 9740
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 2.31,
|
3318 |
+
"learning_rate": 6.986497220015885e-05,
|
3319 |
+
"loss": 0.65,
|
3320 |
+
"step": 9760
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 2.31,
|
3324 |
+
"learning_rate": 6.938840349483717e-05,
|
3325 |
+
"loss": 0.6387,
|
3326 |
+
"step": 9780
|
3327 |
+
},
|
3328 |
+
{
|
3329 |
+
"epoch": 2.32,
|
3330 |
+
"learning_rate": 6.891183478951549e-05,
|
3331 |
+
"loss": 0.6464,
|
3332 |
+
"step": 9800
|
3333 |
+
},
|
3334 |
+
{
|
3335 |
+
"epoch": 2.32,
|
3336 |
+
"eval_loss": 0.6412256360054016,
|
3337 |
+
"eval_runtime": 49.3752,
|
3338 |
+
"eval_samples_per_second": 40.506,
|
3339 |
+
"eval_steps_per_second": 2.532,
|
3340 |
+
"step": 9800
|
3341 |
+
},
|
3342 |
+
{
|
3343 |
+
"epoch": 2.32,
|
3344 |
+
"learning_rate": 6.84352660841938e-05,
|
3345 |
+
"loss": 0.6475,
|
3346 |
+
"step": 9820
|
3347 |
+
},
|
3348 |
+
{
|
3349 |
+
"epoch": 2.33,
|
3350 |
+
"learning_rate": 6.795869737887211e-05,
|
3351 |
+
"loss": 0.6543,
|
3352 |
+
"step": 9840
|
3353 |
+
},
|
3354 |
+
{
|
3355 |
+
"epoch": 2.33,
|
3356 |
+
"learning_rate": 6.748212867355043e-05,
|
3357 |
+
"loss": 0.6545,
|
3358 |
+
"step": 9860
|
3359 |
+
},
|
3360 |
+
{
|
3361 |
+
"epoch": 2.34,
|
3362 |
+
"learning_rate": 6.700555996822874e-05,
|
3363 |
+
"loss": 0.6468,
|
3364 |
+
"step": 9880
|
3365 |
+
},
|
3366 |
+
{
|
3367 |
+
"epoch": 2.34,
|
3368 |
+
"learning_rate": 6.652899126290707e-05,
|
3369 |
+
"loss": 0.651,
|
3370 |
+
"step": 9900
|
3371 |
+
},
|
3372 |
+
{
|
3373 |
+
"epoch": 2.35,
|
3374 |
+
"learning_rate": 6.605242255758538e-05,
|
3375 |
+
"loss": 0.641,
|
3376 |
+
"step": 9920
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 2.35,
|
3380 |
+
"learning_rate": 6.55758538522637e-05,
|
3381 |
+
"loss": 0.657,
|
3382 |
+
"step": 9940
|
3383 |
+
},
|
3384 |
+
{
|
3385 |
+
"epoch": 2.35,
|
3386 |
+
"learning_rate": 6.509928514694201e-05,
|
3387 |
+
"loss": 0.6481,
|
3388 |
+
"step": 9960
|
3389 |
+
},
|
3390 |
+
{
|
3391 |
+
"epoch": 2.36,
|
3392 |
+
"learning_rate": 6.462271644162034e-05,
|
3393 |
+
"loss": 0.6496,
|
3394 |
+
"step": 9980
|
3395 |
+
},
|
3396 |
+
{
|
3397 |
+
"epoch": 2.36,
|
3398 |
+
"learning_rate": 6.414614773629864e-05,
|
3399 |
+
"loss": 0.6451,
|
3400 |
+
"step": 10000
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 2.36,
|
3404 |
+
"eval_loss": 0.6414454579353333,
|
3405 |
+
"eval_runtime": 49.395,
|
3406 |
+
"eval_samples_per_second": 40.49,
|
3407 |
+
"eval_steps_per_second": 2.531,
|
3408 |
+
"step": 10000
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 2.37,
|
3412 |
+
"learning_rate": 6.366957903097696e-05,
|
3413 |
+
"loss": 0.6555,
|
3414 |
+
"step": 10020
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 2.37,
|
3418 |
+
"learning_rate": 6.319301032565528e-05,
|
3419 |
+
"loss": 0.6494,
|
3420 |
+
"step": 10040
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 2.38,
|
3424 |
+
"learning_rate": 6.271644162033359e-05,
|
3425 |
+
"loss": 0.6487,
|
3426 |
+
"step": 10060
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 2.38,
|
3430 |
+
"learning_rate": 6.22398729150119e-05,
|
3431 |
+
"loss": 0.6544,
|
3432 |
+
"step": 10080
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 2.39,
|
3436 |
+
"learning_rate": 6.176330420969023e-05,
|
3437 |
+
"loss": 0.6468,
|
3438 |
+
"step": 10100
|
3439 |
+
},
|
3440 |
+
{
|
3441 |
+
"epoch": 2.39,
|
3442 |
+
"learning_rate": 6.128673550436853e-05,
|
3443 |
+
"loss": 0.6441,
|
3444 |
+
"step": 10120
|
3445 |
+
},
|
3446 |
+
{
|
3447 |
+
"epoch": 2.4,
|
3448 |
+
"learning_rate": 6.081016679904686e-05,
|
3449 |
+
"loss": 0.6478,
|
3450 |
+
"step": 10140
|
3451 |
+
},
|
3452 |
+
{
|
3453 |
+
"epoch": 2.4,
|
3454 |
+
"learning_rate": 6.033359809372518e-05,
|
3455 |
+
"loss": 0.6539,
|
3456 |
+
"step": 10160
|
3457 |
+
},
|
3458 |
+
{
|
3459 |
+
"epoch": 2.41,
|
3460 |
+
"learning_rate": 5.985702938840349e-05,
|
3461 |
+
"loss": 0.6486,
|
3462 |
+
"step": 10180
|
3463 |
+
},
|
3464 |
+
{
|
3465 |
+
"epoch": 2.41,
|
3466 |
+
"learning_rate": 5.938046068308181e-05,
|
3467 |
+
"loss": 0.6467,
|
3468 |
+
"step": 10200
|
3469 |
+
},
|
3470 |
+
{
|
3471 |
+
"epoch": 2.41,
|
3472 |
+
"eval_loss": 0.6406835913658142,
|
3473 |
+
"eval_runtime": 49.5084,
|
3474 |
+
"eval_samples_per_second": 40.397,
|
3475 |
+
"eval_steps_per_second": 2.525,
|
3476 |
+
"step": 10200
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 2.42,
|
3480 |
+
"learning_rate": 5.890389197776013e-05,
|
3481 |
+
"loss": 0.6399,
|
3482 |
+
"step": 10220
|
3483 |
+
},
|
3484 |
+
{
|
3485 |
+
"epoch": 2.42,
|
3486 |
+
"learning_rate": 5.8427323272438435e-05,
|
3487 |
+
"loss": 0.6519,
|
3488 |
+
"step": 10240
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 2.43,
|
3492 |
+
"learning_rate": 5.7950754567116756e-05,
|
3493 |
+
"loss": 0.6465,
|
3494 |
+
"step": 10260
|
3495 |
+
},
|
3496 |
+
{
|
3497 |
+
"epoch": 2.43,
|
3498 |
+
"learning_rate": 5.7474185861795076e-05,
|
3499 |
+
"loss": 0.6479,
|
3500 |
+
"step": 10280
|
3501 |
+
},
|
3502 |
+
{
|
3503 |
+
"epoch": 2.43,
|
3504 |
+
"learning_rate": 5.6997617156473383e-05,
|
3505 |
+
"loss": 0.6462,
|
3506 |
+
"step": 10300
|
3507 |
+
},
|
3508 |
+
{
|
3509 |
+
"epoch": 2.44,
|
3510 |
+
"learning_rate": 5.6521048451151704e-05,
|
3511 |
+
"loss": 0.6451,
|
3512 |
+
"step": 10320
|
3513 |
+
},
|
3514 |
+
{
|
3515 |
+
"epoch": 2.44,
|
3516 |
+
"learning_rate": 5.604447974583002e-05,
|
3517 |
+
"loss": 0.6453,
|
3518 |
+
"step": 10340
|
3519 |
+
},
|
3520 |
+
{
|
3521 |
+
"epoch": 2.45,
|
3522 |
+
"learning_rate": 5.556791104050833e-05,
|
3523 |
+
"loss": 0.6543,
|
3524 |
+
"step": 10360
|
3525 |
+
},
|
3526 |
+
{
|
3527 |
+
"epoch": 2.45,
|
3528 |
+
"learning_rate": 5.509134233518665e-05,
|
3529 |
+
"loss": 0.6428,
|
3530 |
+
"step": 10380
|
3531 |
+
},
|
3532 |
+
{
|
3533 |
+
"epoch": 2.46,
|
3534 |
+
"learning_rate": 5.4614773629864966e-05,
|
3535 |
+
"loss": 0.6491,
|
3536 |
+
"step": 10400
|
3537 |
+
},
|
3538 |
+
{
|
3539 |
+
"epoch": 2.46,
|
3540 |
+
"eval_loss": 0.6400973796844482,
|
3541 |
+
"eval_runtime": 49.3411,
|
3542 |
+
"eval_samples_per_second": 40.534,
|
3543 |
+
"eval_steps_per_second": 2.533,
|
3544 |
+
"step": 10400
|
3545 |
+
},
|
3546 |
+
{
|
3547 |
+
"epoch": 2.46,
|
3548 |
+
"learning_rate": 5.413820492454328e-05,
|
3549 |
+
"loss": 0.649,
|
3550 |
+
"step": 10420
|
3551 |
+
},
|
3552 |
+
{
|
3553 |
+
"epoch": 2.47,
|
3554 |
+
"learning_rate": 5.36616362192216e-05,
|
3555 |
+
"loss": 0.6494,
|
3556 |
+
"step": 10440
|
3557 |
+
},
|
3558 |
+
{
|
3559 |
+
"epoch": 2.47,
|
3560 |
+
"learning_rate": 5.3185067513899913e-05,
|
3561 |
+
"loss": 0.6431,
|
3562 |
+
"step": 10460
|
3563 |
+
},
|
3564 |
+
{
|
3565 |
+
"epoch": 2.48,
|
3566 |
+
"learning_rate": 5.2708498808578234e-05,
|
3567 |
+
"loss": 0.6478,
|
3568 |
+
"step": 10480
|
3569 |
+
},
|
3570 |
+
{
|
3571 |
+
"epoch": 2.48,
|
3572 |
+
"learning_rate": 5.223193010325655e-05,
|
3573 |
+
"loss": 0.6416,
|
3574 |
+
"step": 10500
|
3575 |
+
},
|
3576 |
+
{
|
3577 |
+
"epoch": 2.49,
|
3578 |
+
"learning_rate": 5.175536139793486e-05,
|
3579 |
+
"loss": 0.6507,
|
3580 |
+
"step": 10520
|
3581 |
+
},
|
3582 |
+
{
|
3583 |
+
"epoch": 2.49,
|
3584 |
+
"learning_rate": 5.127879269261318e-05,
|
3585 |
+
"loss": 0.6448,
|
3586 |
+
"step": 10540
|
3587 |
+
},
|
3588 |
+
{
|
3589 |
+
"epoch": 2.5,
|
3590 |
+
"learning_rate": 5.0802223987291496e-05,
|
3591 |
+
"loss": 0.6455,
|
3592 |
+
"step": 10560
|
3593 |
+
},
|
3594 |
+
{
|
3595 |
+
"epoch": 2.5,
|
3596 |
+
"learning_rate": 5.032565528196981e-05,
|
3597 |
+
"loss": 0.6437,
|
3598 |
+
"step": 10580
|
3599 |
+
},
|
3600 |
+
{
|
3601 |
+
"epoch": 2.51,
|
3602 |
+
"learning_rate": 4.984908657664813e-05,
|
3603 |
+
"loss": 0.6488,
|
3604 |
+
"step": 10600
|
3605 |
+
},
|
3606 |
+
{
|
3607 |
+
"epoch": 2.51,
|
3608 |
+
"eval_loss": 0.6400858163833618,
|
3609 |
+
"eval_runtime": 49.8084,
|
3610 |
+
"eval_samples_per_second": 40.154,
|
3611 |
+
"eval_steps_per_second": 2.51,
|
3612 |
+
"step": 10600
|
3613 |
+
},
|
3614 |
+
{
|
3615 |
+
"epoch": 2.51,
|
3616 |
+
"learning_rate": 4.937251787132645e-05,
|
3617 |
+
"loss": 0.6436,
|
3618 |
+
"step": 10620
|
3619 |
+
},
|
3620 |
+
{
|
3621 |
+
"epoch": 2.52,
|
3622 |
+
"learning_rate": 4.889594916600476e-05,
|
3623 |
+
"loss": 0.6446,
|
3624 |
+
"step": 10640
|
3625 |
+
},
|
3626 |
+
{
|
3627 |
+
"epoch": 2.52,
|
3628 |
+
"learning_rate": 4.841938046068308e-05,
|
3629 |
+
"loss": 0.6488,
|
3630 |
+
"step": 10660
|
3631 |
+
},
|
3632 |
+
{
|
3633 |
+
"epoch": 2.52,
|
3634 |
+
"learning_rate": 4.79428117553614e-05,
|
3635 |
+
"loss": 0.6485,
|
3636 |
+
"step": 10680
|
3637 |
+
},
|
3638 |
+
{
|
3639 |
+
"epoch": 2.53,
|
3640 |
+
"learning_rate": 4.7466243050039705e-05,
|
3641 |
+
"loss": 0.6524,
|
3642 |
+
"step": 10700
|
3643 |
+
},
|
3644 |
+
{
|
3645 |
+
"epoch": 2.53,
|
3646 |
+
"learning_rate": 4.6989674344718026e-05,
|
3647 |
+
"loss": 0.6376,
|
3648 |
+
"step": 10720
|
3649 |
+
},
|
3650 |
+
{
|
3651 |
+
"epoch": 2.54,
|
3652 |
+
"learning_rate": 4.6513105639396346e-05,
|
3653 |
+
"loss": 0.649,
|
3654 |
+
"step": 10740
|
3655 |
+
},
|
3656 |
+
{
|
3657 |
+
"epoch": 2.54,
|
3658 |
+
"learning_rate": 4.603653693407465e-05,
|
3659 |
+
"loss": 0.6444,
|
3660 |
+
"step": 10760
|
3661 |
+
},
|
3662 |
+
{
|
3663 |
+
"epoch": 2.55,
|
3664 |
+
"learning_rate": 4.5559968228752974e-05,
|
3665 |
+
"loss": 0.6407,
|
3666 |
+
"step": 10780
|
3667 |
+
},
|
3668 |
+
{
|
3669 |
+
"epoch": 2.55,
|
3670 |
+
"learning_rate": 4.5083399523431294e-05,
|
3671 |
+
"loss": 0.6448,
|
3672 |
+
"step": 10800
|
3673 |
+
},
|
3674 |
+
{
|
3675 |
+
"epoch": 2.55,
|
3676 |
+
"eval_loss": 0.6392157077789307,
|
3677 |
+
"eval_runtime": 49.7963,
|
3678 |
+
"eval_samples_per_second": 40.164,
|
3679 |
+
"eval_steps_per_second": 2.51,
|
3680 |
+
"step": 10800
|
3681 |
+
},
|
3682 |
+
{
|
3683 |
+
"epoch": 2.56,
|
3684 |
+
"learning_rate": 4.46068308181096e-05,
|
3685 |
+
"loss": 0.6454,
|
3686 |
+
"step": 10820
|
3687 |
+
},
|
3688 |
+
{
|
3689 |
+
"epoch": 2.56,
|
3690 |
+
"learning_rate": 4.413026211278792e-05,
|
3691 |
+
"loss": 0.6544,
|
3692 |
+
"step": 10840
|
3693 |
+
},
|
3694 |
+
{
|
3695 |
+
"epoch": 2.57,
|
3696 |
+
"learning_rate": 4.365369340746624e-05,
|
3697 |
+
"loss": 0.6478,
|
3698 |
+
"step": 10860
|
3699 |
+
},
|
3700 |
+
{
|
3701 |
+
"epoch": 2.57,
|
3702 |
+
"learning_rate": 4.3177124702144556e-05,
|
3703 |
+
"loss": 0.6434,
|
3704 |
+
"step": 10880
|
3705 |
+
},
|
3706 |
+
{
|
3707 |
+
"epoch": 2.58,
|
3708 |
+
"learning_rate": 4.270055599682287e-05,
|
3709 |
+
"loss": 0.6482,
|
3710 |
+
"step": 10900
|
3711 |
+
},
|
3712 |
+
{
|
3713 |
+
"epoch": 2.58,
|
3714 |
+
"learning_rate": 4.222398729150119e-05,
|
3715 |
+
"loss": 0.6403,
|
3716 |
+
"step": 10920
|
3717 |
+
},
|
3718 |
+
{
|
3719 |
+
"epoch": 2.59,
|
3720 |
+
"learning_rate": 4.1747418586179504e-05,
|
3721 |
+
"loss": 0.6501,
|
3722 |
+
"step": 10940
|
3723 |
+
},
|
3724 |
+
{
|
3725 |
+
"epoch": 2.59,
|
3726 |
+
"learning_rate": 4.127084988085782e-05,
|
3727 |
+
"loss": 0.6507,
|
3728 |
+
"step": 10960
|
3729 |
+
},
|
3730 |
+
{
|
3731 |
+
"epoch": 2.6,
|
3732 |
+
"learning_rate": 4.079428117553614e-05,
|
3733 |
+
"loss": 0.6496,
|
3734 |
+
"step": 10980
|
3735 |
+
},
|
3736 |
+
{
|
3737 |
+
"epoch": 2.6,
|
3738 |
+
"learning_rate": 4.031771247021445e-05,
|
3739 |
+
"loss": 0.6544,
|
3740 |
+
"step": 11000
|
3741 |
+
},
|
3742 |
+
{
|
3743 |
+
"epoch": 2.6,
|
3744 |
+
"eval_loss": 0.6390016078948975,
|
3745 |
+
"eval_runtime": 49.6306,
|
3746 |
+
"eval_samples_per_second": 40.298,
|
3747 |
+
"eval_steps_per_second": 2.519,
|
3748 |
+
"step": 11000
|
3749 |
+
},
|
3750 |
+
{
|
3751 |
+
"epoch": 2.61,
|
3752 |
+
"learning_rate": 3.984114376489277e-05,
|
3753 |
+
"loss": 0.6405,
|
3754 |
+
"step": 11020
|
3755 |
+
},
|
3756 |
+
{
|
3757 |
+
"epoch": 2.61,
|
3758 |
+
"learning_rate": 3.9364575059571086e-05,
|
3759 |
+
"loss": 0.6429,
|
3760 |
+
"step": 11040
|
3761 |
+
},
|
3762 |
+
{
|
3763 |
+
"epoch": 2.61,
|
3764 |
+
"learning_rate": 3.88880063542494e-05,
|
3765 |
+
"loss": 0.6403,
|
3766 |
+
"step": 11060
|
3767 |
+
},
|
3768 |
+
{
|
3769 |
+
"epoch": 2.62,
|
3770 |
+
"learning_rate": 3.841143764892772e-05,
|
3771 |
+
"loss": 0.6338,
|
3772 |
+
"step": 11080
|
3773 |
+
},
|
3774 |
+
{
|
3775 |
+
"epoch": 2.62,
|
3776 |
+
"learning_rate": 3.7934868943606034e-05,
|
3777 |
+
"loss": 0.6417,
|
3778 |
+
"step": 11100
|
3779 |
+
},
|
3780 |
+
{
|
3781 |
+
"epoch": 2.63,
|
3782 |
+
"learning_rate": 3.7458300238284354e-05,
|
3783 |
+
"loss": 0.6463,
|
3784 |
+
"step": 11120
|
3785 |
+
},
|
3786 |
+
{
|
3787 |
+
"epoch": 2.63,
|
3788 |
+
"learning_rate": 3.698173153296267e-05,
|
3789 |
+
"loss": 0.6498,
|
3790 |
+
"step": 11140
|
3791 |
+
},
|
3792 |
+
{
|
3793 |
+
"epoch": 2.64,
|
3794 |
+
"learning_rate": 3.650516282764098e-05,
|
3795 |
+
"loss": 0.6415,
|
3796 |
+
"step": 11160
|
3797 |
+
},
|
3798 |
+
{
|
3799 |
+
"epoch": 2.64,
|
3800 |
+
"learning_rate": 3.6028594122319296e-05,
|
3801 |
+
"loss": 0.645,
|
3802 |
+
"step": 11180
|
3803 |
+
},
|
3804 |
+
{
|
3805 |
+
"epoch": 2.65,
|
3806 |
+
"learning_rate": 3.5552025416997616e-05,
|
3807 |
+
"loss": 0.6467,
|
3808 |
+
"step": 11200
|
3809 |
+
},
|
3810 |
+
{
|
3811 |
+
"epoch": 2.65,
|
3812 |
+
"eval_loss": 0.6387213468551636,
|
3813 |
+
"eval_runtime": 49.1775,
|
3814 |
+
"eval_samples_per_second": 40.669,
|
3815 |
+
"eval_steps_per_second": 2.542,
|
3816 |
+
"step": 11200
|
3817 |
+
},
|
3818 |
+
{
|
3819 |
+
"epoch": 2.65,
|
3820 |
+
"learning_rate": 3.507545671167593e-05,
|
3821 |
+
"loss": 0.6515,
|
3822 |
+
"step": 11220
|
3823 |
+
},
|
3824 |
+
{
|
3825 |
+
"epoch": 2.66,
|
3826 |
+
"learning_rate": 3.4598888006354244e-05,
|
3827 |
+
"loss": 0.65,
|
3828 |
+
"step": 11240
|
3829 |
+
},
|
3830 |
+
{
|
3831 |
+
"epoch": 2.66,
|
3832 |
+
"learning_rate": 3.4122319301032564e-05,
|
3833 |
+
"loss": 0.6512,
|
3834 |
+
"step": 11260
|
3835 |
+
},
|
3836 |
+
{
|
3837 |
+
"epoch": 2.67,
|
3838 |
+
"learning_rate": 3.364575059571088e-05,
|
3839 |
+
"loss": 0.6443,
|
3840 |
+
"step": 11280
|
3841 |
+
},
|
3842 |
+
{
|
3843 |
+
"epoch": 2.67,
|
3844 |
+
"learning_rate": 3.316918189038919e-05,
|
3845 |
+
"loss": 0.6483,
|
3846 |
+
"step": 11300
|
3847 |
+
},
|
3848 |
+
{
|
3849 |
+
"epoch": 2.68,
|
3850 |
+
"learning_rate": 3.269261318506751e-05,
|
3851 |
+
"loss": 0.6455,
|
3852 |
+
"step": 11320
|
3853 |
+
},
|
3854 |
+
{
|
3855 |
+
"epoch": 2.68,
|
3856 |
+
"learning_rate": 3.2216044479745826e-05,
|
3857 |
+
"loss": 0.6461,
|
3858 |
+
"step": 11340
|
3859 |
+
},
|
3860 |
+
{
|
3861 |
+
"epoch": 2.69,
|
3862 |
+
"learning_rate": 3.173947577442414e-05,
|
3863 |
+
"loss": 0.6505,
|
3864 |
+
"step": 11360
|
3865 |
+
},
|
3866 |
+
{
|
3867 |
+
"epoch": 2.69,
|
3868 |
+
"learning_rate": 3.126290706910246e-05,
|
3869 |
+
"loss": 0.6517,
|
3870 |
+
"step": 11380
|
3871 |
+
},
|
3872 |
+
{
|
3873 |
+
"epoch": 2.7,
|
3874 |
+
"learning_rate": 3.0786338363780774e-05,
|
3875 |
+
"loss": 0.6406,
|
3876 |
+
"step": 11400
|
3877 |
+
},
|
3878 |
+
{
|
3879 |
+
"epoch": 2.7,
|
3880 |
+
"eval_loss": 0.6380326151847839,
|
3881 |
+
"eval_runtime": 49.4129,
|
3882 |
+
"eval_samples_per_second": 40.475,
|
3883 |
+
"eval_steps_per_second": 2.53,
|
3884 |
+
"step": 11400
|
3885 |
+
},
|
3886 |
+
{
|
3887 |
+
"epoch": 2.7,
|
3888 |
+
"learning_rate": 3.030976965845909e-05,
|
3889 |
+
"loss": 0.647,
|
3890 |
+
"step": 11420
|
3891 |
+
},
|
3892 |
+
{
|
3893 |
+
"epoch": 2.7,
|
3894 |
+
"learning_rate": 2.9833200953137408e-05,
|
3895 |
+
"loss": 0.6495,
|
3896 |
+
"step": 11440
|
3897 |
+
},
|
3898 |
+
{
|
3899 |
+
"epoch": 2.71,
|
3900 |
+
"learning_rate": 2.9356632247815725e-05,
|
3901 |
+
"loss": 0.6448,
|
3902 |
+
"step": 11460
|
3903 |
+
},
|
3904 |
+
{
|
3905 |
+
"epoch": 2.71,
|
3906 |
+
"learning_rate": 2.888006354249404e-05,
|
3907 |
+
"loss": 0.6447,
|
3908 |
+
"step": 11480
|
3909 |
+
},
|
3910 |
+
{
|
3911 |
+
"epoch": 2.72,
|
3912 |
+
"learning_rate": 2.840349483717236e-05,
|
3913 |
+
"loss": 0.6527,
|
3914 |
+
"step": 11500
|
3915 |
+
},
|
3916 |
+
{
|
3917 |
+
"epoch": 2.72,
|
3918 |
+
"learning_rate": 2.7926926131850673e-05,
|
3919 |
+
"loss": 0.6406,
|
3920 |
+
"step": 11520
|
3921 |
+
},
|
3922 |
+
{
|
3923 |
+
"epoch": 2.73,
|
3924 |
+
"learning_rate": 2.7450357426528987e-05,
|
3925 |
+
"loss": 0.6443,
|
3926 |
+
"step": 11540
|
3927 |
+
},
|
3928 |
+
{
|
3929 |
+
"epoch": 2.73,
|
3930 |
+
"learning_rate": 2.6973788721207307e-05,
|
3931 |
+
"loss": 0.6351,
|
3932 |
+
"step": 11560
|
3933 |
+
},
|
3934 |
+
{
|
3935 |
+
"epoch": 2.74,
|
3936 |
+
"learning_rate": 2.649722001588562e-05,
|
3937 |
+
"loss": 0.6417,
|
3938 |
+
"step": 11580
|
3939 |
+
},
|
3940 |
+
{
|
3941 |
+
"epoch": 2.74,
|
3942 |
+
"learning_rate": 2.6020651310563938e-05,
|
3943 |
+
"loss": 0.6356,
|
3944 |
+
"step": 11600
|
3945 |
+
},
|
3946 |
+
{
|
3947 |
+
"epoch": 2.74,
|
3948 |
+
"eval_loss": 0.6381237506866455,
|
3949 |
+
"eval_runtime": 49.5534,
|
3950 |
+
"eval_samples_per_second": 40.36,
|
3951 |
+
"eval_steps_per_second": 2.523,
|
3952 |
+
"step": 11600
|
3953 |
+
},
|
3954 |
+
{
|
3955 |
+
"epoch": 2.75,
|
3956 |
+
"learning_rate": 2.5544082605242255e-05,
|
3957 |
+
"loss": 0.6412,
|
3958 |
+
"step": 11620
|
3959 |
+
},
|
3960 |
+
{
|
3961 |
+
"epoch": 2.75,
|
3962 |
+
"learning_rate": 2.506751389992057e-05,
|
3963 |
+
"loss": 0.6418,
|
3964 |
+
"step": 11640
|
3965 |
+
},
|
3966 |
+
{
|
3967 |
+
"epoch": 2.76,
|
3968 |
+
"learning_rate": 2.4590945194598886e-05,
|
3969 |
+
"loss": 0.6426,
|
3970 |
+
"step": 11660
|
3971 |
+
},
|
3972 |
+
{
|
3973 |
+
"epoch": 2.76,
|
3974 |
+
"learning_rate": 2.4114376489277203e-05,
|
3975 |
+
"loss": 0.6461,
|
3976 |
+
"step": 11680
|
3977 |
+
},
|
3978 |
+
{
|
3979 |
+
"epoch": 2.77,
|
3980 |
+
"learning_rate": 2.363780778395552e-05,
|
3981 |
+
"loss": 0.6475,
|
3982 |
+
"step": 11700
|
3983 |
+
},
|
3984 |
+
{
|
3985 |
+
"epoch": 2.77,
|
3986 |
+
"learning_rate": 2.3161239078633834e-05,
|
3987 |
+
"loss": 0.6431,
|
3988 |
+
"step": 11720
|
3989 |
+
},
|
3990 |
+
{
|
3991 |
+
"epoch": 2.78,
|
3992 |
+
"learning_rate": 2.2684670373312148e-05,
|
3993 |
+
"loss": 0.6416,
|
3994 |
+
"step": 11740
|
3995 |
+
},
|
3996 |
+
{
|
3997 |
+
"epoch": 2.78,
|
3998 |
+
"learning_rate": 2.2208101667990468e-05,
|
3999 |
+
"loss": 0.6495,
|
4000 |
+
"step": 11760
|
4001 |
+
},
|
4002 |
+
{
|
4003 |
+
"epoch": 2.78,
|
4004 |
+
"learning_rate": 2.1731532962668782e-05,
|
4005 |
+
"loss": 0.6404,
|
4006 |
+
"step": 11780
|
4007 |
+
},
|
4008 |
+
{
|
4009 |
+
"epoch": 2.79,
|
4010 |
+
"learning_rate": 2.1254964257347096e-05,
|
4011 |
+
"loss": 0.6434,
|
4012 |
+
"step": 11800
|
4013 |
+
},
|
4014 |
+
{
|
4015 |
+
"epoch": 2.79,
|
4016 |
+
"eval_loss": 0.6377163529396057,
|
4017 |
+
"eval_runtime": 49.328,
|
4018 |
+
"eval_samples_per_second": 40.545,
|
4019 |
+
"eval_steps_per_second": 2.534,
|
4020 |
+
"step": 11800
|
4021 |
+
},
|
4022 |
+
{
|
4023 |
+
"epoch": 2.79,
|
4024 |
+
"learning_rate": 2.0778395552025416e-05,
|
4025 |
+
"loss": 0.6437,
|
4026 |
+
"step": 11820
|
4027 |
+
},
|
4028 |
+
{
|
4029 |
+
"epoch": 2.8,
|
4030 |
+
"learning_rate": 2.030182684670373e-05,
|
4031 |
+
"loss": 0.6393,
|
4032 |
+
"step": 11840
|
4033 |
+
},
|
4034 |
+
{
|
4035 |
+
"epoch": 2.8,
|
4036 |
+
"learning_rate": 1.9825258141382047e-05,
|
4037 |
+
"loss": 0.6412,
|
4038 |
+
"step": 11860
|
4039 |
+
},
|
4040 |
+
{
|
4041 |
+
"epoch": 2.81,
|
4042 |
+
"learning_rate": 1.9348689436060364e-05,
|
4043 |
+
"loss": 0.6494,
|
4044 |
+
"step": 11880
|
4045 |
+
},
|
4046 |
+
{
|
4047 |
+
"epoch": 2.81,
|
4048 |
+
"learning_rate": 1.887212073073868e-05,
|
4049 |
+
"loss": 0.6481,
|
4050 |
+
"step": 11900
|
4051 |
+
},
|
4052 |
+
{
|
4053 |
+
"epoch": 2.82,
|
4054 |
+
"learning_rate": 1.8395552025416998e-05,
|
4055 |
+
"loss": 0.6407,
|
4056 |
+
"step": 11920
|
4057 |
+
},
|
4058 |
+
{
|
4059 |
+
"epoch": 2.82,
|
4060 |
+
"learning_rate": 1.7918983320095312e-05,
|
4061 |
+
"loss": 0.6422,
|
4062 |
+
"step": 11940
|
4063 |
+
},
|
4064 |
+
{
|
4065 |
+
"epoch": 2.83,
|
4066 |
+
"learning_rate": 1.744241461477363e-05,
|
4067 |
+
"loss": 0.6487,
|
4068 |
+
"step": 11960
|
4069 |
+
},
|
4070 |
+
{
|
4071 |
+
"epoch": 2.83,
|
4072 |
+
"learning_rate": 1.6965845909451946e-05,
|
4073 |
+
"loss": 0.6478,
|
4074 |
+
"step": 11980
|
4075 |
+
},
|
4076 |
+
{
|
4077 |
+
"epoch": 2.84,
|
4078 |
+
"learning_rate": 1.648927720413026e-05,
|
4079 |
+
"loss": 0.6451,
|
4080 |
+
"step": 12000
|
4081 |
+
},
|
4082 |
+
{
|
4083 |
+
"epoch": 2.84,
|
4084 |
+
"eval_loss": 0.6374698281288147,
|
4085 |
+
"eval_runtime": 49.9107,
|
4086 |
+
"eval_samples_per_second": 40.072,
|
4087 |
+
"eval_steps_per_second": 2.504,
|
4088 |
+
"step": 12000
|
4089 |
+
},
|
4090 |
+
{
|
4091 |
+
"epoch": 2.84,
|
4092 |
+
"learning_rate": 1.6012708498808577e-05,
|
4093 |
+
"loss": 0.6454,
|
4094 |
+
"step": 12020
|
4095 |
+
},
|
4096 |
+
{
|
4097 |
+
"epoch": 2.85,
|
4098 |
+
"learning_rate": 1.5536139793486894e-05,
|
4099 |
+
"loss": 0.6399,
|
4100 |
+
"step": 12040
|
4101 |
+
},
|
4102 |
+
{
|
4103 |
+
"epoch": 2.85,
|
4104 |
+
"learning_rate": 1.5059571088165208e-05,
|
4105 |
+
"loss": 0.6479,
|
4106 |
+
"step": 12060
|
4107 |
+
},
|
4108 |
+
{
|
4109 |
+
"epoch": 2.86,
|
4110 |
+
"learning_rate": 1.4583002382843525e-05,
|
4111 |
+
"loss": 0.6412,
|
4112 |
+
"step": 12080
|
4113 |
+
},
|
4114 |
+
{
|
4115 |
+
"epoch": 2.86,
|
4116 |
+
"learning_rate": 1.4106433677521842e-05,
|
4117 |
+
"loss": 0.65,
|
4118 |
+
"step": 12100
|
4119 |
+
},
|
4120 |
+
{
|
4121 |
+
"epoch": 2.87,
|
4122 |
+
"learning_rate": 1.3629864972200157e-05,
|
4123 |
+
"loss": 0.6461,
|
4124 |
+
"step": 12120
|
4125 |
+
},
|
4126 |
+
{
|
4127 |
+
"epoch": 2.87,
|
4128 |
+
"learning_rate": 1.3153296266878475e-05,
|
4129 |
+
"loss": 0.6434,
|
4130 |
+
"step": 12140
|
4131 |
+
},
|
4132 |
+
{
|
4133 |
+
"epoch": 2.87,
|
4134 |
+
"learning_rate": 1.2676727561556788e-05,
|
4135 |
+
"loss": 0.6463,
|
4136 |
+
"step": 12160
|
4137 |
+
},
|
4138 |
+
{
|
4139 |
+
"epoch": 2.88,
|
4140 |
+
"learning_rate": 1.2200158856235105e-05,
|
4141 |
+
"loss": 0.6399,
|
4142 |
+
"step": 12180
|
4143 |
+
},
|
4144 |
+
{
|
4145 |
+
"epoch": 2.88,
|
4146 |
+
"learning_rate": 1.1723590150913422e-05,
|
4147 |
+
"loss": 0.6446,
|
4148 |
+
"step": 12200
|
4149 |
+
},
|
4150 |
+
{
|
4151 |
+
"epoch": 2.88,
|
4152 |
+
"eval_loss": 0.6372544765472412,
|
4153 |
+
"eval_runtime": 49.6265,
|
4154 |
+
"eval_samples_per_second": 40.301,
|
4155 |
+
"eval_steps_per_second": 2.519,
|
4156 |
+
"step": 12200
|
4157 |
+
}
|
4158 |
+
],
|
4159 |
+
"max_steps": 12690,
|
4160 |
+
"num_train_epochs": 3,
|
4161 |
+
"total_flos": 1.5855992729583485e+19,
|
4162 |
+
"trial_name": null,
|
4163 |
+
"trial_params": null
|
4164 |
+
}
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a070370e87c048b60fc888b8736a0166eb94eeb3a75f5f78918edab715d0fb1c
|
3 |
+
size 3579
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a44d25fe2c7be3065324779281d2f127b5a642d67f1e6454f19700b42493bdd7
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f507c244cdac0a2a8d4da2999644d1b91a384aa62f543cdb6df0f2076c7edb1f
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab02d3b0b43bf78678642d9cd5f53765f64014c5978ba11838067362d9bc2ad
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64dd573126e6ce344168cb0149b372652148f70e76d3a1dc6ae6ddf416540e48
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ebe8baa4484dffe2c79d27911cedebee271659822ff874c04a10526e4d03d6f
|
3 |
+
size 557
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54bc440119a51d3d80c80b0036e812daff5b98ed0f83403347a0707e66b60f65
|
3 |
+
size 627
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/trainer_state.json
ADDED
@@ -0,0 +1,4232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6368712186813354,
|
3 |
+
"best_model_checkpoint": "lora-alpaca-cn/checkpoint-12400",
|
4 |
+
"epoch": 2.9314420803782504,
|
5 |
+
"global_step": 12400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 5.9999999999999995e-05,
|
13 |
+
"loss": 1.7735,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 0.00011999999999999999,
|
19 |
+
"loss": 1.1358,
|
20 |
+
"step": 40
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 0.00017999999999999998,
|
25 |
+
"loss": 0.9749,
|
26 |
+
"step": 60
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 0.00023999999999999998,
|
31 |
+
"loss": 0.9316,
|
32 |
+
"step": 80
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 0.9072,
|
38 |
+
"step": 100
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 0.0002995234312946783,
|
43 |
+
"loss": 0.8963,
|
44 |
+
"step": 120
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"learning_rate": 0.0002990468625893566,
|
49 |
+
"loss": 0.8853,
|
50 |
+
"step": 140
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.04,
|
54 |
+
"learning_rate": 0.0002985702938840349,
|
55 |
+
"loss": 0.8709,
|
56 |
+
"step": 160
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04,
|
60 |
+
"learning_rate": 0.00029809372517871323,
|
61 |
+
"loss": 0.8555,
|
62 |
+
"step": 180
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.05,
|
66 |
+
"learning_rate": 0.00029761715647339156,
|
67 |
+
"loss": 0.8584,
|
68 |
+
"step": 200
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.05,
|
72 |
+
"eval_loss": 0.8360834717750549,
|
73 |
+
"eval_runtime": 49.29,
|
74 |
+
"eval_samples_per_second": 40.576,
|
75 |
+
"eval_steps_per_second": 2.536,
|
76 |
+
"step": 200
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.05,
|
80 |
+
"learning_rate": 0.0002971405877680699,
|
81 |
+
"loss": 0.859,
|
82 |
+
"step": 220
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.06,
|
86 |
+
"learning_rate": 0.00029666401906274816,
|
87 |
+
"loss": 0.8511,
|
88 |
+
"step": 240
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.06,
|
92 |
+
"learning_rate": 0.0002961874503574265,
|
93 |
+
"loss": 0.8401,
|
94 |
+
"step": 260
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.07,
|
98 |
+
"learning_rate": 0.0002957108816521048,
|
99 |
+
"loss": 0.8357,
|
100 |
+
"step": 280
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07,
|
104 |
+
"learning_rate": 0.00029523431294678314,
|
105 |
+
"loss": 0.8413,
|
106 |
+
"step": 300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.08,
|
110 |
+
"learning_rate": 0.00029475774424146147,
|
111 |
+
"loss": 0.8283,
|
112 |
+
"step": 320
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.08,
|
116 |
+
"learning_rate": 0.0002942811755361398,
|
117 |
+
"loss": 0.8202,
|
118 |
+
"step": 340
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.09,
|
122 |
+
"learning_rate": 0.00029380460683081807,
|
123 |
+
"loss": 0.8222,
|
124 |
+
"step": 360
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.09,
|
128 |
+
"learning_rate": 0.0002933280381254964,
|
129 |
+
"loss": 0.8178,
|
130 |
+
"step": 380
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.09,
|
134 |
+
"learning_rate": 0.0002928514694201747,
|
135 |
+
"loss": 0.8177,
|
136 |
+
"step": 400
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.09,
|
140 |
+
"eval_loss": 0.7966175079345703,
|
141 |
+
"eval_runtime": 49.1752,
|
142 |
+
"eval_samples_per_second": 40.671,
|
143 |
+
"eval_steps_per_second": 2.542,
|
144 |
+
"step": 400
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.1,
|
148 |
+
"learning_rate": 0.00029237490071485305,
|
149 |
+
"loss": 0.8057,
|
150 |
+
"step": 420
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.1,
|
154 |
+
"learning_rate": 0.0002918983320095314,
|
155 |
+
"loss": 0.811,
|
156 |
+
"step": 440
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.11,
|
160 |
+
"learning_rate": 0.00029142176330420965,
|
161 |
+
"loss": 0.8056,
|
162 |
+
"step": 460
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.11,
|
166 |
+
"learning_rate": 0.000290945194598888,
|
167 |
+
"loss": 0.7993,
|
168 |
+
"step": 480
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.12,
|
172 |
+
"learning_rate": 0.0002904686258935663,
|
173 |
+
"loss": 0.7982,
|
174 |
+
"step": 500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.12,
|
178 |
+
"learning_rate": 0.0002899920571882446,
|
179 |
+
"loss": 0.8023,
|
180 |
+
"step": 520
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.13,
|
184 |
+
"learning_rate": 0.00028951548848292296,
|
185 |
+
"loss": 0.7968,
|
186 |
+
"step": 540
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.13,
|
190 |
+
"learning_rate": 0.00028903891977760123,
|
191 |
+
"loss": 0.8029,
|
192 |
+
"step": 560
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.14,
|
196 |
+
"learning_rate": 0.00028856235107227956,
|
197 |
+
"loss": 0.7892,
|
198 |
+
"step": 580
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.14,
|
202 |
+
"learning_rate": 0.0002880857823669579,
|
203 |
+
"loss": 0.7946,
|
204 |
+
"step": 600
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.14,
|
208 |
+
"eval_loss": 0.7735009789466858,
|
209 |
+
"eval_runtime": 49.3305,
|
210 |
+
"eval_samples_per_second": 40.543,
|
211 |
+
"eval_steps_per_second": 2.534,
|
212 |
+
"step": 600
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15,
|
216 |
+
"learning_rate": 0.00028760921366163616,
|
217 |
+
"loss": 0.782,
|
218 |
+
"step": 620
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.15,
|
222 |
+
"learning_rate": 0.0002871326449563145,
|
223 |
+
"loss": 0.7799,
|
224 |
+
"step": 640
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.16,
|
228 |
+
"learning_rate": 0.0002866560762509928,
|
229 |
+
"loss": 0.7782,
|
230 |
+
"step": 660
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.16,
|
234 |
+
"learning_rate": 0.00028617950754567114,
|
235 |
+
"loss": 0.7785,
|
236 |
+
"step": 680
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.17,
|
240 |
+
"learning_rate": 0.00028570293884034947,
|
241 |
+
"loss": 0.785,
|
242 |
+
"step": 700
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.17,
|
246 |
+
"learning_rate": 0.0002852263701350278,
|
247 |
+
"loss": 0.7754,
|
248 |
+
"step": 720
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.17,
|
252 |
+
"learning_rate": 0.00028474980142970607,
|
253 |
+
"loss": 0.7804,
|
254 |
+
"step": 740
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18,
|
258 |
+
"learning_rate": 0.0002842732327243844,
|
259 |
+
"loss": 0.7696,
|
260 |
+
"step": 760
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.18,
|
264 |
+
"learning_rate": 0.0002837966640190627,
|
265 |
+
"loss": 0.7692,
|
266 |
+
"step": 780
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.19,
|
270 |
+
"learning_rate": 0.00028332009531374105,
|
271 |
+
"loss": 0.7752,
|
272 |
+
"step": 800
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.19,
|
276 |
+
"eval_loss": 0.7564254403114319,
|
277 |
+
"eval_runtime": 49.106,
|
278 |
+
"eval_samples_per_second": 40.728,
|
279 |
+
"eval_steps_per_second": 2.546,
|
280 |
+
"step": 800
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.19,
|
284 |
+
"learning_rate": 0.0002828435266084194,
|
285 |
+
"loss": 0.7698,
|
286 |
+
"step": 820
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.2,
|
290 |
+
"learning_rate": 0.00028236695790309765,
|
291 |
+
"loss": 0.7699,
|
292 |
+
"step": 840
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.2,
|
296 |
+
"learning_rate": 0.000281890389197776,
|
297 |
+
"loss": 0.7718,
|
298 |
+
"step": 860
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.21,
|
302 |
+
"learning_rate": 0.0002814138204924543,
|
303 |
+
"loss": 0.7644,
|
304 |
+
"step": 880
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.21,
|
308 |
+
"learning_rate": 0.00028093725178713263,
|
309 |
+
"loss": 0.7659,
|
310 |
+
"step": 900
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.22,
|
314 |
+
"learning_rate": 0.00028046068308181096,
|
315 |
+
"loss": 0.7641,
|
316 |
+
"step": 920
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.22,
|
320 |
+
"learning_rate": 0.00027998411437648923,
|
321 |
+
"loss": 0.7535,
|
322 |
+
"step": 940
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.23,
|
326 |
+
"learning_rate": 0.00027950754567116756,
|
327 |
+
"loss": 0.7672,
|
328 |
+
"step": 960
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.23,
|
332 |
+
"learning_rate": 0.0002790309769658459,
|
333 |
+
"loss": 0.7563,
|
334 |
+
"step": 980
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.24,
|
338 |
+
"learning_rate": 0.0002785544082605242,
|
339 |
+
"loss": 0.752,
|
340 |
+
"step": 1000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.24,
|
344 |
+
"eval_loss": 0.7433652281761169,
|
345 |
+
"eval_runtime": 48.9945,
|
346 |
+
"eval_samples_per_second": 40.821,
|
347 |
+
"eval_steps_per_second": 2.551,
|
348 |
+
"step": 1000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.24,
|
352 |
+
"learning_rate": 0.00027807783955520254,
|
353 |
+
"loss": 0.755,
|
354 |
+
"step": 1020
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.25,
|
358 |
+
"learning_rate": 0.00027760127084988087,
|
359 |
+
"loss": 0.7563,
|
360 |
+
"step": 1040
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.25,
|
364 |
+
"learning_rate": 0.00027712470214455914,
|
365 |
+
"loss": 0.7475,
|
366 |
+
"step": 1060
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.26,
|
370 |
+
"learning_rate": 0.00027664813343923747,
|
371 |
+
"loss": 0.7599,
|
372 |
+
"step": 1080
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 0.26,
|
376 |
+
"learning_rate": 0.0002761715647339158,
|
377 |
+
"loss": 0.7533,
|
378 |
+
"step": 1100
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.26,
|
382 |
+
"learning_rate": 0.00027569499602859407,
|
383 |
+
"loss": 0.7488,
|
384 |
+
"step": 1120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.27,
|
388 |
+
"learning_rate": 0.00027521842732327245,
|
389 |
+
"loss": 0.753,
|
390 |
+
"step": 1140
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.27,
|
394 |
+
"learning_rate": 0.0002747418586179507,
|
395 |
+
"loss": 0.7435,
|
396 |
+
"step": 1160
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.28,
|
400 |
+
"learning_rate": 0.00027426528991262905,
|
401 |
+
"loss": 0.7457,
|
402 |
+
"step": 1180
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.28,
|
406 |
+
"learning_rate": 0.0002737887212073074,
|
407 |
+
"loss": 0.742,
|
408 |
+
"step": 1200
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.28,
|
412 |
+
"eval_loss": 0.7321739792823792,
|
413 |
+
"eval_runtime": 48.8876,
|
414 |
+
"eval_samples_per_second": 40.91,
|
415 |
+
"eval_steps_per_second": 2.557,
|
416 |
+
"step": 1200
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.29,
|
420 |
+
"learning_rate": 0.00027331215250198565,
|
421 |
+
"loss": 0.7474,
|
422 |
+
"step": 1220
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.29,
|
426 |
+
"learning_rate": 0.000272835583796664,
|
427 |
+
"loss": 0.7456,
|
428 |
+
"step": 1240
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.3,
|
432 |
+
"learning_rate": 0.0002723590150913423,
|
433 |
+
"loss": 0.7406,
|
434 |
+
"step": 1260
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.3,
|
438 |
+
"learning_rate": 0.00027188244638602063,
|
439 |
+
"loss": 0.7448,
|
440 |
+
"step": 1280
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.31,
|
444 |
+
"learning_rate": 0.00027140587768069896,
|
445 |
+
"loss": 0.7445,
|
446 |
+
"step": 1300
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.31,
|
450 |
+
"learning_rate": 0.00027092930897537723,
|
451 |
+
"loss": 0.7349,
|
452 |
+
"step": 1320
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.32,
|
456 |
+
"learning_rate": 0.00027045274027005556,
|
457 |
+
"loss": 0.7395,
|
458 |
+
"step": 1340
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.32,
|
462 |
+
"learning_rate": 0.0002699761715647339,
|
463 |
+
"loss": 0.7382,
|
464 |
+
"step": 1360
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.33,
|
468 |
+
"learning_rate": 0.0002694996028594122,
|
469 |
+
"loss": 0.7357,
|
470 |
+
"step": 1380
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.33,
|
474 |
+
"learning_rate": 0.00026902303415409054,
|
475 |
+
"loss": 0.7409,
|
476 |
+
"step": 1400
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.33,
|
480 |
+
"eval_loss": 0.7235888242721558,
|
481 |
+
"eval_runtime": 49.2145,
|
482 |
+
"eval_samples_per_second": 40.638,
|
483 |
+
"eval_steps_per_second": 2.54,
|
484 |
+
"step": 1400
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.34,
|
488 |
+
"learning_rate": 0.00026854646544876887,
|
489 |
+
"loss": 0.7376,
|
490 |
+
"step": 1420
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 0.34,
|
494 |
+
"learning_rate": 0.00026806989674344714,
|
495 |
+
"loss": 0.7298,
|
496 |
+
"step": 1440
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.35,
|
500 |
+
"learning_rate": 0.00026759332803812547,
|
501 |
+
"loss": 0.7379,
|
502 |
+
"step": 1460
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.35,
|
506 |
+
"learning_rate": 0.0002671167593328038,
|
507 |
+
"loss": 0.7354,
|
508 |
+
"step": 1480
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.35,
|
512 |
+
"learning_rate": 0.0002666401906274821,
|
513 |
+
"loss": 0.7341,
|
514 |
+
"step": 1500
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.36,
|
518 |
+
"learning_rate": 0.00026616362192216045,
|
519 |
+
"loss": 0.7352,
|
520 |
+
"step": 1520
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.36,
|
524 |
+
"learning_rate": 0.0002656870532168387,
|
525 |
+
"loss": 0.7321,
|
526 |
+
"step": 1540
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.37,
|
530 |
+
"learning_rate": 0.00026521048451151705,
|
531 |
+
"loss": 0.7285,
|
532 |
+
"step": 1560
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.37,
|
536 |
+
"learning_rate": 0.0002647339158061954,
|
537 |
+
"loss": 0.73,
|
538 |
+
"step": 1580
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.38,
|
542 |
+
"learning_rate": 0.00026425734710087365,
|
543 |
+
"loss": 0.7304,
|
544 |
+
"step": 1600
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.38,
|
548 |
+
"eval_loss": 0.716058611869812,
|
549 |
+
"eval_runtime": 48.9201,
|
550 |
+
"eval_samples_per_second": 40.883,
|
551 |
+
"eval_steps_per_second": 2.555,
|
552 |
+
"step": 1600
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.38,
|
556 |
+
"learning_rate": 0.00026378077839555203,
|
557 |
+
"loss": 0.7314,
|
558 |
+
"step": 1620
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.39,
|
562 |
+
"learning_rate": 0.0002633042096902303,
|
563 |
+
"loss": 0.7315,
|
564 |
+
"step": 1640
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.39,
|
568 |
+
"learning_rate": 0.00026282764098490863,
|
569 |
+
"loss": 0.7239,
|
570 |
+
"step": 1660
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.4,
|
574 |
+
"learning_rate": 0.00026235107227958696,
|
575 |
+
"loss": 0.73,
|
576 |
+
"step": 1680
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.4,
|
580 |
+
"learning_rate": 0.00026187450357426523,
|
581 |
+
"loss": 0.7243,
|
582 |
+
"step": 1700
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.41,
|
586 |
+
"learning_rate": 0.00026139793486894356,
|
587 |
+
"loss": 0.7199,
|
588 |
+
"step": 1720
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 0.41,
|
592 |
+
"learning_rate": 0.0002609213661636219,
|
593 |
+
"loss": 0.7216,
|
594 |
+
"step": 1740
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.42,
|
598 |
+
"learning_rate": 0.0002604447974583002,
|
599 |
+
"loss": 0.7358,
|
600 |
+
"step": 1760
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.42,
|
604 |
+
"learning_rate": 0.00025996822875297854,
|
605 |
+
"loss": 0.7313,
|
606 |
+
"step": 1780
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.43,
|
610 |
+
"learning_rate": 0.00025949166004765687,
|
611 |
+
"loss": 0.7236,
|
612 |
+
"step": 1800
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.43,
|
616 |
+
"eval_loss": 0.7097632884979248,
|
617 |
+
"eval_runtime": 49.4908,
|
618 |
+
"eval_samples_per_second": 40.412,
|
619 |
+
"eval_steps_per_second": 2.526,
|
620 |
+
"step": 1800
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.43,
|
624 |
+
"learning_rate": 0.00025901509134233514,
|
625 |
+
"loss": 0.7282,
|
626 |
+
"step": 1820
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.43,
|
630 |
+
"learning_rate": 0.00025853852263701347,
|
631 |
+
"loss": 0.7187,
|
632 |
+
"step": 1840
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.44,
|
636 |
+
"learning_rate": 0.0002580619539316918,
|
637 |
+
"loss": 0.7303,
|
638 |
+
"step": 1860
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.44,
|
642 |
+
"learning_rate": 0.0002575853852263701,
|
643 |
+
"loss": 0.724,
|
644 |
+
"step": 1880
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.45,
|
648 |
+
"learning_rate": 0.00025710881652104845,
|
649 |
+
"loss": 0.7248,
|
650 |
+
"step": 1900
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.45,
|
654 |
+
"learning_rate": 0.0002566322478157267,
|
655 |
+
"loss": 0.7195,
|
656 |
+
"step": 1920
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.46,
|
660 |
+
"learning_rate": 0.00025615567911040505,
|
661 |
+
"loss": 0.7269,
|
662 |
+
"step": 1940
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.46,
|
666 |
+
"learning_rate": 0.0002556791104050834,
|
667 |
+
"loss": 0.7209,
|
668 |
+
"step": 1960
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.47,
|
672 |
+
"learning_rate": 0.0002552025416997617,
|
673 |
+
"loss": 0.7282,
|
674 |
+
"step": 1980
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.47,
|
678 |
+
"learning_rate": 0.00025472597299444003,
|
679 |
+
"loss": 0.7195,
|
680 |
+
"step": 2000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.47,
|
684 |
+
"eval_loss": 0.7037709355354309,
|
685 |
+
"eval_runtime": 49.7167,
|
686 |
+
"eval_samples_per_second": 40.228,
|
687 |
+
"eval_steps_per_second": 2.514,
|
688 |
+
"step": 2000
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.48,
|
692 |
+
"learning_rate": 0.0002542494042891183,
|
693 |
+
"loss": 0.7229,
|
694 |
+
"step": 2020
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 0.48,
|
698 |
+
"learning_rate": 0.00025377283558379664,
|
699 |
+
"loss": 0.718,
|
700 |
+
"step": 2040
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.49,
|
704 |
+
"learning_rate": 0.00025329626687847496,
|
705 |
+
"loss": 0.7223,
|
706 |
+
"step": 2060
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.49,
|
710 |
+
"learning_rate": 0.00025281969817315324,
|
711 |
+
"loss": 0.7209,
|
712 |
+
"step": 2080
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.5,
|
716 |
+
"learning_rate": 0.0002523431294678316,
|
717 |
+
"loss": 0.7151,
|
718 |
+
"step": 2100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.5,
|
722 |
+
"learning_rate": 0.0002518665607625099,
|
723 |
+
"loss": 0.7141,
|
724 |
+
"step": 2120
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.51,
|
728 |
+
"learning_rate": 0.0002513899920571882,
|
729 |
+
"loss": 0.7084,
|
730 |
+
"step": 2140
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.51,
|
734 |
+
"learning_rate": 0.00025091342335186654,
|
735 |
+
"loss": 0.7075,
|
736 |
+
"step": 2160
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.52,
|
740 |
+
"learning_rate": 0.00025043685464654487,
|
741 |
+
"loss": 0.7133,
|
742 |
+
"step": 2180
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 0.52,
|
746 |
+
"learning_rate": 0.00024996028594122314,
|
747 |
+
"loss": 0.7092,
|
748 |
+
"step": 2200
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.52,
|
752 |
+
"eval_loss": 0.6989386677742004,
|
753 |
+
"eval_runtime": 49.2344,
|
754 |
+
"eval_samples_per_second": 40.622,
|
755 |
+
"eval_steps_per_second": 2.539,
|
756 |
+
"step": 2200
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.52,
|
760 |
+
"learning_rate": 0.0002494837172359015,
|
761 |
+
"loss": 0.7178,
|
762 |
+
"step": 2220
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.53,
|
766 |
+
"learning_rate": 0.0002490071485305798,
|
767 |
+
"loss": 0.7188,
|
768 |
+
"step": 2240
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.53,
|
772 |
+
"learning_rate": 0.0002485305798252581,
|
773 |
+
"loss": 0.7161,
|
774 |
+
"step": 2260
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.54,
|
778 |
+
"learning_rate": 0.00024805401111993645,
|
779 |
+
"loss": 0.7078,
|
780 |
+
"step": 2280
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.54,
|
784 |
+
"learning_rate": 0.0002475774424146147,
|
785 |
+
"loss": 0.7,
|
786 |
+
"step": 2300
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.55,
|
790 |
+
"learning_rate": 0.00024710087370929305,
|
791 |
+
"loss": 0.718,
|
792 |
+
"step": 2320
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.55,
|
796 |
+
"learning_rate": 0.0002466243050039714,
|
797 |
+
"loss": 0.7059,
|
798 |
+
"step": 2340
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.56,
|
802 |
+
"learning_rate": 0.0002461477362986497,
|
803 |
+
"loss": 0.712,
|
804 |
+
"step": 2360
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.56,
|
808 |
+
"learning_rate": 0.00024567116759332804,
|
809 |
+
"loss": 0.7116,
|
810 |
+
"step": 2380
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.57,
|
814 |
+
"learning_rate": 0.0002451945988880063,
|
815 |
+
"loss": 0.6986,
|
816 |
+
"step": 2400
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.57,
|
820 |
+
"eval_loss": 0.6939737796783447,
|
821 |
+
"eval_runtime": 49.459,
|
822 |
+
"eval_samples_per_second": 40.438,
|
823 |
+
"eval_steps_per_second": 2.527,
|
824 |
+
"step": 2400
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.57,
|
828 |
+
"learning_rate": 0.00024471803018268464,
|
829 |
+
"loss": 0.7168,
|
830 |
+
"step": 2420
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.58,
|
834 |
+
"learning_rate": 0.00024424146147736296,
|
835 |
+
"loss": 0.7141,
|
836 |
+
"step": 2440
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.58,
|
840 |
+
"learning_rate": 0.00024376489277204126,
|
841 |
+
"loss": 0.7095,
|
842 |
+
"step": 2460
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.59,
|
846 |
+
"learning_rate": 0.00024328832406671962,
|
847 |
+
"loss": 0.7091,
|
848 |
+
"step": 2480
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.59,
|
852 |
+
"learning_rate": 0.00024281175536139792,
|
853 |
+
"loss": 0.7015,
|
854 |
+
"step": 2500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.6,
|
858 |
+
"learning_rate": 0.00024233518665607622,
|
859 |
+
"loss": 0.7109,
|
860 |
+
"step": 2520
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.6,
|
864 |
+
"learning_rate": 0.00024185861795075455,
|
865 |
+
"loss": 0.7086,
|
866 |
+
"step": 2540
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.61,
|
870 |
+
"learning_rate": 0.00024138204924543285,
|
871 |
+
"loss": 0.7118,
|
872 |
+
"step": 2560
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.61,
|
876 |
+
"learning_rate": 0.00024090548054011117,
|
877 |
+
"loss": 0.7033,
|
878 |
+
"step": 2580
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.61,
|
882 |
+
"learning_rate": 0.0002404289118347895,
|
883 |
+
"loss": 0.7128,
|
884 |
+
"step": 2600
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.61,
|
888 |
+
"eval_loss": 0.6901652812957764,
|
889 |
+
"eval_runtime": 49.5038,
|
890 |
+
"eval_samples_per_second": 40.401,
|
891 |
+
"eval_steps_per_second": 2.525,
|
892 |
+
"step": 2600
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.62,
|
896 |
+
"learning_rate": 0.00023995234312946783,
|
897 |
+
"loss": 0.6968,
|
898 |
+
"step": 2620
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.62,
|
902 |
+
"learning_rate": 0.00023947577442414613,
|
903 |
+
"loss": 0.7109,
|
904 |
+
"step": 2640
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.63,
|
908 |
+
"learning_rate": 0.00023899920571882443,
|
909 |
+
"loss": 0.7048,
|
910 |
+
"step": 2660
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.63,
|
914 |
+
"learning_rate": 0.00023852263701350276,
|
915 |
+
"loss": 0.7012,
|
916 |
+
"step": 2680
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.64,
|
920 |
+
"learning_rate": 0.00023804606830818106,
|
921 |
+
"loss": 0.7065,
|
922 |
+
"step": 2700
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.64,
|
926 |
+
"learning_rate": 0.0002375694996028594,
|
927 |
+
"loss": 0.7009,
|
928 |
+
"step": 2720
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.65,
|
932 |
+
"learning_rate": 0.0002370929308975377,
|
933 |
+
"loss": 0.7035,
|
934 |
+
"step": 2740
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.65,
|
938 |
+
"learning_rate": 0.00023661636219221604,
|
939 |
+
"loss": 0.6973,
|
940 |
+
"step": 2760
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.66,
|
944 |
+
"learning_rate": 0.00023613979348689434,
|
945 |
+
"loss": 0.7075,
|
946 |
+
"step": 2780
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.66,
|
950 |
+
"learning_rate": 0.00023566322478157264,
|
951 |
+
"loss": 0.6952,
|
952 |
+
"step": 2800
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.66,
|
956 |
+
"eval_loss": 0.6865400671958923,
|
957 |
+
"eval_runtime": 49.2814,
|
958 |
+
"eval_samples_per_second": 40.583,
|
959 |
+
"eval_steps_per_second": 2.536,
|
960 |
+
"step": 2800
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.67,
|
964 |
+
"learning_rate": 0.00023518665607625097,
|
965 |
+
"loss": 0.6979,
|
966 |
+
"step": 2820
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.67,
|
970 |
+
"learning_rate": 0.0002347100873709293,
|
971 |
+
"loss": 0.6973,
|
972 |
+
"step": 2840
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.68,
|
976 |
+
"learning_rate": 0.00023423351866560762,
|
977 |
+
"loss": 0.7033,
|
978 |
+
"step": 2860
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.68,
|
982 |
+
"learning_rate": 0.00023375694996028592,
|
983 |
+
"loss": 0.6964,
|
984 |
+
"step": 2880
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.69,
|
988 |
+
"learning_rate": 0.00023328038125496422,
|
989 |
+
"loss": 0.7052,
|
990 |
+
"step": 2900
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.69,
|
994 |
+
"learning_rate": 0.00023280381254964255,
|
995 |
+
"loss": 0.6999,
|
996 |
+
"step": 2920
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.7,
|
1000 |
+
"learning_rate": 0.00023232724384432085,
|
1001 |
+
"loss": 0.6963,
|
1002 |
+
"step": 2940
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.7,
|
1006 |
+
"learning_rate": 0.0002318506751389992,
|
1007 |
+
"loss": 0.7025,
|
1008 |
+
"step": 2960
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.7,
|
1012 |
+
"learning_rate": 0.0002313741064336775,
|
1013 |
+
"loss": 0.704,
|
1014 |
+
"step": 2980
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.71,
|
1018 |
+
"learning_rate": 0.00023089753772835583,
|
1019 |
+
"loss": 0.6926,
|
1020 |
+
"step": 3000
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.71,
|
1024 |
+
"eval_loss": 0.6828380227088928,
|
1025 |
+
"eval_runtime": 49.5667,
|
1026 |
+
"eval_samples_per_second": 40.35,
|
1027 |
+
"eval_steps_per_second": 2.522,
|
1028 |
+
"step": 3000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.71,
|
1032 |
+
"learning_rate": 0.00023042096902303413,
|
1033 |
+
"loss": 0.698,
|
1034 |
+
"step": 3020
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.72,
|
1038 |
+
"learning_rate": 0.00022994440031771243,
|
1039 |
+
"loss": 0.6893,
|
1040 |
+
"step": 3040
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.72,
|
1044 |
+
"learning_rate": 0.00022946783161239076,
|
1045 |
+
"loss": 0.6938,
|
1046 |
+
"step": 3060
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.73,
|
1050 |
+
"learning_rate": 0.00022899126290706908,
|
1051 |
+
"loss": 0.6974,
|
1052 |
+
"step": 3080
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.73,
|
1056 |
+
"learning_rate": 0.0002285146942017474,
|
1057 |
+
"loss": 0.6922,
|
1058 |
+
"step": 3100
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.74,
|
1062 |
+
"learning_rate": 0.0002280381254964257,
|
1063 |
+
"loss": 0.7073,
|
1064 |
+
"step": 3120
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.74,
|
1068 |
+
"learning_rate": 0.00022756155679110404,
|
1069 |
+
"loss": 0.6895,
|
1070 |
+
"step": 3140
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.75,
|
1074 |
+
"learning_rate": 0.00022708498808578234,
|
1075 |
+
"loss": 0.7012,
|
1076 |
+
"step": 3160
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.75,
|
1080 |
+
"learning_rate": 0.00022660841938046064,
|
1081 |
+
"loss": 0.6985,
|
1082 |
+
"step": 3180
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.76,
|
1086 |
+
"learning_rate": 0.000226131850675139,
|
1087 |
+
"loss": 0.6901,
|
1088 |
+
"step": 3200
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.76,
|
1092 |
+
"eval_loss": 0.6807068586349487,
|
1093 |
+
"eval_runtime": 49.2421,
|
1094 |
+
"eval_samples_per_second": 40.616,
|
1095 |
+
"eval_steps_per_second": 2.538,
|
1096 |
+
"step": 3200
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.76,
|
1100 |
+
"learning_rate": 0.0002256552819698173,
|
1101 |
+
"loss": 0.697,
|
1102 |
+
"step": 3220
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.77,
|
1106 |
+
"learning_rate": 0.00022517871326449562,
|
1107 |
+
"loss": 0.7002,
|
1108 |
+
"step": 3240
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.77,
|
1112 |
+
"learning_rate": 0.00022470214455917392,
|
1113 |
+
"loss": 0.6918,
|
1114 |
+
"step": 3260
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.78,
|
1118 |
+
"learning_rate": 0.00022422557585385225,
|
1119 |
+
"loss": 0.6999,
|
1120 |
+
"step": 3280
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 0.78,
|
1124 |
+
"learning_rate": 0.00022374900714853055,
|
1125 |
+
"loss": 0.6961,
|
1126 |
+
"step": 3300
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.78,
|
1130 |
+
"learning_rate": 0.0002232724384432089,
|
1131 |
+
"loss": 0.6888,
|
1132 |
+
"step": 3320
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.79,
|
1136 |
+
"learning_rate": 0.0002227958697378872,
|
1137 |
+
"loss": 0.695,
|
1138 |
+
"step": 3340
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.79,
|
1142 |
+
"learning_rate": 0.0002223193010325655,
|
1143 |
+
"loss": 0.6861,
|
1144 |
+
"step": 3360
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.8,
|
1148 |
+
"learning_rate": 0.00022184273232724383,
|
1149 |
+
"loss": 0.6864,
|
1150 |
+
"step": 3380
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.8,
|
1154 |
+
"learning_rate": 0.00022136616362192213,
|
1155 |
+
"loss": 0.6917,
|
1156 |
+
"step": 3400
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.8,
|
1160 |
+
"eval_loss": 0.6773961782455444,
|
1161 |
+
"eval_runtime": 49.3961,
|
1162 |
+
"eval_samples_per_second": 40.489,
|
1163 |
+
"eval_steps_per_second": 2.531,
|
1164 |
+
"step": 3400
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.81,
|
1168 |
+
"learning_rate": 0.00022088959491660043,
|
1169 |
+
"loss": 0.679,
|
1170 |
+
"step": 3420
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.81,
|
1174 |
+
"learning_rate": 0.00022041302621127879,
|
1175 |
+
"loss": 0.6915,
|
1176 |
+
"step": 3440
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 0.82,
|
1180 |
+
"learning_rate": 0.00021993645750595709,
|
1181 |
+
"loss": 0.6937,
|
1182 |
+
"step": 3460
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.82,
|
1186 |
+
"learning_rate": 0.0002194598888006354,
|
1187 |
+
"loss": 0.6831,
|
1188 |
+
"step": 3480
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.83,
|
1192 |
+
"learning_rate": 0.0002189833200953137,
|
1193 |
+
"loss": 0.6875,
|
1194 |
+
"step": 3500
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.83,
|
1198 |
+
"learning_rate": 0.00021850675138999204,
|
1199 |
+
"loss": 0.6916,
|
1200 |
+
"step": 3520
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.84,
|
1204 |
+
"learning_rate": 0.00021803018268467034,
|
1205 |
+
"loss": 0.6896,
|
1206 |
+
"step": 3540
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.84,
|
1210 |
+
"learning_rate": 0.0002175536139793487,
|
1211 |
+
"loss": 0.6986,
|
1212 |
+
"step": 3560
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.85,
|
1216 |
+
"learning_rate": 0.000217077045274027,
|
1217 |
+
"loss": 0.693,
|
1218 |
+
"step": 3580
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.85,
|
1222 |
+
"learning_rate": 0.0002166004765687053,
|
1223 |
+
"loss": 0.6893,
|
1224 |
+
"step": 3600
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.85,
|
1228 |
+
"eval_loss": 0.6753410696983337,
|
1229 |
+
"eval_runtime": 49.3307,
|
1230 |
+
"eval_samples_per_second": 40.543,
|
1231 |
+
"eval_steps_per_second": 2.534,
|
1232 |
+
"step": 3600
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.86,
|
1236 |
+
"learning_rate": 0.00021612390786338362,
|
1237 |
+
"loss": 0.6872,
|
1238 |
+
"step": 3620
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.86,
|
1242 |
+
"learning_rate": 0.00021564733915806192,
|
1243 |
+
"loss": 0.6862,
|
1244 |
+
"step": 3640
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.87,
|
1248 |
+
"learning_rate": 0.00021517077045274025,
|
1249 |
+
"loss": 0.6943,
|
1250 |
+
"step": 3660
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.87,
|
1254 |
+
"learning_rate": 0.00021469420174741858,
|
1255 |
+
"loss": 0.6896,
|
1256 |
+
"step": 3680
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.87,
|
1260 |
+
"learning_rate": 0.0002142176330420969,
|
1261 |
+
"loss": 0.6912,
|
1262 |
+
"step": 3700
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.88,
|
1266 |
+
"learning_rate": 0.0002137410643367752,
|
1267 |
+
"loss": 0.6859,
|
1268 |
+
"step": 3720
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.88,
|
1272 |
+
"learning_rate": 0.0002132644956314535,
|
1273 |
+
"loss": 0.6791,
|
1274 |
+
"step": 3740
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.89,
|
1278 |
+
"learning_rate": 0.00021278792692613183,
|
1279 |
+
"loss": 0.6882,
|
1280 |
+
"step": 3760
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.89,
|
1284 |
+
"learning_rate": 0.00021231135822081013,
|
1285 |
+
"loss": 0.6823,
|
1286 |
+
"step": 3780
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.9,
|
1290 |
+
"learning_rate": 0.0002118347895154885,
|
1291 |
+
"loss": 0.6831,
|
1292 |
+
"step": 3800
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.9,
|
1296 |
+
"eval_loss": 0.6738302707672119,
|
1297 |
+
"eval_runtime": 49.4648,
|
1298 |
+
"eval_samples_per_second": 40.433,
|
1299 |
+
"eval_steps_per_second": 2.527,
|
1300 |
+
"step": 3800
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.9,
|
1304 |
+
"learning_rate": 0.0002113582208101668,
|
1305 |
+
"loss": 0.6818,
|
1306 |
+
"step": 3820
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.91,
|
1310 |
+
"learning_rate": 0.0002108816521048451,
|
1311 |
+
"loss": 0.6912,
|
1312 |
+
"step": 3840
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.91,
|
1316 |
+
"learning_rate": 0.00021040508339952341,
|
1317 |
+
"loss": 0.6884,
|
1318 |
+
"step": 3860
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.92,
|
1322 |
+
"learning_rate": 0.00020992851469420171,
|
1323 |
+
"loss": 0.6888,
|
1324 |
+
"step": 3880
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 0.92,
|
1328 |
+
"learning_rate": 0.00020945194598888004,
|
1329 |
+
"loss": 0.6822,
|
1330 |
+
"step": 3900
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.93,
|
1334 |
+
"learning_rate": 0.00020897537728355837,
|
1335 |
+
"loss": 0.6879,
|
1336 |
+
"step": 3920
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.93,
|
1340 |
+
"learning_rate": 0.0002084988085782367,
|
1341 |
+
"loss": 0.6771,
|
1342 |
+
"step": 3940
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.94,
|
1346 |
+
"learning_rate": 0.000208022239872915,
|
1347 |
+
"loss": 0.684,
|
1348 |
+
"step": 3960
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.94,
|
1352 |
+
"learning_rate": 0.0002075456711675933,
|
1353 |
+
"loss": 0.6878,
|
1354 |
+
"step": 3980
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.95,
|
1358 |
+
"learning_rate": 0.00020706910246227162,
|
1359 |
+
"loss": 0.6913,
|
1360 |
+
"step": 4000
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.95,
|
1364 |
+
"eval_loss": 0.6711302995681763,
|
1365 |
+
"eval_runtime": 49.117,
|
1366 |
+
"eval_samples_per_second": 40.719,
|
1367 |
+
"eval_steps_per_second": 2.545,
|
1368 |
+
"step": 4000
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.95,
|
1372 |
+
"learning_rate": 0.00020659253375694992,
|
1373 |
+
"loss": 0.683,
|
1374 |
+
"step": 4020
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.96,
|
1378 |
+
"learning_rate": 0.00020611596505162828,
|
1379 |
+
"loss": 0.6833,
|
1380 |
+
"step": 4040
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 0.96,
|
1384 |
+
"learning_rate": 0.00020563939634630658,
|
1385 |
+
"loss": 0.6793,
|
1386 |
+
"step": 4060
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.96,
|
1390 |
+
"learning_rate": 0.0002051628276409849,
|
1391 |
+
"loss": 0.6843,
|
1392 |
+
"step": 4080
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.97,
|
1396 |
+
"learning_rate": 0.0002046862589356632,
|
1397 |
+
"loss": 0.6822,
|
1398 |
+
"step": 4100
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.97,
|
1402 |
+
"learning_rate": 0.0002042096902303415,
|
1403 |
+
"loss": 0.6856,
|
1404 |
+
"step": 4120
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.98,
|
1408 |
+
"learning_rate": 0.00020373312152501983,
|
1409 |
+
"loss": 0.6809,
|
1410 |
+
"step": 4140
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.98,
|
1414 |
+
"learning_rate": 0.00020325655281969816,
|
1415 |
+
"loss": 0.6843,
|
1416 |
+
"step": 4160
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.99,
|
1420 |
+
"learning_rate": 0.0002027799841143765,
|
1421 |
+
"loss": 0.6754,
|
1422 |
+
"step": 4180
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 0.99,
|
1426 |
+
"learning_rate": 0.0002023034154090548,
|
1427 |
+
"loss": 0.6823,
|
1428 |
+
"step": 4200
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 0.99,
|
1432 |
+
"eval_loss": 0.6697036027908325,
|
1433 |
+
"eval_runtime": 49.3237,
|
1434 |
+
"eval_samples_per_second": 40.548,
|
1435 |
+
"eval_steps_per_second": 2.534,
|
1436 |
+
"step": 4200
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 1.0,
|
1440 |
+
"learning_rate": 0.00020182684670373312,
|
1441 |
+
"loss": 0.6861,
|
1442 |
+
"step": 4220
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 1.0,
|
1446 |
+
"learning_rate": 0.00020135027799841142,
|
1447 |
+
"loss": 0.6806,
|
1448 |
+
"step": 4240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 1.01,
|
1452 |
+
"learning_rate": 0.00020087370929308972,
|
1453 |
+
"loss": 0.6823,
|
1454 |
+
"step": 4260
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 1.01,
|
1458 |
+
"learning_rate": 0.00020039714058776807,
|
1459 |
+
"loss": 0.6805,
|
1460 |
+
"step": 4280
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.02,
|
1464 |
+
"learning_rate": 0.00019992057188244637,
|
1465 |
+
"loss": 0.6813,
|
1466 |
+
"step": 4300
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.02,
|
1470 |
+
"learning_rate": 0.0001994440031771247,
|
1471 |
+
"loss": 0.675,
|
1472 |
+
"step": 4320
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.03,
|
1476 |
+
"learning_rate": 0.000198967434471803,
|
1477 |
+
"loss": 0.6728,
|
1478 |
+
"step": 4340
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.03,
|
1482 |
+
"learning_rate": 0.0001984908657664813,
|
1483 |
+
"loss": 0.6676,
|
1484 |
+
"step": 4360
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 1.04,
|
1488 |
+
"learning_rate": 0.00019801429706115963,
|
1489 |
+
"loss": 0.6729,
|
1490 |
+
"step": 4380
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 1.04,
|
1494 |
+
"learning_rate": 0.00019753772835583795,
|
1495 |
+
"loss": 0.685,
|
1496 |
+
"step": 4400
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 1.04,
|
1500 |
+
"eval_loss": 0.6667952537536621,
|
1501 |
+
"eval_runtime": 49.3899,
|
1502 |
+
"eval_samples_per_second": 40.494,
|
1503 |
+
"eval_steps_per_second": 2.531,
|
1504 |
+
"step": 4400
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 1.04,
|
1508 |
+
"learning_rate": 0.00019706115965051628,
|
1509 |
+
"loss": 0.6786,
|
1510 |
+
"step": 4420
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.05,
|
1514 |
+
"learning_rate": 0.00019658459094519458,
|
1515 |
+
"loss": 0.6738,
|
1516 |
+
"step": 4440
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 1.05,
|
1520 |
+
"learning_rate": 0.0001961080222398729,
|
1521 |
+
"loss": 0.686,
|
1522 |
+
"step": 4460
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.06,
|
1526 |
+
"learning_rate": 0.0001956314535345512,
|
1527 |
+
"loss": 0.6818,
|
1528 |
+
"step": 4480
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.06,
|
1532 |
+
"learning_rate": 0.0001951548848292295,
|
1533 |
+
"loss": 0.6741,
|
1534 |
+
"step": 4500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 1.07,
|
1538 |
+
"learning_rate": 0.00019467831612390786,
|
1539 |
+
"loss": 0.6756,
|
1540 |
+
"step": 4520
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 1.07,
|
1544 |
+
"learning_rate": 0.00019420174741858616,
|
1545 |
+
"loss": 0.6851,
|
1546 |
+
"step": 4540
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.08,
|
1550 |
+
"learning_rate": 0.0001937251787132645,
|
1551 |
+
"loss": 0.6784,
|
1552 |
+
"step": 4560
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 1.08,
|
1556 |
+
"learning_rate": 0.0001932486100079428,
|
1557 |
+
"loss": 0.6785,
|
1558 |
+
"step": 4580
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 1.09,
|
1562 |
+
"learning_rate": 0.00019277204130262112,
|
1563 |
+
"loss": 0.678,
|
1564 |
+
"step": 4600
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.09,
|
1568 |
+
"eval_loss": 0.6655837297439575,
|
1569 |
+
"eval_runtime": 49.5019,
|
1570 |
+
"eval_samples_per_second": 40.403,
|
1571 |
+
"eval_steps_per_second": 2.525,
|
1572 |
+
"step": 4600
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 1.09,
|
1576 |
+
"learning_rate": 0.00019229547259729942,
|
1577 |
+
"loss": 0.6782,
|
1578 |
+
"step": 4620
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.1,
|
1582 |
+
"learning_rate": 0.00019181890389197777,
|
1583 |
+
"loss": 0.6683,
|
1584 |
+
"step": 4640
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.1,
|
1588 |
+
"learning_rate": 0.00019134233518665607,
|
1589 |
+
"loss": 0.6783,
|
1590 |
+
"step": 4660
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 1.11,
|
1594 |
+
"learning_rate": 0.00019086576648133437,
|
1595 |
+
"loss": 0.675,
|
1596 |
+
"step": 4680
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 1.11,
|
1600 |
+
"learning_rate": 0.0001903891977760127,
|
1601 |
+
"loss": 0.6691,
|
1602 |
+
"step": 4700
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.12,
|
1606 |
+
"learning_rate": 0.000189912629070691,
|
1607 |
+
"loss": 0.6726,
|
1608 |
+
"step": 4720
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.12,
|
1612 |
+
"learning_rate": 0.00018943606036536933,
|
1613 |
+
"loss": 0.68,
|
1614 |
+
"step": 4740
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.13,
|
1618 |
+
"learning_rate": 0.00018895949166004763,
|
1619 |
+
"loss": 0.6694,
|
1620 |
+
"step": 4760
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.13,
|
1624 |
+
"learning_rate": 0.00018848292295472598,
|
1625 |
+
"loss": 0.6686,
|
1626 |
+
"step": 4780
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.13,
|
1630 |
+
"learning_rate": 0.00018800635424940428,
|
1631 |
+
"loss": 0.6766,
|
1632 |
+
"step": 4800
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.13,
|
1636 |
+
"eval_loss": 0.6646501421928406,
|
1637 |
+
"eval_runtime": 49.3188,
|
1638 |
+
"eval_samples_per_second": 40.552,
|
1639 |
+
"eval_steps_per_second": 2.535,
|
1640 |
+
"step": 4800
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 1.14,
|
1644 |
+
"learning_rate": 0.00018752978554408258,
|
1645 |
+
"loss": 0.6724,
|
1646 |
+
"step": 4820
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 1.14,
|
1650 |
+
"learning_rate": 0.0001870532168387609,
|
1651 |
+
"loss": 0.6801,
|
1652 |
+
"step": 4840
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 1.15,
|
1656 |
+
"learning_rate": 0.0001865766481334392,
|
1657 |
+
"loss": 0.6698,
|
1658 |
+
"step": 4860
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.15,
|
1662 |
+
"learning_rate": 0.0001861000794281175,
|
1663 |
+
"loss": 0.6723,
|
1664 |
+
"step": 4880
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 1.16,
|
1668 |
+
"learning_rate": 0.00018562351072279586,
|
1669 |
+
"loss": 0.6693,
|
1670 |
+
"step": 4900
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 1.16,
|
1674 |
+
"learning_rate": 0.00018514694201747416,
|
1675 |
+
"loss": 0.6716,
|
1676 |
+
"step": 4920
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.17,
|
1680 |
+
"learning_rate": 0.0001846703733121525,
|
1681 |
+
"loss": 0.674,
|
1682 |
+
"step": 4940
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 1.17,
|
1686 |
+
"learning_rate": 0.0001841938046068308,
|
1687 |
+
"loss": 0.6702,
|
1688 |
+
"step": 4960
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 1.18,
|
1692 |
+
"learning_rate": 0.00018371723590150912,
|
1693 |
+
"loss": 0.6716,
|
1694 |
+
"step": 4980
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 1.18,
|
1698 |
+
"learning_rate": 0.00018324066719618742,
|
1699 |
+
"loss": 0.672,
|
1700 |
+
"step": 5000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.18,
|
1704 |
+
"eval_loss": 0.662735104560852,
|
1705 |
+
"eval_runtime": 49.275,
|
1706 |
+
"eval_samples_per_second": 40.589,
|
1707 |
+
"eval_steps_per_second": 2.537,
|
1708 |
+
"step": 5000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.19,
|
1712 |
+
"learning_rate": 0.00018276409849086577,
|
1713 |
+
"loss": 0.6701,
|
1714 |
+
"step": 5020
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.19,
|
1718 |
+
"learning_rate": 0.00018228752978554407,
|
1719 |
+
"loss": 0.6663,
|
1720 |
+
"step": 5040
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 1.2,
|
1724 |
+
"learning_rate": 0.00018181096108022237,
|
1725 |
+
"loss": 0.6651,
|
1726 |
+
"step": 5060
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.2,
|
1730 |
+
"learning_rate": 0.0001813343923749007,
|
1731 |
+
"loss": 0.6708,
|
1732 |
+
"step": 5080
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.21,
|
1736 |
+
"learning_rate": 0.000180857823669579,
|
1737 |
+
"loss": 0.6697,
|
1738 |
+
"step": 5100
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.21,
|
1742 |
+
"learning_rate": 0.00018038125496425733,
|
1743 |
+
"loss": 0.662,
|
1744 |
+
"step": 5120
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 1.22,
|
1748 |
+
"learning_rate": 0.00017990468625893566,
|
1749 |
+
"loss": 0.669,
|
1750 |
+
"step": 5140
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 1.22,
|
1754 |
+
"learning_rate": 0.00017942811755361398,
|
1755 |
+
"loss": 0.6649,
|
1756 |
+
"step": 5160
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.22,
|
1760 |
+
"learning_rate": 0.00017895154884829228,
|
1761 |
+
"loss": 0.668,
|
1762 |
+
"step": 5180
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.23,
|
1766 |
+
"learning_rate": 0.00017847498014297058,
|
1767 |
+
"loss": 0.6796,
|
1768 |
+
"step": 5200
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 1.23,
|
1772 |
+
"eval_loss": 0.6609957218170166,
|
1773 |
+
"eval_runtime": 49.2394,
|
1774 |
+
"eval_samples_per_second": 40.618,
|
1775 |
+
"eval_steps_per_second": 2.539,
|
1776 |
+
"step": 5200
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 1.23,
|
1780 |
+
"learning_rate": 0.0001779984114376489,
|
1781 |
+
"loss": 0.6745,
|
1782 |
+
"step": 5220
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 1.24,
|
1786 |
+
"learning_rate": 0.0001775218427323272,
|
1787 |
+
"loss": 0.6646,
|
1788 |
+
"step": 5240
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.24,
|
1792 |
+
"learning_rate": 0.00017704527402700556,
|
1793 |
+
"loss": 0.6682,
|
1794 |
+
"step": 5260
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.25,
|
1798 |
+
"learning_rate": 0.00017656870532168386,
|
1799 |
+
"loss": 0.6713,
|
1800 |
+
"step": 5280
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 1.25,
|
1804 |
+
"learning_rate": 0.00017609213661636216,
|
1805 |
+
"loss": 0.6618,
|
1806 |
+
"step": 5300
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.26,
|
1810 |
+
"learning_rate": 0.0001756155679110405,
|
1811 |
+
"loss": 0.6703,
|
1812 |
+
"step": 5320
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 1.26,
|
1816 |
+
"learning_rate": 0.0001751389992057188,
|
1817 |
+
"loss": 0.6652,
|
1818 |
+
"step": 5340
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 1.27,
|
1822 |
+
"learning_rate": 0.00017466243050039712,
|
1823 |
+
"loss": 0.6698,
|
1824 |
+
"step": 5360
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.27,
|
1828 |
+
"learning_rate": 0.00017418586179507545,
|
1829 |
+
"loss": 0.6728,
|
1830 |
+
"step": 5380
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.28,
|
1834 |
+
"learning_rate": 0.00017370929308975377,
|
1835 |
+
"loss": 0.6752,
|
1836 |
+
"step": 5400
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.28,
|
1840 |
+
"eval_loss": 0.6592395901679993,
|
1841 |
+
"eval_runtime": 49.3426,
|
1842 |
+
"eval_samples_per_second": 40.533,
|
1843 |
+
"eval_steps_per_second": 2.533,
|
1844 |
+
"step": 5400
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.28,
|
1848 |
+
"learning_rate": 0.00017323272438443207,
|
1849 |
+
"loss": 0.6653,
|
1850 |
+
"step": 5420
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.29,
|
1854 |
+
"learning_rate": 0.00017275615567911037,
|
1855 |
+
"loss": 0.669,
|
1856 |
+
"step": 5440
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 1.29,
|
1860 |
+
"learning_rate": 0.0001722795869737887,
|
1861 |
+
"loss": 0.6698,
|
1862 |
+
"step": 5460
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 1.3,
|
1866 |
+
"learning_rate": 0.000171803018268467,
|
1867 |
+
"loss": 0.6742,
|
1868 |
+
"step": 5480
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 1.3,
|
1872 |
+
"learning_rate": 0.00017132644956314536,
|
1873 |
+
"loss": 0.6596,
|
1874 |
+
"step": 5500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 1.3,
|
1878 |
+
"learning_rate": 0.00017084988085782366,
|
1879 |
+
"loss": 0.6699,
|
1880 |
+
"step": 5520
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 1.31,
|
1884 |
+
"learning_rate": 0.00017037331215250198,
|
1885 |
+
"loss": 0.664,
|
1886 |
+
"step": 5540
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.31,
|
1890 |
+
"learning_rate": 0.00016989674344718028,
|
1891 |
+
"loss": 0.6673,
|
1892 |
+
"step": 5560
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.32,
|
1896 |
+
"learning_rate": 0.00016942017474185858,
|
1897 |
+
"loss": 0.6684,
|
1898 |
+
"step": 5580
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 1.32,
|
1902 |
+
"learning_rate": 0.0001689436060365369,
|
1903 |
+
"loss": 0.6769,
|
1904 |
+
"step": 5600
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 1.32,
|
1908 |
+
"eval_loss": 0.6582754850387573,
|
1909 |
+
"eval_runtime": 49.469,
|
1910 |
+
"eval_samples_per_second": 40.429,
|
1911 |
+
"eval_steps_per_second": 2.527,
|
1912 |
+
"step": 5600
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 1.33,
|
1916 |
+
"learning_rate": 0.00016846703733121524,
|
1917 |
+
"loss": 0.6633,
|
1918 |
+
"step": 5620
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 1.33,
|
1922 |
+
"learning_rate": 0.00016799046862589357,
|
1923 |
+
"loss": 0.6679,
|
1924 |
+
"step": 5640
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.34,
|
1928 |
+
"learning_rate": 0.00016751389992057187,
|
1929 |
+
"loss": 0.6601,
|
1930 |
+
"step": 5660
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 1.34,
|
1934 |
+
"learning_rate": 0.0001670373312152502,
|
1935 |
+
"loss": 0.6731,
|
1936 |
+
"step": 5680
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 1.35,
|
1940 |
+
"learning_rate": 0.0001665607625099285,
|
1941 |
+
"loss": 0.6638,
|
1942 |
+
"step": 5700
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.35,
|
1946 |
+
"learning_rate": 0.0001660841938046068,
|
1947 |
+
"loss": 0.6693,
|
1948 |
+
"step": 5720
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.36,
|
1952 |
+
"learning_rate": 0.00016560762509928515,
|
1953 |
+
"loss": 0.6642,
|
1954 |
+
"step": 5740
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.36,
|
1958 |
+
"learning_rate": 0.00016513105639396345,
|
1959 |
+
"loss": 0.6649,
|
1960 |
+
"step": 5760
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.37,
|
1964 |
+
"learning_rate": 0.00016465448768864178,
|
1965 |
+
"loss": 0.663,
|
1966 |
+
"step": 5780
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 1.37,
|
1970 |
+
"learning_rate": 0.00016417791898332008,
|
1971 |
+
"loss": 0.6629,
|
1972 |
+
"step": 5800
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 1.37,
|
1976 |
+
"eval_loss": 0.6574136018753052,
|
1977 |
+
"eval_runtime": 49.3019,
|
1978 |
+
"eval_samples_per_second": 40.566,
|
1979 |
+
"eval_steps_per_second": 2.535,
|
1980 |
+
"step": 5800
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 1.38,
|
1984 |
+
"learning_rate": 0.00016370135027799838,
|
1985 |
+
"loss": 0.6605,
|
1986 |
+
"step": 5820
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 1.38,
|
1990 |
+
"learning_rate": 0.0001632247815726767,
|
1991 |
+
"loss": 0.6707,
|
1992 |
+
"step": 5840
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 1.39,
|
1996 |
+
"learning_rate": 0.00016274821286735503,
|
1997 |
+
"loss": 0.6695,
|
1998 |
+
"step": 5860
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.39,
|
2002 |
+
"learning_rate": 0.00016227164416203336,
|
2003 |
+
"loss": 0.6647,
|
2004 |
+
"step": 5880
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 1.39,
|
2008 |
+
"learning_rate": 0.00016179507545671166,
|
2009 |
+
"loss": 0.6657,
|
2010 |
+
"step": 5900
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.4,
|
2014 |
+
"learning_rate": 0.00016131850675138999,
|
2015 |
+
"loss": 0.6656,
|
2016 |
+
"step": 5920
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 1.4,
|
2020 |
+
"learning_rate": 0.00016084193804606829,
|
2021 |
+
"loss": 0.6676,
|
2022 |
+
"step": 5940
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.41,
|
2026 |
+
"learning_rate": 0.00016036536934074659,
|
2027 |
+
"loss": 0.6678,
|
2028 |
+
"step": 5960
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 1.41,
|
2032 |
+
"learning_rate": 0.00015988880063542494,
|
2033 |
+
"loss": 0.6639,
|
2034 |
+
"step": 5980
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.42,
|
2038 |
+
"learning_rate": 0.00015941223193010324,
|
2039 |
+
"loss": 0.6645,
|
2040 |
+
"step": 6000
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.42,
|
2044 |
+
"eval_loss": 0.656126081943512,
|
2045 |
+
"eval_runtime": 49.5095,
|
2046 |
+
"eval_samples_per_second": 40.396,
|
2047 |
+
"eval_steps_per_second": 2.525,
|
2048 |
+
"step": 6000
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 1.42,
|
2052 |
+
"learning_rate": 0.00015893566322478157,
|
2053 |
+
"loss": 0.6672,
|
2054 |
+
"step": 6020
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.43,
|
2058 |
+
"learning_rate": 0.00015845909451945987,
|
2059 |
+
"loss": 0.6678,
|
2060 |
+
"step": 6040
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 1.43,
|
2064 |
+
"learning_rate": 0.0001579825258141382,
|
2065 |
+
"loss": 0.6676,
|
2066 |
+
"step": 6060
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.44,
|
2070 |
+
"learning_rate": 0.0001575059571088165,
|
2071 |
+
"loss": 0.6717,
|
2072 |
+
"step": 6080
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 1.44,
|
2076 |
+
"learning_rate": 0.00015702938840349485,
|
2077 |
+
"loss": 0.671,
|
2078 |
+
"step": 6100
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 1.45,
|
2082 |
+
"learning_rate": 0.00015655281969817315,
|
2083 |
+
"loss": 0.6611,
|
2084 |
+
"step": 6120
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 1.45,
|
2088 |
+
"learning_rate": 0.00015607625099285145,
|
2089 |
+
"loss": 0.6606,
|
2090 |
+
"step": 6140
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 1.46,
|
2094 |
+
"learning_rate": 0.00015559968228752978,
|
2095 |
+
"loss": 0.6647,
|
2096 |
+
"step": 6160
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.46,
|
2100 |
+
"learning_rate": 0.00015512311358220808,
|
2101 |
+
"loss": 0.6652,
|
2102 |
+
"step": 6180
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.47,
|
2106 |
+
"learning_rate": 0.0001546465448768864,
|
2107 |
+
"loss": 0.6629,
|
2108 |
+
"step": 6200
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 1.47,
|
2112 |
+
"eval_loss": 0.6549723148345947,
|
2113 |
+
"eval_runtime": 49.4871,
|
2114 |
+
"eval_samples_per_second": 40.415,
|
2115 |
+
"eval_steps_per_second": 2.526,
|
2116 |
+
"step": 6200
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.47,
|
2120 |
+
"learning_rate": 0.00015416997617156473,
|
2121 |
+
"loss": 0.6685,
|
2122 |
+
"step": 6220
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.48,
|
2126 |
+
"learning_rate": 0.00015369340746624306,
|
2127 |
+
"loss": 0.6578,
|
2128 |
+
"step": 6240
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"epoch": 1.48,
|
2132 |
+
"learning_rate": 0.00015321683876092136,
|
2133 |
+
"loss": 0.6587,
|
2134 |
+
"step": 6260
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.48,
|
2138 |
+
"learning_rate": 0.00015274027005559966,
|
2139 |
+
"loss": 0.6655,
|
2140 |
+
"step": 6280
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.49,
|
2144 |
+
"learning_rate": 0.000152263701350278,
|
2145 |
+
"loss": 0.6662,
|
2146 |
+
"step": 6300
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 1.49,
|
2150 |
+
"learning_rate": 0.0001517871326449563,
|
2151 |
+
"loss": 0.6648,
|
2152 |
+
"step": 6320
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.5,
|
2156 |
+
"learning_rate": 0.00015131056393963464,
|
2157 |
+
"loss": 0.6638,
|
2158 |
+
"step": 6340
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.5,
|
2162 |
+
"learning_rate": 0.00015083399523431294,
|
2163 |
+
"loss": 0.6614,
|
2164 |
+
"step": 6360
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 1.51,
|
2168 |
+
"learning_rate": 0.00015035742652899124,
|
2169 |
+
"loss": 0.6552,
|
2170 |
+
"step": 6380
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 1.51,
|
2174 |
+
"learning_rate": 0.00014988085782366957,
|
2175 |
+
"loss": 0.6753,
|
2176 |
+
"step": 6400
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.51,
|
2180 |
+
"eval_loss": 0.6544620990753174,
|
2181 |
+
"eval_runtime": 49.3242,
|
2182 |
+
"eval_samples_per_second": 40.548,
|
2183 |
+
"eval_steps_per_second": 2.534,
|
2184 |
+
"step": 6400
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 1.52,
|
2188 |
+
"learning_rate": 0.00014940428911834787,
|
2189 |
+
"loss": 0.6588,
|
2190 |
+
"step": 6420
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 1.52,
|
2194 |
+
"learning_rate": 0.0001489277204130262,
|
2195 |
+
"loss": 0.6609,
|
2196 |
+
"step": 6440
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 1.53,
|
2200 |
+
"learning_rate": 0.00014845115170770452,
|
2201 |
+
"loss": 0.6565,
|
2202 |
+
"step": 6460
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 1.53,
|
2206 |
+
"learning_rate": 0.00014797458300238282,
|
2207 |
+
"loss": 0.6589,
|
2208 |
+
"step": 6480
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.54,
|
2212 |
+
"learning_rate": 0.00014749801429706115,
|
2213 |
+
"loss": 0.6585,
|
2214 |
+
"step": 6500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.54,
|
2218 |
+
"learning_rate": 0.00014702144559173945,
|
2219 |
+
"loss": 0.6737,
|
2220 |
+
"step": 6520
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 1.55,
|
2224 |
+
"learning_rate": 0.00014654487688641778,
|
2225 |
+
"loss": 0.6554,
|
2226 |
+
"step": 6540
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 1.55,
|
2230 |
+
"learning_rate": 0.0001460683081810961,
|
2231 |
+
"loss": 0.6603,
|
2232 |
+
"step": 6560
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 1.56,
|
2236 |
+
"learning_rate": 0.0001455917394757744,
|
2237 |
+
"loss": 0.6647,
|
2238 |
+
"step": 6580
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 1.56,
|
2242 |
+
"learning_rate": 0.00014511517077045273,
|
2243 |
+
"loss": 0.6632,
|
2244 |
+
"step": 6600
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 1.56,
|
2248 |
+
"eval_loss": 0.6527110934257507,
|
2249 |
+
"eval_runtime": 49.2622,
|
2250 |
+
"eval_samples_per_second": 40.599,
|
2251 |
+
"eval_steps_per_second": 2.537,
|
2252 |
+
"step": 6600
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 1.57,
|
2256 |
+
"learning_rate": 0.00014463860206513106,
|
2257 |
+
"loss": 0.6705,
|
2258 |
+
"step": 6620
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 1.57,
|
2262 |
+
"learning_rate": 0.00014416203335980936,
|
2263 |
+
"loss": 0.6703,
|
2264 |
+
"step": 6640
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.57,
|
2268 |
+
"learning_rate": 0.00014368546465448766,
|
2269 |
+
"loss": 0.6602,
|
2270 |
+
"step": 6660
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 1.58,
|
2274 |
+
"learning_rate": 0.000143208895949166,
|
2275 |
+
"loss": 0.6639,
|
2276 |
+
"step": 6680
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 1.58,
|
2280 |
+
"learning_rate": 0.00014273232724384432,
|
2281 |
+
"loss": 0.6645,
|
2282 |
+
"step": 6700
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 1.59,
|
2286 |
+
"learning_rate": 0.00014225575853852262,
|
2287 |
+
"loss": 0.6655,
|
2288 |
+
"step": 6720
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.59,
|
2292 |
+
"learning_rate": 0.00014177918983320094,
|
2293 |
+
"loss": 0.664,
|
2294 |
+
"step": 6740
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 1.6,
|
2298 |
+
"learning_rate": 0.00014130262112787927,
|
2299 |
+
"loss": 0.6656,
|
2300 |
+
"step": 6760
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 1.6,
|
2304 |
+
"learning_rate": 0.00014082605242255757,
|
2305 |
+
"loss": 0.6658,
|
2306 |
+
"step": 6780
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.61,
|
2310 |
+
"learning_rate": 0.0001403494837172359,
|
2311 |
+
"loss": 0.6641,
|
2312 |
+
"step": 6800
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 1.61,
|
2316 |
+
"eval_loss": 0.6513609886169434,
|
2317 |
+
"eval_runtime": 49.4424,
|
2318 |
+
"eval_samples_per_second": 40.451,
|
2319 |
+
"eval_steps_per_second": 2.528,
|
2320 |
+
"step": 6800
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.61,
|
2324 |
+
"learning_rate": 0.0001398729150119142,
|
2325 |
+
"loss": 0.6599,
|
2326 |
+
"step": 6820
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 1.62,
|
2330 |
+
"learning_rate": 0.00013939634630659252,
|
2331 |
+
"loss": 0.6552,
|
2332 |
+
"step": 6840
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 1.62,
|
2336 |
+
"learning_rate": 0.00013891977760127085,
|
2337 |
+
"loss": 0.6616,
|
2338 |
+
"step": 6860
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 1.63,
|
2342 |
+
"learning_rate": 0.00013844320889594915,
|
2343 |
+
"loss": 0.6635,
|
2344 |
+
"step": 6880
|
2345 |
+
},
|
2346 |
+
{
|
2347 |
+
"epoch": 1.63,
|
2348 |
+
"learning_rate": 0.00013796664019062745,
|
2349 |
+
"loss": 0.6608,
|
2350 |
+
"step": 6900
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"epoch": 1.64,
|
2354 |
+
"learning_rate": 0.00013749007148530578,
|
2355 |
+
"loss": 0.6596,
|
2356 |
+
"step": 6920
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 1.64,
|
2360 |
+
"learning_rate": 0.0001370135027799841,
|
2361 |
+
"loss": 0.6589,
|
2362 |
+
"step": 6940
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.65,
|
2366 |
+
"learning_rate": 0.0001365369340746624,
|
2367 |
+
"loss": 0.6627,
|
2368 |
+
"step": 6960
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 1.65,
|
2372 |
+
"learning_rate": 0.00013606036536934073,
|
2373 |
+
"loss": 0.6606,
|
2374 |
+
"step": 6980
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 1.65,
|
2378 |
+
"learning_rate": 0.00013558379666401906,
|
2379 |
+
"loss": 0.6658,
|
2380 |
+
"step": 7000
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 1.65,
|
2384 |
+
"eval_loss": 0.6510519981384277,
|
2385 |
+
"eval_runtime": 49.5012,
|
2386 |
+
"eval_samples_per_second": 40.403,
|
2387 |
+
"eval_steps_per_second": 2.525,
|
2388 |
+
"step": 7000
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 1.66,
|
2392 |
+
"learning_rate": 0.00013510722795869736,
|
2393 |
+
"loss": 0.6571,
|
2394 |
+
"step": 7020
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.66,
|
2398 |
+
"learning_rate": 0.0001346306592533757,
|
2399 |
+
"loss": 0.6607,
|
2400 |
+
"step": 7040
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 1.67,
|
2404 |
+
"learning_rate": 0.000134154090548054,
|
2405 |
+
"loss": 0.6562,
|
2406 |
+
"step": 7060
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 1.67,
|
2410 |
+
"learning_rate": 0.00013367752184273232,
|
2411 |
+
"loss": 0.6582,
|
2412 |
+
"step": 7080
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 1.68,
|
2416 |
+
"learning_rate": 0.00013320095313741064,
|
2417 |
+
"loss": 0.6635,
|
2418 |
+
"step": 7100
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.68,
|
2422 |
+
"learning_rate": 0.00013272438443208894,
|
2423 |
+
"loss": 0.6682,
|
2424 |
+
"step": 7120
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 1.69,
|
2428 |
+
"learning_rate": 0.00013224781572676727,
|
2429 |
+
"loss": 0.6633,
|
2430 |
+
"step": 7140
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 1.69,
|
2434 |
+
"learning_rate": 0.0001317712470214456,
|
2435 |
+
"loss": 0.6671,
|
2436 |
+
"step": 7160
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 1.7,
|
2440 |
+
"learning_rate": 0.0001312946783161239,
|
2441 |
+
"loss": 0.6645,
|
2442 |
+
"step": 7180
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 1.7,
|
2446 |
+
"learning_rate": 0.0001308181096108022,
|
2447 |
+
"loss": 0.6699,
|
2448 |
+
"step": 7200
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 1.7,
|
2452 |
+
"eval_loss": 0.6502068042755127,
|
2453 |
+
"eval_runtime": 49.4619,
|
2454 |
+
"eval_samples_per_second": 40.435,
|
2455 |
+
"eval_steps_per_second": 2.527,
|
2456 |
+
"step": 7200
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 1.71,
|
2460 |
+
"learning_rate": 0.00013034154090548053,
|
2461 |
+
"loss": 0.6617,
|
2462 |
+
"step": 7220
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 1.71,
|
2466 |
+
"learning_rate": 0.00012986497220015885,
|
2467 |
+
"loss": 0.6639,
|
2468 |
+
"step": 7240
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 1.72,
|
2472 |
+
"learning_rate": 0.00012938840349483715,
|
2473 |
+
"loss": 0.6634,
|
2474 |
+
"step": 7260
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.72,
|
2478 |
+
"learning_rate": 0.00012891183478951548,
|
2479 |
+
"loss": 0.663,
|
2480 |
+
"step": 7280
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 1.73,
|
2484 |
+
"learning_rate": 0.00012843526608419378,
|
2485 |
+
"loss": 0.6653,
|
2486 |
+
"step": 7300
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 1.73,
|
2490 |
+
"learning_rate": 0.0001279586973788721,
|
2491 |
+
"loss": 0.6555,
|
2492 |
+
"step": 7320
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 1.74,
|
2496 |
+
"learning_rate": 0.00012748212867355044,
|
2497 |
+
"loss": 0.6653,
|
2498 |
+
"step": 7340
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 1.74,
|
2502 |
+
"learning_rate": 0.00012700555996822874,
|
2503 |
+
"loss": 0.6573,
|
2504 |
+
"step": 7360
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 1.74,
|
2508 |
+
"learning_rate": 0.00012652899126290706,
|
2509 |
+
"loss": 0.658,
|
2510 |
+
"step": 7380
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 1.75,
|
2514 |
+
"learning_rate": 0.0001260524225575854,
|
2515 |
+
"loss": 0.6562,
|
2516 |
+
"step": 7400
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.75,
|
2520 |
+
"eval_loss": 0.6491650342941284,
|
2521 |
+
"eval_runtime": 49.2463,
|
2522 |
+
"eval_samples_per_second": 40.612,
|
2523 |
+
"eval_steps_per_second": 2.538,
|
2524 |
+
"step": 7400
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 1.75,
|
2528 |
+
"learning_rate": 0.0001255758538522637,
|
2529 |
+
"loss": 0.6592,
|
2530 |
+
"step": 7420
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.76,
|
2534 |
+
"learning_rate": 0.000125099285146942,
|
2535 |
+
"loss": 0.6587,
|
2536 |
+
"step": 7440
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 1.76,
|
2540 |
+
"learning_rate": 0.00012462271644162032,
|
2541 |
+
"loss": 0.6616,
|
2542 |
+
"step": 7460
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 1.77,
|
2546 |
+
"learning_rate": 0.00012414614773629865,
|
2547 |
+
"loss": 0.655,
|
2548 |
+
"step": 7480
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 1.77,
|
2552 |
+
"learning_rate": 0.00012366957903097695,
|
2553 |
+
"loss": 0.6591,
|
2554 |
+
"step": 7500
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 1.78,
|
2558 |
+
"learning_rate": 0.00012319301032565527,
|
2559 |
+
"loss": 0.6545,
|
2560 |
+
"step": 7520
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 1.78,
|
2564 |
+
"learning_rate": 0.0001227164416203336,
|
2565 |
+
"loss": 0.6673,
|
2566 |
+
"step": 7540
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 1.79,
|
2570 |
+
"learning_rate": 0.0001222398729150119,
|
2571 |
+
"loss": 0.6626,
|
2572 |
+
"step": 7560
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 1.79,
|
2576 |
+
"learning_rate": 0.00012176330420969023,
|
2577 |
+
"loss": 0.6663,
|
2578 |
+
"step": 7580
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 1.8,
|
2582 |
+
"learning_rate": 0.00012128673550436854,
|
2583 |
+
"loss": 0.6643,
|
2584 |
+
"step": 7600
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 1.8,
|
2588 |
+
"eval_loss": 0.6482685804367065,
|
2589 |
+
"eval_runtime": 49.3591,
|
2590 |
+
"eval_samples_per_second": 40.519,
|
2591 |
+
"eval_steps_per_second": 2.532,
|
2592 |
+
"step": 7600
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 1.8,
|
2596 |
+
"learning_rate": 0.00012081016679904685,
|
2597 |
+
"loss": 0.6623,
|
2598 |
+
"step": 7620
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 1.81,
|
2602 |
+
"learning_rate": 0.00012033359809372518,
|
2603 |
+
"loss": 0.6636,
|
2604 |
+
"step": 7640
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 1.81,
|
2608 |
+
"learning_rate": 0.00011985702938840348,
|
2609 |
+
"loss": 0.6598,
|
2610 |
+
"step": 7660
|
2611 |
+
},
|
2612 |
+
{
|
2613 |
+
"epoch": 1.82,
|
2614 |
+
"learning_rate": 0.0001193804606830818,
|
2615 |
+
"loss": 0.6521,
|
2616 |
+
"step": 7680
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 1.82,
|
2620 |
+
"learning_rate": 0.00011890389197776012,
|
2621 |
+
"loss": 0.664,
|
2622 |
+
"step": 7700
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 1.83,
|
2626 |
+
"learning_rate": 0.00011842732327243844,
|
2627 |
+
"loss": 0.6529,
|
2628 |
+
"step": 7720
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 1.83,
|
2632 |
+
"learning_rate": 0.00011795075456711675,
|
2633 |
+
"loss": 0.6622,
|
2634 |
+
"step": 7740
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 1.83,
|
2638 |
+
"learning_rate": 0.00011747418586179508,
|
2639 |
+
"loss": 0.6608,
|
2640 |
+
"step": 7760
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 1.84,
|
2644 |
+
"learning_rate": 0.00011699761715647338,
|
2645 |
+
"loss": 0.6556,
|
2646 |
+
"step": 7780
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 1.84,
|
2650 |
+
"learning_rate": 0.00011652104845115169,
|
2651 |
+
"loss": 0.6643,
|
2652 |
+
"step": 7800
|
2653 |
+
},
|
2654 |
+
{
|
2655 |
+
"epoch": 1.84,
|
2656 |
+
"eval_loss": 0.6474015116691589,
|
2657 |
+
"eval_runtime": 49.3608,
|
2658 |
+
"eval_samples_per_second": 40.518,
|
2659 |
+
"eval_steps_per_second": 2.532,
|
2660 |
+
"step": 7800
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 1.85,
|
2664 |
+
"learning_rate": 0.00011604447974583002,
|
2665 |
+
"loss": 0.6541,
|
2666 |
+
"step": 7820
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 1.85,
|
2670 |
+
"learning_rate": 0.00011556791104050833,
|
2671 |
+
"loss": 0.6614,
|
2672 |
+
"step": 7840
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 1.86,
|
2676 |
+
"learning_rate": 0.00011509134233518665,
|
2677 |
+
"loss": 0.6499,
|
2678 |
+
"step": 7860
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 1.86,
|
2682 |
+
"learning_rate": 0.00011461477362986497,
|
2683 |
+
"loss": 0.6563,
|
2684 |
+
"step": 7880
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 1.87,
|
2688 |
+
"learning_rate": 0.00011413820492454327,
|
2689 |
+
"loss": 0.6589,
|
2690 |
+
"step": 7900
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 1.87,
|
2694 |
+
"learning_rate": 0.00011366163621922159,
|
2695 |
+
"loss": 0.6544,
|
2696 |
+
"step": 7920
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 1.88,
|
2700 |
+
"learning_rate": 0.00011318506751389992,
|
2701 |
+
"loss": 0.6606,
|
2702 |
+
"step": 7940
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 1.88,
|
2706 |
+
"learning_rate": 0.00011270849880857823,
|
2707 |
+
"loss": 0.657,
|
2708 |
+
"step": 7960
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 1.89,
|
2712 |
+
"learning_rate": 0.00011223193010325654,
|
2713 |
+
"loss": 0.6608,
|
2714 |
+
"step": 7980
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 1.89,
|
2718 |
+
"learning_rate": 0.00011175536139793487,
|
2719 |
+
"loss": 0.6595,
|
2720 |
+
"step": 8000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 1.89,
|
2724 |
+
"eval_loss": 0.6469079256057739,
|
2725 |
+
"eval_runtime": 49.3012,
|
2726 |
+
"eval_samples_per_second": 40.567,
|
2727 |
+
"eval_steps_per_second": 2.535,
|
2728 |
+
"step": 8000
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 1.9,
|
2732 |
+
"learning_rate": 0.00011127879269261318,
|
2733 |
+
"loss": 0.6563,
|
2734 |
+
"step": 8020
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 1.9,
|
2738 |
+
"learning_rate": 0.00011080222398729148,
|
2739 |
+
"loss": 0.6602,
|
2740 |
+
"step": 8040
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 1.91,
|
2744 |
+
"learning_rate": 0.00011032565528196981,
|
2745 |
+
"loss": 0.6603,
|
2746 |
+
"step": 8060
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 1.91,
|
2750 |
+
"learning_rate": 0.00010984908657664812,
|
2751 |
+
"loss": 0.6495,
|
2752 |
+
"step": 8080
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 1.91,
|
2756 |
+
"learning_rate": 0.00010937251787132644,
|
2757 |
+
"loss": 0.6551,
|
2758 |
+
"step": 8100
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 1.92,
|
2762 |
+
"learning_rate": 0.00010891977760127084,
|
2763 |
+
"loss": 0.6497,
|
2764 |
+
"step": 8120
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 1.92,
|
2768 |
+
"learning_rate": 0.00010844320889594917,
|
2769 |
+
"loss": 0.6652,
|
2770 |
+
"step": 8140
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 1.93,
|
2774 |
+
"learning_rate": 0.00010796664019062747,
|
2775 |
+
"loss": 0.6497,
|
2776 |
+
"step": 8160
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 1.93,
|
2780 |
+
"learning_rate": 0.00010749007148530578,
|
2781 |
+
"loss": 0.6554,
|
2782 |
+
"step": 8180
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 1.94,
|
2786 |
+
"learning_rate": 0.00010701350277998411,
|
2787 |
+
"loss": 0.6563,
|
2788 |
+
"step": 8200
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 1.94,
|
2792 |
+
"eval_loss": 0.645990252494812,
|
2793 |
+
"eval_runtime": 49.3957,
|
2794 |
+
"eval_samples_per_second": 40.489,
|
2795 |
+
"eval_steps_per_second": 2.531,
|
2796 |
+
"step": 8200
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 1.94,
|
2800 |
+
"learning_rate": 0.00010653693407466242,
|
2801 |
+
"loss": 0.6572,
|
2802 |
+
"step": 8220
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 1.95,
|
2806 |
+
"learning_rate": 0.00010606036536934074,
|
2807 |
+
"loss": 0.6563,
|
2808 |
+
"step": 8240
|
2809 |
+
},
|
2810 |
+
{
|
2811 |
+
"epoch": 1.95,
|
2812 |
+
"learning_rate": 0.00010558379666401906,
|
2813 |
+
"loss": 0.6535,
|
2814 |
+
"step": 8260
|
2815 |
+
},
|
2816 |
+
{
|
2817 |
+
"epoch": 1.96,
|
2818 |
+
"learning_rate": 0.00010510722795869736,
|
2819 |
+
"loss": 0.655,
|
2820 |
+
"step": 8280
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 1.96,
|
2824 |
+
"learning_rate": 0.00010463065925337568,
|
2825 |
+
"loss": 0.6554,
|
2826 |
+
"step": 8300
|
2827 |
+
},
|
2828 |
+
{
|
2829 |
+
"epoch": 1.97,
|
2830 |
+
"learning_rate": 0.000104154090548054,
|
2831 |
+
"loss": 0.6559,
|
2832 |
+
"step": 8320
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 1.97,
|
2836 |
+
"learning_rate": 0.00010367752184273232,
|
2837 |
+
"loss": 0.6522,
|
2838 |
+
"step": 8340
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 1.98,
|
2842 |
+
"learning_rate": 0.00010320095313741063,
|
2843 |
+
"loss": 0.6568,
|
2844 |
+
"step": 8360
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 1.98,
|
2848 |
+
"learning_rate": 0.00010272438443208896,
|
2849 |
+
"loss": 0.6566,
|
2850 |
+
"step": 8380
|
2851 |
+
},
|
2852 |
+
{
|
2853 |
+
"epoch": 1.99,
|
2854 |
+
"learning_rate": 0.00010224781572676727,
|
2855 |
+
"loss": 0.6496,
|
2856 |
+
"step": 8400
|
2857 |
+
},
|
2858 |
+
{
|
2859 |
+
"epoch": 1.99,
|
2860 |
+
"eval_loss": 0.6457875967025757,
|
2861 |
+
"eval_runtime": 49.0201,
|
2862 |
+
"eval_samples_per_second": 40.8,
|
2863 |
+
"eval_steps_per_second": 2.55,
|
2864 |
+
"step": 8400
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 1.99,
|
2868 |
+
"learning_rate": 0.00010177124702144557,
|
2869 |
+
"loss": 0.66,
|
2870 |
+
"step": 8420
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 2.0,
|
2874 |
+
"learning_rate": 0.0001012946783161239,
|
2875 |
+
"loss": 0.6457,
|
2876 |
+
"step": 8440
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 2.0,
|
2880 |
+
"learning_rate": 0.0001008419380460683,
|
2881 |
+
"loss": 0.6349,
|
2882 |
+
"step": 8460
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 2.0,
|
2886 |
+
"learning_rate": 0.00010036536934074662,
|
2887 |
+
"loss": 0.6545,
|
2888 |
+
"step": 8480
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 2.01,
|
2892 |
+
"learning_rate": 9.988880063542493e-05,
|
2893 |
+
"loss": 0.6515,
|
2894 |
+
"step": 8500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 2.01,
|
2898 |
+
"learning_rate": 9.941223193010326e-05,
|
2899 |
+
"loss": 0.6459,
|
2900 |
+
"step": 8520
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 2.02,
|
2904 |
+
"learning_rate": 9.893566322478156e-05,
|
2905 |
+
"loss": 0.6494,
|
2906 |
+
"step": 8540
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 2.02,
|
2910 |
+
"learning_rate": 9.845909451945987e-05,
|
2911 |
+
"loss": 0.6608,
|
2912 |
+
"step": 8560
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 2.03,
|
2916 |
+
"learning_rate": 9.79825258141382e-05,
|
2917 |
+
"loss": 0.6485,
|
2918 |
+
"step": 8580
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 2.03,
|
2922 |
+
"learning_rate": 9.750595710881651e-05,
|
2923 |
+
"loss": 0.6461,
|
2924 |
+
"step": 8600
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 2.03,
|
2928 |
+
"eval_loss": 0.6450995802879333,
|
2929 |
+
"eval_runtime": 49.2592,
|
2930 |
+
"eval_samples_per_second": 40.602,
|
2931 |
+
"eval_steps_per_second": 2.538,
|
2932 |
+
"step": 8600
|
2933 |
+
},
|
2934 |
+
{
|
2935 |
+
"epoch": 2.04,
|
2936 |
+
"learning_rate": 9.702938840349483e-05,
|
2937 |
+
"loss": 0.6523,
|
2938 |
+
"step": 8620
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 2.04,
|
2942 |
+
"learning_rate": 9.655281969817315e-05,
|
2943 |
+
"loss": 0.6565,
|
2944 |
+
"step": 8640
|
2945 |
+
},
|
2946 |
+
{
|
2947 |
+
"epoch": 2.05,
|
2948 |
+
"learning_rate": 9.607625099285145e-05,
|
2949 |
+
"loss": 0.6541,
|
2950 |
+
"step": 8660
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 2.05,
|
2954 |
+
"learning_rate": 9.559968228752977e-05,
|
2955 |
+
"loss": 0.6585,
|
2956 |
+
"step": 8680
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 2.06,
|
2960 |
+
"learning_rate": 9.51231135822081e-05,
|
2961 |
+
"loss": 0.6531,
|
2962 |
+
"step": 8700
|
2963 |
+
},
|
2964 |
+
{
|
2965 |
+
"epoch": 2.06,
|
2966 |
+
"learning_rate": 9.464654487688641e-05,
|
2967 |
+
"loss": 0.6579,
|
2968 |
+
"step": 8720
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 2.07,
|
2972 |
+
"learning_rate": 9.416997617156472e-05,
|
2973 |
+
"loss": 0.6438,
|
2974 |
+
"step": 8740
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 2.07,
|
2978 |
+
"learning_rate": 9.369340746624305e-05,
|
2979 |
+
"loss": 0.6516,
|
2980 |
+
"step": 8760
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 2.08,
|
2984 |
+
"learning_rate": 9.321683876092136e-05,
|
2985 |
+
"loss": 0.6576,
|
2986 |
+
"step": 8780
|
2987 |
+
},
|
2988 |
+
{
|
2989 |
+
"epoch": 2.08,
|
2990 |
+
"learning_rate": 9.274027005559966e-05,
|
2991 |
+
"loss": 0.6506,
|
2992 |
+
"step": 8800
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 2.08,
|
2996 |
+
"eval_loss": 0.6444578170776367,
|
2997 |
+
"eval_runtime": 49.0631,
|
2998 |
+
"eval_samples_per_second": 40.764,
|
2999 |
+
"eval_steps_per_second": 2.548,
|
3000 |
+
"step": 8800
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 2.09,
|
3004 |
+
"learning_rate": 9.226370135027799e-05,
|
3005 |
+
"loss": 0.6484,
|
3006 |
+
"step": 8820
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 2.09,
|
3010 |
+
"learning_rate": 9.17871326449563e-05,
|
3011 |
+
"loss": 0.6566,
|
3012 |
+
"step": 8840
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 2.09,
|
3016 |
+
"learning_rate": 9.131056393963462e-05,
|
3017 |
+
"loss": 0.6547,
|
3018 |
+
"step": 8860
|
3019 |
+
},
|
3020 |
+
{
|
3021 |
+
"epoch": 2.1,
|
3022 |
+
"learning_rate": 9.083399523431295e-05,
|
3023 |
+
"loss": 0.6532,
|
3024 |
+
"step": 8880
|
3025 |
+
},
|
3026 |
+
{
|
3027 |
+
"epoch": 2.1,
|
3028 |
+
"learning_rate": 9.035742652899126e-05,
|
3029 |
+
"loss": 0.6532,
|
3030 |
+
"step": 8900
|
3031 |
+
},
|
3032 |
+
{
|
3033 |
+
"epoch": 2.11,
|
3034 |
+
"learning_rate": 8.988085782366956e-05,
|
3035 |
+
"loss": 0.6479,
|
3036 |
+
"step": 8920
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 2.11,
|
3040 |
+
"learning_rate": 8.940428911834789e-05,
|
3041 |
+
"loss": 0.6548,
|
3042 |
+
"step": 8940
|
3043 |
+
},
|
3044 |
+
{
|
3045 |
+
"epoch": 2.12,
|
3046 |
+
"learning_rate": 8.89277204130262e-05,
|
3047 |
+
"loss": 0.647,
|
3048 |
+
"step": 8960
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 2.12,
|
3052 |
+
"learning_rate": 8.845115170770452e-05,
|
3053 |
+
"loss": 0.6478,
|
3054 |
+
"step": 8980
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 2.13,
|
3058 |
+
"learning_rate": 8.797458300238284e-05,
|
3059 |
+
"loss": 0.6553,
|
3060 |
+
"step": 9000
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 2.13,
|
3064 |
+
"eval_loss": 0.6433074474334717,
|
3065 |
+
"eval_runtime": 49.3831,
|
3066 |
+
"eval_samples_per_second": 40.5,
|
3067 |
+
"eval_steps_per_second": 2.531,
|
3068 |
+
"step": 9000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 2.13,
|
3072 |
+
"learning_rate": 8.749801429706116e-05,
|
3073 |
+
"loss": 0.6443,
|
3074 |
+
"step": 9020
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 2.14,
|
3078 |
+
"learning_rate": 8.702144559173947e-05,
|
3079 |
+
"loss": 0.6518,
|
3080 |
+
"step": 9040
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 2.14,
|
3084 |
+
"learning_rate": 8.65448768864178e-05,
|
3085 |
+
"loss": 0.6578,
|
3086 |
+
"step": 9060
|
3087 |
+
},
|
3088 |
+
{
|
3089 |
+
"epoch": 2.15,
|
3090 |
+
"learning_rate": 8.60683081810961e-05,
|
3091 |
+
"loss": 0.6472,
|
3092 |
+
"step": 9080
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 2.15,
|
3096 |
+
"learning_rate": 8.559173947577441e-05,
|
3097 |
+
"loss": 0.6471,
|
3098 |
+
"step": 9100
|
3099 |
+
},
|
3100 |
+
{
|
3101 |
+
"epoch": 2.16,
|
3102 |
+
"learning_rate": 8.511517077045274e-05,
|
3103 |
+
"loss": 0.6482,
|
3104 |
+
"step": 9120
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 2.16,
|
3108 |
+
"learning_rate": 8.463860206513105e-05,
|
3109 |
+
"loss": 0.6522,
|
3110 |
+
"step": 9140
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 2.17,
|
3114 |
+
"learning_rate": 8.416203335980937e-05,
|
3115 |
+
"loss": 0.6584,
|
3116 |
+
"step": 9160
|
3117 |
+
},
|
3118 |
+
{
|
3119 |
+
"epoch": 2.17,
|
3120 |
+
"learning_rate": 8.368546465448769e-05,
|
3121 |
+
"loss": 0.6596,
|
3122 |
+
"step": 9180
|
3123 |
+
},
|
3124 |
+
{
|
3125 |
+
"epoch": 2.17,
|
3126 |
+
"learning_rate": 8.320889594916599e-05,
|
3127 |
+
"loss": 0.6581,
|
3128 |
+
"step": 9200
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 2.17,
|
3132 |
+
"eval_loss": 0.6426697969436646,
|
3133 |
+
"eval_runtime": 49.0935,
|
3134 |
+
"eval_samples_per_second": 40.739,
|
3135 |
+
"eval_steps_per_second": 2.546,
|
3136 |
+
"step": 9200
|
3137 |
+
},
|
3138 |
+
{
|
3139 |
+
"epoch": 2.18,
|
3140 |
+
"learning_rate": 8.273232724384431e-05,
|
3141 |
+
"loss": 0.6441,
|
3142 |
+
"step": 9220
|
3143 |
+
},
|
3144 |
+
{
|
3145 |
+
"epoch": 2.18,
|
3146 |
+
"learning_rate": 8.225575853852263e-05,
|
3147 |
+
"loss": 0.6509,
|
3148 |
+
"step": 9240
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 2.19,
|
3152 |
+
"learning_rate": 8.177918983320095e-05,
|
3153 |
+
"loss": 0.6409,
|
3154 |
+
"step": 9260
|
3155 |
+
},
|
3156 |
+
{
|
3157 |
+
"epoch": 2.19,
|
3158 |
+
"learning_rate": 8.130262112787926e-05,
|
3159 |
+
"loss": 0.6475,
|
3160 |
+
"step": 9280
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 2.2,
|
3164 |
+
"learning_rate": 8.082605242255759e-05,
|
3165 |
+
"loss": 0.6597,
|
3166 |
+
"step": 9300
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 2.2,
|
3170 |
+
"learning_rate": 8.03494837172359e-05,
|
3171 |
+
"loss": 0.6544,
|
3172 |
+
"step": 9320
|
3173 |
+
},
|
3174 |
+
{
|
3175 |
+
"epoch": 2.21,
|
3176 |
+
"learning_rate": 7.98729150119142e-05,
|
3177 |
+
"loss": 0.6528,
|
3178 |
+
"step": 9340
|
3179 |
+
},
|
3180 |
+
{
|
3181 |
+
"epoch": 2.21,
|
3182 |
+
"learning_rate": 7.939634630659253e-05,
|
3183 |
+
"loss": 0.644,
|
3184 |
+
"step": 9360
|
3185 |
+
},
|
3186 |
+
{
|
3187 |
+
"epoch": 2.22,
|
3188 |
+
"learning_rate": 7.891977760127084e-05,
|
3189 |
+
"loss": 0.6552,
|
3190 |
+
"step": 9380
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 2.22,
|
3194 |
+
"learning_rate": 7.844320889594916e-05,
|
3195 |
+
"loss": 0.6548,
|
3196 |
+
"step": 9400
|
3197 |
+
},
|
3198 |
+
{
|
3199 |
+
"epoch": 2.22,
|
3200 |
+
"eval_loss": 0.6423606276512146,
|
3201 |
+
"eval_runtime": 49.6466,
|
3202 |
+
"eval_samples_per_second": 40.285,
|
3203 |
+
"eval_steps_per_second": 2.518,
|
3204 |
+
"step": 9400
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 2.23,
|
3208 |
+
"learning_rate": 7.796664019062748e-05,
|
3209 |
+
"loss": 0.6568,
|
3210 |
+
"step": 9420
|
3211 |
+
},
|
3212 |
+
{
|
3213 |
+
"epoch": 2.23,
|
3214 |
+
"learning_rate": 7.74900714853058e-05,
|
3215 |
+
"loss": 0.6539,
|
3216 |
+
"step": 9440
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 2.24,
|
3220 |
+
"learning_rate": 7.70135027799841e-05,
|
3221 |
+
"loss": 0.6468,
|
3222 |
+
"step": 9460
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 2.24,
|
3226 |
+
"learning_rate": 7.653693407466243e-05,
|
3227 |
+
"loss": 0.6425,
|
3228 |
+
"step": 9480
|
3229 |
+
},
|
3230 |
+
{
|
3231 |
+
"epoch": 2.25,
|
3232 |
+
"learning_rate": 7.606036536934074e-05,
|
3233 |
+
"loss": 0.6523,
|
3234 |
+
"step": 9500
|
3235 |
+
},
|
3236 |
+
{
|
3237 |
+
"epoch": 2.25,
|
3238 |
+
"learning_rate": 7.558379666401905e-05,
|
3239 |
+
"loss": 0.6468,
|
3240 |
+
"step": 9520
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 2.26,
|
3244 |
+
"learning_rate": 7.510722795869738e-05,
|
3245 |
+
"loss": 0.6518,
|
3246 |
+
"step": 9540
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 2.26,
|
3250 |
+
"learning_rate": 7.46306592533757e-05,
|
3251 |
+
"loss": 0.6534,
|
3252 |
+
"step": 9560
|
3253 |
+
},
|
3254 |
+
{
|
3255 |
+
"epoch": 2.26,
|
3256 |
+
"learning_rate": 7.415409054805401e-05,
|
3257 |
+
"loss": 0.6471,
|
3258 |
+
"step": 9580
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 2.27,
|
3262 |
+
"learning_rate": 7.367752184273232e-05,
|
3263 |
+
"loss": 0.6465,
|
3264 |
+
"step": 9600
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 2.27,
|
3268 |
+
"eval_loss": 0.6418060064315796,
|
3269 |
+
"eval_runtime": 49.4954,
|
3270 |
+
"eval_samples_per_second": 40.408,
|
3271 |
+
"eval_steps_per_second": 2.525,
|
3272 |
+
"step": 9600
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 2.27,
|
3276 |
+
"learning_rate": 7.320095313741064e-05,
|
3277 |
+
"loss": 0.6577,
|
3278 |
+
"step": 9620
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 2.28,
|
3282 |
+
"learning_rate": 7.272438443208895e-05,
|
3283 |
+
"loss": 0.6453,
|
3284 |
+
"step": 9640
|
3285 |
+
},
|
3286 |
+
{
|
3287 |
+
"epoch": 2.28,
|
3288 |
+
"learning_rate": 7.224781572676726e-05,
|
3289 |
+
"loss": 0.6489,
|
3290 |
+
"step": 9660
|
3291 |
+
},
|
3292 |
+
{
|
3293 |
+
"epoch": 2.29,
|
3294 |
+
"learning_rate": 7.177124702144559e-05,
|
3295 |
+
"loss": 0.6466,
|
3296 |
+
"step": 9680
|
3297 |
+
},
|
3298 |
+
{
|
3299 |
+
"epoch": 2.29,
|
3300 |
+
"learning_rate": 7.12946783161239e-05,
|
3301 |
+
"loss": 0.6493,
|
3302 |
+
"step": 9700
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 2.3,
|
3306 |
+
"learning_rate": 7.081810961080222e-05,
|
3307 |
+
"loss": 0.6537,
|
3308 |
+
"step": 9720
|
3309 |
+
},
|
3310 |
+
{
|
3311 |
+
"epoch": 2.3,
|
3312 |
+
"learning_rate": 7.034154090548053e-05,
|
3313 |
+
"loss": 0.6486,
|
3314 |
+
"step": 9740
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 2.31,
|
3318 |
+
"learning_rate": 6.986497220015885e-05,
|
3319 |
+
"loss": 0.65,
|
3320 |
+
"step": 9760
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 2.31,
|
3324 |
+
"learning_rate": 6.938840349483717e-05,
|
3325 |
+
"loss": 0.6387,
|
3326 |
+
"step": 9780
|
3327 |
+
},
|
3328 |
+
{
|
3329 |
+
"epoch": 2.32,
|
3330 |
+
"learning_rate": 6.891183478951549e-05,
|
3331 |
+
"loss": 0.6464,
|
3332 |
+
"step": 9800
|
3333 |
+
},
|
3334 |
+
{
|
3335 |
+
"epoch": 2.32,
|
3336 |
+
"eval_loss": 0.6412256360054016,
|
3337 |
+
"eval_runtime": 49.3752,
|
3338 |
+
"eval_samples_per_second": 40.506,
|
3339 |
+
"eval_steps_per_second": 2.532,
|
3340 |
+
"step": 9800
|
3341 |
+
},
|
3342 |
+
{
|
3343 |
+
"epoch": 2.32,
|
3344 |
+
"learning_rate": 6.84352660841938e-05,
|
3345 |
+
"loss": 0.6475,
|
3346 |
+
"step": 9820
|
3347 |
+
},
|
3348 |
+
{
|
3349 |
+
"epoch": 2.33,
|
3350 |
+
"learning_rate": 6.795869737887211e-05,
|
3351 |
+
"loss": 0.6543,
|
3352 |
+
"step": 9840
|
3353 |
+
},
|
3354 |
+
{
|
3355 |
+
"epoch": 2.33,
|
3356 |
+
"learning_rate": 6.748212867355043e-05,
|
3357 |
+
"loss": 0.6545,
|
3358 |
+
"step": 9860
|
3359 |
+
},
|
3360 |
+
{
|
3361 |
+
"epoch": 2.34,
|
3362 |
+
"learning_rate": 6.700555996822874e-05,
|
3363 |
+
"loss": 0.6468,
|
3364 |
+
"step": 9880
|
3365 |
+
},
|
3366 |
+
{
|
3367 |
+
"epoch": 2.34,
|
3368 |
+
"learning_rate": 6.652899126290707e-05,
|
3369 |
+
"loss": 0.651,
|
3370 |
+
"step": 9900
|
3371 |
+
},
|
3372 |
+
{
|
3373 |
+
"epoch": 2.35,
|
3374 |
+
"learning_rate": 6.605242255758538e-05,
|
3375 |
+
"loss": 0.641,
|
3376 |
+
"step": 9920
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 2.35,
|
3380 |
+
"learning_rate": 6.55758538522637e-05,
|
3381 |
+
"loss": 0.657,
|
3382 |
+
"step": 9940
|
3383 |
+
},
|
3384 |
+
{
|
3385 |
+
"epoch": 2.35,
|
3386 |
+
"learning_rate": 6.509928514694201e-05,
|
3387 |
+
"loss": 0.6481,
|
3388 |
+
"step": 9960
|
3389 |
+
},
|
3390 |
+
{
|
3391 |
+
"epoch": 2.36,
|
3392 |
+
"learning_rate": 6.462271644162034e-05,
|
3393 |
+
"loss": 0.6496,
|
3394 |
+
"step": 9980
|
3395 |
+
},
|
3396 |
+
{
|
3397 |
+
"epoch": 2.36,
|
3398 |
+
"learning_rate": 6.414614773629864e-05,
|
3399 |
+
"loss": 0.6451,
|
3400 |
+
"step": 10000
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 2.36,
|
3404 |
+
"eval_loss": 0.6414454579353333,
|
3405 |
+
"eval_runtime": 49.395,
|
3406 |
+
"eval_samples_per_second": 40.49,
|
3407 |
+
"eval_steps_per_second": 2.531,
|
3408 |
+
"step": 10000
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 2.37,
|
3412 |
+
"learning_rate": 6.366957903097696e-05,
|
3413 |
+
"loss": 0.6555,
|
3414 |
+
"step": 10020
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 2.37,
|
3418 |
+
"learning_rate": 6.319301032565528e-05,
|
3419 |
+
"loss": 0.6494,
|
3420 |
+
"step": 10040
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 2.38,
|
3424 |
+
"learning_rate": 6.271644162033359e-05,
|
3425 |
+
"loss": 0.6487,
|
3426 |
+
"step": 10060
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 2.38,
|
3430 |
+
"learning_rate": 6.22398729150119e-05,
|
3431 |
+
"loss": 0.6544,
|
3432 |
+
"step": 10080
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 2.39,
|
3436 |
+
"learning_rate": 6.176330420969023e-05,
|
3437 |
+
"loss": 0.6468,
|
3438 |
+
"step": 10100
|
3439 |
+
},
|
3440 |
+
{
|
3441 |
+
"epoch": 2.39,
|
3442 |
+
"learning_rate": 6.128673550436853e-05,
|
3443 |
+
"loss": 0.6441,
|
3444 |
+
"step": 10120
|
3445 |
+
},
|
3446 |
+
{
|
3447 |
+
"epoch": 2.4,
|
3448 |
+
"learning_rate": 6.081016679904686e-05,
|
3449 |
+
"loss": 0.6478,
|
3450 |
+
"step": 10140
|
3451 |
+
},
|
3452 |
+
{
|
3453 |
+
"epoch": 2.4,
|
3454 |
+
"learning_rate": 6.033359809372518e-05,
|
3455 |
+
"loss": 0.6539,
|
3456 |
+
"step": 10160
|
3457 |
+
},
|
3458 |
+
{
|
3459 |
+
"epoch": 2.41,
|
3460 |
+
"learning_rate": 5.985702938840349e-05,
|
3461 |
+
"loss": 0.6486,
|
3462 |
+
"step": 10180
|
3463 |
+
},
|
3464 |
+
{
|
3465 |
+
"epoch": 2.41,
|
3466 |
+
"learning_rate": 5.938046068308181e-05,
|
3467 |
+
"loss": 0.6467,
|
3468 |
+
"step": 10200
|
3469 |
+
},
|
3470 |
+
{
|
3471 |
+
"epoch": 2.41,
|
3472 |
+
"eval_loss": 0.6406835913658142,
|
3473 |
+
"eval_runtime": 49.5084,
|
3474 |
+
"eval_samples_per_second": 40.397,
|
3475 |
+
"eval_steps_per_second": 2.525,
|
3476 |
+
"step": 10200
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 2.42,
|
3480 |
+
"learning_rate": 5.890389197776013e-05,
|
3481 |
+
"loss": 0.6399,
|
3482 |
+
"step": 10220
|
3483 |
+
},
|
3484 |
+
{
|
3485 |
+
"epoch": 2.42,
|
3486 |
+
"learning_rate": 5.8427323272438435e-05,
|
3487 |
+
"loss": 0.6519,
|
3488 |
+
"step": 10240
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 2.43,
|
3492 |
+
"learning_rate": 5.7950754567116756e-05,
|
3493 |
+
"loss": 0.6465,
|
3494 |
+
"step": 10260
|
3495 |
+
},
|
3496 |
+
{
|
3497 |
+
"epoch": 2.43,
|
3498 |
+
"learning_rate": 5.7474185861795076e-05,
|
3499 |
+
"loss": 0.6479,
|
3500 |
+
"step": 10280
|
3501 |
+
},
|
3502 |
+
{
|
3503 |
+
"epoch": 2.43,
|
3504 |
+
"learning_rate": 5.6997617156473383e-05,
|
3505 |
+
"loss": 0.6462,
|
3506 |
+
"step": 10300
|
3507 |
+
},
|
3508 |
+
{
|
3509 |
+
"epoch": 2.44,
|
3510 |
+
"learning_rate": 5.6521048451151704e-05,
|
3511 |
+
"loss": 0.6451,
|
3512 |
+
"step": 10320
|
3513 |
+
},
|
3514 |
+
{
|
3515 |
+
"epoch": 2.44,
|
3516 |
+
"learning_rate": 5.604447974583002e-05,
|
3517 |
+
"loss": 0.6453,
|
3518 |
+
"step": 10340
|
3519 |
+
},
|
3520 |
+
{
|
3521 |
+
"epoch": 2.45,
|
3522 |
+
"learning_rate": 5.556791104050833e-05,
|
3523 |
+
"loss": 0.6543,
|
3524 |
+
"step": 10360
|
3525 |
+
},
|
3526 |
+
{
|
3527 |
+
"epoch": 2.45,
|
3528 |
+
"learning_rate": 5.509134233518665e-05,
|
3529 |
+
"loss": 0.6428,
|
3530 |
+
"step": 10380
|
3531 |
+
},
|
3532 |
+
{
|
3533 |
+
"epoch": 2.46,
|
3534 |
+
"learning_rate": 5.4614773629864966e-05,
|
3535 |
+
"loss": 0.6491,
|
3536 |
+
"step": 10400
|
3537 |
+
},
|
3538 |
+
{
|
3539 |
+
"epoch": 2.46,
|
3540 |
+
"eval_loss": 0.6400973796844482,
|
3541 |
+
"eval_runtime": 49.3411,
|
3542 |
+
"eval_samples_per_second": 40.534,
|
3543 |
+
"eval_steps_per_second": 2.533,
|
3544 |
+
"step": 10400
|
3545 |
+
},
|
3546 |
+
{
|
3547 |
+
"epoch": 2.46,
|
3548 |
+
"learning_rate": 5.413820492454328e-05,
|
3549 |
+
"loss": 0.649,
|
3550 |
+
"step": 10420
|
3551 |
+
},
|
3552 |
+
{
|
3553 |
+
"epoch": 2.47,
|
3554 |
+
"learning_rate": 5.36616362192216e-05,
|
3555 |
+
"loss": 0.6494,
|
3556 |
+
"step": 10440
|
3557 |
+
},
|
3558 |
+
{
|
3559 |
+
"epoch": 2.47,
|
3560 |
+
"learning_rate": 5.3185067513899913e-05,
|
3561 |
+
"loss": 0.6431,
|
3562 |
+
"step": 10460
|
3563 |
+
},
|
3564 |
+
{
|
3565 |
+
"epoch": 2.48,
|
3566 |
+
"learning_rate": 5.2708498808578234e-05,
|
3567 |
+
"loss": 0.6478,
|
3568 |
+
"step": 10480
|
3569 |
+
},
|
3570 |
+
{
|
3571 |
+
"epoch": 2.48,
|
3572 |
+
"learning_rate": 5.223193010325655e-05,
|
3573 |
+
"loss": 0.6416,
|
3574 |
+
"step": 10500
|
3575 |
+
},
|
3576 |
+
{
|
3577 |
+
"epoch": 2.49,
|
3578 |
+
"learning_rate": 5.175536139793486e-05,
|
3579 |
+
"loss": 0.6507,
|
3580 |
+
"step": 10520
|
3581 |
+
},
|
3582 |
+
{
|
3583 |
+
"epoch": 2.49,
|
3584 |
+
"learning_rate": 5.127879269261318e-05,
|
3585 |
+
"loss": 0.6448,
|
3586 |
+
"step": 10540
|
3587 |
+
},
|
3588 |
+
{
|
3589 |
+
"epoch": 2.5,
|
3590 |
+
"learning_rate": 5.0802223987291496e-05,
|
3591 |
+
"loss": 0.6455,
|
3592 |
+
"step": 10560
|
3593 |
+
},
|
3594 |
+
{
|
3595 |
+
"epoch": 2.5,
|
3596 |
+
"learning_rate": 5.032565528196981e-05,
|
3597 |
+
"loss": 0.6437,
|
3598 |
+
"step": 10580
|
3599 |
+
},
|
3600 |
+
{
|
3601 |
+
"epoch": 2.51,
|
3602 |
+
"learning_rate": 4.984908657664813e-05,
|
3603 |
+
"loss": 0.6488,
|
3604 |
+
"step": 10600
|
3605 |
+
},
|
3606 |
+
{
|
3607 |
+
"epoch": 2.51,
|
3608 |
+
"eval_loss": 0.6400858163833618,
|
3609 |
+
"eval_runtime": 49.8084,
|
3610 |
+
"eval_samples_per_second": 40.154,
|
3611 |
+
"eval_steps_per_second": 2.51,
|
3612 |
+
"step": 10600
|
3613 |
+
},
|
3614 |
+
{
|
3615 |
+
"epoch": 2.51,
|
3616 |
+
"learning_rate": 4.937251787132645e-05,
|
3617 |
+
"loss": 0.6436,
|
3618 |
+
"step": 10620
|
3619 |
+
},
|
3620 |
+
{
|
3621 |
+
"epoch": 2.52,
|
3622 |
+
"learning_rate": 4.889594916600476e-05,
|
3623 |
+
"loss": 0.6446,
|
3624 |
+
"step": 10640
|
3625 |
+
},
|
3626 |
+
{
|
3627 |
+
"epoch": 2.52,
|
3628 |
+
"learning_rate": 4.841938046068308e-05,
|
3629 |
+
"loss": 0.6488,
|
3630 |
+
"step": 10660
|
3631 |
+
},
|
3632 |
+
{
|
3633 |
+
"epoch": 2.52,
|
3634 |
+
"learning_rate": 4.79428117553614e-05,
|
3635 |
+
"loss": 0.6485,
|
3636 |
+
"step": 10680
|
3637 |
+
},
|
3638 |
+
{
|
3639 |
+
"epoch": 2.53,
|
3640 |
+
"learning_rate": 4.7466243050039705e-05,
|
3641 |
+
"loss": 0.6524,
|
3642 |
+
"step": 10700
|
3643 |
+
},
|
3644 |
+
{
|
3645 |
+
"epoch": 2.53,
|
3646 |
+
"learning_rate": 4.6989674344718026e-05,
|
3647 |
+
"loss": 0.6376,
|
3648 |
+
"step": 10720
|
3649 |
+
},
|
3650 |
+
{
|
3651 |
+
"epoch": 2.54,
|
3652 |
+
"learning_rate": 4.6513105639396346e-05,
|
3653 |
+
"loss": 0.649,
|
3654 |
+
"step": 10740
|
3655 |
+
},
|
3656 |
+
{
|
3657 |
+
"epoch": 2.54,
|
3658 |
+
"learning_rate": 4.603653693407465e-05,
|
3659 |
+
"loss": 0.6444,
|
3660 |
+
"step": 10760
|
3661 |
+
},
|
3662 |
+
{
|
3663 |
+
"epoch": 2.55,
|
3664 |
+
"learning_rate": 4.5559968228752974e-05,
|
3665 |
+
"loss": 0.6407,
|
3666 |
+
"step": 10780
|
3667 |
+
},
|
3668 |
+
{
|
3669 |
+
"epoch": 2.55,
|
3670 |
+
"learning_rate": 4.5083399523431294e-05,
|
3671 |
+
"loss": 0.6448,
|
3672 |
+
"step": 10800
|
3673 |
+
},
|
3674 |
+
{
|
3675 |
+
"epoch": 2.55,
|
3676 |
+
"eval_loss": 0.6392157077789307,
|
3677 |
+
"eval_runtime": 49.7963,
|
3678 |
+
"eval_samples_per_second": 40.164,
|
3679 |
+
"eval_steps_per_second": 2.51,
|
3680 |
+
"step": 10800
|
3681 |
+
},
|
3682 |
+
{
|
3683 |
+
"epoch": 2.56,
|
3684 |
+
"learning_rate": 4.46068308181096e-05,
|
3685 |
+
"loss": 0.6454,
|
3686 |
+
"step": 10820
|
3687 |
+
},
|
3688 |
+
{
|
3689 |
+
"epoch": 2.56,
|
3690 |
+
"learning_rate": 4.413026211278792e-05,
|
3691 |
+
"loss": 0.6544,
|
3692 |
+
"step": 10840
|
3693 |
+
},
|
3694 |
+
{
|
3695 |
+
"epoch": 2.57,
|
3696 |
+
"learning_rate": 4.365369340746624e-05,
|
3697 |
+
"loss": 0.6478,
|
3698 |
+
"step": 10860
|
3699 |
+
},
|
3700 |
+
{
|
3701 |
+
"epoch": 2.57,
|
3702 |
+
"learning_rate": 4.3177124702144556e-05,
|
3703 |
+
"loss": 0.6434,
|
3704 |
+
"step": 10880
|
3705 |
+
},
|
3706 |
+
{
|
3707 |
+
"epoch": 2.58,
|
3708 |
+
"learning_rate": 4.270055599682287e-05,
|
3709 |
+
"loss": 0.6482,
|
3710 |
+
"step": 10900
|
3711 |
+
},
|
3712 |
+
{
|
3713 |
+
"epoch": 2.58,
|
3714 |
+
"learning_rate": 4.222398729150119e-05,
|
3715 |
+
"loss": 0.6403,
|
3716 |
+
"step": 10920
|
3717 |
+
},
|
3718 |
+
{
|
3719 |
+
"epoch": 2.59,
|
3720 |
+
"learning_rate": 4.1747418586179504e-05,
|
3721 |
+
"loss": 0.6501,
|
3722 |
+
"step": 10940
|
3723 |
+
},
|
3724 |
+
{
|
3725 |
+
"epoch": 2.59,
|
3726 |
+
"learning_rate": 4.127084988085782e-05,
|
3727 |
+
"loss": 0.6507,
|
3728 |
+
"step": 10960
|
3729 |
+
},
|
3730 |
+
{
|
3731 |
+
"epoch": 2.6,
|
3732 |
+
"learning_rate": 4.079428117553614e-05,
|
3733 |
+
"loss": 0.6496,
|
3734 |
+
"step": 10980
|
3735 |
+
},
|
3736 |
+
{
|
3737 |
+
"epoch": 2.6,
|
3738 |
+
"learning_rate": 4.031771247021445e-05,
|
3739 |
+
"loss": 0.6544,
|
3740 |
+
"step": 11000
|
3741 |
+
},
|
3742 |
+
{
|
3743 |
+
"epoch": 2.6,
|
3744 |
+
"eval_loss": 0.6390016078948975,
|
3745 |
+
"eval_runtime": 49.6306,
|
3746 |
+
"eval_samples_per_second": 40.298,
|
3747 |
+
"eval_steps_per_second": 2.519,
|
3748 |
+
"step": 11000
|
3749 |
+
},
|
3750 |
+
{
|
3751 |
+
"epoch": 2.61,
|
3752 |
+
"learning_rate": 3.984114376489277e-05,
|
3753 |
+
"loss": 0.6405,
|
3754 |
+
"step": 11020
|
3755 |
+
},
|
3756 |
+
{
|
3757 |
+
"epoch": 2.61,
|
3758 |
+
"learning_rate": 3.9364575059571086e-05,
|
3759 |
+
"loss": 0.6429,
|
3760 |
+
"step": 11040
|
3761 |
+
},
|
3762 |
+
{
|
3763 |
+
"epoch": 2.61,
|
3764 |
+
"learning_rate": 3.88880063542494e-05,
|
3765 |
+
"loss": 0.6403,
|
3766 |
+
"step": 11060
|
3767 |
+
},
|
3768 |
+
{
|
3769 |
+
"epoch": 2.62,
|
3770 |
+
"learning_rate": 3.841143764892772e-05,
|
3771 |
+
"loss": 0.6338,
|
3772 |
+
"step": 11080
|
3773 |
+
},
|
3774 |
+
{
|
3775 |
+
"epoch": 2.62,
|
3776 |
+
"learning_rate": 3.7934868943606034e-05,
|
3777 |
+
"loss": 0.6417,
|
3778 |
+
"step": 11100
|
3779 |
+
},
|
3780 |
+
{
|
3781 |
+
"epoch": 2.63,
|
3782 |
+
"learning_rate": 3.7458300238284354e-05,
|
3783 |
+
"loss": 0.6463,
|
3784 |
+
"step": 11120
|
3785 |
+
},
|
3786 |
+
{
|
3787 |
+
"epoch": 2.63,
|
3788 |
+
"learning_rate": 3.698173153296267e-05,
|
3789 |
+
"loss": 0.6498,
|
3790 |
+
"step": 11140
|
3791 |
+
},
|
3792 |
+
{
|
3793 |
+
"epoch": 2.64,
|
3794 |
+
"learning_rate": 3.650516282764098e-05,
|
3795 |
+
"loss": 0.6415,
|
3796 |
+
"step": 11160
|
3797 |
+
},
|
3798 |
+
{
|
3799 |
+
"epoch": 2.64,
|
3800 |
+
"learning_rate": 3.6028594122319296e-05,
|
3801 |
+
"loss": 0.645,
|
3802 |
+
"step": 11180
|
3803 |
+
},
|
3804 |
+
{
|
3805 |
+
"epoch": 2.65,
|
3806 |
+
"learning_rate": 3.5552025416997616e-05,
|
3807 |
+
"loss": 0.6467,
|
3808 |
+
"step": 11200
|
3809 |
+
},
|
3810 |
+
{
|
3811 |
+
"epoch": 2.65,
|
3812 |
+
"eval_loss": 0.6387213468551636,
|
3813 |
+
"eval_runtime": 49.1775,
|
3814 |
+
"eval_samples_per_second": 40.669,
|
3815 |
+
"eval_steps_per_second": 2.542,
|
3816 |
+
"step": 11200
|
3817 |
+
},
|
3818 |
+
{
|
3819 |
+
"epoch": 2.65,
|
3820 |
+
"learning_rate": 3.507545671167593e-05,
|
3821 |
+
"loss": 0.6515,
|
3822 |
+
"step": 11220
|
3823 |
+
},
|
3824 |
+
{
|
3825 |
+
"epoch": 2.66,
|
3826 |
+
"learning_rate": 3.4598888006354244e-05,
|
3827 |
+
"loss": 0.65,
|
3828 |
+
"step": 11240
|
3829 |
+
},
|
3830 |
+
{
|
3831 |
+
"epoch": 2.66,
|
3832 |
+
"learning_rate": 3.4122319301032564e-05,
|
3833 |
+
"loss": 0.6512,
|
3834 |
+
"step": 11260
|
3835 |
+
},
|
3836 |
+
{
|
3837 |
+
"epoch": 2.67,
|
3838 |
+
"learning_rate": 3.364575059571088e-05,
|
3839 |
+
"loss": 0.6443,
|
3840 |
+
"step": 11280
|
3841 |
+
},
|
3842 |
+
{
|
3843 |
+
"epoch": 2.67,
|
3844 |
+
"learning_rate": 3.316918189038919e-05,
|
3845 |
+
"loss": 0.6483,
|
3846 |
+
"step": 11300
|
3847 |
+
},
|
3848 |
+
{
|
3849 |
+
"epoch": 2.68,
|
3850 |
+
"learning_rate": 3.269261318506751e-05,
|
3851 |
+
"loss": 0.6455,
|
3852 |
+
"step": 11320
|
3853 |
+
},
|
3854 |
+
{
|
3855 |
+
"epoch": 2.68,
|
3856 |
+
"learning_rate": 3.2216044479745826e-05,
|
3857 |
+
"loss": 0.6461,
|
3858 |
+
"step": 11340
|
3859 |
+
},
|
3860 |
+
{
|
3861 |
+
"epoch": 2.69,
|
3862 |
+
"learning_rate": 3.173947577442414e-05,
|
3863 |
+
"loss": 0.6505,
|
3864 |
+
"step": 11360
|
3865 |
+
},
|
3866 |
+
{
|
3867 |
+
"epoch": 2.69,
|
3868 |
+
"learning_rate": 3.126290706910246e-05,
|
3869 |
+
"loss": 0.6517,
|
3870 |
+
"step": 11380
|
3871 |
+
},
|
3872 |
+
{
|
3873 |
+
"epoch": 2.7,
|
3874 |
+
"learning_rate": 3.0786338363780774e-05,
|
3875 |
+
"loss": 0.6406,
|
3876 |
+
"step": 11400
|
3877 |
+
},
|
3878 |
+
{
|
3879 |
+
"epoch": 2.7,
|
3880 |
+
"eval_loss": 0.6380326151847839,
|
3881 |
+
"eval_runtime": 49.4129,
|
3882 |
+
"eval_samples_per_second": 40.475,
|
3883 |
+
"eval_steps_per_second": 2.53,
|
3884 |
+
"step": 11400
|
3885 |
+
},
|
3886 |
+
{
|
3887 |
+
"epoch": 2.7,
|
3888 |
+
"learning_rate": 3.030976965845909e-05,
|
3889 |
+
"loss": 0.647,
|
3890 |
+
"step": 11420
|
3891 |
+
},
|
3892 |
+
{
|
3893 |
+
"epoch": 2.7,
|
3894 |
+
"learning_rate": 2.9833200953137408e-05,
|
3895 |
+
"loss": 0.6495,
|
3896 |
+
"step": 11440
|
3897 |
+
},
|
3898 |
+
{
|
3899 |
+
"epoch": 2.71,
|
3900 |
+
"learning_rate": 2.9356632247815725e-05,
|
3901 |
+
"loss": 0.6448,
|
3902 |
+
"step": 11460
|
3903 |
+
},
|
3904 |
+
{
|
3905 |
+
"epoch": 2.71,
|
3906 |
+
"learning_rate": 2.888006354249404e-05,
|
3907 |
+
"loss": 0.6447,
|
3908 |
+
"step": 11480
|
3909 |
+
},
|
3910 |
+
{
|
3911 |
+
"epoch": 2.72,
|
3912 |
+
"learning_rate": 2.840349483717236e-05,
|
3913 |
+
"loss": 0.6527,
|
3914 |
+
"step": 11500
|
3915 |
+
},
|
3916 |
+
{
|
3917 |
+
"epoch": 2.72,
|
3918 |
+
"learning_rate": 2.7926926131850673e-05,
|
3919 |
+
"loss": 0.6406,
|
3920 |
+
"step": 11520
|
3921 |
+
},
|
3922 |
+
{
|
3923 |
+
"epoch": 2.73,
|
3924 |
+
"learning_rate": 2.7450357426528987e-05,
|
3925 |
+
"loss": 0.6443,
|
3926 |
+
"step": 11540
|
3927 |
+
},
|
3928 |
+
{
|
3929 |
+
"epoch": 2.73,
|
3930 |
+
"learning_rate": 2.6973788721207307e-05,
|
3931 |
+
"loss": 0.6351,
|
3932 |
+
"step": 11560
|
3933 |
+
},
|
3934 |
+
{
|
3935 |
+
"epoch": 2.74,
|
3936 |
+
"learning_rate": 2.649722001588562e-05,
|
3937 |
+
"loss": 0.6417,
|
3938 |
+
"step": 11580
|
3939 |
+
},
|
3940 |
+
{
|
3941 |
+
"epoch": 2.74,
|
3942 |
+
"learning_rate": 2.6020651310563938e-05,
|
3943 |
+
"loss": 0.6356,
|
3944 |
+
"step": 11600
|
3945 |
+
},
|
3946 |
+
{
|
3947 |
+
"epoch": 2.74,
|
3948 |
+
"eval_loss": 0.6381237506866455,
|
3949 |
+
"eval_runtime": 49.5534,
|
3950 |
+
"eval_samples_per_second": 40.36,
|
3951 |
+
"eval_steps_per_second": 2.523,
|
3952 |
+
"step": 11600
|
3953 |
+
},
|
3954 |
+
{
|
3955 |
+
"epoch": 2.75,
|
3956 |
+
"learning_rate": 2.5544082605242255e-05,
|
3957 |
+
"loss": 0.6412,
|
3958 |
+
"step": 11620
|
3959 |
+
},
|
3960 |
+
{
|
3961 |
+
"epoch": 2.75,
|
3962 |
+
"learning_rate": 2.506751389992057e-05,
|
3963 |
+
"loss": 0.6418,
|
3964 |
+
"step": 11640
|
3965 |
+
},
|
3966 |
+
{
|
3967 |
+
"epoch": 2.76,
|
3968 |
+
"learning_rate": 2.4590945194598886e-05,
|
3969 |
+
"loss": 0.6426,
|
3970 |
+
"step": 11660
|
3971 |
+
},
|
3972 |
+
{
|
3973 |
+
"epoch": 2.76,
|
3974 |
+
"learning_rate": 2.4114376489277203e-05,
|
3975 |
+
"loss": 0.6461,
|
3976 |
+
"step": 11680
|
3977 |
+
},
|
3978 |
+
{
|
3979 |
+
"epoch": 2.77,
|
3980 |
+
"learning_rate": 2.363780778395552e-05,
|
3981 |
+
"loss": 0.6475,
|
3982 |
+
"step": 11700
|
3983 |
+
},
|
3984 |
+
{
|
3985 |
+
"epoch": 2.77,
|
3986 |
+
"learning_rate": 2.3161239078633834e-05,
|
3987 |
+
"loss": 0.6431,
|
3988 |
+
"step": 11720
|
3989 |
+
},
|
3990 |
+
{
|
3991 |
+
"epoch": 2.78,
|
3992 |
+
"learning_rate": 2.2684670373312148e-05,
|
3993 |
+
"loss": 0.6416,
|
3994 |
+
"step": 11740
|
3995 |
+
},
|
3996 |
+
{
|
3997 |
+
"epoch": 2.78,
|
3998 |
+
"learning_rate": 2.2208101667990468e-05,
|
3999 |
+
"loss": 0.6495,
|
4000 |
+
"step": 11760
|
4001 |
+
},
|
4002 |
+
{
|
4003 |
+
"epoch": 2.78,
|
4004 |
+
"learning_rate": 2.1731532962668782e-05,
|
4005 |
+
"loss": 0.6404,
|
4006 |
+
"step": 11780
|
4007 |
+
},
|
4008 |
+
{
|
4009 |
+
"epoch": 2.79,
|
4010 |
+
"learning_rate": 2.1254964257347096e-05,
|
4011 |
+
"loss": 0.6434,
|
4012 |
+
"step": 11800
|
4013 |
+
},
|
4014 |
+
{
|
4015 |
+
"epoch": 2.79,
|
4016 |
+
"eval_loss": 0.6377163529396057,
|
4017 |
+
"eval_runtime": 49.328,
|
4018 |
+
"eval_samples_per_second": 40.545,
|
4019 |
+
"eval_steps_per_second": 2.534,
|
4020 |
+
"step": 11800
|
4021 |
+
},
|
4022 |
+
{
|
4023 |
+
"epoch": 2.79,
|
4024 |
+
"learning_rate": 2.0778395552025416e-05,
|
4025 |
+
"loss": 0.6437,
|
4026 |
+
"step": 11820
|
4027 |
+
},
|
4028 |
+
{
|
4029 |
+
"epoch": 2.8,
|
4030 |
+
"learning_rate": 2.030182684670373e-05,
|
4031 |
+
"loss": 0.6393,
|
4032 |
+
"step": 11840
|
4033 |
+
},
|
4034 |
+
{
|
4035 |
+
"epoch": 2.8,
|
4036 |
+
"learning_rate": 1.9825258141382047e-05,
|
4037 |
+
"loss": 0.6412,
|
4038 |
+
"step": 11860
|
4039 |
+
},
|
4040 |
+
{
|
4041 |
+
"epoch": 2.81,
|
4042 |
+
"learning_rate": 1.9348689436060364e-05,
|
4043 |
+
"loss": 0.6494,
|
4044 |
+
"step": 11880
|
4045 |
+
},
|
4046 |
+
{
|
4047 |
+
"epoch": 2.81,
|
4048 |
+
"learning_rate": 1.887212073073868e-05,
|
4049 |
+
"loss": 0.6481,
|
4050 |
+
"step": 11900
|
4051 |
+
},
|
4052 |
+
{
|
4053 |
+
"epoch": 2.82,
|
4054 |
+
"learning_rate": 1.8395552025416998e-05,
|
4055 |
+
"loss": 0.6407,
|
4056 |
+
"step": 11920
|
4057 |
+
},
|
4058 |
+
{
|
4059 |
+
"epoch": 2.82,
|
4060 |
+
"learning_rate": 1.7918983320095312e-05,
|
4061 |
+
"loss": 0.6422,
|
4062 |
+
"step": 11940
|
4063 |
+
},
|
4064 |
+
{
|
4065 |
+
"epoch": 2.83,
|
4066 |
+
"learning_rate": 1.744241461477363e-05,
|
4067 |
+
"loss": 0.6487,
|
4068 |
+
"step": 11960
|
4069 |
+
},
|
4070 |
+
{
|
4071 |
+
"epoch": 2.83,
|
4072 |
+
"learning_rate": 1.6965845909451946e-05,
|
4073 |
+
"loss": 0.6478,
|
4074 |
+
"step": 11980
|
4075 |
+
},
|
4076 |
+
{
|
4077 |
+
"epoch": 2.84,
|
4078 |
+
"learning_rate": 1.648927720413026e-05,
|
4079 |
+
"loss": 0.6451,
|
4080 |
+
"step": 12000
|
4081 |
+
},
|
4082 |
+
{
|
4083 |
+
"epoch": 2.84,
|
4084 |
+
"eval_loss": 0.6374698281288147,
|
4085 |
+
"eval_runtime": 49.9107,
|
4086 |
+
"eval_samples_per_second": 40.072,
|
4087 |
+
"eval_steps_per_second": 2.504,
|
4088 |
+
"step": 12000
|
4089 |
+
},
|
4090 |
+
{
|
4091 |
+
"epoch": 2.84,
|
4092 |
+
"learning_rate": 1.6012708498808577e-05,
|
4093 |
+
"loss": 0.6454,
|
4094 |
+
"step": 12020
|
4095 |
+
},
|
4096 |
+
{
|
4097 |
+
"epoch": 2.85,
|
4098 |
+
"learning_rate": 1.5536139793486894e-05,
|
4099 |
+
"loss": 0.6399,
|
4100 |
+
"step": 12040
|
4101 |
+
},
|
4102 |
+
{
|
4103 |
+
"epoch": 2.85,
|
4104 |
+
"learning_rate": 1.5059571088165208e-05,
|
4105 |
+
"loss": 0.6479,
|
4106 |
+
"step": 12060
|
4107 |
+
},
|
4108 |
+
{
|
4109 |
+
"epoch": 2.86,
|
4110 |
+
"learning_rate": 1.4583002382843525e-05,
|
4111 |
+
"loss": 0.6412,
|
4112 |
+
"step": 12080
|
4113 |
+
},
|
4114 |
+
{
|
4115 |
+
"epoch": 2.86,
|
4116 |
+
"learning_rate": 1.4106433677521842e-05,
|
4117 |
+
"loss": 0.65,
|
4118 |
+
"step": 12100
|
4119 |
+
},
|
4120 |
+
{
|
4121 |
+
"epoch": 2.87,
|
4122 |
+
"learning_rate": 1.3629864972200157e-05,
|
4123 |
+
"loss": 0.6461,
|
4124 |
+
"step": 12120
|
4125 |
+
},
|
4126 |
+
{
|
4127 |
+
"epoch": 2.87,
|
4128 |
+
"learning_rate": 1.3153296266878475e-05,
|
4129 |
+
"loss": 0.6434,
|
4130 |
+
"step": 12140
|
4131 |
+
},
|
4132 |
+
{
|
4133 |
+
"epoch": 2.87,
|
4134 |
+
"learning_rate": 1.2676727561556788e-05,
|
4135 |
+
"loss": 0.6463,
|
4136 |
+
"step": 12160
|
4137 |
+
},
|
4138 |
+
{
|
4139 |
+
"epoch": 2.88,
|
4140 |
+
"learning_rate": 1.2200158856235105e-05,
|
4141 |
+
"loss": 0.6399,
|
4142 |
+
"step": 12180
|
4143 |
+
},
|
4144 |
+
{
|
4145 |
+
"epoch": 2.88,
|
4146 |
+
"learning_rate": 1.1723590150913422e-05,
|
4147 |
+
"loss": 0.6446,
|
4148 |
+
"step": 12200
|
4149 |
+
},
|
4150 |
+
{
|
4151 |
+
"epoch": 2.88,
|
4152 |
+
"eval_loss": 0.6372544765472412,
|
4153 |
+
"eval_runtime": 49.6265,
|
4154 |
+
"eval_samples_per_second": 40.301,
|
4155 |
+
"eval_steps_per_second": 2.519,
|
4156 |
+
"step": 12200
|
4157 |
+
},
|
4158 |
+
{
|
4159 |
+
"epoch": 2.89,
|
4160 |
+
"learning_rate": 1.1247021445591738e-05,
|
4161 |
+
"loss": 0.6411,
|
4162 |
+
"step": 12220
|
4163 |
+
},
|
4164 |
+
{
|
4165 |
+
"epoch": 2.89,
|
4166 |
+
"learning_rate": 1.0770452740270055e-05,
|
4167 |
+
"loss": 0.6523,
|
4168 |
+
"step": 12240
|
4169 |
+
},
|
4170 |
+
{
|
4171 |
+
"epoch": 2.9,
|
4172 |
+
"learning_rate": 1.0293884034948372e-05,
|
4173 |
+
"loss": 0.6456,
|
4174 |
+
"step": 12260
|
4175 |
+
},
|
4176 |
+
{
|
4177 |
+
"epoch": 2.9,
|
4178 |
+
"learning_rate": 9.817315329626686e-06,
|
4179 |
+
"loss": 0.6394,
|
4180 |
+
"step": 12280
|
4181 |
+
},
|
4182 |
+
{
|
4183 |
+
"epoch": 2.91,
|
4184 |
+
"learning_rate": 9.340746624305003e-06,
|
4185 |
+
"loss": 0.6466,
|
4186 |
+
"step": 12300
|
4187 |
+
},
|
4188 |
+
{
|
4189 |
+
"epoch": 2.91,
|
4190 |
+
"learning_rate": 8.864177918983318e-06,
|
4191 |
+
"loss": 0.6415,
|
4192 |
+
"step": 12320
|
4193 |
+
},
|
4194 |
+
{
|
4195 |
+
"epoch": 2.92,
|
4196 |
+
"learning_rate": 8.387609213661635e-06,
|
4197 |
+
"loss": 0.6349,
|
4198 |
+
"step": 12340
|
4199 |
+
},
|
4200 |
+
{
|
4201 |
+
"epoch": 2.92,
|
4202 |
+
"learning_rate": 7.911040508339953e-06,
|
4203 |
+
"loss": 0.6415,
|
4204 |
+
"step": 12360
|
4205 |
+
},
|
4206 |
+
{
|
4207 |
+
"epoch": 2.93,
|
4208 |
+
"learning_rate": 7.434471803018268e-06,
|
4209 |
+
"loss": 0.6484,
|
4210 |
+
"step": 12380
|
4211 |
+
},
|
4212 |
+
{
|
4213 |
+
"epoch": 2.93,
|
4214 |
+
"learning_rate": 6.957903097696583e-06,
|
4215 |
+
"loss": 0.6522,
|
4216 |
+
"step": 12400
|
4217 |
+
},
|
4218 |
+
{
|
4219 |
+
"epoch": 2.93,
|
4220 |
+
"eval_loss": 0.6368712186813354,
|
4221 |
+
"eval_runtime": 49.0693,
|
4222 |
+
"eval_samples_per_second": 40.759,
|
4223 |
+
"eval_steps_per_second": 2.547,
|
4224 |
+
"step": 12400
|
4225 |
+
}
|
4226 |
+
],
|
4227 |
+
"max_steps": 12690,
|
4228 |
+
"num_train_epochs": 3,
|
4229 |
+
"total_flos": 1.6115968989795975e+19,
|
4230 |
+
"trial_name": null,
|
4231 |
+
"trial_params": null
|
4232 |
+
}
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a070370e87c048b60fc888b8736a0166eb94eeb3a75f5f78918edab715d0fb1c
|
3 |
+
size 3579
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc421ca0cff089fc9d5410754618990eeffd7211650fedbd4ea6c12ce50487d
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07cb1c0cd175ab3c89d7c1d0757096e6296fb26b15857a8055e81cea1ea2cc09
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fea007e68f1c9bcee110c38f61b818ac2bc4fd40e2301190a645e34c33a0f16
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3f8942b136a5483f01aef18b20bc8e5593a6ffc1c98f568387b2998ae5919ea
|
3 |
+
size 14583
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef71700e98ec366ab46243409e3aae93c95cdbd7ffb98f89074ebd1b9ec3b15
|
3 |
+
size 557
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:785a83cf92471c0356ef5051741195c9790867768c86ba3d8a21ba52906bbf2f
|
3 |
+
size 627
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/trainer_state.json
ADDED
@@ -0,0 +1,4300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.636846125125885,
|
3 |
+
"best_model_checkpoint": "lora-alpaca-cn/checkpoint-12600",
|
4 |
+
"epoch": 2.978723404255319,
|
5 |
+
"global_step": 12600,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 5.9999999999999995e-05,
|
13 |
+
"loss": 1.7735,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 0.00011999999999999999,
|
19 |
+
"loss": 1.1358,
|
20 |
+
"step": 40
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 0.00017999999999999998,
|
25 |
+
"loss": 0.9749,
|
26 |
+
"step": 60
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 0.00023999999999999998,
|
31 |
+
"loss": 0.9316,
|
32 |
+
"step": 80
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 0.9072,
|
38 |
+
"step": 100
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 0.0002995234312946783,
|
43 |
+
"loss": 0.8963,
|
44 |
+
"step": 120
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"learning_rate": 0.0002990468625893566,
|
49 |
+
"loss": 0.8853,
|
50 |
+
"step": 140
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.04,
|
54 |
+
"learning_rate": 0.0002985702938840349,
|
55 |
+
"loss": 0.8709,
|
56 |
+
"step": 160
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04,
|
60 |
+
"learning_rate": 0.00029809372517871323,
|
61 |
+
"loss": 0.8555,
|
62 |
+
"step": 180
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.05,
|
66 |
+
"learning_rate": 0.00029761715647339156,
|
67 |
+
"loss": 0.8584,
|
68 |
+
"step": 200
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.05,
|
72 |
+
"eval_loss": 0.8360834717750549,
|
73 |
+
"eval_runtime": 49.29,
|
74 |
+
"eval_samples_per_second": 40.576,
|
75 |
+
"eval_steps_per_second": 2.536,
|
76 |
+
"step": 200
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.05,
|
80 |
+
"learning_rate": 0.0002971405877680699,
|
81 |
+
"loss": 0.859,
|
82 |
+
"step": 220
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.06,
|
86 |
+
"learning_rate": 0.00029666401906274816,
|
87 |
+
"loss": 0.8511,
|
88 |
+
"step": 240
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.06,
|
92 |
+
"learning_rate": 0.0002961874503574265,
|
93 |
+
"loss": 0.8401,
|
94 |
+
"step": 260
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.07,
|
98 |
+
"learning_rate": 0.0002957108816521048,
|
99 |
+
"loss": 0.8357,
|
100 |
+
"step": 280
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07,
|
104 |
+
"learning_rate": 0.00029523431294678314,
|
105 |
+
"loss": 0.8413,
|
106 |
+
"step": 300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.08,
|
110 |
+
"learning_rate": 0.00029475774424146147,
|
111 |
+
"loss": 0.8283,
|
112 |
+
"step": 320
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.08,
|
116 |
+
"learning_rate": 0.0002942811755361398,
|
117 |
+
"loss": 0.8202,
|
118 |
+
"step": 340
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.09,
|
122 |
+
"learning_rate": 0.00029380460683081807,
|
123 |
+
"loss": 0.8222,
|
124 |
+
"step": 360
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.09,
|
128 |
+
"learning_rate": 0.0002933280381254964,
|
129 |
+
"loss": 0.8178,
|
130 |
+
"step": 380
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.09,
|
134 |
+
"learning_rate": 0.0002928514694201747,
|
135 |
+
"loss": 0.8177,
|
136 |
+
"step": 400
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.09,
|
140 |
+
"eval_loss": 0.7966175079345703,
|
141 |
+
"eval_runtime": 49.1752,
|
142 |
+
"eval_samples_per_second": 40.671,
|
143 |
+
"eval_steps_per_second": 2.542,
|
144 |
+
"step": 400
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.1,
|
148 |
+
"learning_rate": 0.00029237490071485305,
|
149 |
+
"loss": 0.8057,
|
150 |
+
"step": 420
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.1,
|
154 |
+
"learning_rate": 0.0002918983320095314,
|
155 |
+
"loss": 0.811,
|
156 |
+
"step": 440
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.11,
|
160 |
+
"learning_rate": 0.00029142176330420965,
|
161 |
+
"loss": 0.8056,
|
162 |
+
"step": 460
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.11,
|
166 |
+
"learning_rate": 0.000290945194598888,
|
167 |
+
"loss": 0.7993,
|
168 |
+
"step": 480
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.12,
|
172 |
+
"learning_rate": 0.0002904686258935663,
|
173 |
+
"loss": 0.7982,
|
174 |
+
"step": 500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.12,
|
178 |
+
"learning_rate": 0.0002899920571882446,
|
179 |
+
"loss": 0.8023,
|
180 |
+
"step": 520
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.13,
|
184 |
+
"learning_rate": 0.00028951548848292296,
|
185 |
+
"loss": 0.7968,
|
186 |
+
"step": 540
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.13,
|
190 |
+
"learning_rate": 0.00028903891977760123,
|
191 |
+
"loss": 0.8029,
|
192 |
+
"step": 560
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.14,
|
196 |
+
"learning_rate": 0.00028856235107227956,
|
197 |
+
"loss": 0.7892,
|
198 |
+
"step": 580
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.14,
|
202 |
+
"learning_rate": 0.0002880857823669579,
|
203 |
+
"loss": 0.7946,
|
204 |
+
"step": 600
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.14,
|
208 |
+
"eval_loss": 0.7735009789466858,
|
209 |
+
"eval_runtime": 49.3305,
|
210 |
+
"eval_samples_per_second": 40.543,
|
211 |
+
"eval_steps_per_second": 2.534,
|
212 |
+
"step": 600
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15,
|
216 |
+
"learning_rate": 0.00028760921366163616,
|
217 |
+
"loss": 0.782,
|
218 |
+
"step": 620
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.15,
|
222 |
+
"learning_rate": 0.0002871326449563145,
|
223 |
+
"loss": 0.7799,
|
224 |
+
"step": 640
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.16,
|
228 |
+
"learning_rate": 0.0002866560762509928,
|
229 |
+
"loss": 0.7782,
|
230 |
+
"step": 660
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.16,
|
234 |
+
"learning_rate": 0.00028617950754567114,
|
235 |
+
"loss": 0.7785,
|
236 |
+
"step": 680
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.17,
|
240 |
+
"learning_rate": 0.00028570293884034947,
|
241 |
+
"loss": 0.785,
|
242 |
+
"step": 700
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.17,
|
246 |
+
"learning_rate": 0.0002852263701350278,
|
247 |
+
"loss": 0.7754,
|
248 |
+
"step": 720
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.17,
|
252 |
+
"learning_rate": 0.00028474980142970607,
|
253 |
+
"loss": 0.7804,
|
254 |
+
"step": 740
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18,
|
258 |
+
"learning_rate": 0.0002842732327243844,
|
259 |
+
"loss": 0.7696,
|
260 |
+
"step": 760
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.18,
|
264 |
+
"learning_rate": 0.0002837966640190627,
|
265 |
+
"loss": 0.7692,
|
266 |
+
"step": 780
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.19,
|
270 |
+
"learning_rate": 0.00028332009531374105,
|
271 |
+
"loss": 0.7752,
|
272 |
+
"step": 800
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.19,
|
276 |
+
"eval_loss": 0.7564254403114319,
|
277 |
+
"eval_runtime": 49.106,
|
278 |
+
"eval_samples_per_second": 40.728,
|
279 |
+
"eval_steps_per_second": 2.546,
|
280 |
+
"step": 800
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.19,
|
284 |
+
"learning_rate": 0.0002828435266084194,
|
285 |
+
"loss": 0.7698,
|
286 |
+
"step": 820
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.2,
|
290 |
+
"learning_rate": 0.00028236695790309765,
|
291 |
+
"loss": 0.7699,
|
292 |
+
"step": 840
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.2,
|
296 |
+
"learning_rate": 0.000281890389197776,
|
297 |
+
"loss": 0.7718,
|
298 |
+
"step": 860
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.21,
|
302 |
+
"learning_rate": 0.0002814138204924543,
|
303 |
+
"loss": 0.7644,
|
304 |
+
"step": 880
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.21,
|
308 |
+
"learning_rate": 0.00028093725178713263,
|
309 |
+
"loss": 0.7659,
|
310 |
+
"step": 900
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.22,
|
314 |
+
"learning_rate": 0.00028046068308181096,
|
315 |
+
"loss": 0.7641,
|
316 |
+
"step": 920
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.22,
|
320 |
+
"learning_rate": 0.00027998411437648923,
|
321 |
+
"loss": 0.7535,
|
322 |
+
"step": 940
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.23,
|
326 |
+
"learning_rate": 0.00027950754567116756,
|
327 |
+
"loss": 0.7672,
|
328 |
+
"step": 960
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.23,
|
332 |
+
"learning_rate": 0.0002790309769658459,
|
333 |
+
"loss": 0.7563,
|
334 |
+
"step": 980
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.24,
|
338 |
+
"learning_rate": 0.0002785544082605242,
|
339 |
+
"loss": 0.752,
|
340 |
+
"step": 1000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.24,
|
344 |
+
"eval_loss": 0.7433652281761169,
|
345 |
+
"eval_runtime": 48.9945,
|
346 |
+
"eval_samples_per_second": 40.821,
|
347 |
+
"eval_steps_per_second": 2.551,
|
348 |
+
"step": 1000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.24,
|
352 |
+
"learning_rate": 0.00027807783955520254,
|
353 |
+
"loss": 0.755,
|
354 |
+
"step": 1020
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.25,
|
358 |
+
"learning_rate": 0.00027760127084988087,
|
359 |
+
"loss": 0.7563,
|
360 |
+
"step": 1040
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.25,
|
364 |
+
"learning_rate": 0.00027712470214455914,
|
365 |
+
"loss": 0.7475,
|
366 |
+
"step": 1060
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.26,
|
370 |
+
"learning_rate": 0.00027664813343923747,
|
371 |
+
"loss": 0.7599,
|
372 |
+
"step": 1080
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 0.26,
|
376 |
+
"learning_rate": 0.0002761715647339158,
|
377 |
+
"loss": 0.7533,
|
378 |
+
"step": 1100
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.26,
|
382 |
+
"learning_rate": 0.00027569499602859407,
|
383 |
+
"loss": 0.7488,
|
384 |
+
"step": 1120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.27,
|
388 |
+
"learning_rate": 0.00027521842732327245,
|
389 |
+
"loss": 0.753,
|
390 |
+
"step": 1140
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.27,
|
394 |
+
"learning_rate": 0.0002747418586179507,
|
395 |
+
"loss": 0.7435,
|
396 |
+
"step": 1160
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.28,
|
400 |
+
"learning_rate": 0.00027426528991262905,
|
401 |
+
"loss": 0.7457,
|
402 |
+
"step": 1180
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.28,
|
406 |
+
"learning_rate": 0.0002737887212073074,
|
407 |
+
"loss": 0.742,
|
408 |
+
"step": 1200
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.28,
|
412 |
+
"eval_loss": 0.7321739792823792,
|
413 |
+
"eval_runtime": 48.8876,
|
414 |
+
"eval_samples_per_second": 40.91,
|
415 |
+
"eval_steps_per_second": 2.557,
|
416 |
+
"step": 1200
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.29,
|
420 |
+
"learning_rate": 0.00027331215250198565,
|
421 |
+
"loss": 0.7474,
|
422 |
+
"step": 1220
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.29,
|
426 |
+
"learning_rate": 0.000272835583796664,
|
427 |
+
"loss": 0.7456,
|
428 |
+
"step": 1240
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.3,
|
432 |
+
"learning_rate": 0.0002723590150913423,
|
433 |
+
"loss": 0.7406,
|
434 |
+
"step": 1260
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.3,
|
438 |
+
"learning_rate": 0.00027188244638602063,
|
439 |
+
"loss": 0.7448,
|
440 |
+
"step": 1280
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.31,
|
444 |
+
"learning_rate": 0.00027140587768069896,
|
445 |
+
"loss": 0.7445,
|
446 |
+
"step": 1300
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.31,
|
450 |
+
"learning_rate": 0.00027092930897537723,
|
451 |
+
"loss": 0.7349,
|
452 |
+
"step": 1320
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.32,
|
456 |
+
"learning_rate": 0.00027045274027005556,
|
457 |
+
"loss": 0.7395,
|
458 |
+
"step": 1340
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.32,
|
462 |
+
"learning_rate": 0.0002699761715647339,
|
463 |
+
"loss": 0.7382,
|
464 |
+
"step": 1360
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.33,
|
468 |
+
"learning_rate": 0.0002694996028594122,
|
469 |
+
"loss": 0.7357,
|
470 |
+
"step": 1380
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.33,
|
474 |
+
"learning_rate": 0.00026902303415409054,
|
475 |
+
"loss": 0.7409,
|
476 |
+
"step": 1400
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.33,
|
480 |
+
"eval_loss": 0.7235888242721558,
|
481 |
+
"eval_runtime": 49.2145,
|
482 |
+
"eval_samples_per_second": 40.638,
|
483 |
+
"eval_steps_per_second": 2.54,
|
484 |
+
"step": 1400
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.34,
|
488 |
+
"learning_rate": 0.00026854646544876887,
|
489 |
+
"loss": 0.7376,
|
490 |
+
"step": 1420
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 0.34,
|
494 |
+
"learning_rate": 0.00026806989674344714,
|
495 |
+
"loss": 0.7298,
|
496 |
+
"step": 1440
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.35,
|
500 |
+
"learning_rate": 0.00026759332803812547,
|
501 |
+
"loss": 0.7379,
|
502 |
+
"step": 1460
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.35,
|
506 |
+
"learning_rate": 0.0002671167593328038,
|
507 |
+
"loss": 0.7354,
|
508 |
+
"step": 1480
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.35,
|
512 |
+
"learning_rate": 0.0002666401906274821,
|
513 |
+
"loss": 0.7341,
|
514 |
+
"step": 1500
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.36,
|
518 |
+
"learning_rate": 0.00026616362192216045,
|
519 |
+
"loss": 0.7352,
|
520 |
+
"step": 1520
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.36,
|
524 |
+
"learning_rate": 0.0002656870532168387,
|
525 |
+
"loss": 0.7321,
|
526 |
+
"step": 1540
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.37,
|
530 |
+
"learning_rate": 0.00026521048451151705,
|
531 |
+
"loss": 0.7285,
|
532 |
+
"step": 1560
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.37,
|
536 |
+
"learning_rate": 0.0002647339158061954,
|
537 |
+
"loss": 0.73,
|
538 |
+
"step": 1580
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.38,
|
542 |
+
"learning_rate": 0.00026425734710087365,
|
543 |
+
"loss": 0.7304,
|
544 |
+
"step": 1600
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.38,
|
548 |
+
"eval_loss": 0.716058611869812,
|
549 |
+
"eval_runtime": 48.9201,
|
550 |
+
"eval_samples_per_second": 40.883,
|
551 |
+
"eval_steps_per_second": 2.555,
|
552 |
+
"step": 1600
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.38,
|
556 |
+
"learning_rate": 0.00026378077839555203,
|
557 |
+
"loss": 0.7314,
|
558 |
+
"step": 1620
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.39,
|
562 |
+
"learning_rate": 0.0002633042096902303,
|
563 |
+
"loss": 0.7315,
|
564 |
+
"step": 1640
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.39,
|
568 |
+
"learning_rate": 0.00026282764098490863,
|
569 |
+
"loss": 0.7239,
|
570 |
+
"step": 1660
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.4,
|
574 |
+
"learning_rate": 0.00026235107227958696,
|
575 |
+
"loss": 0.73,
|
576 |
+
"step": 1680
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.4,
|
580 |
+
"learning_rate": 0.00026187450357426523,
|
581 |
+
"loss": 0.7243,
|
582 |
+
"step": 1700
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.41,
|
586 |
+
"learning_rate": 0.00026139793486894356,
|
587 |
+
"loss": 0.7199,
|
588 |
+
"step": 1720
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 0.41,
|
592 |
+
"learning_rate": 0.0002609213661636219,
|
593 |
+
"loss": 0.7216,
|
594 |
+
"step": 1740
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.42,
|
598 |
+
"learning_rate": 0.0002604447974583002,
|
599 |
+
"loss": 0.7358,
|
600 |
+
"step": 1760
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.42,
|
604 |
+
"learning_rate": 0.00025996822875297854,
|
605 |
+
"loss": 0.7313,
|
606 |
+
"step": 1780
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.43,
|
610 |
+
"learning_rate": 0.00025949166004765687,
|
611 |
+
"loss": 0.7236,
|
612 |
+
"step": 1800
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.43,
|
616 |
+
"eval_loss": 0.7097632884979248,
|
617 |
+
"eval_runtime": 49.4908,
|
618 |
+
"eval_samples_per_second": 40.412,
|
619 |
+
"eval_steps_per_second": 2.526,
|
620 |
+
"step": 1800
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.43,
|
624 |
+
"learning_rate": 0.00025901509134233514,
|
625 |
+
"loss": 0.7282,
|
626 |
+
"step": 1820
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.43,
|
630 |
+
"learning_rate": 0.00025853852263701347,
|
631 |
+
"loss": 0.7187,
|
632 |
+
"step": 1840
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.44,
|
636 |
+
"learning_rate": 0.0002580619539316918,
|
637 |
+
"loss": 0.7303,
|
638 |
+
"step": 1860
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.44,
|
642 |
+
"learning_rate": 0.0002575853852263701,
|
643 |
+
"loss": 0.724,
|
644 |
+
"step": 1880
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.45,
|
648 |
+
"learning_rate": 0.00025710881652104845,
|
649 |
+
"loss": 0.7248,
|
650 |
+
"step": 1900
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.45,
|
654 |
+
"learning_rate": 0.0002566322478157267,
|
655 |
+
"loss": 0.7195,
|
656 |
+
"step": 1920
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.46,
|
660 |
+
"learning_rate": 0.00025615567911040505,
|
661 |
+
"loss": 0.7269,
|
662 |
+
"step": 1940
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.46,
|
666 |
+
"learning_rate": 0.0002556791104050834,
|
667 |
+
"loss": 0.7209,
|
668 |
+
"step": 1960
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.47,
|
672 |
+
"learning_rate": 0.0002552025416997617,
|
673 |
+
"loss": 0.7282,
|
674 |
+
"step": 1980
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.47,
|
678 |
+
"learning_rate": 0.00025472597299444003,
|
679 |
+
"loss": 0.7195,
|
680 |
+
"step": 2000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.47,
|
684 |
+
"eval_loss": 0.7037709355354309,
|
685 |
+
"eval_runtime": 49.7167,
|
686 |
+
"eval_samples_per_second": 40.228,
|
687 |
+
"eval_steps_per_second": 2.514,
|
688 |
+
"step": 2000
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.48,
|
692 |
+
"learning_rate": 0.0002542494042891183,
|
693 |
+
"loss": 0.7229,
|
694 |
+
"step": 2020
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 0.48,
|
698 |
+
"learning_rate": 0.00025377283558379664,
|
699 |
+
"loss": 0.718,
|
700 |
+
"step": 2040
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.49,
|
704 |
+
"learning_rate": 0.00025329626687847496,
|
705 |
+
"loss": 0.7223,
|
706 |
+
"step": 2060
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.49,
|
710 |
+
"learning_rate": 0.00025281969817315324,
|
711 |
+
"loss": 0.7209,
|
712 |
+
"step": 2080
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.5,
|
716 |
+
"learning_rate": 0.0002523431294678316,
|
717 |
+
"loss": 0.7151,
|
718 |
+
"step": 2100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.5,
|
722 |
+
"learning_rate": 0.0002518665607625099,
|
723 |
+
"loss": 0.7141,
|
724 |
+
"step": 2120
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.51,
|
728 |
+
"learning_rate": 0.0002513899920571882,
|
729 |
+
"loss": 0.7084,
|
730 |
+
"step": 2140
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.51,
|
734 |
+
"learning_rate": 0.00025091342335186654,
|
735 |
+
"loss": 0.7075,
|
736 |
+
"step": 2160
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.52,
|
740 |
+
"learning_rate": 0.00025043685464654487,
|
741 |
+
"loss": 0.7133,
|
742 |
+
"step": 2180
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 0.52,
|
746 |
+
"learning_rate": 0.00024996028594122314,
|
747 |
+
"loss": 0.7092,
|
748 |
+
"step": 2200
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.52,
|
752 |
+
"eval_loss": 0.6989386677742004,
|
753 |
+
"eval_runtime": 49.2344,
|
754 |
+
"eval_samples_per_second": 40.622,
|
755 |
+
"eval_steps_per_second": 2.539,
|
756 |
+
"step": 2200
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.52,
|
760 |
+
"learning_rate": 0.0002494837172359015,
|
761 |
+
"loss": 0.7178,
|
762 |
+
"step": 2220
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.53,
|
766 |
+
"learning_rate": 0.0002490071485305798,
|
767 |
+
"loss": 0.7188,
|
768 |
+
"step": 2240
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.53,
|
772 |
+
"learning_rate": 0.0002485305798252581,
|
773 |
+
"loss": 0.7161,
|
774 |
+
"step": 2260
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.54,
|
778 |
+
"learning_rate": 0.00024805401111993645,
|
779 |
+
"loss": 0.7078,
|
780 |
+
"step": 2280
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.54,
|
784 |
+
"learning_rate": 0.0002475774424146147,
|
785 |
+
"loss": 0.7,
|
786 |
+
"step": 2300
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.55,
|
790 |
+
"learning_rate": 0.00024710087370929305,
|
791 |
+
"loss": 0.718,
|
792 |
+
"step": 2320
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.55,
|
796 |
+
"learning_rate": 0.0002466243050039714,
|
797 |
+
"loss": 0.7059,
|
798 |
+
"step": 2340
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.56,
|
802 |
+
"learning_rate": 0.0002461477362986497,
|
803 |
+
"loss": 0.712,
|
804 |
+
"step": 2360
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.56,
|
808 |
+
"learning_rate": 0.00024567116759332804,
|
809 |
+
"loss": 0.7116,
|
810 |
+
"step": 2380
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.57,
|
814 |
+
"learning_rate": 0.0002451945988880063,
|
815 |
+
"loss": 0.6986,
|
816 |
+
"step": 2400
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.57,
|
820 |
+
"eval_loss": 0.6939737796783447,
|
821 |
+
"eval_runtime": 49.459,
|
822 |
+
"eval_samples_per_second": 40.438,
|
823 |
+
"eval_steps_per_second": 2.527,
|
824 |
+
"step": 2400
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.57,
|
828 |
+
"learning_rate": 0.00024471803018268464,
|
829 |
+
"loss": 0.7168,
|
830 |
+
"step": 2420
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.58,
|
834 |
+
"learning_rate": 0.00024424146147736296,
|
835 |
+
"loss": 0.7141,
|
836 |
+
"step": 2440
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.58,
|
840 |
+
"learning_rate": 0.00024376489277204126,
|
841 |
+
"loss": 0.7095,
|
842 |
+
"step": 2460
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.59,
|
846 |
+
"learning_rate": 0.00024328832406671962,
|
847 |
+
"loss": 0.7091,
|
848 |
+
"step": 2480
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.59,
|
852 |
+
"learning_rate": 0.00024281175536139792,
|
853 |
+
"loss": 0.7015,
|
854 |
+
"step": 2500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.6,
|
858 |
+
"learning_rate": 0.00024233518665607622,
|
859 |
+
"loss": 0.7109,
|
860 |
+
"step": 2520
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.6,
|
864 |
+
"learning_rate": 0.00024185861795075455,
|
865 |
+
"loss": 0.7086,
|
866 |
+
"step": 2540
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.61,
|
870 |
+
"learning_rate": 0.00024138204924543285,
|
871 |
+
"loss": 0.7118,
|
872 |
+
"step": 2560
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.61,
|
876 |
+
"learning_rate": 0.00024090548054011117,
|
877 |
+
"loss": 0.7033,
|
878 |
+
"step": 2580
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.61,
|
882 |
+
"learning_rate": 0.0002404289118347895,
|
883 |
+
"loss": 0.7128,
|
884 |
+
"step": 2600
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.61,
|
888 |
+
"eval_loss": 0.6901652812957764,
|
889 |
+
"eval_runtime": 49.5038,
|
890 |
+
"eval_samples_per_second": 40.401,
|
891 |
+
"eval_steps_per_second": 2.525,
|
892 |
+
"step": 2600
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.62,
|
896 |
+
"learning_rate": 0.00023995234312946783,
|
897 |
+
"loss": 0.6968,
|
898 |
+
"step": 2620
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.62,
|
902 |
+
"learning_rate": 0.00023947577442414613,
|
903 |
+
"loss": 0.7109,
|
904 |
+
"step": 2640
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.63,
|
908 |
+
"learning_rate": 0.00023899920571882443,
|
909 |
+
"loss": 0.7048,
|
910 |
+
"step": 2660
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.63,
|
914 |
+
"learning_rate": 0.00023852263701350276,
|
915 |
+
"loss": 0.7012,
|
916 |
+
"step": 2680
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.64,
|
920 |
+
"learning_rate": 0.00023804606830818106,
|
921 |
+
"loss": 0.7065,
|
922 |
+
"step": 2700
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.64,
|
926 |
+
"learning_rate": 0.0002375694996028594,
|
927 |
+
"loss": 0.7009,
|
928 |
+
"step": 2720
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.65,
|
932 |
+
"learning_rate": 0.0002370929308975377,
|
933 |
+
"loss": 0.7035,
|
934 |
+
"step": 2740
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.65,
|
938 |
+
"learning_rate": 0.00023661636219221604,
|
939 |
+
"loss": 0.6973,
|
940 |
+
"step": 2760
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.66,
|
944 |
+
"learning_rate": 0.00023613979348689434,
|
945 |
+
"loss": 0.7075,
|
946 |
+
"step": 2780
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.66,
|
950 |
+
"learning_rate": 0.00023566322478157264,
|
951 |
+
"loss": 0.6952,
|
952 |
+
"step": 2800
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.66,
|
956 |
+
"eval_loss": 0.6865400671958923,
|
957 |
+
"eval_runtime": 49.2814,
|
958 |
+
"eval_samples_per_second": 40.583,
|
959 |
+
"eval_steps_per_second": 2.536,
|
960 |
+
"step": 2800
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 0.67,
|
964 |
+
"learning_rate": 0.00023518665607625097,
|
965 |
+
"loss": 0.6979,
|
966 |
+
"step": 2820
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.67,
|
970 |
+
"learning_rate": 0.0002347100873709293,
|
971 |
+
"loss": 0.6973,
|
972 |
+
"step": 2840
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.68,
|
976 |
+
"learning_rate": 0.00023423351866560762,
|
977 |
+
"loss": 0.7033,
|
978 |
+
"step": 2860
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.68,
|
982 |
+
"learning_rate": 0.00023375694996028592,
|
983 |
+
"loss": 0.6964,
|
984 |
+
"step": 2880
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.69,
|
988 |
+
"learning_rate": 0.00023328038125496422,
|
989 |
+
"loss": 0.7052,
|
990 |
+
"step": 2900
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.69,
|
994 |
+
"learning_rate": 0.00023280381254964255,
|
995 |
+
"loss": 0.6999,
|
996 |
+
"step": 2920
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.7,
|
1000 |
+
"learning_rate": 0.00023232724384432085,
|
1001 |
+
"loss": 0.6963,
|
1002 |
+
"step": 2940
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.7,
|
1006 |
+
"learning_rate": 0.0002318506751389992,
|
1007 |
+
"loss": 0.7025,
|
1008 |
+
"step": 2960
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.7,
|
1012 |
+
"learning_rate": 0.0002313741064336775,
|
1013 |
+
"loss": 0.704,
|
1014 |
+
"step": 2980
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.71,
|
1018 |
+
"learning_rate": 0.00023089753772835583,
|
1019 |
+
"loss": 0.6926,
|
1020 |
+
"step": 3000
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.71,
|
1024 |
+
"eval_loss": 0.6828380227088928,
|
1025 |
+
"eval_runtime": 49.5667,
|
1026 |
+
"eval_samples_per_second": 40.35,
|
1027 |
+
"eval_steps_per_second": 2.522,
|
1028 |
+
"step": 3000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.71,
|
1032 |
+
"learning_rate": 0.00023042096902303413,
|
1033 |
+
"loss": 0.698,
|
1034 |
+
"step": 3020
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.72,
|
1038 |
+
"learning_rate": 0.00022994440031771243,
|
1039 |
+
"loss": 0.6893,
|
1040 |
+
"step": 3040
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.72,
|
1044 |
+
"learning_rate": 0.00022946783161239076,
|
1045 |
+
"loss": 0.6938,
|
1046 |
+
"step": 3060
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.73,
|
1050 |
+
"learning_rate": 0.00022899126290706908,
|
1051 |
+
"loss": 0.6974,
|
1052 |
+
"step": 3080
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.73,
|
1056 |
+
"learning_rate": 0.0002285146942017474,
|
1057 |
+
"loss": 0.6922,
|
1058 |
+
"step": 3100
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.74,
|
1062 |
+
"learning_rate": 0.0002280381254964257,
|
1063 |
+
"loss": 0.7073,
|
1064 |
+
"step": 3120
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.74,
|
1068 |
+
"learning_rate": 0.00022756155679110404,
|
1069 |
+
"loss": 0.6895,
|
1070 |
+
"step": 3140
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.75,
|
1074 |
+
"learning_rate": 0.00022708498808578234,
|
1075 |
+
"loss": 0.7012,
|
1076 |
+
"step": 3160
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.75,
|
1080 |
+
"learning_rate": 0.00022660841938046064,
|
1081 |
+
"loss": 0.6985,
|
1082 |
+
"step": 3180
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.76,
|
1086 |
+
"learning_rate": 0.000226131850675139,
|
1087 |
+
"loss": 0.6901,
|
1088 |
+
"step": 3200
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.76,
|
1092 |
+
"eval_loss": 0.6807068586349487,
|
1093 |
+
"eval_runtime": 49.2421,
|
1094 |
+
"eval_samples_per_second": 40.616,
|
1095 |
+
"eval_steps_per_second": 2.538,
|
1096 |
+
"step": 3200
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.76,
|
1100 |
+
"learning_rate": 0.0002256552819698173,
|
1101 |
+
"loss": 0.697,
|
1102 |
+
"step": 3220
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.77,
|
1106 |
+
"learning_rate": 0.00022517871326449562,
|
1107 |
+
"loss": 0.7002,
|
1108 |
+
"step": 3240
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.77,
|
1112 |
+
"learning_rate": 0.00022470214455917392,
|
1113 |
+
"loss": 0.6918,
|
1114 |
+
"step": 3260
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.78,
|
1118 |
+
"learning_rate": 0.00022422557585385225,
|
1119 |
+
"loss": 0.6999,
|
1120 |
+
"step": 3280
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 0.78,
|
1124 |
+
"learning_rate": 0.00022374900714853055,
|
1125 |
+
"loss": 0.6961,
|
1126 |
+
"step": 3300
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.78,
|
1130 |
+
"learning_rate": 0.0002232724384432089,
|
1131 |
+
"loss": 0.6888,
|
1132 |
+
"step": 3320
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.79,
|
1136 |
+
"learning_rate": 0.0002227958697378872,
|
1137 |
+
"loss": 0.695,
|
1138 |
+
"step": 3340
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.79,
|
1142 |
+
"learning_rate": 0.0002223193010325655,
|
1143 |
+
"loss": 0.6861,
|
1144 |
+
"step": 3360
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.8,
|
1148 |
+
"learning_rate": 0.00022184273232724383,
|
1149 |
+
"loss": 0.6864,
|
1150 |
+
"step": 3380
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.8,
|
1154 |
+
"learning_rate": 0.00022136616362192213,
|
1155 |
+
"loss": 0.6917,
|
1156 |
+
"step": 3400
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.8,
|
1160 |
+
"eval_loss": 0.6773961782455444,
|
1161 |
+
"eval_runtime": 49.3961,
|
1162 |
+
"eval_samples_per_second": 40.489,
|
1163 |
+
"eval_steps_per_second": 2.531,
|
1164 |
+
"step": 3400
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.81,
|
1168 |
+
"learning_rate": 0.00022088959491660043,
|
1169 |
+
"loss": 0.679,
|
1170 |
+
"step": 3420
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.81,
|
1174 |
+
"learning_rate": 0.00022041302621127879,
|
1175 |
+
"loss": 0.6915,
|
1176 |
+
"step": 3440
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 0.82,
|
1180 |
+
"learning_rate": 0.00021993645750595709,
|
1181 |
+
"loss": 0.6937,
|
1182 |
+
"step": 3460
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.82,
|
1186 |
+
"learning_rate": 0.0002194598888006354,
|
1187 |
+
"loss": 0.6831,
|
1188 |
+
"step": 3480
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.83,
|
1192 |
+
"learning_rate": 0.0002189833200953137,
|
1193 |
+
"loss": 0.6875,
|
1194 |
+
"step": 3500
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.83,
|
1198 |
+
"learning_rate": 0.00021850675138999204,
|
1199 |
+
"loss": 0.6916,
|
1200 |
+
"step": 3520
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.84,
|
1204 |
+
"learning_rate": 0.00021803018268467034,
|
1205 |
+
"loss": 0.6896,
|
1206 |
+
"step": 3540
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.84,
|
1210 |
+
"learning_rate": 0.0002175536139793487,
|
1211 |
+
"loss": 0.6986,
|
1212 |
+
"step": 3560
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.85,
|
1216 |
+
"learning_rate": 0.000217077045274027,
|
1217 |
+
"loss": 0.693,
|
1218 |
+
"step": 3580
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.85,
|
1222 |
+
"learning_rate": 0.0002166004765687053,
|
1223 |
+
"loss": 0.6893,
|
1224 |
+
"step": 3600
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.85,
|
1228 |
+
"eval_loss": 0.6753410696983337,
|
1229 |
+
"eval_runtime": 49.3307,
|
1230 |
+
"eval_samples_per_second": 40.543,
|
1231 |
+
"eval_steps_per_second": 2.534,
|
1232 |
+
"step": 3600
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.86,
|
1236 |
+
"learning_rate": 0.00021612390786338362,
|
1237 |
+
"loss": 0.6872,
|
1238 |
+
"step": 3620
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.86,
|
1242 |
+
"learning_rate": 0.00021564733915806192,
|
1243 |
+
"loss": 0.6862,
|
1244 |
+
"step": 3640
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.87,
|
1248 |
+
"learning_rate": 0.00021517077045274025,
|
1249 |
+
"loss": 0.6943,
|
1250 |
+
"step": 3660
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.87,
|
1254 |
+
"learning_rate": 0.00021469420174741858,
|
1255 |
+
"loss": 0.6896,
|
1256 |
+
"step": 3680
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.87,
|
1260 |
+
"learning_rate": 0.0002142176330420969,
|
1261 |
+
"loss": 0.6912,
|
1262 |
+
"step": 3700
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.88,
|
1266 |
+
"learning_rate": 0.0002137410643367752,
|
1267 |
+
"loss": 0.6859,
|
1268 |
+
"step": 3720
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.88,
|
1272 |
+
"learning_rate": 0.0002132644956314535,
|
1273 |
+
"loss": 0.6791,
|
1274 |
+
"step": 3740
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.89,
|
1278 |
+
"learning_rate": 0.00021278792692613183,
|
1279 |
+
"loss": 0.6882,
|
1280 |
+
"step": 3760
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.89,
|
1284 |
+
"learning_rate": 0.00021231135822081013,
|
1285 |
+
"loss": 0.6823,
|
1286 |
+
"step": 3780
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.9,
|
1290 |
+
"learning_rate": 0.0002118347895154885,
|
1291 |
+
"loss": 0.6831,
|
1292 |
+
"step": 3800
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.9,
|
1296 |
+
"eval_loss": 0.6738302707672119,
|
1297 |
+
"eval_runtime": 49.4648,
|
1298 |
+
"eval_samples_per_second": 40.433,
|
1299 |
+
"eval_steps_per_second": 2.527,
|
1300 |
+
"step": 3800
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.9,
|
1304 |
+
"learning_rate": 0.0002113582208101668,
|
1305 |
+
"loss": 0.6818,
|
1306 |
+
"step": 3820
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.91,
|
1310 |
+
"learning_rate": 0.0002108816521048451,
|
1311 |
+
"loss": 0.6912,
|
1312 |
+
"step": 3840
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.91,
|
1316 |
+
"learning_rate": 0.00021040508339952341,
|
1317 |
+
"loss": 0.6884,
|
1318 |
+
"step": 3860
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.92,
|
1322 |
+
"learning_rate": 0.00020992851469420171,
|
1323 |
+
"loss": 0.6888,
|
1324 |
+
"step": 3880
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 0.92,
|
1328 |
+
"learning_rate": 0.00020945194598888004,
|
1329 |
+
"loss": 0.6822,
|
1330 |
+
"step": 3900
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.93,
|
1334 |
+
"learning_rate": 0.00020897537728355837,
|
1335 |
+
"loss": 0.6879,
|
1336 |
+
"step": 3920
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.93,
|
1340 |
+
"learning_rate": 0.0002084988085782367,
|
1341 |
+
"loss": 0.6771,
|
1342 |
+
"step": 3940
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.94,
|
1346 |
+
"learning_rate": 0.000208022239872915,
|
1347 |
+
"loss": 0.684,
|
1348 |
+
"step": 3960
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.94,
|
1352 |
+
"learning_rate": 0.0002075456711675933,
|
1353 |
+
"loss": 0.6878,
|
1354 |
+
"step": 3980
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.95,
|
1358 |
+
"learning_rate": 0.00020706910246227162,
|
1359 |
+
"loss": 0.6913,
|
1360 |
+
"step": 4000
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.95,
|
1364 |
+
"eval_loss": 0.6711302995681763,
|
1365 |
+
"eval_runtime": 49.117,
|
1366 |
+
"eval_samples_per_second": 40.719,
|
1367 |
+
"eval_steps_per_second": 2.545,
|
1368 |
+
"step": 4000
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.95,
|
1372 |
+
"learning_rate": 0.00020659253375694992,
|
1373 |
+
"loss": 0.683,
|
1374 |
+
"step": 4020
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.96,
|
1378 |
+
"learning_rate": 0.00020611596505162828,
|
1379 |
+
"loss": 0.6833,
|
1380 |
+
"step": 4040
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 0.96,
|
1384 |
+
"learning_rate": 0.00020563939634630658,
|
1385 |
+
"loss": 0.6793,
|
1386 |
+
"step": 4060
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.96,
|
1390 |
+
"learning_rate": 0.0002051628276409849,
|
1391 |
+
"loss": 0.6843,
|
1392 |
+
"step": 4080
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.97,
|
1396 |
+
"learning_rate": 0.0002046862589356632,
|
1397 |
+
"loss": 0.6822,
|
1398 |
+
"step": 4100
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.97,
|
1402 |
+
"learning_rate": 0.0002042096902303415,
|
1403 |
+
"loss": 0.6856,
|
1404 |
+
"step": 4120
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.98,
|
1408 |
+
"learning_rate": 0.00020373312152501983,
|
1409 |
+
"loss": 0.6809,
|
1410 |
+
"step": 4140
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.98,
|
1414 |
+
"learning_rate": 0.00020325655281969816,
|
1415 |
+
"loss": 0.6843,
|
1416 |
+
"step": 4160
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.99,
|
1420 |
+
"learning_rate": 0.0002027799841143765,
|
1421 |
+
"loss": 0.6754,
|
1422 |
+
"step": 4180
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 0.99,
|
1426 |
+
"learning_rate": 0.0002023034154090548,
|
1427 |
+
"loss": 0.6823,
|
1428 |
+
"step": 4200
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 0.99,
|
1432 |
+
"eval_loss": 0.6697036027908325,
|
1433 |
+
"eval_runtime": 49.3237,
|
1434 |
+
"eval_samples_per_second": 40.548,
|
1435 |
+
"eval_steps_per_second": 2.534,
|
1436 |
+
"step": 4200
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 1.0,
|
1440 |
+
"learning_rate": 0.00020182684670373312,
|
1441 |
+
"loss": 0.6861,
|
1442 |
+
"step": 4220
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 1.0,
|
1446 |
+
"learning_rate": 0.00020135027799841142,
|
1447 |
+
"loss": 0.6806,
|
1448 |
+
"step": 4240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 1.01,
|
1452 |
+
"learning_rate": 0.00020087370929308972,
|
1453 |
+
"loss": 0.6823,
|
1454 |
+
"step": 4260
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 1.01,
|
1458 |
+
"learning_rate": 0.00020039714058776807,
|
1459 |
+
"loss": 0.6805,
|
1460 |
+
"step": 4280
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 1.02,
|
1464 |
+
"learning_rate": 0.00019992057188244637,
|
1465 |
+
"loss": 0.6813,
|
1466 |
+
"step": 4300
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.02,
|
1470 |
+
"learning_rate": 0.0001994440031771247,
|
1471 |
+
"loss": 0.675,
|
1472 |
+
"step": 4320
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 1.03,
|
1476 |
+
"learning_rate": 0.000198967434471803,
|
1477 |
+
"loss": 0.6728,
|
1478 |
+
"step": 4340
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.03,
|
1482 |
+
"learning_rate": 0.0001984908657664813,
|
1483 |
+
"loss": 0.6676,
|
1484 |
+
"step": 4360
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 1.04,
|
1488 |
+
"learning_rate": 0.00019801429706115963,
|
1489 |
+
"loss": 0.6729,
|
1490 |
+
"step": 4380
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 1.04,
|
1494 |
+
"learning_rate": 0.00019753772835583795,
|
1495 |
+
"loss": 0.685,
|
1496 |
+
"step": 4400
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 1.04,
|
1500 |
+
"eval_loss": 0.6667952537536621,
|
1501 |
+
"eval_runtime": 49.3899,
|
1502 |
+
"eval_samples_per_second": 40.494,
|
1503 |
+
"eval_steps_per_second": 2.531,
|
1504 |
+
"step": 4400
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 1.04,
|
1508 |
+
"learning_rate": 0.00019706115965051628,
|
1509 |
+
"loss": 0.6786,
|
1510 |
+
"step": 4420
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 1.05,
|
1514 |
+
"learning_rate": 0.00019658459094519458,
|
1515 |
+
"loss": 0.6738,
|
1516 |
+
"step": 4440
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 1.05,
|
1520 |
+
"learning_rate": 0.0001961080222398729,
|
1521 |
+
"loss": 0.686,
|
1522 |
+
"step": 4460
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.06,
|
1526 |
+
"learning_rate": 0.0001956314535345512,
|
1527 |
+
"loss": 0.6818,
|
1528 |
+
"step": 4480
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.06,
|
1532 |
+
"learning_rate": 0.0001951548848292295,
|
1533 |
+
"loss": 0.6741,
|
1534 |
+
"step": 4500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 1.07,
|
1538 |
+
"learning_rate": 0.00019467831612390786,
|
1539 |
+
"loss": 0.6756,
|
1540 |
+
"step": 4520
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 1.07,
|
1544 |
+
"learning_rate": 0.00019420174741858616,
|
1545 |
+
"loss": 0.6851,
|
1546 |
+
"step": 4540
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.08,
|
1550 |
+
"learning_rate": 0.0001937251787132645,
|
1551 |
+
"loss": 0.6784,
|
1552 |
+
"step": 4560
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 1.08,
|
1556 |
+
"learning_rate": 0.0001932486100079428,
|
1557 |
+
"loss": 0.6785,
|
1558 |
+
"step": 4580
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 1.09,
|
1562 |
+
"learning_rate": 0.00019277204130262112,
|
1563 |
+
"loss": 0.678,
|
1564 |
+
"step": 4600
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.09,
|
1568 |
+
"eval_loss": 0.6655837297439575,
|
1569 |
+
"eval_runtime": 49.5019,
|
1570 |
+
"eval_samples_per_second": 40.403,
|
1571 |
+
"eval_steps_per_second": 2.525,
|
1572 |
+
"step": 4600
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 1.09,
|
1576 |
+
"learning_rate": 0.00019229547259729942,
|
1577 |
+
"loss": 0.6782,
|
1578 |
+
"step": 4620
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.1,
|
1582 |
+
"learning_rate": 0.00019181890389197777,
|
1583 |
+
"loss": 0.6683,
|
1584 |
+
"step": 4640
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.1,
|
1588 |
+
"learning_rate": 0.00019134233518665607,
|
1589 |
+
"loss": 0.6783,
|
1590 |
+
"step": 4660
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 1.11,
|
1594 |
+
"learning_rate": 0.00019086576648133437,
|
1595 |
+
"loss": 0.675,
|
1596 |
+
"step": 4680
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 1.11,
|
1600 |
+
"learning_rate": 0.0001903891977760127,
|
1601 |
+
"loss": 0.6691,
|
1602 |
+
"step": 4700
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.12,
|
1606 |
+
"learning_rate": 0.000189912629070691,
|
1607 |
+
"loss": 0.6726,
|
1608 |
+
"step": 4720
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.12,
|
1612 |
+
"learning_rate": 0.00018943606036536933,
|
1613 |
+
"loss": 0.68,
|
1614 |
+
"step": 4740
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.13,
|
1618 |
+
"learning_rate": 0.00018895949166004763,
|
1619 |
+
"loss": 0.6694,
|
1620 |
+
"step": 4760
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.13,
|
1624 |
+
"learning_rate": 0.00018848292295472598,
|
1625 |
+
"loss": 0.6686,
|
1626 |
+
"step": 4780
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.13,
|
1630 |
+
"learning_rate": 0.00018800635424940428,
|
1631 |
+
"loss": 0.6766,
|
1632 |
+
"step": 4800
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.13,
|
1636 |
+
"eval_loss": 0.6646501421928406,
|
1637 |
+
"eval_runtime": 49.3188,
|
1638 |
+
"eval_samples_per_second": 40.552,
|
1639 |
+
"eval_steps_per_second": 2.535,
|
1640 |
+
"step": 4800
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 1.14,
|
1644 |
+
"learning_rate": 0.00018752978554408258,
|
1645 |
+
"loss": 0.6724,
|
1646 |
+
"step": 4820
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 1.14,
|
1650 |
+
"learning_rate": 0.0001870532168387609,
|
1651 |
+
"loss": 0.6801,
|
1652 |
+
"step": 4840
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 1.15,
|
1656 |
+
"learning_rate": 0.0001865766481334392,
|
1657 |
+
"loss": 0.6698,
|
1658 |
+
"step": 4860
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.15,
|
1662 |
+
"learning_rate": 0.0001861000794281175,
|
1663 |
+
"loss": 0.6723,
|
1664 |
+
"step": 4880
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 1.16,
|
1668 |
+
"learning_rate": 0.00018562351072279586,
|
1669 |
+
"loss": 0.6693,
|
1670 |
+
"step": 4900
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 1.16,
|
1674 |
+
"learning_rate": 0.00018514694201747416,
|
1675 |
+
"loss": 0.6716,
|
1676 |
+
"step": 4920
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.17,
|
1680 |
+
"learning_rate": 0.0001846703733121525,
|
1681 |
+
"loss": 0.674,
|
1682 |
+
"step": 4940
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 1.17,
|
1686 |
+
"learning_rate": 0.0001841938046068308,
|
1687 |
+
"loss": 0.6702,
|
1688 |
+
"step": 4960
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 1.18,
|
1692 |
+
"learning_rate": 0.00018371723590150912,
|
1693 |
+
"loss": 0.6716,
|
1694 |
+
"step": 4980
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 1.18,
|
1698 |
+
"learning_rate": 0.00018324066719618742,
|
1699 |
+
"loss": 0.672,
|
1700 |
+
"step": 5000
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.18,
|
1704 |
+
"eval_loss": 0.662735104560852,
|
1705 |
+
"eval_runtime": 49.275,
|
1706 |
+
"eval_samples_per_second": 40.589,
|
1707 |
+
"eval_steps_per_second": 2.537,
|
1708 |
+
"step": 5000
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 1.19,
|
1712 |
+
"learning_rate": 0.00018276409849086577,
|
1713 |
+
"loss": 0.6701,
|
1714 |
+
"step": 5020
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.19,
|
1718 |
+
"learning_rate": 0.00018228752978554407,
|
1719 |
+
"loss": 0.6663,
|
1720 |
+
"step": 5040
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 1.2,
|
1724 |
+
"learning_rate": 0.00018181096108022237,
|
1725 |
+
"loss": 0.6651,
|
1726 |
+
"step": 5060
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 1.2,
|
1730 |
+
"learning_rate": 0.0001813343923749007,
|
1731 |
+
"loss": 0.6708,
|
1732 |
+
"step": 5080
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.21,
|
1736 |
+
"learning_rate": 0.000180857823669579,
|
1737 |
+
"loss": 0.6697,
|
1738 |
+
"step": 5100
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.21,
|
1742 |
+
"learning_rate": 0.00018038125496425733,
|
1743 |
+
"loss": 0.662,
|
1744 |
+
"step": 5120
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 1.22,
|
1748 |
+
"learning_rate": 0.00017990468625893566,
|
1749 |
+
"loss": 0.669,
|
1750 |
+
"step": 5140
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 1.22,
|
1754 |
+
"learning_rate": 0.00017942811755361398,
|
1755 |
+
"loss": 0.6649,
|
1756 |
+
"step": 5160
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 1.22,
|
1760 |
+
"learning_rate": 0.00017895154884829228,
|
1761 |
+
"loss": 0.668,
|
1762 |
+
"step": 5180
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.23,
|
1766 |
+
"learning_rate": 0.00017847498014297058,
|
1767 |
+
"loss": 0.6796,
|
1768 |
+
"step": 5200
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 1.23,
|
1772 |
+
"eval_loss": 0.6609957218170166,
|
1773 |
+
"eval_runtime": 49.2394,
|
1774 |
+
"eval_samples_per_second": 40.618,
|
1775 |
+
"eval_steps_per_second": 2.539,
|
1776 |
+
"step": 5200
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 1.23,
|
1780 |
+
"learning_rate": 0.0001779984114376489,
|
1781 |
+
"loss": 0.6745,
|
1782 |
+
"step": 5220
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 1.24,
|
1786 |
+
"learning_rate": 0.0001775218427323272,
|
1787 |
+
"loss": 0.6646,
|
1788 |
+
"step": 5240
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.24,
|
1792 |
+
"learning_rate": 0.00017704527402700556,
|
1793 |
+
"loss": 0.6682,
|
1794 |
+
"step": 5260
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.25,
|
1798 |
+
"learning_rate": 0.00017656870532168386,
|
1799 |
+
"loss": 0.6713,
|
1800 |
+
"step": 5280
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 1.25,
|
1804 |
+
"learning_rate": 0.00017609213661636216,
|
1805 |
+
"loss": 0.6618,
|
1806 |
+
"step": 5300
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.26,
|
1810 |
+
"learning_rate": 0.0001756155679110405,
|
1811 |
+
"loss": 0.6703,
|
1812 |
+
"step": 5320
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 1.26,
|
1816 |
+
"learning_rate": 0.0001751389992057188,
|
1817 |
+
"loss": 0.6652,
|
1818 |
+
"step": 5340
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 1.27,
|
1822 |
+
"learning_rate": 0.00017466243050039712,
|
1823 |
+
"loss": 0.6698,
|
1824 |
+
"step": 5360
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.27,
|
1828 |
+
"learning_rate": 0.00017418586179507545,
|
1829 |
+
"loss": 0.6728,
|
1830 |
+
"step": 5380
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.28,
|
1834 |
+
"learning_rate": 0.00017370929308975377,
|
1835 |
+
"loss": 0.6752,
|
1836 |
+
"step": 5400
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.28,
|
1840 |
+
"eval_loss": 0.6592395901679993,
|
1841 |
+
"eval_runtime": 49.3426,
|
1842 |
+
"eval_samples_per_second": 40.533,
|
1843 |
+
"eval_steps_per_second": 2.533,
|
1844 |
+
"step": 5400
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.28,
|
1848 |
+
"learning_rate": 0.00017323272438443207,
|
1849 |
+
"loss": 0.6653,
|
1850 |
+
"step": 5420
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.29,
|
1854 |
+
"learning_rate": 0.00017275615567911037,
|
1855 |
+
"loss": 0.669,
|
1856 |
+
"step": 5440
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 1.29,
|
1860 |
+
"learning_rate": 0.0001722795869737887,
|
1861 |
+
"loss": 0.6698,
|
1862 |
+
"step": 5460
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 1.3,
|
1866 |
+
"learning_rate": 0.000171803018268467,
|
1867 |
+
"loss": 0.6742,
|
1868 |
+
"step": 5480
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 1.3,
|
1872 |
+
"learning_rate": 0.00017132644956314536,
|
1873 |
+
"loss": 0.6596,
|
1874 |
+
"step": 5500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 1.3,
|
1878 |
+
"learning_rate": 0.00017084988085782366,
|
1879 |
+
"loss": 0.6699,
|
1880 |
+
"step": 5520
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 1.31,
|
1884 |
+
"learning_rate": 0.00017037331215250198,
|
1885 |
+
"loss": 0.664,
|
1886 |
+
"step": 5540
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.31,
|
1890 |
+
"learning_rate": 0.00016989674344718028,
|
1891 |
+
"loss": 0.6673,
|
1892 |
+
"step": 5560
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 1.32,
|
1896 |
+
"learning_rate": 0.00016942017474185858,
|
1897 |
+
"loss": 0.6684,
|
1898 |
+
"step": 5580
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 1.32,
|
1902 |
+
"learning_rate": 0.0001689436060365369,
|
1903 |
+
"loss": 0.6769,
|
1904 |
+
"step": 5600
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 1.32,
|
1908 |
+
"eval_loss": 0.6582754850387573,
|
1909 |
+
"eval_runtime": 49.469,
|
1910 |
+
"eval_samples_per_second": 40.429,
|
1911 |
+
"eval_steps_per_second": 2.527,
|
1912 |
+
"step": 5600
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 1.33,
|
1916 |
+
"learning_rate": 0.00016846703733121524,
|
1917 |
+
"loss": 0.6633,
|
1918 |
+
"step": 5620
|
1919 |
+
},
|
1920 |
+
{
|
1921 |
+
"epoch": 1.33,
|
1922 |
+
"learning_rate": 0.00016799046862589357,
|
1923 |
+
"loss": 0.6679,
|
1924 |
+
"step": 5640
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 1.34,
|
1928 |
+
"learning_rate": 0.00016751389992057187,
|
1929 |
+
"loss": 0.6601,
|
1930 |
+
"step": 5660
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 1.34,
|
1934 |
+
"learning_rate": 0.0001670373312152502,
|
1935 |
+
"loss": 0.6731,
|
1936 |
+
"step": 5680
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 1.35,
|
1940 |
+
"learning_rate": 0.0001665607625099285,
|
1941 |
+
"loss": 0.6638,
|
1942 |
+
"step": 5700
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.35,
|
1946 |
+
"learning_rate": 0.0001660841938046068,
|
1947 |
+
"loss": 0.6693,
|
1948 |
+
"step": 5720
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 1.36,
|
1952 |
+
"learning_rate": 0.00016560762509928515,
|
1953 |
+
"loss": 0.6642,
|
1954 |
+
"step": 5740
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.36,
|
1958 |
+
"learning_rate": 0.00016513105639396345,
|
1959 |
+
"loss": 0.6649,
|
1960 |
+
"step": 5760
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 1.37,
|
1964 |
+
"learning_rate": 0.00016465448768864178,
|
1965 |
+
"loss": 0.663,
|
1966 |
+
"step": 5780
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 1.37,
|
1970 |
+
"learning_rate": 0.00016417791898332008,
|
1971 |
+
"loss": 0.6629,
|
1972 |
+
"step": 5800
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 1.37,
|
1976 |
+
"eval_loss": 0.6574136018753052,
|
1977 |
+
"eval_runtime": 49.3019,
|
1978 |
+
"eval_samples_per_second": 40.566,
|
1979 |
+
"eval_steps_per_second": 2.535,
|
1980 |
+
"step": 5800
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 1.38,
|
1984 |
+
"learning_rate": 0.00016370135027799838,
|
1985 |
+
"loss": 0.6605,
|
1986 |
+
"step": 5820
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 1.38,
|
1990 |
+
"learning_rate": 0.0001632247815726767,
|
1991 |
+
"loss": 0.6707,
|
1992 |
+
"step": 5840
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 1.39,
|
1996 |
+
"learning_rate": 0.00016274821286735503,
|
1997 |
+
"loss": 0.6695,
|
1998 |
+
"step": 5860
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.39,
|
2002 |
+
"learning_rate": 0.00016227164416203336,
|
2003 |
+
"loss": 0.6647,
|
2004 |
+
"step": 5880
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 1.39,
|
2008 |
+
"learning_rate": 0.00016179507545671166,
|
2009 |
+
"loss": 0.6657,
|
2010 |
+
"step": 5900
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.4,
|
2014 |
+
"learning_rate": 0.00016131850675138999,
|
2015 |
+
"loss": 0.6656,
|
2016 |
+
"step": 5920
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 1.4,
|
2020 |
+
"learning_rate": 0.00016084193804606829,
|
2021 |
+
"loss": 0.6676,
|
2022 |
+
"step": 5940
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.41,
|
2026 |
+
"learning_rate": 0.00016036536934074659,
|
2027 |
+
"loss": 0.6678,
|
2028 |
+
"step": 5960
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 1.41,
|
2032 |
+
"learning_rate": 0.00015988880063542494,
|
2033 |
+
"loss": 0.6639,
|
2034 |
+
"step": 5980
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.42,
|
2038 |
+
"learning_rate": 0.00015941223193010324,
|
2039 |
+
"loss": 0.6645,
|
2040 |
+
"step": 6000
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.42,
|
2044 |
+
"eval_loss": 0.656126081943512,
|
2045 |
+
"eval_runtime": 49.5095,
|
2046 |
+
"eval_samples_per_second": 40.396,
|
2047 |
+
"eval_steps_per_second": 2.525,
|
2048 |
+
"step": 6000
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 1.42,
|
2052 |
+
"learning_rate": 0.00015893566322478157,
|
2053 |
+
"loss": 0.6672,
|
2054 |
+
"step": 6020
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.43,
|
2058 |
+
"learning_rate": 0.00015845909451945987,
|
2059 |
+
"loss": 0.6678,
|
2060 |
+
"step": 6040
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 1.43,
|
2064 |
+
"learning_rate": 0.0001579825258141382,
|
2065 |
+
"loss": 0.6676,
|
2066 |
+
"step": 6060
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.44,
|
2070 |
+
"learning_rate": 0.0001575059571088165,
|
2071 |
+
"loss": 0.6717,
|
2072 |
+
"step": 6080
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 1.44,
|
2076 |
+
"learning_rate": 0.00015702938840349485,
|
2077 |
+
"loss": 0.671,
|
2078 |
+
"step": 6100
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 1.45,
|
2082 |
+
"learning_rate": 0.00015655281969817315,
|
2083 |
+
"loss": 0.6611,
|
2084 |
+
"step": 6120
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 1.45,
|
2088 |
+
"learning_rate": 0.00015607625099285145,
|
2089 |
+
"loss": 0.6606,
|
2090 |
+
"step": 6140
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 1.46,
|
2094 |
+
"learning_rate": 0.00015559968228752978,
|
2095 |
+
"loss": 0.6647,
|
2096 |
+
"step": 6160
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.46,
|
2100 |
+
"learning_rate": 0.00015512311358220808,
|
2101 |
+
"loss": 0.6652,
|
2102 |
+
"step": 6180
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 1.47,
|
2106 |
+
"learning_rate": 0.0001546465448768864,
|
2107 |
+
"loss": 0.6629,
|
2108 |
+
"step": 6200
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 1.47,
|
2112 |
+
"eval_loss": 0.6549723148345947,
|
2113 |
+
"eval_runtime": 49.4871,
|
2114 |
+
"eval_samples_per_second": 40.415,
|
2115 |
+
"eval_steps_per_second": 2.526,
|
2116 |
+
"step": 6200
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 1.47,
|
2120 |
+
"learning_rate": 0.00015416997617156473,
|
2121 |
+
"loss": 0.6685,
|
2122 |
+
"step": 6220
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.48,
|
2126 |
+
"learning_rate": 0.00015369340746624306,
|
2127 |
+
"loss": 0.6578,
|
2128 |
+
"step": 6240
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"epoch": 1.48,
|
2132 |
+
"learning_rate": 0.00015321683876092136,
|
2133 |
+
"loss": 0.6587,
|
2134 |
+
"step": 6260
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 1.48,
|
2138 |
+
"learning_rate": 0.00015274027005559966,
|
2139 |
+
"loss": 0.6655,
|
2140 |
+
"step": 6280
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 1.49,
|
2144 |
+
"learning_rate": 0.000152263701350278,
|
2145 |
+
"loss": 0.6662,
|
2146 |
+
"step": 6300
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 1.49,
|
2150 |
+
"learning_rate": 0.0001517871326449563,
|
2151 |
+
"loss": 0.6648,
|
2152 |
+
"step": 6320
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.5,
|
2156 |
+
"learning_rate": 0.00015131056393963464,
|
2157 |
+
"loss": 0.6638,
|
2158 |
+
"step": 6340
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 1.5,
|
2162 |
+
"learning_rate": 0.00015083399523431294,
|
2163 |
+
"loss": 0.6614,
|
2164 |
+
"step": 6360
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 1.51,
|
2168 |
+
"learning_rate": 0.00015035742652899124,
|
2169 |
+
"loss": 0.6552,
|
2170 |
+
"step": 6380
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 1.51,
|
2174 |
+
"learning_rate": 0.00014988085782366957,
|
2175 |
+
"loss": 0.6753,
|
2176 |
+
"step": 6400
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 1.51,
|
2180 |
+
"eval_loss": 0.6544620990753174,
|
2181 |
+
"eval_runtime": 49.3242,
|
2182 |
+
"eval_samples_per_second": 40.548,
|
2183 |
+
"eval_steps_per_second": 2.534,
|
2184 |
+
"step": 6400
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 1.52,
|
2188 |
+
"learning_rate": 0.00014940428911834787,
|
2189 |
+
"loss": 0.6588,
|
2190 |
+
"step": 6420
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 1.52,
|
2194 |
+
"learning_rate": 0.0001489277204130262,
|
2195 |
+
"loss": 0.6609,
|
2196 |
+
"step": 6440
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 1.53,
|
2200 |
+
"learning_rate": 0.00014845115170770452,
|
2201 |
+
"loss": 0.6565,
|
2202 |
+
"step": 6460
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 1.53,
|
2206 |
+
"learning_rate": 0.00014797458300238282,
|
2207 |
+
"loss": 0.6589,
|
2208 |
+
"step": 6480
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.54,
|
2212 |
+
"learning_rate": 0.00014749801429706115,
|
2213 |
+
"loss": 0.6585,
|
2214 |
+
"step": 6500
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 1.54,
|
2218 |
+
"learning_rate": 0.00014702144559173945,
|
2219 |
+
"loss": 0.6737,
|
2220 |
+
"step": 6520
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 1.55,
|
2224 |
+
"learning_rate": 0.00014654487688641778,
|
2225 |
+
"loss": 0.6554,
|
2226 |
+
"step": 6540
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 1.55,
|
2230 |
+
"learning_rate": 0.0001460683081810961,
|
2231 |
+
"loss": 0.6603,
|
2232 |
+
"step": 6560
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 1.56,
|
2236 |
+
"learning_rate": 0.0001455917394757744,
|
2237 |
+
"loss": 0.6647,
|
2238 |
+
"step": 6580
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 1.56,
|
2242 |
+
"learning_rate": 0.00014511517077045273,
|
2243 |
+
"loss": 0.6632,
|
2244 |
+
"step": 6600
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 1.56,
|
2248 |
+
"eval_loss": 0.6527110934257507,
|
2249 |
+
"eval_runtime": 49.2622,
|
2250 |
+
"eval_samples_per_second": 40.599,
|
2251 |
+
"eval_steps_per_second": 2.537,
|
2252 |
+
"step": 6600
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 1.57,
|
2256 |
+
"learning_rate": 0.00014463860206513106,
|
2257 |
+
"loss": 0.6705,
|
2258 |
+
"step": 6620
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 1.57,
|
2262 |
+
"learning_rate": 0.00014416203335980936,
|
2263 |
+
"loss": 0.6703,
|
2264 |
+
"step": 6640
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.57,
|
2268 |
+
"learning_rate": 0.00014368546465448766,
|
2269 |
+
"loss": 0.6602,
|
2270 |
+
"step": 6660
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 1.58,
|
2274 |
+
"learning_rate": 0.000143208895949166,
|
2275 |
+
"loss": 0.6639,
|
2276 |
+
"step": 6680
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 1.58,
|
2280 |
+
"learning_rate": 0.00014273232724384432,
|
2281 |
+
"loss": 0.6645,
|
2282 |
+
"step": 6700
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 1.59,
|
2286 |
+
"learning_rate": 0.00014225575853852262,
|
2287 |
+
"loss": 0.6655,
|
2288 |
+
"step": 6720
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.59,
|
2292 |
+
"learning_rate": 0.00014177918983320094,
|
2293 |
+
"loss": 0.664,
|
2294 |
+
"step": 6740
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 1.6,
|
2298 |
+
"learning_rate": 0.00014130262112787927,
|
2299 |
+
"loss": 0.6656,
|
2300 |
+
"step": 6760
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 1.6,
|
2304 |
+
"learning_rate": 0.00014082605242255757,
|
2305 |
+
"loss": 0.6658,
|
2306 |
+
"step": 6780
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.61,
|
2310 |
+
"learning_rate": 0.0001403494837172359,
|
2311 |
+
"loss": 0.6641,
|
2312 |
+
"step": 6800
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 1.61,
|
2316 |
+
"eval_loss": 0.6513609886169434,
|
2317 |
+
"eval_runtime": 49.4424,
|
2318 |
+
"eval_samples_per_second": 40.451,
|
2319 |
+
"eval_steps_per_second": 2.528,
|
2320 |
+
"step": 6800
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.61,
|
2324 |
+
"learning_rate": 0.0001398729150119142,
|
2325 |
+
"loss": 0.6599,
|
2326 |
+
"step": 6820
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 1.62,
|
2330 |
+
"learning_rate": 0.00013939634630659252,
|
2331 |
+
"loss": 0.6552,
|
2332 |
+
"step": 6840
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 1.62,
|
2336 |
+
"learning_rate": 0.00013891977760127085,
|
2337 |
+
"loss": 0.6616,
|
2338 |
+
"step": 6860
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 1.63,
|
2342 |
+
"learning_rate": 0.00013844320889594915,
|
2343 |
+
"loss": 0.6635,
|
2344 |
+
"step": 6880
|
2345 |
+
},
|
2346 |
+
{
|
2347 |
+
"epoch": 1.63,
|
2348 |
+
"learning_rate": 0.00013796664019062745,
|
2349 |
+
"loss": 0.6608,
|
2350 |
+
"step": 6900
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"epoch": 1.64,
|
2354 |
+
"learning_rate": 0.00013749007148530578,
|
2355 |
+
"loss": 0.6596,
|
2356 |
+
"step": 6920
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 1.64,
|
2360 |
+
"learning_rate": 0.0001370135027799841,
|
2361 |
+
"loss": 0.6589,
|
2362 |
+
"step": 6940
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.65,
|
2366 |
+
"learning_rate": 0.0001365369340746624,
|
2367 |
+
"loss": 0.6627,
|
2368 |
+
"step": 6960
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 1.65,
|
2372 |
+
"learning_rate": 0.00013606036536934073,
|
2373 |
+
"loss": 0.6606,
|
2374 |
+
"step": 6980
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 1.65,
|
2378 |
+
"learning_rate": 0.00013558379666401906,
|
2379 |
+
"loss": 0.6658,
|
2380 |
+
"step": 7000
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 1.65,
|
2384 |
+
"eval_loss": 0.6510519981384277,
|
2385 |
+
"eval_runtime": 49.5012,
|
2386 |
+
"eval_samples_per_second": 40.403,
|
2387 |
+
"eval_steps_per_second": 2.525,
|
2388 |
+
"step": 7000
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 1.66,
|
2392 |
+
"learning_rate": 0.00013510722795869736,
|
2393 |
+
"loss": 0.6571,
|
2394 |
+
"step": 7020
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.66,
|
2398 |
+
"learning_rate": 0.0001346306592533757,
|
2399 |
+
"loss": 0.6607,
|
2400 |
+
"step": 7040
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 1.67,
|
2404 |
+
"learning_rate": 0.000134154090548054,
|
2405 |
+
"loss": 0.6562,
|
2406 |
+
"step": 7060
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 1.67,
|
2410 |
+
"learning_rate": 0.00013367752184273232,
|
2411 |
+
"loss": 0.6582,
|
2412 |
+
"step": 7080
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 1.68,
|
2416 |
+
"learning_rate": 0.00013320095313741064,
|
2417 |
+
"loss": 0.6635,
|
2418 |
+
"step": 7100
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.68,
|
2422 |
+
"learning_rate": 0.00013272438443208894,
|
2423 |
+
"loss": 0.6682,
|
2424 |
+
"step": 7120
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 1.69,
|
2428 |
+
"learning_rate": 0.00013224781572676727,
|
2429 |
+
"loss": 0.6633,
|
2430 |
+
"step": 7140
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 1.69,
|
2434 |
+
"learning_rate": 0.0001317712470214456,
|
2435 |
+
"loss": 0.6671,
|
2436 |
+
"step": 7160
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 1.7,
|
2440 |
+
"learning_rate": 0.0001312946783161239,
|
2441 |
+
"loss": 0.6645,
|
2442 |
+
"step": 7180
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 1.7,
|
2446 |
+
"learning_rate": 0.0001308181096108022,
|
2447 |
+
"loss": 0.6699,
|
2448 |
+
"step": 7200
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 1.7,
|
2452 |
+
"eval_loss": 0.6502068042755127,
|
2453 |
+
"eval_runtime": 49.4619,
|
2454 |
+
"eval_samples_per_second": 40.435,
|
2455 |
+
"eval_steps_per_second": 2.527,
|
2456 |
+
"step": 7200
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 1.71,
|
2460 |
+
"learning_rate": 0.00013034154090548053,
|
2461 |
+
"loss": 0.6617,
|
2462 |
+
"step": 7220
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 1.71,
|
2466 |
+
"learning_rate": 0.00012986497220015885,
|
2467 |
+
"loss": 0.6639,
|
2468 |
+
"step": 7240
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 1.72,
|
2472 |
+
"learning_rate": 0.00012938840349483715,
|
2473 |
+
"loss": 0.6634,
|
2474 |
+
"step": 7260
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.72,
|
2478 |
+
"learning_rate": 0.00012891183478951548,
|
2479 |
+
"loss": 0.663,
|
2480 |
+
"step": 7280
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 1.73,
|
2484 |
+
"learning_rate": 0.00012843526608419378,
|
2485 |
+
"loss": 0.6653,
|
2486 |
+
"step": 7300
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 1.73,
|
2490 |
+
"learning_rate": 0.0001279586973788721,
|
2491 |
+
"loss": 0.6555,
|
2492 |
+
"step": 7320
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 1.74,
|
2496 |
+
"learning_rate": 0.00012748212867355044,
|
2497 |
+
"loss": 0.6653,
|
2498 |
+
"step": 7340
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 1.74,
|
2502 |
+
"learning_rate": 0.00012700555996822874,
|
2503 |
+
"loss": 0.6573,
|
2504 |
+
"step": 7360
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 1.74,
|
2508 |
+
"learning_rate": 0.00012652899126290706,
|
2509 |
+
"loss": 0.658,
|
2510 |
+
"step": 7380
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 1.75,
|
2514 |
+
"learning_rate": 0.0001260524225575854,
|
2515 |
+
"loss": 0.6562,
|
2516 |
+
"step": 7400
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.75,
|
2520 |
+
"eval_loss": 0.6491650342941284,
|
2521 |
+
"eval_runtime": 49.2463,
|
2522 |
+
"eval_samples_per_second": 40.612,
|
2523 |
+
"eval_steps_per_second": 2.538,
|
2524 |
+
"step": 7400
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 1.75,
|
2528 |
+
"learning_rate": 0.0001255758538522637,
|
2529 |
+
"loss": 0.6592,
|
2530 |
+
"step": 7420
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.76,
|
2534 |
+
"learning_rate": 0.000125099285146942,
|
2535 |
+
"loss": 0.6587,
|
2536 |
+
"step": 7440
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 1.76,
|
2540 |
+
"learning_rate": 0.00012462271644162032,
|
2541 |
+
"loss": 0.6616,
|
2542 |
+
"step": 7460
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 1.77,
|
2546 |
+
"learning_rate": 0.00012414614773629865,
|
2547 |
+
"loss": 0.655,
|
2548 |
+
"step": 7480
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 1.77,
|
2552 |
+
"learning_rate": 0.00012366957903097695,
|
2553 |
+
"loss": 0.6591,
|
2554 |
+
"step": 7500
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 1.78,
|
2558 |
+
"learning_rate": 0.00012319301032565527,
|
2559 |
+
"loss": 0.6545,
|
2560 |
+
"step": 7520
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 1.78,
|
2564 |
+
"learning_rate": 0.0001227164416203336,
|
2565 |
+
"loss": 0.6673,
|
2566 |
+
"step": 7540
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 1.79,
|
2570 |
+
"learning_rate": 0.0001222398729150119,
|
2571 |
+
"loss": 0.6626,
|
2572 |
+
"step": 7560
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 1.79,
|
2576 |
+
"learning_rate": 0.00012176330420969023,
|
2577 |
+
"loss": 0.6663,
|
2578 |
+
"step": 7580
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 1.8,
|
2582 |
+
"learning_rate": 0.00012128673550436854,
|
2583 |
+
"loss": 0.6643,
|
2584 |
+
"step": 7600
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 1.8,
|
2588 |
+
"eval_loss": 0.6482685804367065,
|
2589 |
+
"eval_runtime": 49.3591,
|
2590 |
+
"eval_samples_per_second": 40.519,
|
2591 |
+
"eval_steps_per_second": 2.532,
|
2592 |
+
"step": 7600
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 1.8,
|
2596 |
+
"learning_rate": 0.00012081016679904685,
|
2597 |
+
"loss": 0.6623,
|
2598 |
+
"step": 7620
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 1.81,
|
2602 |
+
"learning_rate": 0.00012033359809372518,
|
2603 |
+
"loss": 0.6636,
|
2604 |
+
"step": 7640
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 1.81,
|
2608 |
+
"learning_rate": 0.00011985702938840348,
|
2609 |
+
"loss": 0.6598,
|
2610 |
+
"step": 7660
|
2611 |
+
},
|
2612 |
+
{
|
2613 |
+
"epoch": 1.82,
|
2614 |
+
"learning_rate": 0.0001193804606830818,
|
2615 |
+
"loss": 0.6521,
|
2616 |
+
"step": 7680
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 1.82,
|
2620 |
+
"learning_rate": 0.00011890389197776012,
|
2621 |
+
"loss": 0.664,
|
2622 |
+
"step": 7700
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 1.83,
|
2626 |
+
"learning_rate": 0.00011842732327243844,
|
2627 |
+
"loss": 0.6529,
|
2628 |
+
"step": 7720
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 1.83,
|
2632 |
+
"learning_rate": 0.00011795075456711675,
|
2633 |
+
"loss": 0.6622,
|
2634 |
+
"step": 7740
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 1.83,
|
2638 |
+
"learning_rate": 0.00011747418586179508,
|
2639 |
+
"loss": 0.6608,
|
2640 |
+
"step": 7760
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 1.84,
|
2644 |
+
"learning_rate": 0.00011699761715647338,
|
2645 |
+
"loss": 0.6556,
|
2646 |
+
"step": 7780
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 1.84,
|
2650 |
+
"learning_rate": 0.00011652104845115169,
|
2651 |
+
"loss": 0.6643,
|
2652 |
+
"step": 7800
|
2653 |
+
},
|
2654 |
+
{
|
2655 |
+
"epoch": 1.84,
|
2656 |
+
"eval_loss": 0.6474015116691589,
|
2657 |
+
"eval_runtime": 49.3608,
|
2658 |
+
"eval_samples_per_second": 40.518,
|
2659 |
+
"eval_steps_per_second": 2.532,
|
2660 |
+
"step": 7800
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 1.85,
|
2664 |
+
"learning_rate": 0.00011604447974583002,
|
2665 |
+
"loss": 0.6541,
|
2666 |
+
"step": 7820
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 1.85,
|
2670 |
+
"learning_rate": 0.00011556791104050833,
|
2671 |
+
"loss": 0.6614,
|
2672 |
+
"step": 7840
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 1.86,
|
2676 |
+
"learning_rate": 0.00011509134233518665,
|
2677 |
+
"loss": 0.6499,
|
2678 |
+
"step": 7860
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 1.86,
|
2682 |
+
"learning_rate": 0.00011461477362986497,
|
2683 |
+
"loss": 0.6563,
|
2684 |
+
"step": 7880
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 1.87,
|
2688 |
+
"learning_rate": 0.00011413820492454327,
|
2689 |
+
"loss": 0.6589,
|
2690 |
+
"step": 7900
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 1.87,
|
2694 |
+
"learning_rate": 0.00011366163621922159,
|
2695 |
+
"loss": 0.6544,
|
2696 |
+
"step": 7920
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 1.88,
|
2700 |
+
"learning_rate": 0.00011318506751389992,
|
2701 |
+
"loss": 0.6606,
|
2702 |
+
"step": 7940
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 1.88,
|
2706 |
+
"learning_rate": 0.00011270849880857823,
|
2707 |
+
"loss": 0.657,
|
2708 |
+
"step": 7960
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 1.89,
|
2712 |
+
"learning_rate": 0.00011223193010325654,
|
2713 |
+
"loss": 0.6608,
|
2714 |
+
"step": 7980
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 1.89,
|
2718 |
+
"learning_rate": 0.00011175536139793487,
|
2719 |
+
"loss": 0.6595,
|
2720 |
+
"step": 8000
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 1.89,
|
2724 |
+
"eval_loss": 0.6469079256057739,
|
2725 |
+
"eval_runtime": 49.3012,
|
2726 |
+
"eval_samples_per_second": 40.567,
|
2727 |
+
"eval_steps_per_second": 2.535,
|
2728 |
+
"step": 8000
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 1.9,
|
2732 |
+
"learning_rate": 0.00011127879269261318,
|
2733 |
+
"loss": 0.6563,
|
2734 |
+
"step": 8020
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 1.9,
|
2738 |
+
"learning_rate": 0.00011080222398729148,
|
2739 |
+
"loss": 0.6602,
|
2740 |
+
"step": 8040
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 1.91,
|
2744 |
+
"learning_rate": 0.00011032565528196981,
|
2745 |
+
"loss": 0.6603,
|
2746 |
+
"step": 8060
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 1.91,
|
2750 |
+
"learning_rate": 0.00010984908657664812,
|
2751 |
+
"loss": 0.6495,
|
2752 |
+
"step": 8080
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 1.91,
|
2756 |
+
"learning_rate": 0.00010937251787132644,
|
2757 |
+
"loss": 0.6551,
|
2758 |
+
"step": 8100
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 1.92,
|
2762 |
+
"learning_rate": 0.00010891977760127084,
|
2763 |
+
"loss": 0.6497,
|
2764 |
+
"step": 8120
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 1.92,
|
2768 |
+
"learning_rate": 0.00010844320889594917,
|
2769 |
+
"loss": 0.6652,
|
2770 |
+
"step": 8140
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 1.93,
|
2774 |
+
"learning_rate": 0.00010796664019062747,
|
2775 |
+
"loss": 0.6497,
|
2776 |
+
"step": 8160
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 1.93,
|
2780 |
+
"learning_rate": 0.00010749007148530578,
|
2781 |
+
"loss": 0.6554,
|
2782 |
+
"step": 8180
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 1.94,
|
2786 |
+
"learning_rate": 0.00010701350277998411,
|
2787 |
+
"loss": 0.6563,
|
2788 |
+
"step": 8200
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 1.94,
|
2792 |
+
"eval_loss": 0.645990252494812,
|
2793 |
+
"eval_runtime": 49.3957,
|
2794 |
+
"eval_samples_per_second": 40.489,
|
2795 |
+
"eval_steps_per_second": 2.531,
|
2796 |
+
"step": 8200
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 1.94,
|
2800 |
+
"learning_rate": 0.00010653693407466242,
|
2801 |
+
"loss": 0.6572,
|
2802 |
+
"step": 8220
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 1.95,
|
2806 |
+
"learning_rate": 0.00010606036536934074,
|
2807 |
+
"loss": 0.6563,
|
2808 |
+
"step": 8240
|
2809 |
+
},
|
2810 |
+
{
|
2811 |
+
"epoch": 1.95,
|
2812 |
+
"learning_rate": 0.00010558379666401906,
|
2813 |
+
"loss": 0.6535,
|
2814 |
+
"step": 8260
|
2815 |
+
},
|
2816 |
+
{
|
2817 |
+
"epoch": 1.96,
|
2818 |
+
"learning_rate": 0.00010510722795869736,
|
2819 |
+
"loss": 0.655,
|
2820 |
+
"step": 8280
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 1.96,
|
2824 |
+
"learning_rate": 0.00010463065925337568,
|
2825 |
+
"loss": 0.6554,
|
2826 |
+
"step": 8300
|
2827 |
+
},
|
2828 |
+
{
|
2829 |
+
"epoch": 1.97,
|
2830 |
+
"learning_rate": 0.000104154090548054,
|
2831 |
+
"loss": 0.6559,
|
2832 |
+
"step": 8320
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 1.97,
|
2836 |
+
"learning_rate": 0.00010367752184273232,
|
2837 |
+
"loss": 0.6522,
|
2838 |
+
"step": 8340
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 1.98,
|
2842 |
+
"learning_rate": 0.00010320095313741063,
|
2843 |
+
"loss": 0.6568,
|
2844 |
+
"step": 8360
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 1.98,
|
2848 |
+
"learning_rate": 0.00010272438443208896,
|
2849 |
+
"loss": 0.6566,
|
2850 |
+
"step": 8380
|
2851 |
+
},
|
2852 |
+
{
|
2853 |
+
"epoch": 1.99,
|
2854 |
+
"learning_rate": 0.00010224781572676727,
|
2855 |
+
"loss": 0.6496,
|
2856 |
+
"step": 8400
|
2857 |
+
},
|
2858 |
+
{
|
2859 |
+
"epoch": 1.99,
|
2860 |
+
"eval_loss": 0.6457875967025757,
|
2861 |
+
"eval_runtime": 49.0201,
|
2862 |
+
"eval_samples_per_second": 40.8,
|
2863 |
+
"eval_steps_per_second": 2.55,
|
2864 |
+
"step": 8400
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 1.99,
|
2868 |
+
"learning_rate": 0.00010177124702144557,
|
2869 |
+
"loss": 0.66,
|
2870 |
+
"step": 8420
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 2.0,
|
2874 |
+
"learning_rate": 0.0001012946783161239,
|
2875 |
+
"loss": 0.6457,
|
2876 |
+
"step": 8440
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 2.0,
|
2880 |
+
"learning_rate": 0.0001008419380460683,
|
2881 |
+
"loss": 0.6349,
|
2882 |
+
"step": 8460
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 2.0,
|
2886 |
+
"learning_rate": 0.00010036536934074662,
|
2887 |
+
"loss": 0.6545,
|
2888 |
+
"step": 8480
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 2.01,
|
2892 |
+
"learning_rate": 9.988880063542493e-05,
|
2893 |
+
"loss": 0.6515,
|
2894 |
+
"step": 8500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 2.01,
|
2898 |
+
"learning_rate": 9.941223193010326e-05,
|
2899 |
+
"loss": 0.6459,
|
2900 |
+
"step": 8520
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 2.02,
|
2904 |
+
"learning_rate": 9.893566322478156e-05,
|
2905 |
+
"loss": 0.6494,
|
2906 |
+
"step": 8540
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 2.02,
|
2910 |
+
"learning_rate": 9.845909451945987e-05,
|
2911 |
+
"loss": 0.6608,
|
2912 |
+
"step": 8560
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 2.03,
|
2916 |
+
"learning_rate": 9.79825258141382e-05,
|
2917 |
+
"loss": 0.6485,
|
2918 |
+
"step": 8580
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 2.03,
|
2922 |
+
"learning_rate": 9.750595710881651e-05,
|
2923 |
+
"loss": 0.6461,
|
2924 |
+
"step": 8600
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 2.03,
|
2928 |
+
"eval_loss": 0.6450995802879333,
|
2929 |
+
"eval_runtime": 49.2592,
|
2930 |
+
"eval_samples_per_second": 40.602,
|
2931 |
+
"eval_steps_per_second": 2.538,
|
2932 |
+
"step": 8600
|
2933 |
+
},
|
2934 |
+
{
|
2935 |
+
"epoch": 2.04,
|
2936 |
+
"learning_rate": 9.702938840349483e-05,
|
2937 |
+
"loss": 0.6523,
|
2938 |
+
"step": 8620
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 2.04,
|
2942 |
+
"learning_rate": 9.655281969817315e-05,
|
2943 |
+
"loss": 0.6565,
|
2944 |
+
"step": 8640
|
2945 |
+
},
|
2946 |
+
{
|
2947 |
+
"epoch": 2.05,
|
2948 |
+
"learning_rate": 9.607625099285145e-05,
|
2949 |
+
"loss": 0.6541,
|
2950 |
+
"step": 8660
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 2.05,
|
2954 |
+
"learning_rate": 9.559968228752977e-05,
|
2955 |
+
"loss": 0.6585,
|
2956 |
+
"step": 8680
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 2.06,
|
2960 |
+
"learning_rate": 9.51231135822081e-05,
|
2961 |
+
"loss": 0.6531,
|
2962 |
+
"step": 8700
|
2963 |
+
},
|
2964 |
+
{
|
2965 |
+
"epoch": 2.06,
|
2966 |
+
"learning_rate": 9.464654487688641e-05,
|
2967 |
+
"loss": 0.6579,
|
2968 |
+
"step": 8720
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 2.07,
|
2972 |
+
"learning_rate": 9.416997617156472e-05,
|
2973 |
+
"loss": 0.6438,
|
2974 |
+
"step": 8740
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 2.07,
|
2978 |
+
"learning_rate": 9.369340746624305e-05,
|
2979 |
+
"loss": 0.6516,
|
2980 |
+
"step": 8760
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 2.08,
|
2984 |
+
"learning_rate": 9.321683876092136e-05,
|
2985 |
+
"loss": 0.6576,
|
2986 |
+
"step": 8780
|
2987 |
+
},
|
2988 |
+
{
|
2989 |
+
"epoch": 2.08,
|
2990 |
+
"learning_rate": 9.274027005559966e-05,
|
2991 |
+
"loss": 0.6506,
|
2992 |
+
"step": 8800
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 2.08,
|
2996 |
+
"eval_loss": 0.6444578170776367,
|
2997 |
+
"eval_runtime": 49.0631,
|
2998 |
+
"eval_samples_per_second": 40.764,
|
2999 |
+
"eval_steps_per_second": 2.548,
|
3000 |
+
"step": 8800
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 2.09,
|
3004 |
+
"learning_rate": 9.226370135027799e-05,
|
3005 |
+
"loss": 0.6484,
|
3006 |
+
"step": 8820
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 2.09,
|
3010 |
+
"learning_rate": 9.17871326449563e-05,
|
3011 |
+
"loss": 0.6566,
|
3012 |
+
"step": 8840
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 2.09,
|
3016 |
+
"learning_rate": 9.131056393963462e-05,
|
3017 |
+
"loss": 0.6547,
|
3018 |
+
"step": 8860
|
3019 |
+
},
|
3020 |
+
{
|
3021 |
+
"epoch": 2.1,
|
3022 |
+
"learning_rate": 9.083399523431295e-05,
|
3023 |
+
"loss": 0.6532,
|
3024 |
+
"step": 8880
|
3025 |
+
},
|
3026 |
+
{
|
3027 |
+
"epoch": 2.1,
|
3028 |
+
"learning_rate": 9.035742652899126e-05,
|
3029 |
+
"loss": 0.6532,
|
3030 |
+
"step": 8900
|
3031 |
+
},
|
3032 |
+
{
|
3033 |
+
"epoch": 2.11,
|
3034 |
+
"learning_rate": 8.988085782366956e-05,
|
3035 |
+
"loss": 0.6479,
|
3036 |
+
"step": 8920
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 2.11,
|
3040 |
+
"learning_rate": 8.940428911834789e-05,
|
3041 |
+
"loss": 0.6548,
|
3042 |
+
"step": 8940
|
3043 |
+
},
|
3044 |
+
{
|
3045 |
+
"epoch": 2.12,
|
3046 |
+
"learning_rate": 8.89277204130262e-05,
|
3047 |
+
"loss": 0.647,
|
3048 |
+
"step": 8960
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 2.12,
|
3052 |
+
"learning_rate": 8.845115170770452e-05,
|
3053 |
+
"loss": 0.6478,
|
3054 |
+
"step": 8980
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 2.13,
|
3058 |
+
"learning_rate": 8.797458300238284e-05,
|
3059 |
+
"loss": 0.6553,
|
3060 |
+
"step": 9000
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 2.13,
|
3064 |
+
"eval_loss": 0.6433074474334717,
|
3065 |
+
"eval_runtime": 49.3831,
|
3066 |
+
"eval_samples_per_second": 40.5,
|
3067 |
+
"eval_steps_per_second": 2.531,
|
3068 |
+
"step": 9000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 2.13,
|
3072 |
+
"learning_rate": 8.749801429706116e-05,
|
3073 |
+
"loss": 0.6443,
|
3074 |
+
"step": 9020
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 2.14,
|
3078 |
+
"learning_rate": 8.702144559173947e-05,
|
3079 |
+
"loss": 0.6518,
|
3080 |
+
"step": 9040
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 2.14,
|
3084 |
+
"learning_rate": 8.65448768864178e-05,
|
3085 |
+
"loss": 0.6578,
|
3086 |
+
"step": 9060
|
3087 |
+
},
|
3088 |
+
{
|
3089 |
+
"epoch": 2.15,
|
3090 |
+
"learning_rate": 8.60683081810961e-05,
|
3091 |
+
"loss": 0.6472,
|
3092 |
+
"step": 9080
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 2.15,
|
3096 |
+
"learning_rate": 8.559173947577441e-05,
|
3097 |
+
"loss": 0.6471,
|
3098 |
+
"step": 9100
|
3099 |
+
},
|
3100 |
+
{
|
3101 |
+
"epoch": 2.16,
|
3102 |
+
"learning_rate": 8.511517077045274e-05,
|
3103 |
+
"loss": 0.6482,
|
3104 |
+
"step": 9120
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 2.16,
|
3108 |
+
"learning_rate": 8.463860206513105e-05,
|
3109 |
+
"loss": 0.6522,
|
3110 |
+
"step": 9140
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 2.17,
|
3114 |
+
"learning_rate": 8.416203335980937e-05,
|
3115 |
+
"loss": 0.6584,
|
3116 |
+
"step": 9160
|
3117 |
+
},
|
3118 |
+
{
|
3119 |
+
"epoch": 2.17,
|
3120 |
+
"learning_rate": 8.368546465448769e-05,
|
3121 |
+
"loss": 0.6596,
|
3122 |
+
"step": 9180
|
3123 |
+
},
|
3124 |
+
{
|
3125 |
+
"epoch": 2.17,
|
3126 |
+
"learning_rate": 8.320889594916599e-05,
|
3127 |
+
"loss": 0.6581,
|
3128 |
+
"step": 9200
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 2.17,
|
3132 |
+
"eval_loss": 0.6426697969436646,
|
3133 |
+
"eval_runtime": 49.0935,
|
3134 |
+
"eval_samples_per_second": 40.739,
|
3135 |
+
"eval_steps_per_second": 2.546,
|
3136 |
+
"step": 9200
|
3137 |
+
},
|
3138 |
+
{
|
3139 |
+
"epoch": 2.18,
|
3140 |
+
"learning_rate": 8.273232724384431e-05,
|
3141 |
+
"loss": 0.6441,
|
3142 |
+
"step": 9220
|
3143 |
+
},
|
3144 |
+
{
|
3145 |
+
"epoch": 2.18,
|
3146 |
+
"learning_rate": 8.225575853852263e-05,
|
3147 |
+
"loss": 0.6509,
|
3148 |
+
"step": 9240
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 2.19,
|
3152 |
+
"learning_rate": 8.177918983320095e-05,
|
3153 |
+
"loss": 0.6409,
|
3154 |
+
"step": 9260
|
3155 |
+
},
|
3156 |
+
{
|
3157 |
+
"epoch": 2.19,
|
3158 |
+
"learning_rate": 8.130262112787926e-05,
|
3159 |
+
"loss": 0.6475,
|
3160 |
+
"step": 9280
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 2.2,
|
3164 |
+
"learning_rate": 8.082605242255759e-05,
|
3165 |
+
"loss": 0.6597,
|
3166 |
+
"step": 9300
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 2.2,
|
3170 |
+
"learning_rate": 8.03494837172359e-05,
|
3171 |
+
"loss": 0.6544,
|
3172 |
+
"step": 9320
|
3173 |
+
},
|
3174 |
+
{
|
3175 |
+
"epoch": 2.21,
|
3176 |
+
"learning_rate": 7.98729150119142e-05,
|
3177 |
+
"loss": 0.6528,
|
3178 |
+
"step": 9340
|
3179 |
+
},
|
3180 |
+
{
|
3181 |
+
"epoch": 2.21,
|
3182 |
+
"learning_rate": 7.939634630659253e-05,
|
3183 |
+
"loss": 0.644,
|
3184 |
+
"step": 9360
|
3185 |
+
},
|
3186 |
+
{
|
3187 |
+
"epoch": 2.22,
|
3188 |
+
"learning_rate": 7.891977760127084e-05,
|
3189 |
+
"loss": 0.6552,
|
3190 |
+
"step": 9380
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 2.22,
|
3194 |
+
"learning_rate": 7.844320889594916e-05,
|
3195 |
+
"loss": 0.6548,
|
3196 |
+
"step": 9400
|
3197 |
+
},
|
3198 |
+
{
|
3199 |
+
"epoch": 2.22,
|
3200 |
+
"eval_loss": 0.6423606276512146,
|
3201 |
+
"eval_runtime": 49.6466,
|
3202 |
+
"eval_samples_per_second": 40.285,
|
3203 |
+
"eval_steps_per_second": 2.518,
|
3204 |
+
"step": 9400
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 2.23,
|
3208 |
+
"learning_rate": 7.796664019062748e-05,
|
3209 |
+
"loss": 0.6568,
|
3210 |
+
"step": 9420
|
3211 |
+
},
|
3212 |
+
{
|
3213 |
+
"epoch": 2.23,
|
3214 |
+
"learning_rate": 7.74900714853058e-05,
|
3215 |
+
"loss": 0.6539,
|
3216 |
+
"step": 9440
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 2.24,
|
3220 |
+
"learning_rate": 7.70135027799841e-05,
|
3221 |
+
"loss": 0.6468,
|
3222 |
+
"step": 9460
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 2.24,
|
3226 |
+
"learning_rate": 7.653693407466243e-05,
|
3227 |
+
"loss": 0.6425,
|
3228 |
+
"step": 9480
|
3229 |
+
},
|
3230 |
+
{
|
3231 |
+
"epoch": 2.25,
|
3232 |
+
"learning_rate": 7.606036536934074e-05,
|
3233 |
+
"loss": 0.6523,
|
3234 |
+
"step": 9500
|
3235 |
+
},
|
3236 |
+
{
|
3237 |
+
"epoch": 2.25,
|
3238 |
+
"learning_rate": 7.558379666401905e-05,
|
3239 |
+
"loss": 0.6468,
|
3240 |
+
"step": 9520
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 2.26,
|
3244 |
+
"learning_rate": 7.510722795869738e-05,
|
3245 |
+
"loss": 0.6518,
|
3246 |
+
"step": 9540
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 2.26,
|
3250 |
+
"learning_rate": 7.46306592533757e-05,
|
3251 |
+
"loss": 0.6534,
|
3252 |
+
"step": 9560
|
3253 |
+
},
|
3254 |
+
{
|
3255 |
+
"epoch": 2.26,
|
3256 |
+
"learning_rate": 7.415409054805401e-05,
|
3257 |
+
"loss": 0.6471,
|
3258 |
+
"step": 9580
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 2.27,
|
3262 |
+
"learning_rate": 7.367752184273232e-05,
|
3263 |
+
"loss": 0.6465,
|
3264 |
+
"step": 9600
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 2.27,
|
3268 |
+
"eval_loss": 0.6418060064315796,
|
3269 |
+
"eval_runtime": 49.4954,
|
3270 |
+
"eval_samples_per_second": 40.408,
|
3271 |
+
"eval_steps_per_second": 2.525,
|
3272 |
+
"step": 9600
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 2.27,
|
3276 |
+
"learning_rate": 7.320095313741064e-05,
|
3277 |
+
"loss": 0.6577,
|
3278 |
+
"step": 9620
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 2.28,
|
3282 |
+
"learning_rate": 7.272438443208895e-05,
|
3283 |
+
"loss": 0.6453,
|
3284 |
+
"step": 9640
|
3285 |
+
},
|
3286 |
+
{
|
3287 |
+
"epoch": 2.28,
|
3288 |
+
"learning_rate": 7.224781572676726e-05,
|
3289 |
+
"loss": 0.6489,
|
3290 |
+
"step": 9660
|
3291 |
+
},
|
3292 |
+
{
|
3293 |
+
"epoch": 2.29,
|
3294 |
+
"learning_rate": 7.177124702144559e-05,
|
3295 |
+
"loss": 0.6466,
|
3296 |
+
"step": 9680
|
3297 |
+
},
|
3298 |
+
{
|
3299 |
+
"epoch": 2.29,
|
3300 |
+
"learning_rate": 7.12946783161239e-05,
|
3301 |
+
"loss": 0.6493,
|
3302 |
+
"step": 9700
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 2.3,
|
3306 |
+
"learning_rate": 7.081810961080222e-05,
|
3307 |
+
"loss": 0.6537,
|
3308 |
+
"step": 9720
|
3309 |
+
},
|
3310 |
+
{
|
3311 |
+
"epoch": 2.3,
|
3312 |
+
"learning_rate": 7.034154090548053e-05,
|
3313 |
+
"loss": 0.6486,
|
3314 |
+
"step": 9740
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 2.31,
|
3318 |
+
"learning_rate": 6.986497220015885e-05,
|
3319 |
+
"loss": 0.65,
|
3320 |
+
"step": 9760
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 2.31,
|
3324 |
+
"learning_rate": 6.938840349483717e-05,
|
3325 |
+
"loss": 0.6387,
|
3326 |
+
"step": 9780
|
3327 |
+
},
|
3328 |
+
{
|
3329 |
+
"epoch": 2.32,
|
3330 |
+
"learning_rate": 6.891183478951549e-05,
|
3331 |
+
"loss": 0.6464,
|
3332 |
+
"step": 9800
|
3333 |
+
},
|
3334 |
+
{
|
3335 |
+
"epoch": 2.32,
|
3336 |
+
"eval_loss": 0.6412256360054016,
|
3337 |
+
"eval_runtime": 49.3752,
|
3338 |
+
"eval_samples_per_second": 40.506,
|
3339 |
+
"eval_steps_per_second": 2.532,
|
3340 |
+
"step": 9800
|
3341 |
+
},
|
3342 |
+
{
|
3343 |
+
"epoch": 2.32,
|
3344 |
+
"learning_rate": 6.84352660841938e-05,
|
3345 |
+
"loss": 0.6475,
|
3346 |
+
"step": 9820
|
3347 |
+
},
|
3348 |
+
{
|
3349 |
+
"epoch": 2.33,
|
3350 |
+
"learning_rate": 6.795869737887211e-05,
|
3351 |
+
"loss": 0.6543,
|
3352 |
+
"step": 9840
|
3353 |
+
},
|
3354 |
+
{
|
3355 |
+
"epoch": 2.33,
|
3356 |
+
"learning_rate": 6.748212867355043e-05,
|
3357 |
+
"loss": 0.6545,
|
3358 |
+
"step": 9860
|
3359 |
+
},
|
3360 |
+
{
|
3361 |
+
"epoch": 2.34,
|
3362 |
+
"learning_rate": 6.700555996822874e-05,
|
3363 |
+
"loss": 0.6468,
|
3364 |
+
"step": 9880
|
3365 |
+
},
|
3366 |
+
{
|
3367 |
+
"epoch": 2.34,
|
3368 |
+
"learning_rate": 6.652899126290707e-05,
|
3369 |
+
"loss": 0.651,
|
3370 |
+
"step": 9900
|
3371 |
+
},
|
3372 |
+
{
|
3373 |
+
"epoch": 2.35,
|
3374 |
+
"learning_rate": 6.605242255758538e-05,
|
3375 |
+
"loss": 0.641,
|
3376 |
+
"step": 9920
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 2.35,
|
3380 |
+
"learning_rate": 6.55758538522637e-05,
|
3381 |
+
"loss": 0.657,
|
3382 |
+
"step": 9940
|
3383 |
+
},
|
3384 |
+
{
|
3385 |
+
"epoch": 2.35,
|
3386 |
+
"learning_rate": 6.509928514694201e-05,
|
3387 |
+
"loss": 0.6481,
|
3388 |
+
"step": 9960
|
3389 |
+
},
|
3390 |
+
{
|
3391 |
+
"epoch": 2.36,
|
3392 |
+
"learning_rate": 6.462271644162034e-05,
|
3393 |
+
"loss": 0.6496,
|
3394 |
+
"step": 9980
|
3395 |
+
},
|
3396 |
+
{
|
3397 |
+
"epoch": 2.36,
|
3398 |
+
"learning_rate": 6.414614773629864e-05,
|
3399 |
+
"loss": 0.6451,
|
3400 |
+
"step": 10000
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 2.36,
|
3404 |
+
"eval_loss": 0.6414454579353333,
|
3405 |
+
"eval_runtime": 49.395,
|
3406 |
+
"eval_samples_per_second": 40.49,
|
3407 |
+
"eval_steps_per_second": 2.531,
|
3408 |
+
"step": 10000
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 2.37,
|
3412 |
+
"learning_rate": 6.366957903097696e-05,
|
3413 |
+
"loss": 0.6555,
|
3414 |
+
"step": 10020
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 2.37,
|
3418 |
+
"learning_rate": 6.319301032565528e-05,
|
3419 |
+
"loss": 0.6494,
|
3420 |
+
"step": 10040
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 2.38,
|
3424 |
+
"learning_rate": 6.271644162033359e-05,
|
3425 |
+
"loss": 0.6487,
|
3426 |
+
"step": 10060
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 2.38,
|
3430 |
+
"learning_rate": 6.22398729150119e-05,
|
3431 |
+
"loss": 0.6544,
|
3432 |
+
"step": 10080
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 2.39,
|
3436 |
+
"learning_rate": 6.176330420969023e-05,
|
3437 |
+
"loss": 0.6468,
|
3438 |
+
"step": 10100
|
3439 |
+
},
|
3440 |
+
{
|
3441 |
+
"epoch": 2.39,
|
3442 |
+
"learning_rate": 6.128673550436853e-05,
|
3443 |
+
"loss": 0.6441,
|
3444 |
+
"step": 10120
|
3445 |
+
},
|
3446 |
+
{
|
3447 |
+
"epoch": 2.4,
|
3448 |
+
"learning_rate": 6.081016679904686e-05,
|
3449 |
+
"loss": 0.6478,
|
3450 |
+
"step": 10140
|
3451 |
+
},
|
3452 |
+
{
|
3453 |
+
"epoch": 2.4,
|
3454 |
+
"learning_rate": 6.033359809372518e-05,
|
3455 |
+
"loss": 0.6539,
|
3456 |
+
"step": 10160
|
3457 |
+
},
|
3458 |
+
{
|
3459 |
+
"epoch": 2.41,
|
3460 |
+
"learning_rate": 5.985702938840349e-05,
|
3461 |
+
"loss": 0.6486,
|
3462 |
+
"step": 10180
|
3463 |
+
},
|
3464 |
+
{
|
3465 |
+
"epoch": 2.41,
|
3466 |
+
"learning_rate": 5.938046068308181e-05,
|
3467 |
+
"loss": 0.6467,
|
3468 |
+
"step": 10200
|
3469 |
+
},
|
3470 |
+
{
|
3471 |
+
"epoch": 2.41,
|
3472 |
+
"eval_loss": 0.6406835913658142,
|
3473 |
+
"eval_runtime": 49.5084,
|
3474 |
+
"eval_samples_per_second": 40.397,
|
3475 |
+
"eval_steps_per_second": 2.525,
|
3476 |
+
"step": 10200
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 2.42,
|
3480 |
+
"learning_rate": 5.890389197776013e-05,
|
3481 |
+
"loss": 0.6399,
|
3482 |
+
"step": 10220
|
3483 |
+
},
|
3484 |
+
{
|
3485 |
+
"epoch": 2.42,
|
3486 |
+
"learning_rate": 5.8427323272438435e-05,
|
3487 |
+
"loss": 0.6519,
|
3488 |
+
"step": 10240
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 2.43,
|
3492 |
+
"learning_rate": 5.7950754567116756e-05,
|
3493 |
+
"loss": 0.6465,
|
3494 |
+
"step": 10260
|
3495 |
+
},
|
3496 |
+
{
|
3497 |
+
"epoch": 2.43,
|
3498 |
+
"learning_rate": 5.7474185861795076e-05,
|
3499 |
+
"loss": 0.6479,
|
3500 |
+
"step": 10280
|
3501 |
+
},
|
3502 |
+
{
|
3503 |
+
"epoch": 2.43,
|
3504 |
+
"learning_rate": 5.6997617156473383e-05,
|
3505 |
+
"loss": 0.6462,
|
3506 |
+
"step": 10300
|
3507 |
+
},
|
3508 |
+
{
|
3509 |
+
"epoch": 2.44,
|
3510 |
+
"learning_rate": 5.6521048451151704e-05,
|
3511 |
+
"loss": 0.6451,
|
3512 |
+
"step": 10320
|
3513 |
+
},
|
3514 |
+
{
|
3515 |
+
"epoch": 2.44,
|
3516 |
+
"learning_rate": 5.604447974583002e-05,
|
3517 |
+
"loss": 0.6453,
|
3518 |
+
"step": 10340
|
3519 |
+
},
|
3520 |
+
{
|
3521 |
+
"epoch": 2.45,
|
3522 |
+
"learning_rate": 5.556791104050833e-05,
|
3523 |
+
"loss": 0.6543,
|
3524 |
+
"step": 10360
|
3525 |
+
},
|
3526 |
+
{
|
3527 |
+
"epoch": 2.45,
|
3528 |
+
"learning_rate": 5.509134233518665e-05,
|
3529 |
+
"loss": 0.6428,
|
3530 |
+
"step": 10380
|
3531 |
+
},
|
3532 |
+
{
|
3533 |
+
"epoch": 2.46,
|
3534 |
+
"learning_rate": 5.4614773629864966e-05,
|
3535 |
+
"loss": 0.6491,
|
3536 |
+
"step": 10400
|
3537 |
+
},
|
3538 |
+
{
|
3539 |
+
"epoch": 2.46,
|
3540 |
+
"eval_loss": 0.6400973796844482,
|
3541 |
+
"eval_runtime": 49.3411,
|
3542 |
+
"eval_samples_per_second": 40.534,
|
3543 |
+
"eval_steps_per_second": 2.533,
|
3544 |
+
"step": 10400
|
3545 |
+
},
|
3546 |
+
{
|
3547 |
+
"epoch": 2.46,
|
3548 |
+
"learning_rate": 5.413820492454328e-05,
|
3549 |
+
"loss": 0.649,
|
3550 |
+
"step": 10420
|
3551 |
+
},
|
3552 |
+
{
|
3553 |
+
"epoch": 2.47,
|
3554 |
+
"learning_rate": 5.36616362192216e-05,
|
3555 |
+
"loss": 0.6494,
|
3556 |
+
"step": 10440
|
3557 |
+
},
|
3558 |
+
{
|
3559 |
+
"epoch": 2.47,
|
3560 |
+
"learning_rate": 5.3185067513899913e-05,
|
3561 |
+
"loss": 0.6431,
|
3562 |
+
"step": 10460
|
3563 |
+
},
|
3564 |
+
{
|
3565 |
+
"epoch": 2.48,
|
3566 |
+
"learning_rate": 5.2708498808578234e-05,
|
3567 |
+
"loss": 0.6478,
|
3568 |
+
"step": 10480
|
3569 |
+
},
|
3570 |
+
{
|
3571 |
+
"epoch": 2.48,
|
3572 |
+
"learning_rate": 5.223193010325655e-05,
|
3573 |
+
"loss": 0.6416,
|
3574 |
+
"step": 10500
|
3575 |
+
},
|
3576 |
+
{
|
3577 |
+
"epoch": 2.49,
|
3578 |
+
"learning_rate": 5.175536139793486e-05,
|
3579 |
+
"loss": 0.6507,
|
3580 |
+
"step": 10520
|
3581 |
+
},
|
3582 |
+
{
|
3583 |
+
"epoch": 2.49,
|
3584 |
+
"learning_rate": 5.127879269261318e-05,
|
3585 |
+
"loss": 0.6448,
|
3586 |
+
"step": 10540
|
3587 |
+
},
|
3588 |
+
{
|
3589 |
+
"epoch": 2.5,
|
3590 |
+
"learning_rate": 5.0802223987291496e-05,
|
3591 |
+
"loss": 0.6455,
|
3592 |
+
"step": 10560
|
3593 |
+
},
|
3594 |
+
{
|
3595 |
+
"epoch": 2.5,
|
3596 |
+
"learning_rate": 5.032565528196981e-05,
|
3597 |
+
"loss": 0.6437,
|
3598 |
+
"step": 10580
|
3599 |
+
},
|
3600 |
+
{
|
3601 |
+
"epoch": 2.51,
|
3602 |
+
"learning_rate": 4.984908657664813e-05,
|
3603 |
+
"loss": 0.6488,
|
3604 |
+
"step": 10600
|
3605 |
+
},
|
3606 |
+
{
|
3607 |
+
"epoch": 2.51,
|
3608 |
+
"eval_loss": 0.6400858163833618,
|
3609 |
+
"eval_runtime": 49.8084,
|
3610 |
+
"eval_samples_per_second": 40.154,
|
3611 |
+
"eval_steps_per_second": 2.51,
|
3612 |
+
"step": 10600
|
3613 |
+
},
|
3614 |
+
{
|
3615 |
+
"epoch": 2.51,
|
3616 |
+
"learning_rate": 4.937251787132645e-05,
|
3617 |
+
"loss": 0.6436,
|
3618 |
+
"step": 10620
|
3619 |
+
},
|
3620 |
+
{
|
3621 |
+
"epoch": 2.52,
|
3622 |
+
"learning_rate": 4.889594916600476e-05,
|
3623 |
+
"loss": 0.6446,
|
3624 |
+
"step": 10640
|
3625 |
+
},
|
3626 |
+
{
|
3627 |
+
"epoch": 2.52,
|
3628 |
+
"learning_rate": 4.841938046068308e-05,
|
3629 |
+
"loss": 0.6488,
|
3630 |
+
"step": 10660
|
3631 |
+
},
|
3632 |
+
{
|
3633 |
+
"epoch": 2.52,
|
3634 |
+
"learning_rate": 4.79428117553614e-05,
|
3635 |
+
"loss": 0.6485,
|
3636 |
+
"step": 10680
|
3637 |
+
},
|
3638 |
+
{
|
3639 |
+
"epoch": 2.53,
|
3640 |
+
"learning_rate": 4.7466243050039705e-05,
|
3641 |
+
"loss": 0.6524,
|
3642 |
+
"step": 10700
|
3643 |
+
},
|
3644 |
+
{
|
3645 |
+
"epoch": 2.53,
|
3646 |
+
"learning_rate": 4.6989674344718026e-05,
|
3647 |
+
"loss": 0.6376,
|
3648 |
+
"step": 10720
|
3649 |
+
},
|
3650 |
+
{
|
3651 |
+
"epoch": 2.54,
|
3652 |
+
"learning_rate": 4.6513105639396346e-05,
|
3653 |
+
"loss": 0.649,
|
3654 |
+
"step": 10740
|
3655 |
+
},
|
3656 |
+
{
|
3657 |
+
"epoch": 2.54,
|
3658 |
+
"learning_rate": 4.603653693407465e-05,
|
3659 |
+
"loss": 0.6444,
|
3660 |
+
"step": 10760
|
3661 |
+
},
|
3662 |
+
{
|
3663 |
+
"epoch": 2.55,
|
3664 |
+
"learning_rate": 4.5559968228752974e-05,
|
3665 |
+
"loss": 0.6407,
|
3666 |
+
"step": 10780
|
3667 |
+
},
|
3668 |
+
{
|
3669 |
+
"epoch": 2.55,
|
3670 |
+
"learning_rate": 4.5083399523431294e-05,
|
3671 |
+
"loss": 0.6448,
|
3672 |
+
"step": 10800
|
3673 |
+
},
|
3674 |
+
{
|
3675 |
+
"epoch": 2.55,
|
3676 |
+
"eval_loss": 0.6392157077789307,
|
3677 |
+
"eval_runtime": 49.7963,
|
3678 |
+
"eval_samples_per_second": 40.164,
|
3679 |
+
"eval_steps_per_second": 2.51,
|
3680 |
+
"step": 10800
|
3681 |
+
},
|
3682 |
+
{
|
3683 |
+
"epoch": 2.56,
|
3684 |
+
"learning_rate": 4.46068308181096e-05,
|
3685 |
+
"loss": 0.6454,
|
3686 |
+
"step": 10820
|
3687 |
+
},
|
3688 |
+
{
|
3689 |
+
"epoch": 2.56,
|
3690 |
+
"learning_rate": 4.413026211278792e-05,
|
3691 |
+
"loss": 0.6544,
|
3692 |
+
"step": 10840
|
3693 |
+
},
|
3694 |
+
{
|
3695 |
+
"epoch": 2.57,
|
3696 |
+
"learning_rate": 4.365369340746624e-05,
|
3697 |
+
"loss": 0.6478,
|
3698 |
+
"step": 10860
|
3699 |
+
},
|
3700 |
+
{
|
3701 |
+
"epoch": 2.57,
|
3702 |
+
"learning_rate": 4.3177124702144556e-05,
|
3703 |
+
"loss": 0.6434,
|
3704 |
+
"step": 10880
|
3705 |
+
},
|
3706 |
+
{
|
3707 |
+
"epoch": 2.58,
|
3708 |
+
"learning_rate": 4.270055599682287e-05,
|
3709 |
+
"loss": 0.6482,
|
3710 |
+
"step": 10900
|
3711 |
+
},
|
3712 |
+
{
|
3713 |
+
"epoch": 2.58,
|
3714 |
+
"learning_rate": 4.222398729150119e-05,
|
3715 |
+
"loss": 0.6403,
|
3716 |
+
"step": 10920
|
3717 |
+
},
|
3718 |
+
{
|
3719 |
+
"epoch": 2.59,
|
3720 |
+
"learning_rate": 4.1747418586179504e-05,
|
3721 |
+
"loss": 0.6501,
|
3722 |
+
"step": 10940
|
3723 |
+
},
|
3724 |
+
{
|
3725 |
+
"epoch": 2.59,
|
3726 |
+
"learning_rate": 4.127084988085782e-05,
|
3727 |
+
"loss": 0.6507,
|
3728 |
+
"step": 10960
|
3729 |
+
},
|
3730 |
+
{
|
3731 |
+
"epoch": 2.6,
|
3732 |
+
"learning_rate": 4.079428117553614e-05,
|
3733 |
+
"loss": 0.6496,
|
3734 |
+
"step": 10980
|
3735 |
+
},
|
3736 |
+
{
|
3737 |
+
"epoch": 2.6,
|
3738 |
+
"learning_rate": 4.031771247021445e-05,
|
3739 |
+
"loss": 0.6544,
|
3740 |
+
"step": 11000
|
3741 |
+
},
|
3742 |
+
{
|
3743 |
+
"epoch": 2.6,
|
3744 |
+
"eval_loss": 0.6390016078948975,
|
3745 |
+
"eval_runtime": 49.6306,
|
3746 |
+
"eval_samples_per_second": 40.298,
|
3747 |
+
"eval_steps_per_second": 2.519,
|
3748 |
+
"step": 11000
|
3749 |
+
},
|
3750 |
+
{
|
3751 |
+
"epoch": 2.61,
|
3752 |
+
"learning_rate": 3.984114376489277e-05,
|
3753 |
+
"loss": 0.6405,
|
3754 |
+
"step": 11020
|
3755 |
+
},
|
3756 |
+
{
|
3757 |
+
"epoch": 2.61,
|
3758 |
+
"learning_rate": 3.9364575059571086e-05,
|
3759 |
+
"loss": 0.6429,
|
3760 |
+
"step": 11040
|
3761 |
+
},
|
3762 |
+
{
|
3763 |
+
"epoch": 2.61,
|
3764 |
+
"learning_rate": 3.88880063542494e-05,
|
3765 |
+
"loss": 0.6403,
|
3766 |
+
"step": 11060
|
3767 |
+
},
|
3768 |
+
{
|
3769 |
+
"epoch": 2.62,
|
3770 |
+
"learning_rate": 3.841143764892772e-05,
|
3771 |
+
"loss": 0.6338,
|
3772 |
+
"step": 11080
|
3773 |
+
},
|
3774 |
+
{
|
3775 |
+
"epoch": 2.62,
|
3776 |
+
"learning_rate": 3.7934868943606034e-05,
|
3777 |
+
"loss": 0.6417,
|
3778 |
+
"step": 11100
|
3779 |
+
},
|
3780 |
+
{
|
3781 |
+
"epoch": 2.63,
|
3782 |
+
"learning_rate": 3.7458300238284354e-05,
|
3783 |
+
"loss": 0.6463,
|
3784 |
+
"step": 11120
|
3785 |
+
},
|
3786 |
+
{
|
3787 |
+
"epoch": 2.63,
|
3788 |
+
"learning_rate": 3.698173153296267e-05,
|
3789 |
+
"loss": 0.6498,
|
3790 |
+
"step": 11140
|
3791 |
+
},
|
3792 |
+
{
|
3793 |
+
"epoch": 2.64,
|
3794 |
+
"learning_rate": 3.650516282764098e-05,
|
3795 |
+
"loss": 0.6415,
|
3796 |
+
"step": 11160
|
3797 |
+
},
|
3798 |
+
{
|
3799 |
+
"epoch": 2.64,
|
3800 |
+
"learning_rate": 3.6028594122319296e-05,
|
3801 |
+
"loss": 0.645,
|
3802 |
+
"step": 11180
|
3803 |
+
},
|
3804 |
+
{
|
3805 |
+
"epoch": 2.65,
|
3806 |
+
"learning_rate": 3.5552025416997616e-05,
|
3807 |
+
"loss": 0.6467,
|
3808 |
+
"step": 11200
|
3809 |
+
},
|
3810 |
+
{
|
3811 |
+
"epoch": 2.65,
|
3812 |
+
"eval_loss": 0.6387213468551636,
|
3813 |
+
"eval_runtime": 49.1775,
|
3814 |
+
"eval_samples_per_second": 40.669,
|
3815 |
+
"eval_steps_per_second": 2.542,
|
3816 |
+
"step": 11200
|
3817 |
+
},
|
3818 |
+
{
|
3819 |
+
"epoch": 2.65,
|
3820 |
+
"learning_rate": 3.507545671167593e-05,
|
3821 |
+
"loss": 0.6515,
|
3822 |
+
"step": 11220
|
3823 |
+
},
|
3824 |
+
{
|
3825 |
+
"epoch": 2.66,
|
3826 |
+
"learning_rate": 3.4598888006354244e-05,
|
3827 |
+
"loss": 0.65,
|
3828 |
+
"step": 11240
|
3829 |
+
},
|
3830 |
+
{
|
3831 |
+
"epoch": 2.66,
|
3832 |
+
"learning_rate": 3.4122319301032564e-05,
|
3833 |
+
"loss": 0.6512,
|
3834 |
+
"step": 11260
|
3835 |
+
},
|
3836 |
+
{
|
3837 |
+
"epoch": 2.67,
|
3838 |
+
"learning_rate": 3.364575059571088e-05,
|
3839 |
+
"loss": 0.6443,
|
3840 |
+
"step": 11280
|
3841 |
+
},
|
3842 |
+
{
|
3843 |
+
"epoch": 2.67,
|
3844 |
+
"learning_rate": 3.316918189038919e-05,
|
3845 |
+
"loss": 0.6483,
|
3846 |
+
"step": 11300
|
3847 |
+
},
|
3848 |
+
{
|
3849 |
+
"epoch": 2.68,
|
3850 |
+
"learning_rate": 3.269261318506751e-05,
|
3851 |
+
"loss": 0.6455,
|
3852 |
+
"step": 11320
|
3853 |
+
},
|
3854 |
+
{
|
3855 |
+
"epoch": 2.68,
|
3856 |
+
"learning_rate": 3.2216044479745826e-05,
|
3857 |
+
"loss": 0.6461,
|
3858 |
+
"step": 11340
|
3859 |
+
},
|
3860 |
+
{
|
3861 |
+
"epoch": 2.69,
|
3862 |
+
"learning_rate": 3.173947577442414e-05,
|
3863 |
+
"loss": 0.6505,
|
3864 |
+
"step": 11360
|
3865 |
+
},
|
3866 |
+
{
|
3867 |
+
"epoch": 2.69,
|
3868 |
+
"learning_rate": 3.126290706910246e-05,
|
3869 |
+
"loss": 0.6517,
|
3870 |
+
"step": 11380
|
3871 |
+
},
|
3872 |
+
{
|
3873 |
+
"epoch": 2.7,
|
3874 |
+
"learning_rate": 3.0786338363780774e-05,
|
3875 |
+
"loss": 0.6406,
|
3876 |
+
"step": 11400
|
3877 |
+
},
|
3878 |
+
{
|
3879 |
+
"epoch": 2.7,
|
3880 |
+
"eval_loss": 0.6380326151847839,
|
3881 |
+
"eval_runtime": 49.4129,
|
3882 |
+
"eval_samples_per_second": 40.475,
|
3883 |
+
"eval_steps_per_second": 2.53,
|
3884 |
+
"step": 11400
|
3885 |
+
},
|
3886 |
+
{
|
3887 |
+
"epoch": 2.7,
|
3888 |
+
"learning_rate": 3.030976965845909e-05,
|
3889 |
+
"loss": 0.647,
|
3890 |
+
"step": 11420
|
3891 |
+
},
|
3892 |
+
{
|
3893 |
+
"epoch": 2.7,
|
3894 |
+
"learning_rate": 2.9833200953137408e-05,
|
3895 |
+
"loss": 0.6495,
|
3896 |
+
"step": 11440
|
3897 |
+
},
|
3898 |
+
{
|
3899 |
+
"epoch": 2.71,
|
3900 |
+
"learning_rate": 2.9356632247815725e-05,
|
3901 |
+
"loss": 0.6448,
|
3902 |
+
"step": 11460
|
3903 |
+
},
|
3904 |
+
{
|
3905 |
+
"epoch": 2.71,
|
3906 |
+
"learning_rate": 2.888006354249404e-05,
|
3907 |
+
"loss": 0.6447,
|
3908 |
+
"step": 11480
|
3909 |
+
},
|
3910 |
+
{
|
3911 |
+
"epoch": 2.72,
|
3912 |
+
"learning_rate": 2.840349483717236e-05,
|
3913 |
+
"loss": 0.6527,
|
3914 |
+
"step": 11500
|
3915 |
+
},
|
3916 |
+
{
|
3917 |
+
"epoch": 2.72,
|
3918 |
+
"learning_rate": 2.7926926131850673e-05,
|
3919 |
+
"loss": 0.6406,
|
3920 |
+
"step": 11520
|
3921 |
+
},
|
3922 |
+
{
|
3923 |
+
"epoch": 2.73,
|
3924 |
+
"learning_rate": 2.7450357426528987e-05,
|
3925 |
+
"loss": 0.6443,
|
3926 |
+
"step": 11540
|
3927 |
+
},
|
3928 |
+
{
|
3929 |
+
"epoch": 2.73,
|
3930 |
+
"learning_rate": 2.6973788721207307e-05,
|
3931 |
+
"loss": 0.6351,
|
3932 |
+
"step": 11560
|
3933 |
+
},
|
3934 |
+
{
|
3935 |
+
"epoch": 2.74,
|
3936 |
+
"learning_rate": 2.649722001588562e-05,
|
3937 |
+
"loss": 0.6417,
|
3938 |
+
"step": 11580
|
3939 |
+
},
|
3940 |
+
{
|
3941 |
+
"epoch": 2.74,
|
3942 |
+
"learning_rate": 2.6020651310563938e-05,
|
3943 |
+
"loss": 0.6356,
|
3944 |
+
"step": 11600
|
3945 |
+
},
|
3946 |
+
{
|
3947 |
+
"epoch": 2.74,
|
3948 |
+
"eval_loss": 0.6381237506866455,
|
3949 |
+
"eval_runtime": 49.5534,
|
3950 |
+
"eval_samples_per_second": 40.36,
|
3951 |
+
"eval_steps_per_second": 2.523,
|
3952 |
+
"step": 11600
|
3953 |
+
},
|
3954 |
+
{
|
3955 |
+
"epoch": 2.75,
|
3956 |
+
"learning_rate": 2.5544082605242255e-05,
|
3957 |
+
"loss": 0.6412,
|
3958 |
+
"step": 11620
|
3959 |
+
},
|
3960 |
+
{
|
3961 |
+
"epoch": 2.75,
|
3962 |
+
"learning_rate": 2.506751389992057e-05,
|
3963 |
+
"loss": 0.6418,
|
3964 |
+
"step": 11640
|
3965 |
+
},
|
3966 |
+
{
|
3967 |
+
"epoch": 2.76,
|
3968 |
+
"learning_rate": 2.4590945194598886e-05,
|
3969 |
+
"loss": 0.6426,
|
3970 |
+
"step": 11660
|
3971 |
+
},
|
3972 |
+
{
|
3973 |
+
"epoch": 2.76,
|
3974 |
+
"learning_rate": 2.4114376489277203e-05,
|
3975 |
+
"loss": 0.6461,
|
3976 |
+
"step": 11680
|
3977 |
+
},
|
3978 |
+
{
|
3979 |
+
"epoch": 2.77,
|
3980 |
+
"learning_rate": 2.363780778395552e-05,
|
3981 |
+
"loss": 0.6475,
|
3982 |
+
"step": 11700
|
3983 |
+
},
|
3984 |
+
{
|
3985 |
+
"epoch": 2.77,
|
3986 |
+
"learning_rate": 2.3161239078633834e-05,
|
3987 |
+
"loss": 0.6431,
|
3988 |
+
"step": 11720
|
3989 |
+
},
|
3990 |
+
{
|
3991 |
+
"epoch": 2.78,
|
3992 |
+
"learning_rate": 2.2684670373312148e-05,
|
3993 |
+
"loss": 0.6416,
|
3994 |
+
"step": 11740
|
3995 |
+
},
|
3996 |
+
{
|
3997 |
+
"epoch": 2.78,
|
3998 |
+
"learning_rate": 2.2208101667990468e-05,
|
3999 |
+
"loss": 0.6495,
|
4000 |
+
"step": 11760
|
4001 |
+
},
|
4002 |
+
{
|
4003 |
+
"epoch": 2.78,
|
4004 |
+
"learning_rate": 2.1731532962668782e-05,
|
4005 |
+
"loss": 0.6404,
|
4006 |
+
"step": 11780
|
4007 |
+
},
|
4008 |
+
{
|
4009 |
+
"epoch": 2.79,
|
4010 |
+
"learning_rate": 2.1254964257347096e-05,
|
4011 |
+
"loss": 0.6434,
|
4012 |
+
"step": 11800
|
4013 |
+
},
|
4014 |
+
{
|
4015 |
+
"epoch": 2.79,
|
4016 |
+
"eval_loss": 0.6377163529396057,
|
4017 |
+
"eval_runtime": 49.328,
|
4018 |
+
"eval_samples_per_second": 40.545,
|
4019 |
+
"eval_steps_per_second": 2.534,
|
4020 |
+
"step": 11800
|
4021 |
+
},
|
4022 |
+
{
|
4023 |
+
"epoch": 2.79,
|
4024 |
+
"learning_rate": 2.0778395552025416e-05,
|
4025 |
+
"loss": 0.6437,
|
4026 |
+
"step": 11820
|
4027 |
+
},
|
4028 |
+
{
|
4029 |
+
"epoch": 2.8,
|
4030 |
+
"learning_rate": 2.030182684670373e-05,
|
4031 |
+
"loss": 0.6393,
|
4032 |
+
"step": 11840
|
4033 |
+
},
|
4034 |
+
{
|
4035 |
+
"epoch": 2.8,
|
4036 |
+
"learning_rate": 1.9825258141382047e-05,
|
4037 |
+
"loss": 0.6412,
|
4038 |
+
"step": 11860
|
4039 |
+
},
|
4040 |
+
{
|
4041 |
+
"epoch": 2.81,
|
4042 |
+
"learning_rate": 1.9348689436060364e-05,
|
4043 |
+
"loss": 0.6494,
|
4044 |
+
"step": 11880
|
4045 |
+
},
|
4046 |
+
{
|
4047 |
+
"epoch": 2.81,
|
4048 |
+
"learning_rate": 1.887212073073868e-05,
|
4049 |
+
"loss": 0.6481,
|
4050 |
+
"step": 11900
|
4051 |
+
},
|
4052 |
+
{
|
4053 |
+
"epoch": 2.82,
|
4054 |
+
"learning_rate": 1.8395552025416998e-05,
|
4055 |
+
"loss": 0.6407,
|
4056 |
+
"step": 11920
|
4057 |
+
},
|
4058 |
+
{
|
4059 |
+
"epoch": 2.82,
|
4060 |
+
"learning_rate": 1.7918983320095312e-05,
|
4061 |
+
"loss": 0.6422,
|
4062 |
+
"step": 11940
|
4063 |
+
},
|
4064 |
+
{
|
4065 |
+
"epoch": 2.83,
|
4066 |
+
"learning_rate": 1.744241461477363e-05,
|
4067 |
+
"loss": 0.6487,
|
4068 |
+
"step": 11960
|
4069 |
+
},
|
4070 |
+
{
|
4071 |
+
"epoch": 2.83,
|
4072 |
+
"learning_rate": 1.6965845909451946e-05,
|
4073 |
+
"loss": 0.6478,
|
4074 |
+
"step": 11980
|
4075 |
+
},
|
4076 |
+
{
|
4077 |
+
"epoch": 2.84,
|
4078 |
+
"learning_rate": 1.648927720413026e-05,
|
4079 |
+
"loss": 0.6451,
|
4080 |
+
"step": 12000
|
4081 |
+
},
|
4082 |
+
{
|
4083 |
+
"epoch": 2.84,
|
4084 |
+
"eval_loss": 0.6374698281288147,
|
4085 |
+
"eval_runtime": 49.9107,
|
4086 |
+
"eval_samples_per_second": 40.072,
|
4087 |
+
"eval_steps_per_second": 2.504,
|
4088 |
+
"step": 12000
|
4089 |
+
},
|
4090 |
+
{
|
4091 |
+
"epoch": 2.84,
|
4092 |
+
"learning_rate": 1.6012708498808577e-05,
|
4093 |
+
"loss": 0.6454,
|
4094 |
+
"step": 12020
|
4095 |
+
},
|
4096 |
+
{
|
4097 |
+
"epoch": 2.85,
|
4098 |
+
"learning_rate": 1.5536139793486894e-05,
|
4099 |
+
"loss": 0.6399,
|
4100 |
+
"step": 12040
|
4101 |
+
},
|
4102 |
+
{
|
4103 |
+
"epoch": 2.85,
|
4104 |
+
"learning_rate": 1.5059571088165208e-05,
|
4105 |
+
"loss": 0.6479,
|
4106 |
+
"step": 12060
|
4107 |
+
},
|
4108 |
+
{
|
4109 |
+
"epoch": 2.86,
|
4110 |
+
"learning_rate": 1.4583002382843525e-05,
|
4111 |
+
"loss": 0.6412,
|
4112 |
+
"step": 12080
|
4113 |
+
},
|
4114 |
+
{
|
4115 |
+
"epoch": 2.86,
|
4116 |
+
"learning_rate": 1.4106433677521842e-05,
|
4117 |
+
"loss": 0.65,
|
4118 |
+
"step": 12100
|
4119 |
+
},
|
4120 |
+
{
|
4121 |
+
"epoch": 2.87,
|
4122 |
+
"learning_rate": 1.3629864972200157e-05,
|
4123 |
+
"loss": 0.6461,
|
4124 |
+
"step": 12120
|
4125 |
+
},
|
4126 |
+
{
|
4127 |
+
"epoch": 2.87,
|
4128 |
+
"learning_rate": 1.3153296266878475e-05,
|
4129 |
+
"loss": 0.6434,
|
4130 |
+
"step": 12140
|
4131 |
+
},
|
4132 |
+
{
|
4133 |
+
"epoch": 2.87,
|
4134 |
+
"learning_rate": 1.2676727561556788e-05,
|
4135 |
+
"loss": 0.6463,
|
4136 |
+
"step": 12160
|
4137 |
+
},
|
4138 |
+
{
|
4139 |
+
"epoch": 2.88,
|
4140 |
+
"learning_rate": 1.2200158856235105e-05,
|
4141 |
+
"loss": 0.6399,
|
4142 |
+
"step": 12180
|
4143 |
+
},
|
4144 |
+
{
|
4145 |
+
"epoch": 2.88,
|
4146 |
+
"learning_rate": 1.1723590150913422e-05,
|
4147 |
+
"loss": 0.6446,
|
4148 |
+
"step": 12200
|
4149 |
+
},
|
4150 |
+
{
|
4151 |
+
"epoch": 2.88,
|
4152 |
+
"eval_loss": 0.6372544765472412,
|
4153 |
+
"eval_runtime": 49.6265,
|
4154 |
+
"eval_samples_per_second": 40.301,
|
4155 |
+
"eval_steps_per_second": 2.519,
|
4156 |
+
"step": 12200
|
4157 |
+
},
|
4158 |
+
{
|
4159 |
+
"epoch": 2.89,
|
4160 |
+
"learning_rate": 1.1247021445591738e-05,
|
4161 |
+
"loss": 0.6411,
|
4162 |
+
"step": 12220
|
4163 |
+
},
|
4164 |
+
{
|
4165 |
+
"epoch": 2.89,
|
4166 |
+
"learning_rate": 1.0770452740270055e-05,
|
4167 |
+
"loss": 0.6523,
|
4168 |
+
"step": 12240
|
4169 |
+
},
|
4170 |
+
{
|
4171 |
+
"epoch": 2.9,
|
4172 |
+
"learning_rate": 1.0293884034948372e-05,
|
4173 |
+
"loss": 0.6456,
|
4174 |
+
"step": 12260
|
4175 |
+
},
|
4176 |
+
{
|
4177 |
+
"epoch": 2.9,
|
4178 |
+
"learning_rate": 9.817315329626686e-06,
|
4179 |
+
"loss": 0.6394,
|
4180 |
+
"step": 12280
|
4181 |
+
},
|
4182 |
+
{
|
4183 |
+
"epoch": 2.91,
|
4184 |
+
"learning_rate": 9.340746624305003e-06,
|
4185 |
+
"loss": 0.6466,
|
4186 |
+
"step": 12300
|
4187 |
+
},
|
4188 |
+
{
|
4189 |
+
"epoch": 2.91,
|
4190 |
+
"learning_rate": 8.864177918983318e-06,
|
4191 |
+
"loss": 0.6415,
|
4192 |
+
"step": 12320
|
4193 |
+
},
|
4194 |
+
{
|
4195 |
+
"epoch": 2.92,
|
4196 |
+
"learning_rate": 8.387609213661635e-06,
|
4197 |
+
"loss": 0.6349,
|
4198 |
+
"step": 12340
|
4199 |
+
},
|
4200 |
+
{
|
4201 |
+
"epoch": 2.92,
|
4202 |
+
"learning_rate": 7.911040508339953e-06,
|
4203 |
+
"loss": 0.6415,
|
4204 |
+
"step": 12360
|
4205 |
+
},
|
4206 |
+
{
|
4207 |
+
"epoch": 2.93,
|
4208 |
+
"learning_rate": 7.434471803018268e-06,
|
4209 |
+
"loss": 0.6484,
|
4210 |
+
"step": 12380
|
4211 |
+
},
|
4212 |
+
{
|
4213 |
+
"epoch": 2.93,
|
4214 |
+
"learning_rate": 6.957903097696583e-06,
|
4215 |
+
"loss": 0.6522,
|
4216 |
+
"step": 12400
|
4217 |
+
},
|
4218 |
+
{
|
4219 |
+
"epoch": 2.93,
|
4220 |
+
"eval_loss": 0.6368712186813354,
|
4221 |
+
"eval_runtime": 49.0693,
|
4222 |
+
"eval_samples_per_second": 40.759,
|
4223 |
+
"eval_steps_per_second": 2.547,
|
4224 |
+
"step": 12400
|
4225 |
+
},
|
4226 |
+
{
|
4227 |
+
"epoch": 2.94,
|
4228 |
+
"learning_rate": 6.4813343923749005e-06,
|
4229 |
+
"loss": 0.643,
|
4230 |
+
"step": 12420
|
4231 |
+
},
|
4232 |
+
{
|
4233 |
+
"epoch": 2.94,
|
4234 |
+
"learning_rate": 6.004765687053216e-06,
|
4235 |
+
"loss": 0.6515,
|
4236 |
+
"step": 12440
|
4237 |
+
},
|
4238 |
+
{
|
4239 |
+
"epoch": 2.95,
|
4240 |
+
"learning_rate": 5.528196981731532e-06,
|
4241 |
+
"loss": 0.6512,
|
4242 |
+
"step": 12460
|
4243 |
+
},
|
4244 |
+
{
|
4245 |
+
"epoch": 2.95,
|
4246 |
+
"learning_rate": 5.051628276409849e-06,
|
4247 |
+
"loss": 0.6483,
|
4248 |
+
"step": 12480
|
4249 |
+
},
|
4250 |
+
{
|
4251 |
+
"epoch": 2.96,
|
4252 |
+
"learning_rate": 4.575059571088165e-06,
|
4253 |
+
"loss": 0.6342,
|
4254 |
+
"step": 12500
|
4255 |
+
},
|
4256 |
+
{
|
4257 |
+
"epoch": 2.96,
|
4258 |
+
"learning_rate": 4.098490865766481e-06,
|
4259 |
+
"loss": 0.6445,
|
4260 |
+
"step": 12520
|
4261 |
+
},
|
4262 |
+
{
|
4263 |
+
"epoch": 2.96,
|
4264 |
+
"learning_rate": 3.6219221604447972e-06,
|
4265 |
+
"loss": 0.6419,
|
4266 |
+
"step": 12540
|
4267 |
+
},
|
4268 |
+
{
|
4269 |
+
"epoch": 2.97,
|
4270 |
+
"learning_rate": 3.145353455123113e-06,
|
4271 |
+
"loss": 0.642,
|
4272 |
+
"step": 12560
|
4273 |
+
},
|
4274 |
+
{
|
4275 |
+
"epoch": 2.97,
|
4276 |
+
"learning_rate": 2.6687847498014293e-06,
|
4277 |
+
"loss": 0.6541,
|
4278 |
+
"step": 12580
|
4279 |
+
},
|
4280 |
+
{
|
4281 |
+
"epoch": 2.98,
|
4282 |
+
"learning_rate": 2.1922160444797456e-06,
|
4283 |
+
"loss": 0.6334,
|
4284 |
+
"step": 12600
|
4285 |
+
},
|
4286 |
+
{
|
4287 |
+
"epoch": 2.98,
|
4288 |
+
"eval_loss": 0.636846125125885,
|
4289 |
+
"eval_runtime": 49.1332,
|
4290 |
+
"eval_samples_per_second": 40.706,
|
4291 |
+
"eval_steps_per_second": 2.544,
|
4292 |
+
"step": 12600
|
4293 |
+
}
|
4294 |
+
],
|
4295 |
+
"max_steps": 12690,
|
4296 |
+
"num_train_epochs": 3,
|
4297 |
+
"total_flos": 1.6375945250008465e+19,
|
4298 |
+
"trial_name": null,
|
4299 |
+
"trial_params": null
|
4300 |
+
}
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/checkpoint-12600/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a070370e87c048b60fc888b8736a0166eb94eeb3a75f5f78918edab715d0fb1c
|
3 |
+
size 3579
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-35-50_autodl-container-a629119d3c-e4df2c26/1679643354.1908646/events.out.tfevents.1679643354.autodl-container-a629119d3c-e4df2c26.49450.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:477b50c5556946ba35aa59cfb080f2a1bd4cac9e4a43341795e805da0cb424a6
|
3 |
+
size 5809
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-35-50_autodl-container-a629119d3c-e4df2c26/events.out.tfevents.1679643354.autodl-container-a629119d3c-e4df2c26.49450.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4957dd8c37c2b3f2c2b15760d760ef448dcefee8854fc3a61e4c52f7534aa406
|
3 |
+
size 3824
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-45-35_autodl-container-a629119d3c-e4df2c26/1679643935.915997/events.out.tfevents.1679643935.autodl-container-a629119d3c-e4df2c26.51017.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76cc90b5b36269f261f73b916664154bf922abeb27a09f26454bb838f0eb2025
|
3 |
+
size 5809
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-0.5m/runs/Mar24_15-45-35_autodl-container-a629119d3c-e4df2c26/events.out.tfevents.1679643935.autodl-container-a629119d3c-e4df2c26.51017.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b7d32319c70ab9cd6397d6b0232d2623e3f4d4a8f70cb92200eb2b7e70054f2
|
3 |
+
size 120771
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/adapter_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "/root/autodl-tmp/llama_hf",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"lora_alpha": 16,
|
8 |
+
"lora_dropout": 0.05,
|
9 |
+
"merge_weights": false,
|
10 |
+
"modules_to_save": null,
|
11 |
+
"peft_type": "LORA",
|
12 |
+
"r": 8,
|
13 |
+
"target_modules": [
|
14 |
+
"q_proj",
|
15 |
+
"v_proj"
|
16 |
+
],
|
17 |
+
"task_type": "CAUSAL_LM"
|
18 |
+
}
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a3b43e50220a5244e4f3cdf199c4a63673c716a9ff2d013c0bb1ac7f7c8d916
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a1e464507a0eb6d65330833b5e6a2f0222aa6a42dc1b421a82bc6b179f11d7
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62816331a190d7783fed48f4fe5472a7cf8d37afe2179e5a1f8f0a8168b1dc96
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbf4148eed691c08b2b9f0a833d08075b124d9054abbfc2f5e7747c2ce5c051f
|
3 |
+
size 14575
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e7309791e544e8cb732592406919407855bab183563e2fcbaad5f6249d386dd
|
3 |
+
size 557
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3bbb8e74ed1b7ca44a8f95d5cdb8d457c0318daf33eba316ef6fde8a11ee92c
|
3 |
+
size 627
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53d327ea9f712be818d41a24603cd835992a4e9e3612a85caf2415ab699d6a50
|
3 |
+
size 3579
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c200bd8422cf044a90c223c0d176459a14cf9687f0e41a37cfe2ab3b8d6a67
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4dcdffef65339b11ffc55279a0ad63ce04e3c09e7247c7f54d1a6bc29d6fff2
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52704287125685e13be49c11d3c17bf338c00ed9fdbcdd6972348fc8e6b6dc29
|
3 |
+
size 14575
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d7c2e69e5b3f7cb43530e1cc8336651f8c7f2d08e0e496d6eb190f9cd9c465b
|
3 |
+
size 557
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3630575f35c6cb2516d6d68a466f2304033a5a8ec817a07f3f5722bbb0a874c2
|
3 |
+
size 627
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53d327ea9f712be818d41a24603cd835992a4e9e3612a85caf2415ab699d6a50
|
3 |
+
size 3579
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcc458a10fe82dcee9e9432f212482eba7f9f47f4dbb32c60e5694dcb32c4700
|
3 |
+
size 33629893
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfeed223c297fd668bb441bed81e81acc8a3a709064382564a31530dc6cf16ad
|
3 |
+
size 16822989
|
alpaca-lora-based-origin-llama7b/lora-alpaca-cn-remote-1M/checkpoint-15400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b8e5f28f76ff581dd7c3383f28cad3b8c2550aa95227479150b8b3923f20b65
|
3 |
+
size 14575
|